Re: lowlatency-2.2.13-A1 questions

William Montgomery (william@opinicus.com)
Thu, 2 Dec 1999 11:53:45 -0500 (EST)

On Wed, 1 Dec 1999, Ingo Molnar wrote:
> the 2.2.13 patches do not have the console changes - and text console
> scrollback is introducing latencies around 4msec. The reason is that
> occasionally the console driver has to read+copy the whole (text)
> videoram, and this is slow. I solved this by adding a read-cache for all
> videoram contents, thus videoram only ever has to be written. (which is
> fast)
>
I patched my 2.2.13 kernel with 2.2.12-ikd7.bz2 and fixed the
rejects, then I applied the lowlatency-2.2.13-A1 patch and fixed
the rejects. All this works fine in my new kernel.

I set up a latency test program using the rtc device to interrupt at 64Hz.
I am using the ktrace utility to examine the /proc/trace info after
the latency test program releases a lock indicating a scheduling latency
exceeding 5msec. I see a problem which appears to be unrelated to the
console driver. When the "rtc_interrupt" occurs between the "schedule"
and the "__switch_to" (apparently just prior to __switch_to) another pid
is switched in and even though there are many "system_call"s the
test program is held off ~5msec. Any ideas?

I think the lowlatency patch is a very useful and important enhancement
to the kernel, will it become part of the mainstream kernel source (2.4.x)?

Wm

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/