Subject: Re: Do some disk accesses miss the UVM?
To: Rafal Boni <firstname.lastname@example.org>
From: Jaromir Dolecek <email@example.com>
Date: 01/24/2002 07:19:51
Rafal Boni wrote:
> -> Repeating the find takes about the same length of time, the disk
> -> 'rattles' throughout. Memory use (reported by 'top') stays basically
> -> constant 'Memory: 33M Act, 308K Wired, 187M Free, 1025M Swp free'.
> I bet you run out of vnodes, the vnodes for stuff you've already gotten get
> recycled and you have to go back to disk to fetch the necessary data. I'm
> willing to bet money on the first half, but I'm unsure why you'd need to go
> to disk again anyway -- is this some fallout from metadata not being in UBC?
Note that metadata are cached using old buffer cache (not UBC),
thus it's possible the metadata are kicked off the cache even when
there is still free memory left. However, the size of metadata is
not that much, so it's more likely the vnode thing. I commonly use
kern.maxvnodes=50000 on 384 MB machine.
Jaromir Dolecek <jdolecek@NetBSD.org> http://www.NetBSD.org/Ports/i386/ps2.html
-= Those who would give up liberty for a little temporary safety deserve =-
-= neither liberty nor safety, and will lose both. -- Benjamin Franklin =-