Re: [PATCH] mm/alloc: fallback to first node if the wanted node offline

From: Vlastimil Babka
Date: Tue Dec 04 2018 - 09:42:14 EST


On 12/4/18 9:56 AM, Michal Hocko wrote:
>> The device's node num is 2. And in my case, I used nr_cpus param. Due
>> to init_cpu_to_node() initialize all the possible node. It is hard
>> for me to figure out without this param, how zonelists is accessed
>> before page allocator works.
> I believe we should focus on this. Why does the node have no zonelist
> even though all zonelists should be initialized already? Maybe this is
> nr_cpus pecularity and we do not initialize all the existing numa nodes.
> Or maybe the device is associated to a non-existing node with that
> setup. A full dmesg might help us here.

Yes, a full dmesg should contain line such as this one:

[ 0.137407] Built 1 zonelists, mobility grouping on. Total pages:
6181664

That should at least tell us if nr_cpus=X resulted in some node's
zonelists not being built.