diff options
| author | eunhhu <[email protected]> | 2026-09-26 11:01:59 +0100 |
|---|---|---|
| committer | eunhhu <[email protected]> | 2026-09-26 11:01:59 +0100 |
| commit | d340b1a43255d83be5d9fc64de434a24bd87c8be (patch) | |
| tree | 49fa4222ffe31e45bb8452d35d34ae46416acbfe /research/experiments/009-runtime-drafts/run.py | |
| parent | 6e50736c576b93c09345dc63488bbb95e9203c13 (diff) | |
| download | pure-d340b1a43255d83be5d9fc64de434a24bd87c8be.tar.gz pure-d340b1a43255d83be5d9fc64de434a24bd87c8be.zip | |
Record why the remaining store ideas wait
The zero tail wrote as many bytes as the commits under 64 writers, yet
turning it off changed nothing beyond the SD card's own noise and made
8 writers wait longer, so it stays until faster storage is measured.
Overlapping a sync with the next burst would win a few percent at most.
The second sync of a new process's first commit is rare with one owning
server. The larger lever is write amplification: a 16-byte edit rewrites
its whole leaf and catalog path.
Diffstat (limited to 'research/experiments/009-runtime-drafts/run.py')
0 files changed, 0 insertions, 0 deletions