Re: Regression in mobility grouping?

2016-10-13 Thread Joonsoo Kim
Sorry for late response. On Thu, Sep 29, 2016 at 12:14:02PM -0400, Johannes Weiner wrote: > On Thu, Sep 29, 2016 at 03:14:33PM +0900, Joonsoo Kim wrote: > > On Wed, Sep 28, 2016 at 10:25:40PM -0400, Johannes Weiner wrote: > > > On Wed, Sep 28, 2016 at 11:39:25AM -0400, Johannes Weiner wrote: > >

Re: Regression in mobility grouping?

2016-10-13 Thread Joonsoo Kim
Sorry for late response. On Thu, Sep 29, 2016 at 12:14:02PM -0400, Johannes Weiner wrote: > On Thu, Sep 29, 2016 at 03:14:33PM +0900, Joonsoo Kim wrote: > > On Wed, Sep 28, 2016 at 10:25:40PM -0400, Johannes Weiner wrote: > > > On Wed, Sep 28, 2016 at 11:39:25AM -0400, Johannes Weiner wrote: > >

Re: Regression in mobility grouping?

2016-09-29 Thread Johannes Weiner
On Thu, Sep 29, 2016 at 03:14:33PM +0900, Joonsoo Kim wrote: > On Wed, Sep 28, 2016 at 10:25:40PM -0400, Johannes Weiner wrote: > > On Wed, Sep 28, 2016 at 11:39:25AM -0400, Johannes Weiner wrote: > > > On Wed, Sep 28, 2016 at 11:00:15AM +0200, Vlastimil Babka wrote: > > > > I guess testing revert

Re: Regression in mobility grouping?

2016-09-29 Thread Johannes Weiner
On Thu, Sep 29, 2016 at 03:14:33PM +0900, Joonsoo Kim wrote: > On Wed, Sep 28, 2016 at 10:25:40PM -0400, Johannes Weiner wrote: > > On Wed, Sep 28, 2016 at 11:39:25AM -0400, Johannes Weiner wrote: > > > On Wed, Sep 28, 2016 at 11:00:15AM +0200, Vlastimil Babka wrote: > > > > I guess testing revert

Re: Regression in mobility grouping?

2016-09-29 Thread Vlastimil Babka
On 09/29/2016 04:25 AM, Johannes Weiner wrote: On Wed, Sep 28, 2016 at 11:39:25AM -0400, Johannes Weiner wrote: On Wed, Sep 28, 2016 at 11:00:15AM +0200, Vlastimil Babka wrote: I guess testing revert of 9c0415e could give us some idea. Commit 3a1086f shouldn't result in pageblock marking

Re: Regression in mobility grouping?

2016-09-29 Thread Vlastimil Babka
On 09/29/2016 04:25 AM, Johannes Weiner wrote: On Wed, Sep 28, 2016 at 11:39:25AM -0400, Johannes Weiner wrote: On Wed, Sep 28, 2016 at 11:00:15AM +0200, Vlastimil Babka wrote: I guess testing revert of 9c0415e could give us some idea. Commit 3a1086f shouldn't result in pageblock marking

Re: Regression in mobility grouping?

2016-09-29 Thread Joonsoo Kim
On Wed, Sep 28, 2016 at 10:25:40PM -0400, Johannes Weiner wrote: > On Wed, Sep 28, 2016 at 11:39:25AM -0400, Johannes Weiner wrote: > > On Wed, Sep 28, 2016 at 11:00:15AM +0200, Vlastimil Babka wrote: > > > I guess testing revert of 9c0415e could give us some idea. Commit > > > 3a1086f shouldn't

Re: Regression in mobility grouping?

2016-09-29 Thread Joonsoo Kim
On Wed, Sep 28, 2016 at 10:25:40PM -0400, Johannes Weiner wrote: > On Wed, Sep 28, 2016 at 11:39:25AM -0400, Johannes Weiner wrote: > > On Wed, Sep 28, 2016 at 11:00:15AM +0200, Vlastimil Babka wrote: > > > I guess testing revert of 9c0415e could give us some idea. Commit > > > 3a1086f shouldn't

Re: Regression in mobility grouping?

2016-09-28 Thread Johannes Weiner
On Wed, Sep 28, 2016 at 11:39:25AM -0400, Johannes Weiner wrote: > On Wed, Sep 28, 2016 at 11:00:15AM +0200, Vlastimil Babka wrote: > > I guess testing revert of 9c0415e could give us some idea. Commit > > 3a1086f shouldn't result in pageblock marking differences and as I said > > above, 99592d5

Re: Regression in mobility grouping?

2016-09-28 Thread Johannes Weiner
On Wed, Sep 28, 2016 at 11:39:25AM -0400, Johannes Weiner wrote: > On Wed, Sep 28, 2016 at 11:00:15AM +0200, Vlastimil Babka wrote: > > I guess testing revert of 9c0415e could give us some idea. Commit > > 3a1086f shouldn't result in pageblock marking differences and as I said > > above, 99592d5

Re: Regression in mobility grouping?

2016-09-28 Thread Johannes Weiner
Hi Mel, On Wed, Sep 28, 2016 at 11:26:09AM +0100, Mel Gorman wrote: > On Tue, Sep 27, 2016 at 09:41:48PM -0400, Johannes Weiner wrote: > > Hi guys, > > > > we noticed what looks like a regression in page mobility grouping > > during an upgrade from 3.10 to 4.0. Id

Re: Regression in mobility grouping?

2016-09-28 Thread Johannes Weiner
Hi Mel, On Wed, Sep 28, 2016 at 11:26:09AM +0100, Mel Gorman wrote: > On Tue, Sep 27, 2016 at 09:41:48PM -0400, Johannes Weiner wrote: > > Hi guys, > > > > we noticed what looks like a regression in page mobility grouping > > during an upgrade from 3.10 to 4.0. Id

Re: Regression in mobility grouping?

2016-09-28 Thread Johannes Weiner
Hi Vlastimil, On Wed, Sep 28, 2016 at 11:00:15AM +0200, Vlastimil Babka wrote: > On 09/28/2016 03:41 AM, Johannes Weiner wrote: > > Hi guys, > > > > we noticed what looks like a regression in page mobility grouping > > during an upgrade from 3.10 to 4.0. Id

Re: Regression in mobility grouping?

2016-09-28 Thread Johannes Weiner
Hi Vlastimil, On Wed, Sep 28, 2016 at 11:00:15AM +0200, Vlastimil Babka wrote: > On 09/28/2016 03:41 AM, Johannes Weiner wrote: > > Hi guys, > > > > we noticed what looks like a regression in page mobility grouping > > during an upgrade from 3.10 to 4.0. Id

Re: Regression in mobility grouping?

2016-09-28 Thread Mel Gorman
On Tue, Sep 27, 2016 at 09:41:48PM -0400, Johannes Weiner wrote: > Hi guys, > > we noticed what looks like a regression in page mobility grouping > during an upgrade from 3.10 to 4.0. Identical machines, workloads, and > uptime, but /proc/pagetypeinfo on 3.10 looks like th

Re: Regression in mobility grouping?

2016-09-28 Thread Mel Gorman
On Tue, Sep 27, 2016 at 09:41:48PM -0400, Johannes Weiner wrote: > Hi guys, > > we noticed what looks like a regression in page mobility grouping > during an upgrade from 3.10 to 4.0. Identical machines, workloads, and > uptime, but /proc/pagetypeinfo on 3.10 looks like th

Re: Regression in mobility grouping?

2016-09-28 Thread Vlastimil Babka
On 09/28/2016 03:41 AM, Johannes Weiner wrote: > Hi guys, > > we noticed what looks like a regression in page mobility grouping > during an upgrade from 3.10 to 4.0. Identical machines, workloads, and > uptime, but /proc/pagetypeinfo on 3.10 looks like this: > >

Re: Regression in mobility grouping?

2016-09-28 Thread Vlastimil Babka
On 09/28/2016 03:41 AM, Johannes Weiner wrote: > Hi guys, > > we noticed what looks like a regression in page mobility grouping > during an upgrade from 3.10 to 4.0. Identical machines, workloads, and > uptime, but /proc/pagetypeinfo on 3.10 looks like this: > >

Regression in mobility grouping?

2016-09-27 Thread Johannes Weiner
Hi guys, we noticed what looks like a regression in page mobility grouping during an upgrade from 3.10 to 4.0. Identical machines, workloads, and uptime, but /proc/pagetypeinfo on 3.10 looks like this: Number of blocks type Unmovable Reclaimable Movable Reserve Isolate Node

Regression in mobility grouping?

2016-09-27 Thread Johannes Weiner
Hi guys, we noticed what looks like a regression in page mobility grouping during an upgrade from 3.10 to 4.0. Identical machines, workloads, and uptime, but /proc/pagetypeinfo on 3.10 looks like this: Number of blocks type Unmovable Reclaimable Movable Reserve Isolate Node