Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 29 Jan 2014 12:36:53 +0200
From:      Andriy Gapon <avg@FreeBSD.org>
To:        Volodymyr Kostyrko <c.kworr@gmail.com>, "Nagy, Attila" <bra@fsn.hu>, freebsd-fs@FreeBSD.org
Subject:   Re: Lot more swapping in stable/10 with ZFS
Message-ID:  <52E8D9C5.6020702@FreeBSD.org>
In-Reply-To: <52E8D7E3.9040200@gmail.com>
References:  <52E4DE17.3000206@fsn.hu> <52E7CEB8.7010906@gmail.com> <52E7DBC9.6000708@FreeBSD.org> <52E8AAC3.3040300@fsn.hu> <52E8D7E3.9040200@gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
on 29/01/2014 12:28 Volodymyr Kostyrko said the following:
> I'll rather wait for a couple of days of run time as my load includes heavy disk
> usage at night and running a couple of VM's (VirtualBox) during a day. Probably
> VirtualBox is the root cause of high swap size because when starting/restoring a
> VM it allocates a lot of memory during a very short time period.

[This is offtopic for this list...]

VirtualBox could be a reason, but it is not to blame, IMO.
VirtualBox needs to allocate some amount of contiguous physical memory.  It's
really not too much (2MB or 4MB), but if there is no suitable free chunk, then
FreeBSD could end up cleaning _all_ inactive memory and much less likely all
active memory.  For file backed pages it means that file/page cache is purged,
but all malloc-ed memory would go to swap.

-- 
Andriy Gapon



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?52E8D9C5.6020702>