Date: Fri, 13 Feb 2009 17:08:34 +1100 (EST) From: Ian Smith <smithi@nimnet.asn.au> To: Sam Leffler <sam@freebsd.org> Cc: freebsd-mobile@freebsd.org Subject: Re: Problems with ath at kern.hz=100 Message-ID: <20090213165848.N38905@sola.nimnet.asn.au> In-Reply-To: <4991ABA0.4050300@freebsd.org> References: <uh7iqnjzzi9.fsf@P142.sics.se> <20090210154047.N38905@sola.nimnet.asn.au> <4991ABA0.4050300@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, 10 Feb 2009, Sam Leffler wrote: > Ian Smith wrote: > > On Mon, 9 Feb 2009, Bengt Ahlgren wrote: > > > > > I was changing kern.hz to 100 on my IBM X40 (Pentium-M) laptop to see > > > whether that saves some battery, but ran into problems with ath not > > > working properly. At first I thought that my hardware was failing, > > > but changing hz back to 1000 solved the problem. I am running > > > 7.1-RELEASE-p1 and have the following Atheros chip: > > > > Feb 9 11:13:10 P142 kernel: ath_hal: 0.9.20.3 (AR5210, AR5211, > > AR5212, RF5111, RF5112, RF2413, RF5413) > > > Feb 9 11:13:10 P142 kernel: ath0: <Atheros 5212> mem > > 0xd0200000-0xd020ffff irq 11 at device 2.0 on pci2 > > > Feb 9 11:13:10 P142 kernel: ath0: [ITHREAD] > > > Feb 9 11:13:10 P142 kernel: ath0: WARNING: using obsoleted if_watchdog > > interface > > > Feb 9 11:13:10 P142 kernel: ath0: Ethernet address: 00:05:4e:4e:1f:c7 > > > Feb 9 11:13:10 P142 kernel: ath0: mac 5.6 phy 4.1 5ghz radio 1.7 2ghz > > radio 2.3 > > > > There's an order of magnitude room to move between 100 and 1000 Hz. You > > could also try with maybe 250 or 500? > > > > What speed is your Pentium-M? Are you using powerd? If so, what minimum > > CPU freq does it drop back to (sysctl debug.cpufreq.lowest)? > > > > Sam has talked of a problem with ath (and maybe other) interrupt rates > > overwhelming slow CPUs to the extent that userland (ie powerd) doesn't get > > a look-in for a while, as I understand it. A fast CPU clocked back to less > > than say 300MHz IS a slow CPU, until powerd gets to crank it up. > > > > If powerd starvation were happening you'd see livelock not slow traffic. The > problem was that MIB overflow interrupts from the card were pounding the host > but since the cpu clock was lowered they were not serviced fast enough. > > FWIW I believe the MIB interrupt storm issue is fixed in head. I posted a > patch to stable@ to enable backmerge of the necessary code but received ~zero > feedback in >1 month so RELENG_7 will continue to rot w/ old code. Thanks for the clarification, Sam. I did see your patch but due to ongoing Severe Weather Events here I've not had enough (solar) power to even upgrade my thinkpad to RELENG_7 for months, and the nearest access point is kilometres away, so I've had to shelve wireless dreaming until I can move house. Lame excuses i know .. [..] > You can use tcpdump to monitor traffic at multiple levels in the hierarchy: > > tcpdump -i ath0 -n # tap at 802.3 level > tcpdump -i ath0 -n -y IEEE802_11 # tap at 802.11 level > tcpdump -i ath0 -n -y IEEE802_11_RADIO # tap at driver level > > and/or you can check statistics using athstats and wlanstats or you can turn > on debugging msgs in net80211 or the ath driver using wlandebug and athdebug. > Some of these may require you to build your kernel w/ debug options (e.g. > ATH_DEBUG). All filed for now. cheers, Ian
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20090213165848.N38905>