Re: [RFC PATCH] mm: CONFIG_NR_ZONES_EXTENDED

2016-03-02 Thread Vlastimil Babka
On 03/02/2016 12:43 AM, Dan Williams wrote: On Tue, Mar 1, 2016 at 12:31 AM, Vlastimil Babka wrote: On 03/01/2016 03:06 AM, Dan Williams wrote: On Mon, Feb 29, 2016 at 4:06 PM, Vlastimil Babka wrote: On 29.2.2016 18:55, Dan Williams wrote: On Mon, Feb 29, 2016 at 4:33 AM, Vlastimil Babka

Re: [RFC PATCH] mm: CONFIG_NR_ZONES_EXTENDED

2016-03-01 Thread Dan Williams
On Tue, Mar 1, 2016 at 12:31 AM, Vlastimil Babka wrote: > On 03/01/2016 03:06 AM, Dan Williams wrote: >> >> On Mon, Feb 29, 2016 at 4:06 PM, Vlastimil Babka wrote: >>> >>> On 29.2.2016 18:55, Dan Williams wrote: On Mon, Feb 29, 2016 at 4:33 AM, Vlastimil Babka wrote: > > On 02/

Re: [RFC PATCH] mm: CONFIG_NR_ZONES_EXTENDED

2016-03-01 Thread Vlastimil Babka
On 03/01/2016 03:06 AM, Dan Williams wrote: On Mon, Feb 29, 2016 at 4:06 PM, Vlastimil Babka wrote: On 29.2.2016 18:55, Dan Williams wrote: On Mon, Feb 29, 2016 at 4:33 AM, Vlastimil Babka wrote: On 02/02/2016 06:42 AM, Andrew Morton wrote: In this case it's already part of the equation be

Re: [RFC PATCH] mm: CONFIG_NR_ZONES_EXTENDED

2016-02-29 Thread Dan Williams
On Mon, Feb 29, 2016 at 4:06 PM, Vlastimil Babka wrote: > On 29.2.2016 18:55, Dan Williams wrote: >> On Mon, Feb 29, 2016 at 4:33 AM, Vlastimil Babka wrote: >>> On 02/02/2016 06:42 AM, Andrew Morton wrote: So if you want ZONE_DMA, you're limited to 512 NUMA nodes? That seems reason

Re: [RFC PATCH] mm: CONFIG_NR_ZONES_EXTENDED

2016-02-29 Thread Vlastimil Babka
On 29.2.2016 18:55, Dan Williams wrote: > On Mon, Feb 29, 2016 at 4:33 AM, Vlastimil Babka wrote: >> On 02/02/2016 06:42 AM, Andrew Morton wrote: >>> So if you want ZONE_DMA, you're limited to 512 NUMA nodes? >>> >>> That seems reasonable. >> >> >> Sorry for the late reply, but it seems that with

Re: [RFC PATCH] mm: CONFIG_NR_ZONES_EXTENDED

2016-02-29 Thread Dan Williams
On Mon, Feb 29, 2016 at 4:33 AM, Vlastimil Babka wrote: > On 02/02/2016 06:42 AM, Andrew Morton wrote: >> >> On Wed, 27 Jan 2016 22:19:14 -0800 Dan Williams >> wrote: >> >>> ZONE_DEVICE (merged in 4.3) and ZONE_CMA (proposed) are examples of new >>> mm zones that are bumping up against the curren

Re: [RFC PATCH] mm: CONFIG_NR_ZONES_EXTENDED

2016-02-29 Thread Vlastimil Babka
On 02/02/2016 06:42 AM, Andrew Morton wrote: On Wed, 27 Jan 2016 22:19:14 -0800 Dan Williams wrote: ZONE_DEVICE (merged in 4.3) and ZONE_CMA (proposed) are examples of new mm zones that are bumping up against the current maximum limit of 4 zones, i.e. 2 bits in page->flags. When adding a zon

Re: [RFC PATCH] mm: CONFIG_NR_ZONES_EXTENDED

2016-02-06 Thread Dan Williams
On Mon, Feb 1, 2016 at 9:42 PM, Andrew Morton wrote: > On Wed, 27 Jan 2016 22:19:14 -0800 Dan Williams > wrote: >> #define GFP_ZONE_TABLE ( \ >> - (ZONE_NORMAL << 0 * ZONES_SHIFT) \ >> - | (OPT_ZONE_DMA << ___GFP_DMA * ZONES_SHIFT)

Re: [RFC PATCH] mm: CONFIG_NR_ZONES_EXTENDED

2016-02-01 Thread Andrew Morton
On Wed, 27 Jan 2016 22:19:14 -0800 Dan Williams wrote: > ZONE_DEVICE (merged in 4.3) and ZONE_CMA (proposed) are examples of new > mm zones that are bumping up against the current maximum limit of 4 > zones, i.e. 2 bits in page->flags. When adding a zone this equation > still needs to be satisi

[RFC PATCH] mm: CONFIG_NR_ZONES_EXTENDED

2016-01-27 Thread Dan Williams
ZONE_DEVICE (merged in 4.3) and ZONE_CMA (proposed) are examples of new mm zones that are bumping up against the current maximum limit of 4 zones, i.e. 2 bits in page->flags. When adding a zone this equation still needs to be satisified: SECTIONS_WIDTH + ZONES_WIDTH + NODES_SHIFT + LAST_CPUPI