No subject

Unknown Unknown
Tue Mar 23 09:07:47 PDT 2010


@sekishi.zefyris.com> <20100322181744.GA2162 at sekishi.zefyris.com>
From: Matthew Dillon <dillon at apollo.backplane.com>
Subject: Re: Machine unresponsive with cache_lock: blocked on... message
Date: Mon, 22 Mar 2010 22:42:49 -0700 (PDT)
BestServHost: crater.dragonflybsd.org
List-Post: <mailto:bugs at crater.dragonflybsd.org>
List-Subscribe: <mailto:bugs-request at crater.dragonflybsd.org?body=subscribe>
List-Unsubscribe: <mailto:bugs-request at crater.dragonflybsd.org?body=unsubscribe>
List-Help: <mailto:bugs-request at crater.dragonflybsd.org?body=help>
List-Owner: <mailto:owner-bugs at crater.dragonflybsd.org>
Sender: bugs-errors at crater.dragonflybsd.org
Errors-To: bugs-errors at crater.dragonflybsd.org
Lines: 19
NNTP-Posting-Host: 216.240.41.25
X-Trace: 1269360546 crater_reader.dragonflybsd.org 55375 216.240.41.25
Xref: crater_reader.dragonflybsd.org dragonfly.bugs:11564

:36 is slightly better but one of the running applications was still massively
:paged out after a few hours.
:
:I vote for setting vfs.vm_cycle_point to 40.
:
:-- 
:Francois Tigeot

    Ok, so 36 or 40.  I'm a bit worried about using 40, but I think its
    worth setting it to 40 for the release and seeing how it fares.  People
    can always drop it down if weird situations crop up.

    Theoretically the normal paging hysteresis should be sufficient but
    there is still a chance that the inactive queue can wind up too small
    at 40.

					-Matt
					Matthew Dillon 
					<dillon at backplane.com>





More information about the Bugs mailing list