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
| Operation | Author | What | When | |
|---|---|---|---|---|
| + | r1870400018:69615 | replica 1870400018 | created fe2o3_o3db_sync/src/api/pending.rs | 42 days ago under "Merge branch 'main' into dozone-a3-fix2" |
| + | r1870400018:69616 | replica 1870400018 | inserted 15.5 KiB | 42 days ago under "Merge branch 'main' into dozone-a3-fix2" |
| + | r1870400018:69867 | replica 1870400018 | inserted 608 bytes | 42 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)" |
| + | r1870400018:70079 | replica 1870400018 | inserted 765 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70080 | replica 1870400018 | inserted 31 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70081 | replica 1870400018 | inserted 17 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70082 | replica 1870400018 | inserted 41 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70083 | replica 1870400018 | replaced 47 bytes with 41 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70084 | replica 1870400018 | replaced 14 bytes with 677 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70085 | replica 1870400018 | replaced 48 bytes with 61 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70086 | replica 1870400018 | replaced 94 bytes with 135 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70087 | replica 1870400018 | inserted 75 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70088 | replica 1870400018 | inserted 57 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70089 | replica 1870400018 | replaced 26 bytes with 45 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70090 | replica 1870400018 | replaced 8 bytes with 6 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70091 | replica 1870400018 | replaced 19 bytes with 446 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70092 | replica 1870400018 | replaced 24 bytes with 38 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70093 | replica 1870400018 | inserted 1 byte | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70094 | replica 1870400018 | replaced 42 bytes with 5 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70095 | replica 1870400018 | replaced 9 bytes with 1 byte | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70096 | replica 1870400018 | replaced 1 byte with 9 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70097 | replica 1870400018 | replaced 25 bytes with 160 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70100 | replica 1870400018 | replaced 3 bytes with 25 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70101 | replica 1870400018 | replaced 141 bytes with 361 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70102 | replica 1870400018 | replaced 511 bytes with 296 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70103 | replica 1870400018 | replaced 13 bytes with 21 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70104 | replica 1870400018 | replaced 17 bytes with 1.6 KiB | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70105 | replica 1870400018 | replaced 7 bytes with 39 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70106 | replica 1870400018 | replaced 14 bytes with 36 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70107 | replica 1870400018 | inserted 14 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70108 | replica 1870400018 | inserted 29 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70109 | replica 1870400018 | inserted 29 bytes | 42 days ago under "Merge origin/main into dozone-chunkset" |
| + | r1870400018:70217 | replica 1870400018 | replaced 14 bytes with 23 bytes | 42 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." |
| + | r1870400018:70303 | replica 1870400018 | replaced 295 bytes with 740 bytes | 42 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." |
| + | r1870400018:70304 | replica 1870400018 | replaced 316 bytes with 73 bytes | 42 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." |
| + | r1870400018:70305 | replica 1870400018 | replaced 8 bytes with 80 bytes | 42 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." |
| + | r1870400018:70306 | replica 1870400018 | inserted 27 bytes | 42 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." |
| + | r1870400018:70307 | replica 1870400018 | inserted 24 bytes | 42 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." |
| + | r1870400018:70309 | replica 1870400018 | replaced 56 bytes with 30 bytes | 42 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." |
| + | r1870400018:70310 | replica 1870400018 | replaced 2 bytes with 58 bytes | 42 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." |
| + | r1870400018:70311 | replica 1870400018 | inserted 11 bytes | 42 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." |
| + | r1870400018:70312 | replica 1870400018 | inserted 139 bytes | 42 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." |
| + | r1870400018:70313 | replica 1870400018 | inserted 100 bytes | 42 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." |
| + | r1870400018:70314 | replica 1870400018 | inserted 41 bytes | 42 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." |
| + | r1870400018:70315 | replica 1870400018 | replaced 80 bytes with 97 bytes | 42 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." |
| + | r1870400018:70316 | replica 1870400018 | inserted 55 bytes | 42 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." |
| + | r1870400018:70317 | replica 1870400018 | replaced 92 bytes with 273 bytes | 42 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." |
| + | r1870400018:70318 | replica 1870400018 | inserted 22 bytes | 42 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." |
| + | r1870400018:70319 | replica 1870400018 | replaced 76 bytes with 209 bytes | 42 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." |
| + | r1870400018:70320 | replica 1870400018 | replaced 260 bytes with 317 bytes | 42 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." |
| + | r1870400018:70322 | replica 1870400018 | inserted 14 bytes | 42 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." |
| + | r1870400018:70323 | replica 1870400018 | inserted 111 bytes | 42 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." |
| + | r1870400018:70324 | replica 1870400018 | inserted 72 bytes | 42 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." |
| + | r1870400018:70325 | replica 1870400018 | replaced 341 bytes with 1.0 KiB | 42 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." |
| + | r1870400018:70326 | replica 1870400018 | replaced 91 bytes with 1.7 KiB | 42 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." |
| + | r1870400018:70327 | replica 1870400018 | replaced 38 bytes with 176 bytes | 42 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." |
| + | r1870400018:70328 | replica 1870400018 | inserted 11 bytes | 42 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." |
| + | r1870400018:70329 | replica 1870400018 | replaced 42 bytes with 7 bytes | 42 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." |
| + | r1870400018:70331 | replica 1870400018 | replaced 260 bytes with 551 bytes | 42 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." |
| + | r1870400018:70449 | replica 1870400018 | replaced 6 bytes with 4 bytes | 42 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)" |
| + | r1870400018:70450 | replica 1870400018 | replaced 3 bytes with 4 bytes | 42 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)" |
| + | r1870400018:70451 | replica 1870400018 | inserted 74 bytes | 42 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)" |
| + | r1870400018:70452 | replica 1870400018 | inserted 216 bytes | 42 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)" |
| + | r1870400018:70906 | replica 1870400018 | replaced 44 bytes with 22 bytes | 40 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)" |
| + | r1870400018:70907 | replica 1870400018 | inserted 4 bytes | 40 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)" |
| + | r1870400018:70909 | replica 1870400018 | inserted 4 bytes | 40 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)" |
| + | r1870400018:70911 | replica 1870400018 | inserted 4 bytes | 40 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)" |
| + | r1870400018:70913 | replica 1870400018 | inserted 4 bytes | 40 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)" |
| + | r1870400018:70915 | replica 1870400018 | inserted 4 bytes | 40 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)" |
| + | r1870400018:70917 | replica 1870400018 | inserted 4 bytes | 40 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)" |
| + | r1870400018:70918 | replica 1870400018 | replaced 743 bytes with 682 bytes | 40 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)" |
| + | r1870400018:70920 | replica 1870400018 | inserted 23 bytes | 40 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)" |
| + | r1870400018:70923 | replica 1870400018 | replaced 127 bytes with 51 bytes | 40 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)" |
| + | r1870400018:70924 | replica 1870400018 | replaced 16 bytes with 4 bytes | 40 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)" |
| + | r1870400018:70925 | replica 1870400018 | inserted 6 bytes | 40 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)" |
| + | r1870400018:70926 | replica 1870400018 | inserted 48 bytes | 40 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)" |
| + | r1870400018:70927 | replica 1870400018 | inserted 11 bytes | 40 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)" |
| + | r1870400018:70928 | replica 1870400018 | inserted 32 bytes | 40 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)" |
| + | r1870400018:70929 | replica 1870400018 | replaced 10 bytes with 7 bytes | 40 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)" |
| + | r1870400018:70931 | replica 1870400018 | replaced 423 bytes with 345 bytes | 40 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)" |
| + | r1870400018:70932 | replica 1870400018 | replaced 4 bytes with 4 bytes | 40 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)" |
| + | r1870400018:70933 | replica 1870400018 | replaced 32 bytes with 277 bytes | 40 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)" |
| + | r1870400018:72476 | replica 1870400018 | inserted 148 bytes | 40 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)" |