Ceph

02/15/2019

02:06 AM RADOS Bug #38012: osd bad crc cause the whole cluster stop accepting new request.

Josh Durgin wrote:
> It seems the first step would be reporting the crc mismatches via a perfcounter. Then the mgr c... frank lin

01/24/2019

01:38 AM RADOS Bug #38012: osd bad crc cause the whole cluster stop accepting new request.

Josh Durgin wrote:
> This is likely to be bad networking hardware - the CRC at the ceph level that is failing is des... frank lin

01/23/2019

09:18 AM RADOS Bug #38012 (New): osd bad crc cause the whole cluster stop accepting new request.

I have encounter this problem both on jewel cluster and luminous cluster.
The symptom is some request will be blocke... frank lin

09/13/2018

08:49 AM RADOS Bug #35808: ceph osd ok-to-stop result dosen't match the real situation

xie xingguo wrote:
> I see you are using a pool min_size of 3, so no replicas is allowed to be offline and hence the... frank lin

08:46 AM RADOS Bug #35808: ceph osd ok-to-stop result dosen't match the real situation

John Spray wrote:
> It's a little bit odd that the ok-to-stop command said 4 PGs, but you actually had 5 PGs go inco... frank lin

09/06/2018

09:01 AM RADOS Bug #35808 (Rejected): ceph osd ok-to-stop result dosen't match the real situation

The cluster is in healthy status, when I tried to run ceph osd ok-to-stop 0 it returns... frank lin

05/30/2018

01:58 PM RADOS Bug #24327: osd: segv in pg_log_entry_t::encode()

Sage Weil wrote:
> This crash doesn't look familiar, and it's not clear to me what might cause segfault here. Do yo... frank lin

05/29/2018

07:37 AM RADOS Bug #24327 (Need More Info): osd: segv in pg_log_entry_t::encode()

The affected osd restarted itself and everything seems fine then.But what is the cause of the crash?... frank lin

01/22/2018

06:00 AM bluestore Bug #22616: bluestore_cache_data uses too much memory

I did some test with bluestore_default_buffered_read = false
The bluestore_cache_data now only use around a fe... frank lin

01/19/2018

03:28 PM bluestore Bug #22616: bluestore_cache_data uses too much memory

Sage Weil wrote:
> Two things to try:
>
> - bluestore_default_buffered_read = false should make the problem go aw... frank lin