Compare commits
13
Commits
fd35857d80
...
V1.0.3
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
419b680980 | ||
|
|
4ed283d0ca | ||
|
|
491e807cf8 | ||
|
|
18ce7a1a73 | ||
|
|
d1b5cfea0b | ||
|
|
5e63e3da6b | ||
|
|
855b7a6e30 | ||
|
|
310f897067 | ||
|
|
fedf697977 | ||
|
|
ababb2c3d1 | ||
|
|
a9c3dafc22 | ||
|
|
4088a828c6 | ||
|
|
afb7b1e283 |
@@ -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
|
||||||
~$*
|
~$*
|
||||||
|
|||||||
+95
-19
@@ -37,6 +37,7 @@ 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`) |
|
||||||
|
| BMC 存取 | host 端 `bmc-manager run "<cmd>"`(不需對 BMC 開 SSH,繞開其 busybox 工具鏈) |
|
||||||
| 壓力測試 | `mlucas-avx2`(AMD CPU)、`~/hammer/tools/stress_{mem,ssd,usb}.py` |
|
| 壓力測試 | `mlucas-avx2`(AMD CPU)、`~/hammer/tools/stress_{mem,ssd,usb}.py` |
|
||||||
| 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` |
|
||||||
@@ -106,7 +107,8 @@ 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 +133,9 @@ 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)
|
||||||
@@ -148,6 +152,7 @@ Blanton_TTL_Script/
|
|||||||
│ ├── show_dmesg.ttl # date + dmesg grep error/fail/warning
|
│ ├── show_dmesg.ttl # date + dmesg grep error/fail/warning
|
||||||
│ ├── 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 +172,18 @@ 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
|
||||||
|
├── bmc_monitor.sh # BMC 監控:週期跑 free -m,寫輪替 log
|
||||||
|
├── bmc_monitor_ddr.sh # BMC DDR 壓力:memtester,逾時 3600s
|
||||||
|
│ # ↑ 兩支都要 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
|
||||||
```
|
```
|
||||||
|
|
||||||
---
|
---
|
||||||
@@ -208,6 +219,18 @@ 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 +290,18 @@ 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` V1.0.3 | root 登入 → `date -s` 對時 → `show boot` → **等 pmon 起來**(`wait_init.ttl`)→ BMC 版本 → source 六個 bash 工具 → 清/讀 7 組 PCIe AER → `lspci` → margin 全掃 → PMON 九項 → dmesg → 100G port 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` + 5 份 `stress_mem.py` + `stress_ssd.py` + `stress_usb.py`(**共 8 個 job**)→ 啟動兩支 BMC monitor → `jobs` → 100G port 狀態 → traffic `ps/init/clear/show/start`(**兩個 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)` → PMON + dmesg → 7 組 AER → 停兩支 BMC monitor 並 `cat` 其 log → `cat` mlucas / stress_ssd log → traffic `stop` + `report`(兩個 unit)→ `show reboot-cause` / `show uptime` → 完成 messagebox |
|
||||||
| **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 |
|
||||||
|
| **BMC 監控 / 壓力** | `bmc_monitor.sh` / `bmc_monitor_ddr.sh` `{start\|stop\|status\|fg\|tail\|clear}` | 由 host 端 `bmc-manager run` 週期性打 BMC,背景 detached、log 輪替。前者跑 `free -m`(逾時 30s),後者跑 `memtester`(逾時 3600s),各自獨立 log 與 pid |
|
||||||
|
| **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 |
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
@@ -298,7 +323,12 @@ Script A ── logopen Logs/Blanton_Margin_<ts>.log ──┐ (之後所有畫
|
|||||||
├─ 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 | grep error/fail/warning
|
||||||
|
├─ show interfaces status Ethernet513,Ethernet514 ← 100G uplink 狀態
|
||||||
|
├─ 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 +336,9 @@ 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")
|
||||||
|
├─ BMC: bmc_monitor.sh start + bmc_monitor_ddr.sh start
|
||||||
├─ jobs ← 確認全部起來了
|
├─ jobs ← 確認全部起來了
|
||||||
├─ traffic: ps → init → clear → (pause 3) → show → start (unit 0,VLAN 30..137 loopback)
|
├─ 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 +348,10 @@ 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
|
||||||
|
├─ BMC: 兩支 monitor stop → cat log/bmc_poll.log + log/bmc_ddr.log
|
||||||
├─ cat mlucas_amm_log / log.stress_ssd ← 壓力程式自身的 pass/fail
|
├─ cat mlucas_amm_log / log.stress_ssd ← 壓力程式自身的 pass/fail
|
||||||
└─ traffic: stop → report ← per-pair TX/RX 交叉比對,PASS/FAIL/NA(exit 2 = 有 FAIL/NA)
|
├─ 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
|
||||||
▼
|
▼
|
||||||
[messagebox "GOOD JOB! Test Case DONE"] → 人工檢查 log
|
[messagebox "GOOD JOB! Test Case DONE"] → 人工檢查 log
|
||||||
```
|
```
|
||||||
@@ -369,7 +402,19 @@ 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: $'\r': command not found` + `syntax error near unexpected token`),
|
||||||
|
`settings/*.conf` 則因為是被 `source` 的,未加引號的賦值會變成 `"6\r"`(安靜地壞掉)。
|
||||||
|
`.gitattributes` 已把 `*.sh` `*.conf` `*.py` `*.txt` `*.md` 釘成 LF、`*.ttl` 維持 CRLF。
|
||||||
|
⚠️ 但 `.gitattributes` **不會回頭重寫既有工作區檔案** —— 早於它 clone 出來的目錄,
|
||||||
|
需 `git rm --cached -r . && git reset --hard` 或刪掉目錄重新 checkout 才會生效,
|
||||||
|
而且 `git status` 乾淨**不代表**磁碟上是 LF(`--renormalize` 只在進 index 的路上轉換)。
|
||||||
|
13. **`bmc_monitor*.sh` 需要執行權**:它們是本專案第一組「被執行」而非被 `source` 的腳本,
|
||||||
|
而 `do_start` 內部是 `setsid "$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. **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 +449,9 @@ 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 +487,19 @@ 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。
|
||||||
|
|
||||||
---
|
---
|
||||||
@@ -506,6 +567,10 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值,
|
|||||||
- [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 +595,15 @@ 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。
|
||||||
@@ -570,9 +636,9 @@ 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 +668,16 @@ 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。
|
||||||
|
- **`bmc_monitor*.sh` 的執行權**:目前需人工 `chmod +x`。可在 Script B 起它們之前補一行
|
||||||
|
`chmod +x`(比照既有的 `chmod +x ~/hammer/tools/amd/mlucas-avx2`),或在 publish 時處理。
|
||||||
|
- **`bmc_monitor_ddr.sh` 的壓力強度**:`memtester 500M 1` 配 `INTERVAL_SEC=5` 等於整個 soak
|
||||||
|
近乎不間斷壓 BMC 記憶體,而 BMC 同時還要服務 host 的 `show platform` 查詢。
|
||||||
|
若 PMON 取數變慢,先調大 `INTERVAL_SEC` 或縮小 memtester 的量。
|
||||||
|
|||||||
@@ -9,6 +9,10 @@ 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(2026-08-21)**:Script A/B/C 為 **V1.0.3**,涵蓋 PCIe AER / DDR EDAC / PMON /
|
||||||
|
電壓 margin(9 顆 LTC2980)/ SWB loopback 線速流量(兩個 switch unit)/ BMC 監控與 DDR 壓力。
|
||||||
|
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 +23,7 @@ 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)
|
||||||
- **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 +55,44 @@ 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
|
||||||
|
|
||||||
|
# ── BMC 監控 / 壓力(需先 chmod +x!)────────────────
|
||||||
|
chmod +x ~/Blanton_Script/bmc_monitor*.sh # 佈署後必做一次
|
||||||
|
~/Blanton_Script/bmc_monitor.sh start # free -m 取樣,log/bmc_poll.log
|
||||||
|
~/Blanton_Script/bmc_monitor_ddr.sh start # memtester,log/bmc_ddr.log
|
||||||
|
~/Blanton_Script/bmc_monitor.sh status # pid / log 路徑 / log 大小
|
||||||
|
~/Blanton_Script/bmc_monitor.sh stop
|
||||||
|
# ⚠️ tail 子命令是 tail -f,會卡住不返回;要倒 log 請直接 cat log/*.log
|
||||||
|
|
||||||
# ── 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 +119,10 @@ 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 +159,23 @@ 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 $'\r' <dir>`
|
||||||
|
- ⚠️ **`bmc_monitor*.sh` 需要 exec bit**,且**不是改用 `bash x.sh start` 就能繞過** ——
|
||||||
|
`do_start` 內部是 `setsid "$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 Script B 的 start 會 Permission denied、Script C 的 `cat` 撲空,而且**不會報錯**,
|
||||||
|
只會得到一份 BMC 段全空的 log
|
||||||
|
- ⚠️ **`bmc_monitor*.sh` 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`)
|
||||||
|
- ⚠️ **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 +184,6 @@ 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 +1,108 @@
|
|||||||
|
#!/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 : V1.0.3
|
||||||
; Date : 2026-08-17
|
; Date : 2026-08-21
|
||||||
; Author : ETWen
|
; Author : ETWen
|
||||||
; =============================================================================
|
; =============================================================================
|
||||||
; Version History:
|
; Version History:
|
||||||
@@ -14,7 +14,8 @@
|
|||||||
; 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
|
||||||
; =============================================================================
|
; =============================================================================
|
||||||
include "config.ttl"
|
include "config.ttl"
|
||||||
|
|
||||||
@@ -49,6 +50,18 @@ gettime timestr
|
|||||||
sprintf2 cmd 'sudo date -s "%s %s"' datestr timestr
|
sprintf2 cmd 'sudo date -s "%s %s"' datestr timestr
|
||||||
sendln cmd
|
sendln cmd
|
||||||
|
|
||||||
|
; ========== Show Build Name ==========
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "show boot"
|
||||||
|
|
||||||
|
; ========== Wait DUT Init ==========
|
||||||
|
wait prompt_sonic_root
|
||||||
|
include "utils/wait_init.ttl"
|
||||||
|
|
||||||
|
; ========== BMC version ==========
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "bmc-manager run 'cat /etc/issue'"
|
||||||
|
|
||||||
; ========== 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"
|
||||||
@@ -94,10 +107,32 @@ wait prompt_sonic_root
|
|||||||
;wait prompt_sonic_root
|
;wait prompt_sonic_root
|
||||||
;flushrecv
|
;flushrecv
|
||||||
|
|
||||||
; ========== TRAFFIC-SETUP-STAGE ==========
|
; ========== 100G Port Status ==========
|
||||||
;sendln "command"
|
wait prompt_sonic_root
|
||||||
|
sendln "show interfaces status Ethernet513,Ethernet514"
|
||||||
|
|
||||||
|
; ========== First Traffic Test ==========
|
||||||
|
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"
|
||||||
|
|
||||||
|
; ========== 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'
|
||||||
@@ -20,6 +20,13 @@ 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 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"
|
||||||
|
|
||||||
|
|
||||||
; ========== DDR MEMORY STRESS TEST ==========
|
; ========== DDR MEMORY STRESS TEST ==========
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "python ~/hammer/tools/stress_mem.py &"
|
sendln "python ~/hammer/tools/stress_mem.py &"
|
||||||
@@ -44,20 +51,24 @@ sendln "python ~/hammer/tools/stress_usb.py &"
|
|||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "jobs"
|
sendln "jobs"
|
||||||
|
|
||||||
; ========== Take one round of eye measurement on uplink ports ==========
|
|
||||||
|
; ========== 100G Port Status ==========
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "show interfaces status Ethernet513,Ethernet514"
|
||||||
|
|
||||||
|
|
||||||
; ========== Traffic START ==========
|
; ========== Traffic START ==========
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed ps -u 0"
|
sendln "blanton_traffic_linespeed ps"
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed init -u 0"
|
sendln "blanton_traffic_linespeed init"
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed clear -u 0"
|
sendln "blanton_traffic_linespeed clear"
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
pause 3
|
pause 15
|
||||||
sendln "blanton_traffic_linespeed show -u 0"
|
sendln "blanton_traffic_linespeed show"
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed start -u 0"
|
sendln "blanton_traffic_linespeed start"
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -25,6 +25,17 @@ 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"
|
||||||
|
|
||||||
|
; ========== BMC 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"
|
||||||
|
|
||||||
|
|
||||||
; ========== 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"
|
||||||
@@ -33,9 +44,15 @@ sendln "cat ~/hammer/tools/log.stress_ssd"
|
|||||||
|
|
||||||
; ========== CHECK Traffic counters ==========
|
; ========== CHECK Traffic counters ==========
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed stop -u 0"
|
sendln "blanton_traffic_linespeed stop"
|
||||||
wait prompt_sonic_root
|
wait prompt_sonic_root
|
||||||
sendln "blanton_traffic_linespeed report -u 0"
|
sendln "blanton_traffic_linespeed report"
|
||||||
|
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "show reboot-cause"
|
||||||
|
|
||||||
|
; ========== Show Power on uptime ==========
|
||||||
|
wait prompt_sonic_root
|
||||||
|
sendln "show uptime"
|
||||||
|
|
||||||
messagebox 'GOOD JOB! Test Case DONE' 'teraterm'
|
messagebox 'GOOD JOB! Test Case DONE' 'teraterm'
|
||||||
+22
@@ -1,5 +1,27 @@
|
|||||||
# margin.sh 實際下線指令追蹤 (Command Trace)
|
# margin.sh 實際下線指令追蹤 (Command Trace)
|
||||||
|
|
||||||
|
> ## ⚠️ 過期警告(2026-08-19)
|
||||||
|
>
|
||||||
|
> **本文件第 5~7 章的 SWB 指令追蹤已與現況不符,請勿照抄。**
|
||||||
|
> 上機驗證後 SWB 的 channel 配對與 LTC2977 位址都改了(commit `ababb2c`),
|
||||||
|
> 但本文件的 1223 條 `cb_pmbus_*` 指令是當時依舊值展開的,其中 487 條用到
|
||||||
|
> 已不存在的位址(`0x5D` / `0x5F` / `0x63` / `0x65`)。
|
||||||
|
>
|
||||||
|
> **正解以 `settings/*.conf` 為準:**
|
||||||
|
>
|
||||||
|
> | Channel | 板/接頭 | LTC2977 位址 |
|
||||||
|
> |---|---|---|
|
||||||
|
> | Ch6 | SWB0 CONN14 / CONN16 | CONN14 `0x5C`,`0x5E` ; CONN16 `0x62`,`0x64` |
|
||||||
|
> | Ch8 | SWB0 CONN13 / CONN15 | CONN13 `0x5C`,`0x5E` ; CONN15 `0x62`,`0x64` |
|
||||||
|
> | Ch7 | SWB1 CONN14 / CONN16 | CONN14 `0x5C`,`0x5E` ; CONN16 `0x62`,`0x64` |
|
||||||
|
> | Ch9 | SWB1 CONN13 / CONN15 | CONN13 `0x5C`,`0x5E` ; CONN15 `0x62`,`0x64` |
|
||||||
|
>
|
||||||
|
> 位址在同一顆 LTC2980 內是 **+2** 遞增(7-bit,由規格書 8-bit 配對除以 2 而來),
|
||||||
|
> 不是舊文件寫的 +1。原先記錄的 Ch6 上 `0x5E` 相撞問題已隨這次修正消失。
|
||||||
|
>
|
||||||
|
> 第 1~4 章(CB / i2c 路徑、暫存器語意、LINEAR16 換算)不受影響,仍然有效。
|
||||||
|
> 需要正確的 SWB 指令追蹤請重新產生本文件。
|
||||||
|
|
||||||
對象:`LTC2980_Margin_Script/margin.sh` v2.6.0
|
對象:`LTC2980_Margin_Script/margin.sh` v2.6.0
|
||||||
產生日期:2026-08-18
|
產生日期:2026-08-18
|
||||||
用途:紀錄每個 margin 指令在 I2C / PMBus 線上真正下了什麼,方便對照 log、
|
用途:紀錄每個 margin 指令在 I2C / PMBus 線上真正下了什麼,方便對照 log、
|
||||||
|
|||||||
@@ -17,8 +17,8 @@
|
|||||||
# * DEBUG_MODE collision fix: blanton_fpga_pcimem.sh uses the same var
|
# * DEBUG_MODE collision fix: blanton_fpga_pcimem.sh uses the same var
|
||||||
# name, so pcimem tracing is gated by MARGIN_SWB_PCIMEM_DEBUG
|
# name, so pcimem tracing is gated by MARGIN_SWB_PCIMEM_DEBUG
|
||||||
# * margin_swb_* wrappers (info/probe/scan/reset/sem) for debugging
|
# * margin_swb_* wrappers (info/probe/scan/reset/sem) for debugging
|
||||||
# Physical map: CB F3 Ch6=SWB0 CONN13/14, Ch8=SWB0 CONN15/16,
|
# Physical map: CB F3 Ch6=SWB0 CONN14/16, Ch8=SWB0 CONN13/15,
|
||||||
# Ch7=SWB1 CONN13/14, Ch9=SWB1 CONN15/16
|
# Ch7=SWB1 CONN14/16, Ch9=SWB1 CONN13/15
|
||||||
# v2.5.0 SWB margin support via a per-conf TRANSPORT layer. The SWB margin
|
# 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
|
||||||
@@ -72,10 +72,10 @@ CB_I2C_CH=""
|
|||||||
# --- SWB transport backend (blanton_cb_i2c.sh + blanton_fpga_pcimem.sh) -------
|
# --- 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.
|
# The SWB margin boards' LTC2980s hang off the CB FPGA Function 3 I2C master.
|
||||||
# Physical mapping (per bench wiring):
|
# Physical mapping (per bench wiring):
|
||||||
# CB F3 Ch6 -> SWB0 CONN13 / CONN14
|
# CB F3 Ch6 -> SWB0 CONN14 / CONN16
|
||||||
# CB F3 Ch8 -> SWB0 CONN15 / CONN16
|
# CB F3 Ch8 -> SWB0 CONN13 / CONN15
|
||||||
# CB F3 Ch7 -> SWB1 CONN13 / CONN14
|
# CB F3 Ch7 -> SWB1 CONN14 / CONN16
|
||||||
# CB F3 Ch9 -> SWB1 CONN15 / CONN16
|
# CB F3 Ch9 -> SWB1 CONN13 / CONN15
|
||||||
# Two CONNs share one FPGA I2C channel, so the two boards on a channel MUST use
|
# 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).
|
# different LTC2977 slave addresses (the CHIPS array in each .conf).
|
||||||
MARGIN_SWB_CHANNELS="${MARGIN_SWB_CHANNELS:-6 7 8 9}"
|
MARGIN_SWB_CHANNELS="${MARGIN_SWB_CHANNELS:-6 7 8 9}"
|
||||||
|
|||||||
+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 F3 Ch6 = SWB0 CONN13/CONN14 (shared with CONN14, addr must differ)
|
CB_I2C_CH=8 # CB F3 Ch8 = SWB0 CONN13/CONN15 (shared with CONN15, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- 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=6 # CB F3 Ch6 = SWB0 CONN13/CONN14 (shared with CONN13, addr must differ)
|
CB_I2C_CH=6 # CB F3 Ch6 = SWB0 CONN14/CONN16 (shared with CONN16, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- 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=8 # CB F3 Ch8 = SWB0 CONN15/CONN16 (shared with CONN16, addr must differ)
|
CB_I2C_CH=8 # CB F3 Ch8 = SWB0 CONN13/CONN15 (shared with CONN13, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
@@ -17,7 +17,7 @@ CB_I2C_CH=8 # CB F3 Ch8 = SWB0 CONN15/CONN16 (shared with CONN16, addr
|
|||||||
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 F3 Ch8 = SWB0 CONN15/CONN16 (shared with CONN15, addr must differ)
|
CB_I2C_CH=6 # CB F3 Ch6 = SWB0 CONN14/CONN16 (shared with CONN14, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- 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 F3 Ch7 = SWB1 CONN13/CONN14 (shared with CONN14, addr must differ)
|
CB_I2C_CH=9 # CB F3 Ch9 = SWB1 CONN13/CONN15 (shared with CONN15, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
@@ -17,7 +17,7 @@ CB_I2C_CH=7 # CB F3 Ch7 = SWB1 CONN13/CONN14 (shared with CONN14, addr
|
|||||||
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=7 # CB F3 Ch7 = SWB1 CONN13/CONN14 (shared with CONN13, addr must differ)
|
CB_I2C_CH=7 # CB F3 Ch7 = SWB1 CONN14/CONN16 (shared with CONN16, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- 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=9 # CB F3 Ch9 = SWB1 CONN15/CONN16 (shared with CONN16, addr must differ)
|
CB_I2C_CH=9 # CB F3 Ch9 = SWB1 CONN13/CONN15 (shared with CONN13, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- I2C Configuration ---
|
||||||
|
|
||||||
@@ -17,7 +17,7 @@ CB_I2C_CH=9 # CB F3 Ch9 = SWB1 CONN15/CONN16 (shared with CONN16, addr
|
|||||||
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 F3 Ch9 = SWB1 CONN15/CONN16 (shared with CONN15, addr must differ)
|
CB_I2C_CH=7 # CB F3 Ch7 = SWB1 CONN14/CONN16 (shared with CONN14, addr must differ)
|
||||||
|
|
||||||
# --- I2C Configuration ---
|
# --- 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
|
||||||
@@ -1,10 +1,10 @@
|
|||||||
;================================================================
|
;================================================================
|
||||||
; 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
|
||||||
;================================================================
|
;================================================================
|
||||||
|
|||||||
@@ -0,0 +1,30 @@
|
|||||||
|
; =============================================================================
|
||||||
|
; File : utils/wait_init.ttl
|
||||||
|
; Version : V1.0.0
|
||||||
|
; Date : 2026-08-21
|
||||||
|
; Author : ETWen
|
||||||
|
; =============================================================================
|
||||||
|
; Wait until "show platform temperature" is not "Thermal Not detected".
|
||||||
|
; Enter : prompt of the previous command is NOT consumed.
|
||||||
|
; Exit : "show platform temperature" is sent, prompt NOT consumed.
|
||||||
|
;
|
||||||
|
; Version History:
|
||||||
|
; V1.0.0 2026-08-21 Initial Version
|
||||||
|
; =============================================================================
|
||||||
|
wt_interval = 10
|
||||||
|
timeout = 30
|
||||||
|
wait prompt_sonic_root
|
||||||
|
|
||||||
|
:WAIT_THERMAL
|
||||||
|
sendln "show platform temperature"
|
||||||
|
wait "Thermal Not detected" prompt_sonic_root
|
||||||
|
if result = 2 then
|
||||||
|
goto THERMAL_OK
|
||||||
|
endif
|
||||||
|
wait prompt_sonic_root
|
||||||
|
pause wt_interval
|
||||||
|
goto WAIT_THERMAL
|
||||||
|
|
||||||
|
:THERMAL_OK
|
||||||
|
timeout = 0
|
||||||
|
sendln "show platform temperature"
|
||||||
Reference in New Issue
Block a user