Oh yeah, and the second number is the number of times ALL of the threads have been in use.
Corey On Mon, Oct 10, 2011 at 8:38 PM, Corey Kovacs <corey.kov...@gmail.com>wrote: > Well, I dind't miss, just didn't mention it. The big number is not the > 1-10% of the threads being busy, it's how much time was spent waiting for a > thread to free up to complete an I/O. You could interpret that as busy of > course, but "why" it's busy is more important. > > Corey > > > > On Mon, Oct 10, 2011 at 11:34 AM, Joshua Baker-LePain <jl...@duke.edu>wrote: > >> On Mon, 10 Oct 2011 at 6:59am, Corey Kovacs wrote >> >> One thing that is fairly obvious if you know where to look, is that your >>> server needs to have more threads running. >>> >>> The line... >>> >>> >>> th 8 0 3828.727 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 >>> >>> Indicates this. The "th" means "thread(s)" and the "8" is how many are >>> running. >>> The " 3828.727" is telling you a significant number of instances have >>> occurred >>> in which I/O was waiting for a thread in order to be serviced and this >>> complete. >>> >> >> Actually, I think you missed a field there. As you said, "th" is threads, >> and "8" is how many are running. It's the *next* number, which is 0, which >> is the number of times I/O has been waiting for a free thread. Following >> that there are 10 fields. The first (3828.727) is the amount of time 1-10% >> of the threads have been busy. The second is the amount of time 11-20% of >> the threads have been busy. Etc. So the above actually shows a very >> *non*-busy NFS server. There have been no thread starved I/O events, and >> never has more than 1 thread been busy. >> >> And, to the OP, iftop can be useful here, given that there aren't any >> other significant sources of network traffic. >> >> -- >> Joshua Baker-LePain >> QB3 Shared Cluster Sysadmin >> UCSF >> >> ______________________________**_________________ >> rhelv5-list mailing list >> rhelv5-list@redhat.com >> https://www.redhat.com/**mailman/listinfo/rhelv5-list<https://www.redhat.com/mailman/listinfo/rhelv5-list> >> > >
_______________________________________________ rhelv5-list mailing list rhelv5-list@redhat.com https://www.redhat.com/mailman/listinfo/rhelv5-list
