Btrfs: don't return congestion in write_cache_pages as often
commit9b0d3ace33ef225690a86d7130feadb22367f496
authorChris Mason <chris.mason@oracle.com>
Wed, 4 Feb 2009 14:33:00 +0000 (4 09:33 -0500)
committerChris Mason <chris.mason@oracle.com>
Wed, 4 Feb 2009 14:33:00 +0000 (4 09:33 -0500)
treeeae45955a38b4d4c2515549112ec749590b56aa9
parent7b78c170dc4f538cc7ee66f47b3aac3f3974a36c
Btrfs: don't return congestion in write_cache_pages as often

On fast devices that go from congested to uncongested very quickly, pdflush
is waiting too often in congestion_wait, and the FS is backing off to
easily in write_cache_pages.

For now, fix this on the btrfs side by only checking congestion after
some bios have already gone down.  Longer term a real fix is needed
for pdflush, but that is a larger project.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
fs/btrfs/extent_io.c