On 27/04/2021 10:54, Xuehan Xu wrote:
Hi, everyone. Recently, one of our online cluster experienced a whole cluster power outage, and after the power recovered, many osd started to log the following error: 2021-04-27 15:38:05.503 2b372b957700 -1 bluestore(/var/lib/ceph/osd/ceph-3) _verify_csum bad crc32c/0x1000 checksum at blob offset 0x36000, got 0x41fe1397, expected 0x8d7f5975, device location [0xa7e76000~1000], logical extent 0x1b6000~1000, object #9:45a4e02a:::rbd_data.3b35df93038d.0000000000000095:head# 2021-04-27 15:38:05.504 2b372b957700 -1 bluestore(/var/lib/ceph/osd/ceph-3) _verify_csum bad crc32c/0x1000 checksum at blob offset 0x36000, got 0x41fe1397, expected 0x8d7f5975, device location [0xa7e76000~1000], logical extent 0x1b6000~1000, object #9:45a4e02a:::rbd_data.3b35df93038d.0000000000000095:head# 2021-04-27 15:38:05.505 2b372b957700 -1 bluestore(/var/lib/ceph/osd/ceph-3) _verify_csum bad crc32c/0x1000 checksum at blob offset 0x36000, got 0x41fe1397, expected 0x8d7f5975, device location [0xa7e76000~1000], logical extent 0x1b6000~1000, object #9:45a4e02a:::rbd_data.3b35df93038d.0000000000000095:head# 2021-04-27 15:38:05.506 2b372b957700 -1 bluestore(/var/lib/ceph/osd/ceph-3) _verify_csum bad crc32c/0x1000 checksum at blob offset 0x36000, got 0x41fe1397, expected 0x8d7f5975, device location [0xa7e76000~1000], logical extent 0x1b6000~1000, object #9:45a4e02a:::rbd_data.3b35df93038d.0000000000000095:head# 2021-04-27 15:38:28.379 2b372c158700 -1 bluestore(/var/lib/ceph/osd/ceph-3) _verify_csum bad crc32c/0x1000 checksum at blob offset 0x40000, got 0xce935e16, expected 0x9b502da7, device location [0xa9a80000~1000], logical extent 0x80000~1000, object #9:c2a6d9ae:::rbd_data.3b35df93038d.0000000000000696:head# We are using Nautilus 14.2.10 version, and we put rocksdb on top of SSDs while bluestore data on SATA disks. It seems that the BlueStore didn't survive the power outage, is it supposed to behave this way? Is there any way to prevent it? Thanks:-) _______________________________________________ Dev mailing list -- dev@xxxxxxx To unsubscribe send an email to dev-leave@xxxxxxx
it could also happen due to low cost consumer SSD drives, the majority do not support Power Loss Protection (PLP). PLP is different than support for sync/flush which is the supported by nearly all SSDs, as i understand SSDs do a read/edit/erase/write cycle in larger blocks of 64-256KB and without PLP could lose data during the erase phase in case of power loss. Always use enterprise grade SSDs for this as well as other reasons like DWPD..etc
A while ago we spent about a month doing power failure tests testing durability of dm-writecache while writing high throughput and iops, we would get 1 or 2 failures out of 10 power cycles when using cheap SSDs ranging from inconsistent pgs to unfound objects, we would get no problems when using drives with PLP.
/Maged _______________________________________________ Dev mailing list -- dev@xxxxxxx To unsubscribe send an email to dev-leave@xxxxxxx
