-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi,
Since there is effort undergoing to port a newer pf version to FreeBSD,
I think this work would not be useful for inclusion in -CURRENT.
However, I'd like to share it here as someone may find it useful before
the new pf code hits the tree. The pa
Nice Work! Thanks a lot!
On Thursday 20 August 2009 09:39:27 Xin LI wrote:
> Since there is effort undergoing to port a newer pf version to FreeBSD,
> I think this work would not be useful for inclusion in -CURRENT.
> However, I'd like to share it here as someone may find it useful before
> the n
--- On Thu, 8/20/09, H.Fazaeli wrote:
> From: H.Fazaeli
> Subject: Re: em driver input errors
> To: alexpalias-bsd...@yahoo.com
> Cc: freebsd-net@freebsd.org
> Date: Thursday, August 20, 2009, 12:22 PM
>
>
> can you provide sysctl dev.em.0.debug=1 output?
em0: Adapter hardware address = 0x
Hello.
--- On Wed, 8/19/09, Дмитрий Замураев wrote:
> From: Дмитрий Замураев
> Subject: Re: em driver input errors
> To: alexpalias-bsd...@yahoo.com
> Cc: freebsd-net@freebsd.org
> Date: Wednesday, August 19, 2009, 7:27 PM
> Hello Alex.
>
> What sheduler are you using? ULE or 4BSD
> Have you N
Hello Alex,
SCHED_ULE, HZ=1000:
I use this too
> From the output of "netstat -nI em0 -w 5":
maybe mistake, did you meen "netstat -w5 em0" ?
Nope, exactly as in my mail, "netstat -nI em0 -w 5". It does take 5
seconds to produce meaningful output.
hmm, just comments:
-nShow network addre
--- On Thu, 8/20/09, Dmitriy Zamuraev wrote:
> From: Dmitriy Zamuraev
> Subject: Re: em driver input errors
> To: alexpalias-bsd...@yahoo.com
> Cc: freebsd-net@freebsd.org
> Date: Thursday, August 20, 2009, 2:58 PM
> Hello Alex,
>
> > SCHED_ULE, HZ=1000:
> I use this too
>
> > And "netstat
Try to set
sysctl net.isr.direct=1
swi:net will not use 100% of your CPU.
___
freebsd-net@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "freebsd-net-unsubscr...@freebsd.org"
--- On Wed, 8/19/09, Manish Vachharajani wrote:
> From: Manish Vachharajani
> Subject: Re: Dropped vs. missed packets in the ixgbe driver
> To: "Barney Cordoba"
> Cc: freebsd-net@freebsd.org
> Date: Wednesday, August 19, 2009, 2:46 PM
> Agreed, the errors are reported but
> missed packets are
--- On Wed, 8/19/09, Julian Elischer wrote:
> From: Julian Elischer
> Subject: Re: [PATCH] Fix for e1000 (em/igb) NOARP issue [Was Re: em(4):
> sending ARP regardless of NOARP flag]
> To: "Barney Cordoba"
> Cc: d...@delphij.net, pyu...@gmail.com, "David Christensen"
> , "freebsd-net@freebsd
there were some people looking at adding vnet support to pf.
Since we discussed it last, the rules of the game have
significantly changed for the better. With the addition
of some new facilitiesin FreeBSD, the work needed to virtualize
a module has significantly decreased.
The following doc give
Oh whoops, sorry didn't see that. So the plot thickens. Why don't
these errors show up in the netstat output I forwarded originally?
Ierrs was 0 but the dmesg output clearly shows missed packets. Any
thoughts on what is going on? Looking at the code, missed_rx should
certainly get counted in th
I've been looking at the code due to another problem of bogus flow control
numbers, and there are some changes needed, things that should be 82599 vs
82598 and were not seperated properly. Will be forthcoming. Not sure if it
has any relevance to this, but its possible.
Jack
On Thu, Aug 20, 2009
I noticed the bogus XON, XOFF numbers. I'm glad to see it will be
fixed so I can cross it off my todo list. :) I don't think the issue
is related though, but you never know.
Barney pointed out that missed_rx in the ixgbe_update_stats_counters
function accumulates the missed packet registers int
My co-founder, John, just pointed out the problem.
The MPC register on ixgbe is clear on read. stats.mpc[i] correctly
accumulates the misses, but missed_rx gets set to 0 on any interval
where there are no misses and subsequently, if_errors gets set to 0
(assuming no crcerrs or rlecs.) I believe
Whoops, the correct fix is below. Forgot to use missed_rx_cum when summing:
diff --git a/fbsd/ixgbe-1.7.4/ixgbe.c b/fbsd/ixgbe-1.7.4/ixgbe.c
index f1fa728..262d64d 100644
--- a/fbsd/ixgbe-1.7.4/ixgbe.c
+++ b/fbsd/ixgbe-1.7.4/ixgbe.c
@@ -4294,7 +4294,7 @@ ixgbe_update_stats_counters(struct adapter
Thanks Manish, I will keep this diff around and work it into my final
changes in the
code, you confirmed this solved the problem you were seeing I assume?
Cheers,
Jack
On Thu, Aug 20, 2009 at 10:34 AM, Manish Vachharajani <
mani...@lineratesystems.com> wrote:
> Whoops, the correct fix is below
Yes, in our latest tests, netstat correctly outputs the misses as Ierrs.
Manish
On Thu, Aug 20, 2009 at 11:37 AM, Jack Vogel wrote:
> Thanks Manish, I will keep this diff around and work it into my final
> changes in the
> code, you confirmed this solved the problem you were seeing I assume?
>
>
Lev Serebryakov wrote:
> Hello, Stef.
>
>> ath0: ath_rx_proc: no mbuf!
>
>> The mbufs are in fact all used up. I allocate more via
>> kern.ipc.nmbclusters, and see the same behavior.
> Same problem here on 7.2-STABLE, but incresaing kern.ipc.nmbclusters
> to 65536 helps. It seems, that when traf
Manish,
This is a diff on my changes, note some differences: first, I don't know
what vintage your
code was, but you do NOT want to read RNBC(i) into stats.mpc. also that is
an 82598-only
thing. This means that missed_rx is going to accumulate just as it should,
except it should
be 64 bit.
Th
19 matches
Mail list logo
