* [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU
@ 2020-05-19 1:32 cliff chen
2020-05-20 1:41 ` [Bug 1879425] " cliff chen
` (9 more replies)
0 siblings, 10 replies; 11+ messages in thread
From: cliff chen @ 2020-05-19 1:32 UTC (permalink / raw)
To: qemu-devel
Public bug reported:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL 7.6
CPU: 1
MEM:4G
For qemu-kvm:
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
** Affects: qemu
Importance: Undecided
Status: New
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
New
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL 7.6
CPU: 1
MEM:4G
For qemu-kvm:
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
* [Bug 1879425] Re: The thread of "CPU 0 /KVM" keeping 99.9%CPU
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
@ 2020-05-20 1:41 ` cliff chen
2020-05-20 7:23 ` cliff chen
` (8 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: cliff chen @ 2020-05-20 1:41 UTC (permalink / raw)
To: qemu-devel
one changes:
Guest VM is Red Hat Enterprise Linux 8.1 (Ootpa).
there is no issue once guest VM is RHEL7.6.
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
New
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL 7.6
CPU: 1
MEM:4G
For qemu-kvm:
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
* [Bug 1879425] Re: The thread of "CPU 0 /KVM" keeping 99.9%CPU
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
2020-05-20 1:41 ` [Bug 1879425] " cliff chen
@ 2020-05-20 7:23 ` cliff chen
2020-05-22 1:42 ` cliff chen
` (7 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: cliff chen @ 2020-05-20 7:23 UTC (permalink / raw)
To: qemu-devel
** Description changed:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
- Notes:
+ Notes:
for VM:
- OS: RHEL 7.6
- CPU: 1
- MEM:4G
- For qemu-kvm:
- 1) version:
- /usr/libexec/qemu-kvm -version
- QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
- 2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
- PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
+ OS: RHEL8.1
+ CPU: 1
+ MEM:4G
+ For qemu-kvm(host kernel RHEL7):
+ 1) version:
+ /usr/libexec/qemu-kvm -version
+ QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
+ 2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
+ PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
- 3) use "pstack 493307" and below is function trace
+ 3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
- 4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
+ 4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
- 5) use reset can recover this issue. however, it will reoccurred again.
+ 5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
New
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL8.1
CPU: 1
MEM:4G
For qemu-kvm(host kernel RHEL7):
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
* [Bug 1879425] Re: The thread of "CPU 0 /KVM" keeping 99.9%CPU
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
2020-05-20 1:41 ` [Bug 1879425] " cliff chen
2020-05-20 7:23 ` cliff chen
@ 2020-05-22 1:42 ` cliff chen
2020-05-22 5:10 ` Thomas Huth
` (6 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: cliff chen @ 2020-05-22 1:42 UTC (permalink / raw)
To: qemu-devel
Appreciate any comments or clues
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
New
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL8.1
CPU: 1
MEM:4G
For qemu-kvm(host kernel RHEL7):
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
* [Bug 1879425] Re: The thread of "CPU 0 /KVM" keeping 99.9%CPU
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
` (2 preceding siblings ...)
2020-05-22 1:42 ` cliff chen
@ 2020-05-22 5:10 ` Thomas Huth
2020-05-22 5:22 ` cliff chen
` (5 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Thomas Huth @ 2020-05-22 5:10 UTC (permalink / raw)
To: qemu-devel
Can you try with a newer version of CentOS? I think there should be newer versions of qemu-kvm-ev available, so maybe the problem is gone there.
Otherwise, please either try to reproduce this problem with upstream QEMU, or report it to the CentOS bug tracker (https://bugs.centos.org/), since we do not provide support for distribution builds in the upstream QEMU project here.
** Changed in: qemu
Status: New => Incomplete
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
Incomplete
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL8.1
CPU: 1
MEM:4G
For qemu-kvm(host kernel RHEL7):
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
* [Bug 1879425] Re: The thread of "CPU 0 /KVM" keeping 99.9%CPU
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
` (3 preceding siblings ...)
2020-05-22 5:10 ` Thomas Huth
@ 2020-05-22 5:22 ` cliff chen
2020-05-22 6:02 ` Thomas Huth
` (4 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: cliff chen @ 2020-05-22 5:22 UTC (permalink / raw)
To: qemu-devel
Hi Thomas,
Do you have any quick suggestion before report it on CentOS?
thanks
Cliff
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
Incomplete
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL8.1
CPU: 1
MEM:4G
For qemu-kvm(host kernel RHEL7):
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
* [Bug 1879425] Re: The thread of "CPU 0 /KVM" keeping 99.9%CPU
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
` (4 preceding siblings ...)
2020-05-22 5:22 ` cliff chen
@ 2020-05-22 6:02 ` Thomas Huth
2020-05-22 6:15 ` cliff chen
` (3 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Thomas Huth @ 2020-05-22 6:02 UTC (permalink / raw)
To: qemu-devel
I think you should definitely try a newer version if available -
otherwise they'll likely refuse to help you, too (nobody wants to debug
old versions when bugs are already fixed in newer ones)
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
Incomplete
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL8.1
CPU: 1
MEM:4G
For qemu-kvm(host kernel RHEL7):
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
* [Bug 1879425] Re: The thread of "CPU 0 /KVM" keeping 99.9%CPU
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
` (5 preceding siblings ...)
2020-05-22 6:02 ` Thomas Huth
@ 2020-05-22 6:15 ` cliff chen
2020-05-25 2:29 ` cliff chen
` (2 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: cliff chen @ 2020-05-22 6:15 UTC (permalink / raw)
To: qemu-devel
Got it!
BTW, you can confirm this is bug for qemu-kvm, right?
thank you!
Cliff
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
Incomplete
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL8.1
CPU: 1
MEM:4G
For qemu-kvm(host kernel RHEL7):
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
* [Bug 1879425] Re: The thread of "CPU 0 /KVM" keeping 99.9%CPU
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
` (6 preceding siblings ...)
2020-05-22 6:15 ` cliff chen
@ 2020-05-25 2:29 ` cliff chen
2021-04-22 17:31 ` Thomas Huth
2021-04-23 4:17 ` Launchpad Bug Tracker
9 siblings, 0 replies; 11+ messages in thread
From: cliff chen @ 2020-05-25 2:29 UTC (permalink / raw)
To: qemu-devel
Add the ticket link in centos
https://bugs.centos.org/view.php?id=17385
** Bug watch added: bugs.centos.org/ #17385
https://bugs.centos.org/view.php?id=17385
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
Incomplete
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL8.1
CPU: 1
MEM:4G
For qemu-kvm(host kernel RHEL7):
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
* [Bug 1879425] Re: The thread of "CPU 0 /KVM" keeping 99.9%CPU
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
` (7 preceding siblings ...)
2020-05-25 2:29 ` cliff chen
@ 2021-04-22 17:31 ` Thomas Huth
2021-04-23 4:17 ` Launchpad Bug Tracker
9 siblings, 0 replies; 11+ messages in thread
From: Thomas Huth @ 2021-04-22 17:31 UTC (permalink / raw)
To: qemu-devel
** Bug watch removed: bugs.centos.org/ #17385
https://bugs.centos.org/view.php?id=17385
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
Incomplete
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL8.1
CPU: 1
MEM:4G
For qemu-kvm(host kernel RHEL7):
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
* [Bug 1879425] Re: The thread of "CPU 0 /KVM" keeping 99.9%CPU
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
` (8 preceding siblings ...)
2021-04-22 17:31 ` Thomas Huth
@ 2021-04-23 4:17 ` Launchpad Bug Tracker
9 siblings, 0 replies; 11+ messages in thread
From: Launchpad Bug Tracker @ 2021-04-23 4:17 UTC (permalink / raw)
To: qemu-devel
[Expired for QEMU because there has been no activity for 60 days.]
** Changed in: qemu
Status: Incomplete => Expired
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1879425
Title:
The thread of "CPU 0 /KVM" keeping 99.9%CPU
Status in QEMU:
Expired
Bug description:
Hi Expert:
The VM is hung here after (2, or 3, or 5 and the longest time is 10 hours) by qemu-kvm.
Notes:
for VM:
OS: RHEL8.1
CPU: 1
MEM:4G
For qemu-kvm(host kernel RHEL7):
1) version:
/usr/libexec/qemu-kvm -version
QEMU emulator version 2.10.0(qemu-kvm-ev-2.10.0-21.el7_5.4.1)
2) once the issue is occurred, the CPU of "CPU0 /KVM" is more than 99% by com "top -p VM_pro_ID"
PID UDER PR NI RES S % CPU %MEM TIME+ COMMAND
872067 qemu 20 0 1.6g R 99.9 0.6 37:08.87 CPU 0/KVM
3) use "pstack 493307" and below is function trace
Thread 1 (Thread 0x7f2572e73040 (LWP 872067)):
#0 0x00007f256cad8fcf in ppoll () from /lib64/libc.so.6
#1 0x000055ff34bdf4a9 in qemu_poll_ns ()
#2 0x000055ff34be02a8 in main_loop_wait ()
#3 0x000055ff348bfb1a in main ()
4) use strace "strace -tt -ff -p 872067 -o cfx" and below log keep printing
21:24:02.977833 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
21:24:02.977918 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 911447}, NULL, 8) = 0 (Timeout)
21:24:02.978945 ppoll([{fd=4, events=POLLIN}, {fd=6, events=POLLIN}, {fd=8, events=POLLIN}, {fd=9, events=POLLIN}, {fd=80, events=POLLIN}, {fd=82, events=POLLIN}, {fd=84, events=POLLIN}, {fd=115, events=POLLIN}, {fd=121, events=POLLIN}], 9, {0, 0}, NULL, 8) = 0 (Timeout)
Therefore, I think the thread "CPU 0/KVM" is in tight loop.
5) use reset can recover this issue. however, it will reoccurred again.
Current work around is increase one CPU for this VM, then issue is gone.
thanks
Cliff
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1879425/+subscriptions
^ permalink raw reply [flat|nested] 11+ messages in thread
end of thread, other threads:[~2021-04-23 4:27 UTC | newest]
Thread overview: 11+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-05-19 1:32 [Bug 1879425] [NEW] The thread of "CPU 0 /KVM" keeping 99.9%CPU cliff chen
2020-05-20 1:41 ` [Bug 1879425] " cliff chen
2020-05-20 7:23 ` cliff chen
2020-05-22 1:42 ` cliff chen
2020-05-22 5:10 ` Thomas Huth
2020-05-22 5:22 ` cliff chen
2020-05-22 6:02 ` Thomas Huth
2020-05-22 6:15 ` cliff chen
2020-05-25 2:29 ` cliff chen
2021-04-22 17:31 ` Thomas Huth
2021-04-23 4:17 ` Launchpad Bug Tracker
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.