Bug 692684

Summary: [Libvirt][Scale] Libvirtd hangs forever after restarting the process when ~190 qemu domains are running.
Product: Red Hat Enterprise Linux 6 Reporter: David Naori <dnaori>
Component: libvirtAssignee: Eric Blake <eblake>
Status: CLOSED INSUFFICIENT_DATA QA Contact: Virtualization Bugs <virt-bugs>
Severity: urgent Docs Contact:
Priority: high    
Version: 6.1CC: abaron, dallan, dyuan, eblake, gsun, mgoldboi, vbian, yoyzhang
Target Milestone: rc   
Target Release: ---   
Hardware: x86_64   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2011-06-14 14:42:30 UTC Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Bug Depends On:    
Bug Blocks: 682015    
Attachments:
Description Flags
gdb none

Description David Naori 2011-03-31 20:25:46 UTC
Created attachment 489218 [details]
gdb

Description of problem:
When running 190 vms on a host and restarting libvirtd, libvirtd hangs forever.

Version-Release number of selected component (if applicable):
libvirt-0.8.7-15

How reproducible:
100%

Steps to Reproduce:
1.run 190 vms
2.restart libvird
  
t a a bt full attached.

Comment 1 Daniel Veillard 2011-04-01 02:22:31 UTC
Are you sure it is "stuck" ? The daemon will try to reconnect to the
190 guests before accepting commands, it may take a while but it should
finish. If the host is overloaded by the guests it will take even longer !

Daniel

Comment 2 RHEL Program Management 2011-04-04 02:05:17 UTC
Since RHEL 6.1 External Beta has begun, and this bug remains
unresolved, it has been rejected as it is not proposed as
exception or blocker.

Red Hat invites you to ask your support representative to
propose this request, if appropriate and relevant, in the
next release of Red Hat Enterprise Linux.

Comment 4 Eric Blake 2011-04-18 14:11:38 UTC
Is this reproducible after rebooting the server, or was it only reproducible as a side effect of some other state (such as a kill -s STOP putting a VM into a stopped state)?

Comment 7 David Naori 2011-06-01 12:20:22 UTC
Haim your working on a scale environment, can you please try to reproduce it and answer eblake's question?

Comment 8 Dave Allan 2011-06-02 21:44:30 UTC
Setting cond nak design simply to reflect that we don't have a solid understanding of the situation yet.