Source cleanup treated a retryable conflict such as a lock acquisition
timeout as a permanent cleanup warning. The warning was persisted, mapped
the pool to failed_ignored, and blocked pool completion for the rest of
the run while the source replica stayed on disk. Retryable storage
failures now defer the bucket instead, and only non-retryable failures
keep a permanent warning, so completion still requires a resolved delete
or a successful not-found check.
Recording a bucket deferral no longer overwrites the pool's pending
migration-deferral marker, because that marker is the only signal keeping
a pool from completing at the free-space goal while an entry is retried.
Teach the transient matchers the rendered lock timeout text, unwrap
data-movement stage context before classifying not-found and transient
cleanup failures, and raise the bounded source cleanup deferral budget.
cxymds
a58ac62618