Bug 762445 (GLUSTER-713)

Summary: fsx tool segfaults in readahead and iocache
Product: [Community] GlusterFS Reporter: Raghavendra Bhat <rabhat>
Component: stripeAssignee: Amar Tumballi <amarts>
Status: CLOSED CURRENTRELEASE QA Contact:
Severity: medium Docs Contact:
Priority: medium    
Version: mainlineCC: amarts, gluster-bugs, vraman
Target Milestone: ---   
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: RTA Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:

Description Amar Tumballi 2010-03-11 10:20:47 UTC
This is another version of issue reported in 'bug 762268'. This bug can be fixed by more proper logic to fill in the holes in readv_cbk of stripe.

Comment 1 Raghavendra Bhat 2010-03-11 12:48:16 UTC
The fsx tools segfaults when readahead and iocache perforance translators(any onr of them or both)are loaded. It generates the core.

This is the output generated....

root@bigbang:/mnt/hd# /opt/qa/tools/fsx -R -W -N 100 read mapped writes DISABLED
truncating to largest ever: 0x32740
truncating to largest ever: 0x39212
truncating to largest ever: 0x3bae9
truncating to largest ever: 0x3c1e3
short read: 0x3c5c bytes instead of 0x6450
LOG DUMP (93 total operations):
1(1 mod 256): WRITE	0x1f7e6 thru 0x2250e	(0x2d29 bytes) HOLE
2(2 mod 256): WRITE	0x10f13 thru 0x16b11	(0x5bff bytes)
3(3 mod 256): READ	0x1f48a thru 0x2250e	(0x3085 bytes)
4(4 mod 256): READ	0x16511 thru 0x2250e	(0xbffe bytes)
5(5 mod 256): READ	0x21699 thru 0x2250e	(0xe76 bytes)
6(6 mod 256): READ	0x300 thru 0xe2e8	(0xdfe9 bytes)
7(7 mod 256): READ	0x891 thru 0x9083	(0x87f3 bytes)
8(8 mod 256): READ	0x19c62 thru 0x20cbd	(0x705c bytes)
Segmentation fault (core dumped)



The command ran is fsx -R -W -N <file to be operated on>. This is seen in 3.0.3rc1. But in dht even with those translators loaded this is not seen. In stripe just with stripe(without any performance translators or without readahead and iocache)it passes.

Comment 2 Anand Avati 2010-03-25 09:49:07 UTC
PATCH: http://patches.gluster.com/patch/2970 in master (stripe: proper fix for reading 'holes')

Comment 3 Anand Avati 2010-03-25 09:49:14 UTC
PATCH: http://patches.gluster.com/patch/2968 in release-3.0 (stripe: proper fix for reading 'holes')