Hi Xuehan, Are there any smartctl warnings for the drives that OSD is associated with?  Probably the first step is to verify that the HW and OS are still functioning/sane.  These days I don't see as many problems, but in the past we've run into (consumer grade) HW that lied about durability to gain performance.  We also occasionally used to run into situations in the filestore days where inexplicably -o nobarrier was set on the mount and no one knew how. :P It certainly could be a bug in Ceph, but my first course of action in these kinds of situations is to look at the whole system and any potential points of corruption in the entire write path and start minimizing the problem space by ruling things out.  If you think the HW and OS are all functioning correctly, the next step would be to investigate the state of that object to see if you can determine what was being done to it that left it in the corrupted state.  Not easy work, but it might help shed light on what's going on. The good news is that bluestore actually detected the crc mismatch. Mark On 4/27/21 3:54 AM, 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@ceph.io To unsubscribe send an email to dev-leave@ceph.io