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

[Balbir Singh]

Pavel Emelianov wrote:
> Balbir Singh wrote:
> 
> [snip]
> 
>>>>> +	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))
>> Won't the node_zonelists[ZONE_NORMAL].zones contain all lower zones (including
>> ZONE_DMA and ZONE_DMA32) from various nodes organized by cost?
>>
>> I need to go lookup the node_zonelists creation.
> 
> 
> OK, I've got it. The node's zonelist indexed with ZONE_XXX contains
> the zone specified and all the zones beyond it. Thus shrinking from
> ZONE_HIGHMEM (ZONE_NORMAL if the latter does not exist) is enough.
> 
> Thanks,
> Pavel

Exactly!

-- 
	Warm Regards,
	Balbir Singh
	Linux Technology Center
	IBM, ISTL