Michael Chan wrote:
On Mon, 2007-05-07 at 09:39 -0700, Rick Jones wrote:
On how "topologically big" a system has this resurrection of the PIO read been
tried so far?
If you're asking how much impact the read will have on performance, the
answer is that it will depend on whether you frequently get spurious
interrupts or not without the read. The read itself has a measurable
impact on performance, but it will offset the performance hit of
entering the IRQ handler twice if you get frequent spurious interrupts.
It also prevents the kernel from shutting down the IRQ in some extreme
cases.
If you get spurious interrupts infrequently, the read is unfortunately a
net loss.
Mostly I was thinking that not all PIO reads are the same "length" and so the
effect of the PIO read will vary, perhaps considerably, with the platform,
particularly for a very large NUMA platform.
rick jones
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
