Merge branch 'develop' into integration-clickhouse-benchmark-baseline

Signed-off-by: Peng Jian <pengjian.uestc@gmail.com>

Author: fastio

.github/actions/check-rebuild/action.yml

@@ -0,0 +1,23 @@
+name: "Build and verify rebuild is a no-op"
+description: "Run a cargo command, then re-run it to verify all artifacts are cached"
+inputs:
+  command:
+    description: "The cargo build command to run and verify (--message-format json is appended on the verification run)"
+    required: true
+runs:
+  using: "composite"
+  steps:
+    - name: "Build"
+      shell: bash
+      run: ${{ inputs.command }}
+    - name: "Verify rebuild is a no-op"
+      shell: bash
+      run: |
+        stale=$(${{ inputs.command }} \
+          --message-format json 2>/dev/null \
+          | jq -r 'select(.reason == "compiler-artifact" and .fresh == false) | .target.name')
+        if [ -n "$stale" ]; then
+          echo "ERROR: Rebuild recompiled crates that should have been cached:"
+          echo "$stale"
+          exit 1
+        fi

.github/actions/setup-prebuild/action.yml

@@ -0,0 +1,15 @@
+name: "Setup Prebuild"
+description: "Minimal setup for runners with pre-built Rust toolchain, nextest, and sccache"
+
+runs:
+  using: "composite"
+  steps:
+    - name: Configure sccache timeout
+      shell: bash
+      run: |
+        mkdir -p ~/.config/sccache
+        echo 'server_startup_timeout_ms = 15000' > ~/.config/sccache/config
+
+    - name: Pre-start sccache server
+      shell: bash
+      run: sccache --start-server &

.github/actions/setup-rust/action.yml

@@ -38,25 +38,51 @@ runs:
       if: runner.os == 'Linux'
       uses: rui314/setup-mold@v1
 
+    - name: Check for rustup
+      id: check-rustup
+      shell: bash
+      run: echo "exists=$(command -v rustup &> /dev/null && echo 'true' || echo 'false')" >> $GITHUB_OUTPUT
+
     - name: Rust Toolchain
       id: rust-toolchain
       uses: dtolnay/rust-toolchain@stable
-      if: steps.rustup-cache.outputs.cache-hit != 'true'
+      if: steps.check-rustup.outputs.exists != 'true'
       with:
         toolchain: "${{ steps.toolchain-config.outputs.toolchain }}"
         targets: "${{ inputs.targets }}"
         components: "${{ inputs.components }}"
 
+    - name: Install additional targets and components
+      if: steps.check-rustup.outputs.exists == 'true'
+      shell: bash
+      run: |
+        rustup toolchain install "$TOOLCHAIN"
+        [[ -n "$TARGETS" ]] && rustup target add --toolchain "$TOOLCHAIN" ${TARGETS//,/ }
+        [[ -n "$COMPONENTS" ]] && rustup component add --toolchain "$TOOLCHAIN" ${COMPONENTS//,/ }
+      env:
+        TOOLCHAIN: ${{ steps.toolchain-config.outputs.toolchain }}
+        TARGETS: ${{ inputs.targets }}
+        COMPONENTS: ${{ inputs.components }}
+
+    - name: Configure sccache timeout
+      if: inputs.enable-sccache == 'true'
+      shell: bash
+      run: |
+        mkdir -p ~/.config/sccache
+        echo 'server_startup_timeout_ms = 15000' > ~/.config/sccache/config
+
     - name: Rust Compile Cache
       if: inputs.enable-sccache == 'true'
       uses: mozilla-actions/sccache-action@v0.0.9
 
+    - name: Pre-start sccache server
+      if: inputs.enable-sccache == 'true'
+      shell: bash
+      run: sccache --start-server &
+
     - name: Install Protoc (for lance-encoding build step)
       if: runner.os != 'Windows'
-      uses: arduino/setup-protoc@v3
-      with:
-        version: "29.3"
-        repo-token: ${{ inputs.repo-token }}
+      uses: ./.github/actions/setup-protoc
 
     - name: Install Ninja (for DuckDB build system)
       uses: seanmiddleditch/gha-setup-ninja@master

.github/runs-on.yml

@@ -1,11 +1 @@
-images:
-  vortex-ci-amd64:
-    platform: "linux"
-    arch: "x64"
-    name: "vortex-ci-*"
-    owner: "245040174862"
-  vortex-ci-arm64:
-    platform: "linux"
-    arch: "arm64"
-    name: "vortex-ci-*"
-    owner: "245040174862"
+_extends: .github-private

.github/scripts/fuzz_report/templates/new_issue.md

@@ -5,6 +5,7 @@
 **Crash Location**: `{{CRASH_LOCATION}}`
 
 **Error Message**:
+
 ```
 {{PANIC_MESSAGE}}
 ```
@@ -15,6 +16,7 @@
 ```
 {{STACK_TRACE_RAW}}
 ```
+
 </details>
 {% if CLAUDE_ANALYSIS %}
 
@@ -31,23 +33,45 @@
 - **Commit**: {{COMMIT}}
 - **Crash Artifact**: {{ARTIFACT_URL}}
 
-### Reproduction
+### Reproduce
+
+```bash
+cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} ./fuzz/artifacts/{{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
+```
+
+<details>
+<summary>First-time setup: download and extract the crash artifact</summary>
 
 1. Download the crash artifact:
    - **Direct download**: {{ARTIFACT_URL}}
-   - Extract the zip file
+   - Extract the zip file (`unzip`)
+     - The path should look like `/path/to/{{FUZZ_TARGET}}/{{CRASH_FILE}}`
+     - You can create a `./fuzz/artifacts` directory that will be git-ignored in the `vortex` repo
+     - Full path would be `./fuzz/artifacts/{{FUZZ_TARGET}}/{{CRASH_FILE}}`
+
+2. Assuming you download the zipfile to `~/Downloads`, and your working directory is the repository root:
 
-2. Reproduce locally:
 ```bash
-cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} {{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
+mkdir -p ./fuzz/artifacts
+mv ~/Downloads/{{FUZZ_TARGET}}-crash-artifacts.zip ./fuzz/artifacts/
+unzip ./fuzz/artifacts/{{FUZZ_TARGET}}-crash-artifacts.zip -d ./fuzz/artifacts/
+rm ./fuzz/artifacts/{{FUZZ_TARGET}}-crash-artifacts.zip
+```
+
+3. Get a backtrace:
+
+```bash
+RUST_BACKTRACE=1 cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} ./fuzz/artifacts/{{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
 ```
 
-3. Get full backtrace:
 ```bash
-RUST_BACKTRACE=full cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} {{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
+RUST_BACKTRACE=full cargo +nightly fuzz run -D --sanitizer=none {{FUZZ_TARGET}} ./fuzz/artifacts/{{FUZZ_TARGET}}/{{CRASH_FILE}} -- -rss_limit_mb=0
 ```
 
+</details>
+
 <!-- seed_hash:{{SEED_HASH}} stack_hash:{{STACK_TRACE_HASH}} message_hash:{{MESSAGE_HASH}} -->
 
 ---
-*Auto-created by fuzzing workflow*
+
+_Auto-created by fuzzing workflow_

.github/scripts/run-sql-bench.sh

@@ -15,6 +15,7 @@
 #
 # Options:
 #   --scale-factor <sf>       Scale factor for the benchmark (e.g., 1.0, 10.0)
+#   --iterations <n>          Number of iterations to pass to each benchmark binary
 #   --remote-storage <url>    Remote storage URL (e.g., s3://bucket/path/)
 #                             If provided, runs in remote mode (no lance/clickhouse support).
 #   --benchmark-id <id>       Benchmark ID for error messages (e.g., tpch-s3)
@@ -26,6 +27,7 @@ targets="$2"
 shift 2
 
 scale_factor=""
+iterations=""
 remote_storage=""
 benchmark_id=""
 
@@ -35,6 +37,10 @@ while [[ $# -gt 0 ]]; do
             scale_factor="$2"
             shift 2
             ;;
+        --iterations)
+            iterations="$2"
+            shift 2
+            ;;
         --remote-storage)
             remote_storage="$2"
             shift 2
@@ -92,6 +98,9 @@ if [[ -n "$scale_factor" ]]; then
         opts="--opt scale-factor=$scale_factor"
     fi
 fi
+if [[ -n "$iterations" ]]; then
+    opts="-i $iterations $opts"
+fi
 
 touch results.json
 

.github/workflows/bench-pr.yml

@@ -57,6 +57,8 @@ jobs:
       - uses: actions/checkout@v6
         with:
           ref: ${{ github.event.pull_request.head.sha }}
+      - name: Setup benchmark environment
+        run: sudo bash scripts/setup-benchmark.sh
       - uses: ./.github/actions/setup-rust
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
@@ -91,7 +93,7 @@ jobs:
         env:
           RUST_BACKTRACE: full
         run: |
-          target/release_debug/${{ matrix.benchmark.id }} -d gh-json -o results.json
+          bash scripts/bench-taskset.sh target/release_debug/${{ matrix.benchmark.id }} -d gh-json -o results.json
 
       - name: Setup AWS CLI
         if: github.event.pull_request.head.repo.fork == false
@@ -150,3 +152,81 @@ jobs:
     secrets: inherit
     with:
       mode: "pr"
+      benchmark_matrix: |
+        [
+          {
+            "id": "clickbench-nvme",
+            "subcommand": "clickbench",
+            "name": "Clickbench on NVME",
+            "targets": "datafusion:parquet,datafusion:vortex,duckdb:parquet,duckdb:vortex,duckdb:duckdb"
+          },
+          {
+            "id": "tpch-nvme",
+            "subcommand": "tpch",
+            "name": "TPC-H SF=1 on NVME",
+            "targets": "datafusion:arrow,datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb",
+            "scale_factor": "1.0"
+          },
+          {
+            "id": "tpch-s3",
+            "subcommand": "tpch",
+            "name": "TPC-H SF=1 on S3",
+            "local_dir": "vortex-bench/data/tpch/1.0",
+            "remote_storage": "s3://vortex-ci-benchmark-datasets/${{github.ref_name}}/${{github.run_id}}/tpch/1.0/",
+            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact",
+            "scale_factor": "1.0"
+          },
+          {
+            "id": "tpch-nvme-10",
+            "subcommand": "tpch",
+            "name": "TPC-H SF=10 on NVME",
+            "targets": "datafusion:arrow,datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb",
+            "scale_factor": "10.0"
+          },
+          {
+            "id": "tpch-s3-10",
+            "subcommand": "tpch",
+            "name": "TPC-H SF=10 on S3",
+            "local_dir": "vortex-bench/data/tpch/10.0",
+            "remote_storage": "s3://vortex-ci-benchmark-datasets/${{github.ref_name}}/${{github.run_id}}/tpch/10.0/",
+            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact",
+            "scale_factor": "10.0"
+          },
+          {
+            "id": "tpcds-nvme",
+            "subcommand": "tpcds",
+            "name": "TPC-DS SF=1 on NVME",
+            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb",
+            "scale_factor": "1.0"
+          },
+          {
+            "id": "statpopgen",
+            "subcommand": "statpopgen",
+            "name": "Statistical and Population Genetics",
+            "targets": "duckdb:parquet,duckdb:vortex,duckdb:vortex-compact",
+            "scale_factor": "100"
+          },
+          {
+            "id": "fineweb",
+            "subcommand": "fineweb",
+            "name": "FineWeb NVMe",
+            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact",
+            "scale_factor": "100"
+          },
+          {
+            "id": "fineweb-s3",
+            "subcommand": "fineweb",
+            "name": "FineWeb S3",
+            "local_dir": "vortex-bench/data/fineweb",
+            "remote_storage": "s3://vortex-ci-benchmark-datasets/${{github.ref_name}}/${{github.run_id}}/fineweb/",
+            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact",
+            "scale_factor": "100"
+          },
+          {
+            "id": "polarsignals",
+            "subcommand": "polarsignals",
+            "name": "PolarSignals Profiling",
+            "targets": "datafusion:vortex",
+            "scale_factor": "1"
+          },
+        ]

.github/workflows/bench.yml

@@ -54,6 +54,8 @@ jobs:
         with:
           sccache: s3
       - uses: actions/checkout@v6
+      - name: Setup benchmark environment
+        run: sudo bash scripts/setup-benchmark.sh
       - uses: ./.github/actions/setup-rust
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
@@ -87,7 +89,7 @@ jobs:
         env:
           RUST_BACKTRACE: full
         run: |
-          target/release_debug/${{ matrix.benchmark.id }} --formats ${{ matrix.benchmark.formats }} -d gh-json -o results.json
+          bash scripts/bench-taskset.sh target/release_debug/${{ matrix.benchmark.id }} --formats ${{ matrix.benchmark.formats }} -d gh-json -o results.json
 
       - name: Setup AWS CLI
         uses: aws-actions/configure-aws-credentials@v5