bench: concurrent-read harness against h5py threads and processes

concurrent_read reads one shared File from 1-16 threads: every dataset in full (distinct datasets per thread) and random hyperslabs of one dataset, over a deflate and a contiguous file it generates (or reuses while manifest.json matches). It reports decoded MB/s and scaling efficiency, warm or --cold (posix_fadvise) page cache, sizes the decode pool with --decode-threads, and writes JSON. scripts/concurrent_read_h5py.py runs the same workload on the same files with h5py threads or spawned processes (same splitmix64 data and slab stream, checked at spot elements), and compare_concurrent_read.py prints one table and refuses runs with different workloads. A smoke test runs all three end to end on tiny files (h5py half honours CLAWHDF5_PYTHON / CLAWHDF5_REQUIRE_INTEROP). BENCHMARKS.md gets a "Concurrent reads" section with the commands, marked not yet measured. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-09-25 23:56:36 -05:00
parent bb78d70b99
commit 3b24e6753b
9 changed files with 1100 additions and 0 deletions
@@ -0,0 +1,148 @@
+//! Keeps the concurrent-read harnesses working: runs `concurrent_read`, the
+//! h5py script (threads and processes) and the comparison script end to end
+//! on tiny files. h5py reading the files also checks, element by element at
+//! spot positions, that both harnesses generate the same data and slabs.
+//!
+//! The h5py half is skipped when python3 with h5py is unavailable, unless
+//! `CLAWHDF5_REQUIRE_INTEROP=1`; `CLAWHDF5_PYTHON` picks the interpreter.
+
+use std::path::{Path, PathBuf};
+use std::process::Command;
+
+fn python() -> String {
+    std::env::var("CLAWHDF5_PYTHON").unwrap_or_else(|_| "python3".to_string())
+}
+
+fn interop_required() -> bool {
+    std::env::var("CLAWHDF5_REQUIRE_INTEROP").is_ok_and(|v| v == "1")
+}
+
+fn python_available() -> bool {
+    Command::new(python())
+        .args(["-c", "import h5py, numpy"])
+        .output()
+        .map(|o| o.status.success())
+        .unwrap_or(false)
+}
+
+fn scripts() -> PathBuf {
+    Path::new(env!("CARGO_MANIFEST_DIR")).join("scripts")
+}
+
+fn run(cmd: &mut Command) -> String {
+    let out = cmd.output().expect("spawn");
+    assert!(
+        out.status.success(),
+        "{cmd:?} failed\nSTDOUT:\n{}\nSTDERR:\n{}",
+        String::from_utf8_lossy(&out.stdout),
+        String::from_utf8_lossy(&out.stderr)
+    );
+    String::from_utf8_lossy(&out.stdout).into_owned()
+}
+
+const SMALL: [&str; 8] = [
+    "--threads",
+    "1,2",
+    "--slabs",
+    "8",
+    "--reps",
+    "1",
+    "--slab",
+    "64",
+];
+
+fn results(path: &Path) -> serde_json::Value {
+    serde_json::from_str(&std::fs::read_to_string(path).unwrap()).unwrap()
+}
+
+#[test]
+fn harnesses_run_end_to_end_on_tiny_files() {
+    let dir = tempfile::TempDir::new().unwrap();
+    let data = dir.path().join("data");
+    let claw = dir.path().join("claw.json");
+
+    let bin = env!("CARGO_BIN_EXE_concurrent_read");
+    run(Command::new(bin)
+        .arg("--dir")
+        .arg(&data)
+        .args(["--datasets", "3", "--mib", "1"])
+        .args(SMALL)
+        .arg("--json")
+        .arg(&claw));
+    // Second run reuses the files (and exercises --cold).
+    let out = Command::new(bin)
+        .arg("--dir")
+        .arg(&data)
+        .args(["--datasets", "3", "--mib", "1", "--cold"])
+        .args(SMALL)
+        .output()
+        .unwrap();
+    assert!(out.status.success());
+    assert!(String::from_utf8_lossy(&out.stderr).contains("reusing"));
+
+    let doc = results(&claw);
+    assert_eq!(doc["tool"], "clawhdf5");
+    // 2 layouts x 2 modes x 2 thread counts.
+    assert_eq!(doc["results"].as_array().unwrap().len(), 8);
+    for r in doc["results"].as_array().unwrap() {
+        assert!(r["mb_s"].as_f64().unwrap() > 0.0, "{r}");
+    }
+
+    if !python_available() {
+        assert!(
+            !interop_required(),
+            "CLAWHDF5_REQUIRE_INTEROP=1 but {} has no h5py",
+            python()
+        );
+        eprintln!("skipping the h5py half: no h5py in {}", python());
+        return;
+    }
+    let mut jsons = vec![claw];
+    for executor in ["threads", "processes"] {
+        let out = dir.path().join(format!("h5py-{executor}.json"));
+        run(Command::new(python())
+            .arg(scripts().join("concurrent_read_h5py.py"))
+            .arg("--dir")
+            .arg(&data)
+            .args(["--executor", executor])
+            .args(SMALL)
+            .arg("--json")
+            .arg(&out));
+        let doc = results(&out);
+        assert_eq!(doc["tool"], format!("h5py-{executor}"));
+        assert_eq!(doc["results"].as_array().unwrap().len(), 8);
+        jsons.push(out);
+    }
+    let table = run(Command::new(python())
+        .arg(scripts().join("compare_concurrent_read.py"))
+        .args(&jsons));
+    assert!(table.contains("| deflate | same | 2 |"), "{table}");
+    assert!(table.contains("clawhdf5 / h5py-processes"), "{table}");
+
+    // A different workload must not be compared.
+    let other = dir.path().join("other.json");
+    run(Command::new(python())
+        .arg(scripts().join("concurrent_read_h5py.py"))
+        .arg("--dir")
+        .arg(&data)
+        .args([
+            "--threads",
+            "1",
+            "--slabs",
+            "4",
+            "--reps",
+            "1",
+            "--slab",
+            "64",
+        ])
+        .arg("--json")
+        .arg(&other));
+    let out = Command::new(python())
+        .arg(scripts().join("compare_concurrent_read.py"))
+        .arg(&jsons[0])
+        .arg(&other)
+        .output()
+        .unwrap();
+    assert!(!out.status.success());
+    assert!(String::from_utf8_lossy(&out.stderr).contains("slabs"));
+}