From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cuda.sgi.com (cuda3.sgi.com [192.48.176.15]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id o5OKSre3046340 for ; Thu, 24 Jun 2010 15:28:54 -0500 Received: from mailgate.ics.forth.gr (localhost [127.0.0.1]) by cuda.sgi.com (Spam Firewall) with ESMTP id C135C154542F for ; Thu, 24 Jun 2010 13:31:34 -0700 (PDT) Received: from mailgate.ics.forth.gr (mailgate.ics.forth.gr [139.91.1.2]) by cuda.sgi.com with ESMTP id 5oLrs1bS56y4aXDY for ; Thu, 24 Jun 2010 13:31:34 -0700 (PDT) Received: from av1.ics.forth.gr (av1-in.ics.forth.gr [139.91.1.71]) by mailgate.ics.forth.gr (8.14.3/ICS-FORTH/V10-1.8-GATE) with ESMTP id o5OKVVsJ004496 for ; Thu, 24 Jun 2010 23:31:33 +0300 (EEST) Received: from [192.168.1.63] (adsl-200.91.140.92.tellas.gr [91.140.92.200]) (authenticated bits=0) by enigma.ics.forth.gr (8.14.3//ICS-FORTH/V10.3.0C-EXTNULL-SSL-SASL) with ESMTP id o5OKXD3x023817 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Thu, 24 Jun 2010 23:33:14 +0300 Message-ID: <4C23C074.5080100@ics.forth.gr> Date: Thu, 24 Jun 2010 23:30:44 +0300 From: Yannis Klonatos MIME-Version: 1.0 Subject: Metadata hit ratio List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="us-ascii"; Format="flowed" Sender: xfs-bounces@oss.sgi.com Errors-To: xfs-bounces@oss.sgi.com To: xfs@oss.sgi.com Hello all, Along with my other (yet pending :-( ) question/issue, I have another question (i hope this is the last :-) ) now. I would like to measure the hit ratio of the metadata accesses of XFS (inode+internal buffers). It is my understanding that XFS uses its own data structures, and does not rely on the buffercache mechanisms of the Linux kernel. However, even doing so, there may be cases that the metadata may not fit in the RAM, and I/O operations are required to fetch them from the underlying storage. I have found out that there are two places that XFS uses the submit_bio function. If i add some counters there, would it suffice to measure all the metadata misses? Or is this information available in one (or more) of the xfs_stats counters? And if so, what do i need to sum up in order to get the total metadata hit and miss ratio? Thanks (again!) in advance, Yannis Klonatos _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs