vmstat 'b' (disk busy?) field keeps climbing ...

Max Laier max at love2party.net
Mon Jun 26 21:08:43 UTC 2006


On Monday 26 June 2006 20:25, Marc G. Fournier wrote:
> I think I might have found *at least* one of the problems, and that being
> the excessively high blocked states while ps isn't finding anything ...
>
> MySQL
>
> We just recently started allowing clients to run a MySQL server *within*
> their vServer ... in a drastic move, I just shut them all down on pluto,
> and blocked drop'd from ~86 down to 5 in a matter of moments ...
> restarting them all has it climbing once more, being up around 22 already
> ...
>
> I'm going to go with that theory for now, and keep an eye on things ...
>
> Just curious as to why, even with -H, its not showing any blocked states
> within ps though ... ?

The "blocked" column shows also processes that have objects "paging".  Most 
likely you are *short* on memory.  In order to relieve the pressure 
program .text pages are free'ed and need to be refetched from disc whenever 
the respective code is being executed.

If you allow every vServer to run its own mySQL with all the libaries etc it's 
clear what is killing you!  Add more memory or make sure that .text pages can 
be reused by several processes.  As far as I understand vServer will all see 
a different source and thus not share buffers or the like.

> Thx
>
> On Mon, 26 Jun 2006, Kostik Belousov wrote:
> > On Mon, Jun 26, 2006 at 02:20:12AM -0300, Marc G. Fournier wrote:
> >> On Mon, 26 Jun 2006, Kostik Belousov wrote:
> >>> Yes, this looks like a deadlock. As I understand, that's on 6.1-STABLE
> >>> ?
> >>
> >> Yes, kernel sources, it seems, from May 25th, according to my /usr/src
> >> tree ...
> >>
> >>> BTW, do you use snapshots ?
> >>
> >> Not that I've explicitly enabled ...
> >>
> >>> I think that without ddb access, diagnose and debug the problem would
> >>> be quite hard.
> >>
> >> Would it be a simple matter of:
> >>
> >> CTL-ALT-ESC
> >> panic
> >>
> >> to get it to dump core?  Or would more be involved?  Would a core dump
> >> even work?
> >
> > Core dumps are somewhat unconvenient in this situation. Better,
> > sending report to me, follow my advise in
> > http://www.freebsd.org/doc/en_US.ISO8859-1/books/developers-handbook/kern
> >eldebug-deadlocks.html
>
> ----
> Marc G. Fournier           Hub.Org Networking Services (http://www.hub.org)
> Email . scrappy at hub.org                              MSN . scrappy at hub.org
> Yahoo . yscrappy               Skype: hub.org        ICQ . 7615664
> _______________________________________________
> freebsd-stable at freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-stable
> To unsubscribe, send any mail to "freebsd-stable-unsubscribe at freebsd.org"

-- 
/"\  Best regards,                      | mlaier at freebsd.org
\ /  Max Laier                          | ICQ #67774661
 X   http://pf4freebsd.love2party.net/  | mlaier at EFnet
/ \  ASCII Ribbon Campaign              | Against HTML Mail and News
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
Url : http://lists.freebsd.org/pipermail/freebsd-stable/attachments/20060626/a0fec014/attachment.pgp


More information about the freebsd-stable mailing list