miner/.gitea/workflows/bench.yaml

---
# GPU hashrate and parity measurement on a fleet mining host (quantus/miner#2).
#
# Runner containers on the GPU hosts have no device passthrough (gongfoo gives
# them `devices: None`), so the benchmark cannot run inside the runner. The
# binary is built on a runner and executed on the host over ssh as gitea_ci,
# which has the GPU device nodes (0666) and the Vulkan ICD, exactly like the
# miner. The host's quantus-miner.service is stopped for the window and started
# again afterwards, under a trap, so a failed run cannot leave the host idle.
#
# Benjy (4090, dedicated) is the reference card; beast (2x 5090) also serves
# inference and is only benchmarked by manual dispatch.
name: bench

on:
  workflow_dispatch:
    inputs:
      host:
        description: mining host to measure
        default: benjy.hanzalova.internal
        type: choice
        options:
          - benjy.hanzalova.internal
          - quadbrat.hanzalova.internal
          - beast.hanzalova.internal
      duration_secs:
        description: seconds per timed window
        default: "30"
      runs:
        description: timed windows (median reported)
        default: "5"
      batch_size:
        description: nonces per GPU batch
        default: "1000000"
      workers:
        description: worker threads (one per card)
        default: "1"
  pull_request:
    paths:
      - crates/engine-gpu/**
      - crates/engine-cpu/**
      - crates/pow-core/**
      - crates/miner-service/**
      - crates/bench-harness/**
      - Cargo.lock
      - .gitea/workflows/bench.yaml

env:
  CARGO_TERM_COLOR: always
  BENCH_HOST: ${{ github.event.inputs.host || 'benjy.hanzalova.internal' }}
  DURATION: ${{ github.event.inputs.duration_secs || '30' }}
  RUNS: ${{ github.event.inputs.runs || '5' }}
  BATCH: ${{ github.event.inputs.batch_size || '1000000' }}
  WORKERS: ${{ github.event.inputs.workers || '1' }}

# One measurement per host at a time; a second one would share the card.
concurrency:
  group: bench-${{ github.event.inputs.host || 'benjy.hanzalova.internal' }}
  cancel-in-progress: false

jobs:
  build:
    # cuda-13.0, not rust: the rust image is Fedora 44 and the mining hosts are
    # Fedora 43, so a binary built there needs a glibc the hosts do not have
    # (observed: "GLIBC_2.43 not found"). cuda-13.0 is Fedora 43 based, matches
    # the hosts, and is what the deploy in #8 builds on anyway.
    runs-on: cuda-13.0
    steps:
      - uses: actions/checkout@v4
      - name: build quantus-bench
        env:
          MINER_BUILD_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
        run: cargo build --release --locked -p bench-harness
      - uses: actions/upload-artifact@v3
        with:
          name: quantus-bench
          path: target/release/quantus-bench

  measure:
    runs-on: fedora-43
    needs: build
    steps:
      - uses: actions/checkout@v4
      - uses: actions/download-artifact@v3
        with: { name: quantus-bench, path: _bin }

      - name: write ssh key
        run: |
          set -euo pipefail
          install -d -m 0700 ~/.ssh
          printf '%s\n' "${{ secrets.RSYNC_SSH_KEY }}" > ~/.ssh/id_gitea_ci
          chmod 0600 ~/.ssh/id_gitea_ci

      - name: measure on ${{ env.BENCH_HOST }}
        run: |
          set -euo pipefail
          SSHOPTS="-i $HOME/.ssh/id_gitea_ci -o StrictHostKeyChecking=accept-new"
          run() { ssh $SSHOPTS gitea_ci@"$BENCH_HOST" "$@"; }

          # Per-run file names: two runs may overlap on the host until the
          # host-side flock serialises them, and scp over a running binary
          # fails with ETXTBSY.
          id="${{ github.run_id }}"
          dir=/var/lib/gitea_ci/bench
          run "install -d -m 0750 $dir"
          scp $SSHOPTS -q _bin/quantus-bench gitea_ci@"$BENCH_HOST":$dir/quantus-bench.$id
          scp $SSHOPTS -q crates/bench-harness/bench-on-host.sh gitea_ci@"$BENCH_HOST":$dir/bench-on-host.$id.sh
          run "chmod 0755 $dir/quantus-bench.$id"
          cleanup() { ssh $SSHOPTS gitea_ci@"$BENCH_HOST" "rm -f $dir/quantus-bench.$id $dir/bench-on-host.$id.sh $dir/record.$id.json"; }
          trap cleanup EXIT

          label="${{ github.event.pull_request.number && format('pr-{0}', github.event.pull_request.number) || github.ref_name }}"
          # The host script pauses the miner, holds the per-host lock, measures,
          # and resumes the miner under its own trap.
          run "bash $dir/bench-on-host.$id.sh $dir/quantus-bench.$id $DURATION $RUNS $BATCH $WORKERS $label $dir/record.$id.json" | tee bench.log
          # The summary is everything from the harness's markdown header on.
          sed -n '/^## quantus-bench/,$p' bench.log > bench.md
          scp $SSHOPTS -q gitea_ci@"$BENCH_HOST":$dir/record.$id.json record.json
          { echo; cat bench.md; } >> "$GITHUB_STEP_SUMMARY"

      - uses: actions/upload-artifact@v3
        if: always()
        with:
          name: bench-record-${{ env.BENCH_HOST }}
          path: |
            record.json
            bench.md

      - name: comment on the pull request
        if: github.event_name == 'pull_request'
        run: |
          set -euo pipefail
          body=$(python3 - <<'PY'
          import json, pathlib
          print(json.dumps({"body": pathlib.Path("bench.md").read_text()}))
          PY
          )
          curl -fsS -X POST \
            -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
            -H "Content-Type: application/json" \
            "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/issues/${{ github.event.pull_request.number }}/comments" \
            -d "$body" > /dev/null