[ceph-users] Heavy rocksdb activity in newly added osd

Hi All We had a cluster (v13.2.4) with 32 osds in total. At first, an osd (osd.18) in cluster was down. So, we tried to remove the osd and added a new one (osd.32) with new ID. We unplugged the disk (osd.18) and plugged in a new disk in the same slot and add osd.32 into cluster. Then, osd.32 was b

[ceph-users] It takes long time for a newly added osd booting to up state due to heavy rocksdb activity

Hi All We had a cluster (v13.2.4) with 32 osds in total. At first, an osd (osd.18) in cluster was down. So, we tried to remove the osd and added a new one (osd.32) with new ID. We unplugged the disk (osd.18) and plugged in a new disk in the same slot and add osd.32 into cluster. Then, osd.32 was b

[ceph-users] Re: bluestore: osd bluestore_allocated is much larger than bluestore_stored

Understand.Thank you! Best Jerry Igor Fedotov 於 2020年7月9日 週四 18:56 寫道： > Hi Jerry, > > we haven't heard about frequent occurrences of this issue and the backport > didn't look trivial hence we decided to omit it for M and L. > > > Thanks, > > Igor > On

[ceph-users] Re: bluestore: osd bluestore_allocated is much larger than bluestore_stored

Hi Igor We are curious why blob garbage collection is not backported to mimic or luminous? https://github.com/ceph/ceph/pull/28229 Thanks Jerry Jerry Pu 於 2020年7月8日 週三 下午6:04寫道： > OK. Thanks for your reminder. We will think about how to make the > adjustment to our cluster. > >

[ceph-users] Re: bluestore: osd bluestore_allocated is much larger than bluestore_stored

OK. Thanks for your reminder. We will think about how to make the adjustment to our cluster. Best Jerry Pu Igor Fedotov 於 2020年7月8日 週三 下午5:40寫道： > Please note that simple min_alloc_size downsizing might negatively impact > OSD performance. That's why this modification has been pos

[ceph-users] Re: bluestore: osd bluestore_allocated is much larger than bluestore_stored

Thanks for your reply. It's helpful! We may consider to adjust min_alloc_size to a lower value or take other actions based on your analysis for space overhead with EC pools. Thanks. Best Jerry Pu Igor Fedotov 於 2020年7月7日 週二 下午4:10寫道： > I think you're facing the issue covered by

[ceph-users] bluestore: osd bluestore_allocated is much larger than bluestore_stored

Hi: We have a cluster (v13.2.4), and we do some tests on a EC k=2, m=1 pool "VMPool0". We deploy some VMs (Windows, CentOS7) on the pool and then use IOMeter to write data to these VMs. After a period of time, we observe a strange thing that pool actual usage is much larger than stored da