| Summary: | [svvp][qemu-kvm]Guest hang when running Disk Stress (Logo) job if guest memory much larger than host memeory | ||
|---|---|---|---|
| Product: | Red Hat Enterprise Linux 6 | Reporter: | Mike Cao <bcao> |
| Component: | qemu-kvm | Assignee: | Vadim Rozenfeld <vrozenfe> |
| Status: | CLOSED CURRENTRELEASE | QA Contact: | Virtualization Bugs <virt-bugs> |
| Severity: | unspecified | Docs Contact: | |
| Priority: | unspecified | ||
| Version: | 6.6 | CC: | bcao, chayang, juzhang, michen, mkenneth, qzhang, rbalakri, rpacheco, virt-maint |
| Target Milestone: | rc | ||
| Target Release: | --- | ||
| Hardware: | Unspecified | ||
| OS: | Unspecified | ||
| Whiteboard: | |||
| Fixed In Version: | Doc Type: | Bug Fix | |
| Doc Text: | Story Points: | --- | |
| Clone Of: | Environment: | ||
| Last Closed: | 2015-11-05 07:19:20 UTC | Type: | Bug |
| Regression: | --- | Mount Type: | --- |
| Documentation: | --- | CRM: | |
| Verified Versions: | Category: | --- | |
| oVirt Team: | --- | RHEL 7.3 requirements from Atomic Host: | |
| Cloudforms Team: | --- | Target Upstream Version: | |
Possibly related: Bug 1040002 Hi Mike, Is it still the issue in RHEL 6.7? Thanks, Vadim. Sorry for the late response ,I still do not get the environment provided by xigao. needinfo xigao until she can provide the testing environment. Retest this issue on 2.6.32-530.el6.x86_64 qemu-kvm-rhev-0.12.1.2-2.452.el6.x86_64 virtio-win-1.7.2-2.el6.noarch Steps same as comment#0 Actual Results: Can not hit the original issue.The job can pass, qemu-kvm do not quit |
Description of problem: As I want to start -smp 64 -mem 1TB for SVVP Test but we do not have such big hosts ,Ronen suggests "Since the 64/1011 refer to the guest size, you can try to run such guest on the largest machine that you do have. The host will need a large swap partition, preferably a fast one (maybe several SSDs will do a good work)" following tests is undering this scenario Version-Release number of selected component (if applicable): qemu-kvm-0.12.1.2-2.415.el6.x86_64 seabios-0.6.1.2-28.el6.x86_64 seabios-0.6.1.2-28.el6.x86_64 How reproducible: 100% Steps to Reproduce: 1.find 2*60GB SSD card on the hosts ,make it as raid0 /dev/md0 ,then make /dev/md0 to swap partition #swapoff -a #modprobe raid456 #mdadm --create --verbose /dev/md0 --level=stripe --raid-devices=2 /dev/sdb1 /dev/sdc1 -c 4096 #mkswap /dev/md0 #swapon /dev/md0 2.# free -g total used free shared buffers cached Mem: 7 7 0 0 0 0 -/+ buffers/cache: 7 0 Swap: 111 40 71 [root@dell-op780-06 ~]# 3.Start VM with 48GB memory (win2k12R2) /usr/libexec/qemu-kvm -M rhel6.5.0 -cpu Penryn -enable-kvm -m 48G -smp 4,cores=4 -name bcao_svvp -uuid 970a2c71-2366-4069-80e5-17ac5f634648 -rtc base=localtime,clock=host,driftfix=slew -drive file=win2k12-R2-Raw,if=none,media=disk,serial=aaabbbccc,werror=stop,rerror=stop,cache=none,format=raw,id=drive-disk0 -device ide-drive,drive=drive-disk0,id=disk0,bootindex=1 -drive file=/usr/share/virtio-win/virtio-win.iso,media=cdrom,if=none,id=bb -device ide-drive,id=bb1,drive=bb -netdev tap,vhost=on,id=netdev0 -device e1000,netdev=netdev0,id=nic1,mac=00:52:11:22:37:49 -vnc :1 -vga cirrus -monitor stdio -usb -device usb-tablet,id=tablet0 -global PIIX4_PM.disable_s3=1 -global PIIX_PM.disable_s4=1 -monitor stdio 4.run Disk stress (logo) job Actual results: qemu-kvm process hang with ""(qemu) *** glibc detected *** /usr/libexec/qemu-kvm: corrupted double-linked list: 0x00007ff198b65000 *** *** glibc detected *** /usr/libexec/qemu-kvm: corrupted double-linked list: 0x00007ff198b65000 ***" Expected results: no hang occures Additional info: I think load block device can also reproceue it