Oregami
Repositories/oxedyne/fe2o3

fe2o3_o3db_sync/src/api/pending.rs

83 operations, oldest first

created by r1870400018:69615, which is this file's identity for as long as the history lasts, whatever it is later renamed to

read the file · who wrote it · compare two states

An operation carries no clock of its own. Each row is therefore dated by the first mark written after it by the same replica, which is one copy of the repository, and that mark is where the command that wrote the operation ended.

+ signed and verified, ? signed by a key this forge does not carry, - unsigned

OperationAuthorWhatWhen
+r1870400018:69615replica 1870400018created fe2o3_o3db_sync/src/api/pending.rs42 days ago under "Merge branch 'main' into dozone-a3-fix2"
+r1870400018:69616replica 1870400018inserted 15.5 KiB42 days ago under "Merge branch 'main' into dozone-a3-fix2"
+r1870400018:69867replica 1870400018inserted 608 bytes42 days ago under "fe2o3_o3db_sync close: the server bots are the first stage of a close, so a chunked put accepted before close() is stored or refused, never told Written and lost (A3 QA M2), and a failure to send a store's next step reaches its caller (m1)"
+r1870400018:70079replica 1870400018inserted 765 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70080replica 1870400018inserted 31 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70081replica 1870400018inserted 17 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70082replica 1870400018inserted 41 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70083replica 1870400018replaced 47 bytes with 41 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70084replica 1870400018replaced 14 bytes with 677 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70085replica 1870400018replaced 48 bytes with 61 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70086replica 1870400018replaced 94 bytes with 135 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70087replica 1870400018inserted 75 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70088replica 1870400018inserted 57 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70089replica 1870400018replaced 26 bytes with 45 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70090replica 1870400018replaced 8 bytes with 6 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70091replica 1870400018replaced 19 bytes with 446 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70092replica 1870400018replaced 24 bytes with 38 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70093replica 1870400018inserted 1 byte42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70094replica 1870400018replaced 42 bytes with 5 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70095replica 1870400018replaced 9 bytes with 1 byte42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70096replica 1870400018replaced 1 byte with 9 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70097replica 1870400018replaced 25 bytes with 160 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70100replica 1870400018replaced 3 bytes with 25 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70101replica 1870400018replaced 141 bytes with 361 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70102replica 1870400018replaced 511 bytes with 296 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70103replica 1870400018replaced 13 bytes with 21 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70104replica 1870400018replaced 17 bytes with 1.6 KiB42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70105replica 1870400018replaced 7 bytes with 39 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70106replica 1870400018replaced 14 bytes with 36 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70107replica 1870400018inserted 14 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70108replica 1870400018inserted 29 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70109replica 1870400018inserted 29 bytes42 days ago under "Merge origin/main into dozone-chunkset"
+r1870400018:70217replica 1870400018replaced 14 bytes with 23 bytes42 days ago under "fe2o3_o3db_sync: a stamp floor and one tie order -- a write after a restart outranks every record on disk even after the clock steps back, and two records of a key with one stamp are ordered by place in every path, so a key reads the same value live and after a restart (Ozone run 1) Replay raises the process's stamp clock past every stamp it reads (api::raise_stamp_floor in both bot_initgc replay paths) before start returns, and every record, tombstones included, is stamped through api::write_stamp (pending.rs own-set retire, data/core.rs zero-time record); KeyVal::stamp_time_now is gone. data::cache::supersedes orders by (time, fnum, offset) and is shared by Cache::insert, replay and bot_scan."
+r1870400018:70303replica 1870400018replaced 295 bytes with 740 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70304replica 1870400018replaced 316 bytes with 73 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70305replica 1870400018replaced 8 bytes with 80 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70306replica 1870400018inserted 27 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70307replica 1870400018inserted 24 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70309replica 1870400018replaced 56 bytes with 30 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70310replica 1870400018replaced 2 bytes with 58 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70311replica 1870400018inserted 11 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70312replica 1870400018inserted 139 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70313replica 1870400018inserted 100 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70314replica 1870400018inserted 41 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70315replica 1870400018replaced 80 bytes with 97 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70316replica 1870400018inserted 55 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70317replica 1870400018replaced 92 bytes with 273 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70318replica 1870400018inserted 22 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70319replica 1870400018replaced 76 bytes with 209 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70320replica 1870400018replaced 260 bytes with 317 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70322replica 1870400018inserted 14 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70323replica 1870400018inserted 111 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70324replica 1870400018inserted 72 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70325replica 1870400018replaced 341 bytes with 1.0 KiB42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70326replica 1870400018replaced 91 bytes with 1.7 KiB42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70327replica 1870400018replaced 38 bytes with 176 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70328replica 1870400018inserted 11 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70329replica 1870400018replaced 42 bytes with 7 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70331replica 1870400018replaced 260 bytes with 551 bytes42 days ago under "fe2o3_o3db_sync: retire on supersession, hold until final -- a store retires the chunk set of the record its durable head displaced, as the cache bot answers it, instead of reading the key back, so overlapping overwrites and deletes leave no live orphan; a chunk set is held from the draw of its id until its head's outcome is final, so the orphan sweep never takes a set in flight (Ozone run 2) The cache bot that enters a ticketed head answers HeadInserted(cind, Displaced): Nothing, Itself (a newer record was already there: the store retires its own set), or Record { meta, prior } with Prior::Head(bytes), HeadUnread (a replayed head, matched against the value read before the store began by metadata) or NotHead. Heads never enter the write tracker; Cache::insert moves the old value's bytes out on supersession, so a newer valueless record no longer leaves a stale value under a new location. The writer releases a hold only when the syncer check or the Data append fails; the cache bot releases it after an insert, confirmed or not, and keeps it on an insert error. The forcing path (test support) is unticketed and retires nothing. A delete is a store with no chunks whose tombstone is the head. Retire tombstones are stamped by api::retire_stamp, the ordered clock without the stale-stamp test hook."
+r1870400018:70449replica 1870400018replaced 6 bytes with 4 bytes42 days ago under "fe2o3_o3db_sync: a set retires only against a confirmed winner, a pinned-heads gauge, and a sweep that reads no clock -- a record beaten or displaced only by an unconfirmed one is neither old nor an orphan, and every set let go during a sweep is kept by the sweep that watched it (Ozone R2-1, R2-5, R1-1)"
+r1870400018:70450replica 1870400018replaced 3 bytes with 4 bytes42 days ago under "fe2o3_o3db_sync: a set retires only against a confirmed winner, a pinned-heads gauge, and a sweep that reads no clock -- a record beaten or displaced only by an unconfirmed one is neither old nor an orphan, and every set let go during a sweep is kept by the sweep that watched it (Ozone R2-1, R2-5, R1-1)"
+r1870400018:70451replica 1870400018inserted 74 bytes42 days ago under "fe2o3_o3db_sync: a set retires only against a confirmed winner, a pinned-heads gauge, and a sweep that reads no clock -- a record beaten or displaced only by an unconfirmed one is neither old nor an orphan, and every set let go during a sweep is kept by the sweep that watched it (Ozone R2-1, R2-5, R1-1)"
+r1870400018:70452replica 1870400018inserted 216 bytes42 days ago under "fe2o3_o3db_sync: a set retires only against a confirmed winner, a pinned-heads gauge, and a sweep that reads no clock -- a record beaten or displaced only by an unconfirmed one is neither old nor an orphan, and every set let go during a sweep is kept by the sweep that watched it (Ozone R2-1, R2-5, R1-1)"
+r1870400018:70906replica 1870400018replaced 44 bytes with 22 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70907replica 1870400018inserted 4 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70909replica 1870400018inserted 4 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70911replica 1870400018inserted 4 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70913replica 1870400018inserted 4 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70915replica 1870400018inserted 4 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70917replica 1870400018inserted 4 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70918replica 1870400018replaced 743 bytes with 682 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70920replica 1870400018inserted 23 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70923replica 1870400018replaced 127 bytes with 51 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70924replica 1870400018replaced 16 bytes with 4 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70925replica 1870400018inserted 6 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70926replica 1870400018inserted 48 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70927replica 1870400018inserted 11 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70928replica 1870400018inserted 32 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70929replica 1870400018replaced 10 bytes with 7 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70931replica 1870400018replaced 423 bytes with 345 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70932replica 1870400018replaced 4 bytes with 4 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:70933replica 1870400018replaced 32 bytes with 277 bytes40 days ago under "fe2o3_o3db_sync: a failed cut back whose fault record cannot be written is held by the refusal marker alone, which carries its cut, and clearing the marker folds the cut into the record so the next open cuts the pair back -- a test now pins that path of the round-2 marker; and the torn-append error no longer carries a run of spaces from a string continued without its backslash (Ozone APPENDSEEK, rebase onto round 2)"
+r1870400018:72476replica 1870400018inserted 148 bytes40 days ago under "fe2o3_o3db_sync: review fixes to the interrupted delete at open -- F1: a failed unlink or directory sync while completing the delete now names the index, the data file and the phase, and says no record was changed; F3: settle no longer reads every value in the store to tell whether a lone chunk is named, since a chunked write stamps its head and every chunk with one Meta, so it asks each cache bot for the heads carrying the lone chunks' stamps (OzoneMsg::HeadsStamped, Cache::heads_stamped) and reads only those, so an unreadable value elsewhere no longer blocks the open while an unreadable head of the chunk's own write still refuses; legacy set ids: the builds of 2026-09 took the chunk set id from the key alone, so a torn same-length rewrite left the first write's head naming the second write's chunks under another stamp, and heads_stamped and settle now also match a head whose key's legacy set id is the chunk's (legacy_chunk_set_id, free fn in api.rs); F2: no Ozone user writes a Tup5u64 key, noted at the judgement; new test hooks set_delete_cut (the old data-first unlink order with an abort after the nth whole-file delete) and set_head_drop (a store drops its head after its chunks); tests/lone_index.rs gains the F1, F3, guard and two legacy tests and runs serially since the hooks are process-wide; tests/lone_index_campaign.rs re-executes a child per crash cut (16 cut images, 0 failures); red on 9f64d2fc for F1 and F3, mutants: the full-value scan reddens F3, dropping the legacy match reddens the torn legacy rewrite (Ozone interrupted GC at open, review F1-F3 + legacy set ids)"