mirror of
https://github.com/ceph/ceph
synced 2025-02-10 12:32:40 +00:00
c22d5a0fce
For EC pools we have a lot of shards, and 30% probability on each one means we are very like to repeatedly fail backfill reservations.. long enough that teuthology gives up waiting. Signed-off-by: Sage Weil <sage@redhat.com>
21 lines
459 B
YAML
21 lines
459 B
YAML
overrides:
|
|
ceph:
|
|
log-whitelist:
|
|
- but it is still running
|
|
- objects unfound and apparently lost
|
|
conf:
|
|
mon:
|
|
mon osd pool ec fast read: 1
|
|
osd:
|
|
osd debug reject backfill probability: .1
|
|
osd scrub min interval: 60
|
|
osd scrub max interval: 120
|
|
osd max backfills: 3
|
|
tasks:
|
|
- thrashosds:
|
|
timeout: 1200
|
|
chance_pgnum_grow: 1
|
|
chance_pgnum_shrink: 1
|
|
chance_pgpnum_fix: 1
|
|
min_in: 4
|