Home » General » Support » OOM didn't save the machine
| Re: OOM didn't save the machine [message #35490 is a reply to message #35486] |
Mon, 30 March 2009 19:24   |
lazy
Messages: 16
Registered: January 2008
|
Junior Member |
|
|
Thank's for Your answer.
It's possible the "leak" started after the machine was rsynced (f
Now it's happening again, apache process is using 100% cpu, I can't enter the vps beancounters bellow
3000: kmemsize 68901194 68920466 668435456 836870912 0
lockedpages 0 0 2562 2562 0
privvmpages 157683 171574 512000 537600 0
shmpages 284 284 15374 15374 0
dummy 0 0 0 0 0
numproc 98 127 2000 2000 0
physpages 50345 59833 0 9223372036854775807 0
vmguarpages 0 0 35236 9223372036854775807 0
oomguarpages 50345 59833 35236 9223372036854775807 0
numtcpsock 15 95 2000 2000 0
numflock 1 13 1000 1100 0
numpty 0 1 200 200 0
numsiginfo 1 30 1024 1024 0
tcpsndbuf 178640 1460304 9300923 17492923 0
tcprcvbuf 1296 286512 638976 1048576 0
othersockbuf 11600 1270944 4650461 12842461 0
dgramrcvbuf 0 4368 4650461 4650461 0
numothersock 9 33 8000 9000 0
dcachesize 0 0 11452893 11796480 0
numfile 3101 4801 20480 20480 0
dummy 0 0 0 0 0
dummy 0 0 0 0 0
dummy 0 0 0 0 0
numiptent 10 10 200 200 0
0: kmemsize 49891537 49960180 9223372036854775807 9223372036854775807 0
lockedpages 0 0 9223372036854775807 9223372036854775807 0
privvmpages 6277 18544 9223372036854775807 9223372036854775807 0
shmpages 647 663 9223372036854775807 9223372036854775807 0
dummy 0 0 9223372036854775807 9223372036854775807 0
numproc 90 98 9223372036854775807 9223372036854775807 0
physpages 3690 15435 9223372036854775807 9223372036854775807 0
vmguarpages 0 0 9223372036854775807 9223372036854775807 0
oomguarpages 3697 15435 9223372036854775807 9223372036854775807 0
numtcpsock 5 6 9223372036854775807 9223372036854775807 0
numflock 1 7 9223372036854775807 9223372036854775807 0
numpty 4 4 9223372036854775807 9223372036854775807 0
numsiginfo 1 3 9223372036854775807 9223372036854775807 0
tcpsndbuf 85216 698000 9223372036854775807 9223372036854775807 0
tcprcvbuf 81920 1312608 9223372036854775807 9223372036854775807 0
othersockbuf 9280 24832 9223372036854775807 9223372036854775807 0
dgramrcvbuf 0 8464 9223372036854775807 9223372036854775807 0
numothersock 22 27 9223372036854775807 9223372036854775807 0
dcachesize 0 0 9223372036854775807 9223372036854775807 0
numfile 1680 1825 9223372036854775807 9223372036854775807 0
dummy 0 0 9223372036854775807 9223372036854775807 0
dummy 0 0 9223372036854775807 9223372036854775807 0
dummy 0 0 9223372036854775807 9223372036854775807 0
numiptent 10 10 9223372036854775807 9223372036854775807 0
this apache is heavly modified and it can be stuck in some recvmsg, i cant kill -9, memory is starting to be eaten
meminfo from hn
MemTotal: 8161180 kB
MemFree: 55608 kB
Buffers: 114284 kB
Cached: 2716572 kB
SwapCached: 0 kB
Active: 3450172 kB
Inactive: 2065236 kB
HighTotal: 0 kB
HighFree: 0 kB
LowTotal: 8161180 kB
LowFree: 55608 kB
SwapTotal: 1023992 kB
SwapFree: 1023964 kB
Dirty: 9504 kB
Writeback: 188 kB
AnonPages: 2683688 kB
Mapped: 28620 kB
Slab: 2479572 kB
PageTables: 32560 kB
NFS_Unstable: 0 kB
Bounce: 0 kB
CommitLimit: 5104580 kB
Committed_AS: 4361756 kB
VmallocTotal: 34359738364 kB
VmallocUsed: 273424 kB
VmallocChunk: 34359464744 kB
vps are eating total 2,6G physp + 2,6G cache and 140M free
any pointers how to kill that vps, i'm thinging about taking away its privvmpages and thus forcing oom
this process is untracable
its wchan is init_level4_pg, and is eating 100% cpu
vzctl enter 3000 ends
brk(0xa41e000) = 0xa41e000
rt_sigaction(SIGPIPE, {SIG_IGN}, NULL,  = 0
open("/etc/vz/vz.conf", O_RDONLY) = 3
stat("/etc/vz/vz.conf", {st_mode=S_IFREG|0644, st_size=1103, ...}) = 0
fstat(3, {st_mode=S_IFREG|0644, st_size=1103, ...}) = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x2b3071a0b000
read(3, "## Global parameters\nVIRTUOZZO=y"..., 4096) = 1103
read(3, "", 4096) = 0
close(3) = 0
munmap(0x2b3071a0b000, 4096) = 0
open("/var/log/vzctl.log", O_WRONLY|O_APPEND|O_CREAT, 0666) = 3
fstat(3, {st_mode=S_IFREG|0644, st_size=0, ...}) = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x2b3071a0b000
fstat(3, {st_mode=S_IFREG|0644, st_size=0, ...}) = 0
lseek(3, 0, SEEK_SET) = 0
stat("/etc/vz/conf/3000.conf", {st_mode=S_IFREG|0644, st_size=1194, ...}) = 0
open("/etc/vz/conf/3000.conf", O_RDONLY) = 4
stat("/etc/vz/conf/3000.conf", {st_mode=S_IFREG|0644, st_size=1194, ...}) = 0
fstat(4, {st_mode=S_IFREG|0644, st_size=1194, ...}) = 0
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x2b3071a0c000
read(4, "# Configuration file generated b"..., 4096) = 1194
read(4, "", 4096) = 0
close(4) = 0
munmap(0x2b3071a0c000, 4096) = 0
fcntl(0, F_GETFL) = 0x8002 (flags O_RDWR|O_LARGEFILE)
fcntl(1, F_GETFL) = 0x8002 (flags O_RDWR|O_LARGEFILE)
fcntl(2, F_GETFL) = 0x8002 (flags O_RDWR|O_LARGEFILE)
open("/dev/vzctl", O_RDWR) = 4
ioctl(4, 0x400c2e05, 0x7fff392db2f0) = 0
ioctl(4, 0x400c2e05, 0x7fff392db150) = 0
clone(child_stack=0, flags=CLONE_CHILD_CLEARTID|CLONE_CHILD_SETTID|SIGCHLD, child_tidptr=0x2b3071e52b70) = 4189
wait4(4189,
root 2283 0.0 0.0 10228 872 pts/2 S+ 21:01 0:00 vzctl enter 3000
root 2284 0.0 0.0 10228 376 ? Ds 21:01 0:00 vzctl enter 3000
...
|
|
|
|
Current Time: Sun Jul 28 10:12:10 GMT 2024
Total time taken to generate the page: 0.02767 seconds
|
OpenVZ Forum
Members
Search
Help
Register
Login
Home
