On Thu, Nov 24, 2016 at 08:26:39AM +0100, Vlastimil Babka wrote:
> On 11/23/2016 05:33 PM, Mel Gorman wrote:
> > > > +
> > > > +static inline unsigned int pindex_to_order(unsigned int pindex)
> > > > +{
> > > > + return pindex < MIGRATE_PCPTYPES ? 0 : pindex -
> > > > MIGRATE_PCPTYPES + 1;
On Thu, Nov 24, 2016 at 08:26:39AM +0100, Vlastimil Babka wrote:
> On 11/23/2016 05:33 PM, Mel Gorman wrote:
> > > > +
> > > > +static inline unsigned int pindex_to_order(unsigned int pindex)
> > > > +{
> > > > + return pindex < MIGRATE_PCPTYPES ? 0 : pindex -
> > > > MIGRATE_PCPTYPES + 1;
On 11/23/2016 05:33 PM, Mel Gorman wrote:
+
+static inline unsigned int pindex_to_order(unsigned int pindex)
+{
+ return pindex < MIGRATE_PCPTYPES ? 0 : pindex - MIGRATE_PCPTYPES + 1;
+}
+
+static inline unsigned int order_to_pindex(int migratetype, unsigned int order)
+{
+ return
On 11/23/2016 05:33 PM, Mel Gorman wrote:
+
+static inline unsigned int pindex_to_order(unsigned int pindex)
+{
+ return pindex < MIGRATE_PCPTYPES ? 0 : pindex - MIGRATE_PCPTYPES + 1;
+}
+
+static inline unsigned int order_to_pindex(int migratetype, unsigned int order)
+{
+ return
On Wed, Nov 23, 2016 at 04:37:06PM +0100, Vlastimil Babka wrote:
> On 11/21/2016 04:55 PM, Mel Gorman wrote:
>
> ...
>
> > hackbench was also tested with both socket and pipes and both processes
> > and threads and the results are interesting in terms of how variability
> > is imapcted
> >
> >
On Wed, Nov 23, 2016 at 04:37:06PM +0100, Vlastimil Babka wrote:
> On 11/21/2016 04:55 PM, Mel Gorman wrote:
>
> ...
>
> > hackbench was also tested with both socket and pipes and both processes
> > and threads and the results are interesting in terms of how variability
> > is imapcted
> >
> >
On 11/21/2016 04:55 PM, Mel Gorman wrote:
...
hackbench was also tested with both socket and pipes and both processes
and threads and the results are interesting in terms of how variability
is imapcted
1-socket machine -- pipes and processes
4.9.0-rc5
On 11/21/2016 04:55 PM, Mel Gorman wrote:
...
hackbench was also tested with both socket and pipes and both processes
and threads and the results are interesting in terms of how variability
is imapcted
1-socket machine -- pipes and processes
4.9.0-rc5
SLUB has been the default small kernel object allocator for quite some time
but it is not universally used due to performance concerns and a reliance
on high-order pages. The high-order concerns has two major components --
high-order pages are not always available and high-order page allocations
SLUB has been the default small kernel object allocator for quite some time
but it is not universally used due to performance concerns and a reliance
on high-order pages. The high-order concerns has two major components --
high-order pages are not always available and high-order page allocations
10 matches
Mail list logo