on 21/08/2010 09:50 Andriy Gapon said the following: > on 21/08/2010 03:03 Doug Barton said the following: >> Here are the results of a vmstat -i, the old dtrace script, and Andriy's >> new one. > > I think that for such amount of data it is better to use links (perhaps a > service like pastebin) rather than inlining it. > BTW, it seems that there are no followups/comments on results of the old dtrace > script, so I am not sure if there is any point in continuing to post it. > It is useless personally for me. > > Back to the data. > Could you please report results of > procstat -k 10 > procstat -k 11 > ? Some additional stuff. Could you please remind what the "old dtrace script" is? :-) Output of sysctl dev.cpu (normal and when the problem hits) Another dtrace script: profile:::profile-1001 { _at_stacks[curthread->td_oncpu, pid, tid, stack()] = count(); } END { trunc(_at_stacks, 20); printa(_at_stacks); } -- Andriy GaponReceived on Sat Aug 21 2010 - 05:10:13 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:40:06 UTC