diff options
author | Steven Whitehouse <swhiteho@redhat.com> | 2007-01-15 13:52:17 +0000 |
---|---|---|
committer | Steven Whitehouse <swhiteho@redhat.com> | 2007-02-05 13:37:01 -0500 |
commit | a8d638e30e768adc6956541f79f7bf05139ba475 (patch) | |
tree | 07cee3c3d06eee9ff138f17023c7dadcb338f467 /fs | |
parent | 222d396092acc11b4af03bede309aa066945e920 (diff) | |
download | talos-obmc-linux-a8d638e30e768adc6956541f79f7bf05139ba475.tar.gz talos-obmc-linux-a8d638e30e768adc6956541f79f7bf05139ba475.zip |
[GFS2] Add writepages for "data=writeback" mounts
It occurred to me that although a gfs2 specific writepages for ordered
writes and journaled data would be tricky, by hooking writepages only
for "data=writeback" mounts we could take advantage of not needing
buffer heads (we don't use them on the read side, nor have we for some
time) and create much larger I/Os for the block layer.
Using blktrace both before and after, its possible to see that for large
I/Os, most of the requests generated through writepages are now 1024
sectors after this patch is applied as opposed to 8 sectors before.
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Diffstat (limited to 'fs')
-rw-r--r-- | fs/gfs2/ops_address.c | 27 |
1 files changed, 27 insertions, 0 deletions
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c index 37bfeb961eb3..9ddf9753a552 100644 --- a/fs/gfs2/ops_address.c +++ b/fs/gfs2/ops_address.c @@ -16,6 +16,7 @@ #include <linux/pagevec.h> #include <linux/mpage.h> #include <linux/fs.h> +#include <linux/writeback.h> #include <linux/gfs2_ondisk.h> #include <linux/lm_interface.h> @@ -157,6 +158,31 @@ out_ignore: } /** + * gfs2_writepages - Write a bunch of dirty pages back to disk + * @mapping: The mapping to write + * @wbc: Write-back control + * + * For journaled files and/or ordered writes this just falls back to the + * kernel's default writepages path for now. We will probably want to change + * that eventually (i.e. when we look at allocate on flush). + * + * For the data=writeback case though we can already ignore buffer heads + * and write whole extents at once. This is a big reduction in the + * number of I/O requests we send and the bmap calls we make in this case. + */ +int gfs2_writepages(struct address_space *mapping, struct writeback_control *wbc) +{ + struct inode *inode = mapping->host; + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_sbd *sdp = GFS2_SB(inode); + + if (sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK && !gfs2_is_jdata(ip)) + return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc); + + return generic_writepages(mapping, wbc); +} + +/** * stuffed_readpage - Fill in a Linux page with stuffed file data * @ip: the inode * @page: the page @@ -757,6 +783,7 @@ out: const struct address_space_operations gfs2_file_aops = { .writepage = gfs2_writepage, + .writepages = gfs2_writepages, .readpage = gfs2_readpage, .readpages = gfs2_readpages, .sync_page = block_sync_page, |