diff options
| author | Mel Gorman <mgorman@suse.de> | 2014-12-13 01:56:33 +0100 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-12-13 21:42:49 +0100 |
| commit | 441c228f817f7597e090d84aca74bdb7c2bd5040 (patch) | |
| tree | 2b03cb17475aeb302d230e4c36dcd18a374a05f6 /mm/fadvise.c | |
| parent | mm/vmalloc.c: fix memory ordering bug (diff) | |
| download | linux-441c228f817f7597e090d84aca74bdb7c2bd5040.tar.xz linux-441c228f817f7597e090d84aca74bdb7c2bd5040.zip | |
mm: fadvise: document the fadvise(FADV_DONTNEED) behaviour for partial pages
A random seek IO benchmark appeared to regress because of a change to
readahead but the real problem was the benchmark. To ensure the IO
request accesssed disk, it used fadvise(FADV_DONTNEED) on a block boundary
(512K) but the hint is ignored by the kernel. This is correct but not
necessarily obvious behaviour. As much as I dislike comment patches, the
explanation for this behaviour predates current git history. Clarify why
it behaves like this in case someone "fixes" fadvise or readahead for the
wrong reasons.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/fadvise.c')
| -rw-r--r-- | mm/fadvise.c | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/mm/fadvise.c b/mm/fadvise.c index 3bcfd81db45e..2ad7adf4f0a4 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -117,7 +117,11 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) __filemap_fdatawrite_range(mapping, offset, endbyte, WB_SYNC_NONE); - /* First and last FULL page! */ + /* + * First and last FULL page! Partial pages are deliberately + * preserved on the expectation that it is better to preserve + * needed memory than to discard unneeded memory. + */ start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT; end_index = (endbyte >> PAGE_CACHE_SHIFT); |