Re: [patch 10/12] Memoryless nodes: Update memory policy and page migration

Re: [patch 10/12] Memoryless nodes: Update memory policy and page migration

[KAMEZAWA Hiroyuki]

On Tue, 10 Jul 2007 14:52:15 -0700
Christoph Lameter <clameter@sgi.com> wrote:

> +			*nodes = node_memory_map;
>  		else
node_states[N_MEMORY]  ?


>  		check_pgd_range(vma, vma->vm_start, vma->vm_end,
> -				&node_online_map, MPOL_MF_STATS, md);
> +				&node_memory_map, MPOL_MF_STATS, md);
>  	}

Again here.

-Kame

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [patch 11/12] Memoryless nodes: Fix GFP_THISNODE behavior

[KAMEZAWA Hiroyuki]

some nitpicks...

On Tue, 10 Jul 2007 14:52:16 -0700
Christoph Lameter <clameter@sgi.com> wrote:

> +static void build_thisnode_zonelists(pg_data_t *pgdat)
> +{
> +	enum zone_type i;
> +	int j;
> +	struct zonelist *zonelist;
> +
> +	for (i = 0; i < MAX_NR_ZONES; i++) {
> +		zonelist = pgdat->node_zonelists + MAX_NR_ZONES + i;
> + 		j = build_zonelists_node(pgdat, zonelist, 0, i);
> +		zonelist->zones[j] = NULL;
> +	}
> +}
adding explanation as following is maybe good.
==
	/* 
         * NUMA default zonelist is structured as
	 * [0....MAX_NR_ZONES) : allows fallbacks to other node for each GFP_MASK.
	 * [MAX_NR_ZONES...MAX_ZONELISTS) : disallow fallbacks for GFP_XXX |GFP_THISNODE
	 */
==
> +
> +/*
>   * Build zonelists ordered by zone and nodes within zones.
>   * This results in conserving DMA zone[s] until all Normal memory is
>   * exhausted, but results in overflowing to remote node while memory
> @@ -2267,7 +2283,7 @@ static void build_zonelists(pg_data_t *p
>  	int order = current_zonelist_order;
>  
>  	/* initialize zonelists */
> -	for (i = 0; i < MAX_NR_ZONES; i++) {
> +	for (i = 0; i < 2 * MAX_NR_ZONES; i++) {

please use MAX_ZONELISTS here.

-Kame

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [patch 08/12] Uncached allocator: Handle memoryless nodes

[Jes Sorensen]

Christoph Lameter wrote:
> The checks for node_online in the uncached allocator are made to make sure
> that memory is available on these nodes. Thus switch all the checks to use
> the node_memory and for_each_memory_node functions.
> 
> Cc: jes@sgi.com
> Signed-off-by: Christoph Lameter <clameter@sgi.com>

I'm fine with this:

Signed-off-by: Jes Sorensen <jes@sgi.com>

Jes


> ---
>  arch/ia64/kernel/uncached.c |    4 ++--
>  drivers/char/mspec.c        |    2 +-
>  2 files changed, 3 insertions(+), 3 deletions(-)
> 
> Index: linux-2.6.22-rc6-mm1/arch/ia64/kernel/uncached.c
> ===================================================================
> --- linux-2.6.22-rc6-mm1.orig/arch/ia64/kernel/uncached.c	2007-06-24 16:21:48.000000000 -0700
> +++ linux-2.6.22-rc6-mm1/arch/ia64/kernel/uncached.c	2007-07-09 22:24:42.000000000 -0700
> @@ -196,7 +196,7 @@ unsigned long uncached_alloc_page(int st
>  	nid = starting_nid;
>  
>  	do {
> -		if (!node_online(nid))
> +		if (!node_state(nid, N_MEMORY))
>  			continue;
>  		uc_pool = &uncached_pools[nid];
>  		if (uc_pool->pool == NULL)
> @@ -268,7 +268,7 @@ static int __init uncached_init(void)
>  {
>  	int nid;
>  
> -	for_each_online_node(nid) {
> +	for_each_node_state(nid, N_ONLINE) {
>  		uncached_pools[nid].pool = gen_pool_create(PAGE_SHIFT, nid);
>  		mutex_init(&uncached_pools[nid].add_chunk_mutex);
>  	}
> Index: linux-2.6.22-rc6-mm1/drivers/char/mspec.c
> ===================================================================
> --- linux-2.6.22-rc6-mm1.orig/drivers/char/mspec.c	2007-07-03 17:19:24.000000000 -0700
> +++ linux-2.6.22-rc6-mm1/drivers/char/mspec.c	2007-07-09 22:24:42.000000000 -0700
> @@ -353,7 +353,7 @@ mspec_init(void)
>  		is_sn2 = 1;
>  		if (is_shub2()) {
>  			ret = -ENOMEM;
> -			for_each_online_node(nid) {
> +			for_each_node_state(nid, N_ONLINE) {
>  				int actual_nid;
>  				int nasid;
>  				unsigned long phys;
> 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [patch 10/12] Memoryless nodes: Update memory policy and page migration

[Nishanth Aravamudan]

On 11.07.2007 [16:48:11 +0900], KAMEZAWA Hiroyuki wrote:
> On Tue, 10 Jul 2007 14:52:15 -0700
> Christoph Lameter <clameter@sgi.com> wrote:
> 
> > +			*nodes = node_memory_map;
> >  		else
> node_states[N_MEMORY]  ?
> 
> 
> >  		check_pgd_range(vma, vma->vm_start, vma->vm_end,
> > -				&node_online_map, MPOL_MF_STATS, md);
> > +				&node_memory_map, MPOL_MF_STATS, md);
> >  	}
> 
> Again here.

I think Christoph missed a hunk in the node_memory_map patch, which
would

#define node_memory_map node_stats[N_MEMORY]

Thanks,
Nish

-- 
Nishanth Aravamudan <nacc@us.ibm.com>
IBM Linux Technology Center

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [patch 02/12] NUMA: Introduce node_memory_map

[Nishanth Aravamudan]

On 10.07.2007 [14:52:07 -0700], Christoph Lameter wrote:
> It is necessary to know if nodes have memory since we have recently
> begun to add support for memoryless nodes. For that purpose we introduce
> a new node state N_MEMORY.
> 
> A node has its bit in node_memory_map set if it has memory. If a node
> has memory then it has at least one zone defined in its pgdat structure
> that is located in the pgdat itself.

Uh, except node_memory_map is not defined below.

I'm guessing you just need

#define	node_memory_map	node_states[N_MEMORY]

below.

Thanks,
Nish

> N_MEMORY can then be used in various places to insure that we
> do the right thing when we encounter a memoryless node.
> 
> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
> Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
> Signed-off-by: Christoph Lameter <clameter@sgi.com>
> 
> ---
>  include/linux/nodemask.h |    1 +
>  mm/page_alloc.c          |    9 +++++++--
>  2 files changed, 8 insertions(+), 2 deletions(-)
> 
> Index: linux-2.6.22-rc6-mm1/include/linux/nodemask.h
> ===================================================================
> --- linux-2.6.22-rc6-mm1.orig/include/linux/nodemask.h	2007-07-09 22:13:44.000000000 -0700
> +++ linux-2.6.22-rc6-mm1/include/linux/nodemask.h	2007-07-09 22:16:05.000000000 -0700
> @@ -343,6 +343,7 @@ static inline void __nodes_remap(nodemas
>  enum node_states {
>  	N_POSSIBLE,	/* The node could become online at some point */
>  	N_ONLINE,	/* The node is online */
> +	N_MEMORY,	/* The node has memory */
>  	NR_NODE_STATES
>  };
> 
> Index: linux-2.6.22-rc6-mm1/mm/page_alloc.c
> ===================================================================
> --- linux-2.6.22-rc6-mm1.orig/mm/page_alloc.c	2007-07-09 22:15:45.000000000 -0700
> +++ linux-2.6.22-rc6-mm1/mm/page_alloc.c	2007-07-09 22:19:28.000000000 -0700
> @@ -2392,8 +2392,13 @@ static int __build_all_zonelists(void *d
>  	int nid;
> 
>  	for_each_online_node(nid) {
> -		build_zonelists(NODE_DATA(nid));
> -		build_zonelist_cache(NODE_DATA(nid));
> +		pg_data_t *pgdat = NODE_DATA(nid);
> +
> +		build_zonelists(pgdat);
> +		build_zonelist_cache(pgdat);
> +
> +		if (pgdat->node_present_pages)
> +			node_set_state(nid, N_MEMORY);
>  	}
>  	return 0;
>  }
> 
> -- 

-- 
Nishanth Aravamudan <nacc@us.ibm.com>
IBM Linux Technology Center

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [patch 10/12] Memoryless nodes: Update memory policy and page migration

[Nishanth Aravamudan]

On 11.07.2007 [09:16:53 -0700], Nishanth Aravamudan wrote:
> On 11.07.2007 [16:48:11 +0900], KAMEZAWA Hiroyuki wrote:
> > On Tue, 10 Jul 2007 14:52:15 -0700
> > Christoph Lameter <clameter@sgi.com> wrote:
> > 
> > > +			*nodes = node_memory_map;
> > >  		else
> > node_states[N_MEMORY]  ?
> > 
> > 
> > >  		check_pgd_range(vma, vma->vm_start, vma->vm_end,
> > > -				&node_online_map, MPOL_MF_STATS, md);
> > > +				&node_memory_map, MPOL_MF_STATS, md);
> > >  	}
> > 
> > Again here.
> 
> I think Christoph missed a hunk in the node_memory_map patch, which
> would
> 
> #define node_memory_map node_stats[N_MEMORY]

Or maybe it's intentional -- and your changes are appropriate (and
in-line with the other changes Christoph's patches made).

Thanks,
Nish

-- 
Nishanth Aravamudan <nacc@us.ibm.com>
IBM Linux Technology Center

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [patch 10/12] Memoryless nodes: Update memory policy and page migration

[Christoph Lameter]

On Wed, 11 Jul 2007, Nishanth Aravamudan wrote:

> I think Christoph missed a hunk in the node_memory_map patch, which
> would
> 
> #define node_memory_map node_stats[N_MEMORY]

No. Somehow the patch was not updated. Need to send out a new rev.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [patch 11/12] Memoryless nodes: Fix GFP_THISNODE behavior

[Christoph Lameter]

On Wed, 11 Jul 2007, KAMEZAWA Hiroyuki wrote:

> > +	struct zonelist *zonelist;
> > +
> > +	for (i = 0; i < MAX_NR_ZONES; i++) {
> > +		zonelist = pgdat->node_zonelists + MAX_NR_ZONES + i;
> > + 		j = build_zonelists_node(pgdat, zonelist, 0, i);
> > +		zonelist->zones[j] = NULL;
> > +	}
> > +}
> adding explanation as following is maybe good.
> ==
> 	/* 
>          * NUMA default zonelist is structured as
> 	 * [0....MAX_NR_ZONES) : allows fallbacks to other node for each GFP_MASK.
> 	 * [MAX_NR_ZONES...MAX_ZONELISTS) : disallow fallbacks for GFP_XXX |GFP_THISNODE
> 	 */
> ==


Will add this.
> > +
> > +/*
> >   * Build zonelists ordered by zone and nodes within zones.
> >   * This results in conserving DMA zone[s] until all Normal memory is
> >   * exhausted, but results in overflowing to remote node while memory
> > @@ -2267,7 +2283,7 @@ static void build_zonelists(pg_data_t *p
> >  	int order = current_zonelist_order;
> >  
> >  	/* initialize zonelists */
> > -	for (i = 0; i < MAX_NR_ZONES; i++) {
> > +	for (i = 0; i < 2 * MAX_NR_ZONES; i++) {
> 
> please use MAX_ZONELISTS here.

Right. Thanks.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>