Hi,
we have a problem with rgw bilogs not being trimmed. This is a multisite with 2 sites on
Nautilius 14.2.18, sync status is fine. radosgw-admin bilog list grows especially for
buckets with lots of deletes.
So from time to time we get this "large OMAP" warnings, which we easily fix with
bilog trim on the affected buckets and deep-scrubbing the PG.
As this is annoying I digged deeper and found these errors occurring 16 times in a batch
for random buckets. It seems to affect every bucket. I think this is related to
autotrimming which is not working in our case. The command "radosgw-admin bilog
autotrim" shows the same messages (and does no trimming):
ERROR: failed to get bucket instance info for
.bucket.meta.57d082821ddc45a097b2e3401388e93d/mybucket:feec71ec-408e-4a2b-b3bd-4d214e7c8685.7724460.7
But these are buckets/instances that exists (no shards btw):
radosgw-admin metadata get
bucket.instance:57d082821ddc45a097b2e3401388e93d/mybucket:feec71ec-408e-4a2b-b3bd-4d214e7c8685.7724460.7
{
"key":
"bucket.instance:57d082821ddc45a097b2e3401388e93d/mybucket:feec71ec-408e-4a2b-b3bd-4d214e7c8685.7724460.7",
"ver": {
"tag": "_2pmP8x8r0exeEyQ7pn2r0nG",
"ver": 1
},
"mtime": "2020-01-20 08:52:34.220312Z",
"data": {
"bucket_info": {
"bucket": {
"name": "mybucket",
"marker":
"feec71ec-408e-4a2b-b3bd-4d214e7c8685.7724460.7",
"bucket_id":
"feec71ec-408e-4a2b-b3bd-4d214e7c8685.7724460.7",
"tenant": "57d082821ddc45a097b2e3401388e93d",
Does that look familiar to anyone? Any ideas where to dig further?
Best regards,
Björn
Show replies by date