pure/docs/research/109-finding-items.md, branch masterVerified execution runtime unifying state, persistence, and replication.
http://git.yeowoo.org/pure/atom?h=master2026-09-30T12:52:54ZSay what 109 inferred and what it did not measure2026-09-30T12:52:54Zeunhhunecpition205@gmail.com2026-09-30T12:52:54Zurn:sha1:a4e96c56f9126b23cf27d2d493415090402919d9Say that prefetching items did not pay, and why (109)2026-09-30T12:52:30Zeunhhunecpition205@gmail.com2026-09-30T12:52:30Zurn:sha1:68dca986ee7ff7d729a15565e2e07127d5b5d1a4
Fetching a found item's cells, a leaf's keys and each level's keys ahead
made finding and reading items 20% faster on 100,000 items in a micro
benchmark, but TPC-C's clean pairs moved 1% at most and finding alone got
48% slower, so it is not in. The owner's finding samples were the descent,
not the fields: a write right after a read copies the leaf whole anyway,
and what costs is walking structures larger than the caches at random.
Say what finding items should gain, before measuring it (109)2026-09-30T12:32:49Zeunhhunecpition205@gmail.com2026-09-30T12:32:49Zurn:sha1:dacc3cf3e1e7fe6554575cefdb4ac6d7a19a61c6