chore: Block building benchmark via github-action-benchmark (#11202)

Deletes old benchmarks, along with the benchmark-related scripts and
types.

Adds a single benchmark for block building, with a stubbed
`TelemetryClient` that collects all datapoints in memory, and then
flushes a set of specified metrics into the custom format expected by
[github-action-benchmark](https://github.com/benchmark-action/github-action-benchmark),
which we're currently using for bb.

Benchmarks get published to
https://aztecprotocol.github.io/aztec-packages/dev/e2e-bench/

Fixes #11154

Author: spalladino

.github/workflows/ci.yml

@@ -239,7 +239,7 @@ jobs:
             ci3/cache_upload_flag "$artifact"
           fi
 
-  # all the benchmarking end-to-end integration tests for aztec (not required to merge)
+  # All the benchmarking end-to-end integration tests for aztec (not required to merge)
   bench-e2e:
     needs: [images-e2e, configure]
     if: needs.configure.outputs.e2e-all == 'true' || needs.configure.outputs.bench-list != '[]'
@@ -260,15 +260,28 @@ jobs:
           if ci3/test_should_run "$artifact"; then
             docker pull aztecprotocol/aztec:${{ env.GIT_COMMIT }}
             docker pull aztecprotocol/end-to-end:${{ env.GIT_COMMIT }}
-            export FORCE_COLOR=1
-            export EARTHLY_BUILD_ARGS="${{ env.EARTHLY_BUILD_ARGS }}"
-            ./yarn-project/end-to-end/scripts/e2e_test.sh ${{ matrix.test }}
-            export COMMIT_HASH=${{ env.GIT_COMMIT }}
-            export PULL_REQUEST=${{ github.event.pull_request.number }}
-            export BRANCH=${{ github.ref_name }}
-            scripts/logs/upload_logs_to_s3.sh /usr/var/log
+            FORCE_COLOR=1 ./yarn-project/end-to-end/scripts/e2e_test.sh ${{ matrix.test }}
             ci3/cache_upload_flag "$artifact"
           fi
+      - name: Inspect data folder
+        continue-on-error: true
+        run: tree ./yarn-project/end-to-end/out
+      - name: Store benchmark result
+        if: github.ref == 'refs/heads/master'
+        continue-on-error: true
+        uses: benchmark-action/github-action-benchmark@4de1bed97a47495fc4c5404952da0499e31f5c29
+        with:
+          name: "End-to-end Benchmark"
+          benchmark-data-dir-path: "dev/e2e-bench"
+          tool: "customSmallerIsBetter"
+          output-file-path: ./yarn-project/end-to-end/out/bench.json
+          github-token: ${{ secrets.AZTEC_BOT_GITHUB_TOKEN }}
+          auto-push: true
+          alert-threshold: "150%"
+          comment-on-alert: true
+          fail-on-alert: false
+          alert-comment-cc-users: "@philwindle @spalladino"
+          max-items-in-chart: 50
 
   # Only e2e test that can't run on standard github runner
   e2e-prover-full:
@@ -320,49 +333,6 @@ jobs:
               ci3/cache_upload_flag acir-bench-$(./barretenberg/acir_tests/bootstrap.sh hash)
             fi
 
-  # TODO(ci3) fix and reinstate
-  # bench-summary:
-  #   if: needs.configure.outputs.e2e-all == 'true'
-  #   needs:
-  #     - acir-bench
-  #     - bench-e2e
-  #     - configure
-  #   runs-on: ubuntu-latest
-  #   steps:
-  #     - uses: actions/checkout@v4
-  #       with:
-  #         fetch-depth: 100 # Downloading base benchmark from master requires access to history
-  #         ref: "${{ github.event.pull_request.head.sha }}"
-  #     - uses: ./.github/ci-setup-action
-  #     - name: "Build and upload bench aggregate file"
-  #       uses: ./.github/ensure-builder
-  #       with:
-  #         runner_type: builder-x86
-  #         username: ${{ needs.configure.outputs.username }}
-  #         run: scripts/earthly-ci ./yarn-project/scripts/+bench-aggregate
-  #     - name: "Download base benchmark and package into earthly"
-  #       if: github.event_name == 'pull_request'
-  #       uses: ./.github/run-on-builder
-  #       env:
-  #         AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
-  #         AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-  #         BENCH_FOLDER: "./scripts/logs/tmp/bench"
-  #         PULL_REQUEST: "${{ github.event.pull_request.number }}"
-  #       with:
-  #         run: |
-  #           # Download the base benchmark locally (requires AWS creds and .git history)
-  #           mkdir -p $BENCH_FOLDER
-  #           ./scripts/logs/download_base_benchmark_from_s3.sh
-  #           # Package it into an earthly artifact to read from bench-comment
-  #           scripts/earthly-ci ./scripts/logs+pack-base-benchmark
-  #     - name: "Generate summary comment if pull request"
-  #       if: github.event_name == 'pull_request'
-  #       uses: ./.github/run-on-builder
-  #       env:
-  #         AZTEC_BOT_GITHUB_TOKEN: ${{ secrets.AZTEC_BOT_GITHUB_TOKEN }}
-  #       with:
-  #         run: scripts/earthly-ci ./yarn-project/scripts/+bench-comment
-
   # barretenberg (prover) native, AVM (public VM) and Merkle tree (world state) tests
   # ran on own runner for resource reasons (memory x cpu intensive)
   bb-native-tests:

scripts/logs/Earthfile

@@ -1,18 +1 @@
 export * from './stats.js';
-export * from './metrics.js';
-export * from './benchmarks.js';
-
-/** Block sizes to use for benchmark tests on multiple block sizes. */
-export const BENCHMARK_BLOCK_SIZES = process.env.BENCHMARK_BLOCK_SIZES
-  ? process.env.BENCHMARK_BLOCK_SIZES.split(',').map(Number)
-  : [4, 8, 16];
-
-/** Block size to use for building chains of multiple blocks. */
-export const BENCHMARK_HISTORY_BLOCK_SIZE = process.env.BENCHMARK_HISTORY_BLOCK_SIZE
-  ? +process.env.BENCHMARK_HISTORY_BLOCK_SIZE
-  : 8;
-
-/** Chain lengths to test for history processing benchmarks. */
-export const BENCHMARK_HISTORY_CHAIN_LENGTHS = process.env.BENCHMARK_HISTORY_CHAIN_LENGTHS
-  ? process.env.BENCHMARK_HISTORY_CHAIN_LENGTHS.split(',').map(x => Number(x))
-  : [3, 5];