commit | 890871be854b5f5e43e7ba2475f706209906cc24 | [log] [tgz] |
---|---|---|
author | Chris Mason <chris.mason@oracle.com> | Wed Sep 02 16:24:52 2009 -0400 |
committer | Chris Mason <chris.mason@oracle.com> | Fri Sep 11 13:31:05 2009 -0400 |
tree | 9d087adf7a28bb910992d07d93ea2a992e394110 | |
parent | 57fd5a5ff8b48b99e90b22fc143082aba755c6c0 [diff] |
Btrfs: switch extent_map to a rw lock There are two main users of the extent_map tree. The first is regular file inodes, where it is evenly spread between readers and writers. The second is the chunk allocation tree, which maps blocks from logical addresses to phyiscal ones, and it is 99.99% reads. The mapping tree is a point of lock contention during heavy IO workloads, so this commit switches things to a rw lock. Signed-off-by: Chris Mason <chris.mason@oracle.com>