Re: [PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-08-05 Thread Vlastimil Babka
On 8/5/19 6:58 PM, Mike Kravetz wrote: >> Signed-off-by: Vlastimil Babka > > Acked-by: Mike Kravetz > > Would you like me to add this to the series, or do you want to send later? Please add, thanks!

Re: [PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-08-05 Thread Mike Kravetz
On 8/5/19 3:57 AM, Vlastimil Babka wrote: > On 8/5/19 10:42 AM, Vlastimil Babka wrote: >> On 8/3/19 12:39 AM, Mike Kravetz wrote: >>> From: Hillf Danton >>> >>> Address the issue of should_continue_reclaim continuing true too often >>> for __GFP_RETRY_MAYFAIL attempts when !nr_reclaimed and nr_sca

Re: [PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-08-05 Thread Mike Kravetz
On 8/5/19 1:42 AM, Vlastimil Babka wrote: > On 8/3/19 12:39 AM, Mike Kravetz wrote: >> From: Hillf Danton >> >> Address the issue of should_continue_reclaim continuing true too often >> for __GFP_RETRY_MAYFAIL attempts when !nr_reclaimed and nr_scanned. >> This could happen during hugetlb page all

Re: [PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-08-05 Thread Vlastimil Babka
On 8/5/19 10:42 AM, Vlastimil Babka wrote: > On 8/3/19 12:39 AM, Mike Kravetz wrote: >> From: Hillf Danton >> >> Address the issue of should_continue_reclaim continuing true too often >> for __GFP_RETRY_MAYFAIL attempts when !nr_reclaimed and nr_scanned. >> This could happen during hugetlb page al

Re: [PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-08-05 Thread Vlastimil Babka
On 8/3/19 12:39 AM, Mike Kravetz wrote: > From: Hillf Danton > > Address the issue of should_continue_reclaim continuing true too often > for __GFP_RETRY_MAYFAIL attempts when !nr_reclaimed and nr_scanned. > This could happen during hugetlb page allocation causing stalls for > minutes or hours. >

[PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-08-02 Thread Mike Kravetz
From: Hillf Danton Address the issue of should_continue_reclaim continuing true too often for __GFP_RETRY_MAYFAIL attempts when !nr_reclaimed and nr_scanned. This could happen during hugetlb page allocation causing stalls for minutes or hours. We can stop reclaiming pages if compaction reports i

Re: [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-08-01 Thread Vlastimil Babka
On 7/31/19 11:11 PM, Mike Kravetz wrote: > On 7/31/19 4:08 AM, Vlastimil Babka wrote: >> >> I agree this is an improvement overall, but perhaps the patch does too >> many things at once. The reshuffle is one thing and makes sense. The >> change of the last return condition could perhaps be separate

Re: [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-07-31 Thread Mike Kravetz
On 7/31/19 4:08 AM, Vlastimil Babka wrote: > > I agree this is an improvement overall, but perhaps the patch does too > many things at once. The reshuffle is one thing and makes sense. The > change of the last return condition could perhaps be separate. Also > AFAICS the ultimate result is that wh

Re: [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-07-31 Thread Mel Gorman
makes sense that if compaction reports it can make progress that it is > >> unnecessary to continue reclaiming. > > > > Thanks Mike and Mel. > > > > Hillf > > ---8<--- > > From: Hillf Danton > > Subject: [RFC PATCH 1/3] mm, r

Re: [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-07-31 Thread Vlastimil Babka
cessary to continue reclaiming. > > Thanks Mike and Mel. > > Hillf > ---8<--- > From: Hillf Danton > Subject: [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform > dryrun detection > > Address the issue of should_continue_reclaim continuing true too

Re: [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-07-26 Thread Mel Gorman
> From: Hillf Danton > Subject: [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform > dryrun detection > > Address the issue of should_continue_reclaim continuing true too often > for __GFP_RETRY_MAYFAIL attempts when !nr_reclaimed and nr_scanned. > Thi

Re: [RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-07-25 Thread Mel Gorman
On Wed, Jul 24, 2019 at 10:50:12AM -0700, Mike Kravetz wrote: > From: Hillf Danton > > Address the issue of should_continue_reclaim continuing true too often > for __GFP_RETRY_MAYFAIL attempts when !nr_reclaimed and nr_scanned. > This could happen during hugetlb page allocation causing stalls for

[RFC PATCH 1/3] mm, reclaim: make should_continue_reclaim perform dryrun detection

2019-07-24 Thread Mike Kravetz
From: Hillf Danton Address the issue of should_continue_reclaim continuing true too often for __GFP_RETRY_MAYFAIL attempts when !nr_reclaimed and nr_scanned. This could happen during hugetlb page allocation causing stalls for minutes or hours. Restructure code so that false will be returned in t