mel.flynn+fbsd.questions at mailing.thruhere.net
Sat Nov 21 17:10:18 UTC 2009
On Fri, 20 Nov 2009 19:07:42 -0700, Brett Glass <brett at lariat.net> wrote:
> At 06:25 PM 11/20/2009, Mel Flynn wrote:
>>So that means that you give the kernel .25 microseconds to poll and act
>>any pending network IO. That's probably not enough.
> I think that you mean ".25 milliseconds," not ".25 microseconds," above.
Yes, sorry. It should be enough, but...it's related to CPU speed and number
of interfaces. On FreeBSD-net they can give you better advice, most notably
whether all 6 interfaces are done in one poll and so each task needs to be
completed within 1/HZ/N? I cannot say this with certainty.
>>It is further explained by
>>comment in sys/kern/kern_poll.c:
>> * Hook from hardclock. Tries to schedule a netisr, but keeps track
>> * of lost ticks due to the previous handler taking too long.
>> * Normally, this should not happen, because polling handler should
>> * run for a short time. However, in some cases (e.g. when there are
>> * changes in link status etc.) the drivers take a very long time
>> * (even in the order of milliseconds) to reset and reconfigure the
>> * device, causing apparent lost polls.
>> * The first part of the code is just for debugging purposes, and tries
>> * to count how often hardclock ticks are shorter than they should,
>> * meaning either stray interrupts or delayed events.
> Well, even at HZ=2000, kern.polling.lost_polls and
> kern.polling.suspect are both incrementing, as is kern.polling.stalled:
> stargate# sysctl -a | grep polling
> kern.polling.burst: 150
> kern.polling.burst_max: 150
> kern.polling.each_burst: 5
> kern.polling.idle_poll: 0
> kern.polling.user_frac: 50
> kern.polling.reg_frac: 20
> kern.polling.short_ticks: 0
> kern.polling.lost_polls: 41229
> kern.polling.pending_polls: 0
> kern.polling.residual_burst: 0
> kern.polling.handlers: 2
That bugs me: if you have 6 devices, the number of handlers should be
* Try to register routine for polling. Returns 0 if successful
* (and polling should be enabled), error code otherwise.
* A device is not supposed to register itself multiple times.
* This is called from within the *_ioctl() functions.
Unless this should really read "drivers", but I think it's devices.
> kern.polling.enable: 0
> kern.polling.phase: 0
> kern.polling.suspect: 31653
> kern.polling.stalled: 10
> kern.polling.idlepoll_sleeping: 1
> hw.acpi.thermal.polling_rate: 10
> But if I slow the clock down to 1000 Hz, it's unclear if the
> machine will be able to keep up with traffic. I was already getting
> more than 1,000 network interrupts per second before I tried
> polling, and I'm not sure how many packets the interfaces (some
> fxp, some em) can buffer up. I'm going to try it, but if it doesn't
> work I will have to go back to interrupt-driven operation.
You might be able if your network architecture allows it, to bring down
the task load by increasing the MTU and enable jumbo frames.
Support for Jumbo Frames is provided via the interface MTU setting.
Selecting an MTU larger than 1500 bytes with the ifconfig(8) utility
figures the adapter to receive and transmit Jumbo Frames. The maximum
MTU size for Jumbo Frames is 16114.
More information about the freebsd-questions