diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md index 0fb15bb..ace8ca7 100644 --- a/ARCHITECTURE.md +++ b/ARCHITECTURE.md @@ -120,6 +120,7 @@ Blanton_TTL_Script/ │ ├── Blantons_FPGA_Registers_draft.docx # 同上，客戶原始 docx │ ├── Blantons_FPGA_Registers_Map_draft.xlsx │ ├── Blantons_PCIe_AER_and_DDR_EDAC_checks.pdf # AER / EDAC 檢查點依據 +│ ├── Blanton_Test_Flow.drawio # A/B/C + 熱安規四支的測試流程圖（draw.io） │ ├── LTC2980_channel_map.csv # 9 個 settings/*.conf 合併：Board,CONN,Ch,NetName,Vnom（144 列） │ ├── TTL_Script_Blanton_Status_20260814.xlsx │ └── TTL_Script_Blanton_Status_20260817.xlsx # ⭐ 最新：三支腳本逐項 Status（OK / On-Going + Owner） @@ -152,6 +153,7 @@ Blanton_TTL_Script/ └── src/ └── Script_ABC_Blanton/ # ← Tera Term 的工作目錄（整包給測試員） │ + ├── 4_Blanton_Script_thermal_safety.ttl # 熱 / 安規：獨立跑，不接 A→B→C ├── config.ttl # 全域設定：testcase 名、EN_Margin / EN_log、三個 prompt 字串 ├── 1_Blanton_Script_A.ttl # Pre-test：登入 → 對時 → source 工具 → 清 AER → 抓基線 ├── 2_Blanton_Script_B.ttl # Stress：開壓力程序 → while 1 每輪抓 fan/temp/margin @@ -355,9 +357,10 @@ 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` V1.1.2 | 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 → **一輪流量基線** → `show uptime` | -| **Script B（Stress）** | `2_Blanton_Script_B.ttl` | `mlucas-avx2 -cpu 0:15` + `bgctl run` 的 `memtester` / SSD / USB 壓力 + BMC DDR（`bmc-manager run memtester`）→ BMC USB net test（探測 cdc_ncm 介面，`systemd-run` 掛 4 小時 ping）→ 啟動 mgmt ping 監控 → **啟動 NFC 輪詢** → `jobs` / `bgctl list` → traffic（依 `SWB_UNIT`）→ `while 1` 每輪完整 PMON + margin | -| **Script C（Post-test）** | `3_Blanton_Script_C.ttl` | `kill $(jobs -p)` + `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` → `ip -s link show eth0/eth1` → `cat` mlucas log → **NFC `report`** → traffic `stop` + `report` → **BER 掃描**（依 `SWB_UNIT`）→ NVMe 健康 → `show reboot-cause` / `uptime` → **job log 複製到 USB（帶時戳）** → `hw-test-session finish` | +| **Script A（Pre-test）** | `1_Blanton_Script_A.ttl` V1.1.4 | 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` | `mlucas-avx2 -cpu 0:15` + `bgctl run` 的 `memtester` / SSD / USB 壓力 + BMC DDR（`bmc-manager run memtester`）→ BMC USB net test（探測 cdc_ncm 介面，`systemd-run` 掛 4 小時 ping）→ 啟動 mgmt ping 監控 → **啟動 NFC 輪詢** → `jobs` / `bgctl list` → traffic（依 `SWB_UNIT`）→ `while 1` 每輪 PMON + `bgctl list`/`jobs` + `pause 60`（**V1.1.4 起 margin 不在迴圈內**）| +| **Script C（Post-test）** | `3_Blanton_Script_C.ttl` | `kill $(jobs -p)` + `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` → `ip -s link show eth0/eth1` → `cat` mlucas log → **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` | | **SWB loopback 流量** | `blanton_traffic_linespeed [-u 0\|1\|all]` | `init`（VLAN 30..137，成對 `cdN`/`cdN+32`）→ `clear` → `start`（`tx 100 length=512`）→ `stop` → `report`（per-pair TX/RX 交叉比對 PASS/FAIL）；另有 `ps`（link/speed）與 `run`（一條龍）。**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 [data]`、`fpga_rescan` | pcimem 打 `resource0` + BAR 相對 offset，32-bit word；BDF 於 source 時自動偵測；`pmc/icb/swb0/swb1_fpga` 走 VSPI 窗口 | | **CB I2C / PMBus** | `cb_i2c_init/scan/read/write`、`cb_pmbus_read/write/linear16` | FPGA F3 OpenCores master，**讀用 Repeated START**（SMBus/PMBus 裝置必需） | @@ -801,6 +804,14 @@ margin status、全部 VRM 軌的 Vin/Vout/Iout/Temp、CB + ICB 溫感讀值， **`sleep 120` 的方向還沒驗證** —— 若 `tr 518` 的流量是有時限的（參數含 `runtime=1`、 `CheckDataTime=200`），等 120 秒可能量到已經降下來的值，要上機比對 0s / 30s / 120s 三次； TTL 尚未呼叫它。 +- **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 + （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。 diff --git a/CLAUDE.md b/CLAUDE.md index 0df8479..024aa77 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -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（2026-08-30）**：Script A 為 **V1.1.3**（A 集中記錄 A/B/C 三支的變更）。涵蓋 +**目前狀態（2026-08-31）**：Script A 為 **V1.1.4**（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 @@ -23,7 +23,10 @@ TR518 負載（`blanton_tr518.sh`，**TTL 尚未接**）、SWB 軌功耗（`TH6_ Script A 開頭會先收掉前一輪殘留（`hw-test-session finish` + `bgctl reset/stop --all`）， 再 `bgctl list` 確認沒有 job 留著佔資源。 NFC tag 讀取由 `nfc_polling.sh` 背景輪詢（A 做基線、B 起、C 停並 report）。 -最後一次發布是 **V1.1.2**；SWB 的 I2C 通道與位址已於 2026-08-19 上機驗證。 +另有 **`4_Blanton_Script_thermal_safety.ttl`**（熱 / 安規，**獨立跑不接 A→B→C**，滿載後每分鐘 +取 PMON + 兩片 SWB 的軌功耗；**沒有收尾段**，中斷後要手動 `blanton_tr518.sh stop`）。 +流程圖：`docs/Blanton_Test_Flow.drawio`。 +最後一次發布是 **V1.1.3**；SWB 的 I2C 通道與位址已於 2026-08-19 上機驗證。 margin 的 `VNOM` 已於 2026-08-30 改為 Blanton 實測中位數（144 條軌中 86 條上調 0.8~2.5%）。 交付用 `./publish/publish.sh` 打包。 @@ -219,6 +222,11 @@ Tera Term 連 COM port (115200-8-N-1) - ⚠️ **ICB/PDB 一律走 VI2C（`blanton_icb_vi2c.sh`），不要走 VSPI**：VSPI ~18 ms/reg 會讓 I2C byte 相間隔拉到 ~50 ms，踩中 SMBus 25–35 ms timeout，裝置直接 NACK。實測全掃 9.4 s vs 34.0 s。 - ⚠️ **I2C 讀一律 Repeated START**（不是 STOP + START），否則 PMBus/SMBus 裝置（VRM、EFUSE）不理。 +- ⚠️ **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)` +- ⚠️ **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 同時移動「看到的數字」和「實際打出去的電壓」。**跨這個日期的 margin log 不能直接互比。** diff --git a/docs/Blanton_Test_Flow.drawio b/docs/Blanton_Test_Flow.drawio new file mode 100644 index 0000000..f16441d --- /dev/null +++ b/docs/Blanton_Test_Flow.drawio @@ -0,0 +1,172 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/docs/release-notes/v1.1.4.md b/docs/release-notes/v1.1.4.md new file mode 100644 index 0000000..19ac72d --- /dev/null +++ b/docs/release-notes/v1.1.4.md @@ -0,0 +1,61 @@ +# v1.1.4 — A thermal and safety run that loads the box and watches the rails + +## ✨ New features + +**`4_Blanton_Script_thermal_safety.ttl`** +* A **standalone** script — it is not part of the A → B → C chain and is not started by any of them. Run it on its own when the question is thermal or safety rather than functional. +* Brings the DUT up the same way Script A does (login, session reset, fan speed, `wait_init`, DUT inventory, BMC, PCIe error clear, `pcie_bus`, PMON, dmesg), then loads it: `mlucas-avx2 -cpu 0:15` in the background and `blanton_tr518.sh start` on the data plane. +* Then loops every minute: platform data, **both switch boards' rail power** via `TH6_SWB0/1_power_readback.sh`, and `bgctl list` / `jobs`. That is the point of the script — power per rail under sustained full load, sampled over hours. +* **It has no teardown.** When you interrupt it the DUT is still in `port cd lb=mac`, `l2 learn off` and `test mode nr=yes`, and `mlucas-avx2` is still running. Run `blanton_tr518.sh stop` and `kill $(jobs -p)` before anything else uses the box — nothing in `show interfaces status` reveals the leftover state. +* **It cannot share a DUT with Script B.** Both take over the `cd` ports. + +**Test flow diagram** +* `docs/Blanton_Test_Flow.drawio` draws all four scripts side by side, with the config flags that change each step marked, the one real `goto` in Script B drawn, and the manual handoffs between A → B → C shown as such. + +## 🐛 Bug fixes + +**The soak loop spent most of its minute reading margin** +* Script B's per-round loop is meant to be a quick sample. `margin_status_all.sh` walks nine LTC2980s over I2C and dominated the round. The scan moved to Script C, which takes it once before `show uptime`. +* **The trade-off is real and worth knowing**: margin is now only measured at the start (Script A) and the end (Script C). Drift that happens *during* the soak is no longer visible. + +**`hw-test-session finish` ran from inside the session's own shell** +* Script C now sends `exit` and waits for `Script done` first, so `finish` runs in the login shell that opened the session. + +**The new script arrived with LF line endings** +* Every other `.ttl` in the repo is CRLF, and `.gitattributes` marks `*.ttl` as `-text` — whatever is committed is exactly what Tera Term gets. Converted to CRLF to match. + +## 📦 Downloads + +| File | Contents | +|---|---| +| `Script_ABC_Blanton_V1.1.4.zip` | The full Tera Term working directory, including `Blanton_Script/` to copy onto the DUT | + +**After copying to the DUT:** + +```bash +chmod +x ~/Blanton_Script/*.sh # see below +grep -rlU $'\r' ~/Blanton_Script # expect no output +``` + +`blanton_ber.sh`, `nfc_polling.sh`, `blanton_tr518.sh` and the two `TH6_SWB*_power_readback.sh` are invoked through `./` or `~/`, so they need the execute bit along with `bmc_monitor.sh` and `usb_target.sh` — neither git nor a Windows/USB copy carries it reliably. + +## ⚠️ Before you run + +* **Script 4 leaves the switch loaded and looped back.** Always finish with `blanton_tr518.sh stop`. If the next test starts without it, traffic and BER results are meaningless and nothing warns you. +* **Do not run Script 4 and Script B on the same DUT.** Same ports, same L2 settings. +* **Margin is no longer sampled during the soak** — only Script A (start) and Script C (end). +* **Re-baseline your margin limits if you have not already**: `VNOM` became the measured median in v1.1.3, which moved both the deviation % and the margin window. +* **These three cannot share the switch**: `blanton_ber.sh`, `blanton_tr518.sh`, `blanton_traffic_linespeed`. +* **PRBS takes the links down** while `blanton_ber.sh` is armed. +* **`ce0` keeps circulating until you stop it.** +* **Two numbers must stay in step**: Script C's `sleep 30` and `blanton_ber.sh`'s `BER_INTERVAL`. +* **`FAN_SPEED` is 100** — relevant here more than anywhere: a thermal run at full fan is not the same test as one at 30%. +* **The three items listed as unverified in v1.1.0 are still unverified**: the `ce0` ingress mirror, the 120s settle in `blanton_tr518.sh`, and `test mode nr=no` on stop. The settle matters most for this release — Script 4 depends on `tr 518` still driving traffic minutes after it was started. + +## 🔗 Links + +* [Blanton_Test_Flow.drawio](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/src/branch/main/docs/Blanton_Test_Flow.drawio) — the four scripts side by side +* [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:** [V1.1.3...V1.1.4](https://etgit.et-wen.com/etwen/Blanton_TTL_Script/compare/V1.1.3...V1.1.4) diff --git a/src/Script_ABC_Blanton/1_Blanton_Script_A.ttl b/src/Script_ABC_Blanton/1_Blanton_Script_A.ttl index 691d74e..66c945f 100644 --- a/src/Script_ABC_Blanton/1_Blanton_Script_A.ttl +++ b/src/Script_ABC_Blanton/1_Blanton_Script_A.ttl @@ -1,7 +1,7 @@ ; ============================================================================= ; Script A for Blanton -; Version : V1.1.3 -; Date : 2026-08-30 +; Version : V1.1.4 +; Date : 2026-08-31 ; Author : ETWen ; ============================================================================= ; Version History: @@ -178,6 +178,29 @@ ; board at comboA, which this change deleted - all 9 ; boards would have failed with "Profile not found" ; docs/LTC2980_channel_map.csv Regenerated (tools/gen_channel_map.sh) - it is output +; V1.1.4 2026-08-31 4_Blanton_Script_thermal_safety.ttl Add the thermal / safety run - a STANDALONE script, +; not part of the A -> B -> C chain +; Script A style setup (login, session, fan, wait_init, +; DUT info, BMC, PCIe clear, pcie_bus, pmon, dmesg) +; then FULL LOAD: mlucas-avx2 -cpu 0:15 in the +; background + blanton_tr518.sh start +; then while 1: setup_pmon + TH6_SWB0/SWB1 power +; readback + bgctl list + jobs, pause 60 +; !! no teardown section: after you interrupt it the +; unit is still on port cd lb=mac / l2 learn off / +; test mode nr=yes - run blanton_tr518.sh stop +; !! it drives the same ports as traffic and BER, so it +; cannot share a DUT with Script B +; ScriptB Drop the margin scan from the soak loop +; The loop is a fast per-minute sample; margin_status +; walks 9 LTC2980 over I2C and dominated the round +; ScriptC Take the margin scan instead, once, before uptime +; Trade-off: no margin drift DURING the soak any more, +; only a start (Script A) and end (Script C) reading +; ScriptC exit + wait "Script done" before hw-test-session +; finish - leaves the session shell first, so finish +; runs in the login shell that opened it +; docs/Blanton_Test_Flow.drawio Add the A/B/C + thermal flow diagram ; ============================================================================= include "config.ttl" diff --git a/src/Script_ABC_Blanton/2_Blanton_Script_B.ttl b/src/Script_ABC_Blanton/2_Blanton_Script_B.ttl index 4332cb0..6187b32 100644 --- a/src/Script_ABC_Blanton/2_Blanton_Script_B.ttl +++ b/src/Script_ABC_Blanton/2_Blanton_Script_B.ttl @@ -174,9 +174,5 @@ while 1 sendln "bgctl list" wait prompt_sonic_root sendln "jobs" - ; ========== Check Margin ========== - if EN_Margin = 1 then - include "utils/show_margin_status.ttl" - endif pause 60 endwhile diff --git a/src/Script_ABC_Blanton/3_Blanton_Script_C.ttl b/src/Script_ABC_Blanton/3_Blanton_Script_C.ttl index 7ead29b..4df7a0e 100644 --- a/src/Script_ABC_Blanton/3_Blanton_Script_C.ttl +++ b/src/Script_ABC_Blanton/3_Blanton_Script_C.ttl @@ -184,6 +184,11 @@ sendln "/usr/sbin/smartctl -x /dev/nvme0" wait prompt_sonic_root sendln "show reboot-cause" +; ========== Check Margin ========== +if EN_Margin = 1 then + include "utils/show_margin_status.ttl" +endif + ; ========== Show Power on uptime ========== wait prompt_sonic_root sendln "show uptime" @@ -219,6 +224,9 @@ sendln cmd ; ========== HW Test Session ========== wait prompt_sonic_root +sendln "exit" +wait "Script done" +wait prompt_sonic_root sendln "hw-test-session finish" wait prompt_sonic_root sendln "bgctl reset --yes" diff --git a/src/Script_ABC_Blanton/4_Blanton_Script_thermal_safety.ttl b/src/Script_ABC_Blanton/4_Blanton_Script_thermal_safety.ttl new file mode 100644 index 0000000..6742658 --- /dev/null +++ b/src/Script_ABC_Blanton/4_Blanton_Script_thermal_safety.ttl @@ -0,0 +1,158 @@ +include "config.ttl" + +flushrecv +;================================================================ +; Log File Creation +;================================================================ +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 strTestcase str_starttime + logopen filename 0 1 1 1 +endif + +; ========== Root Login ========== +wait prompt_login +sendln "admin" +wait "Password:" +sendln "YourPaSsWoRd" +wait prompt_sonic +sendln "sudo -i" + +; ========== Pre Setting ========== +; Make log directory +wait prompt_sonic_root +sendln "mkdir ./logs" + +; Setting System Time +getdate datestr +gettime timestr +sprintf2 cmd 'sudo date -s "%s %s"' datestr timestr +sendln cmd + +;Stress log clear +wait prompt_sonic_root +sendln "rm /host/hw-eval/jobs/*" + +; ========== HW Test Session ========== +; Clear session +wait prompt_sonic_root +sendln "hw-test-session finish" +wait prompt_sonic_root +sendln "bgctl reset --yes" +wait prompt_sonic_root +sendln "bgctl stop --all" +wait prompt_sonic_root +sendln "bgctl list" + +wait prompt_sonic_root +sendln "hw-test-session start" +wait prompt_sonic_root +sendln "hw-test-session log" +wait prompt_sonic_root +sendln "hw-test-session status" + +; ========== FAN SPEED ========== +wait prompt_sonic_root +sendln "echo 18-0020 > /sys/bus/i2c/drivers/max31790/unbind" +wait prompt_sonic_root +sendln "sleep .5" +wait prompt_sonic_root +sendln "echo 18-0020 > /sys/bus/i2c/drivers/max31790/bind" +wait prompt_sonic_root +sendln "echo 25-0020 > /sys/bus/i2c/drivers/max31790/unbind" +wait prompt_sonic_root +sendln "sleep .5" +wait prompt_sonic_root +sendln "echo 25-0020 > /sys/bus/i2c/drivers/max31790/bind" + +wait prompt_sonic_root +sprintf2 fan_ctrl_cmd 'fan-speed-control.sh %d' FAN_SPEED +sendln fan_ctrl_cmd + +wait "Set all configured fan channels to" +sendln "y" + +; ========== Wait DUT Init ========== +include "utils/wait_init.ttl" + +; ========== DUT Info ========== +wait prompt_sonic_root +sendln "show boot" +wait prompt_sonic_root +sendln "show version" +wait prompt_sonic_root +sendln "fwutil show status" +wait prompt_sonic_root +sendln "show system-memory" +wait prompt_sonic_root +sendln "show service" +wait prompt_sonic_root +sendln "show platform syseeprom" +wait prompt_sonic_root +sendln "show platform ssdhealth" +wait prompt_sonic_root +sendln "qfx5252-tpm-version" +wait prompt_sonic_root +sendln "/usr/sbin/nvme smart-log -H /dev/nvme0" +wait prompt_sonic_root +sendln "/usr/sbin/smartctl -x /dev/nvme0" + +; ========== BMC version ========== +;wait prompt_sonic_root +;sendln "bmc-manager run 'cat /etc/issue'" +wait prompt_sonic_root +sendln "bmc-first-enroll" +wait prompt_sonic_root +sendln "bmc-manager version" +wait prompt_sonic_root +sendln "bmc-manager status" + +; ========== CLEAR PCIE Error ========== +include "utils/show_pcie_error_reg_TH6_SWB0.ttl" +include "utils/show_pcie_error_reg_TH6_SWB1.ttl" +include "utils/show_pcie_error_reg_FPGA.ttl" +include "utils/show_pcie_error_reg_BMC.ttl" +include "utils/show_pcie_error_reg_DDR.ttl" +include "utils/show_pcie_error_reg_I210.ttl" +include "utils/show_pcie_error_reg_SSD.ttl" + +wait prompt_sonic_root +sendln "/usr/sbin/ras-mc-ctl --summary" + +; ========== Check PCIE tree + PCIE link status + GET PCIE bandwidth Test ========== +include "utils/pcie_bus.ttl" + +; ========== TAKE DATA ========== +include "utils/setup_pmon.ttl" +include "utils/show_dmesg.ttl" + +; ========== Full Load ========== +; AMD CPU STRESS TEST +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 &" + +; TR518 TEST +wait prompt_sonic_root +sendln "~/Blanton_Script/blanton_tr518.sh start" + +while 1 + ; Base info polling + include "utils/setup_pmon.ttl" + + ; TH6 Power Polling + wait prompt_sonic_root + sendln "~/Blanton_Script/TH6_SWB0_power_readback.sh" + wait prompt_sonic_root + sendln "~/Blanton_Script/TH6_SWB1_power_readback.sh" + + ; Background jobs Check + wait prompt_sonic_root + sendln "bgctl list" + wait prompt_sonic_root + sendln "jobs" + pause 60 +endwhile