Compare commits
10
Commits
4648f936c7
..
main
| Author | SHA1 | Date | |
|---|---|---|---|
  etwenandClaude Opus 5
|
a5b7c4757b | ||
|
etwenandClaude Opus 5
|
f5694345fb | ||
|
etwenandClaude Opus 5
|
7a1967bc9a | ||
|
etwenandClaude Opus 5
|
496e3ab650 | ||
|
etwenandClaude Opus 5
|
29ec4c2239 | ||
|
etwenandClaude Opus 5
|
d73b119dc3 | ||
|
etwenandClaude Opus 5
|
79a3604ac4 | ||
|
etwenandClaude Opus 5
|
b84188322d | ||
|
etwenandClaude Opus 5
|
b4148c9571 | ||
|
etwenandClaude Opus 5
|
eacb218da8 |
+53
-24
@@ -161,7 +161,7 @@ Blanton_TTL_Script/
|
||||
│
|
||||
├── 4_Blanton_Script_thermal_safety.ttl # 熱 / 安規：獨立跑，不接 A→B→C
|
||||
├── 5_Blanton_Script_Reboot_Cycle.ttl # 重開機循環：獨立跑，while 1 無止境（未上機驗證）
|
||||
├── config.ttl # 全域設定：testcase 名、EN_Margin / EN_log / EN_timestamp、
|
||||
├── config.ttl # 全域設定：testcase 名、EN_Margin / EN_TX_FIR / EN_log / EN_timestamp、
|
||||
│ # 風扇與 SWB 宣告、SSD/USB/BMC_USB 壓力秒數、三個 prompt 字串
|
||||
├── hammer/ # 🚫 gitignored — mlucas ELF binary（~99 MB），DUT image 自帶，
|
||||
│ # publish.sh 也排除；Script B / Script 4 只負責 chmod +x 後執行
|
||||
@@ -199,7 +199,11 @@ Blanton_TTL_Script/
|
||||
├── mgmt_ping_monitor.sh # 10G/1G 管理網路 ping 監控（iproute2）
|
||||
│ # eth0→TARGET_10G、eth1→TARGET_1G，兩張卡同時持續 ping
|
||||
├── port_prbs_monitor.sh # 100G uplink PRBS 測試（bcmcmd phy diag）
|
||||
│ # ⚠️ V1.1.9 起 A/B/C 內註解掉的呼叫已整段刪除，只剩手動執行
|
||||
├── blanton_ber.sh # 全機 SerDes BER 掃描（phydiag prbs / prbsstat）
|
||||
├── bcm_dsc_scan.sh # 全機 SerDes DSC dump（phydiag <port> dsc，~445 port × 2 unit）
|
||||
│ # 由 EN_TX_FIR 控制，A 與 C 各掃一次；單次約 10 分鐘
|
||||
├── bcm_dsc_parse.sh # DSC raw log → <prefix>_lane.csv / _pm.csv（純 sh + awk）
|
||||
├── blanton_multiphase_margin.sh # 多相 VRM margin（原生 i2c，38 條軌）
|
||||
├── pwr_brick.sh # PDB / CPB power brick 讀值（VI2C ch4）
|
||||
├── nfc_polling.sh # NFC tag 背景輪詢 + PASS/FAIL 統計
|
||||
@@ -210,7 +214,7 @@ Blanton_TTL_Script/
|
||||
│ # ⚠️ 已納入交付，但 A/B/C 的呼叫仍註解掉（bring-up 中）
|
||||
├── usb_target.sh # 偵測 USB 裝置節點／掛載點（排除系統碟）
|
||||
├── bmc_monitor.sh # BMC 監控：free -m + I2C 寫入/讀回圖樣測試
|
||||
├── bmc_monitor_ddr.sh # ⚠️ 已停用：B/C 內呼叫處已註解，DDR 壓力改走 bgctl + bmc-manager
|
||||
├── bmc_monitor_ddr.sh # ⚠️ 已停用：V1.1.9 起 B/C 內的註解區塊已刪除，DDR 壓力走 bgctl + bmc-manager
|
||||
│ # ↑ 三支都要 chmod +x 才能跑（見 Key Constraints）
|
||||
└── LTC2980_Margin_Script/ # 電壓 margin 子專案（另有獨立 repo）
|
||||
├── margin.sh # margin_init/status/set/apply_profile/save
|
||||
@@ -370,10 +374,10 @@ PROFILE_CHANNELS=( "0:high:8" "1:low:8" ... ) # "channel:operation:change_perc
|
||||
|
||||
| 模組 | 進入點 | 功能 |
|
||||
|------|--------|------|
|
||||
| **Script A（Pre-test）** | `1_Blanton_Script_A.ttl` V1.1.8 | root 登入 → `date -s` 對時 → 清 job log → **收掉前一輪殘留**（`hw-test-session finish` → `bgctl reset --yes` → `bgctl stop --all` → `bgctl list` 確認清空）→ `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** → **NFC 基線**（start → 30s → stop → report）→ 100G uplink 設定與狀態 → **一輪流量基線** → `show uptime` |
|
||||
| **Script B（Stress）** | `2_Blanton_Script_B.ttl` | **V1.1.8 起 `mlucas-avx2 -cpu 0:15` 由 `systemd-run --unit=mlucas-amm`（`Type=exec`、`Restart=always`）啟動，不再是 shell 的 `&` 背景 job** + `bgctl run` 的 `memtester` / SSD / USB 壓力（v1.1.7 起 SSD/USB 的 `--runtime`/`--passes` 讀 `config.ttl` 的 `SSD_RUNTIME`/`SSD_COUNT`、`USB_RUNTIME`/`USB_COUNT`；BMC memtester 不帶次數 = 跑到被停） + BMC DDR（`bmc-manager run memtester`）→ BMC USB net test（探測 cdc_ncm 介面，`systemd-run` 掛 `BMC_USB_RUNTIME` 秒的 ping，V1.1.8 前寫死 4 小時）→ 啟動 mgmt ping 監控 → **啟動 NFC 輪詢** → `jobs` / `systemctl is-active mlucas-amm` / `bgctl list` → traffic（依 `SWB_UNIT`）→ `while 1` 每輪 PMON + `bgctl list`/`jobs`/`systemctl is-active mlucas-amm` + `pause 60`（**V1.1.4 起 margin 不在迴圈內**）|
|
||||
| **Script C（Post-test）** | `3_Blanton_Script_C.ttl` | `kill $(jobs -p)` + **`systemctl stop mlucas-amm`**（systemd unit 不是 shell job，`jobs -p` 抓不到）+ `bgctl stop --all` / `reset` + 停 BMC USB unit、mgmt ping 與 **NFC 輪詢** → PMON + dmesg → 7 組 AER + `ras-mc-ctl` → BMC USB `journalctl` **寫進 `log/bmc_usb_net.log`**（不再印在 console） → `ip -s link show eth0/eth1` → `cat` mlucas log（並 `cp` 進 job 目錄一起帶走）→ **NFC `report`** → traffic `stop` + `report` → **BER 掃描**（依 `SWB_UNIT`）→ NVMe 健康 → `show reboot-cause` → **margin 掃描**（`EN_Margin`，V1.1.4 由 Script B 移來）→ `uptime` → **job log 複製到 USB（帶時戳）** → `exit` + wait『Script done』→ `hw-test-session finish` |
|
||||
| **Script 4（Thermal / Safety）** | `4_Blanton_Script_thermal_safety.ttl` | **獨立腳本，不接 A→B→C。** Script A 式的環境建立（登入 / session / 風扇 / `wait_init` / DUT 清單 / BMC / PCIe 清除 / `pcie_bus` / PMON / dmesg）→ **滿載**（`mlucas-avx2 -cpu 0:15` 背景 + `blanton_tr518.sh start`）→ `while 1`：PMON + `TH6_SWB0/1_power_readback.sh` + `bgctl list` / `jobs`，`pause 60`。**沒有收尾段** —— 中斷後 DUT 仍在 `port cd lb=mac` / `l2 learn off` / `test mode nr=yes`，要手動 `blanton_tr518.sh stop` |
|
||||
| **Script A（Pre-test）** | `1_Blanton_Script_A.ttl` V1.2.1 | root 登入 → `date -s` 對時 → 清 job log → **收掉前一輪殘留**（`hw-test-session finish` → `bgctl reset --yes` → `bgctl stop --all` → `bgctl list` 確認清空）→ `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** → **NFC 基線**（start → 30s → stop → report）→ 100G uplink 設定與狀態 → **BER 基線掃描**（依 `SWB_UNIT`，V1.2.1 新增）→ **一輪流量基線** → **SerDes DSC 基線**（`EN_TX_FIR`）→ `show uptime` |
|
||||
| **Script B（Stress）** | `2_Blanton_Script_B.ttl` | **V1.1.8 起 `mlucas-avx2 -cpu 0:15` 由 `systemd-run --unit=mlucas-amm`（`Type=exec`、`Restart=always`）啟動，不再是 shell 的 `&` 背景 job** + `bgctl run` 的 `memtester` / SSD / USB 壓力（v1.1.7 起 SSD/USB 的 `--runtime`/`--passes` 讀 `config.ttl` 的 `SSD_RUNTIME`/`SSD_COUNT`、`USB_RUNTIME`/`USB_COUNT`；BMC memtester 不帶次數 = 跑到被停） + BMC DDR（`bmc-manager run memtester`）→ BMC USB net test（探測 cdc_ncm 介面，`systemd-run` 掛 `BMC_USB_RUNTIME` 秒的 ping，V1.1.8 前寫死 4 小時）→ 啟動 mgmt ping 監控 → **啟動 NFC 輪詢** → `jobs` / `systemctl is-active mlucas-amm` / `bgctl list` → traffic（依 `SWB_UNIT`）→ `while 1` 每輪 PMON + `bgctl list`/`jobs`/`systemctl is-active mlucas-amm` + `sleep 60`（**V1.1.4 起 margin 不在迴圈內**；V1.2.0 起等待走 DUT 端 `sleep` 而非 macro 端 `pause`）|
|
||||
| **Script C（Post-test）** | `3_Blanton_Script_C.ttl` | `kill $(jobs -p)` + **`systemctl stop mlucas-amm`**（systemd unit 不是 shell job，`jobs -p` 抓不到）+ `bgctl stop --all` / `reset` + 停 BMC USB unit、mgmt ping 與 **NFC 輪詢** → PMON + dmesg → 7 組 AER + `ras-mc-ctl` → BMC USB `journalctl` **寫進 `log/bmc_usb_net.log`**（不再印在 console） → `ip -s link show eth0/eth1` → `cat` mlucas log（並 `cp` 進 job 目錄一起帶走）→ **NFC `report`** → traffic `stop` + `report` → **SerDes DSC 收尾**（`EN_TX_FIR`）→ **BER 掃描**（依 `SWB_UNIT`）→ NVMe 健康 → `show reboot-cause` → **margin 掃描**（`EN_Margin`，V1.1.4 由 Script B 移來）→ `uptime` → **job log 複製到 USB（帶時戳）** → `exit` + wait『Script done』→ `hw-test-session finish` |
|
||||
| **Script 4（Thermal / Safety）** | `4_Blanton_Script_thermal_safety.ttl` | **獨立腳本，不接 A→B→C。** Script A 式的環境建立（登入 / session / 風扇 / `wait_init` / DUT 清單 / BMC / PCIe 清除 / `pcie_bus` / PMON / dmesg）→ **滿載**（`mlucas-avx2 -cpu 0:15`，V1.1.8 起與 Script B 同樣掛成 `mlucas-amm` systemd unit + `blanton_tr518.sh start`）→ `while 1`：PMON + `TH6_SWB0/1_power_readback.sh` + `bgctl list` / `jobs` / `systemctl is-active mlucas-amm`，`pause 60`。**沒有收尾段** —— 中斷後 DUT 仍在 `port cd lb=mac` / `l2 learn off` / `test mode nr=yes`，且 CPU 仍滿載，要手動 `blanton_tr518.sh stop` + `systemctl stop mlucas-amm` |
|
||||
| **Script 5（Reboot Cycle）** | `5_Blanton_Script_Reboot_Cycle.ttl` | **獨立腳本，不接 A→B→C。** `while 1`：登入 → `sudo -i` → 對時 → 風扇 → **Check Pt1~Pt13**（DUT/BMC info、mgmt ping、NFC、SSD、USB、BMC USB、port status + 15s traffic、BER、NVMe、platform data、dmesg i2c、PCIe error counters）→ `show uptime` → `reboot` → `wait "Booting in blind mode"`。`cnt_cycle` 每輪 +1 印在標頭。**沒有結束條件** —— 要停就關掉 Tera Term 的 macro。**尚未上機驗證** |
|
||||
| **SWB loopback 流量** | `blanton_traffic_linespeed <sub> [-u 0\|1\|all]` | `init`（VLAN 30..137，成對 `cdN`/`cdN+32`）→ `clear` → `start`（`tx 200 length=324 PatternRandom=yes`，v0.7.0 起）→ `stop` → `report`（per-pair TX/RX 交叉比對 PASS/FAIL）；另有 `ps`（link/speed）與 `run`（一條龍）。**V0.6.0 起含 100G uplink `ce0`**（VLAN 138）：它沒有 loopback 對象，靠 **ingress mirror 打回自己**維持循環，`report` 最後一列就是它，底下再接一份跨 unit summary |
|
||||
| **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 |
|
||||
@@ -386,9 +390,10 @@ PROFILE_CHANNELS=( "0:high:8" "1:low:8" ... ) # "channel:operation:change_perc
|
||||
| **Margin 寫 NVM** | `margin_save` / `margin_save all` / `margin_save blanton` | ⚠️ 永久寫入。`0x15` 送 PMBus **send-byte**（不帶 data byte）。`all` = 依 `settings/` 走 9 顆、跑完還原原本載入的板子；`blanton` = 本平台捷徑，18 顆全走原生 i2c bus（`MARGIN_BLANTON_STORE` 表），不需 `margin_init`。每筆之間 `MARGIN_STORE_SETTLE`（0.5s），工具**不 poll busy bit** |
|
||||
| **管理網路 ping** | `mgmt_ping_monitor.sh {start\|stop\|status\|fg\|tail\|clear\|summary}` | 一輪 = 10G leg + 1G leg，各自 `ip address/route replace` 後 `ping -I <if>` 打自己的對端；兩張卡都保持 up。每 leg 記 `ip -s link show` 與該卡的 TX/RX packet delta，另出一行可 grep 的 `RESULT` |
|
||||
| **BMC 監控** | `bmc_monitor.sh {start\|stop\|status\|fg\|tail\|clear}` | 由 host 端 `bmc-manager run` 週期取樣 `free -m`，另加一組 **I2C 寫入/讀回圖樣測試**（bus 1、addr 0x41、offset 0x00C0，寫 `55AA55AA` 讀回、再寫 `AA55AA55` 讀回）。B 啟動、C 停止並 `cat log/bmc_poll.log` |
|
||||
| **BMC DDR 壓力** | `bmc_monitor_ddr.sh` | ⚠️ **已停用** —— B/C 內呼叫處已註解，改由 `bgctl run bmc-manager run memtester` 取代。檔案保留未刪 |
|
||||
| **100G PRBS** | `port_prbs_monitor.sh {start [both\|a\|b]\|stop\|status\|report\|clear}` | 兩個 uplink 各一個 worker，可同時或單獨跑。setup（`lpmode off` → `prbs set` → `prbsstat STArt`）→ 週期 `prbs get`（判定）+ `prbsstat Ber`（只記錄）→ teardown（`STOp` + `prbs clear`）。輸出含 `PRBS OK!` 才算 PASS。**⚠️ A/B/C 的呼叫目前註解掉** |
|
||||
| **SerDes BER 掃描** | `blanton_ber.sh {init\|clear\|start\|stop\|report} [-u 0\|1\|all]` | 全機每個對接 port 的 PRBS BER：`prbs set p=3` + `prbs get`（確認每條 lane 都鎖上）→ `prbsstat STArt Interval=30` →（等一個 interval）→ `prbsstat Ber` → `STOp` → `prbs clear`。`report` 一列一條 lane，**BER < 1e-6 才 PASS**，最後跨 unit 的 summary 帶最差 lane。⚠️ PRBS 期間 link 顯示 DOWN、不過流量 |
|
||||
| **BMC DDR 壓力** | `bmc_monitor_ddr.sh` | ⚠️ **已停用** —— V1.1.9 起 B/C 內的註解區塊已刪除，改由 `bgctl run bmc-manager run memtester` 取代。檔案保留未刪 |
|
||||
| **SerDes DSC 擷取** | `bcm_dsc_scan.sh [-u 0\|1] [-f <name>] [-F] [-n] [-C]` + `bcm_dsc_parse.sh -i <log> -o <prefix>` | `bcmcmd -n <unit> -c "dsh -c 'phydiag <port> dsc'"` 掃全清單（1 個 100G + 445 個 200G port）× 2 unit，raw log 寫進 `<script_dir>/log` 再 `cp` 到 `/host/hw-eval/jobs`。`-f` 支援 `%u` / `%t`；沒帶 `%u` 時自動插 `_u0`/`_u1`。成功與否**不看 `bcmcmd` 的 exit code**，改比對 `SERDES DISPLAY DIAG DATA END` 數量 + 實際迭代筆數，結尾印 `### DSC_SCAN_DONE rc=<n>`。parse 端輸出 `_lane.csv`（每 lane：TXEQ/RXFFE/DFE/EYE/SNR）與 `_pm.csv`（每 pm_id：溫度/PLL/lane 數/統計）。**由 `EN_TX_FIR` 控制，預設關** |
|
||||
| **100G PRBS** | `port_prbs_monitor.sh {start [both\|a\|b]\|stop\|status\|report\|clear}` | 兩個 uplink 各一個 worker，可同時或單獨跑。setup（`lpmode off` → `prbs set` → `prbsstat STArt`）→ 週期 `prbs get`（判定）+ `prbsstat Ber`（只記錄）→ teardown（`STOp` + `prbs clear`）。輸出含 `PRBS OK!` 才算 PASS。**⚠️ V1.1.9 起 A/B/C 內的註解呼叫已刪除，只能手動跑** |
|
||||
| **SerDes BER 掃描** | `blanton_ber.sh {init\|clear\|start\|stop\|report} [-u 0\|1\|all]` | 全機每個對接 port 的 PRBS BER：`prbs set p=3` + `prbs get`（確認每條 lane 都鎖上）→ `prbsstat STArt Interval=30` →（等一個 interval）→ `prbsstat Ber` → `STOp` → `prbs clear`。`report` 一列一條 lane，**BER < 1e-6 才 PASS**，最後跨 unit 的 summary 帶最差 lane。⚠️ PRBS 期間 link 顯示 DOWN、不過流量。V1.2.1 起 Script A 與 Script C 各跑一次（A 在流量之前、C 在流量報表之後），夾住 soak |
|
||||
| **TR518 負載** | `blanton_tr518.sh {start\|stop} [-u 0\|1\|all]` | `port cd lb=mac` → `l2 learn off` → `test mode nr=yes` → `tr 518 ... testphase=1`，然後 settle `TR_SETTLE_SEC`（120s）再讓人量功耗。`stop` 只送 `port cd lb=none`（照 `TR518.txt`），L2 學習與 test mode **不會還原**，`TR_RESTORE_*=1` 才會 |
|
||||
| **PDB / CPB brick** | `pwr_brick.sh show [-r]` | 5 顆 brick 的 Vin / Iin / Vout / Iout / Temp（SWB0 `0x62`/`0x63`、SWB1 `0x60`/`0x61`、CPB `0x26`）。四顆 ADPM12200 **每個量各自一個 PMBus PAGE**（Vin 9、Iin 10、Vout 2、Iout 14、Temp 18），讀之前一定要先寫 PAGE —— `blanton_pwr_data.sh` 完全沒寫，所以整張 PDB 表都是 NA。換算用手冊 DIRECT 公式 `X=(1/m)(Y×10⁻ᴿ−b)`。每個值重讀到通過三道檢查為止（非 `0xFFFF`、非 `0x0000`、落在合理範圍）—— 這條匯流排**只壞高位元組**，`11.98 V` 會變成 `32.00 V`，全一過濾擋不住 |
|
||||
| **SWB 軌功耗** | `TH6_SWB{0,1}_power_readback.sh` | 讀 `show platform voltage/current` **各一次**，19 條軌 V×I 與總功耗。舊版每軌各讀一次（38 次呼叫、每軌不同時刻），總和是不同瞬間的加總 |
|
||||
@@ -510,6 +515,11 @@ pwr_data
|
||||
`vlan create` 的 `Entry exists`（重跑 init）與 `vlan remove` 的 `not found`（init 前先 stop）
|
||||
當良性情況分開計數。另外 `bcmcmd` 一律以 `</dev/null` 執行 ——
|
||||
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）。
|
||||
**2026-09-07 `bcm_dsc_scan.sh` 又踩了同一個坑**（port 清單走 stdin，445 個 port 只掃了 1 個），
|
||||
而且因為 `### PORT` marker 與 dsc 區塊數量一起變少，原本的比對檢查完全看不出來、`rc=0`。
|
||||
修法：迴圈改讀 fd 3（`done 3< "$PORTFILE"`）+ `bcmcmd ... < /dev/null`，再加一道
|
||||
「實際迭代筆數 == 清單筆數」的獨立檢查。**寫任何餵檔案給 `while` 又在裡面呼叫 `bcmcmd` 的迴圈，
|
||||
都要假設它會讀 stdin；而且完整性檢查不能只比對兩個會一起變少的數字。**
|
||||
11. **DUT 密碼不得進 git**：`1_Blanton_Script_A.ttl` 目前的 `sendln "YourPaSsWoRd"` 是 placeholder，
|
||||
實際帳密必須放 `secret/config_secret.ttl`（gitignored）並由 `config.ttl` include。
|
||||
12. **`.sh` / `.conf` 必須是 LF**：CRLF 的 shell script 在 SONiC 上直接掛
|
||||
@@ -545,11 +555,19 @@ pwr_data
|
||||
搬到 `mlucas-amm` unit（好處：掉線不會停、`jobs` 看不見的問題消失、`Restart=always` 會自動拉回），
|
||||
代價是 Script C 少了那行 `systemctl stop` 就會讓 CPU 滿載燒進收工量測與下一輪測試 ——
|
||||
而 `show interfaces status` 之類的檢查完全看不出來。目前 `mlucas-amm` 與
|
||||
`qfx5252-bmc-usb-net-test` 兩個 unit 都已在 Script C 收掉；
|
||||
⚠️ **`4_Blanton_Script_thermal_safety.ttl` 的 `mlucas-avx2` 仍是 `&` 背景 job**，
|
||||
兩支腳本目前用不同機制，改動時不要互相套用。
|
||||
18. **`config.ttl` 少一個變數會讓 macro 當場中止**，不是當成 0。V1.1.8 新增 `EN_timestamp`
|
||||
（Script A `logopen` 的第 5 個參數）與 `BMC_USB_RUNTIME`（Script B 的 ping unit）。
|
||||
`qfx5252-bmc-usb-net-test` 兩個 unit 都已在 Script C 收掉。
|
||||
⚠️ **`4_Blanton_Script_thermal_safety.ttl` 用同一個 `mlucas-amm` unit，但它沒有收尾段**，
|
||||
所以那行 `systemctl stop mlucas-amm` 必須由測試員手動下 —— 這是 Script 4 目前
|
||||
唯一一個「不下就會延續到下一輪」的負載。
|
||||
18. **`pause` 停的是 macro，`sleep` 停的是 DUT。** V1.2.0 起 A/B/C 的等待一律改成
|
||||
`sendln "sleep N"` + `wait prompt_sonic_root`。`pause N` 期間 macro 不理會 DUT，shell 是閒著的，
|
||||
等於用猜的估上一個指令要跑多久 —— DUT 一忙就會提早往下送指令；改成 DUT 端 `sleep` 之後，
|
||||
prompt 回來才繼續，兩邊不可能走散，而且這段等待會帶時戳進 log，事後看得出哪一輪跑久了。
|
||||
⚠️ **Script 4 與 Script 5 尚未轉換，仍在用 `pause`**；B/C 開頭的 `pause 1` 也保留
|
||||
（它在登入前執行，沒有 prompt 可等）。
|
||||
19. **`config.ttl` 少一個變數會讓 macro 當場中止**，不是當成 0。V1.1.8 新增 `EN_timestamp`
|
||||
（Script A `logopen` 的第 5 個參數）與 `BMC_USB_RUNTIME`（Script B 的 ping unit）；
|
||||
V1.2.0 再加 `EN_TX_FIR`（A/C 的 DSC 掃描與 C 的四行 `cp`，預設 0）。
|
||||
只更新 `.ttl` 卻沿用舊的 `config.ttl`，Script A 會停在 `logopen` 那一行。
|
||||
另外 **時間戳的「格式」不在 macro 裡** —— 它在 Tera Term 的
|
||||
Setup → Additional settings → Log，存在那台電腦的 `TERATERM.INI`，會跟著 PC 而不是跟著腳本走。
|
||||
@@ -786,7 +804,7 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值，
|
||||
- [ ] `CHANGELOG.md`：延續三支腳本頂端的 Version History，集中成一份
|
||||
- [ ] 三支腳本的 header 版號與 `CHANGELOG.md` 對齊，`config.ttl` 加 `script_version` 並寫進 log 開頭
|
||||
- [ ] `docs/TTL_Script_Blanton_Status_*.xlsx` 更新為全 OK，或把剩餘項目移進 Future Extensions
|
||||
- [x] 打 git tag，push `nas` + `gitea`（已至 `V1.1.8`；`publish/` 依 Script A 檔頭版號打包）
|
||||
- [x] 打 git tag，push `nas` + `gitea`（已至 `V1.2.1`；`publish/` 依 Script A 檔頭版號打包）
|
||||
|
||||
**驗收條件：** 從 zip 解壓到一台乾淨的測試 NB，照 README 操作，不看原始碼就能完成一輪 A→B→C
|
||||
並產出 summary；`publish/` 內容與 git tag 一致。
|
||||
@@ -820,14 +838,19 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值，
|
||||
Script A 既不往下走也不報錯。可加最大重試次數 + `messagebox` 提示。
|
||||
- **腳本的執行權**：`mgmt_ping_monitor.sh` 與 `bmc_monitor.sh`（以及已停用的 `bmc_monitor_ddr.sh`）需人工 `chmod +x`。
|
||||
可在 Script B 起它之前補一行（比照既有的 `chmod +x ~/hammer/tools/amd/mlucas-avx2`），或在 publish 時處理。
|
||||
- **`bmc_monitor_ddr.sh` 已停用**：B/C 內的呼叫已註解，DDR 壓力改由 `bgctl run bmc-manager run memtester`
|
||||
取代。檔案還留在 repo，待確認不再需要後刪除，或在檔頭標註停用。
|
||||
- **`bmc_monitor_ddr.sh` 已停用**：V1.1.9 起 B/C 內那段註解掉的呼叫已刪除，DDR 壓力由
|
||||
`bgctl run bmc-manager run memtester` 取代。檔案還留在 repo，待確認不再需要後刪除，或在檔頭標註停用。
|
||||
（`bmc_monitor.sh` 已於 2026-08-25 重新啟用，並加上 I2C 寫入/讀回圖樣測試。）
|
||||
- **`rm /host/hw-eval/jobs/*` 清不掉子目錄**：Script A 用的是不帶 `-r` 的 `rm`，但 Script C
|
||||
是 `cp -r` 那個目錄，代表裡面可能有子目錄。清不乾淨的話，上一輪的 job log 會被當成這輪的一起
|
||||
複製到 USB。要確認 `bgctl` 的產出結構，必要時改成 `rm -rf .../jobs/*`。
|
||||
- **100G PRBS 尚未接進 A/B/C**：`port_prbs_monitor.sh` 已隨包交付、可手動執行，但三支腳本裡的呼叫
|
||||
都還註解著（bring-up 中）。要啟用時記得 PRBS 期間 link 會顯示 down，`stop` 之後才會回來。
|
||||
- **100G PRBS 已從 A/B/C 移除**：`port_prbs_monitor.sh` 仍隨包交付、仍可手動執行，但 V1.1.9 起
|
||||
三支腳本裡那些註解掉的呼叫已整段刪除（連同 Script C 的 `bmc_monitor_ddr.sh` 區塊）。
|
||||
要接回去得重寫，不是把註解拿掉。啟用時記得 PRBS 期間 link 會顯示 down，`stop` 之後才會回來。
|
||||
- **DSC 擷取預設是關的**：`EN_TX_FIR = 0`，所以出貨設定不會跑 `bcm_dsc_scan.sh`。
|
||||
開啟後 Script A 與 Script C 各掃一次、整輪多約 20 分鐘；只要單邊資料可以在腳本裡改成 `-u 0`。
|
||||
掃描本身是唯讀（`phydiag ... dsc` 不改 SerDes 設定），但**它與 `blanton_ber.sh` /
|
||||
`blanton_traffic_linespeed` / `blanton_tr518.sh` 一樣都在動同一批 port，不要同時跑**。
|
||||
- **Script 5（Reboot Cycle）尚未上機驗證**：`5_Blanton_Script_Reboot_Cycle.ttl` 隨 V1.1.7 交付，
|
||||
但還沒在真 DUT 上跑過一輪完整循環。兩個要現場確認的點：`wait "Booting in blind mode"` 是否
|
||||
真的在每一版開機訊息裡出現（沒出現就會永遠等下去，而且沒有 `timeout` 保護）；以及每輪重跑
|
||||
@@ -883,16 +906,22 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值，
|
||||
LTC2980 PMBus）摸同一批軌，各自都假設自己是唯一的寫入者。目前只靠文件與 help 提醒，
|
||||
沒有任何執行期檢查。
|
||||
- **Script 4 沒有收尾段**：`while 1` 之後就是檔案結尾，中斷時 DUT 停在 `port cd lb=mac` /
|
||||
`l2 learn off` / `test mode nr=yes`，而且 `mlucas-avx2` 還在背景跑。要手動
|
||||
`blanton_tr518.sh stop` + `kill`，否則下一輪任何測試都在被污染的狀態上開始
|
||||
`l2 learn off` / `test mode nr=yes`，而且 CPU 壓力還在跑。要手動
|
||||
`blanton_tr518.sh stop` + `systemctl stop mlucas-amm`（V1.1.8 起它是 systemd unit，
|
||||
關掉 Tera Term 或 `kill $(jobs -p)` 都收不掉），否則下一輪任何測試都在被污染的狀態上開始
|
||||
（Script A 的 `bgctl reset/stop --all` 收得掉 job，但收不掉 bcm 的 loopback 設定）。
|
||||
可考慮加一支對應的收尾腳本，或在檔尾用 `messagebox` 提示要下哪些指令。
|
||||
- **margin 在 soak 期間不再取樣**（V1.1.4）：只剩 Script A 的起始值與 Script C 的結束值。
|
||||
漂移發生在中間就看不到了。若要恢復，比較好的做法是在 B 的迴圈內每 N 輪才掃一次，
|
||||
而不是每輪都掃。
|
||||
- **`blanton_ber.sh` 的 `sleep 30` 與 `BER_INTERVAL` 是兩處要同步改的數字**：Script C 寫死
|
||||
`sendln "sleep 30"`，腳本預設 `BER_INTERVAL=30`。改一邊沒改另一邊，report 會讀到還沒累積完
|
||||
一個 interval 的數字，而且不會有任何警告。
|
||||
- **`blanton_ber.sh` 的 `sleep 30` 與 `BER_INTERVAL` 是兩處要同步改的數字**：Script A（V1.2.1 起）
|
||||
與 Script C 都寫死 `sendln "sleep 30"`，腳本預設 `BER_INTERVAL=30`。改一邊沒改另一邊，report 會
|
||||
讀到還沒累積完一個 interval 的數字，而且不會有任何警告。現在有**三處**要一起改。
|
||||
- **Script A 的 BER `clear` 與第一輪流量之間沒有 settle**：V1.2.1 把 BER 掃描放在流量**之前**，
|
||||
而 PRBS 是把 lane 拉出正常運作、`clear` 才放回去的。Script A 的 `blanton_ber.sh clear` 之後
|
||||
緊接著就是 `blanton_traffic_linespeed ps` / `init`，中間沒有等待；Script C 的 BER 在流量報表
|
||||
之後，沒有這個順序。上機時比對兩份 traffic report —— Script A 有 NA/FAIL 而 Script C 沒有，
|
||||
就是 lane 尚未回穩，在 `clear` 後加一個 `sleep` 即可。**尚未上機驗證。**
|
||||
- **`ce0` 的 ingress mirror 尚未上機驗證**：`mirror port ce0 Mode=Ingress DestPort=ce0` 這條路是
|
||||
推論出來的（鏡像複本不受 egress filter 的 source-port knockout 限制），語法取自 DUT 的
|
||||
`help mirror`，但**還沒證明硬體真的接受 destport == srcport**。驗證方式是隔 10 秒看兩次
|
||||
|
||||
@@ -9,18 +9,23 @@ DUT 端的取數能力由一組 **bash 工具庫** 提供（CB FPGA `pcimem` →
|
||||
|
||||
完整架構見 [ARCHITECTURE.md](ARCHITECTURE.md)。
|
||||
|
||||
**目前狀態（2026-09-06）**：Script A 為 **V1.1.8**（A 集中記錄所有 TTL 的變更）。涵蓋
|
||||
**目前狀態（2026-09-08）**：Script A 為 **V1.2.1**（A 集中記錄所有 TTL 的變更）。涵蓋
|
||||
PCIe AER / DDR EDAC / PMON+TPM / 電壓 margin（9 顆 LTC2980）/ SWB loopback 線速流量 /
|
||||
10G+1G 管理網路 ping / BMC DDR 與 USB / NVMe 健康，壓力層走平台的 `bgctl`。
|
||||
switch unit 數量由 `config.ttl` 的 `SWB_UNIT0` / `SWB_UNIT1` 宣告，風扇轉速由 `FAN_SPEED` 指定
|
||||
（預設 100 = 全速；soak 是熱測試，散熱不該是變因）。
|
||||
測試 job log 收在 DUT 的 `/host/hw-eval/jobs/`，Script C 結束時掛好 USB 再帶時戳複製到 `/mnt/usb/`。
|
||||
100G PRBS（`port_prbs_monitor.sh`）已隨包交付，但 **A/B/C 的呼叫仍註解掉**，還在 bring-up。
|
||||
Script B 的 soak 迴圈每輪印 `bgctl list` + `jobs` + `systemctl is-active mlucas-amm`，並 `pause 60`
|
||||
（V1.0.10 之前完全沒有 pause）。V1.1.8 起 AMD CPU 壓力（`mlucas-avx2`）由 `systemd-run` 掛成
|
||||
100G PRBS（`port_prbs_monitor.sh`）已隨包交付、可手動執行，但 **V1.1.9 起 A/B/C 裡註解掉的呼叫已整段刪除**，
|
||||
要接回去得重寫（`bmc_monitor_ddr.sh` 在 Script C 的註解區塊同時移除）。
|
||||
V1.1.9 新增 **SerDes DSC 擷取**：`bcm_dsc_scan.sh`（DUT 端，`phydiag <port> dsc` 掃全機 ~445 port × 2 unit，
|
||||
約 10 分鐘）由 Script A 與 Script C 各跑一次夾住 soak，`bcm_dsc_parse.sh`（Host 端）把 raw log 轉成
|
||||
`_lane.csv` / `_pm.csv`。**由 `config.ttl` 的 `EN_TX_FIR` 控制，預設 0（關）** —— 開了整輪測試多 ~20 分鐘。
|
||||
Script B 的 soak 迴圈每輪印 `bgctl list` + `jobs` + `systemctl is-active mlucas-amm`，並 `sendln "sleep 60"`
|
||||
（V1.0.10 之前完全沒有間隔；V1.2.0 起 A/B/C 的等待一律改成 DUT 端 `sleep` 而非 macro 端 `pause`）。V1.1.8 起 AMD CPU 壓力（`mlucas-avx2`）由 `systemd-run` 掛成
|
||||
`mlucas-amm` transient unit（`Restart=always`），不再是 shell 的 `&` 背景 job —— 掉線也不會停，
|
||||
Script C 用 `systemctl stop mlucas-amm` 收掉並把 log 複製到隨身碟。
|
||||
V1.1.0 新增全機 SerDes BER 掃描（`blanton_ber.sh`，**Script C 已接**，依 `SWB_UNIT` 分支）、
|
||||
V1.1.0 新增全機 SerDes BER 掃描（`blanton_ber.sh`，依 `SWB_UNIT` 分支）；**V1.2.1 起 Script A 也接了一次**，
|
||||
在第一輪流量之前取基線，與 Script C 流量報表之後的收尾掃描一起夾住 soak（同 DSC 的做法）。另有
|
||||
TR518 負載（`blanton_tr518.sh`，**TTL 尚未接**）、SWB 軌功耗（`TH6_SWB{0,1}_power_readback.sh`），
|
||||
線速流量也納入 100G `ce0`（VLAN 138，靠 ingress mirror 維持循環）。
|
||||
Script A 開頭會先收掉前一輪殘留（`hw-test-session finish` + `bgctl reset/stop --all`），
|
||||
@@ -150,6 +155,22 @@ sleep 30 # 至少等一個 interval 再 rep
|
||||
# -u 0 / -u 1 單邊；-c 1e-9 換門檻；-F 只列失敗；-f <log> 離線重解
|
||||
# ⚠️ 不能跟 blanton_traffic_linespeed / blanton_tr518 同時跑（都會接管同一批 port）
|
||||
|
||||
# ── SerDes DSC 擷取（TX_FIR / RXFFE / DFE / EYE / SNR）──
|
||||
./Blanton_Script/bcm_dsc_scan.sh # unit 0+1 全掃，約 10 分鐘
|
||||
./Blanton_Script/bcm_dsc_scan.sh -u 0 # 只掃一個 unit（時間減半）
|
||||
./Blanton_Script/bcm_dsc_scan.sh -f my.log -F # 自訂檔名 + 覆蓋
|
||||
./Blanton_Script/bcm_dsc_scan.sh -n # dry-run，只列要掃的 port
|
||||
# log: ~/Blanton_Script/log/，掃完自動 cp 到 /host/hw-eval/jobs（-C 可關）
|
||||
# 檔名沒帶 %u 時會自動插 _u0 / _u1，所以兩個 unit 不會互相覆蓋
|
||||
# 結尾固定印 "### DSC_SCAN_DONE rc=<n>"；rc=0 才是全部 port 都拿到完整 dump
|
||||
# ⚠️ 由 TTL 的 EN_TX_FIR 控制，預設 0（關）—— A 與 C 各掃一次，開了整輪多 ~20 分鐘
|
||||
|
||||
# ── DSC raw log → CSV（離線解，Host 或 DUT 都可）──────
|
||||
sh ~/Blanton_Script/bcm_dsc_parse.sh -i blanton_dsc_ScriptA_u0.log -o u0
|
||||
# 產出 u0_lane.csv（每 lane 一列）+ u0_pm.csv（每 pm_id 一列）
|
||||
# 純 sh + awk（mawk 相容），欄位靠括號群組順序抓，SDK 改排版不會壞；
|
||||
# 群組數 != 9 的列標成 UNPARSED 印到 stderr，不會安靜解錯
|
||||
|
||||
# ── TR518 負載 + 量功耗（TTL 尚未接）─────────────────
|
||||
./Blanton_Script/blanton_tr518.sh start # 兩 unit，跑完 settle 120s
|
||||
./Blanton_Script/TH6_SWB0_power_readback.sh # 19 條軌 V×I + TOTAL POWER
|
||||
@@ -261,8 +282,8 @@ Tera Term 連 COM port (115200-8-N-1)
|
||||
唯一線索，**不會報警**。V1.1.8 起出貨預設改為 `RUNTIME=3600`（1 小時），2 天 soak 要填 `172800`
|
||||
- ⚠️ **`utils/kill_all_process.ttl` 只有 `kill $(jobs -p)`，抓不到 systemd unit**：把壓力工作改成
|
||||
`systemd-run` 之後，Script C 一定要補對應的 `systemctl stop <unit>`，否則它會活過 Script C 燒進
|
||||
下一輪，**收工的溫度／功耗全部是在滿載下量的**。V1.1.8 已為 `mlucas-amm` 補上；
|
||||
**Script 4 的 `mlucas-avx2` 仍是 `&` 背景 job**，兩支目前用不同機制，改動時別互相套用
|
||||
下一輪，**收工的溫度／功耗全部是在滿載下量的**。V1.1.8 已為 `mlucas-amm` 補上。
|
||||
Script 4 也改用同一個 unit，但它**沒有收尾段**，所以那行 `systemctl stop` 得由人手動下
|
||||
- ⚠️ **`config.ttl` 少一個變數會讓 macro 當場中止，不是當成 0**：`EN_timestamp`（V1.1.8 新增，
|
||||
餵 Script A `logopen` 的第 5 個參數）、`BMC_USB_RUNTIME` 都是必要項。只更新 `.ttl` 卻沿用舊的
|
||||
`config.ttl`，Script A 會停在 `logopen` 那一行
|
||||
@@ -276,7 +297,8 @@ Tera Term 連 COM port (115200-8-N-1)
|
||||
- ⚠️ **Script 4（thermal/safety）沒有收尾**：`while 1` 之後就是檔尾。中斷後 DUT 停在
|
||||
`port cd lb=mac` / `l2 learn off` / `test mode nr=yes`，`mlucas-avx2` 也還在背景。
|
||||
下一個測試會在被污染的狀態上開始，而且 **`show interfaces status` 看不出來**。
|
||||
收尾：`blanton_tr518.sh stop` + `kill $(jobs -p)`
|
||||
收尾：`blanton_tr518.sh stop` + `kill $(jobs -p)` + **`systemctl stop mlucas-amm`**
|
||||
（V1.1.8 起 CPU 壓力是 systemd unit，`kill $(jobs -p)` 收不掉，少這一行 CPU 會一直滿載）
|
||||
- ⚠️ **Script 4 與 Script B 不能共用同一台 DUT**：兩者都會接管 `port cd` 的 loopback
|
||||
- ⚠️ **`settings/*.conf` 的 `VNOM` 是實測中位數，不是規格值**（2026-08-30 起）。它同時是
|
||||
`margin_status` 偏差 % 的分母、也是 `margin_set` 推算 high/low/OV/UV 的基準，所以改它會
|
||||
@@ -303,9 +325,17 @@ Tera Term 連 COM port (115200-8-N-1)
|
||||
`Failed to execute the diagnostic command` 都照樣回 0），所以 `blanton_traffic_linespeed.sh`
|
||||
是**比對輸出**而非看 exit code。另外 `bcmcmd` 一律要 `</dev/null` ——
|
||||
否則它會吃掉 while 迴圈的 stdin，**只有第一個 VLAN 被設定**（V0.3.1 修過的 bug，很難看出來）。
|
||||
**2026-09-07 `bcm_dsc_scan.sh` 又踩了同一個坑**：port 清單走 stdin，第一次 `bcmcmd` 就把剩下的吃光，
|
||||
445 個 port 只掃了 1 個，而且 marker 與 dump 數量一起變少 → 比對通過、exit 0、log 看起來正常。
|
||||
修法是迴圈改讀 fd 3（`done 3< "$PORTFILE"`）+ `bcmcmd ... < /dev/null`，並加一道
|
||||
「實際迭代筆數 == 清單筆數」的檢查。**任何 `while ... done < file` 裡呼叫 `bcmcmd` 都要當它會讀 stdin。**
|
||||
- ⚠️ **`stress_hhmd.py` / `stress_pcie.py` 已於 2026-08-17 由 KC 移除**（Status 表 ScriptB #5/#7）。
|
||||
Script B 現在是 **8 個背景 job**（1 mlucas + 5 mem + ssd + usb），不是 10 個。
|
||||
I2C／PCIe 的持續讀取壓力目前沒有替代品。
|
||||
- ⚠️ **`pause` 是停 macro，`sleep` 是停 DUT**（V1.2.0 起 A/B/C 一律用後者）：`pause N` 期間 macro 不理會
|
||||
DUT，shell 是閒著的，等於用猜的估上一個指令跑多久；`sendln "sleep N"` + `wait prompt_sonic_root`
|
||||
把等待放到 DUT 上，prompt 回來才繼續，兩邊不會走散，而且這一段會帶時戳進 log。
|
||||
**Script 4 / Script 5 尚未轉換，仍在用 `pause`**；B/C 開頭那個 `pause 1` 也保留（登入前沒有 prompt 可等）
|
||||
- ⚠️ **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。
|
||||
（`-u 0` 已於 `491e807` 移除，A/B/C 現在都跑兩個 switch unit。）
|
||||
- 🔒 **`.sh` / `.conf` 一定要 LF**。CRLF 的 shell script 在 SONiC 上直接掛（`$'\r': command not found`）；
|
||||
@@ -324,6 +354,10 @@ Tera Term 連 COM port (115200-8-N-1)
|
||||
- ⚠️ **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**
|
||||
- ⚠️ **BER 的 `clear` 才是把 lane 放回正常運作的動作**：V1.2.1 起 Script A 在第一輪流量**之前**跑 BER，
|
||||
而 `blanton_ber.sh clear` 與緊接著的 `blanton_traffic_linespeed ps` 之間**沒有任何 settle**。
|
||||
Script C 是流量報表之後才跑 BER，沒有這個順序問題。第一次上機時比對兩邊的 traffic report ——
|
||||
**Script A 有 NA/FAIL 而 Script C 沒有，就是 lane 還沒回穩**，在 `clear` 後補一個 `sleep` 即可
|
||||
- ⚠️ **PRBS 跑起來時 `show interfaces status` 會顯示 DOWN**，那是 link 離開正常運作模式，不是故障。
|
||||
`port_prbs_monitor.sh` 的 `start` 因此刻意不印 port status（避免測試員誤判），只在 `prbs clear` 之後的報表裡印
|
||||
- ⚠️ **`ip -s link` 的欄位順序是 `bytes packets errors ...`**，要 packet 數取的是**第 2 欄**不是第 1 欄
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
## ✨ New features
|
||||
|
||||
**`mlucas` now runs as a systemd unit, so it survives a lost session**
|
||||
* The AMD CPU load is started as `systemd-run --unit=mlucas-amm --property=Type=exec --property=Restart=always --property=RestartSec=2`, instead of being backgrounded with `&` in the login shell.
|
||||
* The AMD CPU load is started as `systemd-run --unit=mlucas-amm --property=Type=exec --property=Restart=always --property=RestartSec=2`, instead of being backgrounded with `&` in the login shell. Script B and the thermal/safety macro (Script 4) both use it.
|
||||
* As a shell job it belonged to that one terminal: close Tera Term, drop the console, reconnect on a different session, and the load was gone — while `jobs` from the new session showed nothing to tell you. A multi-day soak could spend most of its length with an idle CPU and produce thermal numbers that looked fine because nothing was loading the part.
|
||||
* `Restart=always` brings it back if it exits on its own, and the log is appended (`>>`) inside the unit while being truncated (`>`) once before the unit starts, so a restart adds to the run rather than erasing it.
|
||||
* Script B now prints `systemctl is-active mlucas-amm` beside `jobs`, both in the one-shot check and in every pass of the monitor loop. One word — `active` — tells you the CPU is still loaded.
|
||||
@@ -53,7 +53,7 @@ ls ~/hammer/tools/amd/mlucas-avx2 # must already be there - see below
|
||||
* **The three stress durations are deliberately different**: SSD and USB at 1 hour, the BMC USB ping at 2 days. Set each to match the soak you are actually running.
|
||||
* **`--runtime` is the job's overall limit, not a per-pass one.** `qfx5252-stress-*` stops after `RUNTIME` seconds whatever `--passes` says. For a 24 hour soak set `RUNTIME` to `86400`.
|
||||
* **`mlucas-amm` has not been run on hardware yet.** The unit resolves `~` through bash's fallback to the passwd entry, because systemd does not set `HOME` for a system service without `User=`. It should land on `/root/hammer`, the same path the interactive shell uses — confirm it on the bench, or change both paths to an absolute `/root/hammer/...`.
|
||||
* **Script 4 still backgrounds `mlucas-avx2` with `&`.** The two macros use different mechanisms now; do not copy one's teardown into the other.
|
||||
* **Script 4 uses the same unit but has no teardown.** The thermal/safety macro now starts `mlucas-amm` the same way Script B does, and it still ends at `while 1` — so stopping it means `blanton_tr518.sh stop` **and** `systemctl stop mlucas-amm`. Closing Tera Term does not stop the CPU load any more.
|
||||
* **Script 5 (reboot cycle) is still unverified on hardware**, still has no exit condition, and `wait "Booting in blind mode"` still has no `timeout` guard.
|
||||
* **`blanton_multiphase_margin.sh save` is permanent**, and must not be mixed with `margin.sh` — same rails, two access paths, no interlock.
|
||||
* **`READ_VIN` and `READ_IIN` are still not in the ADPM12200 coefficient table.**
|
||||
|
||||
@@ -0,0 +1,76 @@
|
||||
# v1.2.0 — SerDes DSC capture, and the macro now waits on the DUT
|
||||
|
||||
## ✨ New features
|
||||
|
||||
**Full-machine SerDes DSC capture, before and after the soak**
|
||||
* `bcm_dsc_scan.sh` runs `phydiag <port> dsc` through the Broadcom diag shell across the whole port list — one 100G port plus the 200G ranges, about 445 per unit, on both units — and writes the raw log under `Blanton_Script/log/`, then copies it to `/host/hw-eval/jobs/`.
|
||||
* Script A takes a baseline and Script C takes a closing dump, so the pair brackets the stress run and the two are directly comparable.
|
||||
* `-u 0` scans one unit, `-f <name>` names the log (`%u` → `u0`/`u1`, `%t` → timestamp), `-F` overwrites, `-n` dry runs, `-C` skips the copy. A name without `%u` gets `_u0` / `_u1` inserted automatically, so unit 1 can never overwrite unit 0.
|
||||
* Every run ends with `### DSC_SCAN_DONE rc=<n>`. `rc=0` means every port returned a complete dump.
|
||||
* `phydiag ... dsc` is read-only — it does not change any SerDes setting.
|
||||
|
||||
**`bcm_dsc_parse.sh` turns a raw DSC log into two CSVs**
|
||||
* `<prefix>_lane.csv` — one row per lane: TXEQ, RXFFE, DFE, EYE, SNR and the rest.
|
||||
* `<prefix>_pm.csv` — one row per `pm_id`: temperature, PLL, lane count, SNR/EYE statistics.
|
||||
* POSIX `sh` + `awk`, no Python, so it runs on the DUT as happily as on a laptop. Lane rows are read by the order of their bracket groups rather than by fixed column positions, so the SDK re-spacing its output does not break parsing; a row that does not yield 9 groups is reported as `UNPARSED` on stderr instead of being parsed wrongly.
|
||||
|
||||
**`EN_TX_FIR` in `config.ttl` — the DSC scan is off by default**
|
||||
* A full scan is about 10 minutes and both Script A and Script C do one, so the shipped default (`0`) keeps ~20 minutes out of a routine run. Set it to `1` when the SerDes data is what you are after.
|
||||
|
||||
**The macro now waits on the DUT instead of on itself**
|
||||
* Every `pause N` in Scripts A, B and C became `sendln "sleep N"` followed by `wait prompt_sonic_root`.
|
||||
* `pause` stopped the macro for N seconds without touching the DUT — the shell sat idle and the macro was guessing how long the previous command would take. On a loaded DUT the guess ran short and the next command went out before the previous one had finished, putting the whole run a beat ahead of the switch. Now the wait happens on the DUT and the macro resumes when the prompt actually comes back.
|
||||
* It also means the wait appears in the console log with a timestamp, so a round that ran long is visible afterwards.
|
||||
* Timings changed with it: the management-ping sample in Script A is 15 s (was 30), the settle after each traffic `clear` is 5 s (was 15). The traffic run itself stays 15 s and Script B's monitor loop stays 60 s.
|
||||
|
||||
## 🐛 Bug fixes
|
||||
|
||||
**The DSC scan only ever scanned one port — and reported success**
|
||||
* The scan loop read its port list on stdin, and `bcmcmd` reads stdin too, so the first call swallowed the rest of the file and the loop ended after a single port.
|
||||
* Nothing looked wrong. The log held one port marker and one dsc block, the marker-to-dump comparison passed because both numbers shrank together, the exit code was 0, and a 445-port scan simply finished in seconds.
|
||||
* The loop now reads on file descriptor 3 and `bcmcmd` is given `< /dev/null`, and there is a new check that the number of iterations matches the number of ports in the list — a check that cannot be fooled by the loop ending early.
|
||||
|
||||
**Dead call sites removed from Scripts A, B and C**
|
||||
* The commented-out 100G PRBS calls, a duplicated commented 100G port-status block in Script A, and the stale `bmc_monitor_ddr.sh` block in Script C have been deleted. They had been dead since bring-up.
|
||||
* `port_prbs_monitor.sh` still ships and still runs by hand — but re-enabling it means writing the calls again, not un-commenting them.
|
||||
|
||||
## 🔧 Changes
|
||||
|
||||
* **Script C no longer prints the BMC poll log or the mlucas log to the console.** Both files are still copied to `/host/hw-eval/jobs/` and out to the USB stick with everything else; only the master log got shorter.
|
||||
|
||||
## 📦 Downloads
|
||||
|
||||
| File | Contents |
|
||||
|---|---|
|
||||
| `Script_ABC_Blanton_V1.2.0.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 # bcm_dsc_scan.sh is invoked as ./Blanton_Script/... and needs it
|
||||
grep -rlU $'\r' ~/Blanton_Script # expect no output
|
||||
ls ~/hammer/tools/amd/mlucas-avx2 # must already be there
|
||||
```
|
||||
|
||||
## ⚠️ Before you run
|
||||
|
||||
* **Replace `config.ttl` along with the macros.** `EN_TX_FIR` is new, and Tera Term aborts on an undefined variable rather than treating it as 0.
|
||||
* **`bcm_dsc_scan.sh` needs the execute bit.** Script A and Script C invoke it as `./Blanton_Script/bcm_dsc_scan.sh`. Without `chmod +x` it fails with `Permission denied`, the macro walks straight past it, and Script C's four `cp` lines then each report a missing file.
|
||||
* **The DSC scan shares the ports with `blanton_ber.sh`, `blanton_traffic_linespeed` and `blanton_tr518.sh`** — do not run it alongside any of them.
|
||||
* **Script 4 and Script 5 still use `pause`.** Only A, B and C were converted.
|
||||
* **`--runtime` is the job's overall limit, not a per-pass one.** `--passes` does not extend it; for a 24 hour soak set `RUNTIME` to `86400`.
|
||||
* **Script 4 has no teardown**: finish it with `blanton_tr518.sh stop` **and** `systemctl stop mlucas-amm`.
|
||||
* **Script 5 (reboot cycle) is still unverified on hardware**, has no exit condition, and its `wait "Booting in blind mode"` has no `timeout` guard.
|
||||
* **`blanton_multiphase_margin.sh save` is permanent**, and must not be mixed with `margin.sh`.
|
||||
* **`READ_VIN` and `READ_IIN` are still not in the ADPM12200 coefficient table.**
|
||||
* **The BMC USB service log only exists on the USB stick.**
|
||||
* **`FAN_SPEED` is 100.**
|
||||
* **Still unverified from v1.1.0**: the `ce0` ingress mirror, the 120 s settle in `blanton_tr518.sh`, and `test mode nr=no` on stop.
|
||||
|
||||
## 🔗 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
|
||||
* [Blanton_Test_Flow.drawio](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/docs/Blanton_Test_Flow.drawio) — the scripts side by side
|
||||
|
||||
**Full changelog:** [V1.1.8...V1.2.0](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/compare/V1.1.8...V1.2.0)
|
||||
@@ -0,0 +1,49 @@
|
||||
# v1.2.1 — A BER baseline, so the SerDes numbers have something to be compared against
|
||||
|
||||
## ✨ New features
|
||||
|
||||
**Script A now takes a SerDes BER sweep before the first traffic run**
|
||||
* `blanton_ber.sh init → start → sleep 30 → report → stop → clear`, branched on `SWB_UNIT0` / `SWB_UNIT1` exactly like the traffic block beside it.
|
||||
* Script C already ran the closing sweep after its traffic report. With this one at the front, the pair brackets the soak — the same shape as the DSC scans added in v1.2.0, and the same reason: a BER figure on its own says very little, a *change* in it says a lot.
|
||||
* The `sleep 30` matches `blanton_ber.sh`'s `BER_INTERVAL`. Reporting before one full interval has accumulated reads a window that has not finished, and nothing warns you about it.
|
||||
|
||||
## 🐛 Bug fixes
|
||||
|
||||
**The new block's comment described the wrong position**
|
||||
* It was copied out of Script C, which runs BER *after* the traffic report, and the comment came with it and still said "after". In Script A the block runs *before* traffic. The comment now says what the code does and why the ordering is what it is.
|
||||
|
||||
## ⚠️ Before you run
|
||||
|
||||
* **Watch Script A's first traffic report on the first run.** PRBS holds the lanes out of normal operation and `blanton_ber.sh clear` is what releases them — and in Script A nothing settles between that `clear` and the `blanton_traffic_linespeed ps` / `init` that follows. Script C does not have this ordering, so the two reports are a built-in comparison: **if Script A shows NA or FAIL pairs that Script C does not, the lanes had not come back yet**, and a `sleep` after `clear` is the fix. This has not been run on hardware yet.
|
||||
* **`sleep 30` and `BER_INTERVAL` now live in three places** — Script A, Script C, and `blanton_ber.sh` itself. Changing one without the others silently reports a partial interval.
|
||||
* **BER, `blanton_traffic_linespeed` and `blanton_tr518.sh` cannot overlap.** They all take over the same ports. Script A now touches those ports twice before the soak even starts.
|
||||
* **`EN_TX_FIR` is still 0 by default**, so the DSC scans do not run unless you turn them on; a full scan is ~10 min in each of Script A and Script C.
|
||||
* **Replace `config.ttl` along with the macros.** Tera Term aborts the macro on an undefined variable rather than treating it as 0.
|
||||
* **`bcm_dsc_scan.sh` needs the execute bit**: `chmod +x ~/Blanton_Script/*.sh` after copying.
|
||||
* **`--runtime` is the job's overall limit, not a per-pass one.** `--passes` does not extend it.
|
||||
* **Script 4 has no teardown**: finish it with `blanton_tr518.sh stop` **and** `systemctl stop mlucas-amm`.
|
||||
* **Script 5 (reboot cycle) has no exit condition.** A 199-cycle / 60-hour run has now been analysed: PCIe AER stayed at 0, all 218 traffic pairs and all 864 lanes passed every cycle, and the BMC never reset. Two things it did surface — `bmc-first-enroll` does not exist on that BMC build, and NFC returned FAIL on every cycle.
|
||||
* **`blanton_multiphase_margin.sh save` is permanent**, and must not be mixed with `margin.sh`.
|
||||
* **`READ_VIN` and `READ_IIN` are still not in the ADPM12200 coefficient table.**
|
||||
* **The BMC USB service log only exists on the USB stick.**
|
||||
* **`FAN_SPEED` is 100.**
|
||||
* **Still unverified from v1.1.0**: the `ce0` ingress mirror, the 120 s settle in `blanton_tr518.sh`, and `test mode nr=no` on stop.
|
||||
|
||||
## 📦 Downloads
|
||||
|
||||
| File | Contents |
|
||||
|---|---|
|
||||
| `Script_ABC_Blanton_V1.2.1.zip` | The full Tera Term working directory, including `Blanton_Script/` to copy onto the DUT |
|
||||
|
||||
```bash
|
||||
chmod +x ~/Blanton_Script/*.sh
|
||||
grep -rlU $'\r' ~/Blanton_Script # expect no output
|
||||
ls ~/hammer/tools/amd/mlucas-avx2 # must already be there
|
||||
```
|
||||
|
||||
## 🔗 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:** [V1.2.0...V1.2.1](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/compare/V1.2.0...V1.2.1)
|
||||
@@ -1,7 +1,7 @@
|
||||
; =============================================================================
|
||||
; Script A for Blanton
|
||||
; Version : V1.1.8
|
||||
; Date : 2026-09-06
|
||||
; Version : V1.2.2
|
||||
; Date : 2026-09-09
|
||||
; Author : ETWen
|
||||
; =============================================================================
|
||||
; Version History:
|
||||
@@ -387,6 +387,17 @@
|
||||
; !! ScriptB and ScriptC change together. Whoever moves a
|
||||
; stress job to systemd owns the matching stop in
|
||||
; ScriptC
|
||||
; Script4 Use the same mlucas-amm systemd unit as ScriptB
|
||||
; The thermal / safety macro started mlucas the same way
|
||||
; ScriptB used to, with '&', so it had the same failure:
|
||||
; the load quietly ended when the console went away, in the
|
||||
; one test where a long steady full load is the whole point
|
||||
; 'systemctl is-active mlucas-amm' joins 'bgctl list' and
|
||||
; 'jobs' in the monitor loop
|
||||
; !! Script4 still has no teardown section, so the matching
|
||||
; stop is manual: blanton_tr518.sh stop AND systemctl
|
||||
; stop mlucas-amm. Closing Tera Term no longer stops the
|
||||
; CPU load, and 'kill $(jobs -p)' never reached a unit
|
||||
; config.ttl Add EN_timestamp and BMC_USB_RUNTIME, raise stress runtimes
|
||||
; EN_timestamp = 1 feeds ScriptA's logopen; BMC_USB_RUNTIME
|
||||
; = 172800 feeds ScriptB's ping unit
|
||||
@@ -408,6 +419,221 @@
|
||||
; happened to have the binaries locally would have shipped
|
||||
; a 100 MB zip while a clone shipped 200 KB. The bundle is
|
||||
; now the same either way
|
||||
; V1.1.9 2026-09-07
|
||||
; Blanton_Script/bcm_dsc_scan.sh Created V1.2.0 - batch SerDes DSC dump
|
||||
; Runs bcmcmd -n <unit> -c "dsh -c 'phydiag <port> dsc'"
|
||||
; over the whole port list (1 x 100G + 445 x 200G ranges),
|
||||
; both units, and leaves the raw log in <script_dir>/log
|
||||
; before copying it to /host/hw-eval/jobs
|
||||
; -f names the log (%u -> u0/u1, %t -> timestamp), -F
|
||||
; overwrites, -u picks one unit, -n dry runs, -C skips the
|
||||
; copy. -f takes a filename only; the directory comes from
|
||||
; -o
|
||||
; bcmcmd exits 0 even when the diag shell rejects a
|
||||
; command, so success is judged by counting 'SERDES DISPLAY
|
||||
; DIAG DATA END' markers, not by the exit code - the same
|
||||
; trap blanton_traffic_linespeed.sh hit
|
||||
; Paths come from $0, not $HOME, because Script A runs it
|
||||
; after sudo -i and a literal ~ would depend on the
|
||||
; environment. Ends with '### DSC_SCAN_DONE rc=<n>' for a
|
||||
; TTL wait to key on
|
||||
; Non-tty output is one line per port instead of a progress
|
||||
; bar, so it does not flood the Tera Term log
|
||||
; !! phydiag dsc is read-only and does not change any
|
||||
; SerDes setting, but a full scan is ~10 min per run.
|
||||
; ScriptA and ScriptC each do one, so the test is ~20
|
||||
; min longer than before. Do not set DELAY to 0
|
||||
; Blanton_Script/bcm_dsc_parse.sh Created V1.0.0 - offline DSC log to CSV
|
||||
; Host side. -i <raw log> -o <prefix> produces
|
||||
; <prefix>_lane.csv (one row per lane: TXEQ / RXFFE / DFE /
|
||||
; EYE / SNR) and <prefix>_pm.csv (one row per pm_id:
|
||||
; temperature / PLL / lane count / SNR-EYE stats)
|
||||
; POSIX sh + awk, mawk compatible, no Python. Lane rows are
|
||||
; read by the order of their bracket groups rather than
|
||||
; fixed columns, so re-spacing by the SDK does not break
|
||||
; it; a row whose group count is not 9 is marked UNPARSED
|
||||
; on stderr instead of being parsed wrongly
|
||||
; SD / LCK sticky '*' flags are kept as separate columns
|
||||
; and not interpreted; a BER field of '!chk_en' means the
|
||||
; checker was off and is passed through unchanged
|
||||
; ScriptA Collect the SerDes DSC baseline before 'show uptime'
|
||||
; ./Blanton_Script/bcm_dsc_scan.sh -f
|
||||
; blanton_dsc_ScriptA.log -F
|
||||
; The name has no %u, so the script inserts _u0 / _u1
|
||||
; itself and unit 1 cannot overwrite unit 0 - that is where
|
||||
; the file names ScriptC copies come from
|
||||
; ScriptA / ScriptB / ScriptC Remove the commented-out 100G PRBS blocks
|
||||
; The port_prbs_monitor.sh calls had been commented out in
|
||||
; all three since bring-up, together with a second copy of
|
||||
; the 100G port status block in ScriptA and the stale
|
||||
; bmc_monitor_ddr.sh block in ScriptC
|
||||
; port_prbs_monitor.sh still ships and still runs by hand;
|
||||
; only the dead call sites are gone
|
||||
; ScriptC Collect the closing DSC dump and carry the four logs out
|
||||
; ./Blanton_Script/bcm_dsc_scan.sh -f
|
||||
; blanton_dsc_ScriptC.log -F, then cp of
|
||||
; blanton_dsc_Script{A,C}_u{0,1}.log into
|
||||
; /host/hw-eval/jobs/
|
||||
; The scan already copies its own output there; these four
|
||||
; are a second pass so a failed copy inside the scan still
|
||||
; leaves the data on the USB stick
|
||||
; Blanton_Script Both new scripts need the execute bit on the DUT
|
||||
; !! git records them 100644 like every other .sh here, and
|
||||
; ScriptA / ScriptC invoke them as
|
||||
; ./Blanton_Script/bcm_dsc_scan.sh, so they join
|
||||
; bmc_monitor.sh and friends in the chmod +x line after
|
||||
; deployment. Without it both scans fail with Permission
|
||||
; denied and the macro walks straight past it
|
||||
; V1.2.0 2026-09-07
|
||||
; Blanton_Script/bcm_dsc_scan.sh v1.3.0 bcmcmd was eating the port list
|
||||
; The scan loop read the port file on stdin, and bcmcmd
|
||||
; reads stdin too, so the first call swallowed the rest of
|
||||
; the file and the loop ended after ONE port
|
||||
; Nothing looked wrong: the log held one PORT marker and
|
||||
; one dsc block, markers == dumps, exit code 0. A 445 port
|
||||
; scan finished in seconds and reported success
|
||||
; Fixed by reading the loop on fd 3 (done 3< "$PORTFILE")
|
||||
; and giving bcmcmd < /dev/null
|
||||
; Added a check that the iteration count equals the port
|
||||
; list count. The marker / dump comparison cannot catch a
|
||||
; loop that ends early, because both numbers shrink
|
||||
; together; the Saved: line now reports dumps out of TOTAL,
|
||||
; not out of markers
|
||||
; !! this is the same bcmcmd trap
|
||||
; blanton_traffic_linespeed.sh hit at v0.3.1, where only
|
||||
; the first VLAN was configured. Every while ... done <
|
||||
; file loop that calls bcmcmd needs < /dev/null - assume
|
||||
; it will read stdin unless proven otherwise
|
||||
; ScriptA / ScriptB / ScriptC Wait on the DUT with 'sleep', not on the macro with 'pause'
|
||||
; pause N stops the macro for N seconds without touching
|
||||
; the DUT: the shell sits idle and the macro is guessing
|
||||
; how long the last command took. sendln "sleep N" + wait
|
||||
; prompt_sonic_root moves the wait onto the DUT, so the
|
||||
; macro resumes when the prompt actually comes back and the
|
||||
; two cannot drift apart
|
||||
; It also lands in the console log with a timestamp, so a
|
||||
; round that ran long is visible afterwards instead of
|
||||
; invisible
|
||||
; Durations changed with it: ScriptA mgmt ping 30 -> 15 s;
|
||||
; the settle after every traffic 'clear' 15 -> 5 s; the
|
||||
; traffic run itself stays 15 s; ScriptB's monitor loop
|
||||
; stays 60 s
|
||||
; !! Script4 and Script5 were NOT converted and still use
|
||||
; pause. The 'pause 1' at the top of ScriptB / ScriptC
|
||||
; also stays - it only spaces the log header and runs
|
||||
; before there is a prompt to wait for
|
||||
; config.ttl Add EN_TX_FIR to gate the SerDes DSC scan
|
||||
; EN_TX_FIR = 1 enables bcm_dsc_scan.sh in ScriptA and
|
||||
; ScriptC, and the four cp lines that carry
|
||||
; blanton_dsc_Script{A,C}_u{0,1}.log to /host/hw-eval/jobs.
|
||||
; Default is 0
|
||||
; A full scan is ~10 min and both scripts do one, so
|
||||
; leaving it off keeps ~20 min out of a routine run. Turn
|
||||
; it on when the SerDes data is what you are after
|
||||
; ScriptC Stop printing the BMC poll and mlucas logs to the console
|
||||
; cat bmc_poll.log and cat mlucas_amm_log are commented
|
||||
; out. Both files are still copied to /host/hw-eval/jobs
|
||||
; and out to the USB stick with everything else, so no data
|
||||
; is lost - the master log is just shorter
|
||||
; V1.2.1 2026-09-08
|
||||
; ScriptA Add a BER baseline sweep before the traffic run
|
||||
; blanton_ber.sh init / start / sleep 30 / report / stop /
|
||||
; clear, branched on SWB_UNIT0 and SWB_UNIT1 the same way
|
||||
; the traffic block is. ScriptC already took the closing
|
||||
; sweep after its traffic report, so the two now bracket
|
||||
; the soak the way the DSC scans do
|
||||
; sleep 30 is not arbitrary: it is blanton_ber.sh's
|
||||
; BER_INTERVAL. 'report' before one full interval has
|
||||
; accumulated reads a window that has not finished
|
||||
; The block was copied from ScriptC, which runs it AFTER
|
||||
; traffic, and its comment said so. In ScriptA it runs
|
||||
; BEFORE traffic, so the comment was rewritten to match
|
||||
; where the code actually is
|
||||
; !! nothing settles between 'blanton_ber.sh clear' and
|
||||
; 'blanton_traffic_linespeed ps' that follows it. PRBS
|
||||
; holds the lanes out of normal operation and 'clear' is
|
||||
; what releases them, so the first traffic run of
|
||||
; ScriptA now starts on lanes that have just been
|
||||
; released. ScriptC does not have this ordering. Watch
|
||||
; ScriptA's first traffic report for NA or FAIL pairs
|
||||
; that ScriptC's does not show - if they appear, a sleep
|
||||
; after 'clear' is the fix
|
||||
; !! ScriptA now runs BER twice as far as the switch is
|
||||
; concerned: once here and once inside ScriptC. Neither
|
||||
; can overlap blanton_traffic_linespeed or
|
||||
; blanton_tr518.sh - they all take over the same ports
|
||||
; V1.2.2 2026-09-09
|
||||
; 5_.._Boot_Cycle.ttl Renamed from 5_Blanton_Script_Reboot_Cycle.ttl
|
||||
; It does warm and cold now, so 'Reboot' was too narrow.
|
||||
; Same macro otherwise - git records it as a rename
|
||||
; 5_.._Boot_Cycle.ttl Warm or cold boot, chosen by EN_Cold_Warm_boot
|
||||
; 1 = 'reboot' (warm, what the macro always did). 2 = cold,
|
||||
; by writing the CB FPGA: pcimem
|
||||
; /sys/bus/pci/devices/0000:05:00.0/resource0 0x480 w
|
||||
; 0xD0000. 0 = neither
|
||||
; !! EN_Cold_Warm_boot = 0 hangs the macro. Neither branch
|
||||
; runs, so nothing reboots, and the 'wait "Booting in
|
||||
; blind mode"' underneath has no timeout - cycle 1
|
||||
; finishes and the macro then waits for a boot that will
|
||||
; never come. 0 is the value for the A/B/C flow, where
|
||||
; this macro is not used at all; do not run ScriptBoot
|
||||
; with it
|
||||
; !! 0x480 is ICB_CTRL_REG in
|
||||
; docs/Blantons_FPGA_Registers.md, and that table
|
||||
; carries no bit definitions for it. 0xD0000 is not
|
||||
; written down anywhere in this repo either. Whoever
|
||||
; knows what those bits do should put it in the register
|
||||
; doc before someone changes the value
|
||||
; !! the BDF 0000:05:00.0 is hard-coded here, while
|
||||
; blanton_fpga_pcimem.sh auto-detects the CB FPGA
|
||||
; precisely because it moves per unit (see the V1.0.x
|
||||
; notes and Key Constraints #4). On a DUT where the FPGA
|
||||
; is not at 05:00.0 this becomes a raw 32-bit write to
|
||||
; an unknown register on some other device. Verify the
|
||||
; BDF on every unit before running the cold path
|
||||
; !! NOT verified on hardware. The warm path has 199 cycles
|
||||
; behind it; the cold path has none
|
||||
; 5_.._Boot_Cycle.ttl Truncate the two stress logs before each run
|
||||
; rm -rf /host/hw-eval/jobs/qfx5252-stress-ssd.log and the
|
||||
; usb one, added ahead of each qfx5252-stress-* call
|
||||
; qfx5252-stress-* APPENDS to its --log file and the macro
|
||||
; cats the whole thing afterwards, so every cycle printed
|
||||
; back everything the ones before it had written
|
||||
; Measured on the 199 cycle log from 2026-09-04: cycle 1
|
||||
; printed 289 lines, cycle 199 printed 36,555. At ~6.2 ms a
|
||||
; line - which is what a 115200 baud console costs - that
|
||||
; is +212 s of the +214 s the cycle grew over the run. The
|
||||
; stress itself is fixed at --runtime 30, and the other
|
||||
; eleven segments between check points drifted by less than
|
||||
; 1.5 s each. The DUT was never getting slower; the test
|
||||
; was reading its own history aloud once per cycle
|
||||
; 5_.._Boot_Cycle.ttl Name the log file and the banner after the kind of boot
|
||||
; EN_Cold_Warm_boot = 1 gives
|
||||
; Logs\Blanton_Reboot_Cycle_<ts>.log and a 'Reboot Cycle :
|
||||
; N' banner; = 2 gives Blanton_Power_Cycle_<ts>.log and
|
||||
; 'Power Cycle : N'. Three sites now branch on the flag:
|
||||
; the log name, the banner and the boot itself
|
||||
; !! with 0 there is no longer a logopen either, so the run
|
||||
; that already hangs at wait "Booting in blind mode" now
|
||||
; also leaves no log to show where it stopped. EN_log =
|
||||
; 1 no longer guarantees a log in this macro -
|
||||
; EN_Cold_Warm_boot has to be 1 or 2 as well
|
||||
; !! anything that parses these logs has to accept BOTH
|
||||
; banners. The cycle banner is the record separator the
|
||||
; check-point and per-segment timing reports are built
|
||||
; on, so a parser that only greps 'Reboot Cycle :' finds
|
||||
; zero cycles in a power-cycle log and silently reports
|
||||
; nothing at all
|
||||
; The logopen timestamp flag is still a literal 1 here
|
||||
; rather than EN_timestamp the way ScriptA does it. Leaving
|
||||
; it on is the right call - the per-segment timing analysis
|
||||
; is derived from those timestamps and there is nothing
|
||||
; else to recover them from - but it does mean this macro
|
||||
; ignores EN_timestamp = 0
|
||||
; config.ttl Add EN_Cold_Warm_boot
|
||||
; 0 = normal test (A/B/C), 1 = reboot cycle, 2 = power
|
||||
; cycle. Default 0 so that opening the shared config cannot
|
||||
; reboot anyone's DUT by accident
|
||||
; =============================================================================
|
||||
include "config.ttl"
|
||||
|
||||
@@ -573,7 +799,8 @@ include "utils/show_dmesg.ttl"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/mgmt_ping_monitor.sh start"
|
||||
wait prompt_sonic_root
|
||||
pause 30
|
||||
sendln "sleep 15"
|
||||
wait prompt_sonic_root
|
||||
sendln "~/Blanton_Script/mgmt_ping_monitor.sh stop"
|
||||
wait prompt_sonic_root
|
||||
sendln "cat ~/Blanton_Script/log/mgmt_ping.log"
|
||||
@@ -608,36 +835,6 @@ sendln "config save -y"
|
||||
wait prompt_sonic_root
|
||||
sendln "show interfaces status Ethernet513,Ethernet514"
|
||||
|
||||
;=============================================================================================================
|
||||
; ========== 100G PRBS ==========
|
||||
;wait prompt_sonic_root
|
||||
;sendln "~/Blanton_Script/port_prbs_monitor.sh start"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "sleep 10"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "~/Blanton_Script/port_prbs_monitor.sh status"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "~/Blanton_Script/port_prbs_monitor.sh stop"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "~/Blanton_Script/port_prbs_monitor.sh report"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "~/Blanton_Script/port_prbs_monitor.sh clear"
|
||||
|
||||
; ========== 100G Port Status ==========
|
||||
;wait prompt_sonic_root
|
||||
;sendln "sudo sfputil lpmode off Ethernet513"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "sudo sfputil lpmode off Ethernet514"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "config interface -n asic0 startup Ethernet513"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "config interface -n asic1 startup Ethernet514"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "config save -y"
|
||||
|
||||
;wait prompt_sonic_root
|
||||
;sendln "show interfaces status Ethernet513,Ethernet514"
|
||||
;=============================================================================================================
|
||||
|
||||
; ========== First Traffic Test ==========
|
||||
; Silent MAC
|
||||
@@ -646,6 +843,56 @@ sendln "config feature state lldp disabled"
|
||||
wait prompt_sonic_root
|
||||
sendln "config save -y"
|
||||
|
||||
; ========== BER ==========
|
||||
; Baseline sweep, taken BEFORE the traffic run - ScriptC takes the closing
|
||||
; one after its traffic report, so the pair brackets the soak.
|
||||
; PRBS takes the SerDes out of normal operation; 'clear' is what puts the
|
||||
; lanes back, so it has to run before the traffic block below.
|
||||
; sleep 30 matches blanton_ber.sh BER_INTERVAL - reporting earlier reads an
|
||||
; interval that has not finished accumulating.
|
||||
if SWB_UNIT0 = 1 && SWB_UNIT1 = 1 then
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh init"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh start"
|
||||
wait prompt_sonic_root
|
||||
sendln "sleep 30"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh report"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh stop"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh clear"
|
||||
elseif SWB_UNIT0 = 1 && SWB_UNIT1 = 0 then
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh init -u 0"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh start -u 0"
|
||||
wait prompt_sonic_root
|
||||
sendln "sleep 30"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh report -u 0"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh stop -u 0"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh clear -u 0"
|
||||
elseif SWB_UNIT0 = 0 && SWB_UNIT1 = 1 then
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh init -u 1"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh start -u 1"
|
||||
wait prompt_sonic_root
|
||||
sendln "sleep 30"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh report -u 1"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh stop -u 1"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/blanton_ber.sh clear -u 1"
|
||||
else
|
||||
|
||||
endif
|
||||
|
||||
if SWB_UNIT0 = 1 && SWB_UNIT1 = 1 then
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed ps"
|
||||
@@ -654,12 +901,14 @@ if SWB_UNIT0 = 1 && SWB_UNIT1 = 1 then
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed clear"
|
||||
wait prompt_sonic_root
|
||||
pause 15
|
||||
sendln "sleep 5"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed show"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed start"
|
||||
wait prompt_sonic_root
|
||||
pause 15
|
||||
sendln "sleep 15"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed stop"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed report"
|
||||
@@ -671,12 +920,14 @@ elseif SWB_UNIT0 = 1 && SWB_UNIT1 = 0 then
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed clear -u 0"
|
||||
wait prompt_sonic_root
|
||||
pause 15
|
||||
sendln "sleep 5"
|
||||
wait prompt_sonic_root
|
||||
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 "sleep 15"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed stop -u 0"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed report -u 0"
|
||||
@@ -688,12 +939,14 @@ elseif SWB_UNIT0 = 0 && SWB_UNIT1 = 1 then
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed clear -u 1"
|
||||
wait prompt_sonic_root
|
||||
pause 15
|
||||
sendln "sleep 5"
|
||||
wait prompt_sonic_root
|
||||
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 "sleep 15"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed stop -u 1"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed report -u 1"
|
||||
@@ -701,6 +954,12 @@ else
|
||||
|
||||
endif
|
||||
|
||||
if EN_TX_FIR = 1 then
|
||||
; ========== Collect bcm dsc data ==========
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/bcm_dsc_scan.sh -f blanton_dsc_ScriptA.log -F"
|
||||
endif
|
||||
|
||||
; ========== Show Power on uptime ==========
|
||||
wait prompt_sonic_root
|
||||
sendln "show uptime"
|
||||
|
||||
@@ -109,7 +109,8 @@ timeout = 0
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/mgmt_ping_monitor.sh start"
|
||||
wait prompt_sonic_root
|
||||
pause 3
|
||||
sendln "sleep 3"
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/mgmt_ping_monitor.sh status"
|
||||
|
||||
; ========== NFC Test ==========
|
||||
@@ -123,12 +124,6 @@ sendln "~/Blanton_Script/nfc_polling.sh status"
|
||||
wait prompt_sonic_root
|
||||
sendln "show interfaces status Ethernet513,Ethernet514"
|
||||
|
||||
;=============================================================================================================
|
||||
; ========== 100G PRBS ==========
|
||||
;wait prompt_sonic_root
|
||||
;sendln "~/Blanton_Script/port_prbs_monitor.sh start"
|
||||
;=============================================================================================================
|
||||
|
||||
|
||||
; ========== Traffic START ==========
|
||||
; Silent MAC
|
||||
@@ -145,7 +140,8 @@ if SWB_UNIT0 = 1 && SWB_UNIT1 = 1 then
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed clear"
|
||||
wait prompt_sonic_root
|
||||
pause 15
|
||||
sendln "sleep 5"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed show"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed start"
|
||||
@@ -157,7 +153,8 @@ elseif SWB_UNIT0 = 1 && SWB_UNIT1 = 0 then
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed clear -u 0"
|
||||
wait prompt_sonic_root
|
||||
pause 15
|
||||
sendln "sleep 5"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed show -u 0"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed start -u 0"
|
||||
@@ -169,7 +166,8 @@ elseif SWB_UNIT0 = 0 && SWB_UNIT1 = 1 then
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed clear -u 1"
|
||||
wait prompt_sonic_root
|
||||
pause 15
|
||||
sendln "sleep 5"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed show -u 1"
|
||||
wait prompt_sonic_root
|
||||
sendln "blanton_traffic_linespeed start -u 1"
|
||||
@@ -179,7 +177,7 @@ endif
|
||||
|
||||
|
||||
|
||||
; ========== Monitor loop: platform data + background jobs (pause 60s per round) ==========
|
||||
; ========== Monitor loop: platform data + background jobs (sleep 60s per round) ==========
|
||||
while 1
|
||||
include "utils/setup_pmon.ttl"
|
||||
wait prompt_sonic_root
|
||||
@@ -188,5 +186,6 @@ while 1
|
||||
sendln "jobs"
|
||||
wait prompt_sonic_root
|
||||
sendln "systemctl is-active mlucas-amm"
|
||||
pause 60
|
||||
wait prompt_sonic_root
|
||||
sendln "sleep 60"
|
||||
endwhile
|
||||
|
||||
@@ -33,23 +33,6 @@ sendln "~/Blanton_Script/mgmt_ping_monitor.sh stop"
|
||||
wait prompt_sonic_root
|
||||
sendln "~/Blanton_Script/nfc_polling.sh stop"
|
||||
|
||||
;=============================================================================================================
|
||||
; 100G PRBS STOP
|
||||
;wait prompt_sonic_root
|
||||
;sendln "~/Blanton_Script/port_prbs_monitor.sh stop"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "sudo sfputil lpmode off Ethernet513"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "sudo sfputil lpmode off Ethernet514"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "config interface -n asic0 startup Ethernet513"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "config interface -n asic1 startup Ethernet514"
|
||||
;=============================================================================================================
|
||||
|
||||
|
||||
|
||||
|
||||
; ========== TAKE DATA ==========
|
||||
include "utils/setup_pmon.ttl"
|
||||
include "utils/show_dmesg.ttl"
|
||||
@@ -66,21 +49,12 @@ include "utils/show_pcie_error_reg_SSD.ttl"
|
||||
wait prompt_sonic_root
|
||||
sendln "/usr/sbin/ras-mc-ctl --summary"
|
||||
|
||||
; ========== BMC DDR TAKE DATA ==========
|
||||
;wait prompt_sonic_root
|
||||
;sendln "./Blanton_Script/bmc_monitor_ddr.sh stop"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "./Blanton_Script/bmc_monitor.sh stop"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "cat ./Blanton_Script/log/bmc_poll.log"
|
||||
;wait prompt_sonic_root
|
||||
;sendln "cat ./Blanton_Script/log/bmc_ddr.log"
|
||||
|
||||
; ========== BMC Monitor TAKE DATA ==========
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/bmc_monitor.sh stop"
|
||||
wait prompt_sonic_root
|
||||
sendln "cat ./Blanton_Script/log/bmc_poll.log"
|
||||
; wait prompt_sonic_root
|
||||
; sendln "cat ./Blanton_Script/log/bmc_poll.log"
|
||||
|
||||
; ========== BMC USB Test result ==========
|
||||
wait prompt_sonic_root
|
||||
@@ -90,8 +64,8 @@ sendln "journalctl -u qfx5252-bmc-usb-net-test.service --no-pager -o short-iso >
|
||||
|
||||
|
||||
; ========== CHECK Stress results ==========
|
||||
wait prompt_sonic_root
|
||||
sendln "cat ~/hammer/tools/amd/mlucas_amm_log"
|
||||
; wait prompt_sonic_root
|
||||
; sendln "cat ~/hammer/tools/amd/mlucas_amm_log"
|
||||
wait prompt_sonic_root
|
||||
sendln "cat /host/hw-eval/jobs/qfx5252-stress-ssd.log"
|
||||
wait prompt_sonic_root
|
||||
@@ -108,10 +82,6 @@ sendln "~/Blanton_Script/nfc_polling.sh report"
|
||||
; ========== 100G Port ==========
|
||||
wait prompt_sonic_root
|
||||
sendln "show interfaces status Ethernet513,Ethernet514"
|
||||
;=============================================================================================================
|
||||
;wait prompt_sonic_root
|
||||
;sendln "cat ~/Blanton_Script/log/port_prbs.log "
|
||||
;=============================================================================================================
|
||||
|
||||
; ========== CHECK Traffic counters ==========
|
||||
if SWB_UNIT0 = 1 && SWB_UNIT1 = 1 then
|
||||
@@ -180,6 +150,11 @@ else
|
||||
|
||||
endif
|
||||
|
||||
if EN_TX_FIR = 1 then
|
||||
; ========== Collect bcm dsc data ==========
|
||||
wait prompt_sonic_root
|
||||
sendln "./Blanton_Script/bcm_dsc_scan.sh -f blanton_dsc_ScriptC.log -F"
|
||||
endif
|
||||
|
||||
; ========== NVME Err Info ==========
|
||||
wait prompt_sonic_root
|
||||
@@ -226,6 +201,16 @@ sendln "cp ./Blanton_Script/log/mgmt_ping.log /host/hw-eval/jobs/"
|
||||
wait prompt_sonic_root
|
||||
sendln "cp ./Blanton_Script/log/nfc_poll.log /host/hw-eval/jobs/"
|
||||
|
||||
if EN_TX_FIR = 1 then
|
||||
wait prompt_sonic_root
|
||||
sendln "cp ./Blanton_Script/log/blanton_dsc_ScriptA_u0.log /host/hw-eval/jobs/"
|
||||
wait prompt_sonic_root
|
||||
sendln "cp ./Blanton_Script/log/blanton_dsc_ScriptA_u1.log /host/hw-eval/jobs/"
|
||||
wait prompt_sonic_root
|
||||
sendln "cp ./Blanton_Script/log/blanton_dsc_ScriptC_u0.log /host/hw-eval/jobs/"
|
||||
wait prompt_sonic_root
|
||||
sendln "cp ./Blanton_Script/log/blanton_dsc_ScriptC_u1.log /host/hw-eval/jobs/"
|
||||
endif
|
||||
|
||||
wait prompt_sonic_root
|
||||
getdate ts_date "%Y%m%d"
|
||||
|
||||
@@ -129,11 +129,15 @@ include "utils/setup_pmon.ttl"
|
||||
include "utils/show_dmesg.ttl"
|
||||
|
||||
; ========== Full Load ==========
|
||||
; AMD CPU STRESS TEST
|
||||
; AMD CPU STRESS TEST
|
||||
; Clear the log file first
|
||||
wait prompt_sonic_root
|
||||
sendln "> ~/hammer/tools/amd/mlucas_amm_log"
|
||||
wait prompt_sonic_root
|
||||
sendln 'chmod +x ~/hammer/tools/amd/mlucas-avx2'
|
||||
wait prompt_sonic_root
|
||||
sendln "~/hammer/tools/amd/mlucas-avx2 -s l -cpu 0:15 > ~/hammer/tools/amd/mlucas_amm_log 2>&1 &"
|
||||
;sendln "~/hammer/tools/amd/mlucas-avx2 -s l -cpu 0:15 > ~/hammer/tools/amd/mlucas_amm_log 2>&1 &"
|
||||
sendln "systemd-run --unit=mlucas-amm --property=Type=exec --property=Restart=always --property=RestartSec=2 /bin/bash -c '~/hammer/tools/amd/mlucas-avx2 -s l -cpu 0:15 >> ~/hammer/tools/amd/mlucas_amm_log 2>&1'"
|
||||
|
||||
; TR518 TEST
|
||||
wait prompt_sonic_root
|
||||
@@ -154,5 +158,7 @@ while 1
|
||||
sendln "bgctl list"
|
||||
wait prompt_sonic_root
|
||||
sendln "jobs"
|
||||
wait prompt_sonic_root
|
||||
sendln "systemctl is-active mlucas-amm"
|
||||
pause 60
|
||||
endwhile
|
||||
|
||||
+31
-7
@@ -8,8 +8,14 @@ gettime str_starttime "%Y%m%d-%H%M%S"
|
||||
getdir mdir
|
||||
|
||||
if EN_log = 1 then
|
||||
sprintf2 filename '%s\Logs\%s_%s_%s.log' mdir project_name "Reboot_Cycle" str_starttime
|
||||
logopen filename 0 1 1 1
|
||||
if EN_Cold_Warm_boot = 1 then
|
||||
sprintf2 filename '%s\Logs\%s_%s_%s.log' mdir project_name "Reboot_Cycle" str_starttime
|
||||
logopen filename 0 1 1 1
|
||||
elseif EN_Cold_Warm_boot = 2 then
|
||||
sprintf2 filename '%s\Logs\%s_%s_%s.log' mdir project_name "Power_Cycle" str_starttime
|
||||
logopen filename 0 1 1 1
|
||||
else
|
||||
endif
|
||||
endif
|
||||
|
||||
cnt_cycle = 0
|
||||
@@ -26,9 +32,16 @@ while 1
|
||||
wait prompt_sonic_root
|
||||
sendln "sleep 10"
|
||||
|
||||
wait prompt_sonic_root
|
||||
sprintf2 strTitle "echo -e '\033[1;32mReboot Cycle : %d \033[0m'" cnt_cycle
|
||||
sendln strTitle
|
||||
if EN_Cold_Warm_boot = 1 then
|
||||
wait prompt_sonic_root
|
||||
sprintf2 strTitle "echo -e '\033[1;32mReboot Cycle : %d \033[0m'" cnt_cycle
|
||||
sendln strTitle
|
||||
elseif EN_Cold_Warm_boot = 2 then
|
||||
wait prompt_sonic_root
|
||||
sprintf2 strTitle "echo -e '\033[1;32mPower Cycle : %d \033[0m'" cnt_cycle
|
||||
sendln strTitle
|
||||
else
|
||||
endif
|
||||
|
||||
; ========== Pre Setting ==========
|
||||
; Make log directory
|
||||
@@ -172,6 +185,8 @@ while 1
|
||||
sprintf2 strCKPt5 "echo -e '\033[36mCheck Pt5 : SSD Test\033[0m'"
|
||||
sendln strCKPt5
|
||||
|
||||
wait prompt_sonic_root
|
||||
sendln "rm -rf /host/hw-eval/jobs/qfx5252-stress-ssd.log"
|
||||
wait prompt_sonic_root
|
||||
sendln "qfx5252-stress-ssd 1G --runtime 30 --passes 2 --write --force --log /host/hw-eval/jobs/qfx5252-stress-ssd.log"
|
||||
wait prompt_sonic_root
|
||||
@@ -189,6 +204,8 @@ while 1
|
||||
waitregex '<<DEV=([^>]*)>>'
|
||||
usb_dev = groupmatchstr1
|
||||
|
||||
wait prompt_sonic_root
|
||||
sendln "rm -rf /host/hw-eval/jobs/qfx5252-stress-usb.log"
|
||||
wait prompt_sonic_root
|
||||
sprintf2 cmd "qfx5252-stress-usb %s 256M --runtime 30 --passes 2 --write --log /host/hw-eval/jobs/qfx5252-stress-usb.log" usb_dev
|
||||
sendln cmd
|
||||
@@ -412,8 +429,15 @@ while 1
|
||||
sendln "show uptime"
|
||||
|
||||
; ========== Show Power on uptime ==========
|
||||
wait prompt_sonic_root
|
||||
sendln "reboot"
|
||||
if EN_Cold_Warm_boot = 1 then
|
||||
wait prompt_sonic_root
|
||||
sendln "reboot"
|
||||
elseif EN_Cold_Warm_boot = 2 then
|
||||
wait prompt_sonic_root
|
||||
sendln "pcimem /sys/bus/pci/devices/0000:05:00.0/resource0 0x480 w 0xD0000"
|
||||
else
|
||||
endif
|
||||
|
||||
|
||||
wait "Booting in blind mode"
|
||||
endwhile
|
||||
@@ -0,0 +1,204 @@
|
||||
#!/bin/sh
|
||||
# =============================================================================
|
||||
# bcm_dsc_parse_V1.0.0.sh
|
||||
#
|
||||
# Author : ETWen
|
||||
# Date : 20260906
|
||||
#
|
||||
# Version History
|
||||
# V1.0.0 20260906 Initial Version
|
||||
#
|
||||
# Description:
|
||||
# Parse Broadcom diag shell "phydiag <pm_id> dsc" raw log into CSV.
|
||||
# 支援多個 pm_id 串接在同一份 log,以 "pm_id =" 當 record separator。
|
||||
#
|
||||
# Output:
|
||||
# <prefix>_lane.csv : 每個 lane 一列(TXEQ / RXFFE / DFE / EYE / SNR ...)
|
||||
# <prefix>_pm.csv : 每個 pm_id 一列(溫度 / PLL / lane 數 / SNR-EYE 統計)
|
||||
#
|
||||
# Usage:
|
||||
# ./bcm_dsc_parse_V1.0.0.sh -i dsc_raw.log [-o out_prefix]
|
||||
#
|
||||
# Design notes:
|
||||
# - 純 POSIX sh + awk(mawk 相容),不依賴 Python。
|
||||
# - Lane row 採「括號群組出現順序」抽取,而非固定欄位位置,對排版空白
|
||||
# 變動免疫。SDK 若增減欄位,群組數不等於 9,該列會被標記 UNPARSED
|
||||
# 並輸出到 stderr,不會靜默解析錯誤。
|
||||
# - 已知 header 名稱數與資料欄數不一致之處:
|
||||
# * (P RX, CDRxN, UC_CFG, UC_STS, RST, STP) 6 個名字 / 7 個值
|
||||
# (RST 實際是 "0,0" 兩欄)
|
||||
# * TXEQ 尾端多一個逗號
|
||||
# * AVG_TMON 顯示為 "(11) 66C" 兩個 token
|
||||
# - SD / LCK 的 "*" 為 sticky 旗標,本版拆成獨立欄位保留,不做判讀。
|
||||
# - BER 欄若為 "!chk_en" 表示 checker 未開啟,值無效,原樣保留。
|
||||
# =============================================================================
|
||||
|
||||
set -e
|
||||
|
||||
IN=""
|
||||
PREFIX="dsc"
|
||||
|
||||
usage() {
|
||||
echo "Usage: $0 -i <raw_log> [-o <out_prefix>]" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
while getopts "i:o:h" opt; do
|
||||
case "$opt" in
|
||||
i) IN="$OPTARG" ;;
|
||||
o) PREFIX="$OPTARG" ;;
|
||||
*) usage ;;
|
||||
esac
|
||||
done
|
||||
|
||||
[ -n "$IN" ] || usage
|
||||
[ -f "$IN" ] || { echo "ERROR: input not found: $IN" >&2; exit 2; }
|
||||
|
||||
LANE_CSV="${PREFIX}_lane.csv"
|
||||
PM_CSV="${PREFIX}_pm.csv"
|
||||
|
||||
# 先去掉 CR(console / telnet log 常帶),再交給 awk
|
||||
tr -d '\r' < "$IN" | awk -v LANE_CSV="$LANE_CSV" -v PM_CSV="$PM_CSV" '
|
||||
function trim(s) { sub(/^[ \t]+/, "", s); sub(/[ \t]+$/, "", s); return s }
|
||||
|
||||
# 掃描一列,取出所有頂層括號群組到 G[],群組前的英數 prefix 到 P[],
|
||||
# 其餘純量文字留在 REST。回傳群組數。
|
||||
function split_groups(line, i, ch, d, buf, ng, rest, prefix) {
|
||||
split("", G, ":"); split("", P, ":")
|
||||
ng = 0; d = 0; buf = ""; rest = ""; prefix = ""
|
||||
for (i = 1; i <= length(line); i++) {
|
||||
ch = substr(line, i, 1)
|
||||
if (ch == "(") {
|
||||
d++
|
||||
if (d == 1) {
|
||||
buf = ""; prefix = ""
|
||||
if (match(rest, /[A-Za-z_]+$/)) {
|
||||
prefix = substr(rest, RSTART, RLENGTH)
|
||||
rest = substr(rest, 1, RSTART - 1)
|
||||
}
|
||||
continue
|
||||
}
|
||||
}
|
||||
if (ch == ")") {
|
||||
d--
|
||||
if (d == 0) { ng++; G[ng] = buf; P[ng] = prefix; rest = rest " "; continue }
|
||||
}
|
||||
if (d > 0) { buf = buf ch; continue }
|
||||
rest = rest ch
|
||||
}
|
||||
REST = rest
|
||||
return ng
|
||||
}
|
||||
|
||||
# 取括號群組的第 n 個子欄位(以逗號分隔)
|
||||
function gf(idx, n, a, c) {
|
||||
c = split(G[idx], a, ",")
|
||||
if (n > c) return ""
|
||||
return trim(a[n])
|
||||
}
|
||||
|
||||
function is_num(s) { return (s ~ /^[+-]?[0-9]+(\.[0-9]+)?$/) }
|
||||
|
||||
function reset_pm() {
|
||||
core = ""; sdtype = ""; hw_lanes = ""; lane_sel = ""
|
||||
live_temp = ""; avg_tmon = ""; pll_lock = ""
|
||||
n_lane = 0; snr_min = ""; snr_max = ""; eye_min = ""; all_lck = 1
|
||||
}
|
||||
|
||||
function flush_pm() {
|
||||
if (pm == "") return
|
||||
printf "%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s\n",
|
||||
pm, core, sdtype, hw_lanes, lane_sel, n_lane,
|
||||
live_temp, avg_tmon, pll_lock,
|
||||
(snr_min == "" ? "NA" : snr_min),
|
||||
(eye_min == "" ? "NA" : eye_min),
|
||||
(n_lane == 0 ? "NA" : (all_lck ? "PASS" : "FAIL")) > PM_CSV
|
||||
}
|
||||
|
||||
BEGIN {
|
||||
pm = ""; in_lane = 0; core_row = 0; bad = 0
|
||||
print "pm_id,core,lane,serdes_type,sd,sd_sticky,lck,lck_sticky,rxppm,txppm," \
|
||||
"txeq_n3,txeq_n2,txeq_n1,txeq_m,txeq_p1,txeq_p2,txeq_sum," \
|
||||
"rxffe_n3,rxffe_n2,rxffe_n1,rxffe_m,rxffe_p1,rxffe_p2," \
|
||||
"dfe1,dfe2,pf_m,pf_l,pf_h,vga,dco,tp0,tp1,tp2,flt_m,flt_s," \
|
||||
"nlc_u,nlc_l,eye_u,eye_m,eye_l,link_time,snr,ber," \
|
||||
"live_temp,avg_tmon,pll_lock,rx_pol,cdr,uc_cfg,uc_sts,rst,stp" > LANE_CSV
|
||||
print "pm_id,core,serdes_type,hw_lanes,lane_select,active_lanes," \
|
||||
"live_temp,avg_tmon,pll_lock,snr_min,eye_min,lck_all" > PM_CSV
|
||||
}
|
||||
|
||||
/^pm_id[ \t]*=/ { flush_pm(); pm = $NF; reset_pm(); in_lane = 0; next }
|
||||
/^Core[ \t]*=/ { if (match($0, /Core[ \t]*=[ \t]*[0-9]+/)) { core = $0; sub(/.*Core[ \t]*=[ \t]*/, "", core); sub(/[^0-9].*/, "", core) } next }
|
||||
/^SerDes type[ \t]*=/ { sdtype = $NF; next }
|
||||
/^Rev ID # Lanes/ { hw_lanes = $NF; next }
|
||||
/^lane_select[ \t]*=/ { lane_sel = $NF; next }
|
||||
|
||||
/^CORE[ \t]+RST_ST/ { core_row = 1; next }
|
||||
core_row == 1 {
|
||||
line = $0
|
||||
gsub(/\([^)]*\)[ \t]*/, "", line) # 去掉 AVG_TMON 的 "(11)"
|
||||
n = split(trim(line), c, /[ \t]+/)
|
||||
if (n >= 15) { live_temp = c[9]; avg_tmon = c[10]; pll_lock = c[15] }
|
||||
core_row = 0
|
||||
next
|
||||
}
|
||||
|
||||
/^LN[ \t]*\(/ { in_lane = 1; next }
|
||||
/SERDES DISPLAY DIAG DATA END/ { in_lane = 0; next }
|
||||
|
||||
in_lane && /^[0-9]+[ \t]*\(/ {
|
||||
ng = split_groups($0)
|
||||
if (ng != 9) {
|
||||
printf "UNPARSED (groups=%d) pm_id=%s: %s\n", ng, pm, $0 > "/dev/stderr"
|
||||
bad++
|
||||
next
|
||||
}
|
||||
nr = split(trim(REST), r, /[ \t]+/)
|
||||
if (nr != 10) {
|
||||
printf "UNPARSED (scalars=%d) pm_id=%s: %s\n", nr, pm, $0 > "/dev/stderr"
|
||||
bad++
|
||||
next
|
||||
}
|
||||
|
||||
lane = r[1]
|
||||
sd = r[2]; sd_st = (sd ~ /\*/) ? 1 : 0; gsub(/\*/, "", sd)
|
||||
lck = r[3]; lck_st = (lck ~ /\*/) ? 1 : 0; gsub(/\*/, "", lck)
|
||||
rxppm = r[4]; vga = r[5]; dco = r[6]; txppm = r[7]
|
||||
link_time = r[8]; snr = r[9]; ber = r[10]
|
||||
|
||||
# TXEQ 六個 tap 與總和(僅在全為數值時計算)
|
||||
tsum = 0; tok = 1
|
||||
for (i = 1; i <= 6; i++) {
|
||||
tq[i] = gf(7, i)
|
||||
if (is_num(tq[i])) tsum += tq[i]; else tok = 0
|
||||
}
|
||||
|
||||
printf "%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,", pm, core, lane, sdtype, sd, sd_st, lck, lck_st, rxppm, txppm > LANE_CSV
|
||||
printf "%s,%s,%s,%s,%s,%s,%s,", tq[1], tq[2], tq[3], tq[4], tq[5], tq[6], (tok ? tsum : "NA") > LANE_CSV
|
||||
printf "%s,%s,%s,%s,%s,%s,", gf(4,1), gf(4,2), gf(4,3), gf(4,4), gf(4,5), gf(4,6) > LANE_CSV
|
||||
printf "%s,%s,", gf(5,1), gf(5,2) > LANE_CSV
|
||||
printf "%s,%s,%s,%s,%s,", gf(2,1), gf(2,2), gf(2,3), vga, dco > LANE_CSV
|
||||
printf "%s,%s,%s,%s,%s,", gf(3,1), gf(3,2), gf(3,3), gf(6,1), gf(6,2) > LANE_CSV
|
||||
printf "%s,%s,%s,%s,%s,", gf(8,1), gf(8,2), gf(9,1), gf(9,2), gf(9,3) > LANE_CSV
|
||||
printf "%s,%s,%s,", link_time, snr, ber > LANE_CSV
|
||||
printf "%s,%s,%s,", live_temp, avg_tmon, pll_lock > LANE_CSV
|
||||
printf "%s,%s,%s,%s,%s/%s,%s\n", gf(1,1), gf(1,2), gf(1,3), gf(1,4), gf(1,5), gf(1,6), gf(1,7) > LANE_CSV
|
||||
|
||||
# per-PM 統計
|
||||
n_lane++
|
||||
if (lck != "1" || sd != "1") all_lck = 0
|
||||
if (is_num(snr)) { if (snr_min == "" || snr + 0 < snr_min + 0) snr_min = snr }
|
||||
for (i = 1; i <= 3; i++) {
|
||||
e = gf(9, i)
|
||||
if (is_num(e)) { if (eye_min == "" || e + 0 < eye_min + 0) eye_min = e }
|
||||
}
|
||||
next
|
||||
}
|
||||
|
||||
END {
|
||||
flush_pm()
|
||||
if (bad > 0) printf "WARN: %d lane row(s) unparsed\n", bad > "/dev/stderr"
|
||||
}
|
||||
'
|
||||
|
||||
echo "OK: ${LANE_CSV}, ${PM_CSV}"
|
||||
@@ -0,0 +1,347 @@
|
||||
#!/bin/sh
|
||||
# =============================================================================
|
||||
# bcm_dsc_scan.sh
|
||||
#
|
||||
# Author : ETWen
|
||||
# Date : 20260906
|
||||
#
|
||||
# Version History
|
||||
# V1.0.0 20260906 Initial Version
|
||||
# V1.1.0 20260906 Log 預設輸出至 <script_dir>/log,掃描後自動複製到
|
||||
# /host/hw-eval/jobs/;非 tty 環境改用逐行進度輸出,
|
||||
# 避免灌爆 Tera Term logopen 的 log
|
||||
# V1.2.0 20260906 新增 -f 自訂 log 檔名(支援 %u / %t 佔位符)與
|
||||
# -F 強制覆蓋;預設不覆蓋既有檔案,自動加序號
|
||||
# V1.3.0 20260907 修正 bcmcmd 讀取 stdin 導致掃描迴圈在第一筆之後
|
||||
# 提前結束的問題(迴圈改用 fd 3,bcmcmd 導向
|
||||
# /dev/null);新增實際迭代筆數與清單筆數的檢查
|
||||
#
|
||||
# Description:
|
||||
# 在 Blanton SONiC DUT 上批次執行 Broadcom diag shell 的
|
||||
# "phydiag <port> dsc",收集 raw log 供離線解析。
|
||||
#
|
||||
# 實際下的指令為:
|
||||
# bcmcmd -n <unit> -c "dsh -c 'phydiag <port> dsc'"
|
||||
#
|
||||
# Deployment:
|
||||
# Script : /root/Blanton_Script/bcm_dsc_scan.sh
|
||||
# Log : /root/Blanton_Script/log/dsc_raw_u<unit>_<YYYYmmdd_HHMMSS>.log
|
||||
# Copy : /host/hw-eval/jobs/
|
||||
#
|
||||
# Log 檔名可用 -f 覆寫,支援兩個佔位符:
|
||||
# %u -> u0 / u1
|
||||
# %t -> YYYYmmdd_HHMMSS
|
||||
# -f 只接受檔名,不接受路徑;目錄一律由 -o 決定。
|
||||
# 同時掃兩個 unit 但檔名未含 %u 時,會自動在副檔名前插入 _u<unit>,
|
||||
# 避免第二個 unit 覆蓋掉第一個。
|
||||
#
|
||||
# 路徑由 $0 推導,不依賴 $HOME。Script A 以 sudo -i 執行時 ~ 為 /root,
|
||||
# 直接寫死 ~ 會有風險,故一律使用絕對路徑。
|
||||
#
|
||||
# Usage:
|
||||
# ./bcm_dsc_scan.sh # unit 0 與 1 都掃,掃完自動複製
|
||||
# ./bcm_dsc_scan.sh -u 0 # 只掃 unit 0
|
||||
# ./bcm_dsc_scan.sh -n # dry-run,只列出要掃的 port
|
||||
# ./bcm_dsc_scan.sh -C # 不複製到 /host/hw-eval/jobs
|
||||
# ./bcm_dsc_scan.sh -c /other/dir # 指定複製目的地
|
||||
# ./bcm_dsc_scan.sh -u 0 -f dsc_before_reboot.log
|
||||
# ./bcm_dsc_scan.sh -f blanton_dsc_%u_%t.log
|
||||
#
|
||||
# Exit code:
|
||||
# 0 = 全部 port 皆取得完整 dump
|
||||
# 1 = 有 port 未取得完整 dump,或複製失敗
|
||||
# 2 = 參數 / 路徑錯誤
|
||||
# 3 = 找不到 bcmcmd
|
||||
#
|
||||
# 結束時固定輸出一行 "### DSC_SCAN_DONE rc=<n>",供 TTL 端 wait 判斷。
|
||||
#
|
||||
# Design notes:
|
||||
# - 純 POSIX sh,不依賴 bash / Python。
|
||||
# - Port 清單以「範圍字串」定義在下方 PORTS_* 變數,展開後去重。
|
||||
# 100G 清單先展開,故重複的 port 會被判定為 100G(目前僅 port 268)。
|
||||
# - bcmcmd 即使指令失敗通常仍回傳 0,因此不以 exit code 判斷成功與否;
|
||||
# 改由 marker 行 + "SERDES DISPLAY DIAG DATA END" 數量比對。
|
||||
# - 先寫入本機 log 目錄再複製,而非直接寫遠端,避免中途失敗遺失整份資料。
|
||||
#
|
||||
# Assumptions:
|
||||
# - unit 0 與 unit 1 使用相同的 port 清單。
|
||||
# - phydiag 的參數為此清單中的 port 編號(非 port name)。
|
||||
# - 由 root 執行(Script A 的 sudo -i 之後),故不呼叫 sudo。
|
||||
#
|
||||
# Cautions:
|
||||
# - 全清單約 445 port x 2 unit,估計 10 分鐘,請勿把 DELAY 設為 0。
|
||||
# - phydiag ... dsc 為唯讀操作,不會變更 SerDes 設定。
|
||||
# =============================================================================
|
||||
|
||||
set -u
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Port list (以空白分隔的範圍或單一值)
|
||||
# ----------------------------------------------------------------------------
|
||||
PORTS_100G="268"
|
||||
PORTS_200G="1-24 40-96 112-168 184-240 256-308 310-327 342-380 382-399 414-452 454-471 486-524 526-543 558-565"
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Paths / defaults
|
||||
# ----------------------------------------------------------------------------
|
||||
SCRIPT_DIR=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd) || exit 2
|
||||
|
||||
UNITS="0 1"
|
||||
OUTDIR="${SCRIPT_DIR}/log"
|
||||
COPYDIR="/host/hw-eval/jobs"
|
||||
DELAY="0.2"
|
||||
DRYRUN=0
|
||||
DOCOPY=1
|
||||
LOGNAME="" # -f 指定的 log 檔名,空字串表示使用預設命名
|
||||
FORCE=0 # -F 允許覆蓋既有檔案
|
||||
PROGRESS_EVERY=50 # 非 tty 環境每 N 筆印一行進度
|
||||
|
||||
usage() {
|
||||
cat >&2 << 'USAGE'
|
||||
Usage: bcm_dsc_scan.sh [-u <0|1>] [-o <outdir>] [-f <logname>] [-F]
|
||||
[-c <copydir>] [-C] [-d <sec>] [-n] [-h]
|
||||
|
||||
-u <unit> 只掃指定 unit。省略則 unit 0 與 1 都掃。
|
||||
-o <dir> log 輸出目錄 (default: <script_dir>/log)
|
||||
-f <name> 自訂 log 檔名(僅檔名,不含路徑)
|
||||
佔位符: %u -> u0/u1 , %t -> YYYYmmdd_HHMMSS
|
||||
default: dsc_raw_%u_%t.log
|
||||
-F 允許覆蓋既有同名檔案 (default: 自動加序號 _1 / _2 ...)
|
||||
-c <dir> 掃描後複製目的地 (default: /host/hw-eval/jobs)
|
||||
-C 不複製
|
||||
-d <sec> 每筆 phydiag 之間的間隔 (default: 0.2)
|
||||
-n dry-run,列出展開後的 port 清單與指令,不實際執行
|
||||
-h 顯示此說明
|
||||
USAGE
|
||||
exit 1
|
||||
}
|
||||
|
||||
while getopts "u:o:f:Fc:Cd:nh" opt; do
|
||||
case "$opt" in
|
||||
u)
|
||||
case "$OPTARG" in
|
||||
0|1) UNITS="$OPTARG" ;;
|
||||
*) echo "ERROR: -u 只接受 0 或 1 (got: $OPTARG)" >&2; exit 2 ;;
|
||||
esac
|
||||
;;
|
||||
o) OUTDIR="$OPTARG" ;;
|
||||
f)
|
||||
case "$OPTARG" in
|
||||
"") echo "ERROR: -f 不可為空" >&2; exit 2 ;;
|
||||
*/*) echo "ERROR: -f 只接受檔名,路徑請用 -o (got: $OPTARG)" >&2; exit 2 ;;
|
||||
*) LOGNAME="$OPTARG" ;;
|
||||
esac
|
||||
;;
|
||||
F) FORCE=1 ;;
|
||||
c) COPYDIR="$OPTARG" ;;
|
||||
C) DOCOPY=0 ;;
|
||||
d) DELAY="$OPTARG" ;;
|
||||
n) DRYRUN=1 ;;
|
||||
*) usage ;;
|
||||
esac
|
||||
done
|
||||
|
||||
mkdir -p "$OUTDIR" 2>/dev/null || { echo "ERROR: cannot create outdir: $OUTDIR" >&2; exit 2; }
|
||||
[ -w "$OUTDIR" ] || { echo "ERROR: outdir not writable: $OUTDIR" >&2; exit 2; }
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# sleep 是否支援小數秒(busybox sleep 可能只吃整數)
|
||||
# ----------------------------------------------------------------------------
|
||||
if ! sleep "$DELAY" 2>/dev/null; then
|
||||
echo "WARN: sleep '$DELAY' 不支援,改用 sleep 1" >&2
|
||||
DELAY="1"
|
||||
fi
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# 展開 port 清單。100G 先展開,重複者以 100G 為準。
|
||||
# 輸出格式: "<port>,<speed>",依 port 數值排序。
|
||||
# ----------------------------------------------------------------------------
|
||||
PORTFILE=$(mktemp) || { echo "ERROR: mktemp failed" >&2; exit 2; }
|
||||
trap 'rm -f "$PORTFILE"' EXIT
|
||||
trap 'echo "" >&2; echo "### DSC_SCAN_DONE rc=130 (INTERRUPTED)" >&2; rm -f "$PORTFILE"; exit 130' INT TERM
|
||||
|
||||
awk -v a="$PORTS_100G" -v b="$PORTS_200G" '
|
||||
function expand(s, spd, n, i, j, p, k, lo, hi) {
|
||||
n = split(s, p, /[ \t]+/)
|
||||
for (i = 1; i <= n; i++) {
|
||||
if (p[i] == "") continue
|
||||
if (split(p[i], k, "-") == 2) { lo = k[1] + 0; hi = k[2] + 0 }
|
||||
else { lo = p[i] + 0; hi = lo }
|
||||
if (hi < lo) { printf "ERROR: bad range %s\n", p[i] > "/dev/stderr"; continue }
|
||||
for (j = lo; j <= hi; j++) if (!(j in SPD)) SPD[j] = spd
|
||||
}
|
||||
}
|
||||
BEGIN {
|
||||
expand(a, "100G") # 先展開 100G,重複的 port 由 100G 取得
|
||||
expand(b, "200G")
|
||||
for (p in SPD) print p "," SPD[p]
|
||||
}' | sort -t, -k1,1n > "$PORTFILE"
|
||||
|
||||
TOTAL=$(wc -l < "$PORTFILE" | tr -d ' ')
|
||||
[ "$TOTAL" -gt 0 ] || { echo "ERROR: port list is empty" >&2; exit 2; }
|
||||
|
||||
N100=$(grep -c ',100G$' "$PORTFILE" || true)
|
||||
N200=$(grep -c ',200G$' "$PORTFILE" || true)
|
||||
|
||||
echo "Script dir : $SCRIPT_DIR" >&2
|
||||
echo "Log dir : $OUTDIR" >&2
|
||||
echo "Port list : $TOTAL ports (200G x2: $N200, 100G: $N100)" >&2
|
||||
echo "Units : $UNITS" >&2
|
||||
echo "Delay : ${DELAY}s" >&2
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Dry-run
|
||||
# ----------------------------------------------------------------------------
|
||||
if [ "$DRYRUN" -eq 1 ]; then
|
||||
for U in $UNITS; do
|
||||
echo "--- unit $U ---"
|
||||
while IFS=, read -r P SPD; do
|
||||
printf 'bcmcmd -n %s -c "dsh -c '\''phydiag %s dsc'\''" # %s\n' "$U" "$P" "$SPD"
|
||||
done < "$PORTFILE"
|
||||
done
|
||||
echo "### DSC_SCAN_DONE rc=0 (dry-run)" >&2
|
||||
exit 0
|
||||
fi
|
||||
|
||||
command -v bcmcmd > /dev/null 2>&1 || {
|
||||
echo "ERROR: bcmcmd not found in PATH" >&2
|
||||
echo "### DSC_SCAN_DONE rc=3" >&2
|
||||
exit 3
|
||||
}
|
||||
|
||||
# stderr 是 tty 才用 \r 進度條;被導向檔案(Tera Term logopen)時改逐行輸出
|
||||
if [ -t 2 ]; then TTY=1; else TTY=0; fi
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Log 檔名處理
|
||||
# ----------------------------------------------------------------------------
|
||||
|
||||
# 純 POSIX 的字串取代,避免 sed 對檔名中的特殊字元誤判
|
||||
replace_all() { # $1=haystack $2=needle $3=replacement
|
||||
_s=$1; _n=$2; _r=$3; _out=""
|
||||
while :; do
|
||||
case "$_s" in
|
||||
*"$_n"*)
|
||||
_out="${_out}${_s%%"$_n"*}${_r}"
|
||||
_s=${_s#*"$_n"}
|
||||
;;
|
||||
*) _out="${_out}${_s}"; break ;;
|
||||
esac
|
||||
done
|
||||
printf '%s' "$_out"
|
||||
}
|
||||
|
||||
# 依 unit 組出 log 檔名。未指定 -f 時使用預設命名。
|
||||
build_logname() { # $1=unit
|
||||
_u=$1
|
||||
_n=${LOGNAME:-dsc_raw_%u_%t.log}
|
||||
case "$_n" in *%u*) _has_u=1 ;; *) _has_u=0 ;; esac
|
||||
_n=$(replace_all "$_n" '%u' "u${_u}")
|
||||
_n=$(replace_all "$_n" '%t' "$TS")
|
||||
# 掃兩個 unit 但檔名沒有 %u,第二個 unit 會覆蓋第一個,故自動加上 _u<unit>
|
||||
if [ "$_has_u" -eq 0 ] && [ "$MULTI" -eq 1 ]; then
|
||||
case "$_n" in
|
||||
*.*) _n="${_n%.*}_u${_u}.${_n##*.}" ;;
|
||||
*) _n="${_n}_u${_u}" ;;
|
||||
esac
|
||||
fi
|
||||
printf '%s' "$_n"
|
||||
}
|
||||
|
||||
# 檔案已存在時自動加序號,避免覆蓋掉先前的掃描結果(-F 可強制覆蓋)
|
||||
uniquify() { # $1=filename
|
||||
_f=$1
|
||||
[ -e "${OUTDIR}/${_f}" ] || { printf '%s' "$_f"; return; }
|
||||
if [ "$FORCE" -eq 1 ]; then
|
||||
echo "WARN: 覆蓋既有檔案 ${OUTDIR}/${_f}" >&2
|
||||
printf '%s' "$_f"; return
|
||||
fi
|
||||
case "$_f" in
|
||||
*.*) _b=${_f%.*}; _e=".${_f##*.}" ;;
|
||||
*) _b=$_f; _e="" ;;
|
||||
esac
|
||||
_i=1
|
||||
while [ -e "${OUTDIR}/${_b}_${_i}${_e}" ]; do _i=$((_i + 1)); done
|
||||
echo "WARN: ${_f} 已存在,改用 ${_b}_${_i}${_e}(-F 可強制覆蓋)" >&2
|
||||
printf '%s' "${_b}_${_i}${_e}"
|
||||
}
|
||||
|
||||
MULTI=0
|
||||
[ "$(echo "$UNITS" | wc -w | tr -d ' ')" -gt 1 ] && MULTI=1
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Scan
|
||||
# ----------------------------------------------------------------------------
|
||||
TS=$(date +%Y%m%d_%H%M%S)
|
||||
RC=0
|
||||
LOGS=""
|
||||
|
||||
for U in $UNITS; do
|
||||
LOG="${OUTDIR}/$(uniquify "$(build_logname "$U")")"
|
||||
: > "$LOG" || { echo "ERROR: cannot write $LOG" >&2; exit 2; }
|
||||
LOGS="$LOGS $LOG"
|
||||
|
||||
printf '### SCAN_BEGIN unit=%s time=%s total=%s script=bcm_dsc_scan_V1.3.0\n' \
|
||||
"$U" "$(date '+%Y-%m-%d %H:%M:%S')" "$TOTAL" >> "$LOG"
|
||||
|
||||
echo "[unit $U] scanning $TOTAL ports -> $LOG" >&2
|
||||
|
||||
SEQ=0
|
||||
while IFS=, read -r P SPD <&3; do
|
||||
SEQ=$((SEQ + 1))
|
||||
printf '### PORT unit=%s port=%s speed=%s seq=%s/%s\n' "$U" "$P" "$SPD" "$SEQ" "$TOTAL" >> "$LOG"
|
||||
# bcmcmd 會讀取 stdin,若不導成 /dev/null 會把 PORTFILE 剩餘內容吸走,
|
||||
# 導致迴圈在第一筆之後就讀到 EOF 而提前結束。
|
||||
bcmcmd -n "$U" -c "dsh -c 'phydiag $P dsc'" >> "$LOG" 2>&1 < /dev/null || RC=1
|
||||
|
||||
if [ "$TTY" -eq 1 ]; then
|
||||
printf '\r[unit %s] %s/%s port=%-5s' "$U" "$SEQ" "$TOTAL" "$P" >&2
|
||||
elif [ $((SEQ % PROGRESS_EVERY)) -eq 0 ] || [ "$SEQ" -eq "$TOTAL" ]; then
|
||||
printf '[unit %s] %s/%s port=%s\n' "$U" "$SEQ" "$TOTAL" "$P" >&2
|
||||
fi
|
||||
|
||||
sleep "$DELAY"
|
||||
done 3< "$PORTFILE"
|
||||
|
||||
[ "$TTY" -eq 1 ] && printf '\n' >&2
|
||||
printf '### SCAN_END unit=%s time=%s\n' "$U" "$(date '+%Y-%m-%d %H:%M:%S')" >> "$LOG"
|
||||
|
||||
# 檢查 1:實際迭代筆數是否等於 port 清單筆數。
|
||||
# 迴圈若因 stdin 被子程序吸走而提前結束,只靠下面的 marker/dump 比對抓不到。
|
||||
if [ "$SEQ" -ne "$TOTAL" ]; then
|
||||
echo "ERROR: unit $U 只跑了 $SEQ/$TOTAL 筆,迴圈提前結束" >&2
|
||||
RC=1
|
||||
fi
|
||||
|
||||
# 檢查 2:每筆 PORT marker 應對應一個 dsc 區塊
|
||||
MARK=$(grep -c '^### PORT ' "$LOG" || true)
|
||||
DUMP=$(grep -c 'SERDES DISPLAY DIAG DATA END' "$LOG" || true)
|
||||
if [ "$MARK" -ne "$DUMP" ]; then
|
||||
echo "WARN: unit $U markers=$MARK dsc_blocks=$DUMP (有 port 未取得完整 dump)" >&2
|
||||
RC=1
|
||||
fi
|
||||
echo "Saved: $LOG (${DUMP}/${TOTAL} dumps)" >&2
|
||||
done
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Copy to job directory
|
||||
# ----------------------------------------------------------------------------
|
||||
if [ "$DOCOPY" -eq 1 ]; then
|
||||
if mkdir -p "$COPYDIR" 2>/dev/null && [ -w "$COPYDIR" ]; then
|
||||
for L in $LOGS; do
|
||||
if cp -p "$L" "$COPYDIR/"; then
|
||||
echo "Copied: $COPYDIR/$(basename "$L")" >&2
|
||||
else
|
||||
echo "ERROR: copy failed: $L -> $COPYDIR" >&2
|
||||
RC=1
|
||||
fi
|
||||
done
|
||||
sync
|
||||
else
|
||||
echo "ERROR: copydir not writable: $COPYDIR (log 仍保留在 $OUTDIR)" >&2
|
||||
RC=1
|
||||
fi
|
||||
fi
|
||||
|
||||
echo "### DSC_SCAN_DONE rc=${RC}" >&2
|
||||
exit "$RC"
|
||||
@@ -5,6 +5,8 @@ project_name = "Blanton"
|
||||
strTestcase="ENV" ;ENV,EMC,Margin...etc
|
||||
|
||||
EN_Margin = 0 ; 1: Enable Margin Test, 0: Disable Margin Test
|
||||
EN_TX_FIR = 0 ; 1: Enable bcm_dsc_scan.sh collect port TX_FIR, 0: Disable (saves ~20 min: ScriptA and ScriptC each scan for ~10 min)
|
||||
|
||||
EN_log = 1 ; 1: Enable log, 0: Disable log
|
||||
EN_timestamp = 1 ; 1: Enable timestamp in log, 0: Disable timestamp in log
|
||||
|
||||
@@ -32,4 +34,13 @@ BMC_USB_RUNTIME = 172800 ; Unit seconds, 172800 = 2 days
|
||||
;================================================================
|
||||
prompt_login = "sonic login:"
|
||||
prompt_sonic = "admin@sonic:~$"
|
||||
prompt_sonic_root = "root@sonic:~#"
|
||||
prompt_sonic_root = "root@sonic:~#"
|
||||
|
||||
|
||||
;================================================================
|
||||
; Reboot or Power Cycle
|
||||
;================================================================
|
||||
; 0: Normal Test
|
||||
; 1: Enable Reboot Cycle
|
||||
; 2: Enable Power Cycle
|
||||
EN_Cold_Warm_boot = 0
|
||||
Reference in New Issue
Block a user