ocfs2: Optimize inode allocation by remembering last group

Browse source

In ocfs2, the inode block search looks for the "emptiest" inode
group to allocate from. So if an inode alloc file has many equally
(or almost equally) empty groups, new inodes will tend to get
spread out amongst them, which in turn can put them all over the
disk. This is undesirable because directory operations on conceptually
"nearby" inodes force a large number of seeks.

So we add ip_last_used_group in core directory inodes which records
the last used allocation group. Another field named ip_last_used_slot
is also added in case inode stealing happens. When claiming new inode,
we passed in directory's inode so that the allocation can use this
information.
For more details, please see
http://oss.oracle.com/osswiki/OCFS2/DesignDocs/InodeAllocationStrategy.

Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>

...

This commit is contained in:

Tao Ma 2009-02-25 00:53:23 +08:00 • committed by Mark Fasheh

parent 1d46dc08d3

commit 138211515c

5 changed files with 46 additions and 2 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

2

fs/ocfs2/inode.c

View file

4

fs/ocfs2/inode.h

View file

4

fs/ocfs2/namei.c

View file

36

fs/ocfs2/suballoc.c

View file

2

fs/ocfs2/suballoc.h

View file