At 05:00 PM 11/9/2006, Mike Tancsa wrote:
At 10:51 AM 11/9/2006, Scott Long wrote:
Mike Tancsa wrote:
At 08:19 PM 11/8/2006, Jack Vogel wrote:
BUT, I've added the FAST_INTR changes back into the code, so
if you go into your Makefile and add -DEM_FAST_INTR you will
then get the taskqueue stuff.
It certainly does make a difference performance wise. I did some
quick testing with netperf and netrate. Back to back boxes, using
an AMD x2 with bge nic and one intel box
CPU: AMD Athlon(tm) 64 X2 Dual Core Processor 3800+ (2009.27-MHz
686-class CPU)
CPU: Intel(R) Core(TM)2 CPU 6400 @ 2.13GHz (2144.01-MHz
686-class CPU)
The intel is a DG965SS with integrated em nic, the AMD a Tyan
with integrated bge. Both running SMP kernels with pf built in, no inet6.
Intel box as sender. In this test its with the patch from
yesterday. The first set with the patch as is, the second test
with -DEM_FAST_INTR.
Thanks for the tests. One thing to note is that Gleb reported a higher
rate of dropped packets with INTR_FAST. He is the only one who has
reported this, so I'd like to find out if there is something unique to
his environment, or if there is a larger problem to be addressed. There
are ways that we can change the driver to not drop any packets at all
for Gleb, but they expose the system to risk if there is ever an
accidental (or malicious) RX flood on the interface.
With a high rate of packets, I am able to live lock the box. I
setup the following
Some more tests. I tried again with what was committed to today's
RELENG_6. I am guessing its pretty well the same patch. Polling is
the only way to avoid livelock at a high pps rate. Does anyone know
of any simple tools to measure end to end packet loss ? Polling will
end up dropping some packets and I want to be able to compare. Same
hardware from the previous post.
SMP kernel fastfwd pf ipfw FAST_INTR streams np
(Mb)
x x x 2 livelock
x x x x 2 468 livelock
x x 2 453 lost
packets, box sluggish
x x x 2 lost
packets, box sluggish
x 2 468 lost
packets, box
sluggish
x x 2 468 livelock
x x x 2 468 livelock
2 475 livelock
x 2 livelock
P 2 OK
P x 2 OK
P x 2 OK
The P is for Uniproc, but with Polling enabled (also kern.polling.idle_poll=1)
UP single stream 58Kpps, no polling in kernel
[bsd6-32bit]# ./netblast 192.168.44.1 500 10 10
start: 1163184051.627479975
finish: 1163184061.628200458
send calls: 5869051
send errors: 0
approx send rate: 586905
approx error rate: 0
with polling
[bsd6-32bit]# ./netblast 192.168.44.1 500 10 10
start: 1163184606.651001121
finish: 1163184616.651288588
send calls: 5866199
send errors: 1
approx send rate: 586619
approx error rate: 0
With polling and 2 streams at the same time (a lot of pps! and its
still totally responsive!!)
[r6-32bit]# ./netblast 192.168.88.218 500 10 10
start: 1163184712.103954688
finish: 1163184722.104388542
send calls: 4528941
send errors: 0
approx send rate: 452894
approx error rate: 0
[r6-32bit]#
[bsd6-32bit]# ./netblast 192.168.44.1 500 10 20
start: 1163184793.172036336
finish: 1163184813.173028921
send calls: 11550594
send errors: 0
approx send rate: 577529
approx error rate: 0
[bsd6-32bit]#
polling, 2 streams at the same time
[bsd6-32bit]# ./netblast 192.168.44.1 500 10 20
start: 1163185058.477137404
finish: 1163185078.478025226
send calls: 11679831
send errors: 0
approx send rate: 583991
approx error rate: 0
[bsd6-32bit]# ./netblast 192.168.44.1 500 10 20
start: 1163185167.969551943
finish: 1163185187.970435295
send calls: 11706825
send errors: 0
approx send rate: 585341
approx error rate: 0
[bsd6-32bit]#
_______________________________________________
freebsd-net@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
