Re: [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range

2021-01-28 Thread Minchan Kim
On Thu, Jan 28, 2021 at 08:53:25AM +0100, Michal Hocko wrote: > On Wed 27-01-21 12:42:45, Minchan Kim wrote: > > On Tue, Jan 26, 2021 at 08:44:49AM +0100, Michal Hocko wrote: > > > On Mon 25-01-21 11:33:36, Minchan Kim wrote: > > > > On Mon, Jan 25, 2021 at 02:12:00PM +0100, Michal Hocko wrote: >

Re: [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range

2021-01-27 Thread Michal Hocko
On Wed 27-01-21 12:42:45, Minchan Kim wrote: > On Tue, Jan 26, 2021 at 08:44:49AM +0100, Michal Hocko wrote: > > On Mon 25-01-21 11:33:36, Minchan Kim wrote: > > > On Mon, Jan 25, 2021 at 02:12:00PM +0100, Michal Hocko wrote: > > > > On Thu 21-01-21 09:55:00, Minchan Kim wrote: > > > > >

Re: [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range

2021-01-27 Thread Minchan Kim
On Tue, Jan 26, 2021 at 08:44:49AM +0100, Michal Hocko wrote: > On Mon 25-01-21 11:33:36, Minchan Kim wrote: > > On Mon, Jan 25, 2021 at 02:12:00PM +0100, Michal Hocko wrote: > > > On Thu 21-01-21 09:55:00, Minchan Kim wrote: > > > > Contiguous memory allocation can be stalled due to waiting > > >

Re: [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range

2021-01-27 Thread Michal Hocko
On Tue 26-01-21 11:10:18, Minchan Kim wrote: > On Tue, Jan 26, 2021 at 08:44:49AM +0100, Michal Hocko wrote: > > On Mon 25-01-21 11:33:36, Minchan Kim wrote: > > > On Mon, Jan 25, 2021 at 02:12:00PM +0100, Michal Hocko wrote: > > > > On Thu 21-01-21 09:55:00, Minchan Kim wrote: > > > > >

Re: [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range

2021-01-26 Thread Minchan Kim
On Tue, Jan 26, 2021 at 08:44:49AM +0100, Michal Hocko wrote: > On Mon 25-01-21 11:33:36, Minchan Kim wrote: > > On Mon, Jan 25, 2021 at 02:12:00PM +0100, Michal Hocko wrote: > > > On Thu 21-01-21 09:55:00, Minchan Kim wrote: > > > > Contiguous memory allocation can be stalled due to waiting > > >

Re: [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range

2021-01-26 Thread Michal Hocko
On Mon 25-01-21 11:33:36, Minchan Kim wrote: > On Mon, Jan 25, 2021 at 02:12:00PM +0100, Michal Hocko wrote: > > On Thu 21-01-21 09:55:00, Minchan Kim wrote: > > > Contiguous memory allocation can be stalled due to waiting > > > on page writeback and/or page lock which causes unpredictable > > >

Re: [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range

2021-01-26 Thread Minchan Kim
On Mon, Jan 25, 2021 at 02:12:00PM +0100, Michal Hocko wrote: > On Thu 21-01-21 09:55:00, Minchan Kim wrote: > > Contiguous memory allocation can be stalled due to waiting > > on page writeback and/or page lock which causes unpredictable > > delay. It's a unavoidable cost for the requestor to get

Re: [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range

2021-01-25 Thread Michal Hocko
On Mon 25-01-21 14:12:02, Michal Hocko wrote: > On Thu 21-01-21 09:55:00, Minchan Kim wrote: > > Contiguous memory allocation can be stalled due to waiting > > on page writeback and/or page lock which causes unpredictable > > delay. It's a unavoidable cost for the requestor to get *big* > >

Re: [PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range

2021-01-25 Thread Michal Hocko
On Thu 21-01-21 09:55:00, Minchan Kim wrote: > Contiguous memory allocation can be stalled due to waiting > on page writeback and/or page lock which causes unpredictable > delay. It's a unavoidable cost for the requestor to get *big* > contiguous memory but it's expensive for *small* contiguous >

[PATCH v4 2/4] mm: failfast mode with __GFP_NORETRY in alloc_contig_range

2021-01-21 Thread Minchan Kim
Contiguous memory allocation can be stalled due to waiting on page writeback and/or page lock which causes unpredictable delay. It's a unavoidable cost for the requestor to get *big* contiguous memory but it's expensive for *small* contiguous memory(e.g., order-4) because caller could retry the