Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 2 Sep 2006 15:26:48 +0200
From:      =?utf-8?Q?Daniel_Dvo=C5=99=C3=A1k?= <dandee@hellteam.net>
To:        "'Sam Leffler'" <sam@errno.com>
Cc:        freebsd-stable@freebsd.org
Subject:   RE: atheros driver under high load, panics and even more freezes
Message-ID:  <000001c6ce93$72a247b0$6508280a@tocnet28.jspoj.czf>
In-Reply-To: <44F901B9.3040309@errno.com>

next in thread | previous in thread | raw e-mail | index | archive | help
Ok, I will upgrade my boxes and I will do simple ping tests again.

Did you see my sysctl.conf file ?

I mean these options:

kern.ipc.maxsockbuf=3D2097152
net.inet.ip.fastforwarding=3D1
net.inet.tcp.sendspace=3D65536

Could be this connected with increasing latency up to 500ms ?

I tested this issue on another box, box of my friend, you know him too.

--- 10.27.128.13 ping statistics ---
10000 packets transmitted, 10000 packets received, 0% packet loss
round-trip min/avg/max/stddev =3D 0.932/1.101/9.657/0.433 ms

There is nice avg 1,1ms.

In his sysctl.conf, there are not these maxsockbuf, fastforwarding and =
sendscpace.
It is ironic, because it was he, who advised me these values.

You wrote me "look at memory usage with vmstat and/or netstat".

Ok, bud you did not told me what I should to search for ...

And I do not know how the command write with vmstat and netstat, there =
are many switches. :)

What to find ?

Thank you.

Daniel


> -----Original Message-----
> From: Sam Leffler [mailto:sam@errno.com]=20
> Sent: Saturday, September 02, 2006 6:00 AM
> To: dandee@volny.cz
> Cc: freebsd-stable@freebsd.org; current@freebsd.org
> Subject: Re: atheros driver under high load, panics and even=20
> more freezes
>=20
> Daniel Dvo=C3=B8=C3=A1k wrote:
> > Hi all,
> > =20
> > first of all, I=C2=B4m sorry maybe for my bad English.
> > =20
> > We have 2 routers which I maintain in our mesh wireless=20
> community network.
> > =20
> > The Router 1 has 2 atheros adapters, ath0=3Dwistron cm9, =
ath1=3Dwistron=20
> > cm10, of course some sisX, fxpX and so on.
> > The Router 2 has 1 atheros adapter, ath1=3Dwistron CM10.
> > =20
> > My R1 panics and even more it freezes very often. Maybe the=20
> reason for=20
> > panicing and freezing is the same and maybe not.
> > =20
> > I started  (only after vmcore.5, so vmcore.6 is with this=20
> option)  to=20
> > use "option SW_WATCHDOG" in both my custom kernels on the R1 and R2=20
> > recently in hope, it is some walkaround for freezing at=20
> least if not for panicing.
> > =20
> > This router was installed on the 1st of April 2006.
> > =20
> > Statistics:
> > =20
> > 9 panics with 8 kernel dumps, 1 missed
> > =20
> > 10 freezes
> > =20
> > I think that all panics some how connected to athX taskq=20
> process, page=20
> > fault in kernel panic and sbflush_locked.
>=20
> Why?
>=20
> > =20
> > I guess that panic comes when router transmits and receives=20
> datas at=20
> > the maximum throughput for setted nominal media rate speed, exactly=20
> > 24Mbps, more I do not use, because there are problems with quagga
> > =20
> > ospfd packets, it is known issue.
> > =20
> > Today I did a small test with throughput.
> > =20
> > Router 1 executed this command:
> > =20
> > # ping -i 0.001 -c 100000 -s 1472 ANY IP
> > =20
> > As you see, it is not even flood ping, it is almost flood,=20
> but not flood.
> > =20
> > Throughput was about 1,13-1,2 MB/s as bmon showed me. I=20
> notice there=20
> > is not any qos and icmp.limit is so high net.inet.icmp.icmplim:=20
> > 2147483647
> > net.ineticmp.icmplim_output: 0.
> >=20
> > =20
> > First 5 s latency was about 1,1-1,7 ms After it goes to=20
> 10-30, 50-70,=20
> > 110-130, 270-300, up 300ms and packet loss
> > =20
> > .... some seconds ....
> > =20
> > panic
>=20
> 	<...lots of stuff deleted...>
>=20
> Sounds like a resource leak to me.  You've got crash dumps,=20
> look at memory usage with vmstat and/or netstat.  Past that=20
> it sounds like you're running 6.1 RELEASE which is now 6+=20
> months old.  Many bugs have been fixed including, I believe,=20
> some resource-related ones.  Please try 6-STABLE.
>=20
> 	Sam
>=20
>=20




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?000001c6ce93$72a247b0$6508280a>