lkml.org 
[lkml]   [2010]   [Mar]   [24]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 10/11] Direct compact when a high-order allocation fails
On Wed, Mar 24, 2010 at 09:06:51PM +0900, Minchan Kim wrote:
> On Wed, Mar 24, 2010 at 8:59 PM, Minchan Kim <minchan.kim@gmail.com> wrote:
> > On Wed, Mar 24, 2010 at 8:11 PM, Mel Gorman <mel@csn.ul.ie> wrote:
> >> On Wed, Mar 24, 2010 at 08:10:40AM +0900, Minchan Kim wrote:
> >>> Hi, Mel.
> >>>
> >>> On Tue, Mar 23, 2010 at 9:25 PM, Mel Gorman <mel@csn.ul.ie> wrote:
> >>> > Ordinarily when a high-order allocation fails, direct reclaim is entered to
> >>> > free pages to satisfy the allocation.  With this patch, it is determined if
> >>> > an allocation failed due to external fragmentation instead of low memory
> >>> > and if so, the calling process will compact until a suitable page is
> >>> > freed. Compaction by moving pages in memory is considerably cheaper than
> >>> > paging out to disk and works where there are locked pages or no swap. If
> >>> > compaction fails to free a page of a suitable size, then reclaim will
> >>> > still occur.
> >>> >
> >>> > Direct compaction returns as soon as possible. As each block is compacted,
> >>> > it is checked if a suitable page has been freed and if so, it returns.
> >>> >
> >>> > Signed-off-by: Mel Gorman <mel@csn.ul.ie>
> >>> > Acked-by: Rik van Riel <riel@redhat.com>
> >>> > ---
> >>> >  include/linux/compaction.h |   16 +++++-
> >>> >  include/linux/vmstat.h     |    1 +
> >>> >  mm/compaction.c            |  118 ++++++++++++++++++++++++++++++++++++++++++++
> >>> >  mm/page_alloc.c            |   26 ++++++++++
> >>> >  mm/vmstat.c                |   15 +++++-
> >>> >  5 files changed, 172 insertions(+), 4 deletions(-)
> >>> >
> >>> > diff --git a/include/linux/compaction.h b/include/linux/compaction.h
> >>> > index c94890b..b851428 100644
> >>> > --- a/include/linux/compaction.h
> >>> > +++ b/include/linux/compaction.h
> >>> > @@ -1,14 +1,26 @@
> >>> >  #ifndef _LINUX_COMPACTION_H
> >>> >  #define _LINUX_COMPACTION_H
> >>> >
> >>> > -/* Return values for compact_zone() */
> >>> > +/* Return values for compact_zone() and try_to_compact_pages() */
> >>> >  #define COMPACT_INCOMPLETE     0
> >>> > -#define COMPACT_COMPLETE       1
> >>> > +#define COMPACT_PARTIAL                1
> >>> > +#define COMPACT_COMPLETE       2
> >>> >
> >>> >  #ifdef CONFIG_COMPACTION
> >>> >  extern int sysctl_compact_memory;
> >>> >  extern int sysctl_compaction_handler(struct ctl_table *table, int write,
> >>> >                        void __user *buffer, size_t *length, loff_t *ppos);
> >>> > +
> >>> > +extern int fragmentation_index(struct zone *zone, unsigned int order);
> >>> > +extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
> >>> > +                       int order, gfp_t gfp_mask, nodemask_t *mask);
> >>> > +#else
> >>> > +static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
> >>> > +                       int order, gfp_t gfp_mask, nodemask_t *nodemask)
> >>> > +{
> >>> > +       return COMPACT_INCOMPLETE;
> >>> > +}
> >>> > +
> >>> >  #endif /* CONFIG_COMPACTION */
> >>> >
> >>> >  #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
> >>> > diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
> >>> > index 56e4b44..b4b4d34 100644
> >>> > --- a/include/linux/vmstat.h
> >>> > +++ b/include/linux/vmstat.h
> >>> > @@ -44,6 +44,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
> >>> >                KSWAPD_SKIP_CONGESTION_WAIT,
> >>> >                PAGEOUTRUN, ALLOCSTALL, PGROTATED,
> >>> >                COMPACTBLOCKS, COMPACTPAGES, COMPACTPAGEFAILED,
> >>> > +               COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS,
> >>> >  #ifdef CONFIG_HUGETLB_PAGE
> >>> >                HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,
> >>> >  #endif
> >>> > diff --git a/mm/compaction.c b/mm/compaction.c
> >>> > index 8df6e3d..6688700 100644
> >>> > --- a/mm/compaction.c
> >>> > +++ b/mm/compaction.c
> >>> > @@ -34,6 +34,8 @@ struct compact_control {
> >>> >        unsigned long nr_anon;
> >>> >        unsigned long nr_file;
> >>> >
> >>> > +       unsigned int order;             /* order a direct compactor needs */
> >>> > +       int migratetype;                /* MOVABLE, RECLAIMABLE etc */
> >>> >        struct zone *zone;
> >>> >  };
> >>> >
> >>> > @@ -301,10 +303,31 @@ static void update_nr_listpages(struct compact_control *cc)
> >>> >  static inline int compact_finished(struct zone *zone,
> >>> >                                                struct compact_control *cc)
> >>> >  {
> >>> > +       unsigned int order;
> >>> > +       unsigned long watermark = low_wmark_pages(zone) + (1 << cc->order);
> >>> > +
> >>> >        /* Compaction run completes if the migrate and free scanner meet */
> >>> >        if (cc->free_pfn <= cc->migrate_pfn)
> >>> >                return COMPACT_COMPLETE;
> >>> >
> >>> > +       /* Compaction run is not finished if the watermark is not met */
> >>> > +       if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
> >>> > +               return COMPACT_INCOMPLETE;
> >>> > +
> >>> > +       if (cc->order == -1)
> >>> > +               return COMPACT_INCOMPLETE;
> >>> > +
> >>> > +       /* Direct compactor: Is a suitable page free? */
> >>> > +       for (order = cc->order; order < MAX_ORDER; order++) {
> >>> > +               /* Job done if page is free of the right migratetype */
> >>> > +               if (!list_empty(&zone->free_area[order].free_list[cc->migratetype]))
> >>> > +                       return COMPACT_PARTIAL;
> >>> > +
> >>> > +               /* Job done if allocation would set block type */
> >>> > +               if (order >= pageblock_order && zone->free_area[order].nr_free)
> >>> > +                       return COMPACT_PARTIAL;
> >>> > +       }
> >>> > +
> >>> >        return COMPACT_INCOMPLETE;
> >>> >  }
> >>> >
> >>> > @@ -348,6 +371,101 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
> >>> >        return ret;
> >>> >  }
> >>> >
> >>> > +static inline unsigned long compact_zone_order(struct zone *zone,
> >>> > +                                               int order, gfp_t gfp_mask)
> >>> > +{
> >>> > +       struct compact_control cc = {
> >>> > +               .nr_freepages = 0,
> >>> > +               .nr_migratepages = 0,
> >>> > +               .order = order,
> >>> > +               .migratetype = allocflags_to_migratetype(gfp_mask),
> >>> > +               .zone = zone,
> >>> > +       };
> >>> > +       INIT_LIST_HEAD(&cc.freepages);
> >>> > +       INIT_LIST_HEAD(&cc.migratepages);
> >>> > +
> >>> > +       return compact_zone(zone, &cc);
> >>> > +}
> >>> > +
> >>> > +/**
> >>> > + * try_to_compact_pages - Direct compact to satisfy a high-order allocation
> >>> > + * @zonelist: The zonelist used for the current allocation
> >>> > + * @order: The order of the current allocation
> >>> > + * @gfp_mask: The GFP mask of the current allocation
> >>> > + * @nodemask: The allowed nodes to allocate from
> >>> > + *
> >>> > + * This is the main entry point for direct page compaction.
> >>> > + */
> >>> > +unsigned long try_to_compact_pages(struct zonelist *zonelist,
> >>> > +                       int order, gfp_t gfp_mask, nodemask_t *nodemask)
> >>> > +{
> >>> > +       enum zone_type high_zoneidx = gfp_zone(gfp_mask);
> >>> > +       int may_enter_fs = gfp_mask & __GFP_FS;
> >>> > +       int may_perform_io = gfp_mask & __GFP_IO;
> >>> > +       unsigned long watermark;
> >>> > +       struct zoneref *z;
> >>> > +       struct zone *zone;
> >>> > +       int rc = COMPACT_INCOMPLETE;
> >>> > +
> >>> > +       /* Check whether it is worth even starting compaction */
> >>> > +       if (order == 0 || !may_enter_fs || !may_perform_io)
> >>> > +               return rc;
> >>> > +
> >>> > +       /*
> >>> > +        * We will not stall if the necessary conditions are not met for
> >>> > +        * migration but direct reclaim seems to account stalls similarly
> >>> > +        */
>
> Then, Let's remove this comment.
>

Yes, it hinders more than it helps in this case. It's deleted now.

--
Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM Dublin Software Lab
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2010-03-24 13:13    [from the cache]
©2003-2011 Jasper Spaans