From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Moyer Subject: Re: [PATCH 6/6] cfq: Increase default value of target_latency Date: Thu, 26 Jun 2014 14:04:34 -0400 Message-ID: References: <1403683129-10814-1-git-send-email-mgorman@suse.de> <1403683129-10814-7-git-send-email-mgorman@suse.de> <20140626161955.GH10819@suse.de> <20140626174500.GI10819@suse.de> Mime-Version: 1.0 Content-Type: text/plain Cc: Linux Kernel , Linux-MM , Linux-FSDevel , Johannes Weiner , Jens Axboe , Dave Chinner To: Mel Gorman Return-path: In-Reply-To: <20140626174500.GI10819@suse.de> (Mel Gorman's message of "Thu, 26 Jun 2014 18:45:00 +0100") Sender: owner-linux-mm@kvack.org List-Id: linux-fsdevel.vger.kernel.org Mel Gorman writes: >> And we should probably run our standard set of I/O exercisers at the >> very least. But, like I said, it seems like wasted effort. >> > > Out of curiousity, what do you consider to be the standard set of I/O > exercisers? Yes, that was vague, sorry. I was referring to any io generator that will perform sequential and random I/O (writes, re-writes, reads, random writes, random reads, strided reads, backwards reads, etc). We use iozone internally, testing both buffered and direct I/O, varying file and record sizes and across multiple file systems. Data sets that fall inside of the page cache tend to have a high standard deviation, so, as an I/O guy, I ignore those. ;-) Cheers, Jeff -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org