|| ||Minchan Kim <minchan-AT-kernel.org> |
|| ||Paul Turner <pjt-AT-google.com> |
|| ||Re: [RFC v2] Support volatile range for anon vma |
|| ||Thu, 1 Nov 2012 10:46:04 +0900|
|| ||KOSAKI Motohiro <kosaki.motohiro-AT-gmail.com>,
Andrew Morton <akpm-AT-linux-foundation.org>,
John Stultz <john.stultz-AT-linaro.org>,
Christoph Lameter <cl-AT-linux.com>,
Android Kernel Team <kernel-team-AT-android.com>,
Robert Love <rlove-AT-google.com>, Mel Gorman <mel-AT-csn.ul.ie>,
Hugh Dickins <hughd-AT-google.com>,
Dave Hansen <dave-AT-linux.vnet.ibm.com>,
Rik van Riel <riel-AT-redhat.com>, Dave Chinner <david-AT-fromorbit.com>,
Neil Brown <neilb-AT-suse.de>, Mike Hommey <mh-AT-glandium.org>,
Taras Glek <tglek-AT-mozilla.com>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu-AT-jp.fujitsu.com>,
sanjay-AT-google.com, David Rientjes <rientjes-AT-google.com>|
|| ||Article, Thread
On Wed, Oct 31, 2012 at 06:15:33PM -0700, Paul Turner wrote:
> On Wed, Oct 31, 2012 at 3:56 PM, KOSAKI Motohiro
> <firstname.lastname@example.org> wrote:
> >>> > Allocator should call madvise(MADV_NOVOLATILE) before reusing for
> >>> > allocating that area to user. Otherwise, accessing of volatile range
> >>> > will meet SIGBUS error.
> >>> Well, why? It would be easy enough for the fault handler to give
> >>> userspace a new, zeroed page at that address.
> >> Note: MADV_DONTNEED already has this (nice) property.
> > I don't think I strictly understand this patch. but maybe I can answer why
> > userland and malloc folks don't like MADV_DONTNEED.
> > glibc malloc discard freed memory by using MADV_DONTNEED
> > as tcmalloc. and it is often a source of large performance decrease.
> > because of MADV_DONTNEED discard memory immediately and
> > right after malloc() call fall into page fault and pagesize memset() path.
> > then, using DONTNEED increased zero fill and cache miss rate.
> > At called free() time, malloc don't have a knowledge when next big malloc()
> > is called. then, immediate discarding may or may not get good performance
> > gain. (Ah, ok, the rate is not 5:5. then usually it is worth. but not everytime)
> Ah; In tcmalloc allocations (and their associated free-lists) are
> binned into separate lists as a function of object-size which helps to
> mitigate this.
> I'd make a separate more general argument here:
> If I'm allocating a large (multi-kilobyte object) the cost of what I'm
> about to do with that object is likely fairly large -- The fault/zero
> cost a probably fairly small proportional cost, which limits the
> optimization value.
While I look at thread trial of Rik which is same goal while implementation
is different, I found this number.
I believe optimiation is valuable. Of course, I need simillar testing for
> > In past, several developers tryied to avoid such situation, likes
> > - making zero page daemon and avoid pagesize zero fill at page fault
> > - making new vma or page flags and mark as discardable w/o swap and
> > vmscan treat it. (like this and/or MADV_FREE)
> > - making new process option and avoid page zero fill from page fault path.
> > (yes, it is big incompatibility and insecure. but some embedded folks thought
> > they are acceptable downside)
> > - etc
> > btw, I'm not sure this patch is better for malloc because current MADV_DONTNEED
> > don't need mmap_sem and works very effectively when a lot of threads case.
> > taking mmap_sem might bring worse performance than DONTNEED. dunno.
> MADV_VOLATILE also seems to end up looking quite similar to a
> user-visible (range-based) cleancache.
> A second popular use-case for such semantics is the case of
> discardable cache elements (e.g. web browser). I suspect we'd want to
> at least mention these in the changelog. (Alternatively, what does a
> cleancache-backed-fs exposing these semantics look like?)
It's a trial of John Stultz(http://lwn.net/Articles/518130/, there was another
trial long time ago https://lkml.org/lkml/2005/11/1/384) and I want to
expand the concept from file-backed page to anonymous page so this patch
is a trial for anonymous page. So, usecase of my patch have focussed on
I hope both are able to be unified.
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to email@example.com. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"firstname.lastname@example.org"> email@example.com </a>
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to firstname.lastname@example.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"email@example.com"> firstname.lastname@example.org </a>
to post comments)