Compare commits
5
Commits
V1.2.1
..
b911ccd658
| Author | SHA1 | Date | |
|---|---|---|---|
  etwenandClaude Opus 5
|
b911ccd658 | ||
|
etwenandClaude Opus 5
|
dd558a7b0f | ||
|
etwenandClaude Opus 5
|
690be5db7d | ||
|
etwenandClaude Opus 5
|
a5b7c4757b | ||
|
etwenandClaude Opus 5
|
f5694345fb |
+19
-3
@@ -136,6 +136,7 @@ Blanton_TTL_Script/
|
||||
│ ├── 100G_PRBS.txt # 100G PRBS 原始指令（port_prbs_monitor.sh 的來源）
|
||||
│ ├── TR518.txt # 內建封包測試 tr 518 → blanton_tr518.sh
|
||||
│ ├── BER_Test.txt # 全機 PRBS BER 指令 → blanton_ber.sh
|
||||
│ ├── 100G_dsc_cycle.txt # 100G tuning + link 循環 + DSC → bcm_100g_dsc_cycle.sh
|
||||
│ ├── Multiphase_{high3,low3,comboA,comboB,Save}.txt # → blanton_multiphase_margin.sh
|
||||
│ ├── Multiphase_Netname # 38 條軌的 net 名稱（區塊順序對應）
|
||||
│ ├── 100G_Traffic.txt # ce0 VLAN 138 打流 → blanton_traffic_linespeed.sh
|
||||
@@ -201,6 +202,8 @@ Blanton_TTL_Script/
|
||||
├── 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）
|
||||
│ # V1.2.2 起含 port 268（100G ce0），summary 每 unit 分 200G/100G/TOTAL
|
||||
├── bcm_100g_dsc_cycle.sh # 100G link down/up 循環 + 每輪 DSC 與 retimer TX/RX 讀回（未驗證）
|
||||
├── 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）
|
||||
@@ -374,7 +377,7 @@ 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` V1.2.1 | 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 A（Pre-test）** | `1_Blanton_Script_A.ttl` V1.2.2 | 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` |
|
||||
@@ -393,7 +396,8 @@ PROFILE_CHANNELS=( "0:high:8" "1:low:8" ... ) # "channel:operation:change_perc
|
||||
| **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 |
|
||||
| **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。**V1.2.2（腳本 v1.1.0）起清單納入 port 268（100G uplink ce0）**，summary 每個 unit 拆成 200G ports / 100G p268 / TOTAL 三列；某組零 lane 算 FAIL |
|
||||
| **100G link 循環 + DSC** | `bcm_100g_dsc_cycle.sh <cycles> [-d] [-T] [-P] [-n]` | tuning（`docker pause gbsyncd*` → `serdes-tx-set sys 0..7` → 每 lane `tx_taps set`）一次，之後每輪：`port 268 en=0` → 輪詢 `bcmcmd ps 268` 等 `!ena` → `en=1` → 等 `up` → 兩個 unit 的 `phydiag 268 dsc` + `serdes-tx-get`/`serdes-rx-get sys 0..7`。log 一次執行一份（`~/dsc_log/`），每輪一段 `### TEST CYCLE n/N`，結尾 `### DSC_CYCLE_DONE rc=<n>`。**全 ASCII 輸出**（DUT console 會把 UTF-8 弄成亂碼）。⚠️ 尚未上機驗證 |
|
||||
| **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 |
|
||||
@@ -804,7 +808,7 @@ 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 `V1.2.1`；`publish/` 依 Script A 檔頭版號打包）
|
||||
- [x] 打 git tag，push `nas` + `gitea`（已至 `V1.2.2`；`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。
|
||||
@@ -851,6 +855,10 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值，
|
||||
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**。
|
||||
- **`bcm_100g_dsc_cycle.sh` 尚未上機驗證**：`port en=0/1` 之後 link 多久會動、以及
|
||||
`docker pause gbsyncd*` 期間的影響，都要上機才知道。等待是讀 SDK（`bcmcmd ps <port>`）而不是
|
||||
`show interfaces status`，所以理論上不受 gbsyncd 暫停影響，但沒實測過。
|
||||
結束時（含 Ctrl-C）會自動 `docker unpause`，`RESUME_GBSYNCD=0` 可關掉。
|
||||
- **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
|
||||
@@ -914,6 +922,14 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值，
|
||||
- **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` 不再把 lane 的量測結果當成 shell 錯誤**（v1.1.1，2026-09-15）：
|
||||
`prbs get` 每條 lane 一行，沒鎖上的會印 `PRBS Error!`，而錯誤樣式是拿
|
||||
`grep -i 'ERROR|Invalid|...'` 掃整份輸出的 —— 於是正常的 init 會報「the BCM shell rejected」，
|
||||
而且提早 return，**把「哪幾條 lane 沒鎖」這個真正有用的資訊吞掉**。現在 per-lane 行排除在
|
||||
掃描外、改成大小寫敏感、真正的拒絕會把該行印出來。
|
||||
⚠️ **這類「完整性檢查自己看不到失敗」的錯在這個 repo 已經出現三次**
|
||||
（`bcm_dsc_scan.sh` v1.3.0 數 marker、`blanton_ber.sh` v1.1.1、以及 power cycle 報告的
|
||||
ping 解析把 100% 丟包當成「沒資料」）。寫檢查時要問：**失敗長什麼樣，這段程式碼看得到嗎？**
|
||||
- **`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。
|
||||
|
||||
@@ -9,7 +9,7 @@ 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（2026-09-08）**：Script A 為 **V1.2.1**（A 集中記錄所有 TTL 的變更）。涵蓋
|
||||
**目前狀態（2026-09-15）**：Script A 為 **V1.2.2**（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
|
||||
@@ -25,6 +25,7 @@ Script B 的 soak 迴圈每輪印 `bgctl list` + `jobs` + `systemctl is-active m
|
||||
`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`，依 `SWB_UNIT` 分支）；**V1.2.1 起 Script A 也接了一次**，
|
||||
**V1.2.2 起清單納入 port 268（100G uplink，ce0）**，summary 每個 unit 拆成「200G ports / 100G p268 / TOTAL」三列；
|
||||
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）。
|
||||
@@ -152,6 +153,8 @@ sleep 30 # 至少等一個 interval 再 rep
|
||||
./Blanton_Script/blanton_ber.sh report # 每 lane 一列，BER < 1e-6 才 PASS，最後 summary
|
||||
./Blanton_Script/blanton_ber.sh stop # prbsstat STOp
|
||||
./Blanton_Script/blanton_ber.sh clear # prbs clear（會解除 PRBS，要重測得再 init）
|
||||
# summary 每個 unit 三列：200G ports / 100G p268 / TOTAL（兩個 unit 各有自己的 ce0(268)）
|
||||
# ⚠️ 某一組「一條 lane 都沒回報」算 FAIL 不算 PASS —— 待測的 port 沉默不是通過
|
||||
# -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）
|
||||
|
||||
@@ -171,6 +174,17 @@ sh ~/Blanton_Script/bcm_dsc_parse.sh -i blanton_dsc_ScriptA_u0.log -o u0
|
||||
# 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
|
||||
|
||||
# ── 100G link down/up 循環 + DSC（TTL 尚未接）────────
|
||||
./Blanton_Script/bcm_100g_dsc_cycle.sh # 印說明
|
||||
./Blanton_Script/bcm_100g_dsc_cycle.sh 200 # 跑 200 輪（-c 200 亦可）
|
||||
./Blanton_Script/bcm_100g_dsc_cycle.sh 200 -d # 每行指令以灰色 [CMD] 印出來
|
||||
./Blanton_Script/bcm_100g_dsc_cycle.sh 20 -T # 跳過 tuning
|
||||
./Blanton_Script/bcm_100g_dsc_cycle.sh 1 -n # dry-run，不碰硬體也不 sleep
|
||||
# log: ~/dsc_log/100G_dsc_cycle_test_<ts>.log，每輪一段 '### TEST CYCLE n/N'
|
||||
# 每輪收：兩個 unit 的 phydiag dsc + serdes-tx-get / serdes-rx-get sys 0..7
|
||||
# 等 link 是輪詢 'bcmcmd ps 268'（每 -p 秒，上限 -w 秒），不是 show interfaces status
|
||||
# ⚠️ 尚未上機驗證；與 blanton_ber / blanton_traffic_linespeed / blanton_tr518 互斥
|
||||
|
||||
# ── 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
|
||||
@@ -354,6 +368,11 @@ 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**
|
||||
- ⚠️ **`prbs get` 印的每一行是資料，不是 shell 的錯誤訊息**：沒鎖上的 lane 會印 `PRBS Error!`，
|
||||
而 `blanton_ber.sh` 從 v1.0.0 就用 `grep -i 'ERROR|Invalid|...'` 掃**整份輸出**判斷「指令被拒絕」——
|
||||
於是**跑得好好的 init 會報 `the BCM shell rejected 'phydiag ... prbs get'`**，而且因為提早 return，
|
||||
那段「數 PRBS OK / 總數」的檢查根本沒跑，**你看到一個假錯誤，卻看不到哪幾條 lane 真的沒鎖**。
|
||||
v1.1.1 已把 per-lane 行排除在錯誤掃描外、改成大小寫敏感，並把真正的拒絕訊息印出來
|
||||
- ⚠️ **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 ——
|
||||
|
||||
@@ -0,0 +1,63 @@
|
||||
# v1.2.2 — The 100G uplink joins the BER sweep, and a boot cycle that can pull the power
|
||||
|
||||
## ✨ New features
|
||||
|
||||
**The BER sweep now measures port 268, the 100G uplink**
|
||||
* The port list ran `256-259` straight to `270-308`, so `ce0(268)` — the 100G uplink — was never in it. It is now its own group alongside the 200G ports.
|
||||
* The summary gives **each unit three rows**: `200G ports`, `100G p268`, and `TOTAL`. Unit 0 and unit 1 each have their own `ce0(268)`, and a marginal uplink lane averaged into 432 others is invisible; on its own row it is not.
|
||||
* A group that reports no lane at all now counts as a **failure**, not a pass. Silence on the port under test is the easiest way to ship a green report that measured nothing.
|
||||
|
||||
**Script 5 is now a boot cycle, warm or cold**
|
||||
* `5_Blanton_Script_Reboot_Cycle.ttl` → `5_Blanton_Script_Boot_Cycle.ttl`, with `EN_Cold_Warm_boot` in `config.ttl` choosing: `1` = `reboot` (warm), `2` = a cold cycle by writing the CB FPGA, `0` = neither.
|
||||
* The log file and the per-round banner are named after the kind of boot: `Blanton_Reboot_Cycle_<ts>.log` / `Reboot Cycle : N`, or `Blanton_Power_Cycle_<ts>.log` / `Power Cycle : N`.
|
||||
* Both stress logs are removed before each run. `qfx5252-stress-*` appends to its `--log` and the macro `cat`s the whole thing, so every cycle was printing back everything the earlier cycles had written — 289 lines at cycle 1 and 36,555 by cycle 199. At roughly 6.2 ms a line on a 115200 console that accounted for **+212 s of the +214 s the cycle grew** over a 199-cycle run. The DUT was never getting slower.
|
||||
|
||||
**`bcm_100g_dsc_cycle.sh` — 100G link down/up cycling with SerDes capture**
|
||||
* Tuning once, then N cycles of `port 268 en=0` → wait → `en=1` → wait → `phydiag 268 dsc` on both units → retimer `serdes-tx-get` / `serdes-rx-get` for `sys 0..7`. One log per run under `~/dsc_log/`, split by `### TEST CYCLE n/N`.
|
||||
* Waiting is a **poll of `bcmcmd ps 268`**, not `show interfaces status`. `port en=` changes the SDK, and the SONiC table only follows once gbsyncd has synced it — and this test pauses gbsyncd.
|
||||
* `-d` echoes every command as a grey `[CMD]` line before running it; `-n` is a dry run that touches nothing; the cycle count can be a bare argument (`./bcm_100g_dsc_cycle.sh 200`).
|
||||
|
||||
## 🐛 Bug fixes
|
||||
|
||||
**`blanton_ber.sh init` reported a hard error on runs that were working**
|
||||
* `[ERR ] unit 1: the BCM shell rejected 'phydiag ... prbs get'` — except the command was fine. `prbs get` prints one line per lane, a lane that has not locked says `PRBS Error!`, and the rejection check grepped the **whole** output case-insensitively for `ERROR|Invalid|...`.
|
||||
* Worse than the false alarm: the function returned early, so the lock count that was meant to judge those very lanes never ran. The operator saw an error they could not act on, and did **not** see which lanes had failed to lock. That check has been there since v1.0.0.
|
||||
* Per-lane result lines are now excluded, the match is case-sensitive, and a genuine rejection prints the offending line.
|
||||
|
||||
## 🔧 Changes
|
||||
|
||||
* **Script A takes a BER baseline before its first traffic run** (v1.2.1), so together with Script C's closing sweep the pair brackets the soak.
|
||||
* **`EN_TX_FIR`** gates the SerDes DSC scans in Script A and Script C. Default `0`: a full scan is ~10 min and both scripts do one.
|
||||
|
||||
## 📦 Downloads
|
||||
|
||||
| File | Contents |
|
||||
|---|---|
|
||||
| `Script_ABC_Blanton_V1.2.2.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
|
||||
```
|
||||
|
||||
## ⚠️ Before you run
|
||||
|
||||
* **Replace `config.ttl` with the macros.** `EN_Cold_Warm_boot` is new, and Tera Term aborts on an undefined variable rather than treating it as 0.
|
||||
* **Do not run the boot cycle with `EN_Cold_Warm_boot = 0`.** Nothing reboots, the `wait "Booting in blind mode"` underneath has no timeout, and since v1.2.2 there is no `logopen` either — so it hangs *and* leaves no log showing where. `0` is the value for the A → B → C flow, where that macro is not used.
|
||||
* **The cold path writes a raw FPGA register.** `0x480` is `ICB_CTRL_REG`; the register map carries no bit definitions for it and `0xD0000` is not documented anywhere in this repo. The BDF `0000:05:00.0` is hard-coded while `blanton_fpga_pcimem.sh` auto-detects it because it moves per unit — **check the BDF on every board before running the cold path**.
|
||||
* **Anything that parses these logs must accept both banners**, `Reboot Cycle : N` and `Power Cycle : N`. A parser that greps only the first finds zero cycles in a power-cycle log and reports nothing without complaining.
|
||||
* **`bcm_100g_dsc_cycle.sh` has not been run on hardware.** It pauses `gbsyncd0/1` for tuning and unpauses them on exit, Ctrl-C included; `-P` leaves them alone.
|
||||
* **`sleep 30` and `BER_INTERVAL` now live in three places** — Script A, Script C and `blanton_ber.sh`.
|
||||
* **BER, the DSC cycle, `blanton_traffic_linespeed` and `blanton_tr518.sh` cannot overlap.** They all take the same ports.
|
||||
* **Script 4 has no teardown**: finish it with `blanton_tr518.sh stop` **and** `systemctl stop mlucas-amm`.
|
||||
* **`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.**
|
||||
* **`FAN_SPEED` is 100.**
|
||||
|
||||
## 🔗 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:** [V1.2.1...V1.2.2](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/compare/V1.2.1...V1.2.2)
|
||||
@@ -1,7 +1,7 @@
|
||||
; =============================================================================
|
||||
; Script A for Blanton
|
||||
; Version : V1.2.1
|
||||
; Date : 2026-09-08
|
||||
; Version : V1.2.2
|
||||
; Date : 2026-09-15
|
||||
; Author : ETWen
|
||||
; =============================================================================
|
||||
; Version History:
|
||||
@@ -562,6 +562,136 @@
|
||||
; 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 2026-09-15
|
||||
; 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
|
||||
; Blanton_Script/blanton_ber.sh v1.1.0 Add port 268, the 100G uplink
|
||||
; The port list jumps 256-259 -> 270-308, so 268 (ce0) was
|
||||
; never measured. It is now its own group: BER_PORTS_200G
|
||||
; and BER_PORTS_100G, joined for the phydiag command but
|
||||
; reported apart
|
||||
; The summary gives each unit three rows - 200G ports /
|
||||
; 100G p268 / TOTAL - because unit 0 and unit 1 each have
|
||||
; their own ce0(268). A bad uplink lane averaged into 432
|
||||
; others is invisible; on its own row it is not
|
||||
; TOTAL is not a hand-added sum: every lane is folded into
|
||||
; its own group and into ALL separately, so the parts
|
||||
; cannot drift from the whole
|
||||
; !! a group that reports no lane at all is a FAILURE, not
|
||||
; a pass. Silence on the port under test is the easiest
|
||||
; way to ship a green report that measured nothing
|
||||
; Blanton_Script/blanton_ber.sh v1.1.1 Stop reading lane results as shell errors
|
||||
; init kept answering "the BCM shell rejected 'phydiag ...
|
||||
; prbs get'" on runs that were working. The check grepped
|
||||
; the WHOLE output case-insensitively for
|
||||
; ERROR|Invalid|..., and 'prbs get' prints one line per
|
||||
; lane - a lane that had not locked says PRBS Error!, which
|
||||
; matched
|
||||
; So a good run reported a hard error, and worse, the
|
||||
; function returned before the lock-count check that was
|
||||
; supposed to judge those very lanes. The operator saw a
|
||||
; failure and did NOT see which lanes were unlocked
|
||||
; Per-lane lines are now excluded from the check, the match
|
||||
; is case-sensitive, and a genuine rejection prints the
|
||||
; offending line so it can be read
|
||||
; !! this was in the file from v1.0.0. Any earlier init
|
||||
; that printed that error was probably fine, and any
|
||||
; earlier init that passed said nothing about lanes that
|
||||
; had failed to lock
|
||||
; Blanton_Script/bcm_100g_dsc_cycle.sh Created v1.2.0 - 100G link down/up cycle with DSC capture
|
||||
; Tuning once (gbsyncd pause, serdes-tx-set sys 0..7,
|
||||
; tx_taps per lane), then N cycles of: port en=0, wait,
|
||||
; port en=1, wait, phydiag dsc on both units, serdes-tx-get
|
||||
; and serdes-rx-get sys 0..7. One log per run under
|
||||
; ~/dsc_log, split by '### TEST CYCLE n/N'
|
||||
; Waiting polls 'bcmcmd ps <port>' every -p seconds up to
|
||||
; -w, and reads the state from the row whose first field
|
||||
; ends in (<port>). Asking the SDK matters here: 'port en='
|
||||
; changes the SDK, while 'show interfaces status' only
|
||||
; follows once gbsyncd has synced it - and this test pauses
|
||||
; gbsyncd
|
||||
; -d prints every command as [CMD] in grey before running
|
||||
; it, CMD_DELAY paces them, -n is a dry run that touches
|
||||
; nothing and sleeps not at all
|
||||
; !! all output is ASCII English on purpose. The DUT serial
|
||||
; console mangles UTF-8: a Chinese error message came
|
||||
; back as "ERROR: -c ? 1", which is worse than no
|
||||
; message
|
||||
; !! NOT verified on hardware
|
||||
; tools/100G_dsc_cycle.txt Created - the hand-typed command list behind that script
|
||||
; Same role as BER_Test.txt and TR518.txt: the bench
|
||||
; version of the commands, kept so the .sh can be checked
|
||||
; against what a person would actually type. Change one and
|
||||
; change the other
|
||||
; =============================================================================
|
||||
include "config.ttl"
|
||||
|
||||
|
||||
+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 +1,608 @@
|
||||
#!/bin/sh
|
||||
# =============================================================================
|
||||
# bcm_100g_dsc_cycle.sh
|
||||
#
|
||||
# Author : ETWen
|
||||
# Date : 20260909
|
||||
#
|
||||
# Version History
|
||||
# V1.0.0 20260909 Initial Version
|
||||
# V1.1.0 20260909 All runtime output is ASCII English - the DUT serial
|
||||
# console mangles UTF-8 (a Chinese error message came
|
||||
# back as "ERROR: -c ? 1"). Cycle count may be given as
|
||||
# a bare argument. Added -d to echo every command, and
|
||||
# CMD_DELAY to pace them.
|
||||
# V1.2.0 20260909 Wait on "bcmcmd ps <port>" instead of
|
||||
# "show interfaces status". The state comes from the
|
||||
# SDK, which is what "port en=" actually changes, so it
|
||||
# no longer depends on gbsyncd syncing into the DB.
|
||||
#
|
||||
# Description:
|
||||
# Link down/up cycling on the 100G uplink. After every re-link it collects a
|
||||
# SerDes DSC dump and reads the retimer back, so you can see whether the
|
||||
# tuned TX taps settle to the same place each time the link comes up.
|
||||
#
|
||||
# One run has two parts:
|
||||
# 1. Tuning -- once. pause gbsyncd -> serdes-tx-set sys 0..7
|
||||
# -> tx_taps set on four lanes of each unit
|
||||
# 2. Cycle -- repeated N times:
|
||||
# port en=0 -> wait until "ps <port>" reads !ena on both units
|
||||
# port en=1 -> wait until "ps <port>" reads up on both units
|
||||
# phydiag <port> dsc on each unit
|
||||
# serdes-tx-get / serdes-rx-get sys 0..7
|
||||
# all of it appended to one log, under a per-cycle heading
|
||||
#
|
||||
# Command source: tools/100G_dsc_cycle.txt (the hand-typed bench version).
|
||||
# Change that file and this one together.
|
||||
#
|
||||
# Deployment:
|
||||
# Script : /root/Blanton_Script/bcm_100g_dsc_cycle.sh
|
||||
# Log : ~/dsc_log/100G_dsc_cycle_test_<YYYYmmdd_HHMMSS>.log
|
||||
# One file per run, every cycle in it, split by "### TEST CYCLE n/N".
|
||||
#
|
||||
# Paths come from $HOME. Run as root (after sudo -i) and ~ is /root.
|
||||
#
|
||||
# Usage:
|
||||
# ./bcm_100g_dsc_cycle.sh # print this help
|
||||
# ./bcm_100g_dsc_cycle.sh 200 # 200 cycles
|
||||
# ./bcm_100g_dsc_cycle.sh -c 200 # same thing
|
||||
# ./bcm_100g_dsc_cycle.sh -c 200 -d # echo every command as it is issued
|
||||
# ./bcm_100g_dsc_cycle.sh -c 10 -T # skip tuning, cycle only
|
||||
# ./bcm_100g_dsc_cycle.sh -c 1 -n # dry run, print commands, touch nothing
|
||||
#
|
||||
# Exit code:
|
||||
# 0 = every cycle linked down and up as expected, and all data was collected
|
||||
# 1 = a cycle timed out waiting for link, or data was missing
|
||||
# 2 = bad argument / path
|
||||
# 3 = a required tool is missing (bcmcmd / show / blanton_barchetta_tool)
|
||||
#
|
||||
# The last line is always "### DSC_CYCLE_DONE rc=<n>", for a TTL wait to
|
||||
# key on.
|
||||
#
|
||||
# Design notes:
|
||||
# - POSIX sh. No bash, no Python.
|
||||
# - All runtime output is plain ASCII. The DUT console is not UTF-8 clean:
|
||||
# Chinese comes back as "M-^A"-style garbage, and an error you cannot read
|
||||
# is worse than no error at all. Comments are English for the same reason -
|
||||
# whoever debugs this on the bench is reading it through that console.
|
||||
# - Link state comes from "bcmcmd -n <unit> -c 'ps <port>'". Its header is
|
||||
# two stacked lines, so a column index cannot be derived from it the way
|
||||
# it can from a SONiC table. Instead the data row is found by its first
|
||||
# field ending in "(<port>)" - e.g. ce0(268) - and the state is the field
|
||||
# after it:
|
||||
# ce0(268) !ena 4 100G FD ... <- port disabled
|
||||
# ce0(268) up 4 100G FD ... <- link up
|
||||
# "down" is therefore tested as "not up", which covers !ena as well as an
|
||||
# enabled port whose link has not come back.
|
||||
# - Asking the SDK rather than "show interfaces status" matters here: "port
|
||||
# en=" changes the SDK, and the SONiC table only follows once gbsyncd and
|
||||
# orchagent have synced it into the DB. Since this test pauses gbsyncd,
|
||||
# the SONiC table was the wrong thing to wait on.
|
||||
# - bcmcmd reads stdin, and inside a while loop it will swallow the loop's
|
||||
# input. blanton_traffic_linespeed.sh hit this at v0.3.1 (only the first
|
||||
# VLAN was configured) and bcm_dsc_scan.sh hit it again at v1.3.0 (only
|
||||
# the first port was scanned). Every external command here gets
|
||||
# < /dev/null.
|
||||
# - bcmcmd exits 0 even when the diag shell rejects a command, so the DSC is
|
||||
# verified by counting "SERDES DISPLAY DIAG DATA END", and the retimer read
|
||||
# by counting sections that actually have output under them - not by exit
|
||||
# code, and not by counting headings this script prints itself.
|
||||
#
|
||||
# Cautions:
|
||||
# - !! While gbsyncd is paused the gearbox state stops being synced into the
|
||||
# DB. The wait reads the SDK directly ("ps <port>") so it is not affected,
|
||||
# but anything you check by hand with "show interfaces status" during the
|
||||
# run may be stale. Set PAUSE_GBSYNCD=0 (or -P) if that gets in the way.
|
||||
# - !! On exit, including Ctrl-C, both gbsyncd containers are unpaused again
|
||||
# so nothing is left paused. Set RESUME_GBSYNCD=0 to keep them paused.
|
||||
# - !! phydiag dsc is read-only, but port en=0/1 and tx_taps set do change
|
||||
# the hardware. Do not run this at the same time as blanton_ber.sh,
|
||||
# blanton_traffic_linespeed or blanton_tr518.sh - they take the same ports.
|
||||
# - !! NOT verified on hardware yet.
|
||||
# =============================================================================
|
||||
|
||||
set -u
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Knobs - change these for a different DUT or port, not the flow below
|
||||
# ----------------------------------------------------------------------------
|
||||
PORT=268 # bcmcmd port number, not a port name
|
||||
UNITS="0 1" # units to drive
|
||||
SYS_LANES="0 1 2 3 4 5 6 7" # blanton_barchetta_tool sys lanes, tuning
|
||||
SYS_TX="pre=-10 main=87 post=0" # TX setting applied to each of them
|
||||
|
||||
# tx_taps, one line per lane: "<unit> <lane> <main> <pre1> <post1>"
|
||||
TX_TAPS="
|
||||
0 0 31 4 13
|
||||
0 1 31 4 13
|
||||
0 2 27 4 13
|
||||
0 3 29 4 13
|
||||
1 0 29 4 13
|
||||
1 1 30 4 13
|
||||
1 2 31 4 13
|
||||
1 3 30 4 13
|
||||
"
|
||||
|
||||
TX_LANES="0 1 2 3 4 5 6 7" # retimer TX lanes read back each cycle
|
||||
RX_LANES="0 1 2 3 4 5 6 7" # retimer RX lanes read back each cycle
|
||||
|
||||
SUDO="" # set to "sudo" if not running as root
|
||||
PAUSE_GBSYNCD=1 # pause gbsyncd0/1 before tuning
|
||||
RESUME_GBSYNCD=1 # unpause again on exit, Ctrl-C included
|
||||
GBSYNCD="gbsyncd0 gbsyncd1"
|
||||
|
||||
LINK_WAIT=90 # give up waiting for a link state after this
|
||||
POLL=2 # seconds between "ps <port>" reads while waiting
|
||||
SETTLE=2 # quiet time after link up, before collecting
|
||||
CMD_DELAY=0.2 # pause after every command issued to the DUT
|
||||
|
||||
OUTDIR="${HOME:-/root}/dsc_log"
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
CYCLES=0
|
||||
DRYRUN=0
|
||||
DOTUNE=1
|
||||
DEBUG=0
|
||||
RC=0
|
||||
|
||||
usage() {
|
||||
cat >&2 << 'USAGE'
|
||||
Usage: bcm_100g_dsc_cycle.sh <cycles> [options]
|
||||
bcm_100g_dsc_cycle.sh -c <cycles> [options]
|
||||
|
||||
-c <n> how many cycles to run. May also be given as a bare argument.
|
||||
-o <dir> log directory (default: ~/dsc_log)
|
||||
-w <sec> how long to wait for a link state (default: 90)
|
||||
-p <sec> how often to re-read the port state (default: 2)
|
||||
-s <sec> quiet time after link up, before collecting (default: 2)
|
||||
-d debug: echo every command as [CMD] before running it
|
||||
-T skip tuning, go straight to the cycles
|
||||
-P leave gbsyncd alone (no pause, no unpause)
|
||||
-n dry run: print the commands, touch nothing
|
||||
-h this help
|
||||
|
||||
One log per run:
|
||||
~/dsc_log/100G_dsc_cycle_test_<YYYYmmdd_HHMMSS>.log
|
||||
|
||||
Each cycle is one "### TEST CYCLE n/N" section holding, in order: the "ps"
|
||||
output showing the port down, the same showing it up, phydiag dsc for both
|
||||
units, and the retimer serdes-tx-get / serdes-rx-get for sys 0..7.
|
||||
|
||||
Waiting for a port state is a poll, not a single read: "bcmcmd ps <port>" on
|
||||
every unit, every -p seconds, until both agree or -w seconds have passed.
|
||||
|
||||
Examples:
|
||||
./bcm_100g_dsc_cycle.sh 200
|
||||
./bcm_100g_dsc_cycle.sh 200 -d
|
||||
./bcm_100g_dsc_cycle.sh -c 20 -T -w 120
|
||||
USAGE
|
||||
exit 1
|
||||
}
|
||||
|
||||
[ $# -eq 0 ] && usage
|
||||
|
||||
# getopts stops at the first argument that is not an option, so "200 -d" would
|
||||
# leave -d unread. Parse, take the bare count, then parse whatever followed it.
|
||||
# getopts inside a function reads the function's own arguments; OPTIND is
|
||||
# global, so it has to be reset on each entry.
|
||||
PARSED=0
|
||||
parse_opts() {
|
||||
OPTIND=1
|
||||
while getopts "c:o:w:p:s:dTPnh" opt; do
|
||||
case "$opt" in
|
||||
c) CYCLES="$OPTARG" ;;
|
||||
o) OUTDIR="$OPTARG" ;;
|
||||
w) LINK_WAIT="$OPTARG" ;;
|
||||
p) POLL="$OPTARG" ;;
|
||||
s) SETTLE="$OPTARG" ;;
|
||||
d) DEBUG=1 ;;
|
||||
T) DOTUNE=0 ;;
|
||||
P) PAUSE_GBSYNCD=0; RESUME_GBSYNCD=0 ;;
|
||||
n) DRYRUN=1 ;;
|
||||
*) usage ;;
|
||||
esac
|
||||
done
|
||||
PARSED=$((OPTIND - 1))
|
||||
}
|
||||
|
||||
parse_opts "$@"
|
||||
shift "$PARSED"
|
||||
|
||||
# Allow the count as a bare argument: "... 200" == "... -c 200". That is what
|
||||
# most people type first, and answering it with an error helps nobody.
|
||||
if [ "$CYCLES" = "0" ] && [ $# -ge 1 ]; then
|
||||
case "$1" in
|
||||
-*) : ;; # an option; leave it for the second pass
|
||||
*) CYCLES="$1"; shift ;; # anything else is meant to be the count,
|
||||
esac # and the check below says so if it is not
|
||||
fi
|
||||
|
||||
# Anything after the count is options again: "200 -d -T"
|
||||
if [ $# -gt 0 ]; then
|
||||
parse_opts "$@"
|
||||
shift "$PARSED"
|
||||
fi
|
||||
|
||||
if [ $# -gt 0 ]; then
|
||||
echo "ERROR: unexpected argument '$1'" >&2
|
||||
echo " run with no argument to see the usage" >&2
|
||||
exit 2
|
||||
fi
|
||||
|
||||
case "$CYCLES" in
|
||||
''|*[!0-9]*)
|
||||
echo "ERROR: cycle count must be a positive integer (got: '$CYCLES')" >&2
|
||||
echo " try: $0 200 or $0 -c 200" >&2
|
||||
exit 2 ;;
|
||||
esac
|
||||
if [ "$CYCLES" -lt 1 ]; then
|
||||
echo "ERROR: cycle count must be at least 1 (got: $CYCLES)" >&2
|
||||
exit 2
|
||||
fi
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Colour, only when stdout is a terminal, so a redirected run stays clean
|
||||
# ----------------------------------------------------------------------------
|
||||
if [ -t 1 ] && [ -z "${NO_COLOR:-}" ]; then
|
||||
C_INFO=$(printf '\033[1;34m') # blue
|
||||
C_OK=$(printf '\033[1;32m') # green
|
||||
C_WARN=$(printf '\033[1;33m') # yellow
|
||||
C_ERR=$(printf '\033[1;31m') # red
|
||||
C_CMD=$(printf '\033[90m') # dark grey
|
||||
C_OFF=$(printf '\033[0m')
|
||||
else
|
||||
C_INFO=''; C_OK=''; C_WARN=''; C_ERR=''; C_CMD=''; C_OFF=''
|
||||
fi
|
||||
|
||||
# A dry run touches nothing, so it must not sleep either - otherwise
|
||||
# "-c 200 -n" sits there for as long as the real thing would.
|
||||
naptime() { [ "$DRYRUN" = "1" ] && return 0; [ "${1:-0}" = "0" ] && return 0; sleep "$1"; }
|
||||
|
||||
info() { printf '%s[info]%s %s\n' "$C_INFO" "$C_OFF" "$*"; }
|
||||
ok() { printf '%s[ OK ]%s %s\n' "$C_OK" "$C_OFF" "$*"; }
|
||||
warn() { printf '%s[warn]%s %s\n' "$C_WARN" "$C_OFF" "$*" >&2; }
|
||||
err() { printf '%s[ERR ]%s %s\n' "$C_ERR" "$C_OFF" "$*" >&2; }
|
||||
|
||||
# Both -d and -n print commands. During collection the whole block is
|
||||
# redirected into a temp file, so those lines would end up in the file with
|
||||
# nothing on screen. Bind fd 9 to the terminal up front and print there.
|
||||
if { [ "$DEBUG" = "1" ] || [ "$DRYRUN" = "1" ]; } && ( true > /dev/tty ) 2>/dev/null; then
|
||||
exec 9> /dev/tty
|
||||
else
|
||||
exec 9>&1
|
||||
fi
|
||||
# ':' is a special built-in in dash (the DUT's /bin/sh); a failed redirection
|
||||
# on one kills the whole shell with no message. Hence (true > /dev/tty) in a
|
||||
# subshell above - if that cannot open, only the subshell dies.
|
||||
|
||||
# Print a command the way you would type it: quote any argument that needs it,
|
||||
# so the line can be copied back to the prompt as is.
|
||||
# NOTE: sh has no local variables - every name assigned here is global. All
|
||||
# helper variables are therefore prefixed. _show_cmd used to assign "tag",
|
||||
# which silently overwrote the caller's cycle label and turned every later
|
||||
# message into "[info] [CMD] : Wait Port Link Down".
|
||||
_show_cmd() {
|
||||
_sc_tag="$1"; _sc_col="$2"; shift 2
|
||||
{
|
||||
printf '%s%s%s' "$_sc_col" "$_sc_tag" "$C_OFF"
|
||||
for a in "$@"; do
|
||||
case "$a" in
|
||||
''|*[!A-Za-z0-9_./=:,+-]*) printf " '%s'" "$a" ;;
|
||||
*) printf ' %s' "$a" ;;
|
||||
esac
|
||||
done
|
||||
printf '\n'
|
||||
} >&9
|
||||
}
|
||||
|
||||
# Every external command goes through here: never reads stdin, echoed when
|
||||
# asked, and paced by CMD_DELAY so the DUT is not hammered.
|
||||
run() {
|
||||
[ "$DEBUG" = "1" ] && [ "$DRYRUN" = "0" ] && _show_cmd '[CMD]' "$C_CMD" "$@"
|
||||
if [ "$DRYRUN" = "1" ]; then
|
||||
_show_cmd ' +' "$C_CMD" "$@"
|
||||
return 0
|
||||
fi
|
||||
"$@" < /dev/null
|
||||
_cmd_rc=$?
|
||||
naptime "$CMD_DELAY"
|
||||
return $_cmd_rc
|
||||
}
|
||||
|
||||
# Same, but discards output. Do not write "> /dev/null" at the call site or
|
||||
# the [CMD] line goes with it.
|
||||
runq() {
|
||||
[ "$DEBUG" = "1" ] && [ "$DRYRUN" = "0" ] && _show_cmd '[CMD]' "$C_CMD" "$@"
|
||||
if [ "$DRYRUN" = "1" ]; then
|
||||
_show_cmd ' +' "$C_CMD" "$@"
|
||||
return 0
|
||||
fi
|
||||
"$@" < /dev/null > /dev/null 2>&1
|
||||
_cmd_rc=$?
|
||||
naptime "$CMD_DELAY"
|
||||
return $_cmd_rc
|
||||
}
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Preflight
|
||||
# ----------------------------------------------------------------------------
|
||||
if [ "$DRYRUN" = "0" ]; then
|
||||
command -v bcmcmd > /dev/null 2>&1 || { err "not found: bcmcmd"; exit 3; }
|
||||
# -T only skips tuning; the per-cycle retimer read still needs this tool
|
||||
if [ ! -x /usr/sbin/blanton_barchetta_tool ]; then
|
||||
err "not found: /usr/sbin/blanton_barchetta_tool (tuning and the per-cycle retimer read both use it)"
|
||||
exit 3
|
||||
fi
|
||||
fi
|
||||
|
||||
# busybox sleep may not take a fraction
|
||||
if [ "$DRYRUN" = "0" ] && [ "$CMD_DELAY" != "0" ] && ! sleep "$CMD_DELAY" 2>/dev/null; then
|
||||
warn "sleep '$CMD_DELAY' not supported, falling back to 1"
|
||||
CMD_DELAY=1
|
||||
fi
|
||||
|
||||
mkdir -p "$OUTDIR" 2>/dev/null || { err "cannot create outdir: $OUTDIR"; exit 2; }
|
||||
[ -w "$OUTDIR" ] || { err "outdir not writable: $OUTDIR"; exit 2; }
|
||||
|
||||
TS=$(date '+%Y%m%d_%H%M%S')
|
||||
LOG="${OUTDIR}/100G_dsc_cycle_test_${TS}.log"
|
||||
: > "$LOG" || { err "cannot write $LOG"; exit 2; }
|
||||
|
||||
STATUS_TMP=$(mktemp) || { err "mktemp failed"; exit 2; }
|
||||
CYCLE_TMP=$(mktemp) || { err "mktemp failed"; exit 2; }
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# gbsyncd must go back the way it was found, or the container stays paused
|
||||
# ----------------------------------------------------------------------------
|
||||
PAUSED=0
|
||||
resume_gbsyncd() {
|
||||
[ "$PAUSED" = "1" ] || return 0
|
||||
[ "$RESUME_GBSYNCD" = "1" ] || return 0
|
||||
PAUSED=0
|
||||
for _rg_c in $GBSYNCD; do
|
||||
if runq $SUDO docker unpause "$_rg_c"; then
|
||||
info "gbsyncd resumed: $_rg_c"
|
||||
else
|
||||
warn "docker unpause $_rg_c failed - check it by hand"
|
||||
fi
|
||||
done
|
||||
}
|
||||
on_exit() { rm -f "$STATUS_TMP" "$CYCLE_TMP"; resume_gbsyncd; }
|
||||
on_int() {
|
||||
echo ""
|
||||
warn "interrupted by user"
|
||||
resume_gbsyncd
|
||||
printf '\n### DSC_CYCLE_DONE rc=130 (INTERRUPTED)\n' >> "$LOG"
|
||||
printf '### DSC_CYCLE_DONE rc=130 (INTERRUPTED)\n'
|
||||
rm -f "$STATUS_TMP" "$CYCLE_TMP"
|
||||
exit 130
|
||||
}
|
||||
trap on_exit EXIT
|
||||
trap on_int INT TERM
|
||||
|
||||
tee_log() { tee -a "$LOG"; }
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Link state. Find which field "Oper" is from the header row, then read that
|
||||
# field on every data row. Returns 0 only when every interface matches.
|
||||
# The table itself is left in $STATUS_TMP for the caller to print.
|
||||
# ----------------------------------------------------------------------------
|
||||
# $1 = "up" or "down". Runs "ps <port>" on every unit, leaves the combined
|
||||
# output in $STATUS_TMP for the caller to print, and returns 0 only when every
|
||||
# unit agrees.
|
||||
link_is() {
|
||||
_li_want="$1"
|
||||
: > "$STATUS_TMP"
|
||||
for _li_u in $UNITS; do
|
||||
printf '\n[unit %s] bcmcmd -n %s -c "ps %s"\n' "$_li_u" "$_li_u" "$PORT" >> "$STATUS_TMP"
|
||||
if [ "$DRYRUN" = "1" ]; then
|
||||
_show_cmd ' +' "$C_CMD" bcmcmd -n "$_li_u" -c "ps $PORT"
|
||||
printf ' ce0(%s) %s 4 100G FD (dry-run)\n' \
|
||||
"$PORT" "$([ "$_li_want" = up ] && echo 'up ' || echo '!ena')" >> "$STATUS_TMP"
|
||||
continue
|
||||
fi
|
||||
[ "$DEBUG" = "1" ] && _show_cmd '[CMD]' "$C_CMD" bcmcmd -n "$_li_u" -c "ps $PORT"
|
||||
bcmcmd -n "$_li_u" -c "ps $PORT" < /dev/null >> "$STATUS_TMP" 2>&1
|
||||
naptime "$CMD_DELAY"
|
||||
done
|
||||
|
||||
# The data row is the one whose first field ends in "(<port>)"; the state
|
||||
# is the field right after it. "down" is "not up", so !ena counts.
|
||||
awk -v port="$PORT" -v want="$_li_want" -v units="$(echo "$UNITS" | wc -w)" '
|
||||
$1 ~ ("\\(" port "\\)$") {
|
||||
n++
|
||||
if (want == "up") { if ($2 != "up") bad++ }
|
||||
else { if ($2 == "up") bad++ }
|
||||
}
|
||||
END { exit (n >= units && bad == 0) ? 0 : 1 }
|
||||
' "$STATUS_TMP"
|
||||
}
|
||||
|
||||
# $1 = wanted state (Down/up), $2 = label for the messages
|
||||
wait_link() {
|
||||
_wl_want="$1"; _wl_tag="$2"
|
||||
_wl_waited=0
|
||||
while :; do
|
||||
if link_is "$_wl_want"; then
|
||||
{
|
||||
printf '\n--- port %s after %ss ---\n' "$_wl_want" "$_wl_waited"
|
||||
cat "$STATUS_TMP"
|
||||
} | tee_log
|
||||
ok "$_wl_tag : port $_wl_want after ${_wl_waited}s"
|
||||
return 0
|
||||
fi
|
||||
[ "$_wl_waited" -ge "$LINK_WAIT" ] && break
|
||||
naptime "$POLL"
|
||||
_wl_waited=$((_wl_waited + POLL))
|
||||
done
|
||||
{
|
||||
printf '\n--- TIMEOUT waiting for port %s (%ss) ---\n' "$_wl_want" "$LINK_WAIT"
|
||||
cat "$STATUS_TMP"
|
||||
} | tee_log
|
||||
err "$_wl_tag : TIMEOUT waiting for port $_wl_want (${LINK_WAIT}s)"
|
||||
return 1
|
||||
}
|
||||
|
||||
port_en() {
|
||||
for _pe_u in $UNITS; do
|
||||
runq bcmcmd -n "$_pe_u" -c "port ${PORT} en=$1"
|
||||
done
|
||||
}
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Log header
|
||||
# ----------------------------------------------------------------------------
|
||||
{
|
||||
printf '=====================================================================\n'
|
||||
printf '100G DSC cycle test\n'
|
||||
printf ' script : bcm_100g_dsc_cycle.sh V1.2.0\n'
|
||||
printf ' started : %s\n' "$(date '+%Y-%m-%d %H:%M:%S')"
|
||||
printf ' cycles : %s\n' "$CYCLES"
|
||||
printf ' port : %s units : %s\n' "$PORT" "$UNITS"
|
||||
printf ' tuning : %s\n' "$([ "$DOTUNE" = 1 ] && echo yes || echo 'skipped (-T)')"
|
||||
printf ' tx lanes : %s\n' "$TX_LANES"
|
||||
printf ' rx lanes : %s\n' "$RX_LANES"
|
||||
printf ' link wait: %ss poll %ss settle %ss cmd delay %ss\n' \
|
||||
"$LINK_WAIT" "$POLL" "$SETTLE" "$CMD_DELAY"
|
||||
printf '=====================================================================\n'
|
||||
} >> "$LOG"
|
||||
|
||||
info "log : $LOG"
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# 1. Tuning, once
|
||||
# ----------------------------------------------------------------------------
|
||||
if [ "$DOTUNE" = "1" ]; then
|
||||
info "Tuning"
|
||||
printf '\n### TUNING %s\n' "$(date '+%Y-%m-%d %H:%M:%S')" >> "$LOG"
|
||||
|
||||
if [ "$PAUSE_GBSYNCD" = "1" ]; then
|
||||
for c in $GBSYNCD; do
|
||||
if runq $SUDO docker pause "$c"; then
|
||||
PAUSED=1
|
||||
info "gbsyncd paused: $c"
|
||||
else
|
||||
warn "docker pause $c failed (container not running?)"
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
run $SUDO /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys 0 2>&1 | tee_log
|
||||
|
||||
for l in $SYS_LANES; do
|
||||
# shellcheck disable=SC2086
|
||||
run $SUDO /usr/sbin/blanton_barchetta_tool --serdes-tx-set sys "$l" $SYS_TX 2>&1 | tee_log
|
||||
done
|
||||
|
||||
echo "$TX_TAPS" | while read -r u lane main pre1 post1; do
|
||||
[ -n "${u:-}" ] || continue
|
||||
run bcmcmd -n "$u" -c \
|
||||
" dsh -c 'phydiag ${PORT} tx_taps set lane=${lane} main=${main} pre1=${pre1} post1=${post1}' " \
|
||||
2>&1 | tee_log
|
||||
done
|
||||
|
||||
ok "Tuning done"
|
||||
fi
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# 2. Test cycles
|
||||
# ----------------------------------------------------------------------------
|
||||
n=1
|
||||
while [ "$n" -le "$CYCLES" ]; do
|
||||
tag="Test Cycle $n / $CYCLES"
|
||||
|
||||
printf '\n\n### TEST CYCLE %s/%s %s\n' "$n" "$CYCLES" \
|
||||
"$(date '+%Y-%m-%d %H:%M:%S')" >> "$LOG"
|
||||
|
||||
# ---- Disable Port ------------------------------------------------------
|
||||
info "$tag : Disable Port"
|
||||
port_en 0
|
||||
|
||||
info "$tag : Wait Port Link Down"
|
||||
wait_link down "$tag" || RC=1
|
||||
|
||||
# ---- Enable Port -------------------------------------------------------
|
||||
info "$tag : Enable Port"
|
||||
port_en 1
|
||||
|
||||
info "$tag : Wait Link up"
|
||||
if wait_link up "$tag"; then
|
||||
naptime "$SETTLE"
|
||||
else
|
||||
RC=1
|
||||
fi
|
||||
|
||||
# ---- Collect -----------------------------------------------------------
|
||||
# Written to a per-cycle temp file first, then appended. Appending to the
|
||||
# log and then re-reading it to check would mean re-reading an ever larger
|
||||
# file every round - O(n^2) over 200 cycles.
|
||||
info "$tag : Collect Data"
|
||||
: > "$CYCLE_TMP"
|
||||
for u in $UNITS; do
|
||||
{
|
||||
printf '\n--- phydiag %s dsc : unit %s ---\n' "$PORT" "$u"
|
||||
run bcmcmd -n "$u" -c "dsh -c 'phydiag ${PORT} dsc'" 2>&1
|
||||
} >> "$CYCLE_TMP"
|
||||
done
|
||||
|
||||
info "$tag : Read Retimer TX"
|
||||
for l in $TX_LANES; do
|
||||
{
|
||||
printf '\n--- serdes-tx-get sys %s ---\n' "$l"
|
||||
run $SUDO /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys "$l" 2>&1
|
||||
} >> "$CYCLE_TMP"
|
||||
done
|
||||
|
||||
info "$tag : Read Retimer RX"
|
||||
for l in $RX_LANES; do
|
||||
{
|
||||
printf '\n--- serdes-rx-get sys %s ---\n' "$l"
|
||||
run $SUDO /usr/sbin/blanton_barchetta_tool --serdes-rx-get sys "$l" 2>&1
|
||||
} >> "$CYCLE_TMP"
|
||||
done
|
||||
|
||||
cat "$CYCLE_TMP" >> "$LOG"
|
||||
|
||||
if [ "$DRYRUN" = "0" ]; then
|
||||
# bcmcmd exits 0 even when it failed, so count the end marker instead
|
||||
got=$(grep -c 'SERDES DISPLAY DIAG DATA END' "$CYCLE_TMP" 2>/dev/null || true)
|
||||
want=$(echo "$UNITS" | wc -w)
|
||||
if [ "${got:-0}" -lt "$want" ]; then
|
||||
err "$tag : got only ${got:-0}/${want} DSC dumps"
|
||||
RC=1
|
||||
fi
|
||||
|
||||
# The section headings are printed by this script, so counting them
|
||||
# only proves the loop ran. Count sections that have output under them.
|
||||
for d in tx rx; do
|
||||
case "$d" in
|
||||
tx) wantl="$TX_LANES" ;;
|
||||
rx) wantl="$RX_LANES" ;;
|
||||
esac
|
||||
got_l=$(awk -v pat="--- serdes-${d}-get sys " '
|
||||
index($0, pat) == 1 { if (insec && body) ok++; insec = 1; body = 0; next }
|
||||
/^--- / || /^### / { if (insec && body) ok++; insec = 0; next }
|
||||
insec && NF { body = 1 }
|
||||
END { if (insec && body) ok++; print ok + 0 }
|
||||
' "$CYCLE_TMP")
|
||||
want_l=$(echo "$wantl" | wc -w)
|
||||
if [ "${got_l:-0}" -lt "$want_l" ]; then
|
||||
err "$tag : retimer $(echo "$d" | tr 'a-z' 'A-Z') returned data for only ${got_l:-0}/${want_l} lanes"
|
||||
RC=1
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
n=$((n + 1))
|
||||
done
|
||||
|
||||
resume_gbsyncd
|
||||
|
||||
printf '\n### DSC_CYCLE_DONE rc=%s\n' "$RC" >> "$LOG"
|
||||
if [ "$RC" = "0" ]; then
|
||||
ok "all $CYCLES cycles done -> $LOG"
|
||||
else
|
||||
err "some cycles did not complete as expected - see $LOG"
|
||||
fi
|
||||
printf '### DSC_CYCLE_DONE rc=%s\n' "$RC"
|
||||
exit "$RC"
|
||||
@@ -1,8 +1,31 @@
|
||||
#!/usr/bin/env bash
|
||||
# =============================================================================
|
||||
# blanton_ber.sh -- SerDes BER test over every cabled port (PRBS via phydiag)
|
||||
# blanton_ber.sh -- SerDes BER test, cabled ports PLUS the 100G uplink
|
||||
# =============================================================================
|
||||
# Version History:
|
||||
# V1.1.1 2026-09-15 Fix: "the BCM shell rejected 'phydiag ... prbs get'" on
|
||||
# a run that was in fact working. The rejection check
|
||||
# grepped the WHOLE output, case-insensitively, for
|
||||
# ERROR|Invalid|... -- and 'prbs get' prints one line per
|
||||
# lane, so a lane that had not locked ("PRBS Error!")
|
||||
# matched. The command was fine; the output was data.
|
||||
# Two consequences: a good run reported a hard error, and
|
||||
# the lock-count check that was supposed to judge exactly
|
||||
# those lanes never ran. Per-lane result lines are now
|
||||
# excluded from the check, the match is case-sensitive,
|
||||
# and a real rejection prints the offending line.
|
||||
# The rejection check had been there since V1.0.0, so
|
||||
# every earlier run carried the same blind spot.
|
||||
# V1.1.0 2026-09-15 Adds port 268, the 100G uplink, which the old port list
|
||||
# deliberately skipped (it jumps 256-259 -> 270-308).
|
||||
# The per-lane table is unchanged; the summary now breaks
|
||||
# each unit into "200G ports" and "100G p268" plus a
|
||||
# TOTAL row, so the uplink cannot hide inside a 432-lane
|
||||
# average. A group that reports no lane at all counts as
|
||||
# a failure, not a pass - silence on the port under test
|
||||
# is not a result. Developed on the bench as
|
||||
# blanton_ber_test.sh and folded back over this file once
|
||||
# it was proven, so there is one BER script again.
|
||||
# V1.0.1 2026-08-28 Fix: every lane reported NA and the Port column showed
|
||||
# "NA". bcmcmd returns CRLF, and the BER is the last token
|
||||
# on its line, so the CR stayed glued to the number: it
|
||||
@@ -19,8 +42,24 @@
|
||||
# =============================================================================
|
||||
#
|
||||
# This is the WHOLE-SWITCH BER sweep: every cabled port, both lanes, PRBS-31
|
||||
# through the SerDes. Not to be confused with port_prbs_monitor.sh, which drives
|
||||
# the two 100G uplinks only and polls them continuously.
|
||||
# through the SerDes -- and, unlike blanton_ber.sh, the 100G uplink as well.
|
||||
# Not to be confused with port_prbs_monitor.sh, which drives the two 100G
|
||||
# uplinks only and polls them continuously.
|
||||
#
|
||||
# The port list is two groups:
|
||||
# BER_PORTS_200G the cabled 200G ports (432 lanes per unit)
|
||||
# BER_PORTS_100G the 100G uplink, port 268 = ce0, one per unit
|
||||
# They are measured in one phydiag pass, but the summary reports them
|
||||
# separately per unit, plus a TOTAL:
|
||||
#
|
||||
# Unit GROUP LANES PASS FAIL NA WORST BER ...
|
||||
# unit 0 200G ports 432 432 0 0 2.07e-08 PASS
|
||||
# unit 0 100G p268 4 4 0 0 1.10e-11 PASS
|
||||
# unit 0 TOTAL 436 436 0 0 2.07e-08 PASS
|
||||
# unit 1 ...
|
||||
#
|
||||
# A 100G row of "NO DATA" means the uplink reported no lane at all, and is
|
||||
# treated as a failure -- silence on the port under test is not a pass.
|
||||
#
|
||||
# Order of operations (matches tools/BER_Test.txt):
|
||||
# init phydiag <ports> prbs set p=3 arm PRBS on every lane
|
||||
@@ -51,7 +90,7 @@
|
||||
# -u|--unit <0|1|all|0,1> bcmcmd unit(s). Default: $BER_UNITS ("0 1")
|
||||
# -c|--criteria <ber> report: PASS threshold (default $BER_MAX)
|
||||
# -i|--interval <sec> start: prbsstat Interval (default $BER_INTERVAL)
|
||||
# -p|--ports <list> override the port list
|
||||
# -p|--ports <list> override the whole port list (both groups)
|
||||
# -F|--fail-only report: list only the lanes that FAIL
|
||||
# --tsv report: tab-separated (paste into Excel)
|
||||
# --raw report: also print the raw 'prbsstat Ber' output
|
||||
@@ -63,7 +102,8 @@
|
||||
#
|
||||
# Environment overrides:
|
||||
# BCMCMD_CMD=bcmcmd BER_UNITS="0 1" BER_MAX=1e-6 BER_INTERVAL=30
|
||||
# BER_PORTS="1-24,..." BER_POLY=p=3 BER_LOG_DIR=/tmp DEBUG_MODE=1
|
||||
# BER_PORTS="1-24,..." BER_PORTS_200G=... BER_PORTS_100G=268
|
||||
# BER_POLY=p=3 BER_LOG_DIR=/tmp DEBUG_MODE=1
|
||||
# =============================================================================
|
||||
|
||||
# === Config ==================================================================
|
||||
@@ -73,7 +113,18 @@ BER_UNITS="${BER_UNITS:-0 1}" # one DUT = two switch boards (0 and 1)
|
||||
# The cabled ports, in bcm logical-port numbering. Same list as
|
||||
# blanton_traffic_linespeed.sh's TL_PS_PORTS -- kept as one string so it can be
|
||||
# pasted straight from/into a manual phydiag command.
|
||||
BER_PORTS="${BER_PORTS:-1-24,40-96,112-168,184-240,256-259,270-308,310-327,342-380,382-399,414-452,454-471,486-524,526-543,558-565}"
|
||||
#
|
||||
# Note the gap: the list runs 256-259 then 270-308, so 260..269 are not in it.
|
||||
# 268 is ce0, the 100G uplink, and it is the reason this fork exists.
|
||||
BER_PORTS_200G="${BER_PORTS_200G:-1-24,40-96,112-168,184-240,256-259,270-308,310-327,342-380,382-399,414-452,454-471,486-524,526-543,558-565}"
|
||||
|
||||
# The 100G uplink. One port per unit -- unit 0 and unit 1 each have their own
|
||||
# ce0(268), so a two-unit run measures two of them. Comma-separated if more are
|
||||
# ever added; the summary treats everything in here as the "100G" group.
|
||||
BER_PORTS_100G="${BER_PORTS_100G:-268}"
|
||||
|
||||
# What actually goes on the phydiag command line. -p|--ports overrides the lot.
|
||||
BER_PORTS="${BER_PORTS:-${BER_PORTS_200G},${BER_PORTS_100G}}"
|
||||
|
||||
BER_POLY="${BER_POLY:-p=3}" # passed to 'prbs set'
|
||||
BER_INTERVAL="${BER_INTERVAL:-30}" # passed to 'prbsstat STArt Interval='
|
||||
@@ -111,6 +162,24 @@ _ber_dbg() { [ "$DEBUG_MODE" = "1" ] && echo -e "\033[90m[DEBG] $*\033[0m" >&2;
|
||||
BER_ERR_PAT="${BER_ERR_PAT:-ERROR|Failed to execute|Invalid|Syntax error|Unavailable|Unknown command}"
|
||||
BER_BENIGN_PAT="${BER_BENIGN_PAT:-polling socket timeout}"
|
||||
|
||||
# A per-lane result line -- " 185 : PRBS OK!..." from 'prbs get', or
|
||||
# " 203[1] : 5.05e-09" from 'prbsstat Ber'. These are MEASUREMENTS, never
|
||||
# shell diagnostics, and they must be kept out of the rejection check:
|
||||
# a lane that did not lock prints its own wording (PRBS Error!, and similar),
|
||||
# which a case-insensitive match on "ERROR" reads as the BCM shell refusing
|
||||
# the command. That is what turned a perfectly good run into
|
||||
# [ERR ] unit 1: the BCM shell rejected 'phydiag ... prbs get'
|
||||
# while init/start/report were in fact working -- and it skipped the
|
||||
# lock-count check that was supposed to judge those very lanes.
|
||||
BER_LANE_LINE='^[ \t]*[0-9]+(\[[0-9]+\])?[ \t]*:'
|
||||
|
||||
# _ber_shell_error <output> -- echo the offending line(s), return 0 if any
|
||||
_ber_shell_error() {
|
||||
printf '%s\n' "$1" | tr -d '\r' \
|
||||
| grep -vE "$BER_LANE_LINE" \
|
||||
| grep -E "$BER_ERR_PAT"
|
||||
}
|
||||
|
||||
# _ber_bcm <unit> <phydiag args...> -- wraps in dsh -c 'phydiag <ports> ...'
|
||||
# echoes the DUT output on stdout, returns 0 ok / 1 failed
|
||||
_ber_bcm() {
|
||||
@@ -125,11 +194,14 @@ _ber_bcm() {
|
||||
local out rc
|
||||
out=$("$BCMCMD_CMD" -n "$unit" -c "$cmd" </dev/null 2>&1); rc=$?
|
||||
printf '%s\n' "$out"
|
||||
if echo "$out" | grep -qiE "$BER_ERR_PAT"; then
|
||||
local why
|
||||
why=$(_ber_shell_error "$out")
|
||||
if [ -n "$why" ]; then
|
||||
_ber_err "unit $unit: the BCM shell rejected 'phydiag ... $*'"
|
||||
printf '%s\n' "$why" | sed 's/^/ /' >&2
|
||||
return 1
|
||||
fi
|
||||
if [ "$rc" -ne 0 ] && ! echo "$out" | grep -qiE "$BER_BENIGN_PAT"; then
|
||||
if [ "$rc" -ne 0 ] && ! printf '%s\n' "$out" | grep -qiE "$BER_BENIGN_PAT"; then
|
||||
_ber_err "unit $unit: bcmcmd exited $rc on 'phydiag ... $*'"
|
||||
return 1
|
||||
fi
|
||||
@@ -243,13 +315,32 @@ _ber_render() {
|
||||
-v FAILONLY="$BER_FAIL_ONLY" \
|
||||
-v TSV="$BER_TSV" \
|
||||
-v COLOR="$color" \
|
||||
-v SIDE="$side" '
|
||||
-v SIDE="$side" \
|
||||
-v P100="$BER_PORTS_100G" '
|
||||
function vc(v) {
|
||||
if (!COLOR) return v
|
||||
if (v == "PASS") return "\033[32m" v "\033[0m"
|
||||
if (v == "FAIL") return "\033[31m" v "\033[0m"
|
||||
return "\033[33m" v "\033[0m"
|
||||
}
|
||||
# Fold one lane into a group tally. Called once for its own group and
|
||||
# and once for ALL, so the TOTAL row is never a hand-added sum that can
|
||||
# drift away from the parts.
|
||||
function acct(g, verdict, berstr, berval, label) {
|
||||
GN[g]++
|
||||
if (verdict == "PASS") GP[g]++
|
||||
else if (verdict == "FAIL") GF[g]++
|
||||
else GNA[g]++
|
||||
if (berval >= 0 && (!(g in GW) || berval > GW[g])) {
|
||||
GW[g] = berval; GWS[g] = berstr; GWL[g] = label
|
||||
}
|
||||
}
|
||||
function emit(g, lanes) {
|
||||
lanes = GN[g] + 0
|
||||
printf "SUM %s %d %d %d %d %s %s\n", g, lanes, GP[g] + 0, GF[g] + 0, GNA[g] + 0,
|
||||
(lanes > 0 && (g in GWS)) ? GWS[g] : "-",
|
||||
(lanes > 0 && (g in GWL)) ? GWL[g] : "-" > SIDE
|
||||
}
|
||||
BEGIN {
|
||||
LIM = MAXBER + 0
|
||||
NC = 4
|
||||
@@ -258,6 +349,18 @@ _ber_render() {
|
||||
HDR[3] = "BER"; AL[3] = 1
|
||||
HDR[4] = "RESULT"; AL[4] = 1
|
||||
worst = -1; worstlane = "-"
|
||||
|
||||
# Expand the 100G list ("268" or "268,270-271") into a lookup, so a lane
|
||||
# can be put in the right group by its port number alone.
|
||||
np = split(P100, pp, /[ ,\t]+/)
|
||||
for (i2 = 1; i2 <= np; i2++) {
|
||||
if (pp[i2] == "") continue
|
||||
if (split(pp[i2], rr, "-") == 2) {
|
||||
for (j2 = rr[1] + 0; j2 <= rr[2] + 0; j2++) IS100[j2] = 1
|
||||
} else {
|
||||
IS100[pp[i2] + 0] = 1
|
||||
}
|
||||
}
|
||||
}
|
||||
# bcmcmd hands back CRLF. On the cd/traffic report the counter is followed by
|
||||
# a delta, so the CR got trimmed with the rest of the line; here the BER is
|
||||
@@ -282,6 +385,8 @@ _ber_render() {
|
||||
seen++
|
||||
n++
|
||||
PORT[n] = port; LANE[n] = lane; BERS[n] = ber
|
||||
grp = ((port + 0) in IS100) ? "P100" : "P200"
|
||||
GRP[n] = grp
|
||||
# a lane that reported something non-numeric has no usable measurement
|
||||
if (ber ~ /^[0-9]+(\.[0-9]+)?([eE][-+]?[0-9]+)?$/) {
|
||||
v = ber + 0
|
||||
@@ -290,7 +395,10 @@ _ber_render() {
|
||||
if (v > worst) { worst = v; worstlane = port "[" lane "]"; worststr = ber }
|
||||
} else {
|
||||
V[n] = "NA"; nna++
|
||||
v = -1
|
||||
}
|
||||
acct(grp, V[n], ber, v, port "[" lane "]")
|
||||
acct("ALL", V[n], ber, v, port "[" lane "]")
|
||||
}
|
||||
END {
|
||||
if (seen == 0) {
|
||||
@@ -327,19 +435,32 @@ _ber_render() {
|
||||
}
|
||||
|
||||
print ""
|
||||
printf "# lanes measured : %d\n", n
|
||||
printf "# lanes measured : %d (200G %d, 100G %d)\n", n, GN["P200"] + 0, GN["P100"] + 0
|
||||
printf "# %s %d %s %d %s %d (criteria BER < %s)\n", \
|
||||
vc("PASS"), npass + 0, vc("FAIL"), nfail + 0, vc("NA"), nna + 0, MAXBER
|
||||
if (worst >= 0)
|
||||
printf "# worst lane : %s %s\n", worstlane, worststr
|
||||
if (SIDE != "" && SIDE != "/dev/null")
|
||||
printf "SUM %d %d %d %d %s %s\n", n, npass + 0, nfail + 0, nna + 0, \
|
||||
(worst >= 0 ? worststr : "-"), worstlane > SIDE
|
||||
if (GN["P100"] + 0 == 0)
|
||||
printf "# %s the 100G port list (%s) matched no lane in this capture\n", vc("NA"), P100
|
||||
else
|
||||
printf "# 100G p%s : %s %d %s %d %s %d worst %s %s\n", P100,
|
||||
vc("PASS"), GP["P100"] + 0, vc("FAIL"), GF["P100"] + 0,
|
||||
vc("NA"), GNA["P100"] + 0,
|
||||
("P100" in GWS) ? GWS["P100"] : "-",
|
||||
("P100" in GWL) ? GWL["P100"] : "-"
|
||||
if (SIDE != "" && SIDE != "/dev/null") {
|
||||
emit("P200"); emit("P100"); emit("ALL")
|
||||
}
|
||||
exit (nfail || nna) ? 2 : 0
|
||||
}' "$log"
|
||||
}
|
||||
|
||||
# _ber_summary <stamp> -- one table for every unit, printed last
|
||||
# _ber_summary <stamp> -- one table for every unit, printed last.
|
||||
#
|
||||
# Each unit gets three rows: the 200G ports, the 100G uplink on its own, and a
|
||||
# TOTAL. Unit 0 and unit 1 each have their own ce0(268), so the 100G row is per
|
||||
# unit too -- a bad uplink on one board is what this fork exists to make
|
||||
# visible, and averaged into 432 other lanes it would not be.
|
||||
_ber_summary() {
|
||||
local stamp="$1" unit side g r y n worst=0
|
||||
g=$'\033[32m'; r=$'\033[31m'; y=$'\033[33m'; n=$'\033[0m'
|
||||
@@ -347,27 +468,41 @@ _ber_summary() {
|
||||
|
||||
echo ""
|
||||
echo "===== summary : all units ====="
|
||||
printf '%-8s %8s %8s %8s %8s %-12s %-10s %s\n' \
|
||||
"Unit" "LANES" "PASS" "FAIL" "NA" "WORST BER" "WORST LANE" "RESULT"
|
||||
printf '%-8s %-12s %7s %7s %7s %7s %-12s %-12s %s\n' \
|
||||
"Unit" "GROUP" "LANES" "PASS" "FAIL" "NA" "WORST BER" "WORST LANE" "RESULT"
|
||||
|
||||
local tag lanes pass fail na wber wlane v any=0
|
||||
local tag grp lanes pass fail na wber wlane v any=0 label
|
||||
for unit in $BER_UNITS; do
|
||||
side="$BER_LOG_DIR/berside_unit${unit}_${stamp}"
|
||||
side="$BER_LOG_DIR/bertside_unit${unit}_${stamp}"
|
||||
[ -r "$side" ] || continue
|
||||
read -r tag lanes pass fail na wber wlane < "$side" 2>/dev/null
|
||||
[ "$tag" = "SUM" ] || continue
|
||||
any=1
|
||||
if [ "${fail:-0}" -gt 0 ] || [ "${na:-0}" -gt 0 ]; then
|
||||
v="${r}FAIL${n}"; worst=2
|
||||
else
|
||||
v="${g}PASS${n}"
|
||||
fi
|
||||
printf '%-8s %8s %8s %8s %8s %-12s %-10s %b\n' \
|
||||
"unit $unit" "$lanes" "$pass" "$fail" "$na" "$wber" "$wlane" "$v"
|
||||
while read -r tag grp lanes pass fail na wber wlane; do
|
||||
[ "$tag" = "SUM" ] || continue
|
||||
any=1
|
||||
case "$grp" in
|
||||
P200) label="200G ports" ;;
|
||||
P100) label="100G p${BER_PORTS_100G}" ;;
|
||||
ALL) label="TOTAL" ;;
|
||||
*) label="$grp" ;;
|
||||
esac
|
||||
# A group with no lanes is not a pass. On the 100G row it means the
|
||||
# uplink never reported -- exactly the case worth flagging.
|
||||
if [ "${lanes:-0}" -eq 0 ]; then
|
||||
v="${y}NO DATA${n}"
|
||||
[ "$grp" = "P100" ] && worst=2
|
||||
elif [ "${fail:-0}" -gt 0 ] || [ "${na:-0}" -gt 0 ]; then
|
||||
v="${r}FAIL${n}"; worst=2
|
||||
else
|
||||
v="${g}PASS${n}"
|
||||
fi
|
||||
printf '%-8s %-12s %7s %7s %7s %7s %-12s %-12s %b\n' \
|
||||
"unit $unit" "$label" "$lanes" "$pass" "$fail" "$na" \
|
||||
"$wber" "$wlane" "$v"
|
||||
done < "$side"
|
||||
done
|
||||
[ "$any" = "1" ] || echo " (no unit produced a result)"
|
||||
echo ""
|
||||
printf 'criteria: BER < %s\n' "$BER_MAX"
|
||||
printf '100G group: port(s) %s -- one per unit\n' "$BER_PORTS_100G"
|
||||
echo ""
|
||||
return "$worst"
|
||||
}
|
||||
@@ -391,7 +526,7 @@ blanton_ber_report() {
|
||||
stamp=$(date +%Y%m%d_%H%M%S 2>/dev/null || echo now)
|
||||
for unit in $BER_UNITS; do
|
||||
log="$BER_LOG_DIR/prbsber_unit${unit}_${stamp}.log"
|
||||
side="$BER_LOG_DIR/berside_unit${unit}_${stamp}"
|
||||
side="$BER_LOG_DIR/bertside_unit${unit}_${stamp}"
|
||||
: > "$side"
|
||||
if ! _ber_bcm "$unit" "prbsstat Ber" > "$log" 2>&1; then
|
||||
_ber_err "unit $unit: 'prbsstat Ber' failed (see $log)"; worst=1; continue
|
||||
@@ -409,22 +544,24 @@ blanton_ber_report() {
|
||||
|
||||
_ber_summary "$stamp"; rc=$?
|
||||
[ "$rc" -gt "$worst" ] && worst=$rc
|
||||
rm -f "$BER_LOG_DIR"/berside_unit*_"${stamp}"
|
||||
rm -f "$BER_LOG_DIR"/bertside_unit*_"${stamp}"
|
||||
return "$worst"
|
||||
}
|
||||
|
||||
# === Help ====================================================================
|
||||
blanton_ber_help() {
|
||||
echo -e "\033[1mblanton_ber.sh - SerDes BER test over every cabled port (PRBS via phydiag)\033[0m"
|
||||
echo -e "\033[1mblanton_ber.sh - SerDes BER test: cabled 200G ports + the 100G uplink\033[0m"
|
||||
echo ""
|
||||
echo -e " Units : \033[36m$BER_UNITS\033[0m poly: \033[36m$BER_POLY\033[0m interval: \033[36m${BER_INTERVAL}s\033[0m"
|
||||
echo -e " Criteria : BER < \033[36m$BER_MAX\033[0m"
|
||||
echo -e " Ports : \033[36m$BER_PORTS\033[0m"
|
||||
echo -e " 200G : \033[36m$BER_PORTS_200G\033[0m"
|
||||
echo -e " 100G : \033[36m$BER_PORTS_100G\033[0m (ce0, one per unit -- reported on its own row)"
|
||||
echo ""
|
||||
echo -e "\033[1mSubcommands\033[0m"
|
||||
echo -e " \033[33minit\033[0m prbs set $BER_POLY + prbs get (checks every lane locked)"
|
||||
echo -e " \033[33mstart\033[0m prbsstat STArt Interval=$BER_INTERVAL"
|
||||
echo -e " \033[33mreport\033[0m prbsstat Ber -> per-lane table + PASS/FAIL + summary"
|
||||
echo -e " summary splits each unit into 200G ports / 100G p$BER_PORTS_100G / TOTAL"
|
||||
echo -e " \033[33mstop\033[0m prbsstat STOp"
|
||||
echo -e " \033[33mclear\033[0m prbs clear (disarms PRBS -- 'init' again before measuring)"
|
||||
echo -e " \033[33mhelp\033[0m"
|
||||
@@ -433,7 +570,7 @@ blanton_ber_help() {
|
||||
echo -e " \033[33m-u|--unit\033[0m <0|1|all> bcmcmd unit(s); 'all' = 0 1 (default: $BER_UNITS)"
|
||||
echo -e " \033[33m-c|--criteria\033[0m <ber> PASS threshold (default $BER_MAX)"
|
||||
echo -e " \033[33m-i|--interval\033[0m <sec> prbsstat Interval (default $BER_INTERVAL)"
|
||||
echo -e " \033[33m-p|--ports\033[0m <list> override the port list"
|
||||
echo -e " \033[33m-p|--ports\033[0m <list> override the whole port list (both groups)"
|
||||
echo -e " \033[33m-F|--fail-only\033[0m report: list only failing lanes"
|
||||
echo -e " \033[33m--tsv\033[0m report: tab-separated"
|
||||
echo -e " \033[33m--raw\033[0m report: also print the raw output"
|
||||
|
||||
@@ -34,4 +34,13 @@ BMC_USB_RUNTIME = 172800 ; Unit seconds, 172800 = 2 days
|
||||
;================================================================
|
||||
prompt_login = "sonic login:"
|
||||
prompt_sonic = "admin@sonic:~$"
|
||||
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
|
||||
@@ -0,0 +1,90 @@
|
||||
cd /usr/sbin
|
||||
sudo docker pause gbsyncd1
|
||||
sudo docker pause gbsyncd0
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys 0
|
||||
|
||||
//Tuning
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-set sys 0 pre=-10 main=87 post=0
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-set sys 1 pre=-10 main=87 post=0
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-set sys 2 pre=-10 main=87 post=0
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-set sys 3 pre=-10 main=87 post=0
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-set sys 4 pre=-10 main=87 post=0
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-set sys 5 pre=-10 main=87 post=0
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-set sys 6 pre=-10 main=87 post=0
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-set sys 7 pre=-10 main=87 post=0
|
||||
bcmcmd -n 0 -c " dsh -c 'phydiag 268 tx_taps set lane=0 main=31 pre1=4 post1=13' "
|
||||
bcmcmd -n 0 -c " dsh -c 'phydiag 268 tx_taps set lane=1 main=31 pre1=4 post1=13' "
|
||||
bcmcmd -n 0 -c " dsh -c 'phydiag 268 tx_taps set lane=2 main=27 pre1=4 post1=13' "
|
||||
bcmcmd -n 0 -c " dsh -c 'phydiag 268 tx_taps set lane=3 main=29 pre1=4 post1=13' "
|
||||
bcmcmd -n 1 -c " dsh -c 'phydiag 268 tx_taps set lane=0 main=29 pre1=4 post1=13' "
|
||||
bcmcmd -n 1 -c " dsh -c 'phydiag 268 tx_taps set lane=1 main=30 pre1=4 post1=13' "
|
||||
bcmcmd -n 1 -c " dsh -c 'phydiag 268 tx_taps set lane=2 main=31 pre1=4 post1=13' "
|
||||
bcmcmd -n 1 -c " dsh -c 'phydiag 268 tx_taps set lane=3 main=30 pre1=4 post1=13' "
|
||||
|
||||
以下Test Cycle 目標200次
|
||||
//Disable Port
|
||||
bcmcmd -n 0 -c "port 268 en=0"
|
||||
bcmcmd -n 1 -c "port 268 en=0"
|
||||
|
||||
//Wait Link Down
|
||||
bcmcmd -n 0 -c "ps 268"
|
||||
bcmcmd -n 1 -c "ps 268"
|
||||
root@sonic:~# bcmcmd -n 0 -c "ps 268"
|
||||
ps 268
|
||||
ena/ speed/ link auto STP lrn max cut loop
|
||||
port link Lns duplex scan neg? state pause discrd ops medium frame thru FEC back
|
||||
ce0(268) !ena 4 100G FD SW No Forward Untag FA Backplane 9122 No RS528
|
||||
drivshell>
|
||||
root@sonic:~# bcmcmd -n 1 -c "ps 268"
|
||||
ps 268
|
||||
ena/ speed/ link auto STP lrn max cut loop
|
||||
port link Lns duplex scan neg? state pause discrd ops medium frame thru FEC back
|
||||
ce0(268) !ena 4 100G FD SW No Forward Untag FA Backplane 9122 No RS528
|
||||
drivshell>
|
||||
root@sonic:~#
|
||||
|
||||
|
||||
//Enable Port
|
||||
bcmcmd -n 0 -c "port 268 en=1"
|
||||
bcmcmd -n 1 -c "port 268 en=1"
|
||||
|
||||
//Wait Link Up
|
||||
bcmcmd -n 0 -c "ps 268"
|
||||
bcmcmd -n 1 -c "ps 268"
|
||||
root@sonic:~# bcmcmd -n 0 -c "ps 268"
|
||||
ps 268
|
||||
ena/ speed/ link auto STP lrn max cut loop
|
||||
port link Lns duplex scan neg? state pause discrd ops medium frame thru FEC back
|
||||
ce0(268) up 4 100G FD SW No Forward Untag FA Backplane 9122 No RS528
|
||||
drivshell>
|
||||
root@sonic:~# bcmcmd -n 1 -c "ps 268"
|
||||
ps 268
|
||||
ena/ speed/ link auto STP lrn max cut loop
|
||||
port link Lns duplex scan neg? state pause discrd ops medium frame thru FEC back
|
||||
ce0(268) up 4 100G FD SW No Forward Untag FA Backplane 9122 No RS528
|
||||
drivshell>
|
||||
root@sonic:~#
|
||||
|
||||
|
||||
//Collect DSC Data
|
||||
bcmcmd -n 0 -c "dsh -c 'phydiag 268 dsc'"
|
||||
bcmcmd -n 1 -c "dsh -c 'phydiag 268 dsc'"
|
||||
|
||||
//讀Retimer TX/RX
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys 0
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys 1
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys 2
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys 3
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys 4
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys 5
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys 6
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-tx-get sys 7
|
||||
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-rx-get sys 0
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-rx-get sys 1
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-rx-get sys 2
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-rx-get sys 3
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-rx-get sys 4
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-rx-get sys 5
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-rx-get sys 6
|
||||
sudo /usr/sbin/blanton_barchetta_tool --serdes-rx-get sys 7
|
||||
Reference in New Issue
Block a user