11c4426a96
The fleet's 22:09 UK incident (a Mac-side pkill -f <log file name> matched nothing, the roll-everything script lived on and wiped a held box) and the day's two pgrep self-matches are one class. The check flags pgrep -f / pkill -f with a plain literal (every one on a line), any pgrep/pkill on a file-name shape, and ps | grep with a literal; it allows the bracket form, -x, -F pidfile, kill $(cat pidfile), a variable and a full path; 11 banned and 16 allowed shapes in its self-test; 0.15 s over the tree. The 25 pkill -f sp1-gpu-server inside bash -c bodies (which matched the calling bash) are pkill -x; the other 11 literals take the bracket form; prover-socket-check accepts both. Row R in the record; the CLAUDE.md rule names the check and covers pkill and file names. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
68 lines
6 KiB
PowerShell
68 lines
6 KiB
PowerShell
# Published WITHOUT --stop-miners: the beside-the-miner pair (the 5090 mining at full rate on the same card).
|
|
# Prover floor (5 October 2026): the peak GPU memory and the time of one compressed shard proof through the PATCHED
|
|
# sp1-gpu-server (/opt/igneum-floor/home/.sp1/bin, reached by HOME=/opt/igneum-floor/home: the SDK spawns the
|
|
# server it finds under $HOME/.sp1/bin, sp1-cuda-6.8.1/src/server.rs) on PC 2's RTX 5090, the miners STOPPED by the
|
|
# job (--stop-miners) and the live prover switched off for the run (its server would otherwise own the socket).
|
|
# Every point: every server killed and its socket unlinked, a 1-s nvidia-smi sampler, one `--mode compressed
|
|
# --shard 0` of the pv1 host (/opt/igneum-pv1, the UNPATCHED SDK and verifier: its VERIFIED is the unpatched
|
|
# verifier's word on the patched server's proof), the peak, the time, the FLOOR lines the server prints.
|
|
# The point list comes from the FLOOR_POINTS environment the job carries, else the default sweep below.
|
|
$ErrorActionPreference = 'Continue'
|
|
$urlFile = if ($env:IGNEUM_APP_DIR) { Join-Path $env:IGNEUM_APP_DIR 'app.url' } else { Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' }
|
|
if (-not (Test-Path $urlFile)) { $urlFile = Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' }
|
|
$base = (Get-Content $urlFile -Raw).Trim().TrimEnd('/')
|
|
function Stamp { (Get-Date).ToUniversalTime().ToString('yyyy-MM-ddTHH:mm:ssZ') }
|
|
function Prove($on) { try { (Invoke-RestMethod -Method Post -Uri "$base/api/prove" -ContentType 'application/json' -Body (@{on=$on} | ConvertTo-Json -Compress) -TimeoutSec 10) | ConvertTo-Json -Compress } catch { "error: $_" } }
|
|
"RESULT start $(Stamp) prover off for the run: $(Prove $false)"
|
|
Start-Sleep -Seconds 45
|
|
"RESULT gpus $(Stamp) $((& nvidia-smi --query-gpu=index,name,memory.used,memory.total,utilization.gpu,power.draw --format=csv,noheader,nounits 2>$null) -join ' | ')"
|
|
$job = $env:IGNEUM_JOB_DIR; if (-not $job) { $job = Join-Path $env:TEMP 'igneum-floor-measure' }; New-Item -ItemType Directory -Force -Path $job | Out-Null
|
|
function WslPath($p) { $w = (& wsl.exe -d Ubuntu-24.04 -u root -- wslpath -a ($p -replace '\\', '/') 2>$null); if ($w) { ($w -replace "`0", '').Trim() } else { '/mnt/c' + ($p.Substring(2) -replace '\\', '/') } }
|
|
$jobW = WslPath $job
|
|
$kitFile = Join-Path $env:LOCALAPPDATA 'igneum\app\jobs\chain-pc2-pv1c\block-83616.json'
|
|
if (-not (Test-Path $kitFile)) { Write-Output "RESULT kit missing: $kitFile; republish the fetch after any app update (C32)"; exit 2 }
|
|
$emptyW = WslPath $kitFile
|
|
$points = if ($env:FLOOR_POINTS) { $env:FLOOR_POINTS } else { 'run m12 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=12;run m12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12;run me26 "$V1" SP1_GPU_ELEMENT_THRESHOLD=67108864;run me26 "$EMPTY" SP1_GPU_ELEMENT_THRESHOLD=67108864' }
|
|
$bash = @'
|
|
set -uo pipefail
|
|
export PATH="$HOME/.cargo/bin:$PATH"
|
|
CUDA_DIR="$(ls -d /usr/local/cuda-12.* 2>/dev/null | sort -V | tail -1 || true)"; [ -n "$CUDA_DIR" ] && export PATH="$CUDA_DIR/bin:$PATH" && export LD_LIBRARY_PATH="$CUDA_DIR/lib64:/usr/lib/wsl/lib:${LD_LIBRARY_PATH:-}"
|
|
stamp() { date -u +%Y-%m-%dT%H:%M:%SZ; }
|
|
JOB='JOBW_PLACEHOLDER'; H=/opt/igneum-pv1/igneum-prove-host; FX="/root/igneum-prove-pv1/proving/fixtures"
|
|
FLOORHOME=/opt/igneum-floor/home; SRV=$FLOORHOME/.sp1/bin/sp1-gpu-server
|
|
EMPTY='EMPTY_PLACEHOLDER'; V1="$FX/fees-v1-shards2.json"; FULL="$FX/block-338-shard1.json"; ONE="$FX/block-56-transfers.json"
|
|
[ -x "$SRV" ] || { echo "RESULT measure_failed no patched server at $SRV"; exit 2; }
|
|
[ -x "$H" ] || { echo "RESULT measure_failed no pv1 host at $H"; exit 2; }
|
|
echo "RESULT patched_server sha256=$(sha256sum $SRV | cut -c1-64) version=$($SRV --version 2>/dev/null) host=$(sha256sum $H | cut -c1-16)"
|
|
echo "RESULT live_server sha256=$(sha256sum /root/.sp1/bin/sp1-gpu-server | cut -c1-16) untouched"
|
|
pkill -x sp1-gpu-server 2>/dev/null; sleep 2; rm -f /tmp/sp1-cuda-*.sock
|
|
echo "RESULT idle_mib $(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -1)"
|
|
run() { # name fixture env...
|
|
local name="$1" fx="$2"; shift 2
|
|
local tag="$name-$(basename $fx .json)"
|
|
pkill -x sp1-gpu-server 2>/dev/null; sleep 2; rm -f /tmp/sp1-cuda-*.sock
|
|
local csv="$JOB/smi-$tag.csv" log="$JOB/log-$tag.txt"
|
|
nvidia-smi --query-gpu=timestamp,memory.used,utilization.gpu --format=csv,noheader,nounits -l 1 > "$csv" 2>/dev/null &
|
|
local SMI=$!
|
|
local t0=$(date +%s)
|
|
env HOME=$FLOORHOME SP1_PROVER=cuda RUST_LOG=off SP1_GPU_FLOOR_LOG=1 "$@" $H "$fx" --mode compressed --shard 0 --out "$JOB/res-$tag.json" > "$log" 2>&1
|
|
local rc=$?
|
|
local wall=$(( $(date +%s) - t0 ))
|
|
pkill -x sp1-gpu-server 2>/dev/null; sleep 1; kill $SMI 2>/dev/null; sleep 1; rm -f /tmp/sp1-cuda-*.sock
|
|
local peak=$(awk -F', *' '{ if ($2+0 > m) m=$2+0 } END { print m+0 }' "$csv")
|
|
local n=$(wc -l < "$csv")
|
|
local line=$(grep -E "^RESULT compressed shard" "$log" | tail -1 | sed -E 's/.*prove ([0-9.]+) s, proof ([0-9]+) bytes, verify ([0-9.]+) s, ([A-Z ]+);.*/prove_s=\1 bytes=\2 verify_s=\3 \4/')
|
|
local cyc=$(grep -E "^RESULT execute shard" "$log" | tail -1 | sed -E 's/.*: ([0-9]+) cycles.*/\1/')
|
|
local err=$(grep -iE "error|panick|out of memory|OOM|unsupported" "$log" | grep -v "^FLOOR" | head -1 | cut -c1-200)
|
|
echo "RESULT floor cfg=$name fixture=$(basename $fx .json) peak_mib=$peak samples=$n wall_s=$wall cycles=${cyc:-na} ${line:-no_result} exit=$rc env='$*' ${err:+err=$err}"
|
|
grep -E "^FLOOR" "$log" | sed "s/^/RESULT floorline cfg=$name fixture=$(basename $fx .json) /" | head -40
|
|
}
|
|
POINTS_PLACEHOLDER_BASH
|
|
pkill -x sp1-gpu-server 2>/dev/null; sleep 1; rm -f /tmp/sp1-cuda-*.sock
|
|
echo "RESULT measure_end $(stamp)"
|
|
'@
|
|
$bash = $bash.Replace('JOBW_PLACEHOLDER', $jobW).Replace('EMPTY_PLACEHOLDER', $emptyW).Replace('POINTS_PLACEHOLDER_BASH', ($points -replace ';', "`n"))
|
|
$bashFile = Join-Path $job 'measure.sh'
|
|
[IO.File]::WriteAllText($bashFile, ($bash -replace "`r`n", "`n"), (New-Object System.Text.UTF8Encoding $false))
|
|
& wsl.exe -d Ubuntu-24.04 -u root -- bash (WslPath $bashFile) 2>&1 | ForEach-Object { ($_ -replace "`0", '') }
|
|
"RESULT end $(Stamp) prover back on: $(Prove $true)"
|