Hello Chris,
Wednesday, December 13, 2006, 12:25:40 PM, you wrote:
CG> Robert Milkowski wrote:
>> Hello Chris,
>>
>> Wednesday, December 6, 2006, 6:23:48 PM, you wrote:
>>
>> CG> One of our file servers internally to Sun that reproduces this
>> CG> running nv53 here is the dtrace output:
>>
>>
bash-3.00# lockstat -kgIW sleep 100 | head -30
Profiling interrupt: 38844 events in 100.098 seconds (388 events/sec)
Count genr cuml rcnt nsec Hottest CPU+PILCaller
---
32081 83% 0.00 2432 cpu[1]
Hi.
The problem is getting worse... now even if I destroy all snapshots in a pool
I get performance problem even with zil_disable set to 1.
Despite that I have limit for maximum nfs threads set to 2048 I get only about
1700.
If I want to kill nfsd server it takes 1-4 minutes untill all thread
Robert Milkowski wrote:
Hello Chris,
Wednesday, December 6, 2006, 6:23:48 PM, you wrote:
CG> One of our file servers internally to Sun that reproduces this
CG> running nv53 here is the dtrace output:
Any conclusions yet?
Not yet. We had to delete all the "automatic" snapshots we had so th
Hello Chris,
Wednesday, December 6, 2006, 6:23:48 PM, you wrote:
CG> One of our file servers internally to Sun that reproduces this
CG> running nv53 here is the dtrace output:
Any conclusions yet?
--
Best regards,
Robertmailto:[EMAIL PROTECTED]
One of our file servers internally to Sun that reproduces this running nv53
here is the dtrace output:
unix`mutex_vector_enter+0x120
zfs`metaslab_group_alloc+0x1a0
zfs`metaslab_alloc_dva+0x10c
zfs`metaslab_alloc+0x3c
zfs`zio_dv
