Actions
Bug #51127
closedIndex pool not cleaned up after bucket deletion
Status:
Duplicate
Priority:
Normal
Assignee:
-
Target version:
-
% Done:
0%
Source:
Tags:
rgw multisite index shard omap
Backport:
Regression:
No
Severity:
2 - major
Reviewed:
Affected Versions:
ceph-qa-suite:
rgw
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
Hi,
in my 3 sites multisites setup I just see that on some sites the index pool still has the index files and in SGP even have the omaps which is causes large omap in the cluster.
HGK is the master, ASH and SGP is the secondary, let me show 1 shard in all DCs (FYI the bucket has been deleted which is relates to this bucket index).
HKG and ASH give back empty command output for this:
rados -p hkg or ash.rgw.buckets.index listomapvals .dir.9213182a-14ba-48ad-bde9-289a1c0c0de8.5411362.1.23219
However in SGP it's full with values like this:
ycsappfeed-images/area_id/572303/city_id/23053/country_id/35/datadate/2021-01-28/language_id/1/white_label_id/1/report_id/8/report#STD.jpg value (333 bytes) : 00000000 08 03 47 01 00 00 8a 00 00 00 79 63 73 61 70 70 |..G.......ycsapp| 00000010 66 65 65 64 2d 69 6d 61 67 65 73 2f 61 72 65 61 |feed-images/area| 00000020 5f 69 64 2f 35 37 32 33 30 33 2f 63 69 74 79 5f |_id/572303/city_| 00000030 69 64 2f 32 33 30 35 33 2f 63 6f 75 6e 74 72 79 |id/23053/country| 00000040 5f 69 64 2f 33 35 2f 64 61 74 61 64 61 74 65 2f |_id/35/datadate/| 00000050 32 30 32 31 2d 30 31 2d 32 38 2f 6c 61 6e 67 75 |2021-01-28/langu| 00000060 61 67 65 5f 69 64 2f 31 2f 77 68 69 74 65 5f 6c |age_id/1/white_l| 00000070 61 62 65 6c 5f 69 64 2f 31 2f 72 65 70 6f 72 74 |abel_id/1/report| 00000080 5f 69 64 2f 38 2f 72 65 70 6f 72 74 23 53 54 44 |_id/8/report#STD| 00000090 2e 6a 70 67 2e 7f 32 00 00 00 00 00 01 07 03 61 |.jpg..2........a| 000000a0 00 00 00 01 1c 1d 00 00 00 00 00 00 33 4c 1a 60 |............3L.`| 000000b0 79 81 72 0b 20 00 00 00 65 31 35 66 65 37 32 32 |y.r. ...e15fe722| 000000c0 64 62 31 65 39 30 65 36 37 32 63 61 65 35 65 64 |db1e90e672cae5ed| 000000d0 39 39 39 66 61 65 65 36 03 00 00 00 70 69 78 03 |999faee6....pix.| 000000e0 00 00 00 70 69 78 09 00 00 00 69 6d 61 67 65 2f |...pix....image/| 000000f0 6a 70 67 1c 1d 00 00 00 00 00 00 00 00 00 00 00 |jpg.............| 00000100 00 00 00 00 00 00 00 00 00 00 00 00 01 01 06 00 |................| 00000110 00 00 18 84 2e 7f 32 00 82 8e 02 20 00 00 00 5f |......2.... ..._| 00000120 6b 6a 47 75 70 4d 30 66 76 4e 38 37 65 39 6c 34 |kjGupM0fvN87e9l4| 00000130 42 68 70 4f 48 69 63 68 57 31 43 42 50 63 58 00 |BhpOHichW1CBPcX.| 00000140 00 00 00 00 00 00 00 00 00 00 00 00 00 |.............| 0000014d
The bucket with this id is not available anywhere:
9213182a-14ba-48ad-bde9-289a1c0c0de8.5411362.1
Why it is not cleaned up? How can I cleanup the index pool with any unnecessary entries?
Thank you
Updated by Ist Gab almost 3 years ago
In Sin let me show one omap value entry in the log:
2021-06-08T18:55:14.137383+0700 osd.41 (osd.41) 1218 : cluster [WRN] Large omap object found. Object: 20:3804cbdf:::.dir.9213182a-14ba-48ad-bde9-289a1c0c0de8.29868038.2.7:head PG: 20.fbd3201c (20.1c) Key count: 245027 Size (bytes): 69761281 2021-06-08T18:55:15.785761+0700 osd.41 (osd.41) 1219 : cluster [WRN] Large omap object found. Object: 20:3b4ffa50:::.dir.9213182a-14ba-48ad-bde9-289a1c0c0de8.29868038.2.10:head PG: 20.a5ff2dc (20.1c) Key count: 244808 Size (bytes): 69703662
Updated by Casey Bodley almost 3 years ago
- Is duplicate of Bug #20802: rgw multisite: clean up deleted bucket instance and index objects added
Actions