xfs
[Top] [All Lists]

Re: [PATCH 05/60] xfs: don't do IO when creating an new inode

To: Dave Chinner <david@xxxxxxxxxxxxx>
Subject: Re: [PATCH 05/60] xfs: don't do IO when creating an new inode
From: Mark Tinguely <tinguely@xxxxxxx>
Date: Fri, 21 Jun 2013 08:57:22 -0500
Cc: xfs@xxxxxxxxxxx
Delivered-to: xfs@xxxxxxxxxxx
In-reply-to: <1371617468-32559-6-git-send-email-david@xxxxxxxxxxxxx>
References: <1371617468-32559-1-git-send-email-david@xxxxxxxxxxxxx> <1371617468-32559-6-git-send-email-david@xxxxxxxxxxxxx>
User-agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20120122 Thunderbird/9.0
On 06/18/13 23:50, Dave Chinner wrote:
From: Dave Chinner<dchinner@xxxxxxxxxx>

When we are allocating a new inode, we read the inode cluster off
disk to increment the generation number. We are already using a
random generation number for newly allocated inodes, so if we are not
using the ikeep mode, we can just generate a new generation number
when we initialise the newly allocated inode.

This avoids the need for reading the inode buffer during inode
creation. This will speed up allocation of inodes in cold, partially
allocated clusters as they will no longer need to be read from disk
during allocation. It will also reduce the CPU overhead of inode
allocation by not having the process the buffer read, even on cache
hits.

Signed-off-by: Dave Chinner<dchinner@xxxxxxxxxx>
---


Looks good.

As a side note, the comment in xfs_inode.h for the i_d:
xfs_icdinode_t          i_d;            /* most of ondisk inode */

In Linux 3.10, it is no longer just most.

Reviewed-by: Mark Tinguely <tinguely@xxxxxxx>

<Prev in Thread] Current Thread [Next in Thread>