From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Rainforest Subject: Re: 2.6.20: stripe_cache_size goes boom with 32mb Date: Fri, 23 Feb 2007 22:41:00 +1000 Message-ID: <1172234460.4419.7.camel@merlin> References: Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: Sender: linux-raid-owner@vger.kernel.org To: Justin Piszcz Cc: linux-kernel@vger.kernel.org, linux-raid@vger.kernel.org List-Id: linux-raid.ids Hi Justin, I'm not a RAID or kernel developer, but .. do you have enough RAM to support a 32mb stripe_cache_size?! Here on my 7*250Gb SW RAID5 array, decreasing a stripe_cache_size of 8192 to 4096 frees up no less than 120mb of RAM. Using that as a calculation tool, a 32mb stripe_cache_size would require approximately 960mb of RAM! My RAID box only has 1Gb of RAM, so I'm not game to test such a thing. Others on these lists would definitely have a good idea on what's happening :-) Cheers, Jason On Fri, 2007-02-23 at 06:41 -0500, Justin Piszcz wrote: > Each of these are averaged over three runs with 6 SATA disks in a SW RAID > 5 configuration: > > (dd if=/dev/zero of=file_1 bs=1M count=2000) > > 128k_stripe: 69.2MB/s > 256k_stripe: 105.3MB/s > 512k_stripe: 142.0MB/s > 1024k_stripe: 144.6MB/s > 2048k_stripe: 208.3MB/s > 4096k_stripe: 223.6MB/s > 8192k_stripe: 226.0MB/s > 16384k_stripe: 215.0MB/s > > When I tried a 32768k stripe, this happened: > p34:~# echo 32768 > /sys/block/md4/md/stripe_cache_size > Connection to p34 closed > > I was able to Alt-SysRQ+b but I could not access the console/X/etc, it > appeared to be frozen. > > FYI. > > Justin. > > - > To unsubscribe from this list: send the line "unsubscribe linux-raid" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html