Jeff Layton 8f71465c19 cifs: don't cap ra_pages at the same level as default_backing_dev_info
While testing, I've found that even when we are able to negotiate a
much larger rsize with the server, on-the-wire reads often end up being
capped at 128k because of ra_pages being capped at that level.

Lifting this restriction gave almost a twofold increase in sequential
read performance on my craptactular KVM test rig with a 1M rsize.

I think this is safe since the actual ra_pages that the VM requests
is run through max_sane_readahead() prior to submitting the I/O. Under
memory pressure we should end up with large readahead requests being
suppressed anyway.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
2012-05-01 22:27:54 -05:00
..
2012-03-28 09:58:38 -07:00
2012-04-23 18:22:42 -07:00
2012-03-31 16:03:16 -04:00
2012-04-23 19:52:00 -07:00
2012-03-21 10:15:51 -07:00
2012-03-30 17:31:56 -07:00
2012-04-13 13:50:52 -04:00
2012-03-20 21:29:52 -04:00
2012-03-20 21:29:38 -04:00
2012-03-30 17:31:56 -07:00
2012-03-23 09:27:40 -07:00
2012-03-28 15:58:21 -07:00
2012-04-21 01:58:20 -04:00
2012-03-20 21:29:46 -04:00
2012-03-20 21:29:46 -04:00
2012-01-03 22:52:39 -05:00
2012-03-28 10:07:27 -07:00
2012-03-20 21:29:51 -04:00
2012-03-20 21:29:38 -04:00