Re: libata/sata_nv latency on NVIDIA CK804 [was Re: AMD64 X2 lost ticks on PM timer]

[Ingo Molnar <mingo@elte.hu>]

* Jeff Garzik <jeff@garzik.org> wrote:

> Ingo Molnar wrote:
> >in this particular case there's only very simple (and non-IO) 
> >instructions in that codepath (no loops either), except for 
> >ata_bmdma_status() which does IO ops: so i agree with you that the most 
> >likely candidate for the delay is the readb() or the inb() in 
> >ata_bdma_status().
> >
> >I'm wondering which one of the two. inb()s are known to be horrible on 
> >some systems - but i've never seen them take 16 milliseconds. If it's 
> >the inb(), then that could also involve SMM mode and IO 
> 
> 
> ata_bmdma_status() is just a single IO read, and even 1ms is highly 
> improbable.

well, it's a PIO inb() op i think, and could thus in theory trigger SMM 
BIOS code.

> I'd look elsewhere.  There are a ton of udelay() calls in the legacy 
> PCI IDE BMDMA code paths (sata_nv uses these), so I'm not surprised 
> there is latency in general, in a libata+sata_nv configuration. [...]

they would show up in the latency trace ... the latency trace is very 
clear, and in the previous mail i described the precise codepath where 
we observed the latency. Only that single PIO read is there AFAICS.
  
	Ingo