[Bug 201543] chrome processes stuck at 100% cpu
bugzilla-noreply at freebsd.org
bugzilla-noreply at freebsd.org
Mon Jul 13 21:20:45 UTC 2015
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=201543
Bug ID: 201543
Summary: chrome processes stuck at 100% cpu
Product: Ports & Packages
Version: Latest
Hardware: Any
OS: Any
Status: New
Severity: Affects Some People
Priority: ---
Component: Individual Port(s)
Assignee: freebsd-ports-bugs at FreeBSD.org
Reporter: pete at nomadlogic.org
As reported in this thread:
https://lists.freebsd.org/pipermail/freebsd-chromium/2015-July/002057.html
It seems that after svn commit: r272566 chrome will get pegged at %100. I have
reproduced this locally on the following system:
> uname -ar
FreeBSD pop.rubicorp.com 10.1-RELEASE-p10 FreeBSD 10.1-RELEASE-p10 #0: Wed May
13 06:54:13 UTC 2015
root at amd64-builder.daemonology.net:/usr/obj/usr/src/sys/GENERIC amd64
It was suggested that a debug kernel would be needed to fully triage this, in
lieu of that I have the following output from dtrace that may be of some help
(pid 57340 is the pid of a chrome process consuming %100 of CPU load):
> sudo ./procsystime -a -p 57340
Tracing... Hit Ctrl-C to end...
dtrace: 81122 dynamic variable drops with non-empty dirty list
dtrace: 91681 dynamic variable drops with non-empty dirty list
dtrace: 82802 dynamic variable drops with non-empty dirty list
dtrace: 90719 dynamic variable drops with non-empty dirty list
dtrace: 89757 dynamic variable drops with non-empty dirty list
dtrace: 87624 dynamic variable drops with non-empty dirty list
dtrace: 86992 dynamic variable drops with non-empty dirty list
dtrace: 76832 dynamic variable drops with non-empty dirty list
dtrace: 78768 dynamic variable drops with non-empty dirty list
^C
dtrace: 84817 dynamic variable drops with non-empty dirty list
Elapsed Times for PID 57340,
SYSCALL TIME (ns)
geteuid 4658
gettimeofday 7242
pwrite 12306
close 18184
getpid 19218
lseek 20134
sendto 21719
fstat 21751
fcntl 47850
stat 50083
open 55702
access 66379
read 621131
write 1122555
recvmsg 3495219
fsync 28230935
__sysctl 2155674710
poll 4290330304
kevent 4616842597
_umtx_op 6004928910
TOTAL: 17101591587
CPU Times for PID 57340,
SYSCALL TIME (ns)
geteuid 473
gettimeofday 1263
getpid 1369
lseek 4377
fstat 7779
_umtx_op 9759
pwrite 11183
close 15022
sendto 16664
fcntl 31658
stat 42920
open 49495
access 61612
fsync 76978
read 273086
kevent 533407
write 597449
recvmsg 1209489
poll 2156248
__sysctl 1851122250
TOTAL: 1856222481
Syscall Counts for PID 57340,
SYSCALL COUNT
pwrite 1
sendto 3
access 4
close 4
geteuid 4
gettimeofday 4
_umtx_op 5
fsync 5
open 6
stat 6
fcntl 15
fstat 16
lseek 21
getpid 22
read 266
kevent 351
write 398
poll 605
recvmsg 1815
__sysctl 905216
TOTAL: 908767
I will attempt further testing info when I have cycles to build a debug kernel,
unless someone else beats me to it :)
--
You are receiving this mail because:
You are the assignee for the bug.
More information about the freebsd-ports-bugs
mailing list