mm: vmscan: tracepoint: account for scanned pages similarly for both ftrace and vmstat
authorMel Gorman <mel@csn.ul.ie>
Wed, 22 Dec 2010 01:24:18 +0000 (17:24 -0800)
committerLinus Torvalds <torvalds@linux-foundation.org>
Thu, 23 Dec 2010 03:43:33 +0000 (19:43 -0800)
commit7a2d19bced51af31d2c9ff55219400ed0a6c012f
tree03185e2121499942b9f2f95c50a86abd4d9fce1c
parentdd9e5efe3aa9fc5b1ce484a531ecdba3a7a30bbf
mm: vmscan: tracepoint: account for scanned pages similarly for both ftrace and vmstat

When correlating ftrace results with /proc/vmstat, I noticed that the
reporting scripts value for "pages scanned" differed significantly.  Both
values were "right" depending on how you look at it.

The difference is due to vmstat only counting scanning of the inactive
list towards pages scanned.  The analysis script for the tracepoint counts
active and inactive list yielding a far higher value than vmstat.  The
resulting scanning/reclaim ratio looks much worse.  The tracepoint is ok
but this patch updates the reporting script so that the report values for
scanned are similar to vmstat.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Documentation/trace/postprocess/trace-vmscan-postprocess.pl