From owner-freebsd-stable@FreeBSD.ORG Fri May 29 12:02:15 2009 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CA5E41065701 for ; Fri, 29 May 2009 12:02:15 +0000 (UTC) (envelope-from emikulic@gmail.com) Received: from ipmail04.adl2.internode.on.net (ipmail04.adl2.internode.on.net [203.16.214.57]) by mx1.freebsd.org (Postfix) with ESMTP id 6330E8FC32 for ; Fri, 29 May 2009 12:02:14 +0000 (UTC) (envelope-from emikulic@gmail.com) Received: from ppp154-240.static.internode.on.net ([150.101.154.240]) by ipmail04.adl2.internode.on.net with ESMTP; 29 May 2009 21:32:13 +0930 Received: by ppp154-240.static.internode.on.net (Poo-fix, from userid 1001) id A73B95C46; Fri, 29 May 2009 22:02:12 +1000 (EST) Date: Fri, 29 May 2009 22:02:12 +1000 From: Emil Mikulic To: Ivan Voras Message-ID: <20090529120212.GA74808@dmr.ath.cx> References: <4A1FAB45.4040904@h3q.com> <4A1FBD4A.5080204@pp.dyndns.biz> <20090529112919.GA74359@dmr.ath.cx> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.19 (2009-01-05) Cc: freebsd-stable@freebsd.org Subject: Re: ZFS on top of GELI / Intel Atom 330 system X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 29 May 2009 12:02:21 -0000 On Fri, May 29, 2009 at 01:49:54PM +0200, Ivan Voras wrote: > Emil Mikulic wrote: [...] > > kernel`SHA256_Transform 1178 6.3% > > kernel`rijndaelEncrypt 5574 29.7% > > kernel`acpi_cpu_c1 8383 44.6% > > Hi, > > What is the meaning of counts? Number of calls made or time? Time. Sorry, I inadvertently cut off the headings: function, count, percent As I understand it, hotkernel uses statistical sampling at 1001 Hz, so the percentage is an approximation of how much time is spent in each function, based on how many profiler samples ended up in each function. --Emil