From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bill Davidsen Subject: Re: I/O wait problem with hardware raid Date: Sat, 30 Aug 2008 14:47:21 -0400 Message-ID: <48B995B9.2040600@tmr.com> References: <48B75097.7000509@harvee.org> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <48B75097.7000509@harvee.org> Sender: linux-raid-owner@vger.kernel.org To: "Eric S. Johansson" Cc: linux-raid@vger.kernel.org List-Id: linux-raid.ids Eric S. Johansson wrote: > I'm not sure if this mailing lists is just for the Linux kernel raid so this > query does not belong, feel free to tell me where to go. > > I'm running Ubuntu 8.04 on an HP ProLiant ml350 with an E200i sata raid card. > > The problem is the I/O wait percentage increases during data transfer. A simple > rsync transfer will bring the percent I/O wait value up to the mid-20s to 40s > and a little more stress causes the wait percentage to climb to upper 90% range. > it appears that most of the I/O wait time is from the disk array because a copy > has a similar effect. However, I cannot eliminate some contribution by the > networking code. > > I'm not sure how to debug this. vmstat doesn't show anything extraordinary so > I'm left scratching my head. > > what should I be looking for? > iowait means that there is a program waiting for I/O. That's all. Of course when you do a copy (regardless of software) the CPU is waiting for disk transfers. I'm not sure what you think you should debug, i/o takes time, and if the program is blocked until the next input comes in it will enter the waitio state. If there is no other process to use the available CPU it becomes waitio, which is essentially available CPU cycles similar to idle. What exactly do you think is wrong? -- Bill Davidsen "Woe unto the statesman who makes war without a reason that will still be valid when the war is over..." Otto von Bismark