From mboxrd@z Thu Jan 1 00:00:00 1970 From: Neil Brown Subject: Re: recommendations for stripe/chunk size Date: Thu, 7 Feb 2008 16:46:52 +1100 Message-ID: <18346.39756.292908.58065@notabene.brown> References: <47AA08E7.5000801@tmr.com> <20080206202536.3316124D1D@gemini.denx.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: message from Wolfgang Denk on Wednesday February 6 Sender: linux-raid-owner@vger.kernel.org To: Wolfgang Denk Cc: Bill Davidsen , =?ISO-8859-1?Q?Keld_J=F8rn_Simonsen?= , linux-raid@vger.kernel.org List-Id: linux-raid.ids On Wednesday February 6, wd@denx.de wrote: > > We implemented the option to select kernel page sizes of 4, 16, 64 > and 256 kB for some PowerPC systems (440SPe, to be precise). A nice > graphics of the effect can be found here: > > https://www.amcc.com/MyAMCC/retrieveDocument/PowerPC/440SPe/RAIDinLinux_PB_0529a.pdf Thanks for the link! The second improvement is to remove a memory copy that is internal to the MD driver. The MD driver stages strip data ready to be written next to the I/O controller in a page size pre- allocated buffer. It is possible to bypass this memory copy for sequential writes thereby saving SDRAM access cycles. I sure hope you've checked that the filesystem never (ever) changes a buffer while it is being written out. Otherwise the data written to disk might be different from the data used in the parity calculation :-) And what are the "Second memcpy" and "First memcpy" in the graph? I assume one is the memcpy mentioned above, but what is the other? NeilBrown