From owner-freebsd-fs@FreeBSD.ORG Wed Jan 29 10:38:00 2014 Return-Path: Delivered-To: freebsd-fs@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 4BBE8C1F for ; Wed, 29 Jan 2014 10:38:00 +0000 (UTC) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id 9736A18D9 for ; Wed, 29 Jan 2014 10:37:58 +0000 (UTC) Received: from porto.starpoint.kiev.ua (porto-e.starpoint.kiev.ua [212.40.38.100]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id MAA19176; Wed, 29 Jan 2014 12:37:55 +0200 (EET) (envelope-from avg@FreeBSD.org) Received: from localhost ([127.0.0.1]) by porto.starpoint.kiev.ua with esmtp (Exim 4.34 (FreeBSD)) id 1W8SWp-0003LV-Ef; Wed, 29 Jan 2014 12:37:55 +0200 Message-ID: <52E8D9C5.6020702@FreeBSD.org> Date: Wed, 29 Jan 2014 12:36:53 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:24.0) Gecko/20100101 Thunderbird/24.2.0 MIME-Version: 1.0 To: Volodymyr Kostyrko , "Nagy, Attila" , freebsd-fs@FreeBSD.org Subject: Re: Lot more swapping in stable/10 with ZFS References: <52E4DE17.3000206@fsn.hu> <52E7CEB8.7010906@gmail.com> <52E7DBC9.6000708@FreeBSD.org> <52E8AAC3.3040300@fsn.hu> <52E8D7E3.9040200@gmail.com> In-Reply-To: <52E8D7E3.9040200@gmail.com> X-Enigmail-Version: 1.6 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.17 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 29 Jan 2014 10:38:00 -0000 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