Re: [PATCH 8/8] Per-container pages reclamation

[Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>]

Andrew Morton wrote:
> On Wed, 30 May 2007 19:42:26 +0400
> Pavel Emelianov <xemul@openvz.org> wrote:
> 
[snip]
>>
>> +#ifdef CONFIG_RSS_CONTAINER
>> +unsigned long try_to_free_pages_in_container(struct rss_container *cnt)
>> +{
>> +	struct scan_control sc = {
>> +		.gfp_mask = GFP_KERNEL,
>> +		.may_writepage = 1,
>> +		.swap_cluster_max = 1,
>> +		.may_swap = 1,
>> +		.swappiness = vm_swappiness,
>> +		.order = 0, /* in this case we wanted one page only */
>> +		.cnt = cnt,
>> +		.isolate_pages = isolate_pages_in_container,
>> +	};
>> +	int node;
>> +	struct zone **zones;
>> +
>> +	for_each_online_node(node) {
>> +#ifdef CONFIG_HIGHMEM
>> +		zones = NODE_DATA(node)->node_zonelists[ZONE_HIGHMEM].zones;
>> +		if (do_try_to_free_pages(zones, sc.gfp_mask, &sc))
>> +			return 1;
>> +#endif
>> +		zones = NODE_DATA(node)->node_zonelists[ZONE_NORMAL].zones;
>> +		if (do_try_to_free_pages(zones, sc.gfp_mask, &sc))
>> +			return 1;
>> +	}
> 
> Definitely need to handle ZONE_DMA32 and ZONE_DMA (some architectures put
> all memory into ZONE_DMA (or they used to))

Can we iterate from MAX_NR_ZONES-1 to automatically choose the right
zone for the system?

for_each_online_node(node)
	for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
 		zones = NODE_DATA(node)->node_zonelists[i].zones;
		if (do_try_to_free_pages(zones, sc.gfp_mask, &sc))
			return 1;

The above code works on my PPC64 box where all memory is in ZOME_DMA.

>> +	return 0;
>> +}
>> +#endif
>> +
>>  unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask)
>>  {
>>  	struct scan_control sc = {
> -
> 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/
>