Commit Graph
3 Commits
Author SHA1 Message Date
Daan MeijerandClaude Fable 5.1 4af5e06400 LEASE_CAPTURE_ONLY: group leases of the corpus windows' ranges only
Test and deploy / test (push) Successful in 1m6s
Test and deploy / edge (push) Successful in 2m44s
Test and deploy / deploy (push) Skipped
The lease bounds alone don't select a window: the history planner's oldest
buckets are priority 0-2 as well, so the window worker at 0..0 also took 2026
history at 0 (25k ranges in 40 groups, fetched live) while 1,739 ranges of the
2016 corpus window sat at voyager 2's leftover priorities (done when the window
was marked, planned again by the reset). With LEASE_CAPTURE_ONLY the lease, next
and the prefetcher's run-ahead take capture ranges only; the run-ahead now also
keeps to the lease bounds. Test: a group with history at 0 only isn't leased,
the history range after the window isn't handed out.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-26 23:26:31 +01:00
Daan MeijerandClaude Fable 5.1 29e0cc8f6e The window worker keeps its window over a chunk that doesn't inflate
Test and deploy / test (push) Successful in 1m14s
Test and deploy / edge (push) Successful in 2m37s
Test and deploy / deploy (push) Successful in 3m7s
A live reply cut short (the server's compressed data ending at ".\r\n" at a
read boundary; the spool keeps what Corpus.write refuses) made the worker give
the group back without a snapshot, losing the window and the batch since its
last post (six times in the first 40 minutes on homelab). Now the batch before
the chunk goes out, the chunk is reported (fetched again, plain the second
time) and the range is asked for again from that chunk (RangeOutcome::Again):
the stream waits for the new copy and the window stays. Test: the coordinator
hands the same range back at its resume point after a corrupt report.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-26 22:53:52 +01:00
Daan MeijerandClaude Fable 5.1 1f6e3316ec The window worker: group leases, the stream serving the corpus, the snapshot through the API (design 1 and 5)
Test and deploy / test (push) Successful in 55s
Test and deploy / edge (push) Successful in 2m9s
Test and deploy / deploy (push) Successful in 1m16s
A worker thread leases a group and takes its ranges in article order through
one carried window; the coordinator keeps one cursor a group (group_leases,
migration 6500) and hands out the next range, the rules and nothing about
where the chunks are: the range stream serves a stored range's chunks from the
corpus file and a live one's from the spool. The window's snapshot (bincode:
the frontier, the open files, releases and albums, the upload numbers, the
batch-counter table) goes to the coordinator every EDGE_SNAPSHOT_MINUTES and
when the group is given back, and the next holder restores it; a takeover
after LEASE_TTL_SECONDS plans the ranges from the snapshot's article again.
The prefetcher runs ahead of held groups' cursors and skips chunks the corpus
has. LEASE_MIN_PRIORITY..LEASE_MAX_PRIORITY bound what is leased. edge-node
holds groups by default; --ranges keeps the old per-range path.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-26 18:22:18 +01:00