Re: [patch for-5.3 0/4] revert immediate fallback to remote hugepages

[Vlastimil Babka]

On 10/24/19 8:59 PM, David Rientjes wrote:
>> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
>> index 4ae967bcf954..2c48146f3ee2 100644
>> --- a/mm/mempolicy.c
>> +++ b/mm/mempolicy.c
>> @@ -2129,18 +2129,20 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
>>  		nmask = policy_nodemask(gfp, pol);
>>  		if (!nmask || node_isset(hpage_node, *nmask)) {
>>  			mpol_cond_put(pol);
>> +			/*
>> +			 * First, try to allocate THP only on local node, but
>> +			 * don't reclaim unnecessarily, just compact.
>> +			 */
>>  			page = __alloc_pages_node(hpage_node,
>> -						gfp | __GFP_THISNODE, order);
>> +				gfp | __GFP_THISNODE | __GFP_NORETRY, order);
>>  
>>  			/*
>> -			 * If hugepage allocations are configured to always
>> -			 * synchronous compact or the vma has been madvised
>> -			 * to prefer hugepage backing, retry allowing remote
>> -			 * memory as well.
>> +			 * If that fails, allow both compaction and reclaim,
>> +			 * but on all nodes.
>>  			 */
>> -			if (!page && (gfp & __GFP_DIRECT_RECLAIM))
>> +			if (!page)
>>  				page = __alloc_pages_node(hpage_node,
>> -						gfp | __GFP_NORETRY, order);
>> +								gfp, order);
>>  
>>  			goto out;
>>  		}
> Hi Vlastimil,
> 
> For the default case where thp enabled is not set to "always" and the VMA

I assume you meant "defrag" instead of "enabled".
 
> is not madvised for MADV_HUGEPAGE, how does this prefer to return node 
> local pages rather than remote hugepages?  The idea is to optimize for 
> access latency when the vma has not been explicitly madvised.
 
Right, you mentioned this before IIRC, and I forgot. How about this?
We could be also smarter and consolidate to a single attempt if there's
actually just a single NUMA node, but that can be optimized later.

----8<----