Bill,
> In the future, you can try:
>
> # lockstat -s 10 -I sleep 10
>
> which aggregates on the full stack trace, not just the caller, during
> profiling interrupts. (-s 10 sets the stack depth; tweak up or down to
> taste).
nice. Perhaps lockstat(1M) should be updated to include something like
this in the EXAMPLES section.
> > How should I proceed to further investigate this, and can this be fixed
> > somehow? This way, the machine is almost unusable as a build machine.
>
> you've rediscovered
>
> 6421427 netra x1 slagged by NFS over ZFS leading to long spins in the
> ATA driver code
>
> I've updated the bug to indicate that this wass seen on the Sun Blade
> 1500 as well.
Ok, thanks. One important difference compared to that CR is that those
were local accesses to the FS, but the stack traces from lockstat are
identical.
Any word when this might be fixed?
Thanks.
Rainer
-----------------------------------------------------------------------------
Rainer Orth, Faculty of Technology, Bielefeld University
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
