Project

General

Profile

Actions

Bug #9112

closed

(wip-objecter) librados notify calls freezing

Added by John Spray over 9 years ago. Updated over 9 years ago.

Status:
Resolved
Priority:
Normal
Assignee:
Category:
-
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

Hitting this in rbd tests, periodically the ceph_test_rados_fsx process gets stuck inside IoCtxImpl::notify

#0  pthread_cond_wait@@GLIBC_2.3.2 () at ../nptl/sysdeps/unix/sysv/linux/x86_64/pthread_cond_wait.S:162
#1  0x00007f7560bad863 in Cond::Wait (this=0x7fff08bfae50, mutex=...) at ./common/Cond.h:55

#2  0x00007f7560bbaab5 in librados::IoCtxImpl::notify (this=0x1778900, oid=..., ver=52, bl=...) at librados/IoCtxImpl.cc:1126
---Type <return> to continue, or q <return> to quit---
#3  0x00007f7560b8eef5 in librados::IoCtx::notify (this=0x179d130, oid=..., ver=52, bl=...) at librados/librados.cc:1407
#4  0x00007f756198b466 in librbd::notify_change (io_ctx=..., oid=..., pver=<optimized out>, ictx=<optimized out>) at librbd/internal.cc:277
#5  0x00007f756198c3af in librbd::resize_helper (ictx=0x179cfb0, size=<optimized out>, prog_ctx=...) at librbd/internal.cc:1505
#6  0x00007f756199785b in librbd::resize (ictx=0x179cfb0, size=249405062, prog_ctx=...) at librbd/internal.cc:1532
#7  0x00007f756197c105 in rbd_resize (image=<optimized out>, size=<optimized out>) at librbd/librbd.cc:732
#8  0x0000000000407fea in __librbd_resize (ctx=<optimized out>, size=249405062) at test/librbd/fsx.c:420
#9  0x000000000040929d in dowrite (offset=249387573, size=17489) at test/librbd/fsx.c:1200
#10 0x000000000040a3e6 in test () at test/librbd/fsx.c:1660
#11 0x0000000000407112 in main (argc=<optimized out>, argv=<optimized out>) at test/librbd/fsx.c:2203
Actions #1

Updated by John Spray over 9 years ago

Client log with objecter and librados debug logging at 20 in teuthology:~/jcsp/9112

Actions #2

Updated by John Spray over 9 years ago

  • Status changed from New to In Progress
Actions #3

Updated by John Spray over 9 years ago

  • Status changed from In Progress to Resolved

No longer occurring after reinstating _recalc_linger_op_target and updating related bits of code

Actions

Also available in: Atom PDF