test: Add a shared framework for reproducible fuzz tests

.github/workflows/extended.yml

@@ -69,10 +69,14 @@ jobs:
       - name: Show available disk space
         run: |
           df -h
-      - name: Run tests (excluding doctests)
+      - name: Run extended tests
         run: cargo xtask ci step test extended
-      - name: Run fuzzers with more iterations
+      - name: Run fuzz tests
         run: cargo xtask ci step test fuzz
+      # Migrate it to the above unified fuzz runner over time
+      # Tracker: https://github.com/apache/datafusion/issues/27082
+      - name: Run unmigrated fuzzers with more iterations
+        run: cargo xtask ci step test fuzz-legacy
       - parallel:
           - name: Verify Working Directory Clean
             run: git diff --exit-code

Cargo.toml

@@ -20,6 +20,7 @@ members = [
     "datafusion/execution",
     "datafusion/ffi",
     "datafusion/ffi/integration-tests",
+    "datafusion/fuzz",
     "datafusion/functions",
     "datafusion/functions-aggregate",
     "datafusion/functions-aggregate-common",

datafusion/fuzz/Cargo.toml

@@ -0,0 +1,36 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: See the NOTICE file distributed with this work for additional information regarding copyright ownership
+# SPDX-FileContributor: Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements
+
+# A private crate providing a single entry point for all fuzz tests.
+
+[package]
+name = "datafusion-fuzz"
+version = "0.1.0"
+edition = { workspace = true }
+# Ensure this crate is private
+publish = false
+autotests = false
+
+[lints]
+workspace = true
+
+[features]
+extended_tests = []
+
+[dev-dependencies]
+arrow = { workspace = true }
+bytes = { workspace = true }
+datafusion-common = { workspace = true }
+datafusion-execution = { workspace = true }
+datafusion-physical-plan = { workspace = true }
+futures = { workspace = true }
+parking_lot = { workspace = true }
+rand = { workspace = true }
+test-utils = { path = "../../test-utils" }
+tokio = { workspace = true, features = ["rt-multi-thread", "time"] }
+
+[[test]]
+name = "fuzz"
+path = "tests/fuzz.rs"
+required-features = ["extended_tests"]

datafusion/fuzz/tests/fuzz.rs

@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: See the NOTICE file distributed with this work for additional information regarding copyright ownership
+// SPDX-FileContributor: Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements
+
+//! One integration entrypoint for DataFusion's registered fuzz suites.
+
+use std::future::Future;
+use std::pin::Pin;
+
+use datafusion_common::Result;
+use test_utils::fuzz::{FuzzTest, RunConfig, run};
+
+mod suites;
+
+/// The single registration point for project-wide fuzz campaigns.
+///
+/// Migration of the remaining fuzz tests is tracked in [#27082].
+///
+/// [#27082]: https://github.com/apache/datafusion/issues/27082
+#[tokio::test(flavor = "multi_thread")]
+async fn fuzz_tests() -> Result<()> {
+    let spill_pool = suites::spill_pool::SpillPoolFuzzer;
+    let suites = [Suite::new(
+        &spill_pool,
+        RunConfig {
+            run_seed: Some(0),
+            max_cases: Some(1000),
+            time_limit: None,
+            cases_per_dataset: 1000,
+        },
+    )];
+    run_suites(suites).await
+}
+
+async fn run_suites<'a>(suites: impl IntoIterator<Item = Suite<'a>>) -> Result<()> {
+    for suite in suites {
+        eprintln!("Running fuzz suite: {}", suite.name);
+        suite.run.await?;
+    }
+    Ok(())
+}
+
+/// Wrapper for one fuzzing test suite
+struct Suite<'a> {
+    name: &'a str,
+    /// Run the test suite. Report an error on failure or execution statistics on success.
+    run: Pin<Box<dyn Future<Output = Result<()>> + 'a>>,
+}
+
+impl<'a> Suite<'a> {
+    fn new<T: FuzzTest>(test: &'a T, config: RunConfig) -> Self {
+        Self {
+            name: test.name(),
+            run: Box::pin(async move {
+                let stats = run(test, config).await?;
+                eprintln!(
+                    "Fuzz suite {}: {} cases, {} datasets, {:?}",
+                    test.name(),
+                    stats.cases_passed,
+                    stats.datasets_prepared,
+                    stats.elapsed
+                );
+                Ok(())
+            }),
+        }
+    }
+}

datafusion/fuzz/tests/suites/mod.rs

@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: See the NOTICE file distributed with this work for additional information regarding copyright ownership
+// SPDX-FileContributor: Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements
+
+//! Implementation for fuzz test cases.
+
+pub(crate) mod spill_pool;