Re: [PATCH] memcg: allow exiting tasks to write back data to swap

[Balbir Singh]

On 12/13/24 01:03, Rik van Riel wrote:
> On Thu, 2024-12-12 at 14:25 +1100, Balbir Singh wrote:
>>
>> I was asking about this change (this patch), I know that the return
>> true will help avoid the PAGE_ACTIVATE path, but I am not sure why
>> this function will return false if CONFIG_ZSWAP is enabled (unless
>> zswap_writeback is turned off in one of the groups)
>>
> Some workloads are fine with incurring the latency
> from zswap, but do not want the latency of actual
> block device backed swap.
> 
> Having zswap enabled, with writeback disabled, has
> been beneficial to a number of workloads.
> 

Thanks, that was the missing bit

Balbir