Re: [RFC PATCH] mm: count zram read/write into PSI_IO_WAIT

[Chris Down]

Zhaoyang Huang writes:
> No. Block device related D-state will be counted in via
> psi_dequeue(io_wait). What I am proposing here is do NOT ignore the
> influence on non-productive time by huge numbers of in-context swap
> in/out (zram like). This can help to make IO pressure more accurate
> and coordinate with the number of PSWPIN/OUT. It is like counting the
> IO time within filemap_fault->wait_on_page_bit_common into
> psi_mem_stall, which introduces memory pressure high by IO.

I think part of the confusion here is that the name "io" doesn't really just 
mean "io", it means "disk I/O". As in, we are targeting real, physical or 
network disk I/O. Of course, we can only do what's reasonable if the device 
we're accounting for is layers upon layers eventually leading to a 
memory-backed device, but _intentionally_ polluting that with more memory-bound 
accesses doesn't make any sense when we already have separate accounting for 
memory. Why would anyone want that?

I'm with Johannes here, I think this would actively make memory pressure 
monitoring less useful. This is a NAK from my perspective as someone who 
actually uses these things in production.