revert "kswapd should only wait on IO if there is IO"
authorAndrew Morton <akpm@linux-foundation.org>
Mon, 24 Mar 2008 19:29:52 +0000 (12:29 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Tue, 25 Mar 2008 02:22:19 +0000 (19:22 -0700)
commit4dd4b920218326231156c7991ce5b94afad841c3
tree021d883ec96cd67f5a348eb739a5c6596fcf6d04
parent537878d2c988fa12bbfaec19ee060c7603a48230
revert "kswapd should only wait on IO if there is IO"

Revert commit f1a9ee758de7de1e040de849fdef46e6802ea117:

  Author: Rik van Riel <riel@redhat.com>
  Date:   Thu Feb 7 00:14:08 2008 -0800

    kswapd should only wait on IO if there is IO

    The current kswapd (and try_to_free_pages) code has an oddity where the
    code will wait on IO, even if there is no IO in flight.  This problem is
    notable especially when the system scans through many unfreeable pages,
    causing unnecessary stalls in the VM.

    Additionally, tasks without __GFP_FS or __GFP_IO in the direct reclaim path
    will sleep if a significant number of pages are encountered that should be
    written out.  This gives kswapd a chance to write out those pages, while
    the direct reclaim task sleeps.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Because of large latencies and interactivity problems reported by Carlos,
here: http://lkml.org/lkml/2008/3/22/211

Cc: Rik van Riel <riel@redhat.com>
Cc: "Carlos R. Mafra" <crmafra2@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm/vmscan.c