From aea3f640ea59d91f7ca9b193acfcc3e26740318b Mon Sep 17 00:00:00 2001
From: eunhhu <necpition205@gmail.com>
Date: Sun, 27 Sep 2026 14:46:31 +0100
Subject: Give a compacted file the zeros of its whole cycle (085)

Commits grew the tree store's tail 256 KiB at a time, each growth a sync
that also committed the ext4 journal for the new size and blocks. A file
installed by compaction now carries written zeros up to where the next
compaction will come (4 x live + slack, plus a commit's margin), capped at
the size of the file it replaces, so a store never takes more space than
before and shrinks when its live data does. The cycle's commits then only
overwrite blocks the file has.

Store commits: 317.5 -> 385.5 a second, ext4 journal commits 109 -> 45 for
4,000 commits; durable app posts +5.3%, their p99 the same within this SD
card's noise. The new cycles test keeps sizes still between compactions
once the live data is whole, and shows the file shrinking with it.
---
 research/experiments/013-parallel-syncs/journal.py | 66 ++++++++++++++++++++++
 1 file changed, 66 insertions(+)
 create mode 100644 research/experiments/013-parallel-syncs/journal.py

(limited to 'research/experiments/013-parallel-syncs/journal.py')

diff --git a/research/experiments/013-parallel-syncs/journal.py b/research/experiments/013-parallel-syncs/journal.py
new file mode 100644
index 0000000..5f49095
--- /dev/null
+++ b/research/experiments/013-parallel-syncs/journal.py
@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+"""The tree store's commits under each store variant of variants.py, without
+HTTP: latency percentiles of research/experiments/010-one-sync-commit
+/commits.c, and how many ext4 journal commits (jbd2 transactions, read from
+/proc/fs/jbd2) each run caused. Rounds rotate the variants' order."""
+import argparse
+import json
+import re
+import shutil
+import statistics
+import subprocess
+import sys
+import tempfile
+from pathlib import Path
+
+import variants
+
+HERE = Path(__file__).resolve().parent
+ROOT = HERE.parents[2]
+COMMITS = HERE.parent / '010-one-sync-commit' / 'commits.c'
+
+
+def transactions(device):
+    return int(re.match(r'(\d+) transactions', (Path('/proc/fs/jbd2') / device / 'info').read_text()).group(1))
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--directory', type=Path, default=Path('/var/tmp'), help='on the device to measure')
+    parser.add_argument('--journal', default='mmcblk0p2-8', help='its /proc/fs/jbd2 entry')
+    parser.add_argument('--rounds', type=int, default=4)
+    parser.add_argument('--commits', type=int, default=4000)
+    args = parser.parse_args()
+    with tempfile.TemporaryDirectory() as work:
+        work = Path(work)
+        binaries = {}
+        for number, (name, patches) in enumerate(variants.PATCHES.items()):
+            source = (ROOT / 'store' / 'store-tree.c').read_text()
+            for old, new in patches:
+                assert old in source, old
+                source = source.replace(old, new)
+            (work / f'store-{number}.c').write_text(source)
+            binaries[name] = work / f'commits-{number}'
+            subprocess.run(['cc', '-O2', '-std=c17', f'-I{ROOT / "core"}', '-o', str(binaries[name]), str(COMMITS),
+                            str(work / f'store-{number}.c'), '-lpthread'], check=True)
+        names, runs = list(binaries), {name: [] for name in binaries}
+        for round_ in range(args.rounds):
+            for name in names[round_ % len(names):] + names[:round_ % len(names)]:
+                store = Path(tempfile.mkdtemp(dir=args.directory, prefix='pure-journal-'))
+                shutil.rmtree(store)
+                try:
+                    before = transactions(args.journal)
+                    out = subprocess.run([str(binaries[name]), str(store), str(args.commits)], capture_output=True,
+                                         text=True, check=True)
+                    measured = {**json.loads(out.stdout), 'journal_commits': transactions(args.journal) - before}
+                finally:
+                    shutil.rmtree(store, ignore_errors=True)
+                runs[name].append(measured)
+                print(json.dumps({'round': round_, 'store': name, **measured}), flush=True)
+        for name in names:
+            print(json.dumps({'store': name, 'commits': args.commits, **{key: statistics.median(r[key] for r in runs[name])
+                              for key in ('commits_per_second', 'p50_ms', 'p90_ms', 'p99_ms', 'journal_commits')}}))
+
+
+if __name__ == '__main__':
+    sys.exit(main())
-- 
cgit v1.2.3