Robert Milkowski wrote:
Hi.
Today again the same problem - however not that severe so I'm not sure if
below lockstat is representative.
# lockstat -kgIW sleep 5 | less
Profiling interrupt: 1968 events in 5.072 seconds (388 events/sec)
Count genr cuml rcnt nsec Hottest CPU+PIL Caller
-------------------------------------------------------------------------------
1560 79% ---- 0.00 2520 cpu[3] thread_start
1018 52% ---- 0.00 2069 cpu[2]+11 idle
851 43% ---- 0.00 2093 cpu[2]+11 disp_getwork
591 30% ---- 0.00 3647 cpu[1] metaslab_alloc
591 30% ---- 0.00 3647 cpu[1] metaslab_alloc_dva
591 30% ---- 0.00 3647 cpu[1] metaslab_group_alloc
404 21% ---- 0.00 3488 cpu[1] space_map_load
404 21% ---- 0.00 3488 cpu[1] metaslab_activate
Nice, this is definitely pointing the finger more definitively. Next
time could you try:
dtrace -n '[EMAIL PROTECTED](20)] = count()}' -c 'sleep 5'
(just send the last 10 or so stack traces)
In the mean time I'll talk with our SPA experts and see if I can figure
out how to fix this...
--matt
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
