Bug 888238 - glusterd crashes when sosreport is taken under heavy load
Summary: glusterd crashes when sosreport is taken under heavy load
Keywords:
Status: CLOSED ERRATA
Alias: None
Product: Red Hat Gluster Storage
Classification: Red Hat Storage
Component: glusterd
Version: unspecified
Hardware: Unspecified
OS: Unspecified
high
medium
Target Milestone: ---
: ---
Assignee: Krutika Dhananjay
QA Contact: Sachidananda Urs
URL:
Whiteboard:
: 892884 (view as bug list)
Depends On:
Blocks: 849601 964331
TreeView+ depends on / blocked
 
Reported: 2012-12-18 11:10 UTC by Sachidananda Urs
Modified: 2013-09-23 22:43 UTC (History)
5 users (show)

Fixed In Version: glusterfs-3.4.0qa6
Doc Type: Bug Fix
Doc Text:
Clone Of:
Environment:
Last Closed: 2013-09-23 22:39:23 UTC
Embargoed:


Attachments (Terms of Use)
Core (240.41 KB, application/x-xz)
2012-12-18 11:11 UTC, Sachidananda Urs
no flags Details
Core (348.12 KB, application/x-xz)
2013-01-08 09:31 UTC, Sachidananda Urs
no flags Details

Description Sachidananda Urs 2012-12-18 11:10:00 UTC
Generate load on the filesystem, easy way is to run compilebench.

./compilebench -D /mnt/replicate/ -i 25 -r 75

run sosreport on all the machines in a loop (atleast a few runs)... glusterd crashes.

##########################


[2012-12-18 10:05:46.567305] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.582118] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.585211] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.606251] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.613192] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.621237] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.626739] I [glusterd-handler.c:864:glusterd_handle_cli_list_friends] 0-glusterd: Received cli list req
[2012-12-18 10:05:46.628466] W [socket.c:501:__socket_rwv] 0-socket.management: readv failed (No data available)
[2012-12-18 10:05:46.639262] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.657318] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.670382] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.686864] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.703307] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.720294] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
[2012-12-18 10:05:46.752161] E [rpcsvc.c:519:rpcsvc_handle_rpc_call] 0-glusterd: Request received from non-privileged port. Failing request
pending frames:
frame : type(0) op(0)

patchset: git://git.gluster.com/glusterfs.git
signal received: 11
time of crash: 2012-12-18 10:05:46configuration details:
argp 1
backtrace 1
dlfcn 1
fdatasync 1
libpthread 1
llistxattr 1
setfsid 1
spinlock 1
epoll.h 1
xattr.h 1
st_atim.tv_nsec 1
package-string: glusterfs 3.4.0qa5
/lib64/libc.so.6[0x3517e32900]
/usr/lib64/glusterfs/3.4.0qa5/xlator/mgmt/glusterd.so(glusterd_handle_cli_statedump_volume+0x2d8)[0x7fc8768e0e08]
/usr/lib64/libglusterfs.so.0(synctask_wrap+0x12)[0x7fc87a0a94d2]
/lib64/libc.so.6[0x3517e43610]

Comment 1 Sachidananda Urs 2012-12-18 11:11:31 UTC
Created attachment 665445 [details]
Core

Comment 3 Krutika Dhananjay 2012-12-19 05:48:10 UTC
Fix merged in master : http://review.gluster.org/#change,4324

Comment 4 Sachidananda Urs 2013-01-08 09:27:51 UTC
*** Bug 892884 has been marked as a duplicate of this bug. ***

Comment 5 Sachidananda Urs 2013-01-08 09:29:23 UTC
I can still see this crash with bonnie++ running (And graph changes are done on the volume).

Comment 6 Sachidananda Urs 2013-01-08 09:31:33 UTC
Created attachment 674636 [details]
Core

Comment 7 Krutika Dhananjay 2013-01-09 06:36:56 UTC
This fix needs to be tested in glusterfs-3.4.0qa6. Moving it to MODIFIED state.

Comment 8 Amar Tumballi 2013-01-21 06:42:53 UTC
moving to ON_QA, as the qa6 build is now available.

Comment 9 Sachidananda Urs 2013-03-03 13:41:03 UTC
With some heavy load on the cluster, graph changes are made on the servers. No crash seen. Can safely close the bug.

* Ran with 4 servers, and 3 clients. Graph changes went smoothly.

Comment 10 Scott Haines 2013-09-23 22:39:23 UTC
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. 

For information on the advisory, and where to find the updated files, follow the link below.

If the solution does not work for you, open a new bug report.

http://rhn.redhat.com/errata/RHBA-2013-1262.html

Comment 11 Scott Haines 2013-09-23 22:43:43 UTC
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. 

For information on the advisory, and where to find the updated files, follow the link below.

If the solution does not work for you, open a new bug report.

http://rhn.redhat.com/errata/RHBA-2013-1262.html


Note You need to log in before you can comment on or make changes to this bug.