Message-ID: <50999755.4000209@linux.vnet.ibm.com>
Date: Tue, 06 Nov 2012 15:03:49 -0800
From: Dave Hansen <dave@linux.vnet.ibm.com>
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:16.0) Gecko/20121028 Thunderbird/16.0.2
MIME-Version: 1.0
To: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
CC: akpm@linux-foundation.org, mgorman@suse.de, mjg59@srcf.ucam.org,
        paulmck@linux.vnet.ibm.com, maxime.coquelin@stericsson.com,
        loic.pallardy@stericsson.com, arjan@linux.intel.com,
        kmpark@infradead.org, kamezawa.hiroyu@jp.fujitsu.com, lenb@kernel.org,
        rjw@sisk.pl, gargankita@gmail.com, amit.kachhap@linaro.org,
        svaidy@linux.vnet.ibm.com, thomas.abraham@linaro.org,
        santosh.shilimkar@ti.com, linux-pm@vger.kernel.org, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH 1/8] mm: Introduce memory regions data-structure to
 capture region boundaries within node
References: <20121106195026.6941.24662.stgit@srivatsabhat.in.ibm.com> <20121106195225.6941.2868.stgit@srivatsabhat.in.ibm.com>
In-Reply-To: <20121106195225.6941.2868.stgit@srivatsabhat.in.ibm.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1457
Lines: 34

On 11/06/2012 11:52 AM, Srivatsa S. Bhat wrote:
> But of course, memory regions are sub-divisions *within* a node, so it makes
> sense to keep the data-structures in the node's struct pglist_data. (Thus
> this placement makes memory regions parallel to zones in that node).

I think it's pretty silly to create *ANOTHER* subdivision of memory
separate from sparsemem.  One that doesn't handle large amounts of
memory or scale with memory hotplug.  As it stands, you can only support
256*512MB=128GB of address space, which seems pretty puny.

This node_regions[]:

> @@ -687,6 +698,8 @@ typedef struct pglist_data {
>  	struct zone node_zones[MAX_NR_ZONES];
>  	struct zonelist node_zonelists[MAX_ZONELISTS];
>  	int nr_zones;
> +	struct node_mem_region node_regions[MAX_NR_REGIONS];
> +	int nr_node_regions;
>  #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
>  	struct page *node_mem_map;
>  #ifdef CONFIG_MEMCG

looks like it's indexed the same way regardless of which node it is in.
 In other words, if there are two nodes, at least half of it is wasted,
and 3/4 if there are four nodes.  That seems a bit suboptimal.

Could you remind us of the logic for leaving sparsemem out of the
equation here?

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/