DB
я обновляю - раза 2 уже обновлял
Size: a a a
2016 July 15
DB
но внутри одной мажорной
DB
можно попробовать то что чуваки пишут
DB
By setting
osd pg max concurrent snap trims = 0
and noscrub and nodeep-scrub, the cluster was able to finish replicating and we have then re-added all down osd's again.
But these 3 parameters/flags need to remain set to prevent "random" OSD's to go down.
osd pg max concurrent snap trims = 0
and noscrub and nodeep-scrub, the cluster was able to finish replicating and we have then re-added all down osd's again.
But these 3 parameters/flags need to remain set to prevent "random" OSD's to go down.
DB
и поглядеть - не уйдет ли
PB
слушай
PB
хотел спросить
PB
нормально будет сейчас убивать снап?
PB
ceph osd pool rmsnap pool pool-snap
PB
таким вот образом
PB
видимо вся фигня именно из-за снапов и пошла
DB
да - скорее всего
PB
да - скорее всего
это к безопасности?
PB
626 requests are blocked > 32 sec
PB
2889 requests are blocked > 32 sec
PB
12930 requests are blocked > 32 sec