Bug 437942
Summary: | "pfmon -t 20 --system-wide" cause segment fault | ||
---|---|---|---|
Product: | Red Hat Enterprise Linux 5 | Reporter: | Song, Youquan <youquan.song> |
Component: | pfmon | Assignee: | William Cohen <wcohen> |
Status: | CLOSED ERRATA | QA Contact: | |
Severity: | high | Docs Contact: | |
Priority: | high | ||
Version: | 5.2 | CC: | cward, fche, jvillalo, luyu, psplicha, tao |
Target Milestone: | rc | Keywords: | Reopened |
Target Release: | --- | ||
Hardware: | ia64 | ||
OS: | Linux | ||
Whiteboard: | |||
Fixed In Version: | Doc Type: | Bug Fix | |
Doc Text: | Story Points: | --- | |
Clone Of: | Environment: | ||
Last Closed: | 2009-01-20 21:23:20 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: |
Description
Song, Youquan
2008-03-18 11:08:43 UTC
Youquan, please describe the hardware you're getting this result on. Sorry. The bug was found on the platform: Hitach, with 2 Montvale CPUs. Tested the pfmon shipped with rhel 5.2 beta (3.2) on two different box with two different kernel (one is -84, another is 2.6.25-rc3), Both segment fault exactlly! Tested with pfmon 3.3-alpha , the test case just works well.. So the rhel 5.2 pfmon utility should be synced up with pfmon upstream.. any update on the bug? Youquan, probably we need a IT opened for this bug too. Thanks, Luming I will do it after validate on RHEL5.2 snapshot4, because the the pfmon/oprofile feature will update on snapshot4. This bug is not fixed at RHEL5.2 snapshot4 which include pfmon 32. It need to update to pfmon 3.2-alpha to work round. What ia64 platform was this on? There are different code paths used depending whether this is montecito or an older Itanium 2. I reproduced the problem on tiger4 with montecito. Since pfmon 3.3-alpha just works, I'm just asking for directly upgrading to pfmon 3.3-alpha for fixing this problem.I didn't try to dig out how the problem got fixed in 3.3-alpah. Please let me know your plan on this bug. Thanks, Luming Is this bug going to be fixed inl 5.2? It's too late to include this in 5.2, but I've asked if we can address it in 5.3. This request was evaluated by Red Hat Product Management for inclusion in a Red Hat Enterprise Linux maintenance release. Product Management has requested further review of this request by Red Hat Engineering, for potential inclusion in a Red Hat Enterprise Linux Update release for currently deployed products. This request is not yet committed for inclusion in an Update release. Could you include the results of "rpm -q pfmon libpfm" for the pfmon and libpfm that are causing the crash? When attempting to replicate the problem on a local ia64 machine running RHEL 5 I couldn't reproduce the crash. #rpm -q pfmon libpfm pfmon-3.2-0.060926.4.el5 libpfm-3.2-0.060926.4.el5 #cat /etc/redhat-release Red Hat Enterprise Linux Server release 5.2 (Tikanga) Same underlying issue as rhbz #231095. *** This bug has been marked as a duplicate of bug 231095 *** Re-opening bug since we have no access to Bug #231095 and can't see status on it to see if it is fixed or not. The bug is fixed with the update that will come out with RHEL5.3 beta+. pfmon-3.2-0.060926.5.el5. Please check it when able. Bug reproduced, fix verified in new version on ia64 arch. pfmon-3.2-0.060926.4.el5 :: [ PASS ] :: Testing sleep 3 :: [ PASS ] :: Testing ls /tmp :: [ PASS ] :: Testing ls /tmp -e L3_MISSES :: [ FAIL ] :: Testing --system-wide :: [ FAIL ] :: Testing -t 20 --system-wide :: [ FAIL ] :: Testing --system-wide -e L3_MISSES :: [ PASS ] :: Testing --long-show-events='CPU.*CYCLE.*' :: [ PASS ] :: Testing -i nops_retired pfmon-3.2-0.060926.5.el5 :: [ PASS ] :: Testing sleep 3 :: [ PASS ] :: Testing ls /tmp :: [ PASS ] :: Testing ls /tmp -e L3_MISSES :: [ PASS ] :: Testing --system-wide :: [ PASS ] :: Testing -t 20 --system-wide :: [ PASS ] :: Testing --system-wide -e L3_MISSES :: [ PASS ] :: Testing --long-show-events='CPU.*CYCLE.*' :: [ PASS ] :: Testing -i nops_retired Not moving to VERIFIED yet, we'll wait for Partner feedback to confirm that the fix works for them. Partners, this bug should be fixed in the latest RHEL 5.3 Snapshot. We believe that you have some interest in its correct functionality, so we're making a friendly request to send us some testing feedback. If you have a chance to test it, please share with us your findings. If you have successfully VERIFIED the fix, please add PartnerVerified to the Bugzilla keywords, along with a description of the results. Thanks! PartnerVerified. I test on Hitachi Montvale, the bug as fixed RHEL5.3 Beta. An advisory has been issued which should help the problem described in this bug report. This report is therefore being closed with a resolution of ERRATA. For more information on therefore solution and/or where to find the updated files, please follow the link below. You may reopen this bug report if the solution does not work for you. http://rhn.redhat.com/errata/RHBA-2009-0147.html |