From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id o464FAJ2070817 for ; Wed, 5 May 2010 23:15:10 -0500 Received: from postoffice2.aconex.com (localhost [127.0.0.1]) by cuda.sgi.com (Spam Firewall) with ESMTP id C6324128138D for ; Wed, 5 May 2010 21:17:19 -0700 (PDT) Received: from postoffice2.aconex.com (mail.aconex.com [203.89.202.182]) by cuda.sgi.com with ESMTP id netBeEfaPKTvED5B for ; Wed, 05 May 2010 21:17:19 -0700 (PDT) Date: Thu, 6 May 2010 14:17:04 +1000 (EST) From: nathans@aconex.com Message-ID: <827899224.88951273119424327.JavaMail.root@mail-au> In-Reply-To: <921460991.88921273119221574.JavaMail.root@mail-au> Subject: Re: [PATCH 07/11] xfs: Delayed logging design documentation MIME-Version: 1.0 List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: xfs-bounces@oss.sgi.com Errors-To: xfs-bounces@oss.sgi.com To: Dave Chinner Cc: xfs@oss.sgi.com Yo, Looking good Dave! Thanks for writing this up, it made for some interesting lunch time reading. ;) Here's a few typos I noticed, marked 'em up as I read along... > +required for objects that are frequently logged. Parts inodes are "Some parts of ..."? > +The limitation on asynchrnous transaction throughput is the number "asynchronous" > +Effectively, this gives us the maximum bound out outstanding metadata "out" -> "of" > +formating the changes in a transaction to the log buffer. Hence we "formatting" > +One of the key changes that delayed logging makes to the operation of > the > +journalling subsystem is that is dissociates the amount of "is" -> "it", and "disassociates" (or maybe "dissociates" is what you meant, you chem freak you. ;) > +recovered filesysetm is concerned, there may be many thousands of filesystem. > +This introduces lots of scope of deadlocks with transactions that are "scope for deadlocks"? > +The solution is relatively simple - it just a long time to recognise "took a long time" > +rewrite the vector addresses to point at the memory buffer we end up "and rewriting the" > with a > +self-describing object that it can be passed to the log buffer write "that can be" > is entire > +arbitrary and done to make it easy for debugging - the last items in "is entirely" > +crash during the write of a such a transaction could partially > overwrites the "partially overwrite" > +format structure. That is, two vectors totalling roughly 150 bytes. "totaling" > +the write reservation (the actual space availble to the transaction) "available" > +checkpoint commit to complete. This background push checked and > executed by transaction commit code. "is checked" > +log item completion. THe result of this is that pinning and unpinning "The" > +are entered and completed is the object considered clean.` Spurious "`" there? > + => gain confidence and fix problems reported by early > + adopters (a.k.a. guinea pigs) :-) cheers. -- Nathan _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs