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 +1,70 @@
+#!/usr/bin/env python3
+"""Tabulate concurrent_read JSON results (clawhdf5, h5py threads/processes).
+
+    python compare_concurrent_read.py clawhdf5.json h5py-threads.json h5py-procs.json
+
+Prints one Markdown table: for each layout, mode and thread count, every
+tool's MB/s and scaling efficiency, and the first file's MB/s relative to each
+of the others. Refuses to compare runs whose workload parameters differ.
+"""
+
+import json
+import sys
+
+COMPARED = ("datasets", "rows", "cols", "chunk", "deflate_level", "slab", "slabs", "seed")
+
+
+def main(paths):
+    if len(paths) < 2:
+        sys.exit(__doc__)
+    docs = []
+    for p in paths:
+        with open(p) as fh:
+            docs.append(json.load(fh))
+    ref = docs[0]
+    for d, p in zip(docs[1:], paths[1:]):
+        diff = [k for k in COMPARED if d["params"].get(k) != ref["params"].get(k)]
+        if diff:
+            sys.exit(f"{p}: workload differs from {paths[0]} in {', '.join(diff)}")
+        if d["cache"] != ref["cache"]:
+            print(f"warning: {p} ran {d['cache']!r}, {paths[0]} ran {ref['cache']!r}",
+                  file=sys.stderr)
+        if d.get("host") != ref.get("host"):
+            print(f"warning: {p} ran on {d.get('host')}, {paths[0]} on {ref.get('host')}",
+                  file=sys.stderr)
+
+    names = [d["tool"] for d in docs]
+    for d in docs:
+        extra = f", HDF5 {d['hdf5_version']}" if "hdf5_version" in d else ""
+        print(f"- {d['tool']} {d['version']}{extra}: host {d.get('host')}, "
+              f"{d.get('cpus')} CPUs, cache {d['cache']}, decode threads per read "
+              f"{d.get('decode_threads')}")
+    p = ref["params"]
+    print(f"\n{p['datasets']} datasets of {p['rows']} x {p['cols']} f32, chunks "
+          f"{p['chunk'][0]} x {p['chunk'][1]} (deflate {p['deflate_level']}); "
+          f"`same`: {p['slabs']} slabs of {p['slab']} x {p['slab']}\n")
+
+    index = [{(r["layout"], r["mode"], r["threads"]): r for r in d["results"]} for d in docs]
+    keys = [(r["layout"], r["mode"], r["threads"]) for r in ref["results"]]
+
+    head = ["layout", "mode", "threads"]
+    head += [f"{n} MB/s (eff)" for n in names]
+    head += [f"{names[0]} / {n}" for n in names[1:]]
+    print("| " + " | ".join(head) + " |")
+    print("|---|---|" + "---:|" * (len(head) - 2))
+    for key in keys:
+        cells = [key[0], key[1], str(key[2])]
+        rs = [ix.get(key) for ix in index]
+        for r in rs:
+            if r is None:
+                cells.append("-")
+            else:
+                eff = "-" if r["efficiency"] is None else f"{r['efficiency']:.2f}"
+                cells.append(f"{r['mb_s']:.0f} ({eff})")
+        for r in rs[1:]:
+            cells.append("-" if r is None else f"{rs[0]['mb_s'] / r['mb_s']:.2f}x")
+        print("| " + " | ".join(cells) + " |")
+
+
+if __name__ == "__main__":
+    main(sys.argv[1:])