Compare commits
26
Commits
8aa5c90166
...
V1.0.7
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ef7cbdffd4 | ||
|
|
ae8941a844 | ||
|
|
a6a12cdf2c | ||
|
|
e38d24c775 | ||
|
|
9a11c1d5bb | ||
|
|
cbef5865ec | ||
|
|
8714bbb773 | ||
|
|
d8bf1f7a41 | ||
|
|
da39122c43 | ||
|
|
b66ae47a58 | ||
|
|
d065db7d71 | ||
|
|
419b680980 | ||
|
|
4ed283d0ca | ||
|
|
491e807cf8 | ||
|
|
18ce7a1a73 | ||
|
|
d1b5cfea0b | ||
|
|
5e63e3da6b | ||
|
|
855b7a6e30 | ||
|
|
310f897067 | ||
|
|
fedf697977 | ||
|
|
ababb2c3d1 | ||
|
|
a9c3dafc22 | ||
|
|
4088a828c6 | ||
|
|
afb7b1e283 | ||
|
|
fd35857d80 | ||
|
|
cdf38a09ae |
@@ -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
|
||||||
+2
-1
@@ -12,9 +12,10 @@ For_AI/
|
|||||||
!**/logs/.gitkeep
|
!**/logs/.gitkeep
|
||||||
!**/Logs/.gitkeep
|
!**/Logs/.gitkeep
|
||||||
|
|
||||||
# 打包輸出
|
# 打包輸出:產出不進 git,打包工具本身要進
|
||||||
publish/*
|
publish/*
|
||||||
!publish/.gitkeep
|
!publish/.gitkeep
|
||||||
|
!publish/publish.sh
|
||||||
|
|
||||||
# Office 暫存檔
|
# Office 暫存檔
|
||||||
~$*
|
~$*
|
||||||
|
|||||||
+154
-33
@@ -37,7 +37,12 @@ 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 |
|
| 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`) |
|
| 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`) |
|
| 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/current/jobs/` |
|
||||||
|
| 風扇控制 | max31790 driver rebind(`/sys/bus/i2c/drivers/max31790/{bind,unbind}`)+ `fan-speed-control.sh <%>` |
|
||||||
|
| 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 |
|
| 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` |
|
| 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**) |
|
| 版本控制 | Git(NAS + Gitea 私有 remote;**不推 GitHub,含客戶 NDA 資料**) |
|
||||||
@@ -106,7 +111,8 @@ Blanton_TTL_Script/
|
|||||||
│
|
│
|
||||||
├── CLAUDE.md # 專案記憶 & 給 Claude 的指令
|
├── CLAUDE.md # 專案記憶 & 給 Claude 的指令
|
||||||
├── ARCHITECTURE.md # 本架構文件
|
├── 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)
|
├── 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.md # FPGA 暫存器規格(markdown 正本,查 offset 用)
|
||||||
@@ -131,7 +137,9 @@ Blanton_TTL_Script/
|
|||||||
│
|
│
|
||||||
├── For_AI/ # 🚫 gitignored — AI 協作素材(波形截圖、草稿)
|
├── 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/
|
└── src/
|
||||||
└── Script_ABC_Blanton/ # ← Tera Term 的工作目錄(整包給測試員)
|
└── Script_ABC_Blanton/ # ← Tera Term 的工作目錄(整包給測試員)
|
||||||
@@ -144,10 +152,11 @@ Blanton_TTL_Script/
|
|||||||
├── utils/ # 可 include 的取數片段(TTL,無狀態、只 wait+sendln)
|
├── utils/ # 可 include 的取數片段(TTL,無狀態、只 wait+sendln)
|
||||||
│ ├── pcie_bus.ttl # lspci -tvvv / -vv
|
│ ├── pcie_bus.ttl # lspci -tvvv / -vv
|
||||||
│ ├── setup_pmon.ttl # show platform summary/fan/temperature/psustatus/voltage/
|
│ ├── 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)
|
│ ├── show_margin_status.ttl # source margin_status_all.sh(掃 9 顆 LTC2980)
|
||||||
│ ├── kill_all_process.ttl # kill $(jobs -p)
|
│ ├── 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.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_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
|
│ ├── show_pcie_error_reg_TH6_SWB1.ttl # EP 02:00.0 + RP 00:01.2
|
||||||
@@ -167,12 +176,20 @@ Blanton_TTL_Script/
|
|||||||
├── blanton_pwr_data.sh # SWB VRM + PDB brick 的 Vin/Vout/Iout/Temp 表
|
├── 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)
|
├── blanton_traffic_linespeed.sh # SWB loopback 線速流量(bcmcmd unit 0/1)
|
||||||
│ # init/clear/show/start/stop/ps/report/run
|
│ # 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,兩張卡都保持 up
|
||||||
|
├── bmc_monitor.sh # ⚠️ 已停用:B/C 內呼叫處已註解,改走 bgctl + bmc-manager
|
||||||
|
├── bmc_monitor_ddr.sh # ⚠️ 已停用,同上
|
||||||
|
│ # ↑ 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)
|
└── LTC2980_Margin_Script/ # 電壓 margin 子專案(另有獨立 repo)
|
||||||
├── margin.sh # margin_init/status/set/apply_profile/save
|
├── margin.sh # margin_init/status/set/apply_profile/save
|
||||||
├── settings/*.conf # 一個 .conf = 一顆 LTC2980(CB + SWB0/1 × CONN13~16)
|
├── 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)
|
├── 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
|
├── 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
|
└── 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 +201,20 @@ Blanton_TTL_Script/
|
|||||||
### 1. `config.ttl` — 全域測試參數(TTL 變數)
|
### 1. `config.ttl` — 全域測試參數(TTL 變數)
|
||||||
|
|
||||||
```ini
|
```ini
|
||||||
strTestcase = "Margin" ; 測項名,進 log 檔名
|
|
||||||
project_name = "Blanton" ; 專案名,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
|
EN_log = 1 ; 1=logopen 存檔, 0=不存
|
||||||
|
FAN_SPEED = 30 ; 傳給 fan-speed-control.sh 的風扇轉速 (%)
|
||||||
|
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_login = "sonic login:"
|
||||||
prompt_sonic = "admin@sonic:~$"
|
prompt_sonic = "admin@sonic:~$"
|
||||||
prompt_sonic_root = "root@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`
|
Log 檔名規則:`<mdir>\Logs\<project_name>_<strTestcase>_<YYYYmmdd-HHMMSS>.log`
|
||||||
|
|
||||||
### 2. `settings/<board>.conf` — 一顆 LTC2980(16 channel)
|
### 2. `settings/<board>.conf` — 一顆 LTC2980(16 channel)
|
||||||
@@ -208,6 +230,18 @@ 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)。
|
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。
|
||||||
|
|
||||||
### 3. `profiles/*.conf` — 16-ch 批次 margin 組合
|
### 3. `profiles/*.conf` — 16-ch 批次 margin 組合
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
@@ -267,16 +301,19 @@ PROFILE_CHANNELS=( "0:high:8" "1:low:8" ... ) # "channel:operation:change_perc
|
|||||||
|
|
||||||
| 模組 | 進入點 | 功能 |
|
| 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) |
|
| **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 |
|
| **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) |
|
| **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) |
|
| **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) |
|
| **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 |
|
||||||
|
| **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 / 壓力** | `bmc_monitor.sh` / `bmc_monitor_ddr.sh` | ⚠️ **已停用** —— B/C 內呼叫處已註解,改由 `bgctl` + `bmc-manager run memtester` 取代。檔案保留未刪 |
|
||||||
|
| **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 +328,24 @@ 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)
|
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:~# │
|
├─ 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/current/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) │
|
├─ 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)
|
│ └ 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
|
├─ AER 基線:7 組 EP+RP 的 correctable/nonfatal/fatal
|
||||||
├─ lspci -tvvv / -vv ← 拓樸 + link speed/width
|
├─ lspci -tvvv / -vv ← 拓樸 + link speed/width
|
||||||
├─ margin_status_all ← 9 顆 LTC2980 × 16ch 的 Vout 與偏差%
|
├─ 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
|
├─ 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
|
[messagebox "Start Script B"] ← 人工確認後手動跑 B
|
||||||
│
|
│
|
||||||
@@ -306,8 +353,11 @@ 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)
|
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
|
├─ 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")
|
│ (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)
|
└─ 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]
|
[測試員 Ctrl-C / 停止 macro,接著跑 C]
|
||||||
@@ -317,8 +367,14 @@ Script C
|
|||||||
├─ kill $(jobs -p) ← 收掉所有背景壓力
|
├─ kill $(jobs -p) ← 收掉所有背景壓力
|
||||||
├─ show platform × 9 + dmesg ← 收工快照
|
├─ 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
|
├─ 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
|
||||||
|
├─ cp -r /host/hw-eval/current/jobs/ /mnt/usb/jobs-<YYYYmmdd>_<HHMM>
|
||||||
|
└─ hw-test-session finish
|
||||||
▼
|
▼
|
||||||
[messagebox "GOOD JOB! Test Case DONE"] → 人工檢查 log
|
[messagebox "GOOD JOB! Test Case DONE"] → 人工檢查 log
|
||||||
```
|
```
|
||||||
@@ -369,7 +425,28 @@ 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)。
|
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,
|
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。
|
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**。
|
絕不推 GitHub**。
|
||||||
|
|
||||||
---
|
---
|
||||||
@@ -404,6 +481,9 @@ cp secret/config_secret.ttl.example secret/config_secret.ttl
|
|||||||
|
|
||||||
# ── 2. DUT 端:部署 bash 工具庫 ─────────────────────────────
|
# ── 2. DUT 端:部署 bash 工具庫 ─────────────────────────────
|
||||||
scp -r src/Script_ABC_Blanton/Blanton_Script admin@<DUT_IP>:~/
|
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 $'\r' ~/Blanton_Script
|
||||||
ssh admin@<DUT_IP> 'sudo -i'
|
ssh admin@<DUT_IP> 'sudo -i'
|
||||||
# (現場無網路時改用 USB 隨身碟複製到 ~/Blanton_Script)
|
# (現場無網路時改用 USB 隨身碟複製到 ~/Blanton_Script)
|
||||||
|
|
||||||
@@ -439,6 +519,19 @@ lspci -Dnn # 對照 ARCHITECTURE.md 的 PCIe 拓樸表
|
|||||||
8. 檢查 Logs\Blanton_Margin_<ts>.log
|
8. 檢查 Logs\Blanton_Margin_<ts>.log
|
||||||
```
|
```
|
||||||
|
|
||||||
|
**打包交付:**
|
||||||
|
|
||||||
|
```bash
|
||||||
|
./publish/publish.sh # 版號讀 Script A 檔頭 → publish/Script_ABC_Blanton_V1.0.3/
|
||||||
|
./publish/publish.sh -z # 另外產出同名 .zip
|
||||||
|
./publish/publish.sh -n # dry run,只印會做什麼
|
||||||
|
./publish/publish.sh -f # 覆蓋既有輸出資料夾
|
||||||
|
```
|
||||||
|
|
||||||
|
版號**不是參數而是從 Script A 的 `; Version : Vx.y.z` 讀出來的**,所以資料夾名不可能跟
|
||||||
|
測試員打開 macro 看到的版本不一致。要出新版就先改 Script A 檔頭再跑。
|
||||||
|
輸出會排除 `*.log`(測試 log 含 DUT 序號,不隨交付外流),但保留空的 `logs/` 供 `logopen` 寫入。
|
||||||
|
|
||||||
> 註:本專案非 .NET / Blazor / EC2 架構,`aws-ec2-deploy` 與 `vbox-run-deploy` 兩份部署指南不適用,已跳過。
|
> 註:本專案非 .NET / Blazor / EC2 架構,`aws-ec2-deploy` 與 `vbox-run-deploy` 兩份部署指南不適用,已跳過。
|
||||||
|
|
||||||
---
|
---
|
||||||
@@ -493,19 +586,22 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值,
|
|||||||
**目標:** 壓力程序起得來、起不來看得出來,soak 迴圈有時戳、可控週期。
|
**目標:** 壓力程序起得來、起不來看得出來,soak 迴圈有時戳、可控週期。
|
||||||
|
|
||||||
**包含:**
|
**包含:**
|
||||||
- [ ] 部署 `~/hammer/tools/` 前置檢查:新增 `utils/check_hammer_tools.ttl`
|
- [ ] 前置檢查:`~/hammer/tools/amd/mlucas-avx2` 仍是唯一還依賴 hammer 的項目,缺檔就別往下跑
|
||||||
(`ls -l ~/hammer/tools/` + `ls ~/hammer/tools/amd/mlucas-avx2`),缺檔就別往下跑
|
|
||||||
- [ ] 壓力程序 log 加時戳,避免多輪覆蓋:
|
- [ ] 壓力程序 log 加時戳,避免多輪覆蓋:
|
||||||
`mlucas_amm_log` → `~/logs/mlucas_amm_log_$(date +%Y%m%d-%H%M%S).log`(Status 表 ScriptB #2 的既定寫法)
|
`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)
|
||||||
- [ ] soak 迴圈改為「每輪先 `date`、跑完 `pause <間隔>`」,
|
- [ ] 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」
|
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**
|
**← 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**
|
||||||
- [x] soak 每輪補 `show platform psustatus` / `voltage` / `current`
|
- [x] soak 每輪補 `show platform psustatus` / `voltage` / `current`
|
||||||
—— 迴圈已改為 `include "utils/setup_pmon.ttl"`,九項全收
|
—— 迴圈已改為 `include "utils/setup_pmon.ttl"`,九項全收
|
||||||
- [ ] 補 `; ========== CLEAR EVENT ==========`(Status 表 ScriptB #1,Owner: Alan)
|
- [ ] 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;
|
**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。
|
故意把 `~/hammer` 改名,Script B 會在前置檢查就停下並提示。
|
||||||
@@ -530,14 +626,15 @@ 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`)
|
(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] 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`
|
- [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`、
|
- [ ] `utils/show_interface_detail.ttl`:`show interface transceiver eeprom/dom`、
|
||||||
`show interface link-training`(Status 表 ScriptC #4,仍 On-Going)
|
`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)
|
- [ ] `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
|
- [ ] `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)
|
(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;
|
**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。
|
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 +652,13 @@ 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
|
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
|
- [ ] 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)
|
- [ ] 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
|
- [ ] 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
|
`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
|
- [ ] 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,
|
**驗收條件:** 拿一份既有 log(如 `Blanton_Margin_20260814-164122.log`)跑解析器,
|
||||||
@@ -570,9 +671,9 @@ 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。
|
**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:**
|
**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、
|
- [ ] `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
|
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
|
- [ ] `CHANGELOG.md`:延續三支腳本頂端的 Version History,集中成一份
|
||||||
@@ -602,6 +703,26 @@ 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。
|
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;
|
- **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。
|
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`(以及保留但已停用的 `bmc_monitor*.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.sh` / `bmc_monitor_ddr.sh` 已停用**:B/C 內的呼叫都已註解,改由 `bgctl` +
|
||||||
|
`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。
|
||||||
|
- **`rm /host/hw-eval/current/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/*`。
|
||||||
|
- **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`)。
|
||||||
|
- **USB 掛載點未檢查**:Script C 直接 `cp -r ... /mnt/usb/`,`/mnt/usb` 沒掛載時只會失敗一行,
|
||||||
|
整輪測試的 job log 就沒被帶出來。可在複製前先 `mountpoint -q /mnt/usb` 判斷。
|
||||||
|
- **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`。
|
||||||
|
|||||||
@@ -9,6 +9,14 @@ 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)。
|
完整架構見 [ARCHITECTURE.md](ARCHITECTURE.md)。
|
||||||
|
|
||||||
|
**目前狀態(2026-08-25)**:Script A 為 **V1.0.7**(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。
|
||||||
|
測試 job log 收在 DUT 的 `/host/hw-eval/current/jobs/`,Script C 結束時帶時戳複製到 `/mnt/usb/`。
|
||||||
|
最後一次發布是 **V1.0.5**;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
|
## 技術棧
|
||||||
|
|
||||||
- **Host**:Tera Term 5.x TTL macro(`.ttl`),Windows
|
- **Host**:Tera Term 5.x TTL macro(`.ttl`),Windows
|
||||||
@@ -19,6 +27,10 @@ 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
|
- **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`,
|
- **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
|
`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 *`
|
- **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
|
- **無編譯步驟**:TTL 與 bash 都直譯執行
|
||||||
|
|
||||||
@@ -50,24 +62,51 @@ pwr_data # SWB VRM 全軌
|
|||||||
margin_init Blanton_CB_CONN13 && margin_status
|
margin_init Blanton_CB_CONN13 && margin_status
|
||||||
|
|
||||||
# ── SWB loopback 流量(bcmcmd,unit 0/1)─────────────
|
# ── 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
|
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)
|
# 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
|
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 / bmc_monitor_ddr.sh 已停用(改走 bgctl + bmc-manager),檔案仍在
|
||||||
|
|
||||||
|
# ── 背景壓力(平台工具)──────────────────────────────
|
||||||
|
bgctl run /usr/sbin/memtester 1G 100
|
||||||
|
bgctl list
|
||||||
|
bgctl stop --all ; bgctl reset --yes
|
||||||
|
|
||||||
# ── 各工具的 help ───────────────────────────────────
|
# ── 各工具的 help ───────────────────────────────────
|
||||||
blanton_fpga_help ; blanton_cb_i2c_help ; vi2c_help
|
blanton_fpga_help ; blanton_cb_i2c_help ; vi2c_help
|
||||||
temp_sensor_help ; pwr_data_help ; blanton_traffic_linespeed_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:**
|
**Host 端跑一輪測試:**
|
||||||
|
|
||||||
```
|
```
|
||||||
@@ -94,6 +133,10 @@ 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
|
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` /
|
- **Commit**:Conventional Commits,**英文**。scope 用 `ttl` / `fpga` / `i2c` / `vi2c` /
|
||||||
`margin` / `pwr` / `temp` / `docs`
|
`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),
|
- **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
|
完成一項就同步更新,別讓文件跟腳本脫節
|
||||||
|
|
||||||
@@ -130,9 +173,35 @@ 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)。
|
- ⚠️ **`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。
|
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。
|
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 $'\r' <dir>`
|
||||||
|
- ⚠️ **TTL 的 `timeout` 是全域的**:`timeout = N` 之後**每一個** `wait` 都被限制在 N 秒。逾時的 `wait`
|
||||||
|
直接返回而沒吃到 prompt,下一個指令就在前一個還沒跑完時送出,之後整輪錯開一拍。**設了一定要
|
||||||
|
配一個 `timeout = 0` 還原**(`wait_init.ttl` 60→0;Script B 的 cdc_ncm 探測 15→0 在 `:skip_ping`)
|
||||||
|
- ⚠️ **兩張管理網卡同網段會 ARP flux**:`mgmt_ping_monitor.sh` 讓 eth0/eth1 同時 up,同一個 /24 下
|
||||||
|
對端 ARP 可能由任一張卡回應,回包落在沒送封包的那張。`ARP_STRICT=1` 擋掉;判讀時看 `RESULT` 行的
|
||||||
|
`nic_tx`/`nic_rx`(該卡自己的 packet delta)—— **ping 成功但 `nic_tx` 接近 0 = 封包從另一張卡出去的**
|
||||||
|
- ⚠️ **`ip -s link` 的欄位順序是 `bytes packets errors ...`**,要 packet 數取的是**第 2 欄**不是第 1 欄
|
||||||
|
- ⚠️ **`mgmt_ping_monitor.sh` / `bmc_monitor*.sh` 需要 exec bit**,且**不是改用 `bash x.sh start` 就能繞過** ——
|
||||||
|
`do_start` 內部是 `setsid "$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
|
## 資料夾說明
|
||||||
|
|
||||||
@@ -141,6 +210,6 @@ Tera Term 連 COM port (115200-8-N-1)
|
|||||||
- `tools/` — Host / 離線端:`bcm_mibpair_report_V1.1.0.py`(drivshell log → per-pair 報表)、
|
- `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,
|
`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**)
|
||||||
- `publish/` — 交付用打包輸出(`Blanton_Script_ABC_v<ver>_<date>/` + zip)
|
- `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
|
- `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)
|
- `For_AI/` — 🚫 gitignored:AI 協作素材(波形截圖、草稿筆記)
|
||||||
|
|||||||
@@ -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)
|
||||||
@@ -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
|
||||||
@@ -1,7 +1,7 @@
|
|||||||
; =============================================================================
|
; =============================================================================
|
||||||
; Script A for Blanton
|
; Script A for Blanton
|
||||||
; Version : V1.0.2
|
; Version : V1.0.7
|
||||||
; Date : 2026-08-17
|
; Date : 2026-08-25
|
||||||
; Author : ETWen
|
; Author : ETWen
|
||||||
; =============================================================================
|
; =============================================================================
|
||||||
; Version History:
|
; Version History:
|
||||||
@@ -14,7 +14,35 @@
|
|||||||
; ScriptB Remove stress_hhmd, stress_pcie
|
; ScriptB Remove stress_hhmd, stress_pcie
|
||||||
; Blanton_Script Add blanton_traffic_linespeed.sh
|
; Blanton_Script Add blanton_traffic_linespeed.sh
|
||||||
; ScriptB/C Add Traffic Test
|
; 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
|
||||||
; =============================================================================
|
; =============================================================================
|
||||||
include "config.ttl"
|
include "config.ttl"
|
||||||
|
|
||||||
@@ -49,6 +77,76 @@ gettime timestr
|
|||||||
sprintf2 cmd 'sudo date -s "%s %s"' datestr timestr
|
sprintf2 cmd 'sudo date -s "%s %s"' datestr timestr
|
||||||
sendln cmd
|
sendln cmd
|
||||||
|
|
||||||
|
;Stress log clear
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "rm /host/hw-eval/current/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 ==========
|
; ========== Load Shell Script ==========
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "source ~/Blanton_Script/blanton_fpga_pcimem.sh"
|
sendln "source ~/Blanton_Script/blanton_fpga_pcimem.sh"
|
||||||
@@ -72,14 +170,13 @@ include "utils/show_pcie_error_reg_DDR.ttl"
|
|||||||
include "utils/show_pcie_error_reg_I210.ttl"
|
include "utils/show_pcie_error_reg_I210.ttl"
|
||||||
include "utils/show_pcie_error_reg_SSD.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 ==========
|
; ========== Check PCIE tree + PCIE link status + GET PCIE bandwidth Test ==========
|
||||||
include "utils/pcie_bus.ttl"
|
include "utils/pcie_bus.ttl"
|
||||||
|
|
||||||
; ========== Check History ==========
|
|
||||||
;wait prompt_sonic_root
|
|
||||||
;sendln "command"
|
|
||||||
|
|
||||||
; ========== Check Margin ==========
|
; ========== Check Margin ==========
|
||||||
if EN_Margin = 1 then
|
if EN_Margin = 1 then
|
||||||
include "utils/show_margin_status.ttl"
|
include "utils/show_margin_status.ttl"
|
||||||
@@ -88,16 +185,103 @@ endif
|
|||||||
; ========== TAKE DATA ==========
|
; ========== TAKE DATA ==========
|
||||||
include "utils/setup_pmon.ttl"
|
include "utils/setup_pmon.ttl"
|
||||||
include "utils/show_dmesg.ttl"
|
include "utils/show_dmesg.ttl"
|
||||||
wait prompt_sonic_root
|
|
||||||
|
|
||||||
;include "utils/xxx.ttl"
|
;include "utils/xxx.ttl"
|
||||||
;wait prompt_sonic_root
|
;wait prompt_sonic_root
|
||||||
;flushrecv
|
;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 45
|
||||||
|
sendln "~/Blanton_Script/mgmt_ping_monitor.sh stop"
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "cat ~/Blanton_Script/log/mgmt_ping.log"
|
||||||
|
|
||||||
|
|
||||||
|
; ========== 100G Port Status ==========
|
||||||
|
; Lpmode Disable
|
||||||
|
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
|
wait prompt_sonic_root
|
||||||
messagebox 'Start Script B' 'Script A DONE'
|
messagebox 'Start Script B' 'Script A DONE'
|
||||||
@@ -20,33 +20,92 @@ sendln 'chmod +x ~/hammer/tools/amd/mlucas-avx2'
|
|||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "~/hammer/tools/amd/mlucas-avx2 -s l -cpu 0:15 > ~/hammer/tools/amd/mlucas_amm_log 2>&1 &"
|
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'"
|
||||||
|
|
||||||
; ========== DDR MEMORY STRESS TEST ==========
|
; ========== DDR MEMORY STRESS TEST ==========
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "python ~/hammer/tools/stress_mem.py &"
|
sendln "bgctl run /usr/sbin/memtester 1G 100"
|
||||||
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 ==========
|
; ========== SSD read/write ==========
|
||||||
wait prompt_sonic_root
|
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/current/qfx5252-stress-ssd.log"
|
||||||
|
|
||||||
; ========== USB read/write ==========
|
; ========== USB read/write ==========
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "python ~/hammer/tools/stress_usb.py &"
|
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 ==========
|
; ========== SHOW Background job ==========
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "jobs"
|
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"
|
||||||
|
|
||||||
|
|
||||||
|
; ========== 100G Port ==========
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "show interfaces status Ethernet513,Ethernet514"
|
||||||
|
|
||||||
; ========== Take one round of eye measurement on uplink ports ==========
|
|
||||||
|
|
||||||
; ========== Traffic START ==========
|
; ========== 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
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed ps -u 0"
|
sendln "blanton_traffic_linespeed ps -u 0"
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
@@ -54,10 +113,25 @@ sendln "blanton_traffic_linespeed init -u 0"
|
|||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed clear -u 0"
|
sendln "blanton_traffic_linespeed clear -u 0"
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
pause 3
|
pause 15
|
||||||
sendln "blanton_traffic_linespeed show -u 0"
|
sendln "blanton_traffic_linespeed show -u 0"
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed start -u 0"
|
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
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -12,6 +12,21 @@ pause 1
|
|||||||
|
|
||||||
; ========== Kill Process ==========
|
; ========== Kill Process ==========
|
||||||
include "utils/kill_all_process.ttl"
|
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"
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "bgctl reset --yes"
|
||||||
|
; 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 stop"
|
||||||
|
|
||||||
|
|
||||||
; ========== TAKE DATA ==========
|
; ========== TAKE DATA ==========
|
||||||
include "utils/setup_pmon.ttl"
|
include "utils/setup_pmon.ttl"
|
||||||
include "utils/show_dmesg.ttl"
|
include "utils/show_dmesg.ttl"
|
||||||
@@ -25,17 +40,78 @@ include "utils/show_pcie_error_reg_DDR.ttl"
|
|||||||
include "utils/show_pcie_error_reg_I210.ttl"
|
include "utils/show_pcie_error_reg_I210.ttl"
|
||||||
include "utils/show_pcie_error_reg_SSD.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 USB Test result ==========
|
||||||
|
;wait prompt_sonic_root
|
||||||
|
;sendln "journalctl -u qfx5252-bmc-usb-net-test.service --no-pager"
|
||||||
|
|
||||||
|
; ========== 10G/1G MGMT Test result ==========
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "ip -s link show eth0"
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "ip -s link show eth1"
|
||||||
|
|
||||||
|
|
||||||
; ========== CHECK Stress results ==========
|
; ========== CHECK Stress results ==========
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "cat ~/hammer/tools/amd/mlucas_amm_log"
|
sendln "cat ~/hammer/tools/amd/mlucas_amm_log"
|
||||||
wait prompt_sonic_root
|
|
||||||
sendln "cat ~/hammer/tools/log.stress_ssd"
|
|
||||||
|
|
||||||
; ========== CHECK Traffic counters ==========
|
; ========== 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
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed stop -u 0"
|
sendln "blanton_traffic_linespeed stop -u 0"
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed report -u 0"
|
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"
|
||||||
|
|
||||||
|
; ========== Copy Stress Log to USB ==========
|
||||||
|
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/current/jobs/ %s" usb_dst
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln cmd
|
||||||
|
|
||||||
|
; ========== HW Test Session ==========
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "hw-test-session finish"
|
||||||
|
|
||||||
messagebox 'GOOD JOB! Test Case DONE' 'teraterm'
|
messagebox 'GOOD JOB! Test Case DONE' 'teraterm'
|
||||||
+2455
File diff suppressed because it is too large
Load Diff
@@ -1,444 +0,0 @@
|
|||||||
#!/usr/bin/env bash
|
|
||||||
# =============================================================================
|
|
||||||
# blanton_cb_i2c.sh -- CB FPGA (F3) I2C / PMBus over the OpenCores I2C master
|
|
||||||
# =============================================================================
|
|
||||||
# Version History:
|
|
||||||
# V0.1.0 2026-06-16 CB sibling of blanton_icb_i2c.sh. Same OpenCores I2C
|
|
||||||
# handshake, but the I2C block lives in CB FPGA *Function 3*
|
|
||||||
# register space (base 0x300, stride 0x20, Ch0..Ch17), and
|
|
||||||
# is reached via cb_fpga 3 <off> (direct PCIe BAR -> .3/resource0).
|
|
||||||
# =============================================================================
|
|
||||||
#
|
|
||||||
# IMPORTANT (vs the hand-written cb_fpga.md pcimem commands):
|
|
||||||
# * The CB I2C channels are on PCI **Function 3**, so the sysfs file is
|
|
||||||
# .../0000:02:00.3/resource0 (NOT .0). cb_fpga 3 uses FUNCT3_RES for this.
|
|
||||||
# * This tool uses **Repeated START** for reads (write reg pointer with WR only,
|
|
||||||
# no STOP, then Sr + slave|R) so it works for the SMBus/PMBus parts (VRM,
|
|
||||||
# EFUSE) as well as plain register parts. STOP+START only works for the latter.
|
|
||||||
# * Slave addresses are 7-bit here. The spec lists 8-bit pairs (e.g. MAX31790
|
|
||||||
# "0x40/0x41" -> 7-bit 0x20; TCA9546 "0xE8/0xE9" -> 7-bit 0x74). Divide by 2.
|
|
||||||
#
|
|
||||||
# CB FPGA F3 I2C channels (base 0x300, stride 0x20) -- 7-bit addrs in (...):
|
|
||||||
# Ch0 0x300 SWB_0: TCA9546 mux (0x74), M0.C0 temp sensor, ...
|
|
||||||
# Ch1 0x320 SWB_1: TCA9546 mux (0x74), ...
|
|
||||||
# Ch2 0x340 SWB_0: SWB_FPGA (0x40), IO Exp PCA9555 (0x24), ...
|
|
||||||
# Ch3 0x360 SWB_1: SWB_FPGA (0x40), PCA9555 (0x24), ...
|
|
||||||
# Ch4 0x380 SWB_0: M1 TCA9546 mux (0x74), Clk Gen SI5..., ...
|
|
||||||
# Ch5 0x3A0 SWB_1: M1 TCA9546 mux (0x74), ...
|
|
||||||
# Ch6 0x3C0 SWB_0: VRM M29816 (0x20), VRM M2985B (0x21), ... [PMBus]
|
|
||||||
# Ch7 0x3E0 SWB_1: VRM M29816 (0x20), VRM M2985B (0x21), ... [PMBus]
|
|
||||||
# Ch8 0x400 SWB_0: VRM M2985B (0x25), M2985B (0x26), ... [PMBus]
|
|
||||||
# Ch9 0x420 SWB_1: VRM M2985B (0x25), M2985B (0x26), ... [PMBus]
|
|
||||||
# Ch10 0x440 M0 TCA9543 mux (0x70), M0.C0 Clk Buf 9DBL0452, ...
|
|
||||||
# Ch11 0x460 Fan Ctrl MAX31790 (0x20)
|
|
||||||
# Ch12 0x480 ADC leakage ADC128D818 (0x1F)
|
|
||||||
# Ch13 0x4A0 NFC SM-MFAD4-C02 (0x28)
|
|
||||||
# Ch14 0x4C0 M1 TCA9543 mux (0x70), M1.C0 QSFP28.P1 xcvr, ...
|
|
||||||
# Ch15 0x4E0 Fan1/2 EFUSE STEF48H28 (0x10/0x11), ... [PMBus-ish]
|
|
||||||
# Ch16 0x500 1G PHY I210 Ethernet ctrlr (0x49)
|
|
||||||
# Ch17 0x520 Chassis EEPROM (0x28..0x29), Diag EEPROM (0x2B), ...
|
|
||||||
# (slave 7-bit addrs derived from the 8-bit pairs in the register map; verify
|
|
||||||
# against the device datasheet / your board before driving writes.)
|
|
||||||
#
|
|
||||||
# Per-channel register layout (offset from channel base):
|
|
||||||
# +0x00 I2C_PRSCL_LO +0x04 I2C_PRSCL_HI +0x08 I2C_CTRL (bit7 MOD_EN)
|
|
||||||
# +0x0C I2C_TX(W)/I2C_RX(R) +0x10 I2C_CMD(W)/I2C_STAT(R)
|
|
||||||
# +0x14 I2C_MUX_SEL +0x18 I2C_RST (0xD) +0x1C SEM
|
|
||||||
# CMD : STA=0x80 STO=0x40 RD=0x20 WR=0x10 ACK=0x08(1=NACK) IACK=0x01
|
|
||||||
# STAT: RX_ACK=0x80(1=NACK) BUSY=0x40 ARB_LOST=0x20 TIP=0x02 INT_FLAG=0x01
|
|
||||||
# Prescale = (in_clk/(5*scl))-1 @75MHz: 0x88=100kHz, 0x24=400kHz
|
|
||||||
#
|
|
||||||
# Usage:
|
|
||||||
# source blanton_fpga_pcimem.sh # provides cb_fpga / fpga_debug
|
|
||||||
# source blanton_cb_i2c.sh
|
|
||||||
# cb_i2c_init 11 # Ch11 (Fan Ctrl) @100kHz
|
|
||||||
# cb_i2c_scan 11
|
|
||||||
# cb_i2c_read 11 0x20 0x01 1 # MAX31790 (7-bit 0x20) reg 0x01
|
|
||||||
# cb_pmbus_read 6 0x20 0x8B 2 # Ch6 VRM READ_VOUT
|
|
||||||
# =============================================================================
|
|
||||||
|
|
||||||
# --- Pull in the register-access backend (cb_fpga) if not present -----------
|
|
||||||
if ! declare -F cb_fpga >/dev/null 2>&1; then
|
|
||||||
_CBI2C_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" 2>/dev/null && pwd)"
|
|
||||||
if [ -n "$_CBI2C_DIR" ] && [ -f "$_CBI2C_DIR/blanton_fpga_pcimem.sh" ]; then
|
|
||||||
# shellcheck source=/dev/null
|
|
||||||
source "$_CBI2C_DIR/blanton_fpga_pcimem.sh"
|
|
||||||
else
|
|
||||||
echo -e "[\033[33mWARN\033[0m] blanton_cb_i2c.sh: cb_fpga() not found." >&2
|
|
||||||
echo " source blanton_fpga_pcimem.sh first (provides cb_fpga)." >&2
|
|
||||||
fi
|
|
||||||
fi
|
|
||||||
|
|
||||||
# === CB I2C geometry =========================================================
|
|
||||||
CBI2C_FN=3 # CB PCI Function hosting the I2C block
|
|
||||||
CBI2C_BASE=0x300 # channel 0 base offset (relative to F3 resource0)
|
|
||||||
CBI2C_CH_STRIDE=0x20
|
|
||||||
CBI2C_CH_MAX=17
|
|
||||||
|
|
||||||
# Per-channel register offsets
|
|
||||||
_CBI2C_PRSCL_LO=0x00
|
|
||||||
_CBI2C_PRSCL_HI=0x04
|
|
||||||
_CBI2C_CTRL=0x08
|
|
||||||
_CBI2C_TX=0x0C
|
|
||||||
_CBI2C_RX=0x0C
|
|
||||||
_CBI2C_CMD=0x10
|
|
||||||
_CBI2C_STAT=0x10
|
|
||||||
_CBI2C_MUX_SEL=0x14
|
|
||||||
_CBI2C_RST=0x18
|
|
||||||
_CBI2C_SEM=0x1C
|
|
||||||
|
|
||||||
# I2C_CTRL_REG / CMD / STAT bits
|
|
||||||
_CBI2C_EN=0x80
|
|
||||||
_CBI2C_STA=0x80
|
|
||||||
_CBI2C_STO=0x40
|
|
||||||
_CBI2C_RD=0x20
|
|
||||||
_CBI2C_WR=0x10
|
|
||||||
_CBI2C_NACK=0x08
|
|
||||||
_CBI2C_RXACK=0x80
|
|
||||||
_CBI2C_TIP=0x02
|
|
||||||
_CBI2C_RST_VAL=0xD
|
|
||||||
|
|
||||||
# Defaults
|
|
||||||
CB_I2C_PRESCALE_LO="${CB_I2C_PRESCALE_LO:-0x88}" # 100 kHz @ 75 MHz
|
|
||||||
CB_I2C_PRESCALE_HI="${CB_I2C_PRESCALE_HI:-0x00}"
|
|
||||||
CB_I2C_AUTO_INIT="${CB_I2C_AUTO_INIT:-1}"
|
|
||||||
CB_I2C_TIP_POLL_MAX="${CB_I2C_TIP_POLL_MAX:-100}"
|
|
||||||
|
|
||||||
# --- External I2C-mux RESET control (verified on COM34, 2026-06-16) ----------
|
|
||||||
# The TCA9543 muxes on CH10 (M0) and CH14 (M1) have an FPGA-driven, active-low
|
|
||||||
# RESET line. On power-up / FPGA reload the FPGA holds them in reset, so 0x70
|
|
||||||
# does NOT ACK on the root bus and all downstream legs are unreachable.
|
|
||||||
#
|
|
||||||
# The control is a GLOBAL register in CB FPGA *Function 0*, offset 0x7D4
|
|
||||||
# (I2C_MUX_RST_REG) -- NOT the per-channel I2C_MUX_SEL_REG (+0x14) which is a
|
|
||||||
# device-select and does nothing to the RESET pin. Per bit: 1 = release,
|
|
||||||
# 0 = hold-in-reset. Observed default 0xDD (bit1=CH10 mux, bit5=CH14 mux held).
|
|
||||||
# Writing 0xFF releases all external muxes (normal operating state). This value
|
|
||||||
# is volatile and is lost on the next power cycle / FPGA reload.
|
|
||||||
CBI2C_MUX_RST_FN="${CBI2C_MUX_RST_FN:-0}"
|
|
||||||
CBI2C_MUX_RST_OFF="${CBI2C_MUX_RST_OFF:-0x7D4}"
|
|
||||||
|
|
||||||
# Channels whose root bus carries an external mux that hangs off the RESET reg.
|
|
||||||
# CH10/CH14 = TCA9543; CH0/1/4/5 = TCA9546 (SWB/M1) per the channel map above.
|
|
||||||
CBI2C_MUX_CHANNELS="${CBI2C_MUX_CHANNELS:-0 1 4 5 10 14}"
|
|
||||||
|
|
||||||
# Auto-release external mux RESET before scanning / mux-writing a mux channel.
|
|
||||||
CB_I2C_AUTO_MUX_RST="${CB_I2C_AUTO_MUX_RST:-1}"
|
|
||||||
|
|
||||||
# --- Single FPGA register read/write via cb_fpga <fn> <off> [data] ----------
|
|
||||||
# _cbi2c_reg <abs_offset> [data] data present = write, absent = read (echo hex)
|
|
||||||
_cbi2c_reg() {
|
|
||||||
local off="$1" data="${2:-}"
|
|
||||||
if [ -n "$data" ]; then cb_fpga "$CBI2C_FN" "$off" "$data"; else cb_fpga "$CBI2C_FN" "$off"; fi
|
|
||||||
}
|
|
||||||
|
|
||||||
# Channel base absolute offset
|
|
||||||
_cbi2c_chan_base() {
|
|
||||||
local ch="$1"
|
|
||||||
if (( ch < 0 || ch > CBI2C_CH_MAX )); then
|
|
||||||
echo "blanton_cb_i2c: ch must be 0..$CBI2C_CH_MAX" >&2; return 1
|
|
||||||
fi
|
|
||||||
printf '0x%X' $(( CBI2C_BASE + ch * CBI2C_CH_STRIDE ))
|
|
||||||
}
|
|
||||||
|
|
||||||
# Normalize a register read-back to a number string ("0x...." -> 0x....)
|
|
||||||
_cbi2c_num() { local v="$1"; [[ "$v" =~ (0[xX][0-9a-fA-F]+) ]] && echo "${BASH_REMATCH[1]}" || echo "0"; }
|
|
||||||
|
|
||||||
# Write CMD then poll STAT (same offset) until TIP clears; echo final status hex
|
|
||||||
_cbi2c_cmd_wait() {
|
|
||||||
local cmd_off="$1" cmd_val="$2" i status
|
|
||||||
_cbi2c_reg "$cmd_off" "$cmd_val" >/dev/null
|
|
||||||
for (( i=0; i<CB_I2C_TIP_POLL_MAX; i++ )); do
|
|
||||||
status=$(_cbi2c_num "$(_cbi2c_reg "$cmd_off")")
|
|
||||||
if (( (status & _CBI2C_TIP) == 0 )); then
|
|
||||||
printf '0x%X' "$status"; return 0
|
|
||||||
fi
|
|
||||||
done
|
|
||||||
echo -e "[\033[31mERR\033[0m] CB I2C TIP timeout (status=$status)" >&2
|
|
||||||
printf '0x%X' "${status:-0}"; return 1
|
|
||||||
}
|
|
||||||
|
|
||||||
# Check RX_ACK in status (bit7). 0 = ACK, 1 = NACK -> return 1
|
|
||||||
_cbi2c_check_ack() {
|
|
||||||
local status; status=$(_cbi2c_num "$1")
|
|
||||||
(( (status & _CBI2C_RXACK) != 0 )) && return 1 || return 0
|
|
||||||
}
|
|
||||||
|
|
||||||
# === Public: init / reset / semaphore / mux-sel =============================
|
|
||||||
|
|
||||||
# cb_i2c_init <ch> [prescale_lo] [prescale_hi]
|
|
||||||
cb_i2c_init() {
|
|
||||||
[[ $# -lt 1 ]] && { echo "Usage: cb_i2c_init <ch> [prescale_lo] [prescale_hi]"; return 1; }
|
|
||||||
local ch="$1" lo="${2:-$CB_I2C_PRESCALE_LO}" hi="${3:-$CB_I2C_PRESCALE_HI}" base
|
|
||||||
base=$(_cbi2c_chan_base "$ch") || return 1
|
|
||||||
_cbi2c_reg "$(printf '0x%X' $((base + _CBI2C_CTRL)))" 0x00 >/dev/null # disable
|
|
||||||
_cbi2c_reg "$(printf '0x%X' $((base + _CBI2C_PRSCL_LO)))" "$lo" >/dev/null
|
|
||||||
_cbi2c_reg "$(printf '0x%X' $((base + _CBI2C_PRSCL_HI)))" "$hi" >/dev/null
|
|
||||||
_cbi2c_reg "$(printf '0x%X' $((base + _CBI2C_CTRL)))" "$_CBI2C_EN" >/dev/null # enable
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
|
|
||||||
# cb_i2c_reset <ch>
|
|
||||||
cb_i2c_reset() {
|
|
||||||
[[ $# -lt 1 ]] && { echo "Usage: cb_i2c_reset <ch>"; return 1; }
|
|
||||||
local ch="$1" base; base=$(_cbi2c_chan_base "$ch") || return 1
|
|
||||||
_cbi2c_reg "$(printf '0x%X' $((base + _CBI2C_RST)))" "$_CBI2C_RST_VAL" >/dev/null
|
|
||||||
echo " [RST] ch=$ch local I2C controller reset (0xD)"
|
|
||||||
}
|
|
||||||
|
|
||||||
# cb_i2c_sem <ch> [status|acquire [val]|release]
|
|
||||||
cb_i2c_sem() {
|
|
||||||
[[ $# -lt 1 ]] && { echo "Usage: cb_i2c_sem <ch> [status|acquire [val]|release]"; return 1; }
|
|
||||||
local ch="$1" act="${2:-status}" base off cur
|
|
||||||
base=$(_cbi2c_chan_base "$ch") || return 1
|
|
||||||
off=$(printf '0x%X' $((base + _CBI2C_SEM)))
|
|
||||||
case "$act" in
|
|
||||||
status)
|
|
||||||
cur=$(_cbi2c_num "$(_cbi2c_reg "$off")")
|
|
||||||
(( (cur & 0xFF) == 0 )) && echo " [SEM] ch=$ch free (0x00)" \
|
|
||||||
|| printf ' [SEM] ch=%s held (0x%02X)\n' "$ch" $((cur & 0xFF)) ;;
|
|
||||||
acquire)
|
|
||||||
local val="${3:-0x01}"
|
|
||||||
cur=$(_cbi2c_num "$(_cbi2c_reg "$off")")
|
|
||||||
if (( (cur & 0xFF) != 0 )); then
|
|
||||||
printf ' [SEM] ch=%s already held (0x%02X) -- not acquired\n' "$ch" $((cur & 0xFF)); return 1
|
|
||||||
fi
|
|
||||||
_cbi2c_reg "$off" "$val" >/dev/null
|
|
||||||
cur=$(_cbi2c_num "$(_cbi2c_reg "$off")")
|
|
||||||
(( (cur & 0xFF) != 0 )) && printf ' [SEM] ch=%s acquired (0x%02X)\n' "$ch" $((cur & 0xFF)) \
|
|
||||||
|| { echo " [SEM] ch=$ch acquire failed"; return 1; } ;;
|
|
||||||
release)
|
|
||||||
_cbi2c_reg "$off" 0x00 >/dev/null; echo " [SEM] ch=$ch released (0x00)" ;;
|
|
||||||
*) echo "Usage: cb_i2c_sem <ch> [status|acquire [val]|release]"; return 1 ;;
|
|
||||||
esac
|
|
||||||
}
|
|
||||||
|
|
||||||
# cb_i2c_muxsel <ch> <dev_sel> -- write I2C_MUX_SEL_REG (FPGA drives ext mux pins)
|
|
||||||
cb_i2c_muxsel() {
|
|
||||||
[[ $# -lt 2 ]] && { echo "Usage: cb_i2c_muxsel <ch> <dev_sel>"; return 1; }
|
|
||||||
local ch="$1" sel="$2" base; base=$(_cbi2c_chan_base "$ch") || return 1
|
|
||||||
_cbi2c_reg "$(printf '0x%X' $((base + _CBI2C_MUX_SEL)))" "$sel" >/dev/null
|
|
||||||
printf ' [MUXSEL] ch=%s DEV_SEL <= 0x%02X\n' "$ch" $((sel & 0xFF))
|
|
||||||
}
|
|
||||||
|
|
||||||
# cb_i2c_mux_reset_release -- de-assert ALL external mux RESET lines (F0 0x7D4 <= 0xFF)
|
|
||||||
# Global, not per-channel. Volatile: lost on power cycle / FPGA reload.
|
|
||||||
cb_i2c_mux_reset_release() {
|
|
||||||
cb_fpga "$CBI2C_MUX_RST_FN" "$CBI2C_MUX_RST_OFF" 0xFF >/dev/null
|
|
||||||
local rb; rb=$(_cbi2c_num "$(cb_fpga "$CBI2C_MUX_RST_FN" "$CBI2C_MUX_RST_OFF")")
|
|
||||||
printf ' [MUX-RST] I2C_MUX_RST_REG (F%s %s) <= 0xFF (all external muxes released, readback %s)\n' \
|
|
||||||
"$CBI2C_MUX_RST_FN" "$CBI2C_MUX_RST_OFF" "$rb"
|
|
||||||
}
|
|
||||||
|
|
||||||
# _cbi2c_is_mux_channel <ch> -- 0 (true) if ch is in CBI2C_MUX_CHANNELS
|
|
||||||
_cbi2c_is_mux_channel() {
|
|
||||||
local ch="$1" c
|
|
||||||
for c in $CBI2C_MUX_CHANNELS; do [[ "$c" == "$ch" ]] && return 0; done
|
|
||||||
return 1
|
|
||||||
}
|
|
||||||
|
|
||||||
# _cbi2c_auto_mux_rst <ch> -- release external mux RESET if ch is a mux channel
|
|
||||||
_cbi2c_auto_mux_rst() {
|
|
||||||
[[ "$CB_I2C_AUTO_MUX_RST" == "1" ]] || return 0
|
|
||||||
_cbi2c_is_mux_channel "$1" || return 0
|
|
||||||
cb_i2c_mux_reset_release
|
|
||||||
}
|
|
||||||
|
|
||||||
# === Core transfers (Repeated START, SMBus/PMBus compatible) =================
|
|
||||||
|
|
||||||
# _cbi2c_xfer_read <ch> <slave7> <reg> <nbytes> echoes space-separated hex bytes
|
|
||||||
_cbi2c_xfer_read() {
|
|
||||||
local ch="$1" slave="$2" reg="$3" n="$4" base tx cmd rx status i last cmdv val out=""
|
|
||||||
base=$(_cbi2c_chan_base "$ch") || return 1
|
|
||||||
tx=$(printf '0x%X' $((base + _CBI2C_TX)))
|
|
||||||
cmd=$(printf '0x%X' $((base + _CBI2C_CMD)))
|
|
||||||
rx=$(printf '0x%X' $((base + _CBI2C_RX)))
|
|
||||||
[[ "$CB_I2C_AUTO_INIT" == "1" ]] && cb_i2c_init "$ch" >/dev/null
|
|
||||||
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $(( (slave << 1) & 0xFF )))" >/dev/null
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' $((_CBI2C_STA | _CBI2C_WR)))")
|
|
||||||
_cbi2c_check_ack "$status" || { echo "ERR: NACK on slave addr (W) 0x$(printf %02X "$slave")" >&2; return 1; }
|
|
||||||
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $((reg & 0xFF)))" >/dev/null
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' $((_CBI2C_WR)))") # WR only, no STOP
|
|
||||||
_cbi2c_check_ack "$status" || { echo "ERR: NACK on reg 0x$(printf %02X "$reg")" >&2; return 1; }
|
|
||||||
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $(( ((slave << 1) | 1) & 0xFF )))" >/dev/null
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' $((_CBI2C_STA | _CBI2C_WR)))") # Repeated START
|
|
||||||
_cbi2c_check_ack "$status" || { echo "ERR: NACK on slave addr (R) 0x$(printf %02X "$slave")" >&2; return 1; }
|
|
||||||
|
|
||||||
for (( i=0; i<n; i++ )); do
|
|
||||||
last=$(( i == n-1 ))
|
|
||||||
if (( last )); then cmdv=$(( _CBI2C_RD | _CBI2C_NACK | _CBI2C_STO )); else cmdv=$(( _CBI2C_RD )); fi
|
|
||||||
_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' "$cmdv")" >/dev/null
|
|
||||||
val=$(_cbi2c_num "$(_cbi2c_reg "$rx")")
|
|
||||||
out+="$(printf '0x%02X ' $((val & 0xFF)))"
|
|
||||||
done
|
|
||||||
echo "${out% }"
|
|
||||||
}
|
|
||||||
|
|
||||||
# _cbi2c_xfer_write <ch> <slave7> <reg> <byte> [byte...]
|
|
||||||
_cbi2c_xfer_write() {
|
|
||||||
local ch="$1" slave="$2" reg="$3"; shift 3
|
|
||||||
local base tx cmd status b last cmdv n=$# idx=0
|
|
||||||
[[ $n -lt 1 ]] && { echo "ERR: no data bytes" >&2; return 1; }
|
|
||||||
base=$(_cbi2c_chan_base "$ch") || return 1
|
|
||||||
tx=$(printf '0x%X' $((base + _CBI2C_TX)))
|
|
||||||
cmd=$(printf '0x%X' $((base + _CBI2C_CMD)))
|
|
||||||
[[ "$CB_I2C_AUTO_INIT" == "1" ]] && cb_i2c_init "$ch" >/dev/null
|
|
||||||
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $(( (slave << 1) & 0xFF )))" >/dev/null
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' $((_CBI2C_STA | _CBI2C_WR)))")
|
|
||||||
_cbi2c_check_ack "$status" || { echo "ERR: NACK on slave addr (W) 0x$(printf %02X "$slave")" >&2; return 1; }
|
|
||||||
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $((reg & 0xFF)))" >/dev/null
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' $((_CBI2C_WR)))")
|
|
||||||
_cbi2c_check_ack "$status" || { echo "ERR: NACK on reg 0x$(printf %02X "$reg")" >&2; return 1; }
|
|
||||||
|
|
||||||
for b in "$@"; do
|
|
||||||
idx=$((idx+1)); last=$(( idx == n ))
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $(( $((b)) & 0xFF )))" >/dev/null
|
|
||||||
if (( last )); then cmdv=$(( _CBI2C_WR | _CBI2C_STO )); else cmdv=$(( _CBI2C_WR )); fi
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' "$cmdv")")
|
|
||||||
_cbi2c_check_ack "$status" || { echo "ERR: NACK on data byte #$idx" >&2; return 1; }
|
|
||||||
done
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
|
|
||||||
# _cbi2c_xfer_cmd_only <ch> <slave7> <cmd> -- START+W, cmd byte, STOP (no data)
|
|
||||||
_cbi2c_xfer_cmd_only() {
|
|
||||||
local ch="$1" slave="$2" cc="$3" base tx cmd status
|
|
||||||
base=$(_cbi2c_chan_base "$ch") || return 1
|
|
||||||
tx=$(printf '0x%X' $((base + _CBI2C_TX)))
|
|
||||||
cmd=$(printf '0x%X' $((base + _CBI2C_CMD)))
|
|
||||||
[[ "$CB_I2C_AUTO_INIT" == "1" ]] && cb_i2c_init "$ch" >/dev/null
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $(( (slave << 1) & 0xFF )))" >/dev/null
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' $((_CBI2C_STA | _CBI2C_WR)))")
|
|
||||||
_cbi2c_check_ack "$status" || { echo "ERR: NACK on slave addr (W) 0x$(printf %02X "$slave")" >&2; return 1; }
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $((cc & 0xFF)))" >/dev/null
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' $((_CBI2C_WR | _CBI2C_STO)))")
|
|
||||||
_cbi2c_check_ack "$status" || { echo "ERR: NACK on cmd 0x$(printf %02X "$cc")" >&2; return 1; }
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
|
|
||||||
# === Public: generic I2C =====================================================
|
|
||||||
|
|
||||||
# cb_i2c_read <ch> <slave> <reg> [nbytes]
|
|
||||||
cb_i2c_read() {
|
|
||||||
[[ $# -lt 3 ]] && { echo "Usage: cb_i2c_read <ch> <slave> <reg> [nbytes]"; return 1; }
|
|
||||||
local ch="$1" slave=$(( $2 )) reg=$(( $3 )) n="${4:-1}" bytes
|
|
||||||
bytes=$(_cbi2c_xfer_read "$ch" "$slave" "$reg" "$n") || return 1
|
|
||||||
printf ' [I2C-R] ch=%s slave=0x%02X reg=0x%02X => [%s]\n' "$ch" "$slave" "$reg" "$bytes"
|
|
||||||
}
|
|
||||||
|
|
||||||
# cb_i2c_write <ch> <slave> <reg> <byte> [byte...]
|
|
||||||
cb_i2c_write() {
|
|
||||||
[[ $# -lt 4 ]] && { echo "Usage: cb_i2c_write <ch> <slave> <reg> <byte> [byte...]"; return 1; }
|
|
||||||
local ch="$1" slave=$(( $2 )) reg=$(( $3 )); shift 3
|
|
||||||
_cbi2c_xfer_write "$ch" "$slave" "$reg" "$@" || return 1
|
|
||||||
printf ' [I2C-W] ch=%s slave=0x%02X reg=0x%02X <= [%s]\n' "$ch" "$slave" "$reg" "$*"
|
|
||||||
}
|
|
||||||
|
|
||||||
# cb_i2c_muxwrite <ch> <mux_slave> <ctrl_byte> -- raw 1-byte write, no reg (TCA954x)
|
|
||||||
cb_i2c_muxwrite() {
|
|
||||||
[[ $# -lt 3 ]] && { echo "Usage: cb_i2c_muxwrite <ch> <mux_slave> <ctrl_byte>"; return 1; }
|
|
||||||
local ch="$1" slave=$(( $2 )) val=$(( $3 )) base tx cmd status
|
|
||||||
base=$(_cbi2c_chan_base "$ch") || return 1
|
|
||||||
tx=$(printf '0x%X' $((base + _CBI2C_TX)))
|
|
||||||
cmd=$(printf '0x%X' $((base + _CBI2C_CMD)))
|
|
||||||
[[ "$CB_I2C_AUTO_INIT" == "1" ]] && cb_i2c_init "$ch" >/dev/null
|
|
||||||
_cbi2c_auto_mux_rst "$ch"
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $(( (slave << 1) & 0xFF )))" >/dev/null
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' $((_CBI2C_STA | _CBI2C_WR)))")
|
|
||||||
_cbi2c_check_ack "$status" || { echo "ERR: NACK on mux addr 0x$(printf %02X "$slave")" >&2; return 1; }
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $((val & 0xFF)))" >/dev/null
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' $((_CBI2C_WR | _CBI2C_STO)))")
|
|
||||||
_cbi2c_check_ack "$status" || { echo "ERR: NACK on mux ctrl byte" >&2; return 1; }
|
|
||||||
printf ' [MUX-W] ch=%s mux=0x%02X <= 0x%02X\n' "$ch" "$slave" "$val"
|
|
||||||
}
|
|
||||||
|
|
||||||
# cb_i2c_scan <ch> -- probe 0x08..0x77, report slaves that ACK
|
|
||||||
cb_i2c_scan() {
|
|
||||||
[[ $# -lt 1 ]] && { echo "Usage: cb_i2c_scan <ch>"; return 1; }
|
|
||||||
local ch="$1" base tx cmd a status found=""
|
|
||||||
base=$(_cbi2c_chan_base "$ch") || return 1
|
|
||||||
tx=$(printf '0x%X' $((base + _CBI2C_TX)))
|
|
||||||
cmd=$(printf '0x%X' $((base + _CBI2C_CMD)))
|
|
||||||
cb_i2c_init "$ch" >/dev/null
|
|
||||||
_cbi2c_auto_mux_rst "$ch"
|
|
||||||
for (( a=0x08; a<=0x77; a++ )); do
|
|
||||||
_cbi2c_reg "$tx" "$(printf '0x%X' $(( (a << 1) & 0xFF )))" >/dev/null
|
|
||||||
status=$(_cbi2c_cmd_wait "$cmd" "$(printf '0x%X' $((_CBI2C_STA | _CBI2C_WR | _CBI2C_STO)))")
|
|
||||||
_cbi2c_check_ack "$status" && found+="$(printf '0x%02X ' "$a")"
|
|
||||||
done
|
|
||||||
[[ -n "$found" ]] && echo " [SCAN] ch=$ch found: ${found% }" || echo " [SCAN] ch=$ch no devices"
|
|
||||||
}
|
|
||||||
|
|
||||||
# === Public: PMBus (== SMBus; command code + Repeated START read) ============
|
|
||||||
|
|
||||||
# cb_pmbus_read <ch> <slave> <cmd> [nbytes] (default 2 bytes, LSB first)
|
|
||||||
cb_pmbus_read() {
|
|
||||||
[[ $# -lt 3 ]] && { echo "Usage: cb_pmbus_read <ch> <slave> <cmd> [nbytes]"; return 1; }
|
|
||||||
local ch="$1" slave=$(( $2 )) cc=$(( $3 )) n="${4:-2}" bytes
|
|
||||||
bytes=$(_cbi2c_xfer_read "$ch" "$slave" "$cc" "$n") || return 1
|
|
||||||
if [[ "$n" == "2" ]]; then
|
|
||||||
local b0 b1 word; b0=$(( $(echo "$bytes" | awk '{print $1}') )); b1=$(( $(echo "$bytes" | awk '{print $2}') ))
|
|
||||||
word=$(( b0 | (b1 << 8) ))
|
|
||||||
printf ' [PMB-R] ch=%s slave=0x%02X cmd=0x%02X => 0x%04X raw=[%s] linear16=%s\n' \
|
|
||||||
"$ch" "$slave" "$cc" "$word" "$bytes" "$(cb_pmbus_linear16 "$word")"
|
|
||||||
else
|
|
||||||
printf ' [PMB-R] ch=%s slave=0x%02X cmd=0x%02X => [%s]\n' "$ch" "$slave" "$cc" "$bytes"
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
# cb_pmbus_write <ch> <slave> <cmd> [data byte...] (no byte = send-byte)
|
|
||||||
cb_pmbus_write() {
|
|
||||||
[[ $# -lt 3 ]] && { echo "Usage: cb_pmbus_write <ch> <slave> <cmd> [data byte...]"; return 1; }
|
|
||||||
local ch="$1" slave=$(( $2 )) cc=$(( $3 )); shift 3
|
|
||||||
if [[ $# -eq 0 ]]; then
|
|
||||||
_cbi2c_xfer_cmd_only "$ch" "$slave" "$cc" || return 1
|
|
||||||
printf ' [PMB-W] ch=%s slave=0x%02X cmd=0x%02X <= (send-byte)\n' "$ch" "$slave" "$cc"; return 0
|
|
||||||
fi
|
|
||||||
_cbi2c_xfer_write "$ch" "$slave" "$cc" "$@" || return 1
|
|
||||||
printf ' [PMB-W] ch=%s slave=0x%02X cmd=0x%02X <= [%s]\n' "$ch" "$slave" "$cc" "$*"
|
|
||||||
}
|
|
||||||
|
|
||||||
# cb_pmbus_linear16 <word>
|
|
||||||
cb_pmbus_linear16() {
|
|
||||||
local word=$(( $1 & 0xFFFF ))
|
|
||||||
awk -v w="$word" 'BEGIN{
|
|
||||||
e=int(w/2048)%32; if(e>15)e-=32;
|
|
||||||
m=w%2048; if(m>1023)m-=2048;
|
|
||||||
printf "%.4f", m * (2.0 ^ e);
|
|
||||||
}'
|
|
||||||
}
|
|
||||||
|
|
||||||
# === Help ====================================================================
|
|
||||||
blanton_cb_i2c_help() {
|
|
||||||
echo -e "\033[1mblanton_cb_i2c.sh - CB FPGA (F3) I2C / PMBus over OpenCores I2C master\033[0m"
|
|
||||||
echo ""
|
|
||||||
echo -e " Backend: \033[36mcb_fpga $CBI2C_FN\033[0m (direct PCIe BAR -> .3/resource0), base 0x300, Ch0..$CBI2C_CH_MAX"
|
|
||||||
echo ""
|
|
||||||
echo -e "\033[1mSetup\033[0m"
|
|
||||||
echo -e " \033[33mcb_i2c_init\033[0m <ch> [pre_lo] [pre_hi] prescale + enable (def 0x88/0x00 = 100kHz)"
|
|
||||||
echo -e " \033[33mcb_i2c_reset\033[0m <ch> LCL_RST=0xD"
|
|
||||||
echo -e " \033[33mcb_i2c_sem\033[0m <ch> [status|acquire [v]|release]"
|
|
||||||
echo -e " \033[33mcb_i2c_muxsel\033[0m <ch> <dev_sel> write I2C_MUX_SEL_REG"
|
|
||||||
echo -e " \033[33mcb_i2c_mux_reset_release\033[0m de-assert ALL ext mux RESET (F0 0x7D4<=0xFF)"
|
|
||||||
echo ""
|
|
||||||
echo -e "\033[1mGeneric I2C\033[0m"
|
|
||||||
echo -e " \033[33mcb_i2c_scan\033[0m <ch>"
|
|
||||||
echo -e " \033[33mcb_i2c_read\033[0m <ch> <slave> <reg> [nbytes]"
|
|
||||||
echo -e " \033[33mcb_i2c_write\033[0m <ch> <slave> <reg> <byte> [byte...]"
|
|
||||||
echo -e " \033[33mcb_i2c_muxwrite\033[0m <ch> <mux_slave> <ctrl_byte> raw 1-byte (TCA954x)"
|
|
||||||
echo ""
|
|
||||||
echo -e "\033[1mPMBus / SMBus\033[0m"
|
|
||||||
echo -e " \033[33mcb_pmbus_read\033[0m <ch> <slave> <cmd> [nbytes] (def 2, LE word + linear16)"
|
|
||||||
echo -e " \033[33mcb_pmbus_write\033[0m <ch> <slave> <cmd> [byte...]"
|
|
||||||
echo -e " \033[33mcb_pmbus_linear16\033[0m <word>"
|
|
||||||
echo ""
|
|
||||||
echo -e " Slave = 7-bit (tool shifts). Spec lists 8-bit pairs -> divide by 2."
|
|
||||||
echo -e " \033[33mfpga_debug on\033[0m to see every underlying pcimem command."
|
|
||||||
}
|
|
||||||
|
|
||||||
blanton_cb_i2c_help
|
|
||||||
@@ -1,270 +0,0 @@
|
|||||||
#!/usr/bin/env bash
|
|
||||||
# =============================================================================
|
|
||||||
# blanton_fpga_pcimem.sh -- pcimem backend, sysfs resource file + relative offset
|
|
||||||
# =============================================================================
|
|
||||||
# Version History:
|
|
||||||
# V1.3.0 2026-06-12 pcimem variant (SONiC hardware). memtool variant: blanton_fpga_memtool.sh
|
|
||||||
# Version number kept in sync with blanton_fpga_memtool.sh
|
|
||||||
# V1.4.0 2026-06-15 Fix: VSPI window bases pointed at the VSPI-Flash block
|
|
||||||
# (0x340/0x380/0x3C0/0x400, config-flash channel) so register
|
|
||||||
# reads returned 0; corrected to the VSPI register block
|
|
||||||
# (PMC 0x640 / ICB 0x680 / SWB0 0x6C0 / SWB1 0x700)
|
|
||||||
# Add: _vspi_fnwarn guard - warns when PMC/ICB/SWB are called with
|
|
||||||
# cb_fpga-style "<fn> <addr>" (a read turning into a write)
|
|
||||||
# Change: suppress pcimem write stdout noise (mmap/Written lines)
|
|
||||||
# Docs: comments/help translated to English (ASCII-only for SONiC console)
|
|
||||||
# V1.4.1 2026-06-23 Fix: BDF in example auto-detect was wrong (02:00 vs 04:00); corrected to match the lspci example.
|
|
||||||
# =============================================================================
|
|
||||||
#
|
|
||||||
# SONiC hardware has no memtool / devmem, but it has pcimem. pcimem mmaps the PCI
|
|
||||||
# sysfs resource file directly and takes "resource file + offset relative to BAR
|
|
||||||
# start", not an absolute physical address.
|
|
||||||
#
|
|
||||||
# pcimem { sysfile } { offset } [ type*count [ data ] ]
|
|
||||||
# sysfile : sysfs file for the pci resource (e.g. .../resource0)
|
|
||||||
# offset : offset into pci memory region
|
|
||||||
# type : [b]yte, [h]alfword, [w]ord, [d]ouble-word
|
|
||||||
# *count : number of items (w*100 dump 100 words)
|
|
||||||
# data : data to be written
|
|
||||||
#
|
|
||||||
# This tool always accesses as word (w, 32-bit).
|
|
||||||
#
|
|
||||||
# After sourcing this file the following functions are available:
|
|
||||||
# cb_fpga <fn:0-3> <addr> [data]
|
|
||||||
# pmc_fpga <addr> [data]
|
|
||||||
# icb_fpga <addr> [data]
|
|
||||||
# swb0_fpga <addr> [data]
|
|
||||||
# swb1_fpga <addr> [data]
|
|
||||||
#
|
|
||||||
# data present = write, absent = read.
|
|
||||||
# Usage: source blanton_fpga_pcimem.sh
|
|
||||||
|
|
||||||
# === CB FPGA PCIe resource file (sysfs) ===
|
|
||||||
# Use lspci -D to find the BDF (domain:bus:dev.fn); resource0 is the sysfs mapping of BAR0.
|
|
||||||
# e.g. lspci -Dnn | grep -i fpga -> 0000:02:00.0 ...
|
|
||||||
# memtool variant fills in the BAR value; pcimem variant fills in the resource file
|
|
||||||
# path instead (offset becomes relative to BAR).
|
|
||||||
FUNCT0_RES=/sys/bus/pci/devices/0000:04:00.0/resource0
|
|
||||||
FUNCT1_RES=/sys/bus/pci/devices/0000:04:00.1/resource0
|
|
||||||
FUNCT2_RES=/sys/bus/pci/devices/0000:04:00.2/resource0
|
|
||||||
FUNCT3_RES=/sys/bus/pci/devices/0000:04:00.3/resource0
|
|
||||||
|
|
||||||
# Auto-detect example (uncomment to use; needs the FPGA's BDF prefix):
|
|
||||||
# _BDF=0000:02:00
|
|
||||||
# FUNCT0_RES=/sys/bus/pci/devices/${_BDF}.0/resource0
|
|
||||||
# FUNCT1_RES=/sys/bus/pci/devices/${_BDF}.1/resource0
|
|
||||||
# FUNCT2_RES=/sys/bus/pci/devices/${_BDF}.2/resource0
|
|
||||||
# FUNCT3_RES=/sys/bus/pci/devices/${_BDF}.3/resource0
|
|
||||||
|
|
||||||
# === VSPI window base offset (relative to CB Function 2 resource0 start) ===
|
|
||||||
# NOTE: CB.F2 has TWO near-identical VSPI register blocks (see spec register map):
|
|
||||||
# - VSPI-Flash-* @ 0x340/0x380/0x3C0/0x400 -> accesses the remote FPGA's CONFIG FLASH
|
|
||||||
# - VSPI-* @ 0x640/0x680/0x6C0/0x700 -> accesses the remote FPGA's REGISTERS
|
|
||||||
# This tool reads/writes remote registers, so it uses the VSPI-* block (0x640+).
|
|
||||||
# The VSPI-Flash bases are kept below (commented) in case flash access is needed later.
|
|
||||||
VSPI_PMC_BASE=0x640
|
|
||||||
VSPI_ICB_BASE=0x680
|
|
||||||
VSPI_SWB0_BASE=0x6C0
|
|
||||||
VSPI_SWB1_BASE=0x700
|
|
||||||
|
|
||||||
# VSPI-Flash window bases (config-flash access, not register access):
|
|
||||||
# VSPI_FLASH_PMC_BASE=0x340
|
|
||||||
# VSPI_FLASH_ICB_BASE=0x380
|
|
||||||
# VSPI_FLASH_SWB0_BASE=0x3C0
|
|
||||||
# VSPI_FLASH_SWB1_BASE=0x400
|
|
||||||
|
|
||||||
# === VSPI protocol constants ===
|
|
||||||
_VSPI_CMD_STAT=0x00
|
|
||||||
_VSPI_ADDR=0x04
|
|
||||||
_VSPI_WR_DATA=0x08
|
|
||||||
_VSPI_RD_DATA=0x0C
|
|
||||||
_VSPI_NEW_CMD=0x01
|
|
||||||
_VSPI_READ_W=0x02
|
|
||||||
_VSPI_WRITE_W=0x04
|
|
||||||
_VSPI_READY_MASK=0x100
|
|
||||||
_VSPI_POLL_MAX=200
|
|
||||||
|
|
||||||
# === pcimem command ===
|
|
||||||
PCIMEM_CMD="${PCIMEM_CMD:-pcimem}"
|
|
||||||
|
|
||||||
# === Debug mode (1=print commands AND execute, 0=execute only) ===
|
|
||||||
DEBUG_MODE=${DEBUG_MODE:-0}
|
|
||||||
|
|
||||||
fpga_debug() {
|
|
||||||
if [ "${1:-}" = "on" ]; then DEBUG_MODE=1
|
|
||||||
elif [ "${1:-}" = "off" ]; then DEBUG_MODE=0
|
|
||||||
else [ "$DEBUG_MODE" = "0" ] && DEBUG_MODE=1 || DEBUG_MODE=0; fi
|
|
||||||
echo -e "[\033[34mINFO\033[0m] DEBUG_MODE=$DEBUG_MODE"
|
|
||||||
}
|
|
||||||
|
|
||||||
# Wrapper: debug mode prints command (to stderr) AND executes, normal mode executes only.
|
|
||||||
# On read, returns the parsed hex value (stripping pcimem's mmap noise).
|
|
||||||
# Usage: _pcimem <sysfile> <offset> [data] (data present = write, absent = read)
|
|
||||||
_pcimem() {
|
|
||||||
local sysfile="$1" offset="$2" data="${3:-}"
|
|
||||||
if [[ -n "$data" ]]; then
|
|
||||||
[ "$DEBUG_MODE" = "1" ] && \
|
|
||||||
echo -e "\033[90m[DEBG] $PCIMEM_CMD $sysfile $offset w $data\033[0m" >&2
|
|
||||||
# Write output (opened / Target offset / mmap / Written...readback) is never
|
|
||||||
# parsed -> drop stdout noise; keep stderr so real errors still surface.
|
|
||||||
$PCIMEM_CMD "$sysfile" "$offset" w "$data" >/dev/null
|
|
||||||
else
|
|
||||||
[ "$DEBUG_MODE" = "1" ] && \
|
|
||||||
echo -e "\033[90m[DEBG] $PCIMEM_CMD $sysfile $offset w\033[0m" >&2
|
|
||||||
# pcimem read prints mmap info + "Value at offset ...: 0xXXXX";
|
|
||||||
# take the last 0x... token as the actual read-back value.
|
|
||||||
$PCIMEM_CMD "$sysfile" "$offset" w | grep -oiE '0x[0-9a-f]+' | tail -1
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
# --- Internal VSPI helpers (all hang off CB Function 2's resource0) ---
|
|
||||||
|
|
||||||
_vspi_read() {
|
|
||||||
local win_off="$1" remote_offset="$2"
|
|
||||||
local cmd_off add_off rd_off addr_val status i
|
|
||||||
|
|
||||||
cmd_off=$(printf '0x%X' $(( win_off + _VSPI_CMD_STAT )))
|
|
||||||
add_off=$(printf '0x%X' $(( win_off + _VSPI_ADDR )))
|
|
||||||
rd_off=$(printf '0x%X' $(( win_off + _VSPI_RD_DATA )))
|
|
||||||
addr_val=$(printf '0x%08X' $(( (0x0 << 20) | (remote_offset & 0xFFFFF) )))
|
|
||||||
|
|
||||||
_pcimem "$FUNCT2_RES" "$add_off" "$addr_val"
|
|
||||||
_pcimem "$FUNCT2_RES" "$cmd_off" $(printf '0x%X' $(( _VSPI_NEW_CMD | _VSPI_READ_W )))
|
|
||||||
|
|
||||||
for (( i=0; i<_VSPI_POLL_MAX; i++ )); do
|
|
||||||
status=$(_pcimem "$FUNCT2_RES" "$cmd_off")
|
|
||||||
if (( ( ${status:-0} & _VSPI_READY_MASK) != 0 )); then
|
|
||||||
_pcimem "$FUNCT2_RES" "$rd_off"
|
|
||||||
return 0
|
|
||||||
fi
|
|
||||||
done
|
|
||||||
echo "ERROR: VSPI read timeout @ offset $remote_offset" >&2
|
|
||||||
return 1
|
|
||||||
}
|
|
||||||
|
|
||||||
_vspi_write() {
|
|
||||||
local win_off="$1" remote_offset="$2" data="$3"
|
|
||||||
local cmd_off add_off wr_off addr_val status i
|
|
||||||
|
|
||||||
cmd_off=$(printf '0x%X' $(( win_off + _VSPI_CMD_STAT )))
|
|
||||||
add_off=$(printf '0x%X' $(( win_off + _VSPI_ADDR )))
|
|
||||||
wr_off=$(printf '0x%X' $(( win_off + _VSPI_WR_DATA )))
|
|
||||||
addr_val=$(printf '0x%08X' $(( (0x0 << 20) | (remote_offset & 0xFFFFF) )))
|
|
||||||
|
|
||||||
_pcimem "$FUNCT2_RES" "$wr_off" "$data"
|
|
||||||
_pcimem "$FUNCT2_RES" "$add_off" "$addr_val"
|
|
||||||
_pcimem "$FUNCT2_RES" "$cmd_off" $(printf '0x%X' $(( _VSPI_NEW_CMD | _VSPI_WRITE_W )))
|
|
||||||
|
|
||||||
for (( i=0; i<_VSPI_POLL_MAX; i++ )); do
|
|
||||||
status=$(_pcimem "$FUNCT2_RES" "$cmd_off")
|
|
||||||
if (( ( ${status:-0} & _VSPI_READY_MASK) != 0 )); then
|
|
||||||
return 0
|
|
||||||
fi
|
|
||||||
done
|
|
||||||
echo "ERROR: VSPI write timeout @ offset $remote_offset" >&2
|
|
||||||
return 1
|
|
||||||
}
|
|
||||||
|
|
||||||
# Guard: PMC/ICB/SWB are single-function; signature is <addr> [data], NO fn arg.
|
|
||||||
# Common pitfall: using cb_fpga's "<fn> <addr>" form -> 2nd arg becomes data, a read
|
|
||||||
# turns into a write. If addr is 0~3 (looks like fn) AND data is given, warn and
|
|
||||||
# confirm; on a non-tty (script) just warn, don't block.
|
|
||||||
# Usage: _vspi_fnwarn <name> <addr> <data> non-zero return = cancel
|
|
||||||
_vspi_fnwarn() {
|
|
||||||
local name="$1" addr="$2" data="$3"
|
|
||||||
[[ -z "$data" ]] && return 0 # read, nothing to warn
|
|
||||||
case "$addr" in
|
|
||||||
0|1|2|3|0x0|0x1|0x2|0x3|0x00|0x01|0x02|0x03) ;; # looks like fn, warn below
|
|
||||||
*) return 0 ;; # normal offset, allow
|
|
||||||
esac
|
|
||||||
echo -e "[\033[33mWARN\033[0m] $name has no fn arg; signature is <addr> [data] (NOT cb_fpga's <fn> <addr>)." >&2
|
|
||||||
echo -e " This will WRITE $data to PMC/ICB/SWB offset $addr." >&2
|
|
||||||
echo -e " To READ offset $addr, pass a single arg: $name $addr" >&2
|
|
||||||
if [ -t 0 ]; then
|
|
||||||
local ans
|
|
||||||
read -r -p " Proceed with write anyway? [y/N] " ans
|
|
||||||
case "$ans" in
|
|
||||||
y|Y|yes|YES) return 0 ;;
|
|
||||||
*) echo " Cancelled." >&2; return 1 ;;
|
|
||||||
esac
|
|
||||||
fi
|
|
||||||
return 0
|
|
||||||
}
|
|
||||||
|
|
||||||
# === Public functions ===
|
|
||||||
|
|
||||||
cb_fpga() {
|
|
||||||
if [[ $# -lt 2 ]]; then
|
|
||||||
echo "Usage: cb_fpga <fn:0-3> <addr> [data]"; return 1
|
|
||||||
fi
|
|
||||||
local fn="$1" addr="$2" data="${3:-}" res
|
|
||||||
case "$fn" in
|
|
||||||
0) res=$FUNCT0_RES ;; 1) res=$FUNCT1_RES ;;
|
|
||||||
2) res=$FUNCT2_RES ;; 3) res=$FUNCT3_RES ;;
|
|
||||||
*) echo "cb_fpga: fn must be 0-3" >&2; return 1 ;;
|
|
||||||
esac
|
|
||||||
# pcimem offset is relative to BAR start; do not add BAR.
|
|
||||||
if [[ -z "$data" ]]; then
|
|
||||||
_pcimem "$res" "$addr"
|
|
||||||
else
|
|
||||||
_pcimem "$res" "$addr" "$data"
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
pmc_fpga() {
|
|
||||||
if [[ $# -lt 1 ]]; then
|
|
||||||
echo "Usage: pmc_fpga <addr> [data]"; return 1
|
|
||||||
fi
|
|
||||||
local addr="$1" data="${2:-}"
|
|
||||||
_vspi_fnwarn pmc_fpga "$addr" "$data" || return 1
|
|
||||||
if [[ -z "$data" ]]; then _vspi_read "$VSPI_PMC_BASE" "$addr"
|
|
||||||
else _vspi_write "$VSPI_PMC_BASE" "$addr" "$data"; fi
|
|
||||||
}
|
|
||||||
|
|
||||||
icb_fpga() {
|
|
||||||
if [[ $# -lt 1 ]]; then
|
|
||||||
echo "Usage: icb_fpga <addr> [data]"; return 1
|
|
||||||
fi
|
|
||||||
local addr="$1" data="${2:-}"
|
|
||||||
_vspi_fnwarn icb_fpga "$addr" "$data" || return 1
|
|
||||||
if [[ -z "$data" ]]; then _vspi_read "$VSPI_ICB_BASE" "$addr"
|
|
||||||
else _vspi_write "$VSPI_ICB_BASE" "$addr" "$data"; fi
|
|
||||||
}
|
|
||||||
|
|
||||||
swb0_fpga() {
|
|
||||||
if [[ $# -lt 1 ]]; then
|
|
||||||
echo "Usage: swb0_fpga <addr> [data]"; return 1
|
|
||||||
fi
|
|
||||||
local addr="$1" data="${2:-}"
|
|
||||||
_vspi_fnwarn swb0_fpga "$addr" "$data" || return 1
|
|
||||||
if [[ -z "$data" ]]; then _vspi_read "$VSPI_SWB0_BASE" "$addr"
|
|
||||||
else _vspi_write "$VSPI_SWB0_BASE" "$addr" "$data"; fi
|
|
||||||
}
|
|
||||||
|
|
||||||
swb1_fpga() {
|
|
||||||
if [[ $# -lt 1 ]]; then
|
|
||||||
echo "Usage: swb1_fpga <addr> [data]"; return 1
|
|
||||||
fi
|
|
||||||
local addr="$1" data="${2:-}"
|
|
||||||
_vspi_fnwarn swb1_fpga "$addr" "$data" || return 1
|
|
||||||
if [[ -z "$data" ]]; then _vspi_read "$VSPI_SWB1_BASE" "$addr"
|
|
||||||
else _vspi_write "$VSPI_SWB1_BASE" "$addr" "$data"; fi
|
|
||||||
}
|
|
||||||
|
|
||||||
blanton_fpga_help() {
|
|
||||||
echo -e "\033[1mblanton_fpga (pcimem) - FPGA Register Access Tool\033[0m"
|
|
||||||
echo ""
|
|
||||||
echo -e "\033[1mUsage:\033[0m"
|
|
||||||
echo -e " \033[33mcb_fpga\033[0m <fn:0-3> <addr> [data] CB FPGA direct (sysfs resource0)"
|
|
||||||
echo -e " \033[33mpmc_fpga\033[0m <addr> [data] PMC FPGA via VSPI"
|
|
||||||
echo -e " \033[33micb_fpga\033[0m <addr> [data] ICB FPGA via VSPI"
|
|
||||||
echo -e " \033[33mswb0_fpga\033[0m <addr> [data] SWB0 FPGA via VSPI"
|
|
||||||
echo -e " \033[33mswb1_fpga\033[0m <addr> [data] SWB1 FPGA via VSPI"
|
|
||||||
echo -e " \033[33mfpga_debug\033[0m on|off Toggle debug mode (print commands and execute)"
|
|
||||||
echo ""
|
|
||||||
echo -e " Omit [data] to \033[32mread\033[0m, provide [data] to \033[31mwrite\033[0m."
|
|
||||||
echo -e " Backend: \033[36mpcimem\033[0m (sysfs resource file + relative offset)."
|
|
||||||
echo -e " Run \033[33mblanton_fpga_help\033[0m to show this message again."
|
|
||||||
}
|
|
||||||
|
|
||||||
blanton_fpga_help
|
|
||||||
@@ -5,6 +5,20 @@
|
|||||||
# =============================================================================
|
# =============================================================================
|
||||||
# Version Control
|
# Version Control
|
||||||
# -----------------------------------------------------------------------------
|
# -----------------------------------------------------------------------------
|
||||||
|
# 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.
|
||||||
|
# Adds, for TRANSPORT=swb only (CB/i2c path untouched):
|
||||||
|
# * cb_i2c_init <ch> once in margin_init (prescale 0x88 = 100kHz) and
|
||||||
|
# CB_I2C_AUTO_INIT=0 afterwards -> 4 fewer pcimem writes per transfer
|
||||||
|
# * cb_pmbus_read presence probe of every LTC2977 in CHIPS
|
||||||
|
# * return-code checking on every cb_pmbus_read/write (NACK is reported
|
||||||
|
# instead of silently reading 0x0000)
|
||||||
|
# * 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 CONN14/16, Ch8=SWB0 CONN13/15,
|
||||||
|
# Ch7=SWB1 CONN14/16, Ch9=SWB1 CONN13/15
|
||||||
# v2.5.0 SWB margin support via a per-conf TRANSPORT layer. The SWB margin
|
# 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
|
# 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
|
# through the CB FPGA F3 I2C master instead of a native bus. So the whole
|
||||||
@@ -55,6 +69,37 @@ LOG_MODE=1
|
|||||||
TRANSPORT="i2c"
|
TRANSPORT="i2c"
|
||||||
CB_I2C_CH=""
|
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 CONN14 / CONN16
|
||||||
|
# CB F3 Ch8 -> SWB0 CONN13 / CONN15
|
||||||
|
# CB F3 Ch7 -> SWB1 CONN14 / 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="${MARGIN_SWB_CHANNELS:-6 7 8 9}"
|
||||||
|
# SCL prescale for cb_i2c_init: 0x88 = 100kHz, 0x24 = 400kHz (@75MHz core clk).
|
||||||
|
MARGIN_SWB_PRESCALE_LO="${MARGIN_SWB_PRESCALE_LO:-0x88}"
|
||||||
|
MARGIN_SWB_PRESCALE_HI="${MARGIN_SWB_PRESCALE_HI:-0x00}"
|
||||||
|
# 0 = cb_i2c_init once in margin_init, then CB_I2C_AUTO_INIT=0 so each
|
||||||
|
# cb_pmbus_* transfer skips the 4-register prescale/enable dance (much faster:
|
||||||
|
# margin_status all = 32 transfers). Set 1 to keep the package default (re-init
|
||||||
|
# on every transfer) if something else on the box reprograms the channel.
|
||||||
|
MARGIN_SWB_AUTO_INIT="${MARGIN_SWB_AUTO_INIT:-0}"
|
||||||
|
# 1 = grab the per-channel FPGA semaphore (cb_i2c_sem acquire) in margin_init and
|
||||||
|
# hold it for the whole session; margin_swb_sem_release frees it. Default off so
|
||||||
|
# margin never fails just because someone else holds it.
|
||||||
|
MARGIN_SWB_USE_SEM="${MARGIN_SWB_USE_SEM:-0}"
|
||||||
|
# 1 = probe every LTC2977 in CHIPS (PMBus PAGE read) at margin_init.
|
||||||
|
MARGIN_SWB_PROBE="${MARGIN_SWB_PROBE:-1}"
|
||||||
|
# 1 = also let blanton_fpga_pcimem.sh print every underlying pcimem command.
|
||||||
|
# Needed because that script's debug flag is ALSO called DEBUG_MODE; margin_debug
|
||||||
|
# would otherwise flood the console with pcimem lines.
|
||||||
|
MARGIN_SWB_PCIMEM_DEBUG="${MARGIN_SWB_PCIMEM_DEBUG:-0}"
|
||||||
|
_SWB_READY=0
|
||||||
|
_SWB_SEM_HELD=0
|
||||||
|
|
||||||
# Channel enable for margining. Rails the LTC2980 does not sequence (externally
|
# Channel enable for margining. Rails the LTC2980 does not sequence (externally
|
||||||
# enabled, e.g. an always-on MPQ8625 buck) sit with STATUS_WORD OFF=1 and won't
|
# enabled, e.g. an always-on MPQ8625 buck) sit with STATUS_WORD OFF=1 and won't
|
||||||
# margin, because the servo DAC never soft-connects. Writing ON_OFF_CONFIG (0x02)
|
# margin, because the servo DAC never soft-connects. Writing ON_OFF_CONFIG (0x02)
|
||||||
@@ -131,6 +176,233 @@ margin_debug() {
|
|||||||
echo -e "[\033[34mINFO\033[0m] DEBUG_MODE=$DEBUG_MODE"
|
echo -e "[\033[34mINFO\033[0m] DEBUG_MODE=$DEBUG_MODE"
|
||||||
}
|
}
|
||||||
|
|
||||||
|
# =============================================================================
|
||||||
|
# SWB transport backend (TRANSPORT=swb only -- the CB/i2c path never gets here)
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
# Wire ops come from the shared CB I2C package:
|
||||||
|
# blanton_fpga_pcimem.sh -> cb_fpga <fn> <off> [data] (PCIe BAR via pcimem)
|
||||||
|
# blanton_cb_i2c.sh -> cb_i2c_init / cb_i2c_reset / cb_i2c_sem /
|
||||||
|
# cb_i2c_scan / cb_pmbus_read / cb_pmbus_write
|
||||||
|
# Both live in the parent Blanton_Script/ directory (a copy next to margin.sh is
|
||||||
|
# also honoured if you ever bundle one).
|
||||||
|
# =============================================================================
|
||||||
|
|
||||||
|
# Locate a backend script: next to margin.sh first, then the parent dir.
|
||||||
|
_swb_find_backend() {
|
||||||
|
local name="$1" p
|
||||||
|
for p in "$SCRIPT_DIR/$name" "$SCRIPT_DIR/../$name"; do
|
||||||
|
[ -f "$p" ] && { echo "$p"; return 0; }
|
||||||
|
done
|
||||||
|
return 1
|
||||||
|
}
|
||||||
|
|
||||||
|
# Source blanton_fpga_pcimem.sh (cb_fpga) + blanton_cb_i2c.sh (cb_pmbus_*).
|
||||||
|
_swb_backend_load() {
|
||||||
|
local f
|
||||||
|
if ! declare -F cb_fpga >/dev/null 2>&1; then
|
||||||
|
if f=$(_swb_find_backend "blanton_fpga_pcimem.sh"); then
|
||||||
|
# shellcheck source=/dev/null
|
||||||
|
source "$f"
|
||||||
|
echo -e "[\033[34mINFO\033[0m] SWB backend: sourced $f"
|
||||||
|
else
|
||||||
|
echo -e "[\033[31mERRO\033[0m] blanton_fpga_pcimem.sh not found in $SCRIPT_DIR or its parent"
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
if ! declare -F cb_pmbus_read >/dev/null 2>&1; then
|
||||||
|
if f=$(_swb_find_backend "blanton_cb_i2c.sh"); then
|
||||||
|
# shellcheck source=/dev/null
|
||||||
|
source "$f" >/dev/null
|
||||||
|
echo -e "[\033[34mINFO\033[0m] SWB backend: sourced $f"
|
||||||
|
else
|
||||||
|
echo -e "[\033[31mERRO\033[0m] blanton_cb_i2c.sh not found in $SCRIPT_DIR or its parent"
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
declare -F cb_pmbus_read >/dev/null 2>&1 || {
|
||||||
|
echo -e "[\033[31mERRO\033[0m] cb_pmbus_read still undefined after sourcing the backend"; return 1; }
|
||||||
|
return 0
|
||||||
|
}
|
||||||
|
|
||||||
|
# Run a cb_* command with pcimem tracing suppressed (shared DEBUG_MODE var).
|
||||||
|
# Echoes the command's stdout, preserves its return code.
|
||||||
|
_swb_call() {
|
||||||
|
local _saved="$DEBUG_MODE" _rc
|
||||||
|
[ "$MARGIN_SWB_PCIMEM_DEBUG" = "1" ] || DEBUG_MODE=0
|
||||||
|
"$@"
|
||||||
|
_rc=$?
|
||||||
|
DEBUG_MODE="$_saved"
|
||||||
|
return $_rc
|
||||||
|
}
|
||||||
|
|
||||||
|
# Probe one LTC2977: 1-byte PMBus read of PAGE (0x00). Returns cb_pmbus_read's rc.
|
||||||
|
_swb_probe_addr() {
|
||||||
|
_swb_call cb_pmbus_read "$CB_I2C_CH" "$1" 0x00 1 >/dev/null 2>&1
|
||||||
|
}
|
||||||
|
|
||||||
|
# --- SWB wire ops used by the transport switch below ------------------------
|
||||||
|
# Both use _ADDR (LTC2977 7-bit slave) set by _get_chip and CB_I2C_CH from the
|
||||||
|
# .conf. Unlike i2cset/i2cget these report failures: a NACK on the FPGA I2C
|
||||||
|
# master used to silently turn into Vout=0.0000.
|
||||||
|
|
||||||
|
# _swb_write <reg> <byte> [byte...] -> cb_pmbus_write (LSB first for LINEAR16)
|
||||||
|
_swb_write() {
|
||||||
|
local reg=$1; shift
|
||||||
|
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] cb_pmbus_write $CB_I2C_CH $_ADDR $reg $*\033[0m"
|
||||||
|
if ! _swb_call cb_pmbus_write "$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 failed (NACK/timeout)" >&2
|
||||||
|
_log_detail "ERRO cb_pmbus_write ch=$CB_I2C_CH $_ADDR $reg $*"
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
return 0
|
||||||
|
}
|
||||||
|
|
||||||
|
# _swb_read_word <reg> -> echoes "0xXXXX" parsed out of cb_pmbus_read's "=> 0xXXXX"
|
||||||
|
_swb_read_word() {
|
||||||
|
local reg=$1 out word
|
||||||
|
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] cb_pmbus_read $CB_I2C_CH $_ADDR $reg 2\033[0m" >&2
|
||||||
|
if ! out=$(_swb_call cb_pmbus_read "$CB_I2C_CH" "$_ADDR" "$reg" 2 2>/dev/null); then
|
||||||
|
echo -e "[\033[31mERRO\033[0m] cb_pmbus_read ch=$CB_I2C_CH $_ADDR reg=$reg failed (NACK/timeout)" >&2
|
||||||
|
_log_detail "ERRO cb_pmbus_read ch=$CB_I2C_CH $_ADDR $reg"
|
||||||
|
echo "0x0000"
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
# cb_pmbus_read prints " [PMB-R] ... => 0xXXXX raw=[...] linear16=..."
|
||||||
|
word=$(printf '%s' "$out" | awk -F'=> ' 'NF>1{print $2}' | awk '{print $1}')
|
||||||
|
[[ "$word" =~ ^0[xX][0-9a-fA-F]+$ ]] || word="0x0000"
|
||||||
|
echo "$word"
|
||||||
|
}
|
||||||
|
|
||||||
|
# Bring up the FPGA I2C channel for this .conf: validate CB_I2C_CH, prescale +
|
||||||
|
# enable it once (cb_i2c_init), optionally take the semaphore, then probe CHIPS.
|
||||||
|
_swb_setup() {
|
||||||
|
_SWB_READY=0
|
||||||
|
|
||||||
|
if [ -z "$CB_I2C_CH" ]; then
|
||||||
|
echo -e "[\033[31mERRO\033[0m] TRANSPORT=swb but CB_I2C_CH is empty in the .conf"
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
if ! [[ "$CB_I2C_CH" =~ ^[0-9]+$ ]] || [ "$CB_I2C_CH" -gt 17 ]; then
|
||||||
|
echo -e "[\033[31mERRO\033[0m] CB_I2C_CH='$CB_I2C_CH' invalid (CB F3 I2C channels are 0..17)"
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
case " $MARGIN_SWB_CHANNELS " in
|
||||||
|
*" $CB_I2C_CH "*) ;;
|
||||||
|
*) echo -e "[\033[33mWARN\033[0m] CB_I2C_CH=$CB_I2C_CH is not a known SWB VRM channel ($MARGIN_SWB_CHANNELS)" ;;
|
||||||
|
esac
|
||||||
|
|
||||||
|
# Prescale + MOD_EN on this channel.
|
||||||
|
if ! _swb_call cb_i2c_init "$CB_I2C_CH" "$MARGIN_SWB_PRESCALE_LO" "$MARGIN_SWB_PRESCALE_HI"; then
|
||||||
|
echo -e "[\033[31mERRO\033[0m] cb_i2c_init $CB_I2C_CH failed (FPGA/pcimem access?)"
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
CB_I2C_AUTO_INIT="$MARGIN_SWB_AUTO_INIT"
|
||||||
|
local _khz="?"; [ "$MARGIN_SWB_PRESCALE_LO" = "0x88" ] && _khz="100"
|
||||||
|
[ "$MARGIN_SWB_PRESCALE_LO" = "0x24" ] && _khz="400"
|
||||||
|
echo -e "[\033[34mINFO\033[0m] cb_i2c_init ch=$CB_I2C_CH prescale=$MARGIN_SWB_PRESCALE_LO/$MARGIN_SWB_PRESCALE_HI (~${_khz}kHz), CB_I2C_AUTO_INIT=$CB_I2C_AUTO_INIT"
|
||||||
|
_log "swb: cb_i2c_init ch=$CB_I2C_CH prescale=$MARGIN_SWB_PRESCALE_LO auto_init=$CB_I2C_AUTO_INIT"
|
||||||
|
|
||||||
|
if [ "$MARGIN_SWB_USE_SEM" = "1" ]; then
|
||||||
|
if _swb_call cb_i2c_sem "$CB_I2C_CH" acquire; then
|
||||||
|
_SWB_SEM_HELD=1
|
||||||
|
else
|
||||||
|
echo -e "[\033[33mWARN\033[0m] semaphore on ch=$CB_I2C_CH not acquired; continuing without it"
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
|
_SWB_READY=1
|
||||||
|
|
||||||
|
if [ "$MARGIN_SWB_PROBE" = "1" ]; then
|
||||||
|
local idx=0 chip addr bad=0
|
||||||
|
for chip in "${CHIPS[@]}"; do
|
||||||
|
IFS=':' read -r _ addr <<< "$chip"
|
||||||
|
if _swb_probe_addr "$addr"; then
|
||||||
|
echo -e "[\033[34mINFO\033[0m] probe ch=$CB_I2C_CH LTC2977[$idx] $addr : \033[32mACK\033[0m"
|
||||||
|
else
|
||||||
|
echo -e "[\033[33mWARN\033[0m] probe ch=$CB_I2C_CH LTC2977[$idx] $addr : \033[31mNACK\033[0m (wrong CB_I2C_CH / addr, board absent, or channel stuck -> margin_swb_scan / margin_swb_reset)"
|
||||||
|
bad=1
|
||||||
|
fi
|
||||||
|
idx=$((idx+1))
|
||||||
|
done
|
||||||
|
_log "swb: probe ch=$CB_I2C_CH chips=${CHIPS[*]} $( [ "$bad" = "0" ] && echo all-ACK || echo has-NACK )"
|
||||||
|
fi
|
||||||
|
return 0
|
||||||
|
}
|
||||||
|
|
||||||
|
# --- SWB debug / maintenance wrappers (thin shells over blanton_cb_i2c.sh) ---
|
||||||
|
_swb_guard() {
|
||||||
|
if [ "$TRANSPORT" != "swb" ]; then
|
||||||
|
echo -e "[\033[33mWARN\033[0m] current setting is TRANSPORT=$TRANSPORT (not swb); nothing to do"
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
declare -F cb_pmbus_read >/dev/null 2>&1 || { echo -e "[\033[31mERRO\033[0m] SWB backend not loaded; run margin_init first"; return 1; }
|
||||||
|
return 0
|
||||||
|
}
|
||||||
|
|
||||||
|
# margin_swb_info -- show the transport wiring of the loaded setting
|
||||||
|
margin_swb_info() {
|
||||||
|
echo "-------------"
|
||||||
|
echo "[$PART_NUMBER] transport"
|
||||||
|
echo "-------------"
|
||||||
|
echo " TRANSPORT : $TRANSPORT"
|
||||||
|
if [ "$TRANSPORT" = "swb" ]; then
|
||||||
|
echo " CB_I2C_CH : $CB_I2C_CH (CB FPGA F3, base $(printf '0x%X' $(( 0x300 + CB_I2C_CH * 0x20 ))))"
|
||||||
|
echo " LTC2977 : ${CHIPS[*]} (bus field unused on swb)"
|
||||||
|
echo " prescale : $MARGIN_SWB_PRESCALE_LO/$MARGIN_SWB_PRESCALE_HI auto_init=$CB_I2C_AUTO_INIT sem_held=$_SWB_SEM_HELD"
|
||||||
|
echo " wire ops : cb_pmbus_write $CB_I2C_CH <addr> 0x00 <page> / cb_pmbus_read $CB_I2C_CH <addr> 0x8b 2"
|
||||||
|
else
|
||||||
|
echo " bus:addr : ${CHIPS[*]} (i2cset/i2cget)"
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
# margin_swb_probe -- re-run the PAGE-read presence check on every LTC2977
|
||||||
|
margin_swb_probe() {
|
||||||
|
_swb_guard || return 1
|
||||||
|
local idx=0 chip addr
|
||||||
|
for chip in "${CHIPS[@]}"; do
|
||||||
|
IFS=':' read -r _ addr <<< "$chip"
|
||||||
|
if _swb_probe_addr "$addr"; then
|
||||||
|
echo -e " ch=$CB_I2C_CH $addr : \033[32mACK\033[0m"
|
||||||
|
else
|
||||||
|
echo -e " ch=$CB_I2C_CH $addr : \033[31mNACK\033[0m"
|
||||||
|
fi
|
||||||
|
idx=$((idx+1))
|
||||||
|
done
|
||||||
|
}
|
||||||
|
|
||||||
|
# margin_swb_scan [ch] -- cb_i2c_scan on this conf's channel (0x08..0x77)
|
||||||
|
margin_swb_scan() {
|
||||||
|
_swb_guard || return 1
|
||||||
|
_swb_call cb_i2c_scan "${1:-$CB_I2C_CH}"
|
||||||
|
}
|
||||||
|
|
||||||
|
# margin_swb_reset -- local I2C controller reset (0xD) + re-init, for a stuck bus
|
||||||
|
margin_swb_reset() {
|
||||||
|
_swb_guard || return 1
|
||||||
|
_swb_call cb_i2c_reset "$CB_I2C_CH"
|
||||||
|
_swb_call cb_i2c_init "$CB_I2C_CH" "$MARGIN_SWB_PRESCALE_LO" "$MARGIN_SWB_PRESCALE_HI"
|
||||||
|
echo -e "[\033[34mINFO\033[0m] ch=$CB_I2C_CH reset + re-init done"
|
||||||
|
_log "swb: cb_i2c_reset + cb_i2c_init ch=$CB_I2C_CH"
|
||||||
|
}
|
||||||
|
|
||||||
|
# margin_swb_sem [status|acquire|release]
|
||||||
|
margin_swb_sem() {
|
||||||
|
_swb_guard || return 1
|
||||||
|
local act="${1:-status}"
|
||||||
|
_swb_call cb_i2c_sem "$CB_I2C_CH" "$act"
|
||||||
|
case "$act" in
|
||||||
|
acquire) _SWB_SEM_HELD=1 ;;
|
||||||
|
release) _SWB_SEM_HELD=0 ;;
|
||||||
|
esac
|
||||||
|
}
|
||||||
|
|
||||||
|
# margin_swb_sem_release -- release the session semaphore if margin_init took it
|
||||||
|
margin_swb_sem_release() {
|
||||||
|
[ "$_SWB_SEM_HELD" = "1" ] || { echo -e "[\033[34mINFO\033[0m] no semaphore held by this session"; return 0; }
|
||||||
|
_swb_call cb_i2c_sem "$CB_I2C_CH" release
|
||||||
|
_SWB_SEM_HELD=0
|
||||||
|
}
|
||||||
|
|
||||||
# --- Init: load setting by name ---
|
# --- Init: load setting by name ---
|
||||||
margin_init() {
|
margin_init() {
|
||||||
if [ -z "$1" ]; then
|
if [ -z "$1" ]; then
|
||||||
@@ -150,15 +422,13 @@ margin_init() {
|
|||||||
TRANSPORT="${TRANSPORT:-i2c}" # a blank TRANSPORT="" in a .conf means i2c
|
TRANSPORT="${TRANSPORT:-i2c}" # a blank TRANSPORT="" in a .conf means i2c
|
||||||
echo -e "[\033[34mINFO\033[0m] Loaded setting: $setting_file (transport=$TRANSPORT)"
|
echo -e "[\033[34mINFO\033[0m] Loaded setting: $setting_file (transport=$TRANSPORT)"
|
||||||
|
|
||||||
# SWB rails need the cb_pmbus_* backend; source it on demand.
|
# SWB rails need the cb_pmbus_* backend (blanton_cb_i2c.sh + blanton_fpga_pcimem.sh,
|
||||||
if [ "$TRANSPORT" = "swb" ] && ! declare -F cb_pmbus_read >/dev/null 2>&1; then
|
# normally in the parent Blanton_Script/ dir); load it and bring the FPGA I2C
|
||||||
if [ -f "$SCRIPT_DIR/blanton_cb_i2c.sh" ]; then
|
# channel up once. CB/i2c settings skip this entirely.
|
||||||
# shellcheck source=/dev/null
|
_SWB_READY=0; _SWB_SEM_HELD=0
|
||||||
source "$SCRIPT_DIR/blanton_cb_i2c.sh"
|
if [ "$TRANSPORT" = "swb" ]; then
|
||||||
else
|
_swb_backend_load || return 1
|
||||||
echo -e "[\033[31mERRO\033[0m] TRANSPORT=swb but blanton_cb_i2c.sh not found in $SCRIPT_DIR"
|
_swb_setup || return 1
|
||||||
return 1
|
|
||||||
fi
|
|
||||||
fi
|
fi
|
||||||
_log_start_session
|
_log_start_session
|
||||||
}
|
}
|
||||||
@@ -221,8 +491,7 @@ _get_page() {
|
|||||||
# PAGE is written the same way on both (PMBus command 0x00).
|
# PAGE is written the same way on both (PMBus command 0x00).
|
||||||
_open_page() {
|
_open_page() {
|
||||||
if [ "$TRANSPORT" = "swb" ]; then
|
if [ "$TRANSPORT" = "swb" ]; then
|
||||||
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] cb_pmbus_write $CB_I2C_CH $_ADDR 0x00 $1\033[0m"
|
_swb_write 0x00 "$1"
|
||||||
cb_pmbus_write "$CB_I2C_CH" "$_ADDR" 0x00 "$1" >/dev/null 2>&1
|
|
||||||
return
|
return
|
||||||
fi
|
fi
|
||||||
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] i2cset -y $_BUS $_ADDR 0x00 $1 b\033[0m"
|
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] i2cset -y $_BUS $_ADDR 0x00 $1 b\033[0m"
|
||||||
@@ -233,8 +502,7 @@ _open_page() {
|
|||||||
_i2c_write_word() {
|
_i2c_write_word() {
|
||||||
local reg=$1 lo=$2 hi=$3
|
local reg=$1 lo=$2 hi=$3
|
||||||
if [ "$TRANSPORT" = "swb" ]; then
|
if [ "$TRANSPORT" = "swb" ]; then
|
||||||
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] cb_pmbus_write $CB_I2C_CH $_ADDR $reg $lo $hi\033[0m"
|
_swb_write "$reg" "$lo" "$hi"
|
||||||
cb_pmbus_write "$CB_I2C_CH" "$_ADDR" "$reg" "$lo" "$hi" >/dev/null 2>&1
|
|
||||||
return
|
return
|
||||||
fi
|
fi
|
||||||
local word=$(( (hi << 8) | lo ))
|
local word=$(( (hi << 8) | lo ))
|
||||||
@@ -245,8 +513,7 @@ _i2c_write_word() {
|
|||||||
|
|
||||||
_i2c_write_byte() {
|
_i2c_write_byte() {
|
||||||
if [ "$TRANSPORT" = "swb" ]; then
|
if [ "$TRANSPORT" = "swb" ]; then
|
||||||
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] cb_pmbus_write $CB_I2C_CH $_ADDR $1 $2\033[0m"
|
_swb_write "$1" "$2"
|
||||||
cb_pmbus_write "$CB_I2C_CH" "$_ADDR" "$1" "$2" >/dev/null 2>&1
|
|
||||||
return
|
return
|
||||||
fi
|
fi
|
||||||
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] i2cset -y $_BUS $_ADDR $1 $2 b\033[0m"
|
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] i2cset -y $_BUS $_ADDR $1 $2 b\033[0m"
|
||||||
@@ -256,13 +523,7 @@ _i2c_write_byte() {
|
|||||||
# Read a 16-bit word; echoes "0xXXXX". For swb, parse cb_pmbus_read's "=> 0xXXXX".
|
# Read a 16-bit word; echoes "0xXXXX". For swb, parse cb_pmbus_read's "=> 0xXXXX".
|
||||||
_i2c_read_word() {
|
_i2c_read_word() {
|
||||||
if [ "$TRANSPORT" = "swb" ]; then
|
if [ "$TRANSPORT" = "swb" ]; then
|
||||||
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] cb_pmbus_read $CB_I2C_CH $_ADDR $1 2\033[0m" >&2
|
_swb_read_word "$1"
|
||||||
local out word
|
|
||||||
out=$(cb_pmbus_read "$CB_I2C_CH" "$_ADDR" "$1" 2 2>/dev/null)
|
|
||||||
# cb_pmbus_read prints "... => 0xXXXX raw=[...] ..."; take the word after "=>".
|
|
||||||
word=$(printf '%s' "$out" | awk -F'=> ' 'NF>1{print $2}' | awk '{print $1}')
|
|
||||||
[[ "$word" =~ ^0[xX][0-9a-fA-F]+$ ]] || word="0x0000"
|
|
||||||
echo "$word"
|
|
||||||
return
|
return
|
||||||
fi
|
fi
|
||||||
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] i2cget -y $_BUS $_ADDR $1 w\033[0m" >&2
|
[ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] i2cget -y $_BUS $_ADDR $1 w\033[0m" >&2
|
||||||
|
|||||||
+1
-1
@@ -9,7 +9,7 @@
|
|||||||
# --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
|
# --- 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. ---
|
# it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
|
||||||
TRANSPORT="swb"
|
TRANSPORT="swb"
|
||||||
CB_I2C_CH=6
|
CB_I2C_CH=8 # CB F3 Ch8 = SWB0 CONN13/CONN15 (shared with CONN15, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
|
|||||||
+3
-3
@@ -9,15 +9,15 @@
|
|||||||
# --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
|
# --- 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. ---
|
# it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
|
||||||
TRANSPORT="swb"
|
TRANSPORT="swb"
|
||||||
CB_I2C_CH=8
|
CB_I2C_CH=6 # CB F3 Ch6 = SWB0 CONN14/CONN16 (shared with CONN16, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
# Format: "bus:address" (8 channels per entry / per LTC2977)
|
# Format: "bus:address" (8 channels per entry / per LTC2977)
|
||||||
CHIPS=(
|
CHIPS=(
|
||||||
# chip1: SWB0 (CONN14)
|
# 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)
|
# Pre-commands to run before accessing each chip (empty = none)
|
||||||
|
|||||||
+2
-2
@@ -9,7 +9,7 @@
|
|||||||
# --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
|
# --- 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. ---
|
# it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
|
||||||
TRANSPORT="swb"
|
TRANSPORT="swb"
|
||||||
CB_I2C_CH=6
|
CB_I2C_CH=8 # CB F3 Ch8 = SWB0 CONN13/CONN15 (shared with CONN13, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
@@ -17,7 +17,7 @@ CB_I2C_CH=6
|
|||||||
CHIPS=(
|
CHIPS=(
|
||||||
# chip1: SWB0 (CONN15)
|
# chip1: SWB0 (CONN15)
|
||||||
"0:0x62" # CH0 ~ CH7
|
"0:0x62" # CH0 ~ CH7
|
||||||
"0:0x63" # CH8 ~ CH15
|
"0:0x64" # CH8 ~ CH15
|
||||||
)
|
)
|
||||||
|
|
||||||
# Pre-commands to run before accessing each chip (empty = none)
|
# Pre-commands to run before accessing each chip (empty = none)
|
||||||
|
|||||||
+3
-3
@@ -9,15 +9,15 @@
|
|||||||
# --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
|
# --- 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. ---
|
# it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
|
||||||
TRANSPORT="swb"
|
TRANSPORT="swb"
|
||||||
CB_I2C_CH=8
|
CB_I2C_CH=6 # CB F3 Ch6 = SWB0 CONN14/CONN16 (shared with CONN14, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
# Format: "bus:address" (8 channels per entry / per LTC2977)
|
# Format: "bus:address" (8 channels per entry / per LTC2977)
|
||||||
CHIPS=(
|
CHIPS=(
|
||||||
# chip1: SWB0 (CONN16)
|
# 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)
|
# Pre-commands to run before accessing each chip (empty = none)
|
||||||
|
|||||||
+2
-2
@@ -9,7 +9,7 @@
|
|||||||
# --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
|
# --- 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. ---
|
# it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
|
||||||
TRANSPORT="swb"
|
TRANSPORT="swb"
|
||||||
CB_I2C_CH=7
|
CB_I2C_CH=9 # CB F3 Ch9 = SWB1 CONN13/CONN15 (shared with CONN15, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
@@ -17,7 +17,7 @@ CB_I2C_CH=7
|
|||||||
CHIPS=(
|
CHIPS=(
|
||||||
# chip1: SWB1 (CONN13)
|
# chip1: SWB1 (CONN13)
|
||||||
"1:0x5C" # CH0 ~ CH7
|
"1:0x5C" # CH0 ~ CH7
|
||||||
"1:0x5D" # CH8 ~ CH15
|
"1:0x5E" # CH8 ~ CH15
|
||||||
)
|
)
|
||||||
|
|
||||||
# Pre-commands to run before accessing each chip (empty = none)
|
# Pre-commands to run before accessing each chip (empty = none)
|
||||||
|
|||||||
+3
-3
@@ -9,15 +9,15 @@
|
|||||||
# --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
|
# --- 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. ---
|
# it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
|
||||||
TRANSPORT="swb"
|
TRANSPORT="swb"
|
||||||
CB_I2C_CH=9
|
CB_I2C_CH=7 # CB F3 Ch7 = SWB1 CONN14/CONN16 (shared with CONN16, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
# Format: "bus:address" (8 channels per entry / per LTC2977)
|
# Format: "bus:address" (8 channels per entry / per LTC2977)
|
||||||
CHIPS=(
|
CHIPS=(
|
||||||
# chip1: SWB1 (CONN14)
|
# 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)
|
# Pre-commands to run before accessing each chip (empty = none)
|
||||||
|
|||||||
+2
-2
@@ -9,7 +9,7 @@
|
|||||||
# --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
|
# --- 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. ---
|
# it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
|
||||||
TRANSPORT="swb"
|
TRANSPORT="swb"
|
||||||
CB_I2C_CH=7
|
CB_I2C_CH=9 # CB F3 Ch9 = SWB1 CONN13/CONN15 (shared with CONN13, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
@@ -17,7 +17,7 @@ CB_I2C_CH=7
|
|||||||
CHIPS=(
|
CHIPS=(
|
||||||
# chip1: SWB1 (CONN15)
|
# chip1: SWB1 (CONN15)
|
||||||
"1:0x62" # CH0 ~ CH7
|
"1:0x62" # CH0 ~ CH7
|
||||||
"1:0x63" # CH8 ~ CH15
|
"1:0x64" # CH8 ~ CH15
|
||||||
)
|
)
|
||||||
|
|
||||||
# Pre-commands to run before accessing each chip (empty = none)
|
# Pre-commands to run before accessing each chip (empty = none)
|
||||||
|
|||||||
+3
-3
@@ -9,15 +9,15 @@
|
|||||||
# --- SWB transport (added): this LTC2980 sits behind the CB FPGA F3 I2C; reach
|
# --- 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. ---
|
# it with cb_pmbus, not i2cset. CB_I2C_CH = FPGA I2C channel for this CONN. ---
|
||||||
TRANSPORT="swb"
|
TRANSPORT="swb"
|
||||||
CB_I2C_CH=9
|
CB_I2C_CH=7 # CB F3 Ch7 = SWB1 CONN14/CONN16 (shared with CONN14, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
# Format: "bus:address" (8 channels per entry / per LTC2977)
|
# Format: "bus:address" (8 channels per entry / per LTC2977)
|
||||||
CHIPS=(
|
CHIPS=(
|
||||||
# chip1: SWB1 (CONN16)
|
# 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)
|
# Pre-commands to run before accessing each chip (empty = none)
|
||||||
|
|||||||
@@ -61,6 +61,19 @@
|
|||||||
# intentional difference from
|
# intentional difference from
|
||||||
# tools/bcm_mibpair_report_V1.1.0.py, which hides NA pairs
|
# tools/bcm_mibpair_report_V1.1.0.py, which hides NA pairs
|
||||||
# unless -a is given.
|
# 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
|
# The VLAN/port table below is copied verbatim from
|
||||||
@@ -486,7 +499,7 @@ _tl_pair_report() {
|
|||||||
-v TSV="$TL_REPORT_TSV" \
|
-v TSV="$TL_REPORT_TSV" \
|
||||||
-v COLOR="$color" '
|
-v COLOR="$color" '
|
||||||
function grp(v, s,out,l,i) {
|
function grp(v, s,out,l,i) {
|
||||||
s = sprintf("%d", v)
|
s = sprintf("%.0f", v)
|
||||||
if (!GROUPED) return s
|
if (!GROUPED) return s
|
||||||
out = ""; l = length(s)
|
out = ""; l = length(s)
|
||||||
for (i = 1; i <= l; i++) {
|
for (i = 1; i <= l; i++) {
|
||||||
@@ -557,7 +570,7 @@ _tl_pair_report() {
|
|||||||
if (d <= TOL + 0) { v = "PASS"; npass++ }
|
if (d <= TOL + 0) { v = "PASS"; npass++ }
|
||||||
else {
|
else {
|
||||||
v = "FAIL"; nfail++
|
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)
|
a, b, a, b, dtx, a, b, drx)
|
||||||
}
|
}
|
||||||
ta = grp(TX[a]); ra = grp(RX[a]); tb = grp(TX[b]); rb = grp(RX[b])
|
ta = grp(TX[a]); ra = grp(RX[a]); tb = grp(TX[b]); rb = grp(RX[b])
|
||||||
|
|||||||
@@ -0,0 +1,340 @@
|
|||||||
|
#!/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"
|
||||||
|
#"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
|
||||||
@@ -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
|
||||||
@@ -0,0 +1,463 @@
|
|||||||
|
#!/bin/bash
|
||||||
|
###############################################################################
|
||||||
|
# mgmt_ping_monitor.sh
|
||||||
|
#
|
||||||
|
# Version : V1.0.0
|
||||||
|
# Author : ETWen
|
||||||
|
# Date : 20260824
|
||||||
|
#
|
||||||
|
# Purpose : Exercise both management NICs and ping each one's own target,
|
||||||
|
# appending everything to a rotating log. One round is
|
||||||
|
#
|
||||||
|
# 10G (eth0) : ip link up + address/route replace -> settle
|
||||||
|
# -> ping N x TARGET_10G -> ip -s link show
|
||||||
|
# 1G (eth1) : ip link up + address/route replace -> settle
|
||||||
|
# -> ping N x TARGET_1G -> ip -s link show
|
||||||
|
#
|
||||||
|
# Designed to run detached in the background, same sub-commands as
|
||||||
|
# bmc_monitor.sh: start/stop/status/fg/tail/clear.
|
||||||
|
#
|
||||||
|
# Notes : - Both NICs are brought up and LEFT up. Addresses and default
|
||||||
|
# routes are applied with iproute2 `replace`, which is idempotent:
|
||||||
|
# re-running a round does not stack duplicate addresses or routes.
|
||||||
|
# - The default routes carry different metrics (100 / 200), so the
|
||||||
|
# lower one wins for off-subnet traffic. They do NOT decide which
|
||||||
|
# NIC a ping leaves by: `ping -I <iface>` binds to the device.
|
||||||
|
# - !! SAME-SUBNET WARNING !! With both NICs up on one subnet the
|
||||||
|
# target ARPs for the address and Linux may answer from either
|
||||||
|
# NIC, so replies can arrive on the wrong one and the result is
|
||||||
|
# not attributable. ARP_STRICT=1 sets arp_ignore/arp_announce to
|
||||||
|
# stop that. Leave it on unless the two NICs are on separate
|
||||||
|
# subnets, as in the iproute2 example this was modelled on.
|
||||||
|
# - Each leg logs `ip -s link show <iface>` and the TX/RX packet
|
||||||
|
# delta across the burst, which is the direct evidence of which
|
||||||
|
# NIC actually carried the traffic.
|
||||||
|
# - The first pings after bringing a link up are lost to ARP, not to
|
||||||
|
# the link: a bench capture showed 4x "Destination Host
|
||||||
|
# Unreachable" on the first burst and 0% loss on the very next
|
||||||
|
# one. LINK_SETTLE_SEC absorbs that; it is not packet loss.
|
||||||
|
#
|
||||||
|
# Version History
|
||||||
|
# V1.0.0 20260824 Initial Version
|
||||||
|
# V2.0.0 20260824 Switch from ifconfig to iproute2 (ip link / address
|
||||||
|
# replace / route replace with per-NIC metric). Both
|
||||||
|
# NICs now stay up -- no link down between legs. Add
|
||||||
|
# `ip -s link show` per leg with a TX/RX delta, and
|
||||||
|
# ARP_STRICT for the same-subnet case.
|
||||||
|
###############################################################################
|
||||||
|
|
||||||
|
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" # host this NIC pings
|
||||||
|
PLEN_1G=24
|
||||||
|
GW_1G=""
|
||||||
|
METRIC_1G=200
|
||||||
|
|
||||||
|
# --- ping ---
|
||||||
|
PING_COUNT=10 # echo requests per leg
|
||||||
|
MAX_LOSS_PCT=0 # loss above this marks the leg FAIL
|
||||||
|
|
||||||
|
# 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. Setting
|
||||||
|
# this applies arp_ignore=1 / arp_announce=2 to both, which keeps each NIC to
|
||||||
|
# its own address. RAM only -- reverts on reboot. Set 0 for separate subnets.
|
||||||
|
ARP_STRICT=1
|
||||||
|
|
||||||
|
# Prefix for the ip commands; empty because the daemon already runs as root.
|
||||||
|
SUDO=""
|
||||||
|
|
||||||
|
# Seconds to wait after bringing a link up before pinging, so ARP is resolved
|
||||||
|
# and the PHY has finished autoneg. The bench needed a few seconds on the 1G.
|
||||||
|
LINK_SETTLE_SEC=5
|
||||||
|
|
||||||
|
# Seconds between rounds (0 = start the next round immediately)
|
||||||
|
INTERVAL_SEC=10
|
||||||
|
|
||||||
|
# Per-ping-burst timeout in seconds; stops a wedged ping from freezing the
|
||||||
|
# loop. 0 disables. Must exceed PING_COUNT (one packet per second).
|
||||||
|
PING_TIMEOUT_SEC=60
|
||||||
|
|
||||||
|
# Stop after this many rounds. 0 = run until stopped manually.
|
||||||
|
MAX_ROUNDS=0
|
||||||
|
|
||||||
|
# Logging
|
||||||
|
LOG_DIR="" # empty = <script directory>/log
|
||||||
|
LOG_NAME="mgmt_ping.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
|
||||||
|
}
|
||||||
|
|
||||||
|
interruptible_sleep() {
|
||||||
|
local sec="$1"
|
||||||
|
[ "${sec}" -gt 0 ] 2>/dev/null || return 0
|
||||||
|
sleep "${sec}" &
|
||||||
|
SLEEP_PID=$!
|
||||||
|
wait "${SLEEP_PID}" 2>/dev/null
|
||||||
|
SLEEP_PID=""
|
||||||
|
}
|
||||||
|
|
||||||
|
is_running() {
|
||||||
|
local pid
|
||||||
|
[ -f "${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 >>"${LOG_FILE}" 2>&1
|
||||||
|
printf '[%s] INFO : log rotated at %s MB\n' "$(ts)" "${MAX_LOG_SIZE_MB}"
|
||||||
|
}
|
||||||
|
|
||||||
|
remove_rotated_logs() {
|
||||||
|
local i
|
||||||
|
for (( i = 1; i <= MAX_LOG_KEEP + 1; i++ )); do
|
||||||
|
rm -f "${LOG_FILE}.${i}"
|
||||||
|
done
|
||||||
|
}
|
||||||
|
|
||||||
|
prepare_log_on_start() {
|
||||||
|
local stamp
|
||||||
|
case "${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
|
||||||
|
}
|
||||||
|
|
||||||
|
# Cumulative "<rx_packets> <tx_packets>" for an interface, from ip -s link.
|
||||||
|
# The numbers sit on the line after each RX:/TX: header, and the column order
|
||||||
|
# is "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. `replace` is
|
||||||
|
# idempotent, so repeated rounds do not stack duplicates.
|
||||||
|
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
|
||||||
|
}
|
||||||
|
|
||||||
|
# One leg: configure <if>, settle, ping its own target, report. The NIC is
|
||||||
|
# LEFT UP -- nothing is brought down between legs.
|
||||||
|
# Usage: ping_leg <label> <if> <ip> <plen> <gw> <metric> <target>
|
||||||
|
ping_leg() {
|
||||||
|
local label="$1" iface="$2" ipaddr="$3" plen="$4" gw="$5" metric="$6" target="$7"
|
||||||
|
local out rc tx rx loss avg verdict
|
||||||
|
local c0 c1 rx0 tx0 rx1 tx1 drx dtx
|
||||||
|
|
||||||
|
printf -- '----- [%s] %s : %s (%s/%s) -> %s -----\n' \
|
||||||
|
"$(ts)" "${label}" "${iface}" "${ipaddr}" "${plen}" "${target}"
|
||||||
|
|
||||||
|
if ! setup_iface "${iface}" "${ipaddr}" "${plen}" "${gw}" "${metric}"; then
|
||||||
|
printf '[%s] FAIL : cannot configure %s\n\n' "$(ts)" "${iface}"
|
||||||
|
return 1
|
||||||
|
fi
|
||||||
|
interruptible_sleep "${LINK_SETTLE_SEC}"
|
||||||
|
[ "${STOP}" -eq 0 ] || return 1
|
||||||
|
|
||||||
|
c0="$(if_counters "${iface}")"; rx0="${c0% *}"; tx0="${c0#* }"
|
||||||
|
|
||||||
|
if [ "${PING_TIMEOUT_SEC}" -gt 0 ]; then
|
||||||
|
out="$(timeout "${PING_TIMEOUT_SEC}" ping -I "${iface}" -c "${PING_COUNT}" "${target}" 2>&1)"
|
||||||
|
else
|
||||||
|
out="$(ping -I "${iface}" -c "${PING_COUNT}" "${target}" 2>&1)"
|
||||||
|
fi
|
||||||
|
rc=$?
|
||||||
|
printf '%s\n' "${out}"
|
||||||
|
|
||||||
|
c1="$(if_counters "${iface}")"; rx1="${c1% *}"; tx1="${c1#* }"
|
||||||
|
drx=$(( rx1 - rx0 )); dtx=$(( tx1 - tx0 ))
|
||||||
|
|
||||||
|
printf -- '--- ip -s link show %s ---\n' "${iface}"
|
||||||
|
${SUDO} ip -s link show "${iface}" 2>&1
|
||||||
|
|
||||||
|
# "10 packets transmitted, 10 received, 0% packet loss"
|
||||||
|
tx="$(printf '%s' "${out}" | sed -n 's/^\([0-9]\+\) packets transmitted.*/\1/p' | tail -1)"
|
||||||
|
rx="$(printf '%s' "${out}" | sed -n 's/.*[, ]\([0-9]\+\) received.*/\1/p' | tail -1)"
|
||||||
|
loss="$(printf '%s' "${out}" | sed -n 's/.*[, ]\([0-9]\+\)% packet loss.*/\1/p' | tail -1)"
|
||||||
|
# "rtt min/avg/max/mdev = 1.044/1.743/2.387/0.437 ms"
|
||||||
|
avg="$(printf '%s' "${out}" | 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="-"
|
||||||
|
|
||||||
|
if [ "${rc}" -eq 124 ]; then
|
||||||
|
verdict="FAIL(timeout)"
|
||||||
|
elif [ "${loss}" -le "${MAX_LOSS_PCT}" ]; then
|
||||||
|
verdict="PASS"
|
||||||
|
else
|
||||||
|
verdict="FAIL"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# one greppable line per leg: grep RESULT <log>
|
||||||
|
# nic_tx/nic_rx are this interface's own counter delta across the burst --
|
||||||
|
# if they stay near zero while the ping succeeded, the traffic went out a
|
||||||
|
# different NIC and the result is not attributable to this one.
|
||||||
|
printf '[%s] RESULT %-3s %-6s -> %-15s tx=%s rx=%s loss=%s%% rtt_avg=%sms nic_tx=%s nic_rx=%s %s\n\n' \
|
||||||
|
"$(ts)" "${label}" "${iface}" "${target}" "${tx}" "${rx}" "${loss}" "${avg}" \
|
||||||
|
"${dtx}" "${drx}" "${verdict}"
|
||||||
|
|
||||||
|
[ "${verdict}" = "PASS" ]
|
||||||
|
}
|
||||||
|
|
||||||
|
# arp_ignore=1 : answer ARP only for addresses configured on the incoming NIC
|
||||||
|
# arp_announce=2: pick the source address from the outgoing NIC's own subnet
|
||||||
|
# Both are RAM-only sysctls and revert on reboot.
|
||||||
|
apply_arp_strict() {
|
||||||
|
local i
|
||||||
|
[ "${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
|
||||||
|
printf '[%s] INFO : arp_ignore=1 arp_announce=2 applied to %s,%s\n' \
|
||||||
|
"$(ts)" "${IF_10G}" "${IF_1G}"
|
||||||
|
}
|
||||||
|
|
||||||
|
main_loop() {
|
||||||
|
local round=0 pass=0 fail=0
|
||||||
|
|
||||||
|
command -v ip >/dev/null 2>&1 || die "ip (iproute2) not found"
|
||||||
|
command -v ping >/dev/null 2>&1 || die "ping not found"
|
||||||
|
[ "${PING_COUNT}" -gt 0 ] 2>/dev/null || die "PING_COUNT must be > 0"
|
||||||
|
|
||||||
|
trap on_signal INT TERM
|
||||||
|
|
||||||
|
printf '#############################################################\n'
|
||||||
|
printf '[%s] START: pid=%d count=%d settle=%ds interval=%ds\n' \
|
||||||
|
"$(ts)" "$$" "${PING_COUNT}" "${LINK_SETTLE_SEC}" "${INTERVAL_SEC}"
|
||||||
|
printf '[%s] 10G %s %s/%s -> %s (metric %s)\n' \
|
||||||
|
"$(ts)" "${IF_10G}" "${IP_10G}" "${PLEN_10G}" "${TARGET_10G}" "${METRIC_10G}"
|
||||||
|
printf '[%s] 1G %s %s/%s -> %s (metric %s)\n' \
|
||||||
|
"$(ts)" "${IF_1G}" "${IP_1G}" "${PLEN_1G}" "${TARGET_1G}" "${METRIC_1G}"
|
||||||
|
printf '#############################################################\n'
|
||||||
|
|
||||||
|
apply_arp_strict
|
||||||
|
|
||||||
|
while [ "${STOP}" -eq 0 ]; do
|
||||||
|
round=$(( round + 1 ))
|
||||||
|
printf -- '---------- ROUND %d @ %s ----------\n' "${round}" "$(ts)"
|
||||||
|
|
||||||
|
if ping_leg "10G" "${IF_10G}" "${IP_10G}" "${PLEN_10G}" "${GW_10G}" \
|
||||||
|
"${METRIC_10G}" "${TARGET_10G}"; then
|
||||||
|
pass=$(( pass + 1 )); else fail=$(( fail + 1 ))
|
||||||
|
fi
|
||||||
|
[ "${STOP}" -eq 0 ] || break
|
||||||
|
|
||||||
|
if ping_leg "1G" "${IF_1G}" "${IP_1G}" "${PLEN_1G}" "${GW_1G}" \
|
||||||
|
"${METRIC_1G}" "${TARGET_1G}"; then
|
||||||
|
pass=$(( pass + 1 )); else fail=$(( fail + 1 ))
|
||||||
|
fi
|
||||||
|
|
||||||
|
rotate_log_if_needed
|
||||||
|
|
||||||
|
if [ "${MAX_ROUNDS}" -gt 0 ] && [ "${round}" -ge "${MAX_ROUNDS}" ]; then
|
||||||
|
break
|
||||||
|
fi
|
||||||
|
[ "${STOP}" -eq 0 ] && interruptible_sleep "${INTERVAL_SEC}"
|
||||||
|
done
|
||||||
|
|
||||||
|
printf '[%s] STOP : pid=%d after %d round(s), legs PASS=%d FAIL=%d\n' \
|
||||||
|
"$(ts)" "$$" "${round}" "${pass}" "${fail}"
|
||||||
|
}
|
||||||
|
|
||||||
|
###############################################################################
|
||||||
|
# Sub-commands
|
||||||
|
###############################################################################
|
||||||
|
do_start() {
|
||||||
|
local pid
|
||||||
|
pid="$(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 'ping : count=%d, interval=%ds, settle=%ds\n' "${PING_COUNT}" "${INTERVAL_SEC}" "${LINK_SETTLE_SEC}"
|
||||||
|
printf '10G : %s %s/%s -> %s (metric %s)\n' "${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}"
|
||||||
|
}
|
||||||
|
|
||||||
|
usage() {
|
||||||
|
cat <<EOF
|
||||||
|
Usage: ${SCRIPT_NAME} {start|stop|status|fg|tail|clear|summary}
|
||||||
|
|
||||||
|
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 / configured NICs
|
||||||
|
fg Run in the foreground, output to the terminal (for a quick check)
|
||||||
|
tail tail -f the log file (does NOT return -- do not call from a macro)
|
||||||
|
clear Remove the log file and all rotated copies (must be stopped first)
|
||||||
|
summary Print just the per-leg RESULT lines from the log
|
||||||
|
|
||||||
|
Log file : ${LOG_FILE}
|
||||||
|
|
||||||
|
One round = 10G leg then 1G leg, each pinging its own target. Both NICs are
|
||||||
|
brought up and left up; addresses and routes are applied with
|
||||||
|
"ip address/route replace", so repeating a round does not stack duplicates.
|
||||||
|
|
||||||
|
If both NICs share a subnet, keep ARP_STRICT=1 -- otherwise a reply can come
|
||||||
|
back on the NIC that did not send it. Check nic_tx/nic_rx on the RESULT line:
|
||||||
|
they are that interface's own counter delta across the burst.
|
||||||
|
|
||||||
|
Edit the User Configurable Section at the top to change interfaces, addresses,
|
||||||
|
targets, prefix lengths, gateways, metrics or the packet count.
|
||||||
|
EOF
|
||||||
|
}
|
||||||
|
|
||||||
|
###############################################################################
|
||||||
|
# Entry point
|
||||||
|
###############################################################################
|
||||||
|
case "${1:-}" in
|
||||||
|
start) do_start ;;
|
||||||
|
stop) do_stop ;;
|
||||||
|
status) do_status ;;
|
||||||
|
fg) LOG_TO_FILE=0; main_loop ;;
|
||||||
|
tail) tail -n 50 -f "${LOG_FILE}" ;;
|
||||||
|
summary) grep -a 'RESULT' "${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]*
|
||||||
|
printf 'log cleared\n'
|
||||||
|
;;
|
||||||
|
__daemon) do_daemon ;;
|
||||||
|
-h|--help|"") usage ;;
|
||||||
|
*) printf '[ERROR] unknown sub-command: %s\n\n' "$1" >&2; usage; exit 1 ;;
|
||||||
|
esac
|
||||||
@@ -1,12 +1,22 @@
|
|||||||
;================================================================
|
;================================================================
|
||||||
; User Configuration
|
; User Configuration
|
||||||
;================================================================
|
;================================================================
|
||||||
strTestcase="Margin"
|
|
||||||
project_name = "Blanton"
|
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
|
EN_log = 1 ; 1: Enable log, 0: Disable log
|
||||||
|
|
||||||
|
;================================================================
|
||||||
|
; FAN_SPEED
|
||||||
|
;================================================================
|
||||||
|
FAN_SPEED = 30
|
||||||
|
;================================================================
|
||||||
|
; 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
|
; Prompt Definitions
|
||||||
;================================================================
|
;================================================================
|
||||||
|
|||||||
@@ -16,3 +16,8 @@ wait prompt_sonic_root
|
|||||||
sendln "show platform leak status"
|
sendln "show platform leak status"
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "show platform leak channels"
|
sendln "show platform leak channels"
|
||||||
|
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "tpm-dut-test fru"
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "tpm-dut-test tpm-read"
|
||||||
@@ -1,8 +1,11 @@
|
|||||||
|
; All Event
|
||||||
wait prompt_sonic_root
|
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
|
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
|
wait prompt_sonic_root
|
||||||
sendln "dmesg | grep -i fail"
|
sendln "dmesg -C"
|
||||||
wait prompt_sonic_root
|
|
||||||
sendln "dmesg | grep -i warning"
|
|
||||||
|
|||||||
@@ -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
|
||||||
Reference in New Issue
Block a user