feat(config): Run the fans at full speed by default

FAN_SPEED 30 -> 100. A soak is a thermal test of everything except the
cooling, so the cooling should not be one of the variables in it. At 30%
a long run can throttle partway through, and throttled results read like
a different fault entirely.

Folded into V1.0.11 rather than bumping the version: the tag has not
moved on and this is the same delivery.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014RetWKFZFG1ZHcitQAyhwM

.gitattributes

@@ -0,0 +1,29 @@
+# =============================================================================
+# 換行符政策
+# -----------------------------------------------------------------------------
+# 這個 repo 同時被 Windows（Tera Term 端編輯）與 SONiC/Linux（DUT 端執行）使用，
+# 所以必須明確指定，不能靠各機器的 core.autocrlf。
+#
+# 踩過的坑：margin.sh 帶著 CRLF 進 repo，scp 到 DUT 後 bash 直接掛：
+#     -bash: $'\r': command not found
+#     syntax error near unexpected token `$'{\r''
+# settings/*.conf 同樣危險 —— margin_init 是用 source 讀它們的，未加引號的
+# 賦值（例如 CB_I2C_CH=6）會變成 "6\r"，SWB transport 會拿著壞掉的通道號去打 I2C。
+# =============================================================================
+
+# 在 DUT / Linux 上執行或被 source 的，一律 LF
+*.sh    text eol=lf
+*.conf  text eol=lf
+*.py    text eol=lf
+*.txt   text eol=lf
+*.md    text eol=lf
+
+# Tera Term macro 只在 Windows 上跑，維持 CRLF；標成 -text 讓 git 原樣保存，
+# 避免對既有檔案產生大量純換行符的假 diff
+*.ttl   -text
+
+# 二進位，不要做任何轉換
+*.xlsx  binary
+*.docx  binary
+*.pdf   binary
+*.h5    binary

.gitignore

@@ -12,9 +12,15 @@ For_AI/
 !**/logs/.gitkeep
 !**/Logs/.gitkeep
 
-# 打包輸出
+# monitor 腳本的執行期產物（原始擷取、pid、狀態）
+*.raw
+*.pid
+*.state
+
+# 打包輸出：產出不進 git，打包工具本身要進
 publish/*
 !publish/.gitkeep
+!publish/publish.sh
 
 # Office 暫存檔
 ~$*

ARCHITECTURE.md

@@ -37,7 +37,13 @@ LTC2980 margin 控制器。TTL 只負責「按順序 `sendln` 並把畫面收進
 | 電源 margin | LTC2980（= 2 × LTC2977）over PMBus，LINEAR16 編碼 |
 | 錯誤計數來源 | Linux PCIe AER sysfs（`aer_dev_*`）、EDAC sysfs（`dimm_ce/ue_count`） |
 | 平台監控 | SONiC `show platform *`（pmon container，含 `leak status` / `leak channels`） |
-| 壓力測試 | `mlucas-avx2`（AMD CPU）、`~/hammer/tools/stress_{mem,ssd,usb}.py` |
+| BMC 存取 | host 端 `bmc-manager run "<cmd>"`（不需對 BMC 開 SSH，繞開其 busybox 工具鏈）；`bmc-first-enroll` / `bmc-manager version\|status` |
+| 背景工作管理 | `bgctl run/list/stop --all/reset`（平台工具）；長時間 ping 用 `systemd-run --unit=` 掛成 transient unit |
+| 管理網路 | iproute2（`ip link set` / `ip address replace` / `ip route replace ... metric`）+ `ping -I` |
+| 測試 session | `hw-test-session start\|log\|status\|finish`；job log 收在 `/host/hw-eval/jobs/` |
+| 風扇控制 | max31790 driver rebind（`/sys/bus/i2c/drivers/max31790/{bind,unbind}`）+ `fan-speed-control.sh <%>` |
+| 100G PRBS | `bcmcmd -n <unit> -c 'dsh -c "phy diag <phy> prbs …"'`（set / prbsstat STArt / get / Ber / STOp / clear） |
+| 壓力測試 | `mlucas-avx2`（AMD CPU）、`bgctl run` 排程的 `memtester` / `qfx5252-stress-ssd` / `qfx5252-stress-usb` |
 | 資料面流量 | `bcmcmd`（Broadcom drivshell）VLAN loopback + `tx` burst，switch unit 0 / 1 |
 | 流量報表 | DUT 上 awk（`blanton_traffic_linespeed report`）；離線 `python3 tools/bcm_mibpair_report_V1.1.0.py` |
 | 版本控制 | Git（NAS + Gitea 私有 remote；**不推 GitHub，含客戶 NDA 資料**） |
@@ -106,13 +112,15 @@ Blanton_TTL_Script/
 │
 ├── CLAUDE.md                          # 專案記憶 & 給 Claude 的指令
 ├── ARCHITECTURE.md                    # 本架構文件
-├── .gitignore                         # secret/ + For_AI/ + logs 規則
+├── .gitignore                         # secret/ + For_AI/ + logs + publish 產出
+├── .gitattributes                     # 換行符政策：.sh/.conf 釘 LF、.ttl 保持 CRLF
 │
 ├── docs/                              # 規格與狀態文件（客戶提供 / 專案產出）
 │   ├── Blantons_FPGA_Registers.md         # FPGA 暫存器規格（markdown 正本，查 offset 用）
 │   ├── Blantons_FPGA_Registers_draft.docx # 同上，客戶原始 docx
 │   ├── Blantons_FPGA_Registers_Map_draft.xlsx
 │   ├── Blantons_PCIe_AER_and_DDR_EDAC_checks.pdf  # AER / EDAC 檢查點依據
+│   ├── LTC2980_channel_map.csv            # 9 個 settings/*.conf 合併：Board,CONN,Ch,NetName,Vnom（144 列）
 │   ├── TTL_Script_Blanton_Status_20260814.xlsx
 │   └── TTL_Script_Blanton_Status_20260817.xlsx    # ⭐ 最新：三支腳本逐項 Status（OK / On-Going + Owner）
 │
@@ -120,9 +128,13 @@ Blanton_TTL_Script/
 │   ├── bcm_mibpair_report_V1.1.0.py       # 離線解析 drivshell log → per-pair TX/RX + PASS/FAIL
 │   ├── traffic_loopback_vlan_setting.txt  # bcmcmd VLAN 30..137 建立 + 成對 pbm（cdN <-> cdN+32）
 │   ├── traffic_loopback_start.txt         # bcmcmd tx 100 length=512 VLantag=<vid>
-│   └── traffic_loopback_vlan_remove.txt   # bcmcmd vlan remove <vid> pbm=...
+│   ├── traffic_loopback_vlan_remove.txt   # bcmcmd vlan remove <vid> pbm=...
-│                                          # ↑ 三份為手動貼上用的原始指令表，
+│   │                                      # ↑ 三份為手動貼上用的原始指令表，
-│                                          #   blanton_traffic_linespeed.sh 是其 bash 版
+│   │                                      #   blanton_traffic_linespeed.sh 是其 bash 版
+│   ├── 100G_PRBS.txt                      # 100G PRBS 原始指令（port_prbs_monitor.sh 的來源）
+│   ├── TR518.txt                          # 內建封包測試 tr 518（Scenario=6 Profile=2）— 尚未腳本化
+│   ├── fan_ctrl.txt                       # MAX31790 unbind/bind + fan-speed-control.sh 30
+│   └── gen_channel_map.sh                 # settings/*.conf → docs/LTC2980_channel_map.csv（需 gawk）
 │
 ├── secret/                            # 🚫 gitignored — DUT 密碼、per-unit BDF、COM 設定
 │   ├── README.md                      # ✅ committed — 用途索引
@@ -131,7 +143,9 @@ Blanton_TTL_Script/
 │
 ├── For_AI/                            # 🚫 gitignored — AI 協作素材（波形截圖、草稿）
 │
-├── publish/                           # 可交付的打包輸出（Blanton_Script_ABC_v<ver>_<date>/ + zip）
+├── publish/
+│   ├── publish.sh                     # ✅ committed — 打包工具（版號讀 Script A 檔頭）
+│   └── Script_ABC_Blanton_<Ver>/      # 🚫 產出，gitignored（-z 另出同名 .zip）
 │
 └── src/
     └── Script_ABC_Blanton/            # ← Tera Term 的工作目錄（整包給測試員）
@@ -144,10 +158,11 @@ Blanton_TTL_Script/
         ├── utils/                     # 可 include 的取數片段（TTL，無狀態、只 wait+sendln）
         │   ├── pcie_bus.ttl               # lspci -tvvv / -vv
         │   ├── setup_pmon.ttl             # show platform summary/fan/temperature/psustatus/voltage/
-        │   │                              #   current/ssdhealth/leak status/leak channels（9 項）
+        │   │                              #   current/ssdhealth/leak status/leak channels + TPM（11 項）
-        │   ├── show_dmesg.ttl             # date + dmesg grep error/fail/warning
+        │   ├── show_dmesg.ttl             # dmesg -T 合併 error 正則 + i2c 過濾 + dmesg -C 清空
         │   ├── show_margin_status.ttl     # source margin_status_all.sh（掃 9 顆 LTC2980）
         │   ├── kill_all_process.ttl       # kill $(jobs -p)
+        │   ├── wait_init.ttl              # 輪詢 show platform temperature 直到 pmon 起來
         │   ├── show_pcie_error_reg.ttl        # 舊的合併版（已被下列 per-device 版取代）
         │   ├── show_pcie_error_reg_TH6_SWB0.ttl   # EP 01:00.0 + RP 00:01.1
         │   ├── show_pcie_error_reg_TH6_SWB1.ttl   # EP 02:00.0 + RP 00:01.2
@@ -167,12 +182,24 @@ Blanton_TTL_Script/
             ├── blanton_pwr_data.sh        # SWB VRM + PDB brick 的 Vin/Vout/Iout/Temp 表
             ├── blanton_traffic_linespeed.sh  # SWB loopback 線速流量（bcmcmd unit 0/1）
             │                                 #   init/clear/show/start/stop/ps/report/run
+            ├── mgmt_ping_monitor.sh       # 10G/1G 管理網路 ping 監控（iproute2）
+            │                              #   eth0→TARGET_10G、eth1→TARGET_1G，兩張卡同時持續 ping
+            ├── port_prbs_monitor.sh       # 100G uplink PRBS 測試（bcmcmd phy diag）
+            │                              #   ⚠️ 已納入交付，但 A/B/C 的呼叫仍註解掉（bring-up 中）
+            ├── usb_target.sh              # 偵測 USB 裝置節點／掛載點（排除系統碟）
+            ├── bmc_monitor.sh             # BMC 監控：free -m + I2C 寫入/讀回圖樣測試
+            ├── bmc_monitor_ddr.sh         # ⚠️ 已停用：B/C 內呼叫處已註解，DDR 壓力改走 bgctl + bmc-manager
+            │                              #   ↑ 三支都要 chmod +x 才能跑（見 Key Constraints）
             └── LTC2980_Margin_Script/     # 電壓 margin 子專案（另有獨立 repo）
                 ├── margin.sh              # margin_init/status/set/apply_profile/save
+                #                            #   v2.7.0：margin_save all / margin_save blanton
                 ├── settings/*.conf        # 一個 .conf = 一顆 LTC2980（CB + SWB0/1 × CONN13~16）
                 ├── profiles/*.conf        # 16-ch 批次組合（comboA/B、high3/5、low3/5、normal、off）
                 ├── script/*_all.sh        # 跨 9 顆 LTC2980 的批次 status / apply / save
+                ├── Ref/margin_command_trace.md  # 指令追蹤參考（SWB 章節已標過期，見文件內警告）
                 └── logs/                  # margin 操作 log
+                #  註：v2.6.0 起不再內含 blanton_cb_i2c.sh / blanton_fpga_pcimem.sh 的複本，
+                #      改由 _swb_find_backend 往上層 Blanton_Script/ 找共用版
 ```
 
 ---
@@ -184,15 +211,20 @@ Blanton_TTL_Script/
 ### 1. `config.ttl` — 全域測試參數（TTL 變數）
 
 ```ini
-strTestcase   = "Margin"        ; 測項名，進 log 檔名
 project_name  = "Blanton"       ; 專案名，進 log 檔名
-EN_Margin     = 1               ; 1=跑 margin 掃描, 0=跳過
+strTestcase   = "ENV"           ; 測項名（ENV/EMC/Margin...），進 log 檔名
+EN_Margin     = 0               ; 1=跑 margin 掃描, 0=跳過
 EN_log        = 1               ; 1=logopen 存檔, 0=不存
+FAN_SPEED     = 100             ; 傳給 fan-speed-control.sh 的風扇轉速 (%)，預設全速
+SWB_UNIT0     = 1               ; 這台有 switch unit 0（流量與 wait_init 都依此）
+SWB_UNIT1     = 1               ; 這台有 switch unit 1
 prompt_login      = "sonic login:"
 prompt_sonic      = "admin@sonic:~$"
 prompt_sonic_root = "root@sonic:~#"
 ```
 
+> `SWB_UNIT0` / `SWB_UNIT1` 兩個都是 0 時，`wait_init.ttl` 直接 bypass、A/B/C 的流量段整段跳過。
+
 Log 檔名規則：`<mdir>\Logs\<project_name>_<strTestcase>_<YYYYmmdd-HHMMSS>.log`
 
 ### 2. `settings/<board>.conf` — 一顆 LTC2980（16 channel）
@@ -208,6 +240,43 @@ Log 檔名規則：`<mdir>\Logs\<project_name>_<strTestcase>_<YYYYmmdd-HHMMSS>.l
 
 Channel 定址：`ch / 8` → `CHIPS[]` index，`ch % 8` → LTC2977 PMBus PAGE（0x00~0x07）。
 
+**SWB 通道與位址對應（2026-08-19 上機驗證，`ababb2c`）：**
+
+| FPGA I2C 通道 | 板 / 接頭 | LTC2977 位址（lo / hi） |
+|---|---|---|
+| Ch6 | SWB0 CONN14 / CONN16 | CONN14 `0x5C`,`0x5E` ; CONN16 `0x62`,`0x64` |
+| Ch8 | SWB0 CONN13 / CONN15 | CONN13 `0x5C`,`0x5E` ; CONN15 `0x62`,`0x64` |
+| Ch7 | SWB1 CONN14 / CONN16 | CONN14 `0x5C`,`0x5E` ; CONN16 `0x62`,`0x64` |
+| Ch9 | SWB1 CONN13 / CONN15 | CONN13 `0x5C`,`0x5E` ; CONN15 `0x62`,`0x64` |
+
+> 同一顆 LTC2980 的兩個位址**相差 2**（7-bit，由規格書 8-bit 配對除以 2 而來），不是 1。
+> 兩張板共用一條通道，所以同通道上的位址必須互斥 —— 上表兩組（`0x5C/0x5E` 與 `0x62/0x64`）不重疊。
+
+**同一批 LTC2977 也掛在原生 i2c bus 上**（2026-08-27 上機驗證）：Blanton 的 SONiC 把 CB FPGA F3
+的這四條 I2C 通道同時註冊成 kernel i2c adapter，因此除了 `cb_pmbus_*` → pcimem 這條路，
+還可以用 `i2cset -f -y <bus>` 直接打到同一顆晶片：
+
+| FPGA F3 通道 | Linux bus | CB FPGA 路徑 | 原生 i2c 路徑 |
+|---|---|---|---|
+| Ch6 | 13 | `cb_pmbus_write 6 <addr> …` | `i2cset -f -y 13 <addr> …` |
+| Ch7 | 14 | `cb_pmbus_write 7 <addr> …` | `i2cset -f -y 14 <addr> …` |
+| Ch8 | 15 | `cb_pmbus_write 8 <addr> …` | `i2cset -f -y 15 <addr> …` |
+| Ch9 | 16 | `cb_pmbus_write 9 <addr> …` | `i2cset -f -y 16 <addr> …` |
+
+`margin.sh` 的 `margin_save blanton` 走原生路徑（`MARGIN_BLANTON_STORE` 表），
+其餘功能仍走 `TRANSPORT="swb"` 的 FPGA 路徑。兩條路到的是同一顆 LTC2977，
+**不要同時用**（同一條匯流排上兩個 master 語意的存取）。
+
+**全通道 net / 電壓對照：`docs/LTC2980_channel_map.csv`**（9 個 `.conf` × 16ch = 144 列，
+欄位 `Board,CONN,Ch,NetName,Vnom`）。查「某個 net 在哪片哪個 channel」比翻 9 個 `.conf` 快。
+CSV 是產出物，不是正本 —— 改完 `.conf` 用 `./tools/gen_channel_map.sh` 重產，別手改 CSV。
+兩件從表上看得出來、改 `.conf` 時要記得的事：
+
+- **SWB0 與 SWB1 的 net / 電壓完全相同**，差別只在 `CHIPS[]` 的 bus（`0:` vs `1:`）與 `CB_I2C_CH`。
+  也就是說有兩份會各自漂移的重複資料 —— 改了 SWB0 沒改 SWB1，不會有任何東西擋你。
+- **8 個 NC 通道**（SWB0/1 CONN14 的 CH10/CH11/CH13、CONN15 的 CH10）在 CSV 裡以
+  `NC` / `-` 原樣保留，不是漏掉；濾掉它們會讓 page 編號對不上。
+
 ### 3. `profiles/*.conf` — 16-ch 批次 margin 組合
 
 ```bash
@@ -267,16 +336,23 @@ PROFILE_CHANNELS=( "0:high:8" "1:low:8" ... )   # "channel:operation:change_perc
 
 | 模組 | 進入點 | 功能 |
 |------|--------|------|
-| **Script A（Pre-test）** | `1_Blanton_Script_A.ttl` | root 登入 → `mkdir ./logs` → `date -s` 對時 → source **六個** bash 工具 → 清/讀 7 組 PCIe AER → `lspci -tvvv/-vv` → margin 全掃 → PMON 九項 → dmesg 三 grep → `messagebox` 提示接 Script B |
+| **Script A（Pre-test）** | `1_Blanton_Script_A.ttl` V1.0.7 | root 登入 → `date -s` 對時 → 清 job log → `hw-test-session start` → **設定風扇轉速** → **等資料面就緒**（`wait_init.ttl`）→ DUT 清單（boot/version/fwutil/syseeprom/ssdhealth/TPM/NVMe）→ BMC enroll + version/status → source bash 工具 → 清/讀 7 組 PCIe AER + `ras-mc-ctl --summary` → `lspci` → margin → PMON → dmesg → **10G/1G 管理網路 ping** → 100G uplink 設定與狀態 → **一輪流量基線** → `show uptime` |
-| **Script B（Stress）** | `2_Blanton_Script_B.ttl` | `mlucas-avx2 -cpu 0:15` + 5 份 `stress_mem.py` + `stress_ssd.py` + `stress_usb.py` 背景執行（**共 8 個 job**）→ `jobs` 確認 → traffic `ps/init/clear/show/start -u 0` → `while 1` 每輪完整 PMON + margin |
+| **Script B（Stress）** | `2_Blanton_Script_B.ttl` | `mlucas-avx2 -cpu 0:15` + `bgctl run` 的 `memtester` / SSD / USB 壓力 + BMC DDR（`bmc-manager run memtester`）→ BMC USB net test（探測 cdc_ncm 介面，`systemd-run` 掛 4 小時 ping）→ 啟動 mgmt ping 監控 → `jobs` / `bgctl list` → traffic（依 `SWB_UNIT`）→ `while 1` 每輪完整 PMON + margin |
-| **Script C（Post-test）** | `3_Blanton_Script_C.ttl` | `kill $(jobs -p)` → PMON + dmesg 再抓一次 → 7 組 AER 再抓一次 → `cat` mlucas / stress_ssd log → traffic `stop` + `report -u 0` → 完成 messagebox |
+| **Script C（Post-test）** | `3_Blanton_Script_C.ttl` | `kill $(jobs -p)` + `bgctl stop --all` / `reset` + 停 BMC USB unit 與 mgmt ping → PMON + dmesg → 7 組 AER + `ras-mc-ctl` → BMC USB `journalctl` → `ip -s link show eth0/eth1` → `cat` mlucas log → traffic `stop` + `report` → NVMe 健康 → `show reboot-cause` / `uptime` → **job log 複製到 USB（帶時戳）** → `hw-test-session finish` |
 | **SWB loopback 流量** | `blanton_traffic_linespeed <sub> [-u 0\|1\|all]` | `init`（VLAN 30..137，成對 `cdN`/`cdN+32`）→ `clear` → `start`（`tx 100 length=512`）→ `stop` → `report`（per-pair TX/RX 交叉比對 PASS/FAIL）；另有 `ps`（link/speed）與 `run`（一條龍） |
 | **FPGA 暫存器存取** | `cb_fpga <fn> <addr> [data]`、`fpga_rescan` | pcimem 打 `resource0` + BAR 相對 offset，32-bit word；BDF 於 source 時自動偵測；`pmc/icb/swb0/swb1_fpga` 走 VSPI 窗口 |
 | **CB I2C / PMBus** | `cb_i2c_init/scan/read/write`、`cb_pmbus_read/write/linear16` | FPGA F3 OpenCores master，**讀用 Repeated START**（SMBus/PMBus 裝置必需） |
 | **ICB / PDB 存取** | `vi2c_init/scan/read/write`、`vi2c_scan_all` | CB F3 VI2C proxy，~3.3 ms/reg，取代 VSPI 的 ~18 ms/reg（後者會踩 SMBus 25–35 ms timeout） |
 | **溫度** | `temp_cb` / `temp_icb` / `temp_all` | TMP75（12-bit 左靠齊 ×0.0625）、TMP432（含 RANGE bit 的 −64 偏移、remote1/2） |
 | **電源資料** | `pwr_data` / `pwr_data_pdb` / `pwr_pdb_id` | SWB VRM 全軌 Vin/Vout/Iout/Temp 對齊表；MP29816 解析度**執行期從 `MFR_VOUT_SCALE_LOOP` 讀**，不寫死 |
-| **電壓 Margin** | `margin_init/status/set/apply_profile/save` + `*_all.sh` | 9 顆 LTC2980（CB CONN13、SWB0/1 CONN13~16）批次 high/low margin 與狀態掃描 |
+| **電壓 Margin** | `margin_init/status/set/apply_profile/save` + `*_all.sh` | 9 顆 LTC2980（CB CONN13、SWB0/1 CONN13~16）批次 high/low margin 與狀態掃描。v2.6.0 起 SWB 路徑真正接上共用 cb_i2c 後端，並有 `margin_swb_info/probe/scan/reset/sem` 除錯包裝 |
+| **Margin 寫 NVM** | `margin_save` / `margin_save all` / `margin_save blanton` | ⚠️ 永久寫入。`0x15` 送 PMBus **send-byte**（不帶 data byte）。`all` = 依 `settings/` 走 9 顆、跑完還原原本載入的板子；`blanton` = 本平台捷徑，18 顆全走原生 i2c bus（`MARGIN_BLANTON_STORE` 表），不需 `margin_init`。每筆之間 `MARGIN_STORE_SETTLE`（0.5s），工具**不 poll busy bit** |
+| **管理網路 ping** | `mgmt_ping_monitor.sh {start\|stop\|status\|fg\|tail\|clear\|summary}` | 一輪 = 10G leg + 1G leg，各自 `ip address/route replace` 後 `ping -I <if>` 打自己的對端；兩張卡都保持 up。每 leg 記 `ip -s link show` 與該卡的 TX/RX packet delta，另出一行可 grep 的 `RESULT` |
+| **BMC 監控** | `bmc_monitor.sh {start\|stop\|status\|fg\|tail\|clear}` | 由 host 端 `bmc-manager run` 週期取樣 `free -m`，另加一組 **I2C 寫入/讀回圖樣測試**（bus 1、addr 0x41、offset 0x00C0，寫 `55AA55AA` 讀回、再寫 `AA55AA55` 讀回）。B 啟動、C 停止並 `cat log/bmc_poll.log` |
+| **BMC DDR 壓力** | `bmc_monitor_ddr.sh` | ⚠️ **已停用** —— B/C 內呼叫處已註解，改由 `bgctl run bmc-manager run memtester` 取代。檔案保留未刪 |
+| **100G PRBS** | `port_prbs_monitor.sh {start [both\|a\|b]\|stop\|status\|report\|clear}` | 兩個 uplink 各一個 worker，可同時或單獨跑。setup（`lpmode off` → `prbs set` → `prbsstat STArt`）→ 週期 `prbs get`（判定）+ `prbsstat Ber`（只記錄）→ teardown（`STOp` + `prbs clear`）。輸出含 `PRBS OK!` 才算 PASS。**⚠️ A/B/C 的呼叫目前註解掉** |
+| **USB 目標偵測** | `usb_target.sh [-o dev\|mnt\|both\|id] [-n] [-r sec]` | 找出插入的 USB 儲存裝置，排除 `/` 與 `/host` 的底層碟（本平台可能從 USB DOM 開機），多顆時拒絕猜；掛載時會驗證真的可寫 |
+| **打包交付** | `publish/publish.sh [-v Ver] [-f] [-z] [-n]` | 版號讀 Script A 檔頭，複製成 `publish/Script_ABC_Blanton_<Ver>/`，排除 `*.log`，可另出 zip |
 
 ---
 
@@ -291,14 +367,24 @@ PROFILE_CHANNELS=( "0:high:8" "1:low:8" ... )   # "channel:operation:change_perc
 Script A ── logopen Logs/Blanton_Margin_<ts>.log ──┐  (之後所有畫面都進這個檔)
     │                                              │
     ├─ 登入 admin → sudo -i → root@sonic:~#         │
-    ├─ date -s "<host 時間>"   ← 讓 DUT 時戳可對照   │
+    ├─ date -s "<host 時間>"   ← 讓 DUT 時戳可對照
+    ├─ rm /host/hw-eval/jobs/*   ← 清掉上一輪的 job log
+    ├─ hw-test-session start / log / status
+    ├─ 風扇：max31790 unbind→sleep→bind（18-0020 與 25-0020 各一次）
+    │        → fan-speed-control.sh <FAN_SPEED> → 回答 y 確認   │
     ├─ source 6 個 bash 工具（函數進 shell）         │
     │    └ 此時 blanton_fpga_pcimem.sh 印出 [INFO] CB FPGA BDF = ...（自動偵測結果）
     ├─ AER 基線：7 組 EP+RP 的 correctable/nonfatal/fatal
     ├─ lspci -tvvv / -vv       ← 拓樸 + link speed/width
     ├─ margin_status_all       ← 9 顆 LTC2980 × 16ch 的 Vout 與偏差%
     ├─ show platform × 9       ← fan/temp/psu/voltage/current/ssdhealth/leak status/leak channels
-    └─ dmesg | grep error/fail/warning
+    ├─ dmesg -T（合併 error 正則 + i2c 過濾）→ dmesg -C 清空 ← C 只會看到 soak 期間新產生的
+    ├─ mgmt ping：start → pause 45 → stop → cat log      ← 10G/1G 各一輪
+    ├─ 100G uplink：lpmode off → 兩埠 startup → config save → show interfaces status
+    ├─ 一輪流量基線：ps → init → clear → show → start → stop → report
+    └─ show uptime
+  （最前面還有 wait_init.ttl：輪詢 show platform temperature 直到不再回報
+    "Thermal Not detected"，避免 pmon 還沒起來就抓基線）
     ▼
 [messagebox "Start Script B"] ← 人工確認後手動跑 B
     │
@@ -306,8 +392,11 @@ Script A ── logopen Logs/Blanton_Margin_<ts>.log ──┐  (之後所有畫
 Script B ── 同一個 log 檔續寫（logwrite 分隔線）
     ├─ 背景程序：mlucas-avx2(CPU) ×1, stress_mem ×5, stress_ssd, stress_usb  → 共 8 個 job
     │     （stress_hhmd / stress_pcie 已於 2026-08-17 移除，見 Status 表 ScriptB #5/#7 "KC Remove"）
-    ├─ jobs                     ← 確認全部起來了
+    ├─ bgctl run: memtester 1G / qfx5252-stress-ssd / qfx5252-stress-usb
-    ├─ traffic: ps → init → clear → (pause 3) → show → start   （unit 0，VLAN 30..137 loopback）
+    ├─ BMC: bmc-manager run memtester（DDR）、cdc_ncm 介面探測 + systemd-run 4hr ping（USB）
+    ├─ mgmt_ping_monitor.sh start
+    ├─ jobs / bgctl list        ← 確認全部起來了
+    ├─ traffic: ps → init → clear → (pause 15) → show → start  （unit 0 與 1，VLAN 30..137 loopback）
     └─ while 1: setup_pmon（9 項）→ margin_status_all          （soak 期間持續取樣）
     ▼
 [測試員 Ctrl-C / 停止 macro，接著跑 C]
@@ -317,8 +406,15 @@ Script C
     ├─ kill $(jobs -p)          ← 收掉所有背景壓力
     ├─ show platform × 9 + dmesg  ← 收工快照
     ├─ AER 再抓一次              ← 與 Script A 基線相減 = 本輪新增錯誤
-    ├─ cat mlucas_amm_log / log.stress_ssd  ← 壓力程式自身的 pass/fail
+    ├─ bgctl stop --all / reset、systemctl stop BMC USB unit、mgmt ping stop
-    └─ traffic: stop → report   ← per-pair TX/RX 交叉比對，PASS/FAIL/NA（exit 2 = 有 FAIL/NA）
+    ├─ journalctl BMC USB unit、ip -s link show eth0/eth1、ras-mc-ctl --summary
+    ├─ cat mlucas_amm_log       ← CPU 壓力程式自身的 pass/fail
+    ├─ nvme smart-log / smartctl -x /dev/nvme0
+    ├─ traffic: stop → report   ← per-pair TX/RX 交叉比對，PASS/FAIL/NA（exit 2 = 有 FAIL/NA）
+    ├─ show reboot-cause / show uptime  ← soak 期間有沒有意外重開，一眼看得到
+    ├─ usb_target.sh -o dev → sync → mount <dev> /mnt/usb
+    ├─ cp bmc_poll.log / mgmt_ping.log → jobs/，再 cp -r jobs/ /mnt/usb/jobs-<YYYYmmdd>_<HHMM>
+    └─ hw-test-session finish
     ▼
 [messagebox "GOOD JOB! Test Case DONE"] → 人工檢查 log
 ```
@@ -356,6 +452,8 @@ pwr_data
    只吃 Sr；只有純暫存器裝置兩種都行。
 7. **`margin_save`（`STORE_USER_ALL`）會永久寫進 NVM**，斷電保留。測試流程中**絕不執行**，
    以免覆蓋客戶出廠 config。`margin.sh` 的 auto-enable 只改 RAM（`ON_OFF_CONFIG`），斷電復原。
+   `margin_save all` / `margin_save blanton`（v2.7.0）一次對 9 顆 LTC2980（18 個 LTC2977）
+   下同一道命令，風險同性質但範圍是全機；命令本身是 PMBus send-byte（`0x15`，不帶 data byte）。
 8. **操作硬體電壓有損壞 DUT 的風險**：套 profile 前先確認該軌 OV/UV limit 與 servo DAC 注入電阻
    有 populate（本板部分 margin 電阻標 PROTO，沒 populate 的軌電壓不會動）。
 9. **`ARB_LOST` 不等於裝置存在**：`vi2c_scan` 只看 `RX_ACK`，仲裁失敗會被誤報成「有裝置」。
@@ -369,7 +467,28 @@ pwr_data
     否則它會吃掉 while 迴圈的 stdin，導致**只有第一個 VLAN 被設定**（V0.3.1 修的 bug）。
 11. **DUT 密碼不得進 git**：`1_Blanton_Script_A.ttl` 目前的 `sendln "YourPaSsWoRd"` 是 placeholder，
     實際帳密必須放 `secret/config_secret.ttl`（gitignored）並由 `config.ttl` include。
-12. **客戶 NDA**：`docs/` 內含客戶 FPGA 規格與 schematic 衍生資訊，**本 repo 只推 NAS + Gitea，
+12. **`.sh` / `.conf` 必須是 LF**：CRLF 的 shell script 在 SONiC 上直接掛
+    （`-bash: $'\r': command not found` + `syntax error near unexpected token`），
+    `settings/*.conf` 則因為是被 `source` 的，未加引號的賦值會變成 `"6\r"`（安靜地壞掉）。
+    `.gitattributes` 已把 `*.sh` `*.conf` `*.py` `*.txt` `*.md` 釘成 LF、`*.ttl` 維持 CRLF。
+    ⚠️ 但 `.gitattributes` **不會回頭重寫既有工作區檔案** —— 早於它 clone 出來的目錄，
+    需 `git rm --cached -r . && git reset --hard` 或刪掉目錄重新 checkout 才會生效，
+    而且 `git status` 乾淨**不代表**磁碟上是 LF（`--renormalize` 只在進 index 的路上轉換）。
+13. **`bmc_monitor*.sh` / `mgmt_ping_monitor.sh` 需要執行權**：它們是本專案「被執行」而非被 `source` 的腳本，
+    而 `do_start` 內部是 `setsid "$SCRIPT_PATH" __daemon`，**即使用 `bash x.sh start` 呼叫
+    也仍需 exec bit**。git 記錄為 `100644`，且 Windows → 隨身碟 → DUT 的路徑無法攜帶權限位元，
+    所以佈署後要先 `chmod +x ~/Blanton_Script/bmc_monitor*.sh`，否則 Script B 的 start 會
+    `Permission denied`、Script C 的 `cat` 撲空（BMC 段全空但不會報錯）。
+14. **TTL 的 `timeout` 是全域的，設了就要還原**：`timeout = N` 之後**每一個** `wait` 都被限制在 N 秒，
+    逾時的 `wait` 會直接返回而沒吃到 prompt，於是下一個指令在前一個還沒跑完就送出，之後整輪錯開一拍。
+    `wait_init.ttl` 設 60 後還原 0；Script B 的 cdc_ncm 探測設 15，在 `:skip_ping`（兩條路徑的匯流點）還原。
+    加新的 `timeout` 時務必配一個 `timeout = 0`。
+15. **兩張管理網卡同網段時會 ARP flux**：`mgmt_ping_monitor.sh` 讓 eth0/eth1 同時 up，若兩者在同一個
+    /24（本專案預設 `192.168.1.99` / `.101`），對端 ARP 可能由任一張卡回應，回包落在沒送封包的那張，
+    量到的數字不能歸屬。`ARP_STRICT=1` 會設 `arp_ignore=1` / `arp_announce=2` 擋掉；
+    另外每個 leg 的 `RESULT` 行帶 `nic_tx` / `nic_rx`（該卡自己的 packet delta），
+    **ping 成功但 `nic_tx` 接近 0 就代表封包從另一張卡出去了**。兩張卡在不同網段時可設 0。
+16. **客戶 NDA**：`docs/` 內含客戶 FPGA 規格與 schematic 衍生資訊，**本 repo 只推 NAS + Gitea，
     絕不推 GitHub**。
 
 ---
@@ -383,7 +502,7 @@ pwr_data
 | **客戶機密文件** | `docs/` 內 FPGA 規格（docx/xlsx/md）屬客戶 NDA 範圍；schematic 原始檔（`*.DSN`）一律 gitignore，不進 repo |
 | **Remote 限制** | 只推私有 remote：`nas`（`git.et-wen.com:51222`）+ `gitea`（`etgit.et-wen.com`）。**不設 GitHub `origin`** |
 | **測試 log** | `logs/*.log` 含 DUT 序號、MAC、韌體版本等可識別資訊 → gitignore，只保留目錄結構（`.gitkeep`） |
-| **破壞性硬體指令** | `margin_save` / `STORE_USER_ALL` 為永久 NVM 寫入，工具預設不呼叫；批次腳本 `margin_save_all.sh` 在 README 與腳本頂端都有警語 |
+| **破壞性硬體指令** | `margin_save` / `margin_save all` / `margin_save blanton` / `STORE_USER_ALL` 為永久 NVM 寫入，工具預設不呼叫；`margin_save all` 與批次腳本 `margin_save_all.sh` 在 README 與程式頂端都有警語 |
 | **root 權限** | 全流程在 `root@sonic:~#` 下執行（pcimem / i2c 需要）；腳本不留任何 `chmod 777` 或放寬權限的動作 |
 | **For_AI/** | AI 協作素材（截圖、草稿筆記）整個資料夾 gitignore，避免不小心把客戶圖面帶進 repo |
 
@@ -404,6 +523,9 @@ cp secret/config_secret.ttl.example secret/config_secret.ttl
 
 # ── 2. DUT 端：部署 bash 工具庫 ─────────────────────────────
 scp -r src/Script_ABC_Blanton/Blanton_Script admin@<DUT_IP>:~/
+#   佈署後務必補執行權（Windows/隨身碟路徑帶不動 exec bit）：
+ssh admin@<DUT_IP> 'chmod +x ~/Blanton_Script/bmc_monitor*.sh'
+#   若曾在舊工作區編輯過，先確認沒有 CRLF：grep -rlU $'\r' ~/Blanton_Script
 ssh admin@<DUT_IP> 'sudo -i'
 #   （現場無網路時改用 USB 隨身碟複製到 ~/Blanton_Script）
 
@@ -439,6 +561,19 @@ lspci -Dnn                          # 對照 ARCHITECTURE.md 的 PCIe 拓樸表
 8. 檢查 Logs\Blanton_Margin_<ts>.log
 ```
 
+**打包交付：**
+
+```bash
+./publish/publish.sh          # 版號讀 Script A 檔頭 → publish/Script_ABC_Blanton_V1.0.3/
+./publish/publish.sh -z       # 另外產出同名 .zip
+./publish/publish.sh -n       # dry run，只印會做什麼
+./publish/publish.sh -f       # 覆蓋既有輸出資料夾
+```
+
+版號**不是參數而是從 Script A 的 `; Version : Vx.y.z` 讀出來的**，所以資料夾名不可能跟
+測試員打開 macro 看到的版本不一致。要出新版就先改 Script A 檔頭再跑。
+輸出會排除 `*.log`（測試 log 含 DUT 序號，不隨交付外流），但保留空的 `logs/` 供 `logopen` 寫入。
+
 > 註：本專案非 .NET / Blazor / EC2 架構，`aws-ec2-deploy` 與 `vbox-run-deploy` 兩份部署指南不適用，已跳過。
 
 ---
@@ -493,19 +628,24 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值，
 **目標：** 壓力程序起得來、起不來看得出來，soak 迴圈有時戳、可控週期。
 
 **包含：**
-- [ ] 部署 `~/hammer/tools/` 前置檢查：新增 `utils/check_hammer_tools.ttl`
+- [ ] 前置檢查：`~/hammer/tools/amd/mlucas-avx2` 仍是唯一還依賴 hammer 的項目，缺檔就別往下跑
-      （`ls -l ~/hammer/tools/` + `ls ~/hammer/tools/amd/mlucas-avx2`），缺檔就別往下跑
 - [ ] 壓力程序 log 加時戳，避免多輪覆蓋：
       `mlucas_amm_log` → `~/logs/mlucas_amm_log_$(date +%Y%m%d-%H%M%S).log`（Status 表 ScriptB #2 的既定寫法）
-- [ ] `jobs` 之後加驗證：期望 **8** 個背景 job（1 mlucas + 5 mem + ssd + usb），
+- [x] 壓力層改用平台的 `bgctl`（`memtester` / `qfx5252-stress-ssd` / `qfx5252-stress-usb`），
-      數量不符時 `messagebox` 提示
+      取代 `~/hammer/tools/stress_*.py`；Script B 以 `jobs` + `bgctl list` 兩者並列確認
-      （`stress_hhmd` / `stress_pcie` 已於 2026-08-17 由 KC 移除，原本的 10 改為 8）
+- [ ] `bgctl list` 之後加數量驗證，不符時 `messagebox` 提示（目前只印出來給人看）
+      **← V1.0.10 起 `bgctl list` + `jobs` 改為每輪都印，中途死掉的 job 看得到，但仍要靠人眼比對**
 - [ ] soak 迴圈改為「每輪先 `date`、跑完 `pause <間隔>`」，
       把 `EN_LoopInterval`（預設 600 秒 = 10 min）放進 `config.ttl`，兌現 Status 表的「Get data every 10mins」
-      **← 目前 `while 1` 仍無 `pause`，實際間隔取決於指令執行時間，不是 10 分鐘**
+      **← V1.0.10 已補上 `pause 60`（迴圈不再全速空轉），但 60 秒是寫死的、也還沒有每輪 `date`；
+      距 Status 表的 10 分鐘仍有差距，故本項未結**
 - [x] soak 每輪補 `show platform psustatus` / `voltage` / `current`
       —— 迴圈已改為 `include "utils/setup_pmon.ttl"`，九項全收
 - [ ] 補 `; ========== CLEAR EVENT ==========`（Status 表 ScriptB #1，Owner: Alan）
+- [x] BMC 納入 soak：`bmc_monitor.sh`（`free -m` 取樣）與 `bmc_monitor_ddr.sh`（`memtester`）
+      由 Script B 啟動、Script C 停止並把 log 併進 master log
+- [x] Script A 加開機資訊與就緒等待：`show boot`、BMC `/etc/issue`、`wait_init.ttl`
+- [x] Script C 加 `show reboot-cause` / `show uptime`，soak 期間意外重開看得見
 
 **驗收條件：** Script B 啟動後 `jobs` 顯示 8 個 job；連續跑 3 輪，log 內三段各自帶正確時戳且間隔 ≈10 min；
 故意把 `~/hammer` 改名，Script B 會在前置檢查就停下並提示。
@@ -530,14 +670,15 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值，
       （取代原規劃的 `utils/show_traffic_counters.ttl`）
 - [x] Script B 接上 `ps → init → clear → show → start`、Script C 接上 `stop → report`
 - [x] 原始 bcmcmd 指令表留檔：`tools/traffic_loopback_{vlan_setting,start,vlan_remove}.txt`
-- [ ] **Script A 的 TRAFFIC-SETUP-STAGE 仍是空區塊** —— 目前流量只在 B/C，A 沒有基線
+- [x] **Script A 的流量基線** —— 原本的空區塊已改成完整一輪
+      （`ps → init → clear → show → start → stop → report`，含 15 秒沉澱）
 - [ ] `utils/show_interface_detail.ttl`：`show interface transceiver eeprom/dom`、
       `show interface link-training`（Status 表 ScriptC #4，仍 On-Going）
 - [ ] `utils/show_tech.ttl`：`show techsupport`（Script C 收工快照，Status 表 ScriptC #4）
 - [ ] `config.ttl` 加 `EN_Traffic` 旗標，未接 loopback 線的站點可整段跳過
       （現在 B/C 是無條件執行，沒接線會整批 bcmcmd 失敗）
-- [ ] 兩支腳本目前都寫死 `-u 0`，另一塊 switch board（unit 1）沒被測到；
+- [x] `-u 0` 已從三支腳本移除，全部沿用工具預設 `TL_UNITS="0 1"`，兩塊 switch board 都測到
-      工具本身預設是 `TL_UNITS="0 1"`，要決定是照工具預設跑兩塊，還是維持只測 unit 0
+- [x] 100G uplink 狀態：`show interfaces status Ethernet513,Ethernet514`（A 與 B 各一次）
 
 **驗收條件：** `EN_Traffic=1` 時，Script C 的 `report` 印出 108 對的 TX/RX 表且全 PASS；
 拔掉一條 loopback 線重跑，該對顯示 FAIL 或 NA 且 exit code 為 2；`EN_Traffic=0` 時整段不執行且不報錯。
@@ -555,9 +696,13 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值，
       UE > 0 或 fatal/nonfatal > 0 直接標 FAIL
 - [ ] Margin 表解析：把 9 顆 × 16ch 的 Vout / 偏差% 收成 CSV，標出超出 ±(profile 設定值 + 容差) 的軌
 - [ ] 溫度 / 風扇 / 電源趨勢：soak 期間逐輪取樣 → CSV（可直接畫圖）
-- [ ] Stress 判定：`mlucas_amm_log` 與 `log.stress_ssd` 的錯誤關鍵字掃描
+- [ ] Stress 判定：`mlucas_amm_log` 與 `bgctl` 各工作的 log
+      （`/host/hw-eval/.../qfx5252-stress-{ssd,usb}.log`）的錯誤關鍵字掃描
 - [ ] Traffic 判定：**直接複用 `tools/bcm_mibpair_report_V1.1.0.py`**（它已能吃 console log 的
       `show c` 段落並輸出 PASS/FAIL），不要重寫一套解析
+- [ ] 管理網路判定：抓 `mgmt_ping_monitor.sh` 的 `RESULT` 行（已是單行可 grep 格式），
+      並檢查 `nic_tx`/`nic_rx` 不為 0 —— 否則 PASS 也不能歸屬到那張卡
+- [ ] NVMe / EDAC：`nvme smart-log`、`smartctl -x`、`ras-mc-ctl --summary` 的前後差值
 - [ ] 產出 `Logs/<run>_summary.md`：一頁 PASS/FAIL + 每個子系統一行結論
 
 **驗收條件：** 拿一份既有 log（如 `Blanton_Margin_20260814-164122.log`）跑解析器，
@@ -570,9 +715,9 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值，
 **目標：** 產出可直接交給現場測試員（或客戶）的一包，含操作手冊，不需要看原始碼。
 
 **包含：**
-- [ ] `tools/publish.sh`：把 `src/Script_ABC_Blanton/` + 空 `Logs/` + `secret/*.example`
+- [x] `publish/publish.sh`：把 `src/Script_ABC_Blanton/` 打包成
-      打包成 `publish/Blanton_Script_ABC_v<ver>_<YYYYMMDD>/` 與同名 zip（比照
+      `publish/Script_ABC_Blanton_<Ver>/`（`-z` 另出 zip）。版號讀 Script A 檔頭，
-      既有的 `Blanton_Script_ABC_v1.0_20251229` 命名）
+      排除 `*.log` 但保留空的 `logs/`。工具本身進 git，產出被 gitignore
 - [ ] `README.md`（現場用）：Tera Term 設定、A→B→C 操作順序、常見錯誤（BDF 不符、
       margin 掃不到、hammer 工具缺檔）與對應處理
 - [ ] `CHANGELOG.md`：延續三支腳本頂端的 Version History，集中成一份
@@ -602,6 +747,44 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值，
   bash 工具，速度與可靠度都比 serial 好，TTL 只保留開機階段。
 - **多 DUT 併行**：多台 DUT 同時 soak 時，Tera Term 每台開一個 macro window；
   可考慮改成 Python（`pyserial`）統一排程與集中收 log。
-- **與 `LTC2980_Margin_Script` 獨立 repo 的同步機制**：目前 `Blanton_Script/LTC2980_Margin_Script/`
+- ✅ **margin 子專案的重複檔** —— v2.6.0 已移除內含的 `blanton_cb_i2c.sh` /
-  是該 repo 的複本（少了 `ARCHITECTURE.md`/`CLAUDE.md`/`Reference/`，多了兩支 `blanton_*` 後端）。
+  `blanton_fpga_pcimem.sh` 複本，改由 `_swb_find_backend` 往上層找共用版，漂移風險解除。
-  待評估改用 git submodule 或明確的 vendored 同步腳本。
+  與獨立 repo `LTC2980_Margin_Script` 的同步機制（submodule 或 vendored 腳本）仍待評估。
+- **`Ref/margin_command_trace.md` 需重新產生**：SWB 章節的 1223 條 `cb_pmbus_*` 指令是依
+  修正前的通道／位址展開的（其中 487 條用到已不存在的 `0x5D`/`0x5F`/`0x63`/`0x65`），
+  文件已加過期警告但內文未動。第 1~4 章不受影響。
+- **`wait_init.ttl` 沒有逾時出口**：若 pmon 一直起不來，`result` 既非 1 也非 2，迴圈會無限重試，
+  Script A 既不往下走也不報錯。可加最大重試次數 + `messagebox` 提示。
+- **腳本的執行權**：`mgmt_ping_monitor.sh` 與 `bmc_monitor.sh`（以及已停用的 `bmc_monitor_ddr.sh`）需人工 `chmod +x`。
+  可在 Script B 起它之前補一行（比照既有的 `chmod +x ~/hammer/tools/amd/mlucas-avx2`），或在 publish 時處理。
+- **`bmc_monitor_ddr.sh` 已停用**：B/C 內的呼叫已註解，DDR 壓力改由 `bgctl run bmc-manager run memtester`
+  取代。檔案還留在 repo，待確認不再需要後刪除，或在檔頭標註停用。
+  （`bmc_monitor.sh` 已於 2026-08-25 重新啟用，並加上 I2C 寫入/讀回圖樣測試。）
+- **`rm /host/hw-eval/jobs/*` 清不掉子目錄**：Script A 用的是不帶 `-r` 的 `rm`，但 Script C
+  是 `cp -r` 那個目錄，代表裡面可能有子目錄。清不乾淨的話，上一輪的 job log 會被當成這輪的一起
+  複製到 USB。要確認 `bgctl` 的產出結構，必要時改成 `rm -rf .../jobs/*`。
+- **100G PRBS 尚未接進 A/B/C**：`port_prbs_monitor.sh` 已隨包交付、可手動執行，但三支腳本裡的呼叫
+  都還註解著（bring-up 中）。要啟用時記得 PRBS 期間 link 會顯示 down，`stop` 之後才會回來。
+- **Script C 的 USB 掛載走 `mount` 而非 `usb_target.sh -o mnt`**：目前是 `-o dev` 取節點再自己
+  `mount <dev> /mnt/usb`，繞過了工具內建的 `mkdir -p`、exfat/ntfs `modprobe` 與可寫性驗證。
+  掛載點不存在、檔案系統模組沒載、或媒體唯讀時只會失敗一行，job log 就沒帶出來。
+- **風扇確認提示是無限等待**：`wait "Set all configured fan channels to"` 之後才 `sendln "y"`；
+  若該版 `fan-speed-control.sh` 不再詢問（或字串改了），這個 `wait` 會永遠等下去，Script A 停在那裡
+  且不報錯。加個 `timeout` + 分支會比較保險（記得還原 `timeout = 0`）。
+- **TR518 內建封包測試尚未腳本化**：`tools/TR518.txt` 記下了 `tr 518 Scenario=6 Profile=2 Count=260
+  PktSize=324 PortList=1-259,270-565` 這組指令（含 `port all lb=mac` + `l2 learn off` 前置），
+  目前只能手貼。它與 `blanton_traffic_linespeed` 是兩條互斥的打流路線（都會動 loopback 與 L2 學習），
+  要腳本化的話得先決定兩者怎麼共存，不能同時跑。
+- **SWB 的 LTC2977 有兩條路可以到，目前工具兩條都在用**：`cb_pmbus_*`（CB FPGA F3 → pcimem）
+  是 `margin_init` / `margin_status` / `margin_set` 走的路；原生 i2c bus（Ch+7 = bus 13/14/15/16）
+  是 `margin_save blanton` 走的路。後者短很多 —— 不需要通道初始化、不需要 pcimem，
+  單一 `i2cset` 就到。若原生 bus 在這平台夠穩，整個 `TRANSPORT="swb"` 層其實可以退成
+  「bus 號不同的 i2c 路徑」，`_swb_*`、probe、semaphore、prescale 那整套都能拿掉。
+  要動之前得先確認：讀取（`margin_status` 的 LINEAR16 word read）是否也同樣可靠，
+  以及 kernel driver 有沒有搶著存取（`margin_save blanton` 帶 `-f` 就是為了繞過這件事）。
+- **`settings/` 裡 SWB0 與 SWB1 是兩份相同的資料**：8 個 `.conf` 中，SWB1 的四個除了 `CHIPS[]` 的
+  bus 與 `CB_I2C_CH` 之外，net name 與 `VNOM` 與 SWB0 逐欄相同（見 `docs/LTC2980_channel_map.csv`）。
+  改一邊忘了改另一邊不會有任何警告。可考慮改成「共用 net 定義 + 各自的 transport 覆寫」兩層檔案。
+- **Script C 沒有倒出 `mgmt_ping.log`**：C 會 `stop` 管理網路監控並印 `ip -s link show`，
+  但沒有 `cat ~/Blanton_Script/log/mgmt_ping.log`，所以整個 soak 期間累積的 per-leg `RESULT`
+  留在 DUT 上、沒進 master log。Script A 那輪基線有 `cat`。

CLAUDE.md

@@ -9,6 +9,17 @@ DUT 端的取數能力由一組 **bash 工具庫** 提供（CB FPGA `pcimem` →
 
 完整架構見 [ARCHITECTURE.md](ARCHITECTURE.md)。
 
+**目前狀態（2026-08-27）**：Script A 為 **V1.0.10**（A 集中記錄 A/B/C 三支的變更）。涵蓋
+PCIe AER / DDR EDAC / PMON+TPM / 電壓 margin（9 顆 LTC2980）/ SWB loopback 線速流量 /
+10G+1G 管理網路 ping / BMC DDR 與 USB / NVMe 健康，壓力層走平台的 `bgctl`。
+switch unit 數量由 `config.ttl` 的 `SWB_UNIT0` / `SWB_UNIT1` 宣告，風扇轉速由 `FAN_SPEED` 指定
+（預設 100 = 全速；soak 是熱測試，散熱不該是變因）。
+測試 job log 收在 DUT 的 `/host/hw-eval/jobs/`，Script C 結束時掛好 USB 再帶時戳複製到 `/mnt/usb/`。
+100G PRBS（`port_prbs_monitor.sh`）已隨包交付，但 **A/B/C 的呼叫仍註解掉**，還在 bring-up。
+Script B 的 soak 迴圈每輪印 `bgctl list` + `jobs`，並 `pause 60`（V1.0.10 之前完全沒有 pause）。
+最後一次發布是 **V1.0.9**；SWB 的 I2C 通道與位址已於 2026-08-19 上機驗證。
+交付用 `./publish/publish.sh` 打包。
+
 ## 技術棧
 
 - **Host**：Tera Term 5.x TTL macro（`.ttl`），Windows
@@ -19,6 +30,10 @@ DUT 端的取數能力由一組 **bash 工具庫** 提供（CB FPGA `pcimem` →
 - **Margin**：LTC2980（= 2 × LTC2977）over PMBus，LINEAR16
 - **資料面流量**：`bcmcmd`（Broadcom drivshell）SWB loopback，VLAN 30..137 成對 `cdN`/`cdN+32`，
   `tx 100 length=512`；判定讀 ASIC `MIB_TPOK`/`MIB_RPOK` 做 per-pair 雙向交叉比對
+- **BMC**：host 端 `bmc-manager run "<cmd>"`，不需對 BMC 開 SSH（繞開其 busybox 工具鏈）
+- **背景工作**：平台的 `bgctl run/list/stop --all/reset`；長時間 ping 用 `systemd-run --unit=` 掛 transient unit
+- **管理網路**：iproute2（`ip link set` / `address replace` / `route replace ... metric`）+ `ping -I`
+- **風扇**：max31790 driver rebind + `fan-speed-control.sh <%>`（轉速讀 `config.ttl` 的 `FAN_SPEED`）
 - **判定資料源**：PCIe AER sysfs（`aer_dev_*`）、EDAC sysfs（`dimm_{ce,ue}_count`）、SONiC `show platform *`
 - **無編譯步驟**：TTL 與 bash 都直譯執行
 
@@ -49,25 +64,78 @@ temp_all                           # CB + ICB 溫感
 pwr_data                           # SWB VRM 全軌
 margin_init Blanton_CB_CONN13 && margin_status
 
+# ── 電壓 margin 寫 NVM（⚠️ 永久，測試中絕不執行）─────
+margin_save                        # 只寫當前 margin_init 載入的那顆（2 個 LTC2977）
+margin_save all                    # settings/ 全部 9 顆；跑完自動切回原本載入的那顆
+margin_save blanton                # Blanton SONiC 捷徑：18 顆全走原生 i2c，不用 margin_init
+#   0x15 是 send-byte，不帶 data byte：i2cset -f -y <bus> <addr> 0x15
+#   bus = FPGA F3 通道 + 7 → Ch6=13, Ch7=14, Ch8=15, Ch9=16（CB 本來就是 bus 4）
+#   ⚠️ 沒裝滿的機器：改 margin.sh 頂端的 MARGIN_BLANTON_STORE，把沒有的板子註解掉
+
 # ── SWB loopback 流量（bcmcmd，unit 0/1）─────────────
-blanton_traffic_linespeed ps     -u 0    # 對照線的 link/speed
+# 不帶 -u 就是預設 TL_UNITS="0 1"，兩塊 switch board 都做（TTL 三支腳本即如此）
-blanton_traffic_linespeed init   -u 0    # VLAN 30..137，cdN <-> cdN+32
+blanton_traffic_linespeed ps             # 對照線的 link/speed
-blanton_traffic_linespeed clear  -u 0    # clear c
+blanton_traffic_linespeed init           # VLAN 30..137，cdN <-> cdN+32
-blanton_traffic_linespeed start  -u 0 -tx 100 -length 512
+blanton_traffic_linespeed clear          # clear c
-blanton_traffic_linespeed stop   -u 0    # 移除 VLAN 成員（--destroy 連 VLAN 一起砍）
+blanton_traffic_linespeed start -tx 100 -length 512
-blanton_traffic_linespeed report -u 0    # per-pair TX/RX + PASS/FAIL（exit 2 = 有 FAIL/NA）
+blanton_traffic_linespeed stop           # 移除 VLAN 成員（--destroy 連 VLAN 一起砍）
-blanton_traffic_linespeed run    -u 0    # ps → init → clear → start → report 一條龍
+blanton_traffic_linespeed report         # per-pair TX/RX + PASS/FAIL（exit 2 = 有 FAIL/NA）
-blanton_traffic_linespeed init   -u 0 -n # -n dry-run：只印要下的 bcmcmd，不碰 DUT
+blanton_traffic_linespeed run            # ps → init → clear → start → report 一條龍
+blanton_traffic_linespeed init   -u 0    # 只做單一 unit 時才需要 -u
+blanton_traffic_linespeed init   -n      # -n dry-run：只印要下的 bcmcmd，不碰 DUT
 blanton_traffic_linespeed report -f <log>  # 離線重解一份存下來的 console log
 
 # 離線版報表（開發機上跑，選項更多）
 python3 tools/bcm_mibpair_report_V1.1.0.py <drivshell.log> -a
 
+# ── 管理網路 ping 監控（需先 chmod +x！）──────────────
+chmod +x ~/Blanton_Script/*.sh               # 佈署後必做一次
+~/Blanton_Script/mgmt_ping_monitor.sh fg     # 前景試一輪（約 30 秒），確認 IP/對端/網卡
+~/Blanton_Script/mgmt_ping_monitor.sh start  # 背景，log/mgmt_ping.log（start 會先清空）
+~/Blanton_Script/mgmt_ping_monitor.sh status
+~/Blanton_Script/mgmt_ping_monitor.sh stop
+~/Blanton_Script/mgmt_ping_monitor.sh summary  # 只看每段的 RESULT 行
+#   ⚠️ tail 子命令是 tail -f，會卡住不返回；TTL 裡要倒 log 請用 cat
+#   bmc_monitor.sh   start/stop         # free -m + BMC I2C 寫入/讀回圖樣測試，log/bmc_poll.log
+#   ⚠️ bmc_monitor_ddr.sh 已停用（DDR 壓力改走 bgctl + bmc-manager），檔案仍在
+
+# ── 100G PRBS（目前 TTL 未啟用，手動測用）────────────
+bash ~/Blanton_Script/port_prbs_monitor.sh start        # 兩個 port 同時
+bash ~/Blanton_Script/port_prbs_monitor.sh start a      # 只跑 Ethernet513
+bash ~/Blanton_Script/port_prbs_monitor.sh start b      # 只跑 Ethernet514
+bash ~/Blanton_Script/port_prbs_monitor.sh report       # PASS/FAIL 統計（沒跑的顯示 SKIP）
+bash ~/Blanton_Script/port_prbs_monitor.sh stop         # 收尾會跑 prbsstat STOp + prbs clear
+#   ⚠️ PRBS 打起來時 link 會顯示 down，這是正常的 —— 所以 start 刻意不印 port status
+
+# ── USB 目標偵測 ────────────────────────────────────
+bash ~/Blanton_Script/usb_target.sh -o dev              # /dev/sdX1
+bash ~/Blanton_Script/usb_target.sh -o mnt              # 掛好並回傳掛載點
+
+# ── 背景壓力（平台工具）──────────────────────────────
+bgctl run /usr/sbin/memtester 1G 100
+bgctl list
+bgctl stop --all ; bgctl reset --yes
+
+# ── 通道對照表（開發機上跑，改完 settings/*.conf 一定要重產）──
+./tools/gen_channel_map.sh              # → docs/LTC2980_channel_map.csv（144 列）
+./tools/gen_channel_map.sh -            # 只印到 stdout
+#   ⚠️ 需要 gawk（用到 3 參數的 match()）；mawk 會直接擋下並提示
+
 # ── 各工具的 help ───────────────────────────────────
 blanton_fpga_help ; blanton_cb_i2c_help ; vi2c_help
 temp_sensor_help ; pwr_data_help ; blanton_traffic_linespeed_help
 ```
 
+**打包交付（在開發機上）：**
+
+```bash
+./publish/publish.sh          # 版號讀 Script A 檔頭 → publish/Script_ABC_Blanton_V1.0.3/
+./publish/publish.sh -z       # 另出 zip
+./publish/publish.sh -n       # dry run
+```
+
+要出新版**先改 Script A 檔頭的 `; Version :`**，publish 才會用新版號建資料夾。
+
 **Host 端跑一輪測試：**
 
 ```
@@ -94,6 +162,10 @@ Tera Term 連 COM port (115200-8-N-1)
   若要回到「每支各自記錄」，B/C 的 History 需要補回去
 - **Commit**：Conventional Commits，**英文**。scope 用 `ttl` / `fpga` / `i2c` / `vi2c` /
   `margin` / `pwr` / `temp` / `docs`
+- **換行符**：由 `.gitattributes` 管理 —— `*.sh` `*.conf` `*.py` `*.txt` `*.md` 釘 **LF**
+  （要在 SONiC 上跑／被 source），`*.ttl` 維持 **CRLF**（Tera Term 只在 Windows 跑）。
+  編輯 `.ttl` 時要保留 CRLF，別讓整檔變成 LF 產生假 diff
+- **打包**：`./publish/publish.sh`，版號**讀 Script A 檔頭**不是參數 —— 先改檔頭再打包
 - **Status 表**：`docs/TTL_Script_Blanton_Status_*.xlsx` 是逐項進度的正本（OK / On-Going + Owner），
   完成一項就同步更新，別讓文件跟腳本脫節
 
@@ -115,6 +187,11 @@ Tera Term 連 COM port (115200-8-N-1)
 - ⚠️ **I2C 讀一律 Repeated START**（不是 STOP + START），否則 PMBus/SMBus 裝置（VRM、EFUSE）不理。
 - ⚠️ **`margin_save` / `STORE_USER_ALL` 會永久寫 NVM**，斷電保留 → **測試流程中絕不執行**，
   以免覆蓋客戶出廠 config。`margin.sh` 的 auto-enable（`ON_OFF_CONFIG=0x1a`）只改 RAM，斷電復原。
+  v2.7.0 新增的 **`margin_save all` / `margin_save blanton` 一次寫 18 個 LTC2977**，
+  同一個警告放大 9 倍；另外 `0x15` 現在送 send-byte，不再帶多餘的 `0x00` data byte。
+- ⚠️ **SWB 的 LTC2977 有兩條路可以到**：`cb_pmbus_*`（CB FPGA F3 Ch6/7/8/9 → pcimem）與
+  原生 i2c bus（`i2cset -f -y 13/14/15/16`，Ch+7 = bus）。`margin_save blanton` 走後者，
+  其餘功能走前者。同一顆晶片，**不要同時用兩條路**。
 - ⚠️ **改電壓會弄壞 DUT**：套 profile 前確認該軌 OV/UV limit，且 servo DAC 注入電阻有 populate
   （本板部分 margin 電阻標 PROTO，沒 populate 的軌電壓不會動，不是腳本壞掉）。
 - ⚠️ **`ARB_LOST` ≠ 有裝置**：`vi2c_scan` 只看 `RX_ACK`，仲裁失敗會被誤報成裝置存在。
@@ -130,17 +207,48 @@ Tera Term 連 COM port (115200-8-N-1)
 - ⚠️ **`stress_hhmd.py` / `stress_pcie.py` 已於 2026-08-17 由 KC 移除**（Status 表 ScriptB #5/#7）。
   Script B 現在是 **8 個背景 job**（1 mlucas + 5 mem + ssd + usb），不是 10 個。
   I2C／PCIe 的持續讀取壓力目前沒有替代品。
-- ⚠️ **Script B 的 traffic 與 soak 迴圈都寫死 `-u 0`、且迴圈沒有 `pause`**：
+- ⚠️ **soak 迴圈沒有 `pause`**：取樣間隔不是 Status 表寫的 10 分鐘，而是取決於指令執行時間。
-  只測到一塊 switch board，取樣間隔也不是 Status 表寫的 10 分鐘（取決於指令執行時間）。
+  （`-u 0` 已於 `491e807` 移除，A/B/C 現在都跑兩個 switch unit。）
-  改之前先確認現場期待的是哪一種。
+- 🔒 **`.sh` / `.conf` 一定要 LF**。CRLF 的 shell script 在 SONiC 上直接掛（`$'\r': command not found`）；
+  `settings/*.conf` 更陰險 —— 它們是被 `source` 的，`CB_I2C_CH=6` 會變成 `"6\r"`，安靜地壞掉。
+  `.gitattributes` 已擋住 git 這條路徑，但**不會回頭重寫既有工作區檔案**：早於它 clone 的目錄要
+  `git rm --cached -r . && git reset --hard` 才會生效，而且 **`git status` 乾淨不代表磁碟上是 LF**
+  （`--renormalize` 只在進 index 的路上轉換）。驗證要看 byte：`grep -rlU $'\r' <dir>`
+- ⚠️ **TTL 的 `timeout` 是全域的**：`timeout = N` 之後**每一個** `wait` 都被限制在 N 秒。逾時的 `wait`
+  直接返回而沒吃到 prompt，下一個指令就在前一個還沒跑完時送出，之後整輪錯開一拍。**設了一定要
+  配一個 `timeout = 0` 還原**（`wait_init.ttl` 60→0；Script B 的 cdc_ncm 探測 15→0 在 `:skip_ping`）
+- ⚠️ **兩張管理網卡同網段會 ARP flux**：`mgmt_ping_monitor.sh` 讓 eth0/eth1 同時 up，同一個 /24 下
+  對端 ARP 可能由任一張卡回應，回包落在沒送封包的那張。`ARP_STRICT=1` 擋掉；判讀時看 `RESULT` 行的
+  `nic_tx`/`nic_rx`（該卡自己的 packet delta）—— **ping 成功但 `nic_tx` 接近 0 = 封包從另一張卡出去的**
+- ⚠️ **PRBS 跑起來時 `show interfaces status` 會顯示 DOWN**，那是 link 離開正常運作模式，不是故障。
+  `port_prbs_monitor.sh` 的 `start` 因此刻意不印 port status（避免測試員誤判），只在 `prbs clear` 之後的報表裡印
+- ⚠️ **`ip -s link` 的欄位順序是 `bytes packets errors ...`**，要 packet 數取的是**第 2 欄**不是第 1 欄
+- ⚠️ **`mgmt_ping_monitor.sh` / `bmc_monitor*.sh` 需要 exec bit**，且**不是改用 `bash x.sh start` 就能繞過** ——
+  `do_start` 內部是 `setsid "$SCRIPT_PATH" __daemon`，直接執行該路徑。git 記錄是 `100644`，
+  Windows → 隨身碟 → DUT 也帶不動權限位元，所以佈署後要 `chmod +x ~/Blanton_Script/bmc_monitor*.sh`。
+  沒做的話 start 會 Permission denied、後面的 `cat` 撲空，而且**不會報錯**，只會得到一份全空的 log
+- ⚠️ **這幾支 monitor 的 `tail` 子命令是 `tail -n 50 -f`，永遠不返回**。TTL 裡絕對不要呼叫它
+  （Script C 曾因此卡死，`18ce7a1` 改成直接 `cat log/*.log`）
+- ⚠️ **背景 monitor 的 `start` 只等 1 秒就返回**，不是跑完一輪。Script A 要做一輪基線的話，
+  `start` 和 `stop` 中間必須 `pause`（目前是 45 秒，一輪約 30 秒）—— 少了它 log 只會有 START banner
+- ⚠️ **風扇那段設完會 `wait "Set all configured fan channels to"` 等確認提示再送 `y`**。該提示沒出現
+  （版本改了、字串換了）就會永遠卡住且不報錯 —— 現場看起來像 Script A 當掉
+- ⚠️ **`show_dmesg.ttl` 結尾會 `dmesg -C` 清空 kernel ring buffer**。這是刻意的（讓 Script C 只看到
+  soak 期間新產生的訊息），但代表事後在 DUT 上 `dmesg` 撈不到舊訊息 —— 內容只存在 master log 裡
+- ⚠️ **DUT 的 awk 對 `%d` 會夾到 INT32**（2147483647）。線速流量的計數器是 ~10¹² 量級，
+  所以 awk 裡輸出大數一律用 `%.0f`（double 域，精確到 2⁵³）。`blanton_traffic_linespeed.sh`
+  V0.4.1 已修；寫新的 awk 報表時要記得同一件事
 
 ## 資料夾說明
 
 - `src/Script_ABC_Blanton/` — 可執行內容（Tera Term 工作目錄；內含要 scp 到 DUT 的 `Blanton_Script/`）
-- `docs/` — 客戶 FPGA 規格、AER/EDAC 檢查依據、逐項 Status 表（最新為 `*_20260817.xlsx`）
+- `docs/` — 客戶 FPGA 規格、AER/EDAC 檢查依據、逐項 Status 表（最新為 `*_20260817.xlsx`）、
+  `LTC2980_channel_map.csv`（9 個 `settings/*.conf` 合併成 Board,CONN,Ch,NetName,Vnom 144 列，
+  查 net 對應哪片哪個 channel 用；**改 `.conf` 後要重跑產生**）
 - `tools/` — Host / 離線端：`bcm_mibpair_report_V1.1.0.py`（drivshell log → per-pair 報表）、
   `traffic_loopback_*.txt`（bcmcmd 原始指令表，`blanton_traffic_linespeed.sh` 是其 bash 版，
-  **改 loopback 線路時兩邊要同步**）
+  **改 loopback 線路時兩邊要同步**）、`100G_PRBS.txt` / `TR518.txt` / `fan_ctrl.txt`
-- `publish/` — 交付用打包輸出（`Blanton_Script_ABC_v<ver>_<date>/` + zip）
+  （上機手貼用的原始指令；PRBS 已有 `.sh`，TR518 尚未腳本化）
+- `publish/` — `publish.sh`（打包工具，**進 git**）+ `Script_ABC_Blanton_<Ver>/` 產出（**gitignored**）
 - `secret/` — 🚫 gitignored（除 `README.md` 與 `*.example`）：DUT 帳密、per-unit BDF 覆寫、COM 設定
 - `For_AI/` — 🚫 gitignored：AI 協作素材（波形截圖、草稿筆記）

docs/LTC2980_channel_map.csv

@@ -0,0 +1,145 @@
+Board,CONN,Ch,NetName,Vnom
+CB,CONN13,CH0,V5P0_ALW,5.0
+CB,CONN13,CH1,V3P3_ALW,3.3
+CB,CONN13,CH2,PWR_VDD_MISC_ALW,0.75
+CB,CONN13,CH3,V1P8_ALW,1.8
+CB,CONN13,CH4,PWR_APU_VDDIO_SUS,1.1
+CB,CONN13,CH5,PWR_VDD_MISC_RUN,0.75
+CB,CONN13,CH6,PWR_APU_VDD_MEM_RUN,0.78
+CB,CONN13,CH7,V0P8_PHY2_DVDD,0.8
+CB,CONN13,CH8,V0P8_AVDD,0.8
+CB,CONN13,CH9,V0P8_PHY,0.8
+CB,CONN13,CH10,V1P8_FPGA,1.8
+CB,CONN13,CH11,V2P5_FPGA,2.5
+CB,CONN13,CH12,V1P1_FPGA,1.1
+CB,CONN13,CH13,P5V_STBY,5.0
+CB,CONN13,CH14,P3V3_STBY,3.3
+CB,CONN13,CH15,V0P8_PHY2_AVDD,0.8
+SWB0,CONN13,CH0,P0V75_DVDD_47,0.75
+SWB0,CONN13,CH1,P0V75_AVDD_47,0.75
+SWB0,CONN13,CH2,P1V5_AVDD_47,1.5
+SWB0,CONN13,CH3,P0V9_AVDD_47,0.9
+SWB0,CONN13,CH4,P1V8_1,1.8
+SWB0,CONN13,CH5,PVDD3_3V_SYNTH_LDO_A3,3.3
+SWB0,CONN13,CH6,PVDD3_3V_SYNTH_LDO_B1,3.3
+SWB0,CONN13,CH7,P1V8_3,1.8
+SWB0,CONN13,CH8,P1V8_DVDDIO_3,1.8
+SWB0,CONN13,CH9,P0V75_DVDD_39,0.75
+SWB0,CONN13,CH10,P0V75_AVDD_39,0.75
+SWB0,CONN13,CH11,P1V5_AVDD_39,1.5
+SWB0,CONN13,CH12,P0V9_AVDD_39,0.9
+SWB0,CONN13,CH13,PVDD1V5_2,1.5
+SWB0,CONN13,CH14,PVDD1V8_DUT,1.8
+SWB0,CONN13,CH15,PVDD_MDIO,1.2
+SWB0,CONN14,CH0,P0V75_AVDD_7,0.75
+SWB0,CONN14,CH1,P1V5_AVDD_7,1.5
+SWB0,CONN14,CH2,P0V9_AVDD_7,0.9
+SWB0,CONN14,CH3,P1V8_5,1.8
+SWB0,CONN14,CH4,P1V8_2,1.8
+SWB0,CONN14,CH5,PVDD3_3V_SYNTH_LDO_B2,3.3
+SWB0,CONN14,CH6,PVDD3_3V_SYNTH_LDO_A2,3.3
+SWB0,CONN14,CH7,PVDD3_3V_SYNTH_LDO_A1,3.3
+SWB0,CONN14,CH8,PVDD1V5_TSC,1.5
+SWB0,CONN14,CH9,PVDD1V5_ANLG,1.5
+SWB0,CONN14,CH10,NC,-
+SWB0,CONN14,CH11,NC,-
+SWB0,CONN14,CH12,PVDD1V5_1,1.5
+SWB0,CONN14,CH13,NC,-
+SWB0,CONN14,CH14,P1V8_DVDDIO_1,1.8
+SWB0,CONN14,CH15,P0V75_DVDD_7,0.75
+SWB0,CONN15,CH0,P1V5_AVDD_55,1.5
+SWB0,CONN15,CH1,P0V9_AVDD_55,0.9
+SWB0,CONN15,CH2,P0V75_DVDD_63,0.75
+SWB0,CONN15,CH3,P0V75_AVDD_63,0.75
+SWB0,CONN15,CH4,P1V5_AVDD_63,1.5
+SWB0,CONN15,CH5,P0V9_AVDD_63,0.9
+SWB0,CONN15,CH6,PVDD3_3V_SYNTH_LDO_B3,3.3
+SWB0,CONN15,CH7,PVDD1V5_3,1.5
+SWB0,CONN15,CH8,P0V85_STBY,0.85
+SWB0,CONN15,CH9,P1V8_STBY,1.8
+SWB0,CONN15,CH10,NC,-
+SWB0,CONN15,CH11,P3V3_STBY,3.3
+SWB0,CONN15,CH12,PVDD0V9_2,0.9
+SWB0,CONN15,CH13,P0V75_DVDD_55,0.75
+SWB0,CONN15,CH14,P0V75_AVDD_55,0.75
+SWB0,CONN15,CH15,P1V8_DVDDIO_4,1.8
+SWB0,CONN16,CH0,PVDD1V5_0,1.5
+SWB0,CONN16,CH1,P1V8_4,1.8
+SWB0,CONN16,CH2,PVDD3_3V_SYNTH_LDO_B5,3.3
+SWB0,CONN16,CH3,PVDD3_3V_SYNTH_LDO_A5,3.3
+SWB0,CONN16,CH4,PVDD3_3V_SYNTH_LDO_B4,3.3
+SWB0,CONN16,CH5,PVDD3_3V_SYNTH_LDO_A4,3.3
+SWB0,CONN16,CH6,P3V3,3.3
+SWB0,CONN16,CH7,PVDD0_8V_T3,0.8
+SWB0,CONN16,CH8,P0V75_DVDD_1,0.75
+SWB0,CONN16,CH9,P0V75_AVDD_1,0.75
+SWB0,CONN16,CH10,P1V5_AVDD_1,1.5
+SWB0,CONN16,CH11,P0V9_AVDD_1,0.9
+SWB0,CONN16,CH12,PVDD0V9_0,0.9
+SWB0,CONN16,CH13,PVDD0V9_1,0.9
+SWB0,CONN16,CH14,PVDD0V9_3,0.9
+SWB0,CONN16,CH15,PVDD1V2_T3,1.2
+SWB1,CONN13,CH0,P0V75_DVDD_47,0.75
+SWB1,CONN13,CH1,P0V75_AVDD_47,0.75
+SWB1,CONN13,CH2,P1V5_AVDD_47,1.5
+SWB1,CONN13,CH3,P0V9_AVDD_47,0.9
+SWB1,CONN13,CH4,P1V8_1,1.8
+SWB1,CONN13,CH5,PVDD3_3V_SYNTH_LDO_A3,3.3
+SWB1,CONN13,CH6,PVDD3_3V_SYNTH_LDO_B1,3.3
+SWB1,CONN13,CH7,P1V8_3,1.8
+SWB1,CONN13,CH8,P1V8_DVDDIO_3,1.8
+SWB1,CONN13,CH9,P0V75_DVDD_39,0.75
+SWB1,CONN13,CH10,P0V75_AVDD_39,0.75
+SWB1,CONN13,CH11,P1V5_AVDD_39,1.5
+SWB1,CONN13,CH12,P0V9_AVDD_39,0.9
+SWB1,CONN13,CH13,PVDD1V5_2,1.5
+SWB1,CONN13,CH14,PVDD1V8_DUT,1.8
+SWB1,CONN13,CH15,PVDD_MDIO,1.2
+SWB1,CONN14,CH0,P0V75_AVDD_7,0.75
+SWB1,CONN14,CH1,P1V5_AVDD_7,1.5
+SWB1,CONN14,CH2,P0V9_AVDD_7,0.9
+SWB1,CONN14,CH3,P1V8_5,1.8
+SWB1,CONN14,CH4,P1V8_2,1.8
+SWB1,CONN14,CH5,PVDD3_3V_SYNTH_LDO_B2,3.3
+SWB1,CONN14,CH6,PVDD3_3V_SYNTH_LDO_A2,3.3
+SWB1,CONN14,CH7,PVDD3_3V_SYNTH_LDO_A1,3.3
+SWB1,CONN14,CH8,PVDD1V5_TSC,1.5
+SWB1,CONN14,CH9,PVDD1V5_ANLG,1.5
+SWB1,CONN14,CH10,NC,-
+SWB1,CONN14,CH11,NC,-
+SWB1,CONN14,CH12,PVDD1V5_1,1.5
+SWB1,CONN14,CH13,NC,-
+SWB1,CONN14,CH14,P1V8_DVDDIO_1,1.8
+SWB1,CONN14,CH15,P0V75_DVDD_7,0.75
+SWB1,CONN15,CH0,P1V5_AVDD_55,1.5
+SWB1,CONN15,CH1,P0V9_AVDD_55,0.9
+SWB1,CONN15,CH2,P0V75_DVDD_63,0.75
+SWB1,CONN15,CH3,P0V75_AVDD_63,0.75
+SWB1,CONN15,CH4,P1V5_AVDD_63,1.5
+SWB1,CONN15,CH5,P0V9_AVDD_63,0.9
+SWB1,CONN15,CH6,PVDD3_3V_SYNTH_LDO_B3,3.3
+SWB1,CONN15,CH7,PVDD1V5_3,1.5
+SWB1,CONN15,CH8,P0V85_STBY,0.85
+SWB1,CONN15,CH9,P1V8_STBY,1.8
+SWB1,CONN15,CH10,NC,-
+SWB1,CONN15,CH11,P3V3_STBY,3.3
+SWB1,CONN15,CH12,PVDD0V9_2,0.9
+SWB1,CONN15,CH13,P0V75_DVDD_55,0.75
+SWB1,CONN15,CH14,P0V75_AVDD_55,0.75
+SWB1,CONN15,CH15,P1V8_DVDDIO_4,1.8
+SWB1,CONN16,CH0,PVDD1V5_0,1.5
+SWB1,CONN16,CH1,P1V8_4,1.8
+SWB1,CONN16,CH2,PVDD3_3V_SYNTH_LDO_B5,3.3
+SWB1,CONN16,CH3,PVDD3_3V_SYNTH_LDO_A5,3.3
+SWB1,CONN16,CH4,PVDD3_3V_SYNTH_LDO_B4,3.3
+SWB1,CONN16,CH5,PVDD3_3V_SYNTH_LDO_A4,3.3
+SWB1,CONN16,CH6,P3V3,3.3
+SWB1,CONN16,CH7,PVDD0_8V_T3,0.8
+SWB1,CONN16,CH8,P0V75_DVDD_1,0.75
+SWB1,CONN16,CH9,P0V75_AVDD_1,0.75
+SWB1,CONN16,CH10,P1V5_AVDD_1,1.5
+SWB1,CONN16,CH11,P0V9_AVDD_1,0.9
+SWB1,CONN16,CH12,PVDD0V9_0,0.9
+SWB1,CONN16,CH13,PVDD0V9_1,0.9
+SWB1,CONN16,CH14,PVDD0V9_3,0.9
+SWB1,CONN16,CH15,PVDD1V2_T3,1.2

docs/release-notes/v1.0.10.md

@@ -0,0 +1,56 @@
+# v1.0.10 — The soak loop stops spinning flat out, and shows you what is still running
+
+## ✨ New features
+
+**Every soak round now reports the background jobs**
+* Script B's monitoring loop prints `bgctl list` (platform jobs) and `jobs` (the login shell's own background jobs) on every pass, right after the platform data. A stress job that dies three hours into an overnight soak now shows up as a shorter list on the next round, instead of only being noticed at the end — or not at all.
+* The two lists answer different questions and are both worth having: `bgctl` knows about the platform's job runner, `jobs` knows about anything the macro backgrounded in that shell.
+
+**A single table for all 144 margin channels**
+* `docs/LTC2980_channel_map.csv` flattens the nine `settings/*.conf` files into one sheet — `Board,CONN,Ch,NetName,Vnom` — so "which board and channel is `PVDD1V5_TSC` on?" is one search instead of opening nine files.
+* `tools/gen_channel_map.sh` regenerates it. **The CSV is output, not source**: edit the `.conf` files and re-run the script, never the other way round.
+* Unused channels stay in the table as `NC` / `-` rather than being dropped, because the channel number is also the PMBus page (`ch / 8` picks the chip, `ch % 8` picks the page) — filtering the gaps out would shift everything after them.
+
+**The bench command lists that these scripts came from**
+* `tools/100G_PRBS.txt`, `tools/TR518.txt` and `tools/fan_ctrl.txt` join the existing `traffic_loopback_*.txt` set: the raw `bcmcmd` / sysfs sequences, kept in the form you can paste into a console when a script is misbehaving and you want to drive the hardware directly.
+
+## 🐛 Bug fixes
+
+**The soak loop ran as fast as the DUT could answer**
+* `while 1` had no pause at all, so each round started the moment the previous one finished. Over a long soak that means constant console traffic and a log full of near-identical samples taken seconds apart. The loop now ends each round with `pause 60`.
+* Note the gap this leaves: the Status sheet asks for a 10-minute sampling interval, and 60 seconds is still hard-coded rather than configurable. This makes the loop sane, it does not finish the job.
+
+**A comment promised a cadence the code never had**
+* The loop was labelled `Get data every 10mins` while running with no delay whatsoever. It now says what it does.
+
+## 📦 Downloads
+
+| File | Contents |
+|---|---|
+| `Script_ABC_Blanton_V1.0.10.zip` | The full Tera Term working directory, including `Blanton_Script/` to copy onto the DUT |
+
+**After copying to the DUT:**
+
+```bash
+chmod +x ~/Blanton_Script/*.sh      # see below
+grep -rlU $'\r' ~/Blanton_Script    # expect no output
+```
+
+`mgmt_ping_monitor.sh` and `port_prbs_monitor.sh` launch their workers through `bash`, so those two run without the execute bit. `bmc_monitor.sh` and `usb_target.sh` still need it, and neither git (mode 100644) nor a Windows/USB copy carries it. Without the `chmod`, `start` fails with `Permission denied` and the later `cat` finds nothing: **the section ends up empty and nothing reports an error.**
+
+## ⚠️ Before you run
+
+* **Declare the switch population.** `SWB_UNIT0` / `SWB_UNIT1` in `config.ttl` say which switch units this DUT has; traffic and the readiness gate both follow them.
+* **Set `FAN_SPEED`.** It is applied at the start of every run.
+* **Management connectivity is in use, not preserved.** Both management NICs are up and pinging — drive the run from the serial console.
+* **PRBS is still not wired into the macros.** Run `port_prbs_monitor.sh` by hand if you want it; the calls in A/B/C remain commented out, unchanged from v1.0.9.
+* **TR518 and the loopback traffic test cannot both run.** `tools/TR518.txt` sets `port all lb=mac` and `l2 learn off` across the whole unit, which is the same hardware `blanton_traffic_linespeed` is using. Pick one.
+* **Two settings persist to `config_db.json`** and survive a reboot: LLDP is left disabled and the 100G uplinks are left configured. Restore them before the DUT moves on.
+
+## 🔗 Links
+
+* [ARCHITECTURE.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/ARCHITECTURE.md) — test flow, data models, constraints
+* [CLAUDE.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/CLAUDE.md) — commands and the bench gotchas
+* [LTC2980_channel_map.csv](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/docs/LTC2980_channel_map.csv) — all 144 margin channels
+
+**Full changelog:** [V1.0.9...V1.0.10](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/compare/V1.0.9...V1.0.10)

docs/release-notes/v1.0.11.md

@@ -0,0 +1,59 @@
+# v1.0.11 — Saving the margin settings to NVM is now one command, and the command is correct
+
+## ✨ New features
+
+**`margin_save blanton` — all 18 LTC2977 in one go**
+* On this platform the CB FPGA's I2C channels are also exposed as ordinary Linux i2c buses, so every margin controller on the box — CB and both switch boards — can be reached with plain `i2cset`. `margin_save blanton` walks all 18 of them from one flat list: no `margin_init`, no FPGA channel setup, no `pcimem`.
+* The channel-to-bus mapping it relies on (F3 Ch6 → bus 13, Ch7 → 14, Ch8 → 15, Ch9 → 16; CB is bus 4 as before) is now written down in `ARCHITECTURE.md` and the margin README, not just known at the bench.
+* **A partly-populated DUT is a normal build.** Comment out the lines you do not have in `MARGIN_BLANTON_STORE` at the top of `margin.sh` rather than letting the tool talk to boards that are not there.
+* Missing bus and unresponsive chip are reported as two different failures. `/dev/i2c-16 does not exist` means the FPGA's i2c adapters did not enumerate; `i2cset failed (NACK/busy)` means the board is absent or the address is wrong. Chasing the second when you have the first wastes an afternoon.
+
+**`margin_save all` — every board in `settings/`**
+* Runs `margin_init` + `margin_save` across all nine boards, then puts back whichever board you had loaded, so a following `margin_status` still reports the board you were looking at.
+* It does not stop at the first failure: a half-saved set is harder to reason about than a fully-attempted one. The summary names the boards that failed.
+
+Both print a per-chip line and a `N saved, M failed` tally, and both return a non-zero exit code when anything failed.
+
+**The fans now default to full speed**
+* `FAN_SPEED` in `config.ttl` is 100 instead of 30. A soak is a thermal test of everything *except* the cooling, so the cooling should not be a variable in it — and a DUT that throttles halfway through a run produces results that look like a different fault. Lower it deliberately if quiet operation is what you are measuring.
+
+## 🐛 Bug fixes
+
+**A failed NVM write still reported success**
+* `margin_save` discarded the result of every write, so a NACK printed `Change Saved` exactly like a successful store. For the one operation in this tool that is permanent, that is the worst place to stay quiet. Each store is now checked and named if it fails.
+
+**`STORE_USER_ALL` was sent with a data byte it should not have**
+* The command went out as `0x15` followed by a dummy `0x00` — an SMBus write-byte, where `STORE_USER_ALL` is a send-byte. The LTC2977 tolerated it, but tolerance is not correctness. It is now `i2cset ... 0x15 c` on the native path and a no-data `cb_pmbus_write` on the FPGA path.
+
+## 📦 Downloads
+
+| File | Contents |
+|---|---|
+| `Script_ABC_Blanton_V1.0.11.zip` | The full Tera Term working directory, including `Blanton_Script/` to copy onto the DUT |
+
+**After copying to the DUT:**
+
+```bash
+chmod +x ~/Blanton_Script/*.sh      # see below
+grep -rlU $'\r' ~/Blanton_Script    # expect no output
+```
+
+`mgmt_ping_monitor.sh` and `port_prbs_monitor.sh` launch their workers through `bash`, so those two run without the execute bit. `bmc_monitor.sh` and `usb_target.sh` still need it, and neither git (mode 100644) nor a Windows/USB copy carries it. Without the `chmod`, `start` fails with `Permission denied` and the later `cat` finds nothing: **the section ends up empty and nothing reports an error.**
+
+## ⚠️ Before you run
+
+* **`margin_save` in any form writes NVM permanently.** A power cycle does not undo it. `margin_save all` and `margin_save blanton` do it to all 18 controllers at once. Run `margin_status_all.sh` first and never call any of them during a test run — the macros do not, and should not be made to.
+* **The 18 raw commands were verified on the DUT; the wrapper was not.** `margin_save blanton` issues exactly the sequence that was run by hand at the bench, and the packaging was tested against stubbed hardware, but the function itself has not been run on a DUT yet. Watch the per-chip lines the first time.
+* **Declare the switch population.** `SWB_UNIT0` / `SWB_UNIT1` in `config.ttl` say which switch units this DUT has; traffic and the readiness gate both follow them.
+* **`FAN_SPEED` is now 100.** It is applied at the start of every run, so this build runs the fans flat out unless you change `config.ttl`. Expect the noise.
+* **Management connectivity is in use, not preserved.** Both management NICs are up and pinging — drive the run from the serial console.
+* **PRBS is still not wired into the macros.** Run `port_prbs_monitor.sh` by hand if you want it; the calls in A/B/C remain commented out.
+* **Two settings persist to `config_db.json`** and survive a reboot: LLDP is left disabled and the 100G uplinks are left configured. Restore them before the DUT moves on.
+
+## 🔗 Links
+
+* [ARCHITECTURE.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/ARCHITECTURE.md) — test flow, data models, constraints
+* [CLAUDE.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/CLAUDE.md) — commands and the bench gotchas
+* [LTC2980_Margin_Script/README.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/README.md) — the three `margin_save` variants and what each one sends
+
+**Full changelog:** [V1.0.10...V1.0.11](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/compare/V1.0.10...V1.0.11)

docs/release-notes/v1.0.7.md

@@ -0,0 +1,65 @@
+# v1.0.7 — Management-link ping test, and the fans start where you set them
+
+## ✨ New features
+
+**10G / 1G management port ping test**
+* New `mgmt_ping_monitor.sh` exercises both management NICs in one loop: it brings each up with iproute2, waits for the link to settle, then pings that NIC's own target — `eth0` → `192.168.1.30`, `eth1` → `192.168.1.31`.
+* Runs detached like the other monitors: `start` / `stop` / `status` / `fg` / `summary`. `start` clears the previous log, so one run means one log.
+* Every leg writes a single greppable line — `RESULT 10G eth0 -> 192.168.1.30 tx=10 rx=10 loss=0% rtt_avg=1.743ms nic_tx=10 nic_rx=10 PASS` — so a whole soak can be read with `summary` instead of scrolling.
+* `nic_tx` / `nic_rx` are that interface's own counter delta across the burst. If a ping passes but they stay near zero, the traffic left on the *other* NIC and the number does not belong to this one.
+* Script A runs one round as a baseline; Script B leaves it running through the soak.
+
+**Fan speed is set at the start of every run**
+* `FAN_SPEED` in `config.ttl` (default 30) is applied by Script A, so a run no longer inherits whatever the previous test left the fans doing.
+* Both MAX31790 controllers are rebound first, which clears a controller left in an odd state.
+
+**Stress load moved onto the platform's own job runner**
+* CPU, DDR, SSD and USB stress now go through `bgctl`, replacing the `~/hammer/tools/stress_*.py` scripts. `bgctl list` shows what is running; Script C stops everything with `bgctl stop --all`.
+* BMC DDR stress runs through `bmc-manager`, and a new BMC USB test discovers the `cdc_ncm` interface and pings across it for four hours under `systemd-run`.
+
+**More of the DUT on record**
+* Script A now captures the boot image, `show version`, firmware status, system EEPROM, SSD health, TPM version and NVMe SMART data before the test starts.
+* PCIe AER now sits next to `ras-mc-ctl --summary`, and Script C closes with NVMe health so a disk that degraded during the soak is visible.
+* `dmesg` capture uses human-readable timestamps and one combined error pattern, then clears the ring buffer — so Script C's dmesg shows only what the soak produced, not everything since boot.
+* Each run opens with `hw-test-session start` and closes with `finish`; Script C copies the job logs to `/mnt/usb/jobs-<date>_<time>` so they leave the DUT with the run they belong to.
+
+## 🐛 Bug fixes
+
+**Script A no longer hangs waiting for ports that are already up**
+* The readiness gate required *more than* 216 ports up, but a fully cabled unit reports exactly 216 — 108 loopback pairs times two. Script A sat in the poll loop forever on the very state it was waiting for. It now proceeds at 216.
+* The comments in `wait_init.ttl` still described the old "more than" rule; they now match the code, so the off-by-one cannot be reintroduced by reading the wrong line.
+
+**The macro no longer runs ahead of the DUT during the soak**
+* Script B set a 15-second wait cap for the `cdc_ncm` probe and never restored it. In Tera Term that cap is global, so it stayed in force for everything after — including the traffic setup, which walks 108 VLANs per switch unit and takes far longer. A timed-out wait returns without the prompt, leaving every later command issued a step early.
+
+**Fan controller is no longer bound twice**
+* One of the two MAX31790 controllers received a second `bind` immediately after the first, which could only fail because the driver was already attached.
+
+## 📦 Downloads
+
+| File | Contents |
+|---|---|
+| `Script_ABC_Blanton_V1.0.7.zip` | The full Tera Term working directory, including `Blanton_Script/` to copy onto the DUT |
+
+**After copying to the DUT:**
+
+```bash
+chmod +x ~/Blanton_Script/*.sh      # required -- see below
+grep -rlU $'\r' ~/Blanton_Script    # expect no output
+```
+
+The `chmod +x` is not optional. `mgmt_ping_monitor.sh` is executed rather than sourced and re-execs its own path to daemonise, and neither git (mode 100644) nor a Windows/USB copy carries the execute bit. Without it `start` fails with `Permission denied` and the later `cat` finds nothing — **the section ends up empty and nothing reports an error**.
+
+## ⚠️ Before you run
+
+* **Declare the switch population.** `SWB_UNIT0` / `SWB_UNIT1` in `config.ttl` say which switch units this DUT has. Traffic and the readiness gate both follow them: a single unit gets `-u 0` or `-u 1`, and with neither set the traffic stage is skipped instead of failing against hardware that is not there.
+* **Both management NICs stay up.** If they share a subnet, keep `ARP_STRICT=1` — otherwise the target's ARP can be answered by either NIC and a reply may arrive on the one that did not send.
+* **Management connectivity is exercised, not preserved.** Drive the run from the serial console.
+* **Two settings persist to `config_db.json`** and survive a reboot: LLDP is left disabled, and the 100G uplinks are left configured. Restore them before the DUT moves on.
+
+## 🔗 Links
+
+* [ARCHITECTURE.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/ARCHITECTURE.md) — test flow, data models, constraints
+* [CLAUDE.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/CLAUDE.md) — commands and the bench gotchas
+
+**Full changelog:** [V1.0.5...V1.0.7](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/compare/V1.0.5...V1.0.7)

docs/release-notes/v1.0.8.md

@@ -0,0 +1,61 @@
+# v1.0.8 — Both management links tested at once, and ARP stops looking like packet loss
+
+## ✨ New features
+
+**Both management NICs are pinged simultaneously and continuously**
+* `mgmt_ping_monitor.sh` no longer alternates fixed bursts. `start` configures both NICs, then pings from each at the same time and keeps accumulating until stopped — so a soak-long run is one continuous measurement rather than a series of snapshots.
+* `stop` renders a report into the log: the last 20 entries per NIC, each one's ping statistics and PASS/FAIL, then `ip -s link show` for both interfaces.
+* Every line is timestamped, and a request that got no reply prints a marker instead of merely being absent — a drop is visible in the tail, not inferred from a gap in the sequence numbers.
+* `status` shows both pids and how many replies each NIC has received so far, which is the quick way to see one side is dead without waiting for the report.
+
+**The USB stress target is detected, not assumed**
+* New `usb_target.sh` reports an inserted USB device's node, mount point or by-id path. Script B asks it for the node and builds the stress command from the answer, so a stick that enumerates as `sdb` no longer sends a write test at whatever `/dev/sda1` happens to be.
+* It excludes whatever disk backs `/` and `/host` — this platform can boot from a USB DOM, which also reports as USB — refuses to guess when several USB disks are present, and when it mounts, verifies the result is actually writable rather than trusting that `mount` succeeded.
+
+**BMC I2C integrity is exercised through the soak**
+* `bmc_monitor.sh` is back in the run and now writes two complementary patterns to a BMC scratch register and reads each back. One pattern alone cannot catch a bit stuck the same way it was written; repeating the pair through the soak turns an intermittent I2C fault into something the log records rather than something the tester has to witness.
+
+**Test artefacts leave the DUT with the run**
+* Script C copies `bmc_poll.log` and `mgmt_ping.log` into the job directory before it is archived to USB, so the monitors' output travels with the `bgctl` job logs.
+* DDR stress now runs continuously instead of stopping after 100 passes, matching the other soak loads.
+
+## 🐛 Bug fixes
+
+**Three FAILs that were not link faults**
+* A bench run reported `FAIL=3` with zero NIC errors, zero drops and sub-millisecond replies. Every failure was missing exactly `icmp_seq=1` and nothing else: once the neighbour entry for the target expires, the first echo request is spent resolving ARP and `ping` counts it as loss. A discarded warm-up ping per NIC now absorbs that, which is what lets the loss threshold stay at zero and still mean something. Raising the threshold instead would have hidden genuine single-packet loss.
+
+**Job logs were being cleared before they were collected**
+* Script C ran `bgctl reset --yes` while killing processes — before the job directory is copied to USB. Moved to after the archive, so a run's own logs are collected before anything clears them.
+
+**The fan controller was bound twice**
+* One of the two MAX31790 controllers received a second `bind` immediately after the first, which could only fail because the driver was already attached.
+
+## 📦 Downloads
+
+| File | Contents |
+|---|---|
+| `Script_ABC_Blanton_V1.0.8.zip` | The full Tera Term working directory, including `Blanton_Script/` to copy onto the DUT |
+
+**After copying to the DUT:**
+
+```bash
+chmod +x ~/Blanton_Script/*.sh      # see below
+grep -rlU $'\r' ~/Blanton_Script    # expect no output
+```
+
+`mgmt_ping_monitor.sh` no longer re-execs itself, so `bash mgmt_ping_monitor.sh start` works without the execute bit. `bmc_monitor.sh` and `usb_target.sh` still need it — and neither git (mode 100644) nor a Windows/USB copy carries it. Without the `chmod`, `start` fails with `Permission denied` and the later `cat` finds nothing: **the section ends up empty and nothing reports an error.**
+
+## ⚠️ Before you run
+
+* **Declare the switch population.** `SWB_UNIT0` / `SWB_UNIT1` in `config.ttl` say which switch units this DUT has. Traffic and the readiness gate both follow them; with neither set the traffic stage is skipped rather than failing against hardware that is not there.
+* **Set the fan speed you want.** `FAN_SPEED` in `config.ttl` is applied at the start of every run.
+* **Management connectivity is in use, not preserved.** Both NICs are up and pinging — drive the run from the serial console.
+* **If the two management NICs share a subnet, keep `ARP_STRICT=1`.** Otherwise the target's ARP can be answered by either NIC and a reply may arrive on the one that did not send. Check `nic_tx` / `nic_rx` on the RESULT line: they are that interface's own counter delta.
+* **Two settings persist to `config_db.json`** and survive a reboot: LLDP is left disabled and the 100G uplinks are left configured. Restore them before the DUT moves on.
+
+## 🔗 Links
+
+* [ARCHITECTURE.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/ARCHITECTURE.md) — test flow, data models, constraints
+* [CLAUDE.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/CLAUDE.md) — commands and the bench gotchas
+
+**Full changelog:** [V1.0.7...V1.0.8](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/compare/V1.0.7...V1.0.8)

docs/release-notes/v1.0.9.md

@@ -0,0 +1,63 @@
+# v1.0.9 — 100G PRBS testing, and the job logs actually reach the USB stick
+
+## ✨ New features
+
+**100G uplink PRBS test**
+* New `port_prbs_monitor.sh` drives a PRBS test on both 100G uplinks: it clears low-power mode, arms the pattern, then polls `phy diag <phy> prbs get` in the background until stopped. A poll counts as PASS only when the output says `PRBS OK!`; `prbsstat Ber` is captured alongside every poll for the record.
+* `stop` runs `prbsstat STOp` and `prbs clear` on each port before rendering the report, so the test does not leave PRBS armed behind it.
+* `report` gives the tally the bench actually wants:
+
+  ```
+  PORT           POLLS    PASS     FAIL     RESULT
+  Ethernet513    42       42       0        PASS
+  Ethernet514    42       40       2        FAIL
+  ```
+* **One port at a time is a first-class mode.** `start a` or `start b` runs a single uplink, which is how you separate a genuine port fault from the DUT not coping with two PRBS streams at once. A port that was not run reports `SKIP`, not `FAIL`.
+* Every command and its full output — setup, each poll, teardown — goes to that port's raw log.
+
+> ⚠️ The script ships in this build and can be run by hand, but **the calls in Script A, B and C are commented out**: PRBS is still under bring-up on this platform.
+
+**USB target detection**
+* `usb_target.sh` reports an inserted USB device's node, mount point or by-id path. It excludes whatever disk backs `/` and `/host` — this platform can boot from a USB DOM, which also reports as USB — refuses to guess when several USB disks are present, and when mounting, verifies the result is writable rather than trusting that `mount` succeeded.
+* Script B builds the USB stress command from the detected node instead of a hard-coded `/dev/sda1`.
+
+## 🐛 Bug fixes
+
+**The job logs were being written to a path nobody collected**
+* Stress output, the monitors' logs and the USB archive disagreed about where the job directory lives. Everything now uses `/host/hw-eval/jobs/`, so what Script B writes is what Script C copies out.
+
+**Script C copied to a USB that was never mounted**
+* The archive step assumed `/mnt/usb` was ready. Script C now finds the device and mounts it first, so a run's logs leave the DUT instead of being written into an empty mount point.
+
+**`show interfaces status` right after starting PRBS reads as a failure**
+* With PRBS armed the link is out of normal operation and reports DOWN. `port_prbs_monitor.sh` deliberately does not print the port status at `start` — it appears in the report instead, after `prbs clear`, labelled as the recovered state.
+
+## 📦 Downloads
+
+| File | Contents |
+|---|---|
+| `Script_ABC_Blanton_V1.0.9.zip` | The full Tera Term working directory, including `Blanton_Script/` to copy onto the DUT |
+
+**After copying to the DUT:**
+
+```bash
+chmod +x ~/Blanton_Script/*.sh      # see below
+grep -rlU $'\r' ~/Blanton_Script    # expect no output
+```
+
+`mgmt_ping_monitor.sh` and `port_prbs_monitor.sh` launch their workers through `bash`, so those two run without the execute bit. `bmc_monitor.sh` and `usb_target.sh` still need it, and neither git (mode 100644) nor a Windows/USB copy carries it. Without the `chmod`, `start` fails with `Permission denied` and the later `cat` finds nothing: **the section ends up empty and nothing reports an error.**
+
+## ⚠️ Before you run
+
+* **Declare the switch population.** `SWB_UNIT0` / `SWB_UNIT1` in `config.ttl` say which switch units this DUT has; traffic and the readiness gate both follow them.
+* **Set `FAN_SPEED`.** It is applied at the start of every run.
+* **Management connectivity is in use, not preserved.** Both management NICs are up and pinging — drive the run from the serial console.
+* **PRBS is not wired into the macros yet.** Run `port_prbs_monitor.sh` by hand if you want it; uncommenting the calls in A/B/C is not supported in this build.
+* **Two settings persist to `config_db.json`** and survive a reboot: LLDP is left disabled and the 100G uplinks are left configured. Restore them before the DUT moves on.
+
+## 🔗 Links
+
+* [ARCHITECTURE.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/ARCHITECTURE.md) — test flow, data models, constraints
+* [CLAUDE.md](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/CLAUDE.md) — commands and the bench gotchas
+
+**Full changelog:** [V1.0.8...V1.0.9](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/compare/V1.0.8...V1.0.9)

publish/publish.sh

@@ -0,0 +1,108 @@
+#!/usr/bin/env bash
+# =============================================================================
+# publish.sh  --  package src/Script_ABC_Blanton for delivery
+# =============================================================================
+# Version History:
+#   V1.0.0  2026-08-21  Initial. Copies src/Script_ABC_Blanton to
+#                       publish/Script_ABC_Blanton_<Version>, taking <Version>
+#                       from the "; Version : Vx.y.z" header of
+#                       1_Blanton_Script_A.ttl.
+# =============================================================================
+#
+# The version is READ FROM Script A rather than passed in, so the folder name
+# can never disagree with the header the tester sees when they open the macro.
+# Bump Script A's header first, then run this.
+#
+# Usage:
+#   ./publish/publish.sh              # publish at Script A's version
+#   ./publish/publish.sh -v V1.0.4    # override the version
+#   ./publish/publish.sh -f           # overwrite an existing output folder
+#   ./publish/publish.sh -z           # also produce a .zip next to it
+#   ./publish/publish.sh -n           # dry run: print what would happen
+# =============================================================================
+set -u
+
+SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd -- "${SCRIPT_DIR}/.." && pwd)"
+SRC_DIR="${REPO_ROOT}/src/Script_ABC_Blanton"
+OUT_ROOT="${SCRIPT_DIR}"
+NAME="Script_ABC_Blanton"
+VER=""; FORCE=0; ZIP=0; DRY=0
+
+info() { printf '[\033[34mINFO\033[0m] %s\n' "$*"; }
+ok()   { printf '[\033[32m OK \033[0m] %s\n' "$*"; }
+die()  { printf '[\033[31mERR \033[0m] %s\n' "$*" >&2; exit 1; }
+
+usage() { sed -n '2,26p' "${BASH_SOURCE[0]}" | sed 's/^# \{0,1\}//'; exit 0; }
+
+while [ $# -gt 0 ]; do
+    case "$1" in
+        -v|--version) VER="${2:-}"; shift 2 ;;
+        -f|--force)   FORCE=1; shift ;;
+        -z|--zip)     ZIP=1; shift ;;
+        -n|--dry-run) DRY=1; shift ;;
+        -h|--help)    usage ;;
+        *) die "unknown option '$1' (try -h)" ;;
+    esac
+done
+
+[ -d "${SRC_DIR}" ] || die "source not found: ${SRC_DIR}"
+
+# --- version from Script A's header ------------------------------------------
+# The .ttl files are CRLF, so strip the carriage return or it lands in the
+# folder name and produces a directory no one can cd into.
+if [ -z "${VER}" ]; then
+    A_TTL="${SRC_DIR}/1_Blanton_Script_A.ttl"
+    [ -f "${A_TTL}" ] || die "cannot read version: ${A_TTL} missing"
+    VER=$(grep -m1 -E '^;[[:space:]]*Version[[:space:]]*:' "${A_TTL}" \
+          | tr -d '\r' | sed -E 's/.*:[[:space:]]*//; s/[[:space:]]+$//')
+    [ -n "${VER}" ] || die "no '; Version : Vx.y.z' header in $(basename "${A_TTL}")"
+    info "version from $(basename "${A_TTL}") : ${VER}"
+else
+    info "version (overridden)              : ${VER}"
+fi
+
+case "${VER}" in
+    V[0-9]*) ;;
+    *) die "version '${VER}' does not look like Vx.y.z" ;;
+esac
+
+DEST="${OUT_ROOT}/${NAME}_${VER}"
+info "source                            : ${SRC_DIR#${REPO_ROOT}/}"
+info "destination                       : ${DEST#${REPO_ROOT}/}"
+
+if [ -e "${DEST}" ]; then
+    [ "${FORCE}" = "1" ] || die "${DEST##*/} already exists (use -f to overwrite)"
+    [ "${DRY}" = "1" ] || rm -rf -- "${DEST}"
+    info "existing folder removed (-f)"
+fi
+
+if [ "${DRY}" = "1" ]; then
+    info "dry run: nothing copied"
+    exit 0
+fi
+
+# --- copy ---------------------------------------------------------------------
+# Captured console logs are per-run and often carry DUT serials, so they are
+# never shipped; the empty logs/ directory itself is kept because Script A's
+# logopen writes into it.
+mkdir -p -- "${DEST}" || die "cannot create ${DEST}"
+if command -v rsync >/dev/null 2>&1; then
+    rsync -a --exclude='*.log' "${SRC_DIR}/" "${DEST}/" || die "rsync failed"
+else
+    cp -a -- "${SRC_DIR}/." "${DEST}/" || die "cp failed"
+    find "${DEST}" -type f -name '*.log' -delete
+fi
+
+# Tera Term's logopen target, in case the source tree never had one
+mkdir -p -- "${DEST}/logs"
+
+n_files=$(find "${DEST}" -type f | wc -l)
+ok "${n_files} files -> ${DEST##*/}"
+
+if [ "${ZIP}" = "1" ]; then
+    command -v zip >/dev/null 2>&1 || die "zip not installed"
+    ( cd -- "${OUT_ROOT}" && rm -f -- "${NAME}_${VER}.zip" \
+      && zip -qr "${NAME}_${VER}.zip" "${NAME}_${VER}" ) || die "zip failed"
+    ok "$(du -h "${OUT_ROOT}/${NAME}_${VER}.zip" | cut -f1) -> ${NAME}_${VER}.zip"
+fi

src/Script_ABC_Blanton/1_Blanton_Script_A.ttl

@@ -1,7 +1,7 @@
 ; =============================================================================
 ; Script A for Blanton
-; Version : V1.0.2
+; Version : V1.0.11
-; Date    : 2026-08-17
+; Date    : 2026-08-28
 ; Author  : ETWen
 ; =============================================================================
 ; Version History:
@@ -14,7 +14,87 @@
 ;                       ScriptB                                         Remove stress_hhmd, stress_pcie
 ;                       Blanton_Script                                  Add blanton_traffic_linespeed.sh
 ;                       ScriptB/C                                       Add Traffic Test
-;
+;   V1.0.3  2026-08-21  utils/wait_init.ttl                             Created
+;                       ScriptA                                         Add Wait DUT Ready
+;   V1.0.4  2026-08-21  utils/wait_init.ttl                             Wait on bcmcmd port-up, count (both units > 216)
+;                       utils/wait_init.ttl                             Add WT_UNIT0/WT_UNIT1, skip absent units
+;                       ScriptA                                         Add EEPROM info (hpe-eeprom-tlv --bus 4 --addr 0x50)
+;                       ScriptA                                         Remove empty Check History block
+;                       ScriptA/B                                       Disable lldp + config save before traffic (silent MAC)
+;                       ScriptB                                         Add sfputil lpmode off Ethernet513/514
+;   V1.0.5  2026-08-21  config.ttl                                      Add SWB_UNIT0/SWB_UNIT1
+;                       utils/wait_init.ttl                             Follow config.ttl SWB_UNIT0/SWB_UNIT1
+;                       ScriptA/B/C                                     Traffic follows SWB_UNIT: -u 0 / -u 1 / skip
+;   V1.0.6  2026-08-24  utils/show_dmesg.ttl                            Edited dmesg grep i2c & clear event
+;                       ScriptA                                         HW Test Session
+;                       ScriptC                                         HW Test Session Finish
+;                       ScriptA                                         bmc-first-enroll, bmc version/status
+;                       ScriptB                                         Stress test DDR, SSD, USB, BMC DDR, BMC USB Stress test
+;                       ScriptC                                         BMC USB Stress test result
+;                       ScriptA                                         DUT Info
+;                       ScriptAC                                        10G/1G MGMT ping
+;                       ScriptA                                         Edited 100G Port Status
+;                       ScriptA, utils/setup_pmon.ttl                   Add TPM
+;                       ScriptAC                                        NVME Error Info
+;                       ScriptAC                                        Add PCIe Summary
+;   V1.0.7  2026-08-25  config.ttl                                      Add FAN_SPEED
+;                       ScriptA                                         Add Fan Ctrl (max31790 rebind + fan-speed-control.sh)
+;                       ScriptA                                         Clear /host/hw-eval/current/jobs before the run
+;                       ScriptC                                         Copy stress jobs log to USB, timestamped
+;                       utils/wait_init.ttl                             WT_INTERVAL 10 -> 60, fix WT_MIN comments
+;                       ScriptC                                         Disable BMC USB journalctl dump
+;   V1.0.8  2026-08-25  Blanton_Script/bmc_monitor.sh                   Add BMC I2C write/read-back pattern test
+;                       ScriptB                                         Re-enable bmc_monitor.sh start
+;                       ScriptC                                         Re-enable bmc_monitor.sh stop + cat bmc_poll.log
+;                       ScriptC                                         Copy bmc_poll.log + mgmt_ping.log into jobs/ before the USB archive
+;                       Blanton_Script/usb_target.sh                    Created - auto-detect USB device node / mount point
+;                       ScriptB                                         USB stress uses the detected node, not a hard-coded /dev/sda1
+;                       ScriptB                                         DDR memtester runs continuously (drop the 100-pass limit)
+;                       ScriptC                                         Move bgctl reset --yes after the USB archive
+;                       Blanton_Script/mgmt_ping_monitor.sh             V3.0.0 - both NICs ping simultaneously, accumulating
+;                                                                         + ARP warm-up so a stale neighbour entry is not counted as loss
+;                                                                         + stop renders last-N per NIC, stats, and both ip -s link show
+;                       .gitignore                                      Ignore monitor *.raw / *.pid / *.state
+;                       ScriptA                                         MGMT ping baseline 45s -> 30s, clear the log afterwards
+;                       ScriptB                                         Show mgmt_ping status after start
+;                       ScriptC                                         Show mgmt_ping status before stop, cat the report after
+;   V1.0.9  2026-08-26  Blanton_Script/port_prbs_monitor.sh             Add 100G Port PRBS test
+;                                                                         start [both|a|b] - single port isolates a port fault from
+;                                                                         the DUT not coping with two PRBS streams at once
+;                                                                         !! TTL calls are commented out in A/B/C - still under bring-up
+;                       ScriptA/B/C                                     Job log path /host/hw-eval/current/jobs -> /host/hw-eval/jobs
+;                       ScriptC                                         Mount the USB (usb_target.sh) before copying the job logs
+;                       ScriptC                                         Reorder results: stress logs, then MGMT ping, then 100G status
+;   V1.0.10 2026-08-27  ScriptB                                         Monitor loop lists the background jobs every round
+;                                                                         + bgctl list  - platform jobs
+;                                                                         + jobs        - shell jobs of the login shell
+;                                                                         + pause 60    - the loop used to run with no pause at all
+;                       docs/LTC2980_channel_map.csv                    Channel / net / Vnom map built from settings/*.conf
+;                       tools/gen_channel_map.sh                        Regenerates that CSV - the CSV is output, not source
+;                       tools/100G_PRBS.txt                             Bench command references, kept for hand-run debug
+;                       tools/TR518.txt                                 TR518 = built-in packet test (swutil / bcmcmd tr 518)
+;                       tools/fan_ctrl.txt                              MAX31790 rebind + fan-speed-control.sh
+;   V1.0.11 2026-08-28  LTC2980_Margin_Script/margin.sh                 v2.7.0 - margin_save fixes + two new subcommands
+;                                                                         STORE_USER_ALL (0x15) is now a PMBus send-byte, not
+;                                                                         0x15 followed by a dummy 0x00 data byte. The LTC2977
+;                                                                         tolerated the old form, but it was the wrong protocol
+;                                                                         i2c: i2cset .. 0x15 c   swb: cb_pmbus_write <ch> <addr> 0x15
+;                                                                         + margin_save all     - every board in settings/ (9 boards,
+;                                                                           18 chips), then re-init the one loaded beforehand
+;                                                                         + margin_save blanton - Blanton SONiC shortcut: all 18
+;                                                                           LTC2977 straight over the native i2c buses - no
+;                                                                           margin_init, no FPGA channel setup, no pcimem
+;                                                                           F3 Ch6->bus 13, Ch7->14, Ch8->15, Ch9->16
+;                                                                           board list = MARGIN_BLANTON_STORE at the top of margin.sh
+;                                                                         The store result is now checked - a NACK used to still
+;                                                                         print "Change Saved"
+;                                                                         MARGIN_STORE_SETTLE (0.5s) between stores; nothing in this
+;                                                                         tool polls the part's busy bit
+;                       LTC2980_Margin_Script/README.md                 What each margin_save variant sends, and the
+;                                                                         FPGA-channel -> i2c-bus map
+;                       LTC2980_Margin_Script/Ref/*.md                  0x15 trace note corrected to send-byte
+;                       LTC2980_Margin_Script/script/margin_save_all.sh Point at margin_save all; keep it for subsets
+;                       config.ttl                                      FAN_SPEED 30 -> 100 (full speed by default)
 ; =============================================================================
 include "config.ttl"
 
@@ -49,6 +129,76 @@ gettime timestr
 sprintf2 cmd 'sudo date -s "%s %s"' datestr timestr
 sendln cmd
 
+;Stress log clear
+wait prompt_sonic_root
+sendln "rm /host/hw-eval/jobs/*"
+
+; ========== HW Test Session ==========
+wait prompt_sonic_root
+sendln "hw-test-session start"
+wait prompt_sonic_root
+sendln "hw-test-session log"
+wait prompt_sonic_root
+sendln "hw-test-session status"
+
+; ========== FAN SPEED ==========
+wait prompt_sonic_root
+sendln "echo 18-0020 > /sys/bus/i2c/drivers/max31790/unbind"
+wait prompt_sonic_root
+sendln "sleep .5"
+wait prompt_sonic_root
+sendln "echo 18-0020 > /sys/bus/i2c/drivers/max31790/bind"
+wait prompt_sonic_root
+sendln "echo 25-0020 > /sys/bus/i2c/drivers/max31790/unbind"
+wait prompt_sonic_root
+sendln "sleep .5"
+wait prompt_sonic_root
+sendln "echo 25-0020 > /sys/bus/i2c/drivers/max31790/bind"
+
+wait prompt_sonic_root
+sprintf2 fan_ctrl_cmd 'fan-speed-control.sh %d' FAN_SPEED
+sendln fan_ctrl_cmd
+
+wait "Set all configured fan channels to"
+sendln "y"
+
+
+; ========== Wait DUT Init ==========
+include "utils/wait_init.ttl"
+
+; ========== DUT Info ==========
+wait prompt_sonic_root
+sendln "show boot"
+wait prompt_sonic_root
+sendln "show version"
+wait prompt_sonic_root
+sendln "fwutil show status"
+wait prompt_sonic_root
+sendln "show system-memory"
+wait prompt_sonic_root
+sendln "show service"
+wait prompt_sonic_root
+sendln "show platform syseeprom"
+wait prompt_sonic_root
+sendln "show platform ssdhealth"
+wait prompt_sonic_root
+sendln "qfx5252-tpm-version"
+wait prompt_sonic_root
+sendln "/usr/sbin/nvme smart-log -H /dev/nvme0"
+wait prompt_sonic_root
+sendln "/usr/sbin/smartctl -x /dev/nvme0"
+
+; ========== BMC version ==========
+;wait prompt_sonic_root
+;sendln "bmc-manager run 'cat /etc/issue'"
+wait prompt_sonic_root
+sendln "bmc-first-enroll"
+wait prompt_sonic_root
+sendln "bmc-manager version"
+wait prompt_sonic_root
+sendln "bmc-manager status"
+
+
 ; ========== Load Shell Script ==========
 wait prompt_sonic_root
 sendln "source ~/Blanton_Script/blanton_fpga_pcimem.sh"
@@ -72,14 +222,13 @@ include "utils/show_pcie_error_reg_DDR.ttl"
 include "utils/show_pcie_error_reg_I210.ttl"
 include "utils/show_pcie_error_reg_SSD.ttl"
 
+wait prompt_sonic_root
+sendln "/usr/sbin/ras-mc-ctl --summary"
+
 
 ; ========== Check PCIE tree + PCIE link status + GET PCIE bandwidth Test ==========
 include "utils/pcie_bus.ttl"
 
-; ========== Check History ==========
-    ;wait prompt_sonic_root
-    ;sendln "command"
-
 ; ========== Check Margin ==========
 if EN_Margin = 1 then
     include "utils/show_margin_status.ttl"
@@ -88,16 +237,135 @@ endif
 ; ========== TAKE DATA ==========
 include "utils/setup_pmon.ttl"
 include "utils/show_dmesg.ttl"
-wait prompt_sonic_root
 
 ;include "utils/xxx.ttl"
 ;wait prompt_sonic_root
 ;flushrecv
 
-; ========== TRAFFIC-SETUP-STAGE ==========
+; ========== 10G/1G MGMT Ping Test ==========
-    ;sendln "command"
+wait prompt_sonic_root
+sendln "./Blanton_Script/mgmt_ping_monitor.sh start"
+wait prompt_sonic_root
+pause 30
+sendln "~/Blanton_Script/mgmt_ping_monitor.sh stop"
+wait prompt_sonic_root
+sendln "cat ~/Blanton_Script/log/mgmt_ping.log"
+wait prompt_sonic_root
+sendln "~/Blanton_Script/mgmt_ping_monitor.sh clear"
+
+
+; ========== 100G Port Status ==========
+wait prompt_sonic_root
+sendln "sudo sfputil lpmode off Ethernet513"
+wait prompt_sonic_root
+sendln "sudo sfputil lpmode off Ethernet514"
+wait prompt_sonic_root
+sendln "config interface -n asic0 startup  Ethernet513"
+wait prompt_sonic_root
+sendln "config interface -n asic1 startup  Ethernet514"
+wait prompt_sonic_root
+sendln "config save -y"
+
+wait prompt_sonic_root
+sendln "show interfaces status Ethernet513,Ethernet514"
+
+;=============================================================================================================
+; ========== 100G PRBS ==========
+;wait prompt_sonic_root
+;sendln "~/Blanton_Script/port_prbs_monitor.sh start"
+;wait prompt_sonic_root
+;sendln "sleep 10"
+;wait prompt_sonic_root
+;sendln "~/Blanton_Script/port_prbs_monitor.sh status"
+;wait prompt_sonic_root
+;sendln "~/Blanton_Script/port_prbs_monitor.sh stop"
+;wait prompt_sonic_root
+;sendln "~/Blanton_Script/port_prbs_monitor.sh report"
+;wait prompt_sonic_root
+;sendln "~/Blanton_Script/port_prbs_monitor.sh clear"
+
+; ========== 100G Port Status ==========
+;wait prompt_sonic_root
+;sendln "sudo sfputil lpmode off Ethernet513"
+;wait prompt_sonic_root
+;sendln "sudo sfputil lpmode off Ethernet514"
+;wait prompt_sonic_root
+;sendln "config interface -n asic0 startup  Ethernet513"
+;wait prompt_sonic_root
+;sendln "config interface -n asic1 startup  Ethernet514"
+;wait prompt_sonic_root
+;sendln "config save -y"
+
+;wait prompt_sonic_root
+;sendln "show interfaces status Ethernet513,Ethernet514"
+;=============================================================================================================
+
+; ========== First Traffic Test ==========
+; Silent MAC
+wait prompt_sonic_root
+sendln "config feature state lldp disabled"
+wait prompt_sonic_root
+sendln "config save -y"
+
+if SWB_UNIT0 = 1 && SWB_UNIT1 = 1 then
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed ps"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed init"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed clear"
+    wait prompt_sonic_root
+    pause 15
+    sendln "blanton_traffic_linespeed show"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed start"
+    wait prompt_sonic_root
+    pause 15
+    sendln "blanton_traffic_linespeed stop"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed report"
+elseif SWB_UNIT0 = 1 && SWB_UNIT1 = 0 then
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed ps -u 0"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed init -u 0"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed clear -u 0"
+    wait prompt_sonic_root
+    pause 15
+    sendln "blanton_traffic_linespeed show -u 0"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed start -u 0"
+    wait prompt_sonic_root
+    pause 15
+    sendln "blanton_traffic_linespeed stop -u 0"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed report -u 0"
+elseif SWB_UNIT0 = 0 && SWB_UNIT1 = 1 then
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed ps -u 1"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed init -u 1"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed clear -u 1"
+    wait prompt_sonic_root
+    pause 15
+    sendln "blanton_traffic_linespeed show -u 1"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed start -u 1"
+    wait prompt_sonic_root
+    pause 15
+    sendln "blanton_traffic_linespeed stop -u 1"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed report -u 1"
+else
+
+endif
+
+; ========== Show Power on uptime ==========
+wait prompt_sonic_root
+sendln "show uptime"
 
 
-sendln ""
 wait prompt_sonic_root
 messagebox 'Start Script B' 'Script A DONE'

src/Script_ABC_Blanton/2_Blanton_Script_B.ttl

@@ -20,33 +20,118 @@ sendln 'chmod +x ~/hammer/tools/amd/mlucas-avx2'
 wait prompt_sonic_root
 sendln "~/hammer/tools/amd/mlucas-avx2 -s l -cpu 0:15 > ~/hammer/tools/amd/mlucas_amm_log 2>&1 &"
 
+; ========== BMC DDR Stress Test ==========
+;wait prompt_sonic_root
+;sendln "./Blanton_Script/bmc_monitor_ddr.sh start"
+;wait prompt_sonic_root
+;sendln "./Blanton_Script/bmc_monitor.sh start"
+wait prompt_sonic_root
+sendln "bgctl run bmc-manager run '/usr/bin/memtester 64M 1'"
+
+; ========== BMC Monitor Test ==========
+wait prompt_sonic_root
+sendln "./Blanton_Script/bmc_monitor.sh start"
+
 ; ========== DDR MEMORY STRESS TEST ==========
+;wait prompt_sonic_root
+;sendln "bgctl run /usr/sbin/memtester 1G 100"
 wait prompt_sonic_root
-sendln "python ~/hammer/tools/stress_mem.py &"
+sendln "bgctl run /usr/sbin/memtester 1G"   ; Continue Execture
-wait prompt_sonic_root
-sendln "python ~/hammer/tools/stress_mem.py &"
-wait prompt_sonic_root
-sendln "python ~/hammer/tools/stress_mem.py &"
-wait prompt_sonic_root
-sendln "python ~/hammer/tools/stress_mem.py &"
-wait prompt_sonic_root
-sendln "python ~/hammer/tools/stress_mem.py &"
 
 ; ========== SSD read/write ==========
 wait prompt_sonic_root
-sendln "python ~/hammer/tools/stress_ssd.py &"
+sendln "bgctl run qfx5252-stress-ssd 1G --runtime 3600 --passes 5 --write --force --log /host/hw-eval/jobs/qfx5252-stress-ssd.log"
 
 ; ========== USB read/write ==========
+; ---- Get USB partition node -> usb_dev ----
+usb_dev = ''
 wait prompt_sonic_root
-sendln "python ~/hammer/tools/stress_usb.py &"
+sendln 'D=$(bash ~/Blanton_Script/usb_target.sh -o dev 2>/dev/null); echo "<<D""EV=${D:-NONE}>>"'
+waitregex '<<DEV=([^>]*)>>'
+usb_dev = groupmatchstr1
+
+wait prompt_sonic_root
+sprintf2 cmd "bgctl run qfx5252-stress-usb %s 256M --runtime 60 --passes 1 --write --log /host/hw-eval/jobs/qfx5252-stress-usb.log" usb_dev
+sendln cmd
+
+;wait prompt_sonic_root
+;sendln "bgctl run qfx5252-stress-usb /dev/sda1 256M --runtime 60 --passes 1 --write --log /host/hw-eval/qfx5252-stress-usb.log"
 
 ; ========== SHOW Background job ==========
 wait prompt_sonic_root
 sendln "jobs"
+wait prompt_sonic_root
+sendln "bgctl list"
+
+; ========== BMC USB Test ==========
+wait prompt_sonic_root
+sendln 'echo "NCMIF=$(ls -d /sys/bus/usb/drivers/cdc_ncm/*/net/* 2>/dev/null | head -n 1 | xargs -r basename)"'
+timeout = 15
+waitregex 'NCMIF=[A-Za-z0-9_-]+'
+if result = 0 then
+    messagebox 'cdc_ncm interface not found. Ping test skipped.' 'ERROR'
+    goto skip_ping
+endif
+strlen matchstr
+cut_len = result - 6                    ; 'NCMIF=' = 6 chars
+strcopy matchstr 7 cut_len ncm_if       ; -> ncm_if = "eth2" / "eth3"
+
+sprintf2 cmd 'ip -br link show %s' ncm_if
+wait prompt_sonic_root
+sendln cmd
+
+wait prompt_sonic_root
+sendln 'systemctl stop qfx5252-bmc-usb-net-test.service 2>/dev/null || true'
+wait prompt_sonic_root
+sendln 'systemctl reset-failed qfx5252-bmc-usb-net-test.service 2>/dev/null || true'
+sprintf2 cmd 'systemd-run --unit=qfx5252-bmc-usb-net-test --property=Type=exec /usr/bin/ping -I %s -i 1 -W 2 -w 14400 192.168.200.200' ncm_if
+wait prompt_sonic_root
+sendln cmd
+
+:skip_ping
+; restore the default (no cap): the traffic init below walks 108 VLANs per
+; unit and takes far longer than the 15 s set for the NCM probe above.
+timeout = 0
+
+; ========== 10G/1G MGMT Ping Test ==========
+wait prompt_sonic_root
+sendln "./Blanton_Script/mgmt_ping_monitor.sh start"
+wait prompt_sonic_root
+pause 3
+sendln "./Blanton_Script/mgmt_ping_monitor.sh status"
+
+
+; ========== 100G Port ==========
+wait prompt_sonic_root
+sendln "show interfaces status Ethernet513,Ethernet514"
+
+;=============================================================================================================
+; ========== 100G PRBS ==========
+;wait prompt_sonic_root
+;sendln "~/Blanton_Script/port_prbs_monitor.sh start"
+;=============================================================================================================
 
-; ========== Take one round of eye measurement on uplink ports ==========
 
 ; ========== Traffic START ==========
+; Silent MAC
+wait prompt_sonic_root
+sendln "config feature state lldp disabled"
+wait prompt_sonic_root
+sendln "config save -y"
+
+if SWB_UNIT0 = 1 && SWB_UNIT1 = 1 then
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed ps"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed init"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed clear"
+    wait prompt_sonic_root
+    pause 15
+    sendln "blanton_traffic_linespeed show"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed start"
+elseif SWB_UNIT0 = 1 && SWB_UNIT1 = 0 then
     wait prompt_sonic_root
     sendln "blanton_traffic_linespeed ps -u 0"
     wait prompt_sonic_root
@@ -54,18 +139,38 @@ sendln "blanton_traffic_linespeed init -u 0"
     wait prompt_sonic_root
     sendln "blanton_traffic_linespeed clear -u 0"
     wait prompt_sonic_root
-pause 3
+    pause 15
     sendln "blanton_traffic_linespeed show -u 0"
     wait prompt_sonic_root
     sendln "blanton_traffic_linespeed start -u 0"
+elseif SWB_UNIT0 = 0 && SWB_UNIT1 = 1 then
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed ps -u 1"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed init -u 1"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed clear -u 1"
+    wait prompt_sonic_root
+    pause 15
+    sendln "blanton_traffic_linespeed show -u 1"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed start -u 1"
+else
+
+endif
 
 
 
-; ========== Get data every 10mins ==========
+; ========== Monitor loop: platform data + background jobs (pause 60s per round) ==========
 while 1
     include "utils/setup_pmon.ttl"
+    wait prompt_sonic_root
+    sendln "bgctl list"
+    wait prompt_sonic_root
+    sendln "jobs"
     ; ========== Check Margin ==========
     if EN_Margin = 1 then
         include "utils/show_margin_status.ttl"
     endif
+    pause 60
 endwhile

src/Script_ABC_Blanton/3_Blanton_Script_C.ttl

@@ -12,6 +12,37 @@ pause 1
 
 ; ========== Kill Process ==========
 include "utils/kill_all_process.ttl"
+; bgctrl all stop
+wait prompt_sonic_root
+sendln "bgctl stop --all"
+wait prompt_sonic_root
+sendln "bgctl stop --all"
+; BMC USB Test STOP
+wait prompt_sonic_root
+sendln "systemctl stop qfx5252-bmc-usb-net-test.service"
+; 10G/1G MGMT Test STOP
+wait prompt_sonic_root
+sendln "~/Blanton_Script/mgmt_ping_monitor.sh status"
+wait prompt_sonic_root
+sendln "~/Blanton_Script/mgmt_ping_monitor.sh stop"
+
+;=============================================================================================================
+; 100G PRBS STOP
+;wait prompt_sonic_root
+;sendln "~/Blanton_Script/port_prbs_monitor.sh stop"
+;wait prompt_sonic_root
+;sendln "sudo sfputil lpmode off Ethernet513"
+;wait prompt_sonic_root
+;sendln "sudo sfputil lpmode off Ethernet514"
+;wait prompt_sonic_root
+;sendln "config interface -n asic0 startup  Ethernet513"
+;wait prompt_sonic_root
+;sendln "config interface -n asic1 startup  Ethernet514"
+;=============================================================================================================
+
+
+
+
 ; ========== TAKE DATA ==========
 include "utils/setup_pmon.ttl"
 include "utils/show_dmesg.ttl"
@@ -25,17 +56,115 @@ include "utils/show_pcie_error_reg_DDR.ttl"
 include "utils/show_pcie_error_reg_I210.ttl"
 include "utils/show_pcie_error_reg_SSD.ttl"
 
+wait prompt_sonic_root
+sendln "/usr/sbin/ras-mc-ctl --summary"
+
+; ========== BMC DDR TAKE DATA ==========
+;wait prompt_sonic_root
+;sendln "./Blanton_Script/bmc_monitor_ddr.sh stop"
+;wait prompt_sonic_root
+;sendln "./Blanton_Script/bmc_monitor.sh stop"
+;wait prompt_sonic_root
+;sendln "cat ./Blanton_Script/log/bmc_poll.log"
+;wait prompt_sonic_root
+;sendln "cat ./Blanton_Script/log/bmc_ddr.log"
+
+; ========== BMC Monitor TAKE DATA ==========
+wait prompt_sonic_root
+sendln "./Blanton_Script/bmc_monitor.sh stop"
+wait prompt_sonic_root
+sendln "cat ./Blanton_Script/log/bmc_poll.log"
+
+; ========== BMC USB Test result ==========
+;wait prompt_sonic_root
+;sendln "journalctl -u qfx5252-bmc-usb-net-test.service --no-pager"
+
+
 ; ========== CHECK Stress results ==========
 wait prompt_sonic_root
 sendln "cat ~/hammer/tools/amd/mlucas_amm_log"
 wait prompt_sonic_root
-sendln "cat ~/hammer/tools/log.stress_ssd"
+sendln "cat /host/hw-eval/jobs/qfx5252-stress-ssd.log"
+wait prompt_sonic_root
+sendln "cat /host/hw-eval/jobs/qfx5252-stress-usb.log"
+
+; ========== 10G/1G MGMT Test result ==========
+wait prompt_sonic_root
+sendln "cat ~/Blanton_Script/log/mgmt_ping.log"
+
+; ========== 100G Port ==========
+wait prompt_sonic_root
+sendln "show interfaces status Ethernet513,Ethernet514"
+;=============================================================================================================
+;wait prompt_sonic_root
+;sendln "cat ~/Blanton_Script/log/port_prbs.log "
+;=============================================================================================================
 
 ; ========== CHECK Traffic counters ==========
+if SWB_UNIT0 = 1 && SWB_UNIT1 = 1 then
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed stop"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed report"
+elseif SWB_UNIT0 = 1 && SWB_UNIT1 = 0 then
     wait prompt_sonic_root
     sendln "blanton_traffic_linespeed stop -u 0"
     wait prompt_sonic_root
     sendln "blanton_traffic_linespeed report -u 0"
+elseif SWB_UNIT0 = 0 && SWB_UNIT1 = 1 then
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed stop -u 1"
+    wait prompt_sonic_root
+    sendln "blanton_traffic_linespeed report -u 1"
+else
 
+endif
+
+; ========== NVME Err Info ==========
+wait prompt_sonic_root
+sendln "/usr/sbin/nvme smart-log -H /dev/nvme0"
+wait prompt_sonic_root
+sendln "/usr/sbin/smartctl -x /dev/nvme0"
+
+
+wait prompt_sonic_root
+sendln "show reboot-cause"
+
+; ========== Show Power on uptime ==========
+wait prompt_sonic_root
+sendln "show uptime"
+
+
+; ---- Get USB partition node -> usb_dev ----
+usb_dev = ''
+wait prompt_sonic_root
+sendln 'D=$(bash ~/Blanton_Script/usb_target.sh -o dev 2>/dev/null); echo "<<D""EV=${D:-NONE}>>"'
+waitregex '<<DEV=([^>]*)>>'
+usb_dev = groupmatchstr1
+
+wait prompt_sonic_root
+sendln "sync"
+wait prompt_sonic_root
+sprintf2 cmd "mount %s /mnt/usb" usb_dev
+sendln cmd
+
+; ========== Copy Stress Log to USB ==========
+wait prompt_sonic_root
+sendln "cp ./Blanton_Script/log/bmc_poll.log /host/hw-eval/jobs/"
+wait prompt_sonic_root
+sendln "cp ./Blanton_Script/log/mgmt_ping.log /host/hw-eval/jobs/"
+
+wait prompt_sonic_root
+getdate ts_date "%Y%m%d"
+gettime ts_time "%H%M"
+sprintf2 usb_dst "/mnt/usb/jobs-%s_%s" ts_date ts_time
+sprintf2 cmd "cp -r /host/hw-eval/jobs/ %s" usb_dst
+sendln cmd
+
+; ========== HW Test Session ==========
+wait prompt_sonic_root
+sendln "hw-test-session finish"
+wait prompt_sonic_root
+sendln "bgctl reset --yes"
 
 messagebox 'GOOD JOB! Test Case DONE' 'teraterm'

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/README.md

@@ -14,6 +14,8 @@
 | `margin_operation <ch> <op>` | 只切 OPERATION register |
 | `margin_apply_profile <file>` | 批次套用 profile（套用在當前載入的 LTC2980） |
 | `margin_save` | 寫入 NVM（當前 LTC2980 的兩個 LTC2977 都寫） |
+| `margin_save all` | 對 `settings/` 底下**全部** LTC2980 寫入 NVM，結束後回到原本載入的那顆 |
+| `margin_save blanton` | **Blanton SONiC 專用**：18 顆 LTC2977 全部走原生 i2c bus 寫入，不需要 `margin_init` |
 | `margin_debug [on\|off]` | 開關 debug 模式（不帶參數則 toggle） |
 | `margin_log [on\|off]` | 開關 log 記錄（不帶參數則 toggle，預設開啟） |
 
@@ -79,7 +81,9 @@ margin_init Blanton_SWB1_CONN16
 margin_apply_profile profiles/comboA.conf
 
 # 儲存到 NVM（斷電後保留）
-margin_save
+margin_save            # 只寫當前載入的那顆
+margin_save all        # settings/ 底下 9 顆全部寫，最後自動切回原本那顆
+margin_save blanton    # Blanton SONiC 專用捷徑，18 顆一次寫完（見下）
 ```
 
 ## 一次掃所有 LTC2980
@@ -131,16 +135,87 @@ PROFILES=(
 
 ## 一次把所有 LTC2980 寫入 NVM
 
-`script/margin_save_all.sh` 對 `BOARDS` 列出的每顆 LTC2980 跑 `margin_save`。
-
 > ⚠️  `margin_save` 會把當前 margin / OV / UV 設定**永久寫入 NVM**，
 > 斷電後保留。執行前先用 `margin_status_all.sh` 確認狀態正確。
 
+**全部 9 顆**直接用內建的：
+
+```bash
+margin_save all
+```
+
+依 `settings/*.conf` 的檔名順序跑，中途某顆失敗**不會停**（半套完成的狀態比全部試完更難查），
+最後印出「幾顆成功 / 哪幾顆失敗」的總結，並把 `margin_init` 切回你呼叫前載入的那顆。
+
+**只寫其中幾顆**才需要 `script/margin_save_all.sh`，編 script 頂端的 `BOARDS` 陣列：
+
 ```bash
 source script/margin_save_all.sh
 ```
 
-要改寫哪幾顆，編 script 頂端的 `BOARDS` 陣列即可（同前述）。
+### 送出去的是什麼
+
+`margin_save` 對每顆 LTC2977 送一次 `STORE_USER_ALL`（PMBus command `0x15`），
+**不分 page**（這是整顆晶片的命令），也**不帶 data byte** —— 它是 SMBus send-byte：
+
+```bash
+i2cset -y 4 0x5C 0x15 c            # CB CONN13（原生 bus 4）
+cb_pmbus_write 8 0x5C 0x15         # SWB0 CONN13（CB FPGA F3 Ch8）
+```
+
+> v2.7.0 之前送的是 `0x15 0x00`（write-byte）。LTC2977 在 CB 上吃得下去，但那是零件寬容，
+> 不是規範。同時 v2.7.0 起會檢查回傳值 —— 以前 NACK 了還是印 `Change Saved`。
+
+每顆之間會 `sleep $MARGIN_STORE_SETTLE`（預設 0.5 秒）。這不是量測值，是保守的保護：
+NVM 寫入需要時間，而這支工具**沒有**去 poll 零件的 busy bit。`margin_save all` 連續送 18 次，
+這個間隔就是唯一的緩衝。要關掉設成空字串即可。
+
+## `margin_save blanton` — Blanton SONiC 專用
+
+Blanton 這台把 CB FPGA F3 的 I2C 通道**同時掛成了原生 Linux i2c adapter**，
+所以 SWB 上的 LTC2977 不必走 `cb_pmbus_*` / pcimem，用 `i2cset` 直接打得到：
+
+| FPGA F3 通道 | Linux bus | 板 / 接頭 |
+|---|---|---|
+| Ch6 | 13 | SWB0 CONN14 / CONN16 |
+| Ch8 | 15 | SWB0 CONN13 / CONN15 |
+| Ch7 | 14 | SWB1 CONN14 / CONN16 |
+| Ch9 | 16 | SWB1 CONN13 / CONN15 |
+| —（原生） | 4 | CB CONN13 |
+
+因此 `margin_save blanton` 就是一張平表跑完 18 顆，**不需要 `margin_init`**、
+不做 FPGA 通道初始化、不做 probe，也不會動到你當前載入的那顆板子：
+
+```bash
+margin_save blanton
+```
+
+```
+  CB   CONN13  bus 4  0x5C : saved
+  SWB0 CONN13  bus 15 0x5C : saved
+  ...
+margin_save blanton: 18 saved, 0 failed
+```
+
+送出去的就是這 18 行（2026-08-27 上機驗證）：
+
+```bash
+i2cset -f -y 4  0x5C 0x15   ;  i2cset -f -y 4  0x5E 0x15    # CB   CONN13
+i2cset -f -y 15 0x5C 0x15   ;  i2cset -f -y 15 0x5E 0x15    # SWB0 CONN13
+i2cset -f -y 13 0x5C 0x15   ;  i2cset -f -y 13 0x5E 0x15    # SWB0 CONN14
+i2cset -f -y 15 0x62 0x15   ;  i2cset -f -y 15 0x64 0x15    # SWB0 CONN15
+i2cset -f -y 13 0x62 0x15   ;  i2cset -f -y 13 0x64 0x15    # SWB0 CONN16
+i2cset -f -y 16 0x5C 0x15   ;  i2cset -f -y 16 0x5E 0x15    # SWB1 CONN13
+i2cset -f -y 14 0x5C 0x15   ;  i2cset -f -y 14 0x5E 0x15    # SWB1 CONN14
+i2cset -f -y 16 0x62 0x15   ;  i2cset -f -y 16 0x64 0x15    # SWB1 CONN15
+i2cset -f -y 14 0x62 0x15   ;  i2cset -f -y 14 0x64 0x15    # SWB1 CONN16
+```
+
+`-f` 是因為這些 bus 上的 LTC2977 可能已被 kernel driver 認走；上機驗證過的指令帶 `-f`，就照原樣保留。
+
+**這台沒裝滿的話**，把 `margin.sh` 頂端 `MARGIN_BLANTON_STORE` 陣列裡對應的行註解掉即可，
+不要讓它去打不存在的板子。bus 節點不存在（`/dev/i2c-N` 沒有）與晶片不回應（NACK）
+會分別報不同訊息 —— 前者代表 FPGA 的 i2c adapter 根本沒 enumerate，後者才是板子的問題。
 
 ## Operation 對應
 

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/Ref/margin_command_trace.md

@@ -1,5 +1,27 @@
 # margin.sh 實際下線指令追蹤 (Command Trace)
 
+> ## ⚠️ 過期警告(2026-08-19)
+>
+> **本文件第 5~7 章的 SWB 指令追蹤已與現況不符,請勿照抄。**
+> 上機驗證後 SWB 的 channel 配對與 LTC2977 位址都改了(commit `ababb2c`),
+> 但本文件的 1223 條 `cb_pmbus_*` 指令是當時依舊值展開的,其中 487 條用到
+> 已不存在的位址(`0x5D` / `0x5F` / `0x63` / `0x65`)。
+>
+> **正解以 `settings/*.conf` 為準:**
+>
+> | Channel | 板/接頭 | LTC2977 位址 |
+> |---|---|---|
+> | Ch6 | SWB0 CONN14 / CONN16 | CONN14 `0x5C`,`0x5E` ; CONN16 `0x62`,`0x64` |
+> | Ch8 | SWB0 CONN13 / CONN15 | CONN13 `0x5C`,`0x5E` ; CONN15 `0x62`,`0x64` |
+> | Ch7 | SWB1 CONN14 / CONN16 | CONN14 `0x5C`,`0x5E` ; CONN16 `0x62`,`0x64` |
+> | Ch9 | SWB1 CONN13 / CONN15 | CONN13 `0x5C`,`0x5E` ; CONN15 `0x62`,`0x64` |
+>
+> 位址在同一顆 LTC2980 內是 **+2** 遞增(7-bit,由規格書 8-bit 配對除以 2 而來),
+> 不是舊文件寫的 +1。原先記錄的 Ch6 上 `0x5E` 相撞問題已隨這次修正消失。
+>
+> 第 1~4 章(CB / i2c 路徑、暫存器語意、LINEAR16 換算)不受影響,仍然有效。
+> 需要正確的 SWB 指令追蹤請重新產生本文件。
+
 對象:`LTC2980_Margin_Script/margin.sh` v2.6.0
 產生日期:2026-08-18
 用途:紀錄每個 margin 指令在 I2C / PMBus 線上真正下了什麼,方便對照 log、
@@ -402,8 +424,9 @@ SWB debug 指令(margin.sh v2.6.0 新增,皆為 `blanton_cb_i2c.sh` 的薄包裝
   `Blanton_SWB0_CONN14.conf` 的第一顆也是 `0:0x5E`。兩個 CONN 現在同在 Ch6,
   位址相撞。對照 SWB1 的規律(CONN13=`0x5C/0x5D`、CONN14=`0x5E/0x5F`),
   SWB0_CONN13 第二顆推測應為 `0:0x5D` — **尚未修改,待硬體確認**。
-- `margin_save` 走 `0x15` + data byte(`i2cset ... 0x15 0x00 b`)。PMBus 規範
+- `margin_save` 走 `0x15` **send-byte**(`i2cset ... 0x15 c` / `cb_pmbus_write <ch> <addr> 0x15`),
-  STORE_USER_ALL 是 send-byte;CB 上實測可用故保留原樣,swb 路徑沿用同一寫法。
+  不帶 data byte。v2.7.0 之前送的是 `0x15 0x00`(write-byte),CB 上實測可用,
+  但那是零件寬容而非規範。
 
 ---
 

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/margin.sh

@@ -5,6 +5,24 @@
 # =============================================================================
 # Version Control
 # -----------------------------------------------------------------------------
+# v2.7.0  margin_save fixes and batching:
+#           * STORE_USER_ALL (0x15) is now issued as an SMBus send-byte instead
+#             of a write-byte with a dummy 0x00 data byte. The LTC2977 accepted
+#             the old form on CB, but it was the wrong protocol.
+#             i2c path: i2cset ... 0x15 c   swb path: cb_pmbus_write ch addr 0x15
+#           * margin_save all -- STORE_USER_ALL on every board in settings/,
+#             then re-init whichever board was loaded beforehand. Does not stop
+#             on the first failure; prints a per-board summary at the end.
+#           * The store result is now checked. It used to be discarded, so a
+#             NACK still printed "Change Saved".
+#           * MARGIN_STORE_SETTLE (default 0.5s) between stores - nothing polls
+#             the part's busy bit, and `all` issues 18 of them in a row.
+#           * margin_save blanton -- Blanton SONiC shortcut. On this platform the
+#             CB FPGA F3 I2C channels also appear as native Linux i2c adapters
+#             (Ch6->bus 13, Ch7->14, Ch8->15, Ch9->16), so all 18 LTC2977 can be
+#             stored with plain i2cset: no margin_init, no FPGA channel setup,
+#             no pcimem. Bench-verified on the DUT 2026-08-27. The board list is
+#             MARGIN_BLANTON_STORE at the top of this file.
 # v2.6.0  SWB path actually wired to the shared CB I2C package. blanton_cb_i2c.sh
 #         and blanton_fpga_pcimem.sh live in the PARENT dir (Blanton_Script/), not
 #         next to margin.sh, so the backend is now searched in both places.
@@ -17,8 +35,8 @@
 #           * DEBUG_MODE collision fix: blanton_fpga_pcimem.sh uses the same var
 #             name, so pcimem tracing is gated by MARGIN_SWB_PCIMEM_DEBUG
 #           * margin_swb_* wrappers (info/probe/scan/reset/sem) for debugging
-#         Physical map: CB F3 Ch6=SWB0 CONN13/14, Ch8=SWB0 CONN15/16,
+#         Physical map: CB F3 Ch6=SWB0 CONN14/16, Ch8=SWB0 CONN13/15,
-#                       Ch7=SWB1 CONN13/14, Ch9=SWB1 CONN15/16
+#                       Ch7=SWB1 CONN14/16, Ch9=SWB1 CONN13/15
 # v2.5.0  SWB margin support via a per-conf TRANSPORT layer. The SWB margin
 #         boards are ALSO LTC2980 (2x LTC2977) -- same chip as CB -- just reached
 #         through the CB FPGA F3 I2C master instead of a native bus. So the whole
@@ -72,10 +90,10 @@ CB_I2C_CH=""
 # --- SWB transport backend (blanton_cb_i2c.sh + blanton_fpga_pcimem.sh) -------
 # The SWB margin boards' LTC2980s hang off the CB FPGA Function 3 I2C master.
 # Physical mapping (per bench wiring):
-#   CB F3 Ch6 -> SWB0 CONN13 / CONN14
+#   CB F3 Ch6 -> SWB0 CONN14 / CONN16
-#   CB F3 Ch8 -> SWB0 CONN15 / CONN16
+#   CB F3 Ch8 -> SWB0 CONN13 / CONN15
-#   CB F3 Ch7 -> SWB1 CONN13 / CONN14
+#   CB F3 Ch7 -> SWB1 CONN14 / CONN16
-#   CB F3 Ch9 -> SWB1 CONN15 / CONN16
+#   CB F3 Ch9 -> SWB1 CONN13 / CONN15
 # Two CONNs share one FPGA I2C channel, so the two boards on a channel MUST use
 # different LTC2977 slave addresses (the CHIPS array in each .conf).
 MARGIN_SWB_CHANNELS="${MARGIN_SWB_CHANNELS:-6 7 8 9}"
@@ -115,6 +133,45 @@ ONOFF_ENABLE_VALUE="0x1a"   # controlled_on=1, use_pmbus=1, use_control=0, b1=1
 # margin_status after all channels are set. Bump this if you want margin_set's own
 # read-back to reflect the settled value.
 MARGIN_SETTLE="0.3"
+# Pause after each STORE_USER_ALL. The LTC2977 is busy committing NVM once the
+# command lands and nothing here polls a busy bit, so this is a plain guard
+# rather than a measured value - it matters most for `margin_save all`, which
+# fires 18 stores back to back. Set to "" to disable.
+MARGIN_STORE_SETTLE="${MARGIN_STORE_SETTLE:-0.5}"
+
+# --- `margin_save blanton`: the bench-verified Blanton SONiC store list -------
+# On this platform the CB FPGA F3 I2C channels are ALSO exposed as native Linux
+# i2c adapters, so every LTC2977 - CB and SWB alike - can be reached with plain
+# i2cset. That path needs no FPGA channel setup, no pcimem, and no margin_init:
+# one flat list, 18 commands, done. Verified on the DUT 2026-08-27.
+#
+#   FPGA F3 channel -> Linux bus:  Ch6->13  Ch7->14  Ch8->15  Ch9->16
+#
+# Entry format: "bus:addr:label". Comment out the lines for boards this DUT does
+# not have rather than letting them fail - a single-SWB unit is a normal build.
+MARGIN_BLANTON_STORE=(
+    "4:0x5C:CB   CONN13"
+    "4:0x5E:CB   CONN13"
+    "15:0x5C:SWB0 CONN13"
+    "15:0x5E:SWB0 CONN13"
+    "13:0x5C:SWB0 CONN14"
+    "13:0x5E:SWB0 CONN14"
+    "15:0x62:SWB0 CONN15"
+    "15:0x64:SWB0 CONN15"
+    "13:0x62:SWB0 CONN16"
+    "13:0x64:SWB0 CONN16"
+    "16:0x5C:SWB1 CONN13"
+    "16:0x5E:SWB1 CONN13"
+    "14:0x5C:SWB1 CONN14"
+    "14:0x5E:SWB1 CONN14"
+    "16:0x62:SWB1 CONN15"
+    "16:0x64:SWB1 CONN15"
+    "14:0x62:SWB1 CONN16"
+    "14:0x64:SWB1 CONN16"
+)
+# -f because the LTC2977s may be claimed by a kernel driver on these buses; the
+# command that was verified on the bench carries it, so it stays.
+MARGIN_BLANTON_I2CSET_FLAGS="${MARGIN_BLANTON_I2CSET_FLAGS:--f -y}"
 _BUS=""
 _ADDR=""
 _PRE_SCOPE=""   # set while inside a PRE/POST wrapped operation; prevents nested re-entry
@@ -257,6 +314,20 @@ _swb_write() {
     return 0
 }
 
+# _swb_send <cmd>  -> cb_pmbus_write with NO data byte (SMBus send-byte).
+# cb_pmbus_write routes a no-data call to _cbi2c_xfer_cmd_only: START, slave+W,
+# command byte, STOP. That is what STORE_USER_ALL expects.
+_swb_send() {
+    local reg=$1
+    [ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] cb_pmbus_write $CB_I2C_CH $_ADDR $reg (send-byte)\033[0m"
+    if ! _swb_call cb_pmbus_write "$CB_I2C_CH" "$_ADDR" "$reg" >/dev/null 2>&1; then
+        echo -e "[\033[31mERRO\033[0m] cb_pmbus_write ch=$CB_I2C_CH $_ADDR reg=$reg (send-byte) failed (NACK/timeout)" >&2
+        _log_detail "ERRO cb_pmbus_write ch=$CB_I2C_CH $_ADDR $reg send-byte"
+        return 1
+    fi
+    return 0
+}
+
 # _swb_read_word <reg>  -> echoes "0xXXXX" parsed out of cb_pmbus_read's "=> 0xXXXX"
 _swb_read_word() {
     local reg=$1 out word
@@ -520,6 +591,20 @@ _i2c_write_byte() {
     i2cset -y "$_BUS" "$_ADDR" "$1" "$2" b >/dev/null 2>&1
 }
 
+# Send a PMBus command with NO data byte (SMBus send-byte).
+# STORE_USER_ALL (0x15) and its relatives are send-byte commands: the command
+# byte alone triggers them. Appending a dummy 0x00 makes it a write-byte, which
+# is a different SMBus protocol - the LTC2977 happened to accept it, but that is
+# tolerance, not correctness. i2cset's "c" mode is the send-byte form.
+_i2c_send_byte() {
+    if [ "$TRANSPORT" = "swb" ]; then
+        _swb_send "$1"
+        return
+    fi
+    [ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] i2cset -y $_BUS $_ADDR $1 c\033[0m"
+    i2cset -y "$_BUS" "$_ADDR" "$1" c >/dev/null 2>&1
+}
+
 # Read a 16-bit word; echoes "0xXXXX". For swb, parse cb_pmbus_read's "=> 0xXXXX".
 _i2c_read_word() {
     if [ "$TRANSPORT" = "swb" ]; then
@@ -730,20 +815,171 @@ margin_apply_profile() {
 }
 
 # --- Save to NVM ---
+# margin_save          -- STORE_USER_ALL on the currently initialised board
+# margin_save all      -- ... on every board in settings/, then re-init the one
+#                         that was loaded when you called it
+# margin_save blanton  -- Blanton SONiC shortcut: all 18 LTC2977 straight over
+#                         the native i2c buses, no margin_init needed
+#
+# ⚠️  This is the only permanent write in the tool: it commits the current
+#     margin / OV / UV registers to NVM, and a power cycle will NOT undo it.
+#     Run margin_status first and never call it during a test run.
 margin_save() {
+    if [ "${1:-}" = "all" ]; then
+        _margin_save_every_board
+        return
+    fi
+    if [ "${1:-}" = "blanton" ]; then
+        _margin_save_blanton
+        return
+    fi
+
     local _own=0
     _pre_enter_own && _own=1
 
+    local chip fails=0
     for chip in "${CHIPS[@]}"; do
         IFS=':' read -r _BUS _ADDR <<< "$chip"
-        _i2c_write_byte 0x15 0x00
+        # STORE_USER_ALL is chip-wide (all 8 pages), so no _open_page here.
+        if _i2c_send_byte 0x15; then
+            _log_detail "STORE_USER_ALL $PART_NUMBER $_ADDR ok"
+        else
+            fails=$(( fails + 1 ))
+            echo -e "[\033[31mERRO\033[0m] STORE_USER_ALL failed on $_ADDR" >&2
+            _log_detail "ERRO STORE_USER_ALL $PART_NUMBER $_ADDR"
+        fi
+        # The part is busy writing NVM after this; nothing here polls a busy bit,
+        # so leave a gap before touching it again. See MARGIN_STORE_SETTLE.
+        [ -n "$MARGIN_STORE_SETTLE" ] && sleep "$MARGIN_STORE_SETTLE"
     done
+
+    if [ "$fails" -eq 0 ]; then
         echo "Change Saved (${#CHIPS[@]} chips)"
-    _log_label "margin_save $PART_NUMBER (${#CHIPS[@]} chips)"
+    else
+        echo -e "[\033[31mERRO\033[0m] $fails of ${#CHIPS[@]} chips did NOT save"
+    fi
+    _log_label "margin_save $PART_NUMBER (${#CHIPS[@]} chips, $fails failed)"
 
     [ "$_own" = "1" ] && _pre_exit
+    return $(( fails > 0 ))
 }
 
+# margin_save all -- every .conf in settings/, in filename order.
+# Deliberately does NOT stop on the first failure: a half-saved set is worse to
+# diagnose than a fully-attempted one, and the summary tells you which boards
+# to redo. margin_init is re-run per board because CHIPS / TRANSPORT /
+# CB_I2C_CH are global state.
+_margin_save_every_board() {
+    local files=( "$SETTINGS_DIR"/*.conf )
+    if [ ! -e "${files[0]}" ]; then
+        echo -e "[\033[31mERRO\033[0m] no .conf found in $SETTINGS_DIR"
+        return 1
+    fi
+
+    local restore="$PART_NUMBER"      # empty if margin_init was never run
+    local board f ok=0 bad=0 failed=""
+
+    echo "-------------"
+    echo "margin_save all -- ${#files[@]} boards, permanent NVM write"
+    echo "-------------"
+    _log_label "margin_save all (${#files[@]} boards)"
+
+    for f in "${files[@]}"; do
+        board=$(basename "$f" .conf)
+        echo ""
+        if ! margin_init "$board"; then
+            bad=$(( bad + 1 )); failed="$failed $board(init)"
+            continue
+        fi
+        if margin_save; then
+            ok=$(( ok + 1 ))
+        else
+            bad=$(( bad + 1 )); failed="$failed $board"
+        fi
+    done
+
+    echo ""
+    echo "-------------"
+    printf "margin_save all: %d saved, %d failed\n" "$ok" "$bad"
+    [ "$bad" -gt 0 ] && echo -e "[\033[31mERRO\033[0m] failed:$failed"
+    echo "-------------"
+    _log_label "margin_save all done: $ok ok, $bad failed$failed"
+
+    # Put back whatever board the caller had loaded, so a following
+    # margin_status does not silently report the last board in the list.
+    if [ -n "$restore" ] && [ "$restore" != "$board" ]; then
+        echo ""
+        echo -e "[\033[34mINFO\033[0m] restoring previous board: $restore"
+        margin_init "$restore" >/dev/null
+    fi
+
+    return $(( bad > 0 ))
+}
+
+# margin_save blanton -- Blanton SONiC only. Walks MARGIN_BLANTON_STORE and
+# sends STORE_USER_ALL to each LTC2977 over the native i2c buses.
+#
+# Deliberately does NOT use margin_init / CHIPS / TRANSPORT: the whole point is
+# that on this platform every LTC2977 is reachable with plain i2cset, so the
+# FPGA channel setup and the per-board probe are not needed. That also means it
+# does not touch the loaded board - PART_NUMBER is the same afterwards.
+_margin_save_blanton() {
+    local n=${#MARGIN_BLANTON_STORE[@]}
+    if [ "$n" -eq 0 ]; then
+        echo -e "[\033[31mERRO\033[0m] MARGIN_BLANTON_STORE is empty"
+        return 1
+    fi
+
+    echo "-------------"
+    echo "margin_save blanton -- $n LTC2977, permanent NVM write"
+    echo "-------------"
+    _log_label "margin_save blanton ($n chips)"
+
+    local entry bus addr label ok=0 bad=0 failed=""
+    for entry in "${MARGIN_BLANTON_STORE[@]}"; do
+        IFS=':' read -r bus addr label <<< "$entry"
+
+        # "no such bus" and "chip did not answer" are different faults: the first
+        # means the FPGA i2c adapters did not enumerate, the second means the
+        # board is absent or the address is wrong. Do not blur them into one.
+        if [ ! -e "/dev/i2c-$bus" ]; then
+            echo -e "[\033[31mERRO\033[0m] $label  bus $bus addr $addr : /dev/i2c-$bus does not exist"
+            _log_detail "ERRO STORE_USER_ALL $label bus=$bus addr=$addr no-such-bus"
+            bad=$(( bad + 1 )); failed="$failed [$label $addr]"
+            continue
+        fi
+
+        [ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] i2cset $MARGIN_BLANTON_I2CSET_FLAGS $bus $addr 0x15\033[0m"
+        if i2cset $MARGIN_BLANTON_I2CSET_FLAGS "$bus" "$addr" 0x15 >/dev/null 2>&1; then
+            printf "  %-12s bus %-2s %s : saved\n" "$label" "$bus" "$addr"
+            ok=$(( ok + 1 ))
+            _log_detail "STORE_USER_ALL $label bus=$bus addr=$addr ok"
+        else
+            echo -e "[\033[31mERRO\033[0m] $label  bus $bus addr $addr : i2cset failed (NACK/busy)"
+            _log_detail "ERRO STORE_USER_ALL $label bus=$bus addr=$addr"
+            bad=$(( bad + 1 )); failed="$failed [$label $addr]"
+        fi
+
+        # No busy-bit poll anywhere in this tool; this gap is the only buffer.
+        [ -n "$MARGIN_STORE_SETTLE" ] && sleep "$MARGIN_STORE_SETTLE"
+    done
+
+    echo "-------------"
+    printf "margin_save blanton: %d saved, %d failed\n" "$ok" "$bad"
+    [ "$bad" -gt 0 ] && echo -e "[\033[31mERRO\033[0m] failed:$failed"
+    echo "-------------"
+    _log_label "margin_save blanton done: $ok ok, $bad failed$failed"
+
+    return $(( bad > 0 ))
+}
+
+# --- Tab completion for margin_save ---
+_margin_save_completions() {
+    [ "$COMP_CWORD" -ne 1 ] && return
+    COMPREPLY=($(compgen -W "all blanton" -- "${COMP_WORDS[COMP_CWORD]}"))
+}
+complete -F _margin_save_completions margin_save
+
 if [ -z "$_LOG_FILE" ]; then
     _LOG_FILE="$LOGS_DIR/margin_$(date '+%Y%m%d_%H%M%S').log"
     _LOG_DETAIL_FILE="${_LOG_FILE%.log}_detail.log"

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/script/margin_save_all.sh

@@ -4,6 +4,10 @@
 # ⚠️  margin_save 會把目前的 margin / OV / UV 設定**永久寫入 NVM**，
 #     斷電後仍保留。執行前請務必先 margin_status 確認各 channel 狀態正確。
 #
+# 全部 9 顆請直接用 margin.sh v2.7.0 內建的 `margin_save all` —— 它有成功/失敗總結，
+# 跑完還會把 margin_init 切回你原本載入的那顆。這支只在「只想寫其中幾顆」時才需要，
+# 編下面的 BOARDS 陣列。
+#
 # Usage:
 #   source script/margin_save_all.sh
 

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/settings/Blanton_SWB0_CONN13.conf

@@ -9,7 +9,7 @@
 # --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
 #     it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
 TRANSPORT="swb"
-CB_I2C_CH=6           # CB F3 Ch6 = SWB0 CONN13/CONN14 (shared with CONN14, addr must differ)
+CB_I2C_CH=8           # CB F3 Ch8 = SWB0 CONN13/CONN15 (shared with CONN15, addr must differ)
 
 # --- I2C Configuration ---
 

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/settings/Blanton_SWB0_CONN14.conf

@@ -9,15 +9,15 @@
 # --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
 #     it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
 TRANSPORT="swb"
-CB_I2C_CH=6           # CB F3 Ch6 = SWB0 CONN13/CONN14 (shared with CONN13, addr must differ)
+CB_I2C_CH=6           # CB F3 Ch6 = SWB0 CONN14/CONN16 (shared with CONN16, addr must differ)
 
 # --- I2C Configuration ---
 
 # Format: "bus:address"  (8 channels per entry / per LTC2977)
 CHIPS=(
     # chip1: SWB0 (CONN14)
-    "0:0x5E"    # CH0   ~ CH7
+    "0:0x5C"    # CH0   ~ CH7
-    "0:0x5F"    # CH8   ~ CH15
+    "0:0x5E"    # CH8   ~ CH15
 )
 
 # Pre-commands to run before accessing each chip (empty = none)

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/settings/Blanton_SWB0_CONN15.conf

@@ -9,7 +9,7 @@
 # --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
 #     it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
 TRANSPORT="swb"
-CB_I2C_CH=8           # CB F3 Ch8 = SWB0 CONN15/CONN16 (shared with CONN16, addr must differ)
+CB_I2C_CH=8           # CB F3 Ch8 = SWB0 CONN13/CONN15 (shared with CONN13, addr must differ)
 
 # --- I2C Configuration ---
 
@@ -17,7 +17,7 @@ CB_I2C_CH=8           # CB F3 Ch8 = SWB0 CONN15/CONN16 (shared with CONN16, addr
 CHIPS=(
     # chip1: SWB0 (CONN15)
     "0:0x62"    # CH0   ~ CH7
-    "0:0x63"    # CH8   ~ CH15
+    "0:0x64"    # CH8   ~ CH15
 )
 
 # Pre-commands to run before accessing each chip (empty = none)

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/settings/Blanton_SWB0_CONN16.conf

@@ -9,15 +9,15 @@
 # --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
 #     it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
 TRANSPORT="swb"
-CB_I2C_CH=8           # CB F3 Ch8 = SWB0 CONN15/CONN16 (shared with CONN15, addr must differ)
+CB_I2C_CH=6           # CB F3 Ch6 = SWB0 CONN14/CONN16 (shared with CONN14, addr must differ)
 
 # --- I2C Configuration ---
 
 # Format: "bus:address"  (8 channels per entry / per LTC2977)
 CHIPS=(
     # chip1: SWB0 (CONN16)
-    "0:0x64"    # CH0   ~ CH7
+    "0:0x62"    # CH0   ~ CH7
-    "0:0x65"    # CH8   ~ CH15
+    "0:0x64"    # CH8   ~ CH15
 )
 
 # Pre-commands to run before accessing each chip (empty = none)

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/settings/Blanton_SWB1_CONN13.conf

@@ -9,7 +9,7 @@
 # --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
 #     it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
 TRANSPORT="swb"
-CB_I2C_CH=7           # CB F3 Ch7 = SWB1 CONN13/CONN14 (shared with CONN14, addr must differ)
+CB_I2C_CH=9           # CB F3 Ch9 = SWB1 CONN13/CONN15 (shared with CONN15, addr must differ)
 
 # --- I2C Configuration ---
 
@@ -17,7 +17,7 @@ CB_I2C_CH=7           # CB F3 Ch7 = SWB1 CONN13/CONN14 (shared with CONN14, addr
 CHIPS=(
     # chip1: SWB1 (CONN13)
     "1:0x5C"    # CH0   ~ CH7
-    "1:0x5D"    # CH8   ~ CH15
+    "1:0x5E"    # CH8   ~ CH15
 )
 
 # Pre-commands to run before accessing each chip (empty = none)

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/settings/Blanton_SWB1_CONN14.conf

@@ -9,15 +9,15 @@
 # --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
 #     it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
 TRANSPORT="swb"
-CB_I2C_CH=7           # CB F3 Ch7 = SWB1 CONN13/CONN14 (shared with CONN13, addr must differ)
+CB_I2C_CH=7           # CB F3 Ch7 = SWB1 CONN14/CONN16 (shared with CONN16, addr must differ)
 
 # --- I2C Configuration ---
 
 # Format: "bus:address"  (8 channels per entry / per LTC2977)
 CHIPS=(
     # chip1: SWB1 (CONN14)
-    "1:0x5E"    # CH0   ~ CH7
+    "1:0x5C"    # CH0   ~ CH7
-    "1:0x5F"    # CH8   ~ CH15
+    "1:0x5E"    # CH8   ~ CH15
 )
 
 # Pre-commands to run before accessing each chip (empty = none)

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/settings/Blanton_SWB1_CONN15.conf

@@ -9,7 +9,7 @@
 # --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
 #     it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
 TRANSPORT="swb"
-CB_I2C_CH=9           # CB F3 Ch9 = SWB1 CONN15/CONN16 (shared with CONN16, addr must differ)
+CB_I2C_CH=9           # CB F3 Ch9 = SWB1 CONN13/CONN15 (shared with CONN13, addr must differ)
 
 # --- I2C Configuration ---
 
@@ -17,7 +17,7 @@ CB_I2C_CH=9           # CB F3 Ch9 = SWB1 CONN15/CONN16 (shared with CONN16, addr
 CHIPS=(
     # chip1: SWB1 (CONN15)
     "1:0x62"    # CH0   ~ CH7
-    "1:0x63"    # CH8   ~ CH15
+    "1:0x64"    # CH8   ~ CH15
 )
 
 # Pre-commands to run before accessing each chip (empty = none)

src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/settings/Blanton_SWB1_CONN16.conf

@@ -9,15 +9,15 @@
 # --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
 #     it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
 TRANSPORT="swb"
-CB_I2C_CH=9           # CB F3 Ch9 = SWB1 CONN15/CONN16 (shared with CONN15, addr must differ)
+CB_I2C_CH=7           # CB F3 Ch7 = SWB1 CONN14/CONN16 (shared with CONN14, addr must differ)
 
 # --- I2C Configuration ---
 
 # Format: "bus:address"  (8 channels per entry / per LTC2977)
 CHIPS=(
     # chip1: SWB1 (CONN16)
-    "1:0x64"    # CH0   ~ CH7
+    "1:0x62"    # CH0   ~ CH7
-    "1:0x65"    # CH8   ~ CH15
+    "1:0x64"    # CH8   ~ CH15
 )
 
 # Pre-commands to run before accessing each chip (empty = none)

src/Script_ABC_Blanton/Blanton_Script/blanton_traffic_linespeed.sh

@@ -61,6 +61,19 @@
 #                       intentional difference from
 #                       tools/bcm_mibpair_report_V1.1.0.py, which hides NA pairs
 #                       unless -a is given.
+#   V0.4.1  2026-08-19  Fix: report printed every counter as 2147483647 (INT32_MAX).
+#                       grp() rendered values with sprintf("%d", v); the DUT's awk
+#                       casts to a 32-bit int for %d, so any counter above 2^31-1
+#                       -- i.e. every real line-speed run -- saturated. Values are
+#                       now formatted with %.0f, which stays in awk's double domain
+#                       (exact to 2^53, far above any MIB counter).
+#                       NOTE: the PASS/FAIL verdicts were NEVER affected -- the
+#                       cross-check compares TX[]/RX[] doubles directly and only
+#                       the display path went through grp(). Past reports that said
+#                       PASS were right; only the numbers shown were wrong.
+#                       Same fix applied to the "# FAIL ..." delta line (%+d ->
+#                       %+.0f), which would otherwise saturate when a dead port
+#                       makes the delta the size of the whole counter.
 # =============================================================================
 #
 # The VLAN/port table below is copied verbatim from
@@ -486,7 +499,7 @@ _tl_pair_report() {
         -v TSV="$TL_REPORT_TSV" \
         -v COLOR="$color" '
     function grp(v,   s,out,l,i) {
-        s = sprintf("%d", v)
+        s = sprintf("%.0f", v)
         if (!GROUPED) return s
         out = ""; l = length(s)
         for (i = 1; i <= l; i++) {
@@ -557,7 +570,7 @@ _tl_pair_report() {
                 if (d <= TOL + 0) { v = "PASS"; npass++ }
                 else {
                     v = "FAIL"; nfail++
-                    FL[++nf] = sprintf("# FAIL %s/%s: %s.TX-%s.RX=%+d  %s.RX-%s.TX=%+d", \
+                    FL[++nf] = sprintf("# FAIL %s/%s: %s.TX-%s.RX=%+.0f  %s.RX-%s.TX=%+.0f", \
                                        a, b, a, b, dtx, a, b, drx)
                 }
                 ta = grp(TX[a]); ra = grp(RX[a]); tb = grp(TX[b]); rb = grp(RX[b])

src/Script_ABC_Blanton/Blanton_Script/bmc_monitor.sh

@@ -0,0 +1,344 @@
+#!/bin/bash
+###############################################################################
+# bmc_monitor.sh
+#
+# Version : V1.1.0
+# Author  : ETWen
+# Date    : 20260820
+#
+# Purpose : Periodically execute a list of commands on the BMC through
+#           `bmc-manager run "<cmd>"` from the SONiC host side, and append all
+#           output to a rotating log file. Designed to run detached in the
+#           background so no interactive SSH session to the BMC is required.
+#
+# Notes   : - Everything runs on the HOST. Nothing is deployed to the BMC, so
+#             the BMC busybox toolchain (no base64 / no setsid ...) is a
+#             non-issue.
+#           - `bmc-manager run` prints the remote command output on stdout and
+#             its own banner on stderr; the two streams are captured separately
+#             so the log stays clean.
+#
+# Version History
+# V1.0.0     20260820    Initial Version
+# V1.1.0     20260820    `start` clears the previous log by default
+#                        (START_LOG_MODE: new / archive / append)
+###############################################################################
+
+set -u
+
+###############################################################################
+# User Configurable Section  -- normally this is the only part you need to edit
+###############################################################################
+
+# Commands executed on the BMC, one per line, in this order.
+# Add a line to add a command; comment it out to disable it.
+COMMANDS=(
+    "free -m"
+    "i2ctransfer -f -y 1 w6@0x41 0x00 0xC0 0x55 0xAA 0x55 0xAA"
+    "i2ctransfer -f -y 1 w2@0x41 0x00 0xC0 r4"
+    "i2ctransfer -f -y 1 w6@0x41 0x00 0xC0 0xAA 0x55 0xAA 0x55"
+    "i2ctransfer -f -y 1 w2@0x41 0x00 0xC0 r4"
+    #"uptime"
+    #"cat /proc/loadavg"
+    #"cat /proc/meminfo"
+    #"df -h /tmp"
+    #"dmesg | tail -n 30"
+)
+
+# Seconds to wait after a full round (all COMMANDS executed) before the next one
+INTERVAL_SEC=10
+
+# Seconds to wait between two commands inside the same round (0 = no wait)
+INTER_CMD_DELAY_SEC=0
+
+# Per-command timeout in seconds; prevents a hung bmc-manager from freezing the
+# whole loop. Set to 0 to disable.
+CMD_TIMEOUT_SEC=30
+
+# Stop after this many rounds. 0 = run until stopped manually.
+MAX_ROUNDS=0
+
+# Command runner. Final invocation is:
+#     "$RUNNER_BIN" "${RUNNER_ARGS[@]}" "<command string>"
+#   BMC side  : RUNNER_BIN="bmc-manager" ; RUNNER_ARGS=(run)
+#   BMC by IP : RUNNER_BIN="bmc-manager" ; RUNNER_ARGS=(--ip 192.168.200.200 run)
+#   Host side : RUNNER_BIN="bash"        ; RUNNER_ARGS=(-c)
+RUNNER_BIN="bmc-manager"
+RUNNER_ARGS=(run)
+
+# stderr handling of the runner (bmc-manager banner lives here)
+#   0 = log stderr only when the command fails (recommended, keeps log clean)
+#   1 = always log stderr
+LOG_STDERR=0
+
+# Logging
+LOG_DIR=""                      # empty = <script directory>/log
+LOG_NAME="bmc_poll.log"
+MAX_LOG_SIZE_MB=100             # rotate above this size; 0 = never rotate
+MAX_LOG_KEEP=5                  # keep .1 .. .N
+
+# What `start` does with the log left behind by the previous run:
+#   new     = begin with an empty log; previous content and rotated copies are
+#             discarded (default -- one run, one log)
+#   archive = rename the previous log to <log>.YYYYmmdd-HHMMSS, then begin empty
+#   append  = keep appending to the existing log
+START_LOG_MODE="new"
+
+###############################################################################
+# Internal
+###############################################################################
+SCRIPT_NAME="$(basename -- "${BASH_SOURCE[0]}")"
+SCRIPT_PATH="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)/${SCRIPT_NAME}"
+[ -n "${LOG_DIR}" ] || LOG_DIR="$(dirname -- "${SCRIPT_PATH}")/log"
+LOG_FILE="${LOG_DIR}/${LOG_NAME}"
+PID_FILE="${LOG_DIR}/${LOG_NAME%.log}.pid"
+
+LOG_TO_FILE=0
+STOP=0
+SLEEP_PID=""
+
+ts()  { date '+%Y-%m-%d %H:%M:%S'; }
+die() { printf '[ERROR] %s\n' "$*" >&2; exit 1; }
+
+on_signal() {
+    STOP=1
+    [ -n "${SLEEP_PID}" ] && kill "${SLEEP_PID}" 2>/dev/null
+}
+
+# sleep that can be aborted immediately by SIGTERM/SIGINT
+interruptible_sleep() {
+    local sec="$1"
+    [ "${sec}" -gt 0 ] 2>/dev/null || return 0
+    sleep "${sec}" &
+    SLEEP_PID=$!
+    wait "${SLEEP_PID}" 2>/dev/null
+    SLEEP_PID=""
+}
+
+# echo the pid and return 0 when a live instance is found
+is_running() {
+    local pid
+    [ -f "${PID_FILE}" ] || return 1
+    pid="$(cat "${PID_FILE}" 2>/dev/null)"
+    [[ "${pid}" =~ ^[0-9]+$ ]] || return 1
+    kill -0 "${pid}" 2>/dev/null || return 1
+    grep -qa "${SCRIPT_NAME}" "/proc/${pid}/cmdline" 2>/dev/null || return 1
+    printf '%s' "${pid}"
+    return 0
+}
+
+rotate_log_if_needed() {
+    local max_bytes size i
+    [ "${LOG_TO_FILE}" -eq 1 ] || return 0
+    [ "${MAX_LOG_SIZE_MB}" -gt 0 ] || return 0
+    [ -f "${LOG_FILE}" ] || return 0
+
+    max_bytes=$(( MAX_LOG_SIZE_MB * 1024 * 1024 ))
+    size="$(stat -c %s "${LOG_FILE}" 2>/dev/null || echo 0)"
+    [ "${size}" -ge "${max_bytes}" ] || return 0
+
+    for (( i = MAX_LOG_KEEP - 1; i >= 1; i-- )); do
+        [ -f "${LOG_FILE}.${i}" ] && mv -f "${LOG_FILE}.${i}" "${LOG_FILE}.$(( i + 1 ))"
+    done
+    mv -f "${LOG_FILE}" "${LOG_FILE}.1"
+    exec >>"${LOG_FILE}" 2>&1          # re-bind stdout/stderr to the new file
+    printf '[%s] INFO : log rotated at %s MB\n' "$(ts)" "${MAX_LOG_SIZE_MB}"
+}
+
+# Remove the rotated copies (.1 .. .N) only. Timestamped archives are kept.
+remove_rotated_logs() {
+    local i
+    for (( i = 1; i <= MAX_LOG_KEEP + 1; i++ )); do
+        rm -f "${LOG_FILE}.${i}"
+    done
+}
+
+# Apply START_LOG_MODE just before a background run is launched.
+prepare_log_on_start() {
+    local stamp
+    case "${START_LOG_MODE}" in
+        append)
+            return 0
+            ;;
+        archive)
+            if [ -s "${LOG_FILE}" ]; then
+                stamp="$(date '+%Y%m%d-%H%M%S')"
+                mv -f "${LOG_FILE}" "${LOG_FILE}.${stamp}" \
+                    || die "cannot archive ${LOG_FILE}"
+                printf 'previous log archived: %s.%s\n' "${LOG_FILE}" "${stamp}"
+            fi
+            remove_rotated_logs
+            ;;
+        new)
+            # Truncate rather than unlink: the inode is preserved, so a `tail -f`
+            # that is already attached keeps following the new run.
+            if [ -f "${LOG_FILE}" ]; then
+                : > "${LOG_FILE}" || die "cannot truncate ${LOG_FILE}"
+            fi
+            remove_rotated_logs
+            ;;
+        *)
+            die "invalid START_LOG_MODE: ${START_LOG_MODE}"
+            ;;
+    esac
+}
+
+run_one_command() {
+    local cmd="$1"
+    local out err rc t0 elapsed err_file
+
+    err_file="$(mktemp)"
+    t0=${SECONDS}
+    if [ "${CMD_TIMEOUT_SEC}" -gt 0 ]; then
+        out="$(timeout "${CMD_TIMEOUT_SEC}" \
+               "${RUNNER_BIN}" "${RUNNER_ARGS[@]}" "${cmd}" 2>"${err_file}")"
+    else
+        out="$("${RUNNER_BIN}" "${RUNNER_ARGS[@]}" "${cmd}" 2>"${err_file}")"
+    fi
+    rc=$?
+    elapsed=$(( SECONDS - t0 ))
+    err="$(cat "${err_file}" 2>/dev/null)"
+    rm -f "${err_file}"
+
+    printf '===== [%s] CMD: %s | rc=%d | %ds =====\n' "$(ts)" "${cmd}" "${rc}" "${elapsed}"
+    printf '%s\n' "${out}"
+    if [ "${rc}" -eq 124 ]; then
+        printf '[%s] WARN : timeout after %ds\n' "$(ts)" "${CMD_TIMEOUT_SEC}"
+    fi
+    if [ -n "${err}" ] && { [ "${LOG_STDERR}" -eq 1 ] || [ "${rc}" -ne 0 ]; }; then
+        printf -- '--- stderr ---\n%s\n' "${err}"
+    fi
+    printf '\n'
+}
+
+main_loop() {
+    local round=0 cmd
+
+    [ "${#COMMANDS[@]}" -gt 0 ] || die "COMMANDS is empty"
+    command -v "${RUNNER_BIN}" >/dev/null 2>&1 || die "runner not found: ${RUNNER_BIN}"
+
+    trap on_signal INT TERM
+
+    printf '#############################################################\n'
+    printf '[%s] START: pid=%d interval=%ds timeout=%ds cmds=%d\n' \
+           "$(ts)" "$$" "${INTERVAL_SEC}" "${CMD_TIMEOUT_SEC}" "${#COMMANDS[@]}"
+    printf '#############################################################\n'
+
+    while [ "${STOP}" -eq 0 ]; do
+        round=$(( round + 1 ))
+        printf -- '---------- ROUND %d @ %s ----------\n' "${round}" "$(ts)"
+
+        for cmd in "${COMMANDS[@]}"; do
+            [ "${STOP}" -eq 0 ] || break
+            run_one_command "${cmd}"
+            [ "${INTER_CMD_DELAY_SEC}" -gt 0 ] && interruptible_sleep "${INTER_CMD_DELAY_SEC}"
+        done
+
+        rotate_log_if_needed
+
+        if [ "${MAX_ROUNDS}" -gt 0 ] && [ "${round}" -ge "${MAX_ROUNDS}" ]; then
+            break
+        fi
+        # Fixed gap between rounds. For a fixed cadence instead, replace with:
+        #   interruptible_sleep $(( INTERVAL_SEC - round_elapsed ))
+        [ "${STOP}" -eq 0 ] && interruptible_sleep "${INTERVAL_SEC}"
+    done
+
+    printf '[%s] STOP : pid=%d after %d round(s)\n' "$(ts)" "$$" "${round}"
+}
+
+###############################################################################
+# Sub-commands
+###############################################################################
+do_start() {
+    local pid
+    pid="$(is_running)" && die "already running (pid=${pid})"
+    mkdir -p "${LOG_DIR}" || die "cannot create ${LOG_DIR}"
+    prepare_log_on_start
+
+    if command -v setsid >/dev/null 2>&1; then
+        setsid "${SCRIPT_PATH}" __daemon >/dev/null 2>&1 &
+    else
+        nohup "${SCRIPT_PATH}" __daemon >/dev/null 2>&1 &
+        disown 2>/dev/null
+    fi
+
+    sleep 1
+    pid="$(is_running)" || die "start failed, check ${LOG_FILE}"
+    printf 'started (pid=%s)\nlog: %s\n' "${pid}" "${LOG_FILE}"
+}
+
+do_daemon() {
+    mkdir -p "${LOG_DIR}" || die "cannot create ${LOG_DIR}"
+    LOG_TO_FILE=1
+    exec >>"${LOG_FILE}" 2>&1
+    printf '%d\n' "$$" > "${PID_FILE}"
+    trap 'rm -f "${PID_FILE}"' EXIT
+    main_loop
+}
+
+do_stop() {
+    local pid i
+    pid="$(is_running)" || { printf 'not running\n'; rm -f "${PID_FILE}"; return 0; }
+
+    kill -TERM -"${pid}" 2>/dev/null || kill -TERM "${pid}" 2>/dev/null
+    for (( i = 0; i < 20; i++ )); do
+        kill -0 "${pid}" 2>/dev/null || break
+        sleep 0.5
+    done
+    if kill -0 "${pid}" 2>/dev/null; then
+        printf 'SIGTERM ignored, sending SIGKILL\n'
+        kill -KILL -"${pid}" 2>/dev/null || kill -KILL "${pid}" 2>/dev/null
+    fi
+    rm -f "${PID_FILE}"
+    printf 'stopped (pid=%s)\n' "${pid}"
+}
+
+do_status() {
+    local pid
+    if pid="$(is_running)"; then
+        printf 'status : running (pid=%s)\n' "${pid}"
+    else
+        printf 'status : stopped\n'
+    fi
+    printf 'log    : %s\n' "${LOG_FILE}"
+    [ -f "${LOG_FILE}" ] && printf 'size   : %s\n' "$(du -h "${LOG_FILE}" | cut -f1)"
+    printf 'cmds   : %d, interval=%ds\n' "${#COMMANDS[@]}" "${INTERVAL_SEC}"
+}
+
+usage() {
+    cat <<EOF
+Usage: ${SCRIPT_NAME} {start|stop|status|fg|tail|clear}
+
+  start    Run detached in the background; the previous log is discarded first
+           (see START_LOG_MODE)
+  stop     Stop the background instance
+  status   Show pid / log path / log size
+  fg       Run in the foreground, output to the terminal (for a quick check)
+  tail     tail -f the log file
+  clear    Remove the log file and all rotated copies (must be stopped first)
+
+Log file : ${LOG_FILE}
+
+To add a command, edit the COMMANDS array at the top of this script.
+EOF
+}
+
+###############################################################################
+# Entry point
+###############################################################################
+case "${1:-}" in
+    start)    do_start ;;
+    stop)     do_stop ;;
+    status)   do_status ;;
+    fg)       LOG_TO_FILE=0; main_loop ;;
+    tail)     tail -n 50 -f "${LOG_FILE}" ;;
+    clear)
+        is_running >/dev/null && die "still running, stop it first"
+        rm -f "${LOG_FILE}" "${LOG_FILE}".[0-9]*
+        printf 'log cleared\n'
+        ;;
+    __daemon) do_daemon ;;
+    -h|--help|"") usage ;;
+    *)        printf '[ERROR] unknown sub-command: %s\n\n' "$1" >&2; usage; exit 1 ;;
+esac

src/Script_ABC_Blanton/Blanton_Script/bmc_monitor_ddr.sh

@@ -0,0 +1,340 @@
+#!/bin/bash
+###############################################################################
+# bmc_monitor_ddr.sh
+#
+# Version : V1.1.0
+# Author  : ETWen
+# Date    : 20260820
+#
+# Purpose : Periodically execute a list of commands on the BMC through
+#           `bmc-manager run "<cmd>"` from the SONiC host side, and append all
+#           output to a rotating log file. Designed to run detached in the
+#           background so no interactive SSH session to the BMC is required.
+#
+# Notes   : - Everything runs on the HOST. Nothing is deployed to the BMC, so
+#             the BMC busybox toolchain (no base64 / no setsid ...) is a
+#             non-issue.
+#           - `bmc-manager run` prints the remote command output on stdout and
+#             its own banner on stderr; the two streams are captured separately
+#             so the log stays clean.
+#
+# Version History
+# V1.0.0     20260820    Initial Version
+# V1.1.0     20260820    `start` clears the previous log by default
+#                        (START_LOG_MODE: new / archive / append)
+###############################################################################
+
+set -u
+
+###############################################################################
+# User Configurable Section  -- normally this is the only part you need to edit
+###############################################################################
+
+# Commands executed on the BMC, one per line, in this order.
+# Add a line to add a command; comment it out to disable it.
+COMMANDS=(
+    "memtester 500M 1"
+    #"uptime"
+    #"cat /proc/loadavg"
+    #"cat /proc/meminfo"
+    #"df -h /tmp"
+    #"dmesg | tail -n 30"
+)
+
+# Seconds to wait after a full round (all COMMANDS executed) before the next one
+INTERVAL_SEC=5
+
+# Seconds to wait between two commands inside the same round (0 = no wait)
+INTER_CMD_DELAY_SEC=0
+
+# Per-command timeout in seconds; prevents a hung bmc-manager from freezing the
+# whole loop. Set to 0 to disable.
+CMD_TIMEOUT_SEC=3600
+
+# Stop after this many rounds. 0 = run until stopped manually.
+MAX_ROUNDS=0
+
+# Command runner. Final invocation is:
+#     "$RUNNER_BIN" "${RUNNER_ARGS[@]}" "<command string>"
+#   BMC side  : RUNNER_BIN="bmc-manager" ; RUNNER_ARGS=(run)
+#   BMC by IP : RUNNER_BIN="bmc-manager" ; RUNNER_ARGS=(--ip 192.168.200.200 run)
+#   Host side : RUNNER_BIN="bash"        ; RUNNER_ARGS=(-c)
+RUNNER_BIN="bmc-manager"
+RUNNER_ARGS=(run)
+
+# stderr handling of the runner (bmc-manager banner lives here)
+#   0 = log stderr only when the command fails (recommended, keeps log clean)
+#   1 = always log stderr
+LOG_STDERR=0
+
+# Logging
+LOG_DIR=""                      # empty = <script directory>/log
+LOG_NAME="bmc_ddr.log"
+MAX_LOG_SIZE_MB=100             # rotate above this size; 0 = never rotate
+MAX_LOG_KEEP=5                  # keep .1 .. .N
+
+# What `start` does with the log left behind by the previous run:
+#   new     = begin with an empty log; previous content and rotated copies are
+#             discarded (default -- one run, one log)
+#   archive = rename the previous log to <log>.YYYYmmdd-HHMMSS, then begin empty
+#   append  = keep appending to the existing log
+START_LOG_MODE="new"
+
+###############################################################################
+# Internal
+###############################################################################
+SCRIPT_NAME="$(basename -- "${BASH_SOURCE[0]}")"
+SCRIPT_PATH="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)/${SCRIPT_NAME}"
+[ -n "${LOG_DIR}" ] || LOG_DIR="$(dirname -- "${SCRIPT_PATH}")/log"
+LOG_FILE="${LOG_DIR}/${LOG_NAME}"
+PID_FILE="${LOG_DIR}/${LOG_NAME%.log}.pid"
+
+LOG_TO_FILE=0
+STOP=0
+SLEEP_PID=""
+
+ts()  { date '+%Y-%m-%d %H:%M:%S'; }
+die() { printf '[ERROR] %s\n' "$*" >&2; exit 1; }
+
+on_signal() {
+    STOP=1
+    [ -n "${SLEEP_PID}" ] && kill "${SLEEP_PID}" 2>/dev/null
+}
+
+# sleep that can be aborted immediately by SIGTERM/SIGINT
+interruptible_sleep() {
+    local sec="$1"
+    [ "${sec}" -gt 0 ] 2>/dev/null || return 0
+    sleep "${sec}" &
+    SLEEP_PID=$!
+    wait "${SLEEP_PID}" 2>/dev/null
+    SLEEP_PID=""
+}
+
+# echo the pid and return 0 when a live instance is found
+is_running() {
+    local pid
+    [ -f "${PID_FILE}" ] || return 1
+    pid="$(cat "${PID_FILE}" 2>/dev/null)"
+    [[ "${pid}" =~ ^[0-9]+$ ]] || return 1
+    kill -0 "${pid}" 2>/dev/null || return 1
+    grep -qa "${SCRIPT_NAME}" "/proc/${pid}/cmdline" 2>/dev/null || return 1
+    printf '%s' "${pid}"
+    return 0
+}
+
+rotate_log_if_needed() {
+    local max_bytes size i
+    [ "${LOG_TO_FILE}" -eq 1 ] || return 0
+    [ "${MAX_LOG_SIZE_MB}" -gt 0 ] || return 0
+    [ -f "${LOG_FILE}" ] || return 0
+
+    max_bytes=$(( MAX_LOG_SIZE_MB * 1024 * 1024 ))
+    size="$(stat -c %s "${LOG_FILE}" 2>/dev/null || echo 0)"
+    [ "${size}" -ge "${max_bytes}" ] || return 0
+
+    for (( i = MAX_LOG_KEEP - 1; i >= 1; i-- )); do
+        [ -f "${LOG_FILE}.${i}" ] && mv -f "${LOG_FILE}.${i}" "${LOG_FILE}.$(( i + 1 ))"
+    done
+    mv -f "${LOG_FILE}" "${LOG_FILE}.1"
+    exec >>"${LOG_FILE}" 2>&1          # re-bind stdout/stderr to the new file
+    printf '[%s] INFO : log rotated at %s MB\n' "$(ts)" "${MAX_LOG_SIZE_MB}"
+}
+
+# Remove the rotated copies (.1 .. .N) only. Timestamped archives are kept.
+remove_rotated_logs() {
+    local i
+    for (( i = 1; i <= MAX_LOG_KEEP + 1; i++ )); do
+        rm -f "${LOG_FILE}.${i}"
+    done
+}
+
+# Apply START_LOG_MODE just before a background run is launched.
+prepare_log_on_start() {
+    local stamp
+    case "${START_LOG_MODE}" in
+        append)
+            return 0
+            ;;
+        archive)
+            if [ -s "${LOG_FILE}" ]; then
+                stamp="$(date '+%Y%m%d-%H%M%S')"
+                mv -f "${LOG_FILE}" "${LOG_FILE}.${stamp}" \
+                    || die "cannot archive ${LOG_FILE}"
+                printf 'previous log archived: %s.%s\n' "${LOG_FILE}" "${stamp}"
+            fi
+            remove_rotated_logs
+            ;;
+        new)
+            # Truncate rather than unlink: the inode is preserved, so a `tail -f`
+            # that is already attached keeps following the new run.
+            if [ -f "${LOG_FILE}" ]; then
+                : > "${LOG_FILE}" || die "cannot truncate ${LOG_FILE}"
+            fi
+            remove_rotated_logs
+            ;;
+        *)
+            die "invalid START_LOG_MODE: ${START_LOG_MODE}"
+            ;;
+    esac
+}
+
+run_one_command() {
+    local cmd="$1"
+    local out err rc t0 elapsed err_file
+
+    err_file="$(mktemp)"
+    t0=${SECONDS}
+    if [ "${CMD_TIMEOUT_SEC}" -gt 0 ]; then
+        out="$(timeout "${CMD_TIMEOUT_SEC}" \
+               "${RUNNER_BIN}" "${RUNNER_ARGS[@]}" "${cmd}" 2>"${err_file}")"
+    else
+        out="$("${RUNNER_BIN}" "${RUNNER_ARGS[@]}" "${cmd}" 2>"${err_file}")"
+    fi
+    rc=$?
+    elapsed=$(( SECONDS - t0 ))
+    err="$(cat "${err_file}" 2>/dev/null)"
+    rm -f "${err_file}"
+
+    printf '===== [%s] CMD: %s | rc=%d | %ds =====\n' "$(ts)" "${cmd}" "${rc}" "${elapsed}"
+    printf '%s\n' "${out}"
+    if [ "${rc}" -eq 124 ]; then
+        printf '[%s] WARN : timeout after %ds\n' "$(ts)" "${CMD_TIMEOUT_SEC}"
+    fi
+    if [ -n "${err}" ] && { [ "${LOG_STDERR}" -eq 1 ] || [ "${rc}" -ne 0 ]; }; then
+        printf -- '--- stderr ---\n%s\n' "${err}"
+    fi
+    printf '\n'
+}
+
+main_loop() {
+    local round=0 cmd
+
+    [ "${#COMMANDS[@]}" -gt 0 ] || die "COMMANDS is empty"
+    command -v "${RUNNER_BIN}" >/dev/null 2>&1 || die "runner not found: ${RUNNER_BIN}"
+
+    trap on_signal INT TERM
+
+    printf '#############################################################\n'
+    printf '[%s] START: pid=%d interval=%ds timeout=%ds cmds=%d\n' \
+           "$(ts)" "$$" "${INTERVAL_SEC}" "${CMD_TIMEOUT_SEC}" "${#COMMANDS[@]}"
+    printf '#############################################################\n'
+
+    while [ "${STOP}" -eq 0 ]; do
+        round=$(( round + 1 ))
+        printf -- '---------- ROUND %d @ %s ----------\n' "${round}" "$(ts)"
+
+        for cmd in "${COMMANDS[@]}"; do
+            [ "${STOP}" -eq 0 ] || break
+            run_one_command "${cmd}"
+            [ "${INTER_CMD_DELAY_SEC}" -gt 0 ] && interruptible_sleep "${INTER_CMD_DELAY_SEC}"
+        done
+
+        rotate_log_if_needed
+
+        if [ "${MAX_ROUNDS}" -gt 0 ] && [ "${round}" -ge "${MAX_ROUNDS}" ]; then
+            break
+        fi
+        # Fixed gap between rounds. For a fixed cadence instead, replace with:
+        #   interruptible_sleep $(( INTERVAL_SEC - round_elapsed ))
+        [ "${STOP}" -eq 0 ] && interruptible_sleep "${INTERVAL_SEC}"
+    done
+
+    printf '[%s] STOP : pid=%d after %d round(s)\n' "$(ts)" "$$" "${round}"
+}
+
+###############################################################################
+# Sub-commands
+###############################################################################
+do_start() {
+    local pid
+    pid="$(is_running)" && die "already running (pid=${pid})"
+    mkdir -p "${LOG_DIR}" || die "cannot create ${LOG_DIR}"
+    prepare_log_on_start
+
+    if command -v setsid >/dev/null 2>&1; then
+        setsid "${SCRIPT_PATH}" __daemon >/dev/null 2>&1 &
+    else
+        nohup "${SCRIPT_PATH}" __daemon >/dev/null 2>&1 &
+        disown 2>/dev/null
+    fi
+
+    sleep 1
+    pid="$(is_running)" || die "start failed, check ${LOG_FILE}"
+    printf 'started (pid=%s)\nlog: %s\n' "${pid}" "${LOG_FILE}"
+}
+
+do_daemon() {
+    mkdir -p "${LOG_DIR}" || die "cannot create ${LOG_DIR}"
+    LOG_TO_FILE=1
+    exec >>"${LOG_FILE}" 2>&1
+    printf '%d\n' "$$" > "${PID_FILE}"
+    trap 'rm -f "${PID_FILE}"' EXIT
+    main_loop
+}
+
+do_stop() {
+    local pid i
+    pid="$(is_running)" || { printf 'not running\n'; rm -f "${PID_FILE}"; return 0; }
+
+    kill -TERM -"${pid}" 2>/dev/null || kill -TERM "${pid}" 2>/dev/null
+    for (( i = 0; i < 20; i++ )); do
+        kill -0 "${pid}" 2>/dev/null || break
+        sleep 0.5
+    done
+    if kill -0 "${pid}" 2>/dev/null; then
+        printf 'SIGTERM ignored, sending SIGKILL\n'
+        kill -KILL -"${pid}" 2>/dev/null || kill -KILL "${pid}" 2>/dev/null
+    fi
+    rm -f "${PID_FILE}"
+    printf 'stopped (pid=%s)\n' "${pid}"
+}
+
+do_status() {
+    local pid
+    if pid="$(is_running)"; then
+        printf 'status : running (pid=%s)\n' "${pid}"
+    else
+        printf 'status : stopped\n'
+    fi
+    printf 'log    : %s\n' "${LOG_FILE}"
+    [ -f "${LOG_FILE}" ] && printf 'size   : %s\n' "$(du -h "${LOG_FILE}" | cut -f1)"
+    printf 'cmds   : %d, interval=%ds\n' "${#COMMANDS[@]}" "${INTERVAL_SEC}"
+}
+
+usage() {
+    cat <<EOF
+Usage: ${SCRIPT_NAME} {start|stop|status|fg|tail|clear}
+
+  start    Run detached in the background; the previous log is discarded first
+           (see START_LOG_MODE)
+  stop     Stop the background instance
+  status   Show pid / log path / log size
+  fg       Run in the foreground, output to the terminal (for a quick check)
+  tail     tail -f the log file
+  clear    Remove the log file and all rotated copies (must be stopped first)
+
+Log file : ${LOG_FILE}
+
+To add a command, edit the COMMANDS array at the top of this script.
+EOF
+}
+
+###############################################################################
+# Entry point
+###############################################################################
+case "${1:-}" in
+    start)    do_start ;;
+    stop)     do_stop ;;
+    status)   do_status ;;
+    fg)       LOG_TO_FILE=0; main_loop ;;
+    tail)     tail -n 50 -f "${LOG_FILE}" ;;
+    clear)
+        is_running >/dev/null && die "still running, stop it first"
+        rm -f "${LOG_FILE}" "${LOG_FILE}".[0-9]*
+        printf 'log cleared\n'
+        ;;
+    __daemon) do_daemon ;;
+    -h|--help|"") usage ;;
+    *)        printf '[ERROR] unknown sub-command: %s\n\n' "$1" >&2; usage; exit 1 ;;
+esac

src/Script_ABC_Blanton/Blanton_Script/mgmt_ping_monitor.sh

@@ -0,0 +1,403 @@
+#!/bin/bash
+###############################################################################
+# mgmt_ping_monitor.sh
+#
+# Version : V3.0.0
+# Author  : ETWen
+# Date    : 20260826
+#
+# Purpose : Ping from BOTH management NICs at the same time, continuously, and
+#           keep accumulating until stopped:
+#
+#               10G (eth0) -> TARGET_10G
+#               1G  (eth1) -> TARGET_1G
+#
+#           `stop` renders a report into the log: the last TAIL_LINES entries
+#           per NIC, each one's ping statistics and verdict, then
+#           `ip -s link show` for both interfaces.
+#
+# Notes   : - Both NICs are configured with iproute2 `replace`, which is
+#             idempotent, and both are left up. On a shared subnet the target's
+#             ARP can be answered by either NIC, so ARP_STRICT keeps each one
+#             to its own address.
+#           - ARP WARM-UP: the first packet after a neighbour entry expires is
+#             spent resolving ARP and is counted as loss. On the bench this
+#             produced three FAILs whose only missing packet was icmp_seq=1,
+#             every time, with zero NIC errors or drops. One discarded ping
+#             before the measured run removes that artefact, which is what lets
+#             MAX_LOSS_PCT stay at 0 and still mean something.
+#           - MANAGEMENT CONNECTIVITY IS IN USE while this runs. Drive it from
+#             the serial console.
+#
+# Version History
+# V1.0.0     20260824    Initial Version (ifconfig, one NIC at a time)
+# V2.0.0     20260824    iproute2; both NICs stay up; per-NIC target;
+#                        ip -s link show + TX/RX delta per leg
+# V3.0.0     20260826    Both NICs ping SIMULTANEOUSLY and continuously instead
+#                        of alternating fixed bursts. Add the ARP warm-up.
+#                        `stop` renders last-N per NIC + statistics + both
+#                        ip -s link outputs into the log.
+###############################################################################
+
+set -u
+
+###############################################################################
+# User Configurable Section  -- normally this is the only part you need to edit
+###############################################################################
+
+# --- 10G management port ---
+IF_10G="eth0"
+IP_10G="192.168.1.99"
+TARGET_10G="192.168.1.30"      # host this NIC pings
+PLEN_10G=24                    # prefix length, e.g. 24 = /24
+GW_10G=""                      # default gateway; empty = do not touch routing
+METRIC_10G=100                 # lower metric wins for off-subnet traffic
+
+# --- 1G management port ---
+IF_1G="eth1"
+IP_1G="192.168.1.101"
+TARGET_1G="192.168.1.31"
+PLEN_1G=24
+GW_1G=""
+METRIC_1G=200
+
+# --- ping ---
+PING_INTERVAL_SEC=1            # seconds between echo requests (ping -i)
+MAX_LOSS_PCT=0                 # loss above this marks the NIC FAIL
+TAIL_LINES=20                  # how many recent entries per NIC the report shows
+
+# Extra ping flags. -D timestamps every line, -O prints a marker for a request
+# that got no reply, so a drop is visible in the tail instead of just missing.
+# Clear this if the platform's ping does not accept them.
+PING_EXTRA_OPTS="-D -O"
+
+# One discarded ping per NIC before the measured run, to resolve ARP. Without
+# it the first packet of the run is lost to neighbour resolution and looks
+# exactly like a link fault. 0 disables.
+ARP_WARMUP=1
+ARP_WARMUP_TIMEOUT=2           # seconds to wait for the warm-up reply
+
+# Both NICs stay up. If they share a subnet the target's ARP can be answered by
+# either one, so a reply may arrive on the NIC that did not send. This applies
+# arp_ignore=1 / arp_announce=2 to both. RAM only -- reverts on reboot.
+ARP_STRICT=1
+
+# Prefix for the ip commands; empty because this already runs as root.
+SUDO=""
+
+# Seconds to wait after bringing a link up before pinging.
+LINK_SETTLE_SEC=5
+
+# Logging
+LOG_DIR=""                     # empty = <script directory>/log
+LOG_NAME="mgmt_ping.log"
+
+# What `start` does with the log left behind by the previous run:
+#   new     = discard it (default -- one run, one log)
+#   archive = rename it to <log>.YYYYmmdd-HHMMSS first
+#   append  = keep it
+START_LOG_MODE="new"
+
+###############################################################################
+# Internal
+###############################################################################
+SCRIPT_NAME="$(basename -- "${BASH_SOURCE[0]}")"
+SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
+[ -n "${LOG_DIR}" ] || LOG_DIR="${SCRIPT_DIR}/log"
+
+LOG_FILE="${LOG_DIR}/${LOG_NAME}"
+BASE="${LOG_DIR}/${LOG_NAME%.log}"
+PID_FILE="${BASE}.pid"
+STATE_FILE="${BASE}.state"
+RAW_10G="${BASE}_${IF_10G}.raw"
+RAW_1G="${BASE}_${IF_1G}.raw"
+
+ts()  { date '+%Y-%m-%d %H:%M:%S'; }
+die() { printf '[ERROR] %s\n' "$*" >&2; exit 1; }
+
+# "<rx_packets> <tx_packets>" for an interface. ip -s link orders the columns
+# "bytes packets errors ...", so packets is $2, not $1.
+if_counters() {
+    ${SUDO} ip -s link show "$1" 2>/dev/null | awk '
+        /RX:/ { getline; rx = $2 }
+        /TX:/ { getline; tx = $2 }
+        END   { printf "%s %s", (rx == "" ? 0 : rx), (tx == "" ? 0 : tx) }'
+}
+
+# Bring the NIC up and (re)apply its address and default route.
+setup_iface() {
+    local iface="$1" ipaddr="$2" plen="$3" gw="$4" metric="$5"
+    ${SUDO} ip link set "${iface}" up 2>&1                             || return 1
+    ${SUDO} ip address replace "${ipaddr}/${plen}" dev "${iface}" 2>&1 || return 1
+    if [ -n "${gw}" ]; then
+        ${SUDO} ip route replace default via "${gw}" dev "${iface}" \
+                metric "${metric}" 2>&1                                || return 1
+    fi
+    return 0
+}
+
+apply_arp_strict() {
+    local i
+    [ "${ARP_STRICT}" -eq 1 ] || return 0
+    for i in "${IF_10G}" "${IF_1G}"; do
+        ${SUDO} sysctl -qw "net.ipv4.conf.${i}.arp_ignore=1"   2>/dev/null
+        ${SUDO} sysctl -qw "net.ipv4.conf.${i}.arp_announce=2" 2>/dev/null
+    done
+}
+
+# Resolve the neighbour so the measured run does not spend its first packet on
+# ARP. Result is deliberately discarded.
+arp_warmup() {
+    local iface="$1" target="$2"
+    [ "${ARP_WARMUP}" -eq 1 ] || return 0
+    ping -I "${iface}" -c 1 -W "${ARP_WARMUP_TIMEOUT}" "${target}" >/dev/null 2>&1
+    return 0
+}
+
+# echo "pid_10g pid_1g" and return 0 when both are alive
+is_running() {
+    local p0 p1
+    [ -f "${PID_FILE}" ] || return 1
+    p0="$(sed -n '1p' "${PID_FILE}" 2>/dev/null)"
+    p1="$(sed -n '2p' "${PID_FILE}" 2>/dev/null)"
+    [[ "${p0}" =~ ^[0-9]+$ ]] || return 1
+    [[ "${p1}" =~ ^[0-9]+$ ]] || return 1
+    kill -0 "${p0}" 2>/dev/null || kill -0 "${p1}" 2>/dev/null || return 1
+    printf '%s %s' "${p0}" "${p1}"
+    return 0
+}
+
+###############################################################################
+# Report
+###############################################################################
+
+# The recent entries for one NIC: replies and, thanks to -O, the requests that
+# got none.
+tail_entries() {
+    grep -aE 'bytes from|no answer|Unreachable|Time to live' "$1" 2>/dev/null \
+        | tail -n "${TAIL_LINES}"
+}
+
+# The trailing "--- x ping statistics ---" block.
+stats_block() {
+    sed -n '/ping statistics ---/,$p' "$1" 2>/dev/null
+}
+
+# render_leg <label> <iface> <target> <raw> <rx0> <tx0>
+render_leg() {
+    local label="$1" iface="$2" target="$3" raw="$4" rx0="$5" tx0="$6"
+    local st tx rx loss avg verdict c1 rx1 tx1 drx dtx
+
+    printf -- '----- %s : %s -> %s : last %s entries -----\n' \
+              "${label}" "${iface}" "${target}" "${TAIL_LINES}"
+    tail_entries "${raw}"
+    printf '\n'
+    st="$(stats_block "${raw}")"
+    printf '%s\n' "${st}"
+
+    tx="$(printf '%s' "${st}"   | sed -n 's/^\([0-9]\+\) packets transmitted.*/\1/p'   | tail -1)"
+    rx="$(printf '%s' "${st}"   | sed -n 's/.*[, ]\([0-9]\+\) received.*/\1/p'         | tail -1)"
+    loss="$(printf '%s' "${st}" | sed -n 's/.*[, ]\([0-9]\+\)% packet loss.*/\1/p'     | tail -1)"
+    avg="$(printf '%s' "${st}"  | sed -n 's|.*= [0-9.]*/\([0-9.]*\)/.*|\1|p'           | tail -1)"
+    [ -n "${tx}" ]   || tx=0
+    [ -n "${rx}" ]   || rx=0
+    [ -n "${loss}" ] || loss=100
+    [ -n "${avg}" ]  || avg="-"
+
+    c1="$(if_counters "${iface}")"; rx1="${c1% *}"; tx1="${c1#* }"
+    drx=$(( rx1 - rx0 )); dtx=$(( tx1 - tx0 ))
+
+    if [ "${loss}" -le "${MAX_LOSS_PCT}" ] && [ "${tx}" -gt 0 ]; then
+        verdict="PASS"
+    else
+        verdict="FAIL"
+    fi
+
+    # nic_tx/nic_rx are this interface's own counter delta over the whole run.
+    # A pass with nic_tx near zero means the traffic left on the other NIC.
+    printf '[%s] RESULT %-3s %-6s -> %-15s tx=%s rx=%s loss=%s%% rtt_avg=%sms nic_tx=%s nic_rx=%s %s\n\n' \
+           "$(ts)" "${label}" "${iface}" "${target}" "${tx}" "${rx}" "${loss}" "${avg}" \
+           "${dtx}" "${drx}" "${verdict}"
+}
+
+write_report() {
+    local rx0_10g tx0_10g rx0_1g tx0_1g started
+    started="$(sed -n '1p' "${STATE_FILE}" 2>/dev/null)"
+    rx0_10g="$(sed -n '2p' "${STATE_FILE}" 2>/dev/null)"; rx0_10g="${rx0_10g:-0}"
+    tx0_10g="$(sed -n '3p' "${STATE_FILE}" 2>/dev/null)"; tx0_10g="${tx0_10g:-0}"
+    rx0_1g="$(sed -n '4p' "${STATE_FILE}" 2>/dev/null)";  rx0_1g="${rx0_1g:-0}"
+    tx0_1g="$(sed -n '5p' "${STATE_FILE}" 2>/dev/null)";  tx0_1g="${tx0_1g:-0}"
+
+    {
+        printf '#############################################################\n'
+        printf '[%s] mgmt ping report\n' "$(ts)"
+        printf '  started : %s\n' "${started:-unknown}"
+        printf '  stopped : %s\n' "$(ts)"
+        printf '  10G     : %s %s/%s -> %s (metric %s)\n' \
+               "${IF_10G}" "${IP_10G}" "${PLEN_10G}" "${TARGET_10G}" "${METRIC_10G}"
+        printf '  1G      : %s %s/%s -> %s (metric %s)\n' \
+               "${IF_1G}" "${IP_1G}" "${PLEN_1G}" "${TARGET_1G}" "${METRIC_1G}"
+        printf '  ping    : -i %s %s, max loss %s%%\n' \
+               "${PING_INTERVAL_SEC}" "${PING_EXTRA_OPTS}" "${MAX_LOSS_PCT}"
+        printf '#############################################################\n\n'
+
+        render_leg "10G" "${IF_10G}" "${TARGET_10G}" "${RAW_10G}" "${rx0_10g}" "${tx0_10g}"
+        render_leg "1G"  "${IF_1G}"  "${TARGET_1G}"  "${RAW_1G}"  "${rx0_1g}"  "${tx0_1g}"
+
+        printf -- '--- ip -s link show %s ---\n' "${IF_10G}"
+        ${SUDO} ip -s link show "${IF_10G}" 2>&1
+        printf '\n'
+        printf -- '--- ip -s link show %s ---\n' "${IF_1G}"
+        ${SUDO} ip -s link show "${IF_1G}" 2>&1
+    } >> "${LOG_FILE}"
+}
+
+###############################################################################
+# Sub-commands
+###############################################################################
+prepare_log_on_start() {
+    local stamp
+    case "${START_LOG_MODE}" in
+        append) return 0 ;;
+        archive)
+            if [ -s "${LOG_FILE}" ]; then
+                stamp="$(date '+%Y%m%d-%H%M%S')"
+                mv -f "${LOG_FILE}" "${LOG_FILE}.${stamp}" || die "cannot archive ${LOG_FILE}"
+                printf 'previous log archived: %s.%s\n' "${LOG_FILE}" "${stamp}"
+            fi
+            ;;
+        new)
+            # Truncate rather than unlink, so a tail -f already attached keeps
+            # following the new run.
+            [ -f "${LOG_FILE}" ] && { : > "${LOG_FILE}" || die "cannot truncate ${LOG_FILE}"; }
+            ;;
+        *) die "invalid START_LOG_MODE: ${START_LOG_MODE}" ;;
+    esac
+}
+
+do_start() {
+    local pids p0 p1 c
+
+    pids="$(is_running)" && die "already running (pids=${pids})"
+
+    command -v ip   >/dev/null 2>&1 || die "ip (iproute2) not found"
+    command -v ping >/dev/null 2>&1 || die "ping not found"
+
+    mkdir -p "${LOG_DIR}" || die "cannot create ${LOG_DIR}"
+    prepare_log_on_start
+    : > "${RAW_10G}"
+    : > "${RAW_1G}"
+
+    setup_iface "${IF_10G}" "${IP_10G}" "${PLEN_10G}" "${GW_10G}" "${METRIC_10G}" \
+        || die "cannot configure ${IF_10G}"
+    setup_iface "${IF_1G}"  "${IP_1G}"  "${PLEN_1G}"  "${GW_1G}"  "${METRIC_1G}" \
+        || die "cannot configure ${IF_1G}"
+    apply_arp_strict
+    sleep "${LINK_SETTLE_SEC}"
+
+    # Spend the ARP resolution here, not on the first measured packet.
+    arp_warmup "${IF_10G}" "${TARGET_10G}"
+    arp_warmup "${IF_1G}"  "${TARGET_1G}"
+
+    # Counter baseline, taken after the warm-up so its packets are excluded.
+    { c="$(if_counters "${IF_10G}")"
+      printf '%s\n%s\n%s\n' "$(ts)" "${c% *}" "${c#* }"
+      c="$(if_counters "${IF_1G}")"
+      printf '%s\n%s\n' "${c% *}" "${c#* }"
+    } > "${STATE_FILE}"
+
+    # Both NICs ping at the same time and keep accumulating until stopped.
+    nohup ping -I "${IF_10G}" -i "${PING_INTERVAL_SEC}" ${PING_EXTRA_OPTS} \
+          "${TARGET_10G}" >> "${RAW_10G}" 2>&1 &
+    p0=$!
+    nohup ping -I "${IF_1G}"  -i "${PING_INTERVAL_SEC}" ${PING_EXTRA_OPTS} \
+          "${TARGET_1G}"  >> "${RAW_1G}"  2>&1 &
+    p1=$!
+    disown "${p0}" 2>/dev/null
+    disown "${p1}" 2>/dev/null
+    printf '%s\n%s\n' "${p0}" "${p1}" > "${PID_FILE}"
+
+    sleep 1
+    kill -0 "${p0}" 2>/dev/null || die "10G ping failed to start, see ${RAW_10G}"
+    kill -0 "${p1}" 2>/dev/null || die "1G ping failed to start, see ${RAW_1G}"
+    printf 'started (10G pid=%s, 1G pid=%s)\nlog: %s\n' "${p0}" "${p1}" "${LOG_FILE}"
+}
+
+do_stop() {
+    local pids p0 p1 i
+
+    pids="$(is_running)" || {
+        printf 'not running\n'
+        rm -f "${PID_FILE}"
+        return 0
+    }
+    p0="${pids% *}"; p1="${pids#* }"
+
+    # SIGINT, not SIGTERM: ping prints its statistics block on interrupt, and
+    # that block is what the report parses.
+    kill -INT "${p0}" 2>/dev/null
+    kill -INT "${p1}" 2>/dev/null
+    for (( i = 0; i < 20; i++ )); do
+        kill -0 "${p0}" 2>/dev/null || kill -0 "${p1}" 2>/dev/null || break
+        sleep 0.5
+    done
+    kill -KILL "${p0}" 2>/dev/null
+    kill -KILL "${p1}" 2>/dev/null
+
+    write_report
+    rm -f "${PID_FILE}"
+    printf 'stopped (10G pid=%s, 1G pid=%s)\nreport: %s\n' "${p0}" "${p1}" "${LOG_FILE}"
+}
+
+do_status() {
+    local pids
+    if pids="$(is_running)"; then
+        printf 'status : running (10G pid=%s, 1G pid=%s)\n' "${pids% *}" "${pids#* }"
+    else
+        printf 'status : stopped\n'
+    fi
+    printf 'log    : %s\n' "${LOG_FILE}"
+    printf '10G    : %s %s/%s -> %s\n' "${IF_10G}" "${IP_10G}" "${PLEN_10G}" "${TARGET_10G}"
+    printf '1G     : %s %s/%s -> %s\n' "${IF_1G}"  "${IP_1G}"  "${PLEN_1G}"  "${TARGET_1G}"
+    [ -f "${RAW_10G}" ] && printf '10G recv: %s\n' "$(grep -ac 'bytes from' "${RAW_10G}")"
+    [ -f "${RAW_1G}" ]  && printf '1G  recv: %s\n' "$(grep -ac 'bytes from' "${RAW_1G}")"
+}
+
+usage() {
+    cat <<EOF
+Usage: ${SCRIPT_NAME} {start|stop|status|summary|clear}
+
+  start    Configure both NICs, warm up ARP, then ping from BOTH at the same
+           time and keep accumulating. The previous log is discarded first.
+  stop     Stop both pings and render the report into the log
+  status   Show pids, configured NICs and replies received so far
+  summary  Print just the RESULT lines from the log
+  clear    Remove the log and the raw captures (must be stopped first)
+
+Log file : ${LOG_FILE}
+
+The report holds, per NIC, the last ${TAIL_LINES} entries and the ping
+statistics, then "ip -s link show" for both interfaces.
+
+Both NICs are used at once, so management connectivity is in play -- drive
+this from the serial console. Edit the User Configurable Section at the top
+to change interfaces, addresses, targets or the ping options.
+EOF
+}
+
+###############################################################################
+# Entry point
+###############################################################################
+case "${1:-}" in
+    start)   do_start ;;
+    stop)    do_stop ;;
+    status)  do_status ;;
+    summary) grep -a 'RESULT' "${LOG_FILE}" 2>/dev/null || printf 'no results in %s\n' "${LOG_FILE}" ;;
+    clear)
+        is_running >/dev/null && die "still running, stop it first"
+        rm -f "${LOG_FILE}" "${LOG_FILE}".[0-9]* "${RAW_10G}" "${RAW_1G}" "${STATE_FILE}"
+        printf 'log cleared\n'
+        ;;
+    -h|--help|"") usage ;;
+    *) printf '[ERROR] unknown sub-command: %s\n\n' "$1" >&2; usage; exit 1 ;;
+esac

src/Script_ABC_Blanton/Blanton_Script/port_prbs_monitor.sh

@@ -0,0 +1,431 @@
+#!/bin/bash
+###############################################################################
+# port_prbs_monitor.sh
+#
+# Version : V1.0.0
+# Author  : ETWen
+# Date    : 20260826
+#
+# Purpose : Run a PRBS test on the two 100G uplinks AT THE SAME TIME and keep
+#           polling until stopped. Each port gets its own background worker:
+#
+#               setup : sfputil lpmode off <port>
+#                       phy diag <phy> prbs set <poly>
+#                       phy diag <phy> prbsstat STArt Interval=<n>
+#               poll  : phy diag <phy> prbs get        <- PASS/FAIL comes from here
+#                       phydiag  <phy> prbsstat Ber    <- recorded only
+#               stop  : phydiag <phy> prbsstat STOp
+#                       phydiag <phy> prbs clear
+#
+#           Every command and its full output goes to that port's raw log.
+#           `stop` tears the test down and renders the report; `report`
+#           prints the PASS/FAIL tally per port.
+#
+# Notes   : - A poll counts as PASS only when the output contains "PRBS OK!".
+#             bcmcmd exits 0 even when the BCM shell rejects a command, so the
+#             exit status cannot be used -- only the output can.
+#           - bcmcmd is always run with </dev/null. Without it, it inherits the
+#             polling loop's stdin and eats it, and the loop runs once.
+#
+# Version History
+# V1.0.0     20260826    Initial Version
+###############################################################################
+
+set -u
+
+###############################################################################
+# User Configurable Section  -- normally this is the only part you need to edit
+###############################################################################
+
+# --- port A ---
+PORT_A_NAME="Ethernet513"
+PORT_A_UNIT=0                  # bcmcmd -n <unit>
+PORT_A_PHY=268                 # phy diag <phy>
+
+# --- port B ---
+PORT_B_NAME="Ethernet514"
+PORT_B_UNIT=1
+PORT_B_PHY=268
+
+# Which ports `start` runs when no argument is given: both | a | b
+# Override per run:  start a   /   start b   /   start both
+# Running one at a time is how you tell a genuine port fault from the DUT not
+# coping with two PRBS streams at once.
+PORTS="both"
+
+# --- PRBS ---
+PRBS_POLY="p=3"                # passed to "prbs set"
+PRBS_STAT_INTERVAL=5           # passed to "prbsstat STArt Interval="
+POLL_INTERVAL_SEC=10           # seconds between polls
+PASS_PATTERN="PRBS OK!"        # a poll is PASS only if the output contains this
+
+# Seconds to wait after the setup commands before the first poll, so the link
+# has settled and the counters mean something.
+SETTLE_SEC=10
+
+
+# Stop after this many polls per port. 0 = run until stopped manually.
+MAX_POLLS=0
+
+# How many recent poll blocks the report shows per port.
+TAIL_ENTRIES=20
+
+# Prefix for privileged commands; empty because this already runs as root.
+SUDO=""
+BCMCMD="bcmcmd"
+
+# Logging
+LOG_DIR=""                     # empty = <script directory>/log
+LOG_NAME="port_prbs.log"
+
+# What `start` does with the log left behind by the previous run:
+#   new | archive | append
+START_LOG_MODE="new"
+
+###############################################################################
+# Internal
+###############################################################################
+SCRIPT_NAME="$(basename -- "${BASH_SOURCE[0]}")"
+SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
+SCRIPT_PATH="${SCRIPT_DIR}/${SCRIPT_NAME}"
+[ -n "${LOG_DIR}" ] || LOG_DIR="${SCRIPT_DIR}/log"
+
+LOG_FILE="${LOG_DIR}/${LOG_NAME}"
+BASE="${LOG_DIR}/${LOG_NAME%.log}"
+PID_FILE="${BASE}.pid"
+STATE_FILE="${BASE}.state"
+RAW_A="${BASE}_${PORT_A_NAME}.raw"
+RAW_B="${BASE}_${PORT_B_NAME}.raw"
+
+ts()  { date '+%Y-%m-%d %H:%M:%S'; }
+
+# port_tally <name> <raw>  ->  "<polls> <pass> <fail> <verdict>"
+# A raw without a "PRBS START" line means the port was not run this session,
+# which is SKIP -- reporting it as FAIL would make a deliberate single-port
+# run look like half the hardware is broken.
+port_tally() {
+    local name="$1" raw="$2" pass fail polls verdict
+    if [ ! -s "${raw}" ] || ! grep -aq "PRBS START ${name}" "${raw}" 2>/dev/null; then
+        printf '0 0 0 SKIP'; return 0
+    fi
+    pass=$(grep -ac "PRBS ${name} poll=[0-9]* PASS" "${raw}" 2>/dev/null); pass=${pass:-0}
+    fail=$(grep -ac "PRBS ${name} poll=[0-9]* FAIL" "${raw}" 2>/dev/null); fail=${fail:-0}
+    polls=$(( pass + fail ))
+    if [ "${polls}" -gt 0 ] && [ "${fail}" -eq 0 ]; then verdict=PASS; else verdict=FAIL; fi
+    printf '%s %s %s %s' "${polls}" "${pass}" "${fail}" "${verdict}"
+}
+die() { printf '[ERROR] %s\n' "$*" >&2; exit 1; }
+
+# bcm <unit> <dsh command> -- output on stdout, never trusts the exit status.
+# </dev/null so it cannot consume the caller's stdin.
+bcm() {
+    local unit="$1" cmd="$2"
+    ${SUDO} "${BCMCMD}" -n "${unit}" -c "dsh -c \"${cmd}\"" </dev/null 2>&1
+}
+
+# run_step <unit> <dsh command>
+# The command and its full output are written to the LOG via stderr, because
+# the worker has stderr pointed at the raw file. Only the output itself goes to
+# stdout, so `out="$(run_step ...)"` captures the output without swallowing the
+# log lines -- writing both to stdout would have put the whole record inside
+# the variable and left the log with nothing but the poll verdicts.
+run_step() {
+    local unit="$1" cmd="$2" out
+    out="$(bcm "${unit}" "${cmd}")"
+    {
+        printf '[%s] CMD  : bcmcmd -n %s -c '\''dsh -c "%s"'\''\n' "$(ts)" "${unit}" "${cmd}"
+        printf '%s\n' "${out}"
+    } >&2
+    printf '%s' "${out}"
+}
+
+# Echo "<pid_a> <pid_b>" and return 0 while at least one worker is alive. A
+# port that was not started this run is recorded as "-", so a single-port run
+# is a first-class case rather than a half-broken two-port one.
+is_running() {
+    local pa pb alive=0
+    [ -f "${PID_FILE}" ] || return 1
+    pa="$(sed -n '1p' "${PID_FILE}" 2>/dev/null)"; pa="${pa:--}"
+    pb="$(sed -n '2p' "${PID_FILE}" 2>/dev/null)"; pb="${pb:--}"
+    [[ "${pa}" =~ ^[0-9]+$ ]] && kill -0 "${pa}" 2>/dev/null && alive=1
+    [[ "${pb}" =~ ^[0-9]+$ ]] && kill -0 "${pb}" 2>/dev/null && alive=1
+    [ "${alive}" -eq 1 ] || return 1
+    printf '%s %s' "${pa}" "${pb}"
+    return 0
+}
+
+###############################################################################
+# Worker  -- one per port, launched by `start`
+###############################################################################
+WORKER_STOP=0
+worker_on_signal() { WORKER_STOP=1; }
+
+# __worker <name> <unit> <phy> <rawfile>
+do_worker() {
+    local name="$1" unit="$2" phy="$3" raw="$4"
+    local n=0 pass=0 fail=0 out
+
+    exec >>"${raw}" 2>&1
+    trap worker_on_signal INT TERM
+
+    printf '#############################################################\n'
+    printf '[%s] PRBS START %s (unit %s, phy %s) poly=%s interval=%ss poll=%ss\n' \
+           "$(ts)" "${name}" "${unit}" "${phy}" "${PRBS_POLY}" \
+           "${PRBS_STAT_INTERVAL}" "${POLL_INTERVAL_SEC}"
+    printf '#############################################################\n'
+
+    # --- setup ---
+    printf '[%s] CMD  : sfputil lpmode off %s\n' "$(ts)" "${name}"
+    ${SUDO} sfputil lpmode off "${name}" </dev/null 2>&1
+    run_step "${unit}" "phy diag ${phy} prbs set ${PRBS_POLY}"                 >/dev/null
+    run_step "${unit}" "phy diag ${phy} prbsstat STArt Interval=${PRBS_STAT_INTERVAL}" >/dev/null
+
+    sleep "${SETTLE_SEC}"
+
+    # --- poll ---
+    while [ "${WORKER_STOP}" -eq 0 ]; do
+        n=$(( n + 1 ))
+        printf -- '---------- %s POLL %d @ %s ----------\n' "${name}" "${n}" "$(ts)"
+
+        out="$(run_step "${unit}" "phy diag ${phy} prbs get")"
+        # Ber is recorded for the log only; it does not decide the verdict.
+        run_step "${unit}" "phydiag ${phy} prbsstat Ber" >/dev/null
+
+        if printf '%s' "${out}" | grep -qF "${PASS_PATTERN}"; then
+            pass=$(( pass + 1 ))
+            printf '[%s] PRBS %s poll=%d PASS\n' "$(ts)" "${name}" "${n}"
+        else
+            fail=$(( fail + 1 ))
+            printf '[%s] PRBS %s poll=%d FAIL\n' "$(ts)" "${name}" "${n}"
+        fi
+
+        [ "${MAX_POLLS}" -gt 0 ] && [ "${n}" -ge "${MAX_POLLS}" ] && break
+        [ "${WORKER_STOP}" -eq 0 ] || break
+        sleep "${POLL_INTERVAL_SEC}"
+    done
+
+    # --- teardown ---
+    run_step "${unit}" "phydiag ${phy} prbsstat STOp"  >/dev/null
+    run_step "${unit}" "phydiag ${phy} prbs clear"     >/dev/null
+    printf '[%s] PRBS STOP %s polls=%d PASS=%d FAIL=%d\n' \
+           "$(ts)" "${name}" "${n}" "${pass}" "${fail}"
+}
+
+###############################################################################
+# Report
+###############################################################################
+# render_port <name> <unit> <phy> <raw>
+render_port() {
+    local name="$1" unit="$2" phy="$3" raw="$4"
+    local t polls pass fail verdict
+
+    t="$(port_tally "${name}" "${raw}")"
+    polls="$(printf '%s' "${t}" | awk '{print $1}')"
+    pass="$(printf '%s'  "${t}" | awk '{print $2}')"
+    fail="$(printf '%s'  "${t}" | awk '{print $3}')"
+    verdict="$(printf '%s' "${t}" | awk '{print $4}')"
+
+    if [ "${verdict}" = "SKIP" ]; then
+        printf -- '----- %s (unit %s, phy %s) : not run this session -----\n\n' \
+                  "${name}" "${unit}" "${phy}"
+        printf '[%s] RESULT %-12s polls=%-4s PASS=%-4s FAIL=%-4s %s\n\n' \
+               "$(ts)" "${name}" "${polls}" "${pass}" "${fail}" "${verdict}"
+        return 0
+    fi
+
+    printf -- '----- %s (unit %s, phy %s) : last %s poll blocks -----\n' \
+              "${name}" "${unit}" "${phy}" "${TAIL_ENTRIES}"
+    grep -aE "^-{10} ${name} POLL|PRBS ${name} poll=|prbsstat Ber|^ *[0-9]+ *: " "${raw}" 2>/dev/null \
+        | tail -n $(( TAIL_ENTRIES * 3 ))
+    printf '\n'
+    printf '[%s] RESULT %-12s polls=%-4s PASS=%-4s FAIL=%-4s %s\n\n' \
+           "$(ts)" "${name}" "${polls}" "${pass}" "${fail}" "${verdict}"
+}
+
+write_report() {
+    local started
+    started="$(sed -n '1p' "${STATE_FILE}" 2>/dev/null)"
+    {
+        printf '#############################################################\n'
+        printf '[%s] 100G PRBS report\n' "$(ts)"
+        printf '  started : %s\n' "${started:-unknown}"
+        printf '  stopped : %s\n' "$(ts)"
+        printf '  %s : unit %s, phy %s\n' "${PORT_A_NAME}" "${PORT_A_UNIT}" "${PORT_A_PHY}"
+        printf '  %s : unit %s, phy %s\n' "${PORT_B_NAME}" "${PORT_B_UNIT}" "${PORT_B_PHY}"
+        printf '  poly=%s  prbsstat Interval=%s  poll every %ss\n' \
+               "${PRBS_POLY}" "${PRBS_STAT_INTERVAL}" "${POLL_INTERVAL_SEC}"
+        printf '  a poll is PASS only when the output contains "%s"\n' "${PASS_PATTERN}"
+        printf '#############################################################\n\n'
+
+        render_port "${PORT_A_NAME}" "${PORT_A_UNIT}" "${PORT_A_PHY}" "${RAW_A}"
+        render_port "${PORT_B_NAME}" "${PORT_B_UNIT}" "${PORT_B_PHY}" "${RAW_B}"
+
+        # Taken after prbsstat STOp + prbs clear, so this is the recovered
+        # state. During the test the same command would have reported DOWN.
+        printf -- '--- show interfaces status %s,%s (after prbsstat STOp + prbs clear) ---\n' \
+               "${PORT_A_NAME}" "${PORT_B_NAME}"
+        ${SUDO} show interfaces status "${PORT_A_NAME},${PORT_B_NAME}" </dev/null 2>&1
+    } >> "${LOG_FILE}"
+}
+
+###############################################################################
+# Sub-commands
+###############################################################################
+prepare_log_on_start() {
+    local stamp
+    case "${START_LOG_MODE}" in
+        append) return 0 ;;
+        archive)
+            if [ -s "${LOG_FILE}" ]; then
+                stamp="$(date '+%Y%m%d-%H%M%S')"
+                mv -f "${LOG_FILE}" "${LOG_FILE}.${stamp}" || die "cannot archive ${LOG_FILE}"
+            fi ;;
+        new)
+            [ -f "${LOG_FILE}" ] && { : > "${LOG_FILE}" || die "cannot truncate ${LOG_FILE}"; } ;;
+        *) die "invalid START_LOG_MODE: ${START_LOG_MODE}" ;;
+    esac
+}
+
+# do_start [both|a|b|<port name>]
+do_start() {
+    local which="${1:-${PORTS}}" pids pa="-" pb="-" run_a=0 run_b=0
+
+    case "${which}" in
+        both|BOTH|all)                  run_a=1; run_b=1 ;;
+        a|A|"${PORT_A_NAME}")           run_a=1 ;;
+        b|B|"${PORT_B_NAME}")           run_b=1 ;;
+        *) die "unknown port selector '${which}' (use: both | a | b | ${PORT_A_NAME} | ${PORT_B_NAME})" ;;
+    esac
+
+    pids="$(is_running)" && die "already running (pids=${pids})"
+    command -v "${BCMCMD}" >/dev/null 2>&1 || die "${BCMCMD} not found"
+
+    mkdir -p "${LOG_DIR}" || die "cannot create ${LOG_DIR}"
+    prepare_log_on_start
+    # Only the selected ports are truncated. A raw with no "PRBS START" line is
+    # what the report uses to tell "not run this session" from "ran and failed".
+    [ "${run_a}" -eq 1 ] && : > "${RAW_A}"
+    [ "${run_b}" -eq 1 ] && : > "${RAW_B}"
+    printf '%s\n' "$(ts)" > "${STATE_FILE}"
+
+    # One worker per selected port; with both, they run at the same time.
+    # Invoked through bash so the file does not need the execute bit.
+    if [ "${run_a}" -eq 1 ]; then
+        setsid bash "${SCRIPT_PATH}" __worker \
+               "${PORT_A_NAME}" "${PORT_A_UNIT}" "${PORT_A_PHY}" "${RAW_A}" >/dev/null 2>&1 &
+        pa=$!
+        disown "${pa}" 2>/dev/null
+    fi
+    if [ "${run_b}" -eq 1 ]; then
+        setsid bash "${SCRIPT_PATH}" __worker \
+               "${PORT_B_NAME}" "${PORT_B_UNIT}" "${PORT_B_PHY}" "${RAW_B}" >/dev/null 2>&1 &
+        pb=$!
+        disown "${pb}" 2>/dev/null
+    fi
+    printf '%s\n%s\n' "${pa}" "${pb}" > "${PID_FILE}"
+
+    sleep 1
+    [ "${run_a}" -eq 1 ] && { kill -0 "${pa}" 2>/dev/null || die "${PORT_A_NAME} worker failed, see ${RAW_A}"; }
+    [ "${run_b}" -eq 1 ] && { kill -0 "${pb}" 2>/dev/null || die "${PORT_B_NAME} worker failed, see ${RAW_B}"; }
+    printf 'started (%s pid=%s, %s pid=%s)\nlog: %s\n' \
+           "${PORT_A_NAME}" "${pa}" "${PORT_B_NAME}" "${pb}" "${LOG_FILE}"
+
+    # Deliberately NOT printing "show interfaces status" here. With PRBS armed
+    # the link is out of normal operation and reports DOWN, which reads as a
+    # failure to anyone glancing at the console. The status is shown in the
+    # report instead, once PRBS has been cleared.
+}
+
+do_stop() {
+    local pids pa pb i
+    pids="$(is_running)" || { printf 'not running\n'; rm -f "${PID_FILE}"; return 0; }
+    pa="${pids% *}"; pb="${pids#* }"
+
+    # TERM lets each worker finish its poll and run prbsstat STOp / prbs clear.
+    [[ "${pa}" =~ ^[0-9]+$ ]] && kill -TERM "${pa}" 2>/dev/null
+    [[ "${pb}" =~ ^[0-9]+$ ]] && kill -TERM "${pb}" 2>/dev/null
+    for (( i = 0; i < 120; i++ )); do
+        kill -0 "${pa}" 2>/dev/null || kill -0 "${pb}" 2>/dev/null || break
+        sleep 0.5
+    done
+    if kill -0 "${pa}" 2>/dev/null || kill -0 "${pb}" 2>/dev/null; then
+        printf 'workers did not exit in time, sending SIGKILL (PRBS may be left running)\n' >&2
+        kill -KILL "${pa}" 2>/dev/null
+        kill -KILL "${pb}" 2>/dev/null
+    fi
+
+    write_report
+    rm -f "${PID_FILE}"
+    printf 'stopped\nreport: %s\n' "${LOG_FILE}"
+}
+
+do_report() {
+    local name raw pass fail polls verdict
+    printf '%-14s %-8s %-8s %-8s %s\n' PORT POLLS PASS FAIL RESULT
+    printf '%-14s %-8s %-8s %-8s %s\n' -------------- -------- -------- -------- ------
+    for spec in "${PORT_A_NAME}:${RAW_A}" "${PORT_B_NAME}:${RAW_B}"; do
+        name="${spec%%:*}"; raw="${spec#*:}"
+        set -- $(port_tally "${name}" "${raw}")
+        printf '%-14s %-8s %-8s %-8s %s\n' "${name}" "$1" "$2" "$3" "$4"
+    done
+}
+
+do_status() {
+    local pids
+    if pids="$(is_running)"; then
+        printf 'status : running (%s pid=%s, %s pid=%s)\n' \
+               "${PORT_A_NAME}" "${pids% *}" "${PORT_B_NAME}" "${pids#* }"
+    else
+        printf 'status : stopped\n'
+    fi
+    printf 'log    : %s\n' "${LOG_FILE}"
+    do_report
+}
+
+usage() {
+    cat <<EOF
+Usage: ${SCRIPT_NAME} {start [both|a|b]|stop|status|report|clear}
+
+  start    Set up PRBS and poll in the background. With no argument it runs
+           \$PORTS (currently "${PORTS}"); "a" or "b" runs that port alone,
+           which is how you tell a genuine port fault from the DUT not coping
+           with two PRBS streams at once.
+             start        both ports at the same time
+             start a      ${PORT_A_NAME} only
+             start b      ${PORT_B_NAME} only
+           Port status is NOT shown here: with PRBS armed the link reports
+           DOWN, which looks like a failure. See the report instead.
+  stop     Stop polling, run prbsstat STOp + prbs clear on both ports, and
+           render the report into the log
+  report   Print the PASS/FAIL tally per port
+  status   Show worker pids plus the current tally
+  clear    Remove the log and raw captures (must be stopped first)
+
+Log file : ${LOG_FILE}
+Raw      : ${RAW_A}
+           ${RAW_B}
+
+A poll is PASS only when "phy diag <phy> prbs get" reports "${PASS_PATTERN}".
+prbsstat Ber is captured alongside every poll but does not decide the verdict.
+A port that was not run in this session reports SKIP, not FAIL.
+EOF
+}
+
+###############################################################################
+# Entry point
+###############################################################################
+case "${1:-}" in
+    start)  shift; do_start "${1:-${PORTS}}" ;;
+    stop)   do_stop ;;
+    status) do_status ;;
+    report) do_report ;;
+    clear)
+        is_running >/dev/null && die "still running, stop it first"
+        rm -f "${LOG_FILE}" "${LOG_FILE}".[0-9]* "${RAW_A}" "${RAW_B}" "${STATE_FILE}"
+        printf 'log cleared\n' ;;
+    __worker)
+        shift
+        do_worker "$1" "$2" "$3" "$4" ;;
+    -h|--help|"") usage ;;
+    *) printf '[ERROR] unknown sub-command: %s\n\n' "$1" >&2; usage; exit 1 ;;
+esac

src/Script_ABC_Blanton/Blanton_Script/usb_target.sh

@@ -0,0 +1,203 @@
+#!/bin/bash
+###############################################################################
+# usb_target.sh
+#
+# Version : V1.1.0
+# Author  : ETWen
+# Date    : 20260825
+# Purpose : Auto-detect an inserted USB mass-storage device and report either
+#           its device node, its mount point, or both.
+#
+#           stdout : requested value(s) only, for $(...) capture
+#           stderr : diagnostic messages
+#
+# Usage   : usb_target.sh [-o dev|mnt|both|id] [-n] [-r seconds]
+#
+#             -o dev    print partition device node   (e.g. /dev/sda1)
+#             -o mnt    print mount point             (e.g. /mnt/usb)   [default]
+#             -o both   print "<dev> <mnt>" on one line
+#             -o id     print stable by-id path       (/dev/disk/by-id/...)
+#             -n        detect only, do not mount
+#             -r sec    udev enumeration wait, default 15
+#
+# Exit    : 0  success
+#           1  no USB mass-storage found
+#           2  multiple USB disks detected (refuse to guess)
+#           3  no usable filesystem on the device
+#           4  mount failed
+#           5  mounted but not writable
+#
+# Version History
+# V1.0.0     20260825    Initial Version
+# V1.1.0     20260825    Add -o/-n/-r options; expose device node and by-id path
+###############################################################################
+set -u
+
+MNT_BASE="/mnt/usb"
+RETRY=15
+OUTPUT="mnt"
+DO_MOUNT=1
+
+log() { echo "[usb] $*" >&2; }   # diagnostics go to stderr; stdout stays clean
+
+while getopts "o:nr:h" opt; do
+    case "$opt" in
+        o) OUTPUT="$OPTARG" ;;
+        n) DO_MOUNT=0 ;;
+        r) RETRY="$OPTARG" ;;
+        h) sed -n '3,30p' "$0" >&2; exit 0 ;;
+        *) log "invalid option"; exit 1 ;;
+    esac
+done
+shift $((OPTIND - 1))
+
+case "$OUTPUT" in
+    dev|mnt|both|id) ;;
+    *) log "invalid -o value: $OUTPUT"; exit 1 ;;
+esac
+
+# "-o dev" / "-o id" alone does not require mounting.
+[ "$OUTPUT" = "dev" ] && [ "$DO_MOUNT" = "1" ] && DO_MOUNT=0
+[ "$OUTPUT" = "id" ]  && [ "$DO_MOUNT" = "1" ] && DO_MOUNT=0
+
+#------------------------------------------------------------------------------
+# Identify the physical disk(s) backing rootfs / /host so they can be excluded.
+# Needed because some platforms boot from a USB DOM, which also reports TRAN=usb.
+#------------------------------------------------------------------------------
+get_system_disk() {
+    local src
+    for mp in /host / ; do
+        src=$(findmnt -no SOURCE "$mp" 2>/dev/null) || continue
+        lsblk -no PKNAME "$src" 2>/dev/null | head -1
+    done | sort -u
+}
+
+#------------------------------------------------------------------------------
+# List candidate USB disks (whole devices, not partitions).
+#------------------------------------------------------------------------------
+find_usb_disks() {
+    local sysdisks; sysdisks=$(get_system_disk)
+    lsblk -dn -o NAME,TYPE,TRAN,RM 2>/dev/null | while read -r name type tran rm; do
+        [ "$type" = "disk" ] || continue
+        case "$name" in loop*|ram*|dm-*|sr*|zram*) continue ;; esac
+
+        # Older util-linux may not expose the TRAN column; fall back to sysfs.
+        if [ "$tran" != "usb" ]; then
+            readlink -f "/sys/block/$name/device" 2>/dev/null | grep -q '/usb[0-9]' || continue
+            [ "$rm" = "1" ] || continue
+        fi
+
+        echo "$sysdisks" | grep -qx "$name" && { log "skip $name (system disk)"; continue; }
+        echo "/dev/$name"
+    done
+}
+
+#------------------------------------------------------------------------------
+# Pick a mountable partition from a disk; fall back to the whole device for
+# superfloppy layouts (filesystem written directly, no partition table).
+#------------------------------------------------------------------------------
+pick_partition() {
+    local disk="$1" p
+    p=$(lsblk -ln -o NAME,TYPE,FSTYPE "$disk" | \
+        awk '$2=="part" && $3!="" {print "/dev/"$1; exit}')
+    [ -n "$p" ] && { echo "$p"; return; }
+    [ -n "$(lsblk -dn -o FSTYPE "$disk")" ] && echo "$disk"
+}
+
+#------------------------------------------------------------------------------
+# Resolve a device node to a stable /dev/disk/by-id path, if one exists.
+#------------------------------------------------------------------------------
+resolve_by_id() {
+    local dev="$1" real link
+    real=$(readlink -f "$dev")
+    for link in /dev/disk/by-id/*; do
+        [ -e "$link" ] || continue
+        case "$link" in *-part*|*) ;; esac
+        [ "$(readlink -f "$link")" = "$real" ] && { echo "$link"; return 0; }
+    done
+    return 1
+}
+
+#------------------------------------------------------------------------------
+# Main
+#------------------------------------------------------------------------------
+disks=""
+for i in $(seq 1 "$RETRY"); do
+    disks=$(find_usb_disks)
+    [ -n "$disks" ] && break
+    sleep 1
+done
+
+[ -z "$disks" ] && { log "no USB mass-storage found"; exit 1; }
+
+n=$(echo "$disks" | wc -l)
+if [ "$n" -gt 1 ]; then
+    log "multiple USB disks detected, refuse to guess:"
+    log "$disks"
+    exit 2
+fi
+disk="$disks"
+
+part=$(pick_partition "$disk")
+[ -z "$part" ] && { log "$disk has no usable filesystem"; exit 3; }
+
+fstype=$(lsblk -no FSTYPE "$part")
+log "found $part (disk=$disk fstype=$fstype)"
+
+# --- device-node only: no mount needed ---------------------------------------
+if [ "$OUTPUT" = "dev" ]; then
+    echo "$part"
+    exit 0
+fi
+
+if [ "$OUTPUT" = "id" ]; then
+    if byid=$(resolve_by_id "$part"); then
+        echo "$byid"
+        exit 0
+    fi
+    log "no by-id path for $part, falling back to device node"
+    echo "$part"
+    exit 0
+fi
+
+# --- mount point required ----------------------------------------------------
+mp=$(lsblk -no MOUNTPOINT "$part" | head -1)
+
+if [ -z "$mp" ] && [ "$DO_MOUNT" = "0" ]; then
+    log "$part is not mounted and -n was given"
+    exit 4
+fi
+
+if [ -z "$mp" ]; then
+    log "mounting $part -> $MNT_BASE"
+    mkdir -p "$MNT_BASE"
+
+    # exfat/ntfs are not always built into the platform kernel.
+    case "$fstype" in
+        exfat) grep -qw exfat /proc/filesystems || modprobe exfat 2>/dev/null ;;
+        ntfs)  grep -qw ntfs3 /proc/filesystems || modprobe ntfs3 2>/dev/null ;;
+    esac
+
+    if ! mount -o rw,noatime "$part" "$MNT_BASE" 2>/dev/null; then
+        log "mount failed (fstype=$fstype)"
+        exit 4
+    fi
+    mp="$MNT_BASE"
+
+    # Verify it is actually writable (read-only media, dirty FAT, or full device).
+    if ! touch "$mp/.wtest" 2>/dev/null; then
+        log "mounted read-only or no space left"
+        umount "$mp"
+        exit 5
+    fi
+    rm -f "$mp/.wtest"
+else
+    log "$part already mounted at $mp"
+fi
+
+if [ "$OUTPUT" = "both" ]; then
+    echo "$part $mp"
+else
+    echo "$mp"
+fi
+exit 0

src/Script_ABC_Blanton/config.ttl

@@ -1,12 +1,22 @@
 ;================================================================
 ; User Configuration
 ;================================================================
-strTestcase="Margin"
 project_name = "Blanton"
+strTestcase="ENV"      ;ENV,EMC,Margin...etc 
 
-EN_Margin         = 1  ; 1: Enable Margin Test, 0: Disable Margin Test
+EN_Margin         = 0  ; 1: Enable Margin Test, 0: Disable Margin Test
-
 EN_log            = 1  ; 1: Enable log, 0: Disable log
+
+;================================================================
+; FAN_SPEED
+;================================================================
+FAN_SPEED = 100
+;================================================================
+; Switch Unit Population
+;================================================================
+SWB_UNIT0         = 1   ; 1 = this DUT has switch unit 0, wait for it ; 0 = skip
+SWB_UNIT1         = 1   ; 1 = this DUT has switch unit 1, wait for it ; 0 = skip
+
 ;================================================================
 ; Prompt Definitions
 ;================================================================

src/Script_ABC_Blanton/utils/setup_pmon.ttl

@@ -16,3 +16,8 @@ wait prompt_sonic_root
 sendln "show platform leak status"
 wait prompt_sonic_root
 sendln "show platform leak channels"
+
+wait prompt_sonic_root
+sendln "tpm-dut-test fru"
+wait prompt_sonic_root
+sendln "tpm-dut-test tpm-read"

src/Script_ABC_Blanton/utils/show_dmesg.ttl

@@ -1,8 +1,11 @@
+; All Event
 wait prompt_sonic_root
-sendln "date"
+sendln "dmesg -T | grep -Ei 'error|fail(ed|ure)?|fault|critical|panic|timeout'"
+
+; i2c event
 wait prompt_sonic_root
-sendln "dmesg | grep -i error"
+sendln "dmesg -T | grep -Ei 'error|fail(ed|ure)?|fault|critical|panic|timeout' | grep -i i2c"
+
+; Clear Event
 wait prompt_sonic_root
-sendln "dmesg | grep -i fail"
+sendln "dmesg -C"
-wait prompt_sonic_root
-sendln "dmesg | grep -i warning"

src/Script_ABC_Blanton/utils/wait_init.ttl

@@ -0,0 +1,105 @@
+; =============================================================================
+; File    : utils/wait_init.ttl
+; Version : V3.0.0
+; Date    : 2026-08-21
+; Author  : ETWen
+; =============================================================================
+; Wait until every switch unit ENABLED below reports at least WT_MIN ports up:
+;     bcmcmd -n <u> -c ps | grep -w up | wc -l
+;
+; The DUT is not always fully populated. Which units exist is declared ONCE in
+; config.ttl, so the traffic blocks in Script A/B/C and this wait agree:
+;     both units  -> SWB_UNIT0 = 1 , SWB_UNIT1 = 1
+;     unit 0 only -> SWB_UNIT0 = 1 , SWB_UNIT1 = 0
+;     unit 1 only -> SWB_UNIT0 = 0 , SWB_UNIT1 = 1
+;     no unit     -> SWB_UNIT0 = 0 , SWB_UNIT1 = 0   (bypass, returns immediately)
+;
+; Enter : prompt of the previous command is NOT consumed.
+; Exit  : a command has been sent, prompt NOT consumed (caller does the wait).
+;
+; Why the "PORTS0=" marker: TTL can only test for a string, so reading a count
+; means capturing it. Wrapping the number in an echo gives waitregex a unique
+; anchor, and the ECHO of the command cannot false-match -- it reads
+; "PORTS0=$(bcmcmd ..." and the pattern requires a digit right after the "=".
+;
+; Version History:
+;   V1.0.0  2026-08-21  Initial Version (waited on "show platform temperature"
+;                       until it stopped reporting "Thermal Not detected")
+;   V2.0.0  2026-08-21  Wait on the bcmcmd port-up count of BOTH switch units
+;                       instead of the thermal sensors; proceed only when both
+;                       are greater than WT_MIN (216).
+;   V3.0.0  2026-08-21  Add WT_UNIT0 / WT_UNIT1 so a partly populated DUT can
+;                       be declared: wait on the enabled units only, and bypass
+;                       entirely when neither is set.
+;   V3.1.0  2026-08-21  Take the population from SWB_UNIT0 / SWB_UNIT1 in
+;                       config.ttl instead of local copies, so this wait and the
+;                       traffic blocks cannot drift apart.
+;   V3.1.1  2026-08-25  WT_INTERVAL 10 -> 60. Fix the WT_MIN comments: the test
+;                       has been `< WT_MIN` (at least) since the threshold was
+;                       corrected, but the text still said "more than", which is
+;                       the off-by-one that once hung Script A.
+; =============================================================================
+; ---- which units to wait for: SWB_UNIT0 / SWB_UNIT1, set in config.ttl ------
+WT_MIN      = 216     ; an enabled unit must report AT LEAST this many ports up
+                      ; (216 = 108 loopback pairs x 2, i.e. every cabled port)
+WT_INTERVAL = 60      ; seconds between polls
+; -----------------------------------------------------------------------------
+
+timeout = 60          ; per-wait cap; bcmcmd ps is not instant
+wait prompt_sonic_root
+
+; nothing declared -> bypass
+if SWB_UNIT0 = 0 then
+    if SWB_UNIT1 = 0 then
+        goto NO_UNITS
+    endif
+endif
+
+:WAIT_PORTS
+wt_ok = 1
+
+if SWB_UNIT0 = 1 then
+    wt_up0 = 0
+    sendln "echo PORTS0=$(bcmcmd -n 0 -c ps | grep -w up | wc -l)"
+    waitregex "PORTS0=[ ]*([0-9]+)"
+    if result = 1 then
+        str2int wt_up0 groupmatchstr1
+    endif
+    wait prompt_sonic_root
+    if wt_up0 < WT_MIN then
+        wt_ok = 0
+    endif
+endif
+
+if SWB_UNIT1 = 1 then
+    wt_up1 = 0
+    sendln "echo PORTS1=$(bcmcmd -n 1 -c ps | grep -w up | wc -l)"
+    waitregex "PORTS1=[ ]*([0-9]+)"
+    if result = 1 then
+        str2int wt_up1 groupmatchstr1
+    endif
+    wait prompt_sonic_root
+    if wt_up1 < WT_MIN then
+        wt_ok = 0
+    endif
+endif
+
+if wt_ok = 1 then
+    goto PORTS_OK
+endif
+
+pause WT_INTERVAL
+goto WAIT_PORTS
+
+; ---- exits ------------------------------------------------------------------
+; Both leave exactly one prompt unconsumed, so the caller's next
+; "wait prompt_sonic_root" has something to match.
+:NO_UNITS
+sendln "echo wait_init:no-switch-unit-declared,bypassing-port-wait"
+goto DONE
+
+:PORTS_OK
+sendln ""
+
+:DONE
+timeout = 0

tools/100G_PRBS.txt

@@ -0,0 +1,63 @@
+
+
+echo PORTS0=$(bcmcmd -n 0 -c ps | grep -w up | wc -l)
+echo PORTS0=$(bcmcmd -n 1 -c ps | grep -w up | wc -l)
+
+show interfaces status Ethernet513,Ethernet514
+
+
+//100G Port 513 
+sudo sfputil lpmode off Ethernet513
+bcmcmd -n 0 -c 'dsh -c "phy diag 268 prbs set p=3"'
+bcmcmd -n 0 -c 'dsh -c "phy diag 268 prbsstat STArt Interval=5"'
+
+bcmcmd -n 0 -c 'dsh -c "phy diag 268 prbs get"'
+bcmcmd -n 0 -c 'dsh -c "phydiag 268 prbsstat Ber"'
+
+bcmcmd -n 0 -c 'dsh -c "phydiag 268 prbsstat STOp"'
+bcmcmd -n 0 -c 'dsh -c "phydiag 268 prbs clear"'
+
+
+//100G Port 514
+sudo sfputil lpmode off Ethernet514
+bcmcmd -n 1 -c 'dsh -c "phy diag 268 prbs set p=3"'
+bcmcmd -n 1 -c 'dsh -c "phy diag 268 prbsstat STArt Interval=5"'
+bcmcmd -n 1 -c 'dsh -c "phy diag 268 prbs get"'
+bcmcmd -n 1 -c 'dsh -c "phydiag 268 prbsstat Ber"'
+bcmcmd -n 1 -c 'dsh -c "phydiag 268 prbsstat STOp"'
+bcmcmd -n 1 -c 'dsh -c "phydiag 268 prbs clear"'
+
+
+
+
+
+//100G Port 513 
+sudo sfputil lpmode off Ethernet513
+sudo sfputil lpmode off Ethernet514
+
+bcmcmd -n 0 -c 'dsh -c "phy diag 268 prbs set p=3"'
+sleep 1
+bcmcmd -n 1 -c 'dsh -c "phy diag 268 prbs set p=3"'
+
+bcmcmd -n 0 -c 'dsh -c "phy diag 268 prbsstat STArt Interval=5"'
+sleep 1
+bcmcmd -n 1 -c 'dsh -c "phy diag 268 prbsstat STArt Interval=5"'
+
+bcmcmd -n 0 -c 'dsh -c "phy diag 268 prbs get"'
+sleep 1
+bcmcmd -n 1 -c 'dsh -c "phy diag 268 prbs get"'
+
+bcmcmd -n 0 -c 'dsh -c "phydiag 268 prbsstat Ber"'
+sleep 1
+bcmcmd -n 1 -c 'dsh -c "phydiag 268 prbsstat Ber"'
+
+bcmcmd -n 0 -c 'dsh -c "phydiag 268 prbsstat STOp"'
+sleep 1
+bcmcmd -n 1 -c 'dsh -c "phydiag 268 prbsstat STOp"'
+
+bcmcmd -n 0 -c 'dsh -c "phydiag 268 prbs clear"'
+sleep 1
+bcmcmd -n 1 -c 'dsh -c "phydiag 268 prbs clear"'
+
+
+

tools/TR518.txt

@@ -0,0 +1,32 @@
+bcmcmd -n 0 -c '*:port all lb=mac'
+bcmcmd -n 0 -c '*:l2 learn off'
+bcmcmd -n 0 -c '*:dsh -c "test mode nr=yes"'
+bcmcmd -n 0 -c '*:dsh -c "tr 518 Scenario=6 Profile=2 Count=260 PktSize=324 PortList=1-259,270-565 rm=ext CheckLinkTime=20 CheckDataTime=200 testphase=2"'
+
+bcmcmd -n 1 -c "*:port all lb=mac"
+bcmcmd -n 1 -c "*:l2 learn off"
+bcmcmd -n 1 -c "*:dsh -c 'test mode nr=yes'"
+bcmcmd -n 1 -c "*:dsh -c 'tr 518 Scenario=6 Profile=2 Count=260 PktSize=324 PortList=1-259,270-565 rm=ext CheckLinkTime=20 CheckDataTime=200 testphase=2'"
+
+
+bcmcmd -n 0 -c "*:port all lb=mac"
+sleep 1
+bcmcmd -n 1 -c "*:port all lb=mac"
+sleep 1
+bcmcmd -n 0 -c "*:l2 learn off"
+sleep 1
+bcmcmd -n 1 -c "*:l2 learn off"
+sleep 1
+bcmcmd -n 0 -c "*:dsh -c 'test mode nr=yes'"
+sleep 1
+bcmcmd -n 1 -c "*:dsh -c 'test mode nr=yes'"
+sleep 1
+bcmcmd -n 0 -c "*:dsh -c 'tr 518 Scenario=6 Profile=2 Count=260 PktSize=324 PortList=1-259,270-565 rm=ext CheckLinkTime=20 CheckDataTime=200 testphase=2'"
+sleep 1
+bcmcmd -n 1 -c "*:dsh -c 'tr 518 Scenario=6 Profile=2 Count=260 PktSize=324 PortList=1-259,270-565 rm=ext CheckLinkTime=20 CheckDataTime=200 testphase=2'"
+sleep 1
+
+
+root@(none):/usr/local/bin# swutil *:l2 learn off
+root@(none):/usr/local/bin# swutil *:dsh -c \"test mode nr=yes\"
+root@(none):/usr/local/bin# swutil *:dsh -c \"tr 518 Scenario=6 Profile=2 Count=260 PktSize=324 PortList=1-259,270-565 rm=ext CheckLinkTime=20 CheckDataTime=200 testphase=2"

tools/fan_ctrl.txt

@@ -0,0 +1,7 @@
+echo 18-0020 > /sys/bus/i2c/drivers/max31790/unbind
+sleep .5
+echo 18-0020 > /sys/bus/i2c/drivers/max31790/bind
+echo 25-0020 > /sys/bus/i2c/drivers/max31790/unbind
+sleep .5
+echo 25-0020 > /sys/bus/i2c/drivers/max31790/bind
+fan-speed-control.sh 30

tools/gen_channel_map.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+# =============================================================================
+# gen_channel_map.sh - Build docs/LTC2980_channel_map.csv from settings/*.conf
+# Version : V1.0.0
+# Date    : 2026-08-27
+# Author  : ETWen
+# =============================================================================
+# Runs on the DEV machine, not the DUT. Reads every LTC2980 margin settings
+# file and flattens CH<n>_VNOM / CH<n>_NET into one CSV:
+#
+#     Board,CONN,Ch,NetName,Vnom
+#     CB,CONN13,CH0,V5P0_ALW,5.0
+#
+# NC channels keep their literal NC / "-" so the page numbering still lines up
+# (ch/8 -> CHIPS[] index, ch%8 -> LTC2977 PAGE). Do not filter them out.
+#
+# Usage:
+#   tools/gen_channel_map.sh                 # write docs/LTC2980_channel_map.csv
+#   tools/gen_channel_map.sh -              # write to stdout
+# =============================================================================
+set -eu
+
+REPO_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
+SET_DIR="${REPO_ROOT}/src/Script_ABC_Blanton/Blanton_Script/LTC2980_Margin_Script/settings"
+OUT="${1:-${REPO_ROOT}/docs/LTC2980_channel_map.csv}"
+
+[ -d "${SET_DIR}" ] || { echo "settings dir not found: ${SET_DIR}" >&2; exit 1; }
+
+# 3-argument match(str, regex, array) is a gawk extension. Under mawk it is a
+# syntax error at best and an empty CSV at worst - fail loudly instead.
+awk 'BEGIN { if (match("a", /a/, m) != 1) exit 1 }' 2>/dev/null \
+    || { echo "need gawk (3-arg match); this awk is: $(awk --version 2>&1 | head -1)" >&2; exit 1; }
+
+gen() {
+    printf 'Board,CONN,Ch,NetName,Vnom\n'
+    # CB first, then SWB0/SWB1 CONN13..CONN16 - matches the physical walk order.
+    for f in "${SET_DIR}"/Blanton_CB_CONN*.conf \
+             "${SET_DIR}"/Blanton_SWB0_CONN*.conf \
+             "${SET_DIR}"/Blanton_SWB1_CONN*.conf ; do
+        [ -f "${f}" ] || continue
+        base="$(basename "${f}" .conf)"          # Blanton_SWB0_CONN13
+        board="$(echo "${base}" | cut -d_ -f2)"  # SWB0
+        conn="$(echo  "${base}" | cut -d_ -f3)"  # CONN13
+
+        # .conf files are LF per .gitattributes, but strip CR anyway - a stray
+        # CR would land inside the net name and travel into the CSV unseen.
+        sed 's/\r$//' "${f}" | awk -v b="${board}" -v c="${conn}" '
+            match($0, /^CH([0-9]+)_VNOM="([^"]*)"[^"]*CH[0-9]+_NET="([^"]*)"/, m) {
+                printf "%s,%s,CH%s,%s,%s\n", b, c, m[1], m[3], m[2]
+            }'
+    done
+}
+
+if [ "${OUT}" = "-" ]; then
+    gen
+else
+    gen > "${OUT}"
+    echo "wrote ${OUT}  ($(($(wc -l < "${OUT}") - 1)) channels)"
+fi