Bug 589706

Summary: qpid-cpp broker and clients throw invalid fastbin errors running tests under RHEL-6
Product: Red Hat Enterprise Linux 6 Reporter: Kim van der Riet <kim.vdriet>
Component: glibcAssignee: Andreas Schwab <schwab>
Status: CLOSED CURRENTRELEASE QA Contact: Petr Muller <pmuller>
Severity: urgent Docs Contact:
Priority: high    
Version: 6.0CC: drepper, fweimer, gsim, iboverma, ohudlick, pmuller, sghosh, syeghiay
Target Milestone: rc   
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: glibc-2.12-1.1.el6.1 Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2010-11-11 14:39:30 UTC Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:
Bug Depends On: 593396    
Bug Blocks: 587694    
Attachments:
Description Flags
test case
none
A similar but smaller test case none

Description Kim van der Riet 2010-05-06 17:57:12 UTC 
Running longer stress-tests against the qpid-cpp broker causes either the client (perftest) or the broker to crash with a glibc error:

invalid fastbin entry (free)

If a longer test is used, the probability of a crash is close to certain. The "invalid fastbin entry (!prev)" message is also seen, as are memory corruption messages.

Why this should be showing up only on RHEL-6 (and rawhide) is not clear.

The following test shows up the problem with reasonable consistency:

perftest --iterations 1 --summary --unique-data yes --log-enable info+ --mode topic --qt 1 --durable yes --npubs 2 --nsubs 3 --count 200000 --size 1024 --tx 0 --async-commit no

(perftest is not part of the core RHEL-6 packages, it is in the -devel packages in the MRG channel).
Comment 1 Kim van der Riet 2010-05-06 18:00:59 UTC 
I recommend this be set to blocker status. (I cannot set that myself).
Comment 4 Gordon Sim 2010-05-18 17:43:31 UTC 
Created attachment 414914 [details]
test case

I suspect there is a glibc problem. The attached test program uses no qpid code at all and exhibits the same symptom. As far as I can tell it has no errors in it.
Comment 5 Gordon Sim 2010-05-18 17:47:32 UTC 
Created attachment 414915 [details]
A similar but smaller test case

This requires the -std=c++0x option on compilation; it replaces the trivial wrappers around pthreads used in the previous test code with the std equivalents. It also exhibits the same symptom after a very short period (usually < 1 minute).
Comment 6 Gordon Sim 2010-05-19 18:33:06 UTC 
Fixed in glibc-2.12-1.1.el6.1
Comment 7 Gordon Sim 2010-05-19 18:33:53 UTC 
*** Bug 587694 has been marked as a duplicate of this bug. ***
Comment 10 releng-rhel@redhat.com 2010-11-11 14:39:30 UTC 
Red Hat Enterprise Linux 6.0 is now available and should resolve
the problem described in this bug report. This report is therefore being closed
with a resolution of CURRENTRELEASE. You may reopen this bug report if the
solution does not work for you.