From aea3f640ea59d91f7ca9b193acfcc3e26740318b Mon Sep 17 00:00:00 2001 From: eunhhu 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. --- ...-27-journal-before-085-ext4-linux-aarch64.jsonl | 20 +++++++ .../2026-09-27-journal-ext4-linux-aarch64.jsonl | 20 +++++++ ...-27-store-variants-085-ext4-linux-aarch64.jsonl | 36 ++++++++++++ research/experiments/013-parallel-syncs/journal.py | 66 ++++++++++++++++++++++ .../experiments/013-parallel-syncs/variants.py | 10 +++- 5 files changed, 149 insertions(+), 3 deletions(-) create mode 100644 research/experiments/013-parallel-syncs/2026-09-27-journal-before-085-ext4-linux-aarch64.jsonl create mode 100644 research/experiments/013-parallel-syncs/2026-09-27-journal-ext4-linux-aarch64.jsonl create mode 100644 research/experiments/013-parallel-syncs/2026-09-27-store-variants-085-ext4-linux-aarch64.jsonl create mode 100644 research/experiments/013-parallel-syncs/journal.py (limited to 'research/experiments') diff --git a/research/experiments/013-parallel-syncs/2026-09-27-journal-before-085-ext4-linux-aarch64.jsonl b/research/experiments/013-parallel-syncs/2026-09-27-journal-before-085-ext4-linux-aarch64.jsonl new file mode 100644 index 0000000..5b8320d --- /dev/null +++ b/research/experiments/013-parallel-syncs/2026-09-27-journal-before-085-ext4-linux-aarch64.jsonl @@ -0,0 +1,20 @@ +{"round": 0, "store": "as it is", "commits_per_second": 362, "p50_ms": 1.26, "p90_ms": 3.98, "p99_ms": 55.11, "journal_commits": 113} +{"round": 0, "store": "no compaction", "commits_per_second": 427, "p50_ms": 1.27, "p90_ms": 3.91, "p99_ms": 36.68, "journal_commits": 44} +{"round": 0, "store": "no compaction, no growth", "commits_per_second": 541, "p50_ms": 1.27, "p90_ms": 3.17, "p99_ms": 5.49, "journal_commits": 8} +{"round": 0, "store": "compacted file sized like the old", "commits_per_second": 477, "p50_ms": 1.26, "p90_ms": 3.21, "p99_ms": 10.87, "journal_commits": 46} +{"round": 1, "store": "no compaction", "commits_per_second": 458, "p50_ms": 1.28, "p90_ms": 3.52, "p99_ms": 16.56, "journal_commits": 43} +{"round": 1, "store": "no compaction, no growth", "commits_per_second": 440, "p50_ms": 1.27, "p90_ms": 4.08, "p99_ms": 25.17, "journal_commits": 7} +{"round": 1, "store": "compacted file sized like the old", "commits_per_second": 413, "p50_ms": 1.26, "p90_ms": 3.22, "p99_ms": 25.22, "journal_commits": 48} +{"round": 1, "store": "as it is", "commits_per_second": 370, "p50_ms": 1.29, "p90_ms": 4.01, "p99_ms": 33.16, "journal_commits": 110} +{"round": 2, "store": "no compaction, no growth", "commits_per_second": 424, "p50_ms": 1.28, "p90_ms": 3.94, "p99_ms": 25.66, "journal_commits": 9} +{"round": 2, "store": "compacted file sized like the old", "commits_per_second": 461, "p50_ms": 1.26, "p90_ms": 3.3, "p99_ms": 21.71, "journal_commits": 46} +{"round": 2, "store": "as it is", "commits_per_second": 340, "p50_ms": 1.28, "p90_ms": 4.21, "p99_ms": 35.79, "journal_commits": 114} +{"round": 2, "store": "no compaction", "commits_per_second": 404, "p50_ms": 1.28, "p90_ms": 4.13, "p99_ms": 31.76, "journal_commits": 33} +{"round": 3, "store": "compacted file sized like the old", "commits_per_second": 433, "p50_ms": 1.25, "p90_ms": 3.13, "p99_ms": 25.18, "journal_commits": 46} +{"round": 3, "store": "as it is", "commits_per_second": 373, "p50_ms": 1.27, "p90_ms": 3.94, "p99_ms": 56.67, "journal_commits": 114} +{"round": 3, "store": "no compaction", "commits_per_second": 384, "p50_ms": 1.27, "p90_ms": 3.98, "p99_ms": 53.28, "journal_commits": 36} +{"round": 3, "store": "no compaction, no growth", "commits_per_second": 475, "p50_ms": 1.27, "p90_ms": 3.91, "p99_ms": 21.46, "journal_commits": 13} +{"store": "as it is", "commits": 4000, "commits_per_second": 366.0, "p50_ms": 1.275, "p90_ms": 3.995, "p99_ms": 45.45, "journal_commits": 113.5} +{"store": "no compaction", "commits": 4000, "commits_per_second": 415.5, "p50_ms": 1.275, "p90_ms": 3.9450000000000003, "p99_ms": 34.22, "journal_commits": 39.5} +{"store": "no compaction, no growth", "commits": 4000, "commits_per_second": 457.5, "p50_ms": 1.27, "p90_ms": 3.925, "p99_ms": 23.315, "journal_commits": 8.5} +{"store": "compacted file sized like the old", "commits": 4000, "commits_per_second": 447.0, "p50_ms": 1.26, "p90_ms": 3.215, "p99_ms": 23.445, "journal_commits": 46.0} diff --git a/research/experiments/013-parallel-syncs/2026-09-27-journal-ext4-linux-aarch64.jsonl b/research/experiments/013-parallel-syncs/2026-09-27-journal-ext4-linux-aarch64.jsonl new file mode 100644 index 0000000..0c14f32 --- /dev/null +++ b/research/experiments/013-parallel-syncs/2026-09-27-journal-ext4-linux-aarch64.jsonl @@ -0,0 +1,20 @@ +{"round": 0, "store": "as it is", "commits_per_second": 411, "p50_ms": 1.27, "p90_ms": 3.96, "p99_ms": 25.68, "journal_commits": 52} +{"round": 0, "store": "no compaction", "commits_per_second": 449, "p50_ms": 1.27, "p90_ms": 3.99, "p99_ms": 23.52, "journal_commits": 46} +{"round": 0, "store": "no compaction, no growth", "commits_per_second": 519, "p50_ms": 1.27, "p90_ms": 3.14, "p99_ms": 5.55, "journal_commits": 4} +{"round": 0, "store": "tail grown as commits need it", "commits_per_second": 346, "p50_ms": 1.29, "p90_ms": 4.01, "p99_ms": 26.25, "journal_commits": 117} +{"round": 1, "store": "no compaction", "commits_per_second": 360, "p50_ms": 1.28, "p90_ms": 3.94, "p99_ms": 32.97, "journal_commits": 42} +{"round": 1, "store": "no compaction, no growth", "commits_per_second": 413, "p50_ms": 1.28, "p90_ms": 4.07, "p99_ms": 26.58, "journal_commits": 18} +{"round": 1, "store": "tail grown as commits need it", "commits_per_second": 270, "p50_ms": 1.28, "p90_ms": 4.34, "p99_ms": 50.93, "journal_commits": 110} +{"round": 1, "store": "as it is", "commits_per_second": 382, "p50_ms": 1.25, "p90_ms": 3.99, "p99_ms": 26.49, "journal_commits": 40} +{"round": 2, "store": "no compaction, no growth", "commits_per_second": 463, "p50_ms": 1.27, "p90_ms": 3.96, "p99_ms": 22.29, "journal_commits": 21} +{"round": 2, "store": "tail grown as commits need it", "commits_per_second": 289, "p50_ms": 1.27, "p90_ms": 3.99, "p99_ms": 32.56, "journal_commits": 104} +{"round": 2, "store": "as it is", "commits_per_second": 356, "p50_ms": 1.27, "p90_ms": 3.93, "p99_ms": 37.21, "journal_commits": 46} +{"round": 2, "store": "no compaction", "commits_per_second": 393, "p50_ms": 1.26, "p90_ms": 4.08, "p99_ms": 32.96, "journal_commits": 41} +{"round": 3, "store": "tail grown as commits need it", "commits_per_second": 406, "p50_ms": 1.27, "p90_ms": 4.12, "p99_ms": 26.45, "journal_commits": 108} +{"round": 3, "store": "as it is", "commits_per_second": 389, "p50_ms": 1.27, "p90_ms": 4.06, "p99_ms": 27.31, "journal_commits": 44} +{"round": 3, "store": "no compaction", "commits_per_second": 392, "p50_ms": 1.26, "p90_ms": 3.4, "p99_ms": 52.8, "journal_commits": 44} +{"round": 3, "store": "no compaction, no growth", "commits_per_second": 469, "p50_ms": 1.27, "p90_ms": 3.88, "p99_ms": 22.84, "journal_commits": 15} +{"store": "as it is", "commits": 4000, "commits_per_second": 385.5, "p50_ms": 1.27, "p90_ms": 3.975, "p99_ms": 26.9, "journal_commits": 45.0} +{"store": "no compaction", "commits": 4000, "commits_per_second": 392.5, "p50_ms": 1.2650000000000001, "p90_ms": 3.965, "p99_ms": 32.965, "journal_commits": 43.0} +{"store": "no compaction, no growth", "commits": 4000, "commits_per_second": 466.0, "p50_ms": 1.27, "p90_ms": 3.92, "p99_ms": 22.564999999999998, "journal_commits": 16.5} +{"store": "tail grown as commits need it", "commits": 4000, "commits_per_second": 317.5, "p50_ms": 1.275, "p90_ms": 4.0649999999999995, "p99_ms": 29.505000000000003, "journal_commits": 109.0} diff --git a/research/experiments/013-parallel-syncs/2026-09-27-store-variants-085-ext4-linux-aarch64.jsonl b/research/experiments/013-parallel-syncs/2026-09-27-store-variants-085-ext4-linux-aarch64.jsonl new file mode 100644 index 0000000..5e26b0f --- /dev/null +++ b/research/experiments/013-parallel-syncs/2026-09-27-store-variants-085-ext4-linux-aarch64.jsonl @@ -0,0 +1,36 @@ +{"round": 0, "store": "as it is", "posts_per_second": 23632.25, "p50_us": 1984, "p99_us": 21504, "max_us": 61440, "errors": 0} +{"round": 0, "store": "no compaction", "posts_per_second": 21552.25, "p50_us": 2176, "p99_us": 17408, "max_us": 147456, "errors": 0} +{"round": 0, "store": "no compaction, no growth", "posts_per_second": 24320.25, "p50_us": 1984, "p99_us": 12800, "max_us": 61440, "errors": 0} +{"round": 0, "store": "tail grown as commits need it", "posts_per_second": 21392.25, "p50_us": 2176, "p99_us": 16384, "max_us": 69632, "errors": 0} +{"round": 1, "store": "no compaction", "posts_per_second": 21942.75, "p50_us": 2176, "p99_us": 13312, "max_us": 65536, "errors": 0} +{"round": 1, "store": "no compaction, no growth", "posts_per_second": 22688.25, "p50_us": 1984, "p99_us": 15360, "max_us": 163840, "errors": 0} +{"round": 1, "store": "tail grown as commits need it", "posts_per_second": 21433.5, "p50_us": 2176, "p99_us": 14336, "max_us": 73728, "errors": 0} +{"round": 1, "store": "as it is", "posts_per_second": 24960.25, "p50_us": 1984, "p99_us": 12800, "max_us": 73728, "errors": 0} +{"round": 2, "store": "no compaction, no growth", "posts_per_second": 23088.0, "p50_us": 2176, "p99_us": 12800, "max_us": 53248, "errors": 0} +{"round": 2, "store": "tail grown as commits need it", "posts_per_second": 22016.25, "p50_us": 2176, "p99_us": 15360, "max_us": 65536, "errors": 0} +{"round": 2, "store": "as it is", "posts_per_second": 23760.25, "p50_us": 1984, "p99_us": 12288, "max_us": 90112, "errors": 0} +{"round": 2, "store": "no compaction", "posts_per_second": 21280.25, "p50_us": 2176, "p99_us": 14336, "max_us": 59392, "errors": 0} +{"round": 3, "store": "tail grown as commits need it", "posts_per_second": 22081.25, "p50_us": 2176, "p99_us": 13824, "max_us": 65536, "errors": 0} +{"round": 3, "store": "as it is", "posts_per_second": 22594.75, "p50_us": 2176, "p99_us": 12288, "max_us": 81920, "errors": 0} +{"round": 3, "store": "no compaction", "posts_per_second": 21104.25, "p50_us": 2176, "p99_us": 21504, "max_us": 139264, "errors": 0} +{"round": 3, "store": "no compaction, no growth", "posts_per_second": 23419.25, "p50_us": 2176, "p99_us": 13312, "max_us": 57344, "errors": 0} +{"round": 4, "store": "as it is", "posts_per_second": 22673.25, "p50_us": 2048, "p99_us": 15360, "max_us": 81920, "errors": 0} +{"round": 4, "store": "no compaction", "posts_per_second": 23472.25, "p50_us": 2048, "p99_us": 14336, "max_us": 69632, "errors": 0} +{"round": 4, "store": "no compaction, no growth", "posts_per_second": 23881.5, "p50_us": 1984, "p99_us": 16384, "max_us": 61440, "errors": 0} +{"round": 4, "store": "tail grown as commits need it", "posts_per_second": 17632.25, "p50_us": 2304, "p99_us": 12800, "max_us": 589824, "errors": 0} +{"round": 5, "store": "no compaction", "posts_per_second": 19040.25, "p50_us": 2176, "p99_us": 14336, "max_us": 655360, "errors": 0} +{"round": 5, "store": "no compaction, no growth", "posts_per_second": 23552.25, "p50_us": 2048, "p99_us": 18432, "max_us": 59392, "errors": 0} +{"round": 5, "store": "tail grown as commits need it", "posts_per_second": 22192.0, "p50_us": 2176, "p99_us": 15872, "max_us": 73728, "errors": 0} +{"round": 5, "store": "as it is", "posts_per_second": 20928.25, "p50_us": 2176, "p99_us": 21504, "max_us": 77824, "errors": 0} +{"round": 6, "store": "no compaction, no growth", "posts_per_second": 24608.25, "p50_us": 1984, "p99_us": 12800, "max_us": 61440, "errors": 0} +{"round": 6, "store": "tail grown as commits need it", "posts_per_second": 19088.25, "p50_us": 2176, "p99_us": 15872, "max_us": 589824, "errors": 0} +{"round": 6, "store": "as it is", "posts_per_second": 22576.25, "p50_us": 2048, "p99_us": 20480, "max_us": 77824, "errors": 0} +{"round": 6, "store": "no compaction", "posts_per_second": 23184.25, "p50_us": 1984, "p99_us": 16384, "max_us": 73728, "errors": 0} +{"round": 7, "store": "tail grown as commits need it", "posts_per_second": 22080.25, "p50_us": 2176, "p99_us": 14336, "max_us": 69632, "errors": 0} +{"round": 7, "store": "as it is", "posts_per_second": 23088.25, "p50_us": 2048, "p99_us": 21504, "max_us": 65536, "errors": 0} +{"round": 7, "store": "no compaction", "posts_per_second": 23051.75, "p50_us": 2048, "p99_us": 14336, "max_us": 65536, "errors": 0} +{"round": 7, "store": "no compaction, no growth", "posts_per_second": 22586.5, "p50_us": 2048, "p99_us": 19456, "max_us": 57344, "errors": 0} +{"store": "as it is", "rounds": 8, "posts_per_second_median": 22880.75, "p99_us_median": 17920.0, "max_us": 90112} +{"store": "no compaction", "rounds": 8, "posts_per_second_median": 21747.5, "p99_us_median": 14336.0, "max_us": 655360} +{"store": "no compaction, no growth", "rounds": 8, "posts_per_second_median": 23485.75, "p99_us_median": 14336.0, "max_us": 163840} +{"store": "tail grown as commits need it", "rounds": 8, "posts_per_second_median": 21724.875, "p99_us_median": 14848.0, "max_us": 589824} 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()) diff --git a/research/experiments/013-parallel-syncs/variants.py b/research/experiments/013-parallel-syncs/variants.py index 2c48ab6..ee49d2a 100644 --- a/research/experiments/013-parallel-syncs/variants.py +++ b/research/experiments/013-parallel-syncs/variants.py @@ -1,9 +1,10 @@ #!/usr/bin/env python3 """Where the tree store's extra sync work goes (docs/research/084-parallel-syncs.md). -Builds pure-serve with three stores from store/store-tree.c: as it is; with no -compaction; and with no compaction and a 64 MiB tail written at creation (no -tail growth during a run). Then durable score posts (64 connections), the +Builds pure-serve with stores from store/store-tree.c: as it is; with no +compaction; with no compaction and a 64 MiB tail written at creation (no tail +growth during a run); and as before 085, compacted files getting only 256 KiB +of zeros and commits growing the tail as they need it. Then durable score posts (64 connections), the builds in rotated order per round, each on a fresh store after 64 warm-up posts. Prints one JSON line per run and a summary. """ @@ -25,6 +26,9 @@ PATCHES = { 'no compaction': [('enum { COMPACT_SLACK = 1048576 };', 'enum { COMPACT_SLACK = 1 << 30 };')], 'no compaction, no growth': [('enum { COMPACT_SLACK = 1048576 };', 'enum { COMPACT_SLACK = 1 << 30 };'), ('TAIL_STEP = 262144', 'TAIL_STEP = 67108864')], + # Before 085: a compacted file got 256 KiB of zeros, and commits grew the tail as they needed it. + 'tail grown as commits need it': [('zero_fill(fd, head->end, cycle_end(head, replaced));', + 'zero_fill(fd, head->end, tail_end(head->end));')], } -- cgit v1.2.3