Project

General

Profile

Actions

Bug #8516

closed

rgw: Can not get object correctly

Added by Jingjing Zhao almost 10 years ago. Updated almost 8 years ago.

Status:
Resolved
Priority:
Normal
Assignee:
-
Target version:
-
% Done:

0%

Source:
other
Tags:
Backport:
Regression:
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

For ec pool could work correctly, we adjusted the rgw_max_chunk_size to 640KB, in default it's 512KB. [you can see the details at http://tracker.ceph.com/issues/8442#change-36610]

When get object form cluster, which size was greater than 4M, the download was incomplete. The default rgw_obj_stripe_size is 4MB in default. When upload a object greater than 4M, the shadow is not 4MB, but 4.4MB actually, cause the rgw_max_chunk_size is 640KB. But when you download a object, the rgw consider each shadow is 4MB, then error occurs.

Change the rgw_obj_stripe_size to 5MB, which can be divided evenly by rgw_max_chunk_size, the get operation works correctly. Though the problem can resolved by setting parameter, this also need to fix in future.

Thanks,
Jingjing

Actions #1

Updated by Yehuda Sadeh almost 8 years ago

  • Status changed from New to Resolved

this was resolved

Actions

Also available in: Atom PDF