Return-path: Received: from mail.gmx.net ([213.165.64.20]:45126 "HELO mail.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S966694AbZLHXxV (ORCPT ); Tue, 8 Dec 2009 18:53:21 -0500 From: "Stefan Lippers-Hollmann" To: Johannes Berg Subject: Re: regression: rt2561 frequent "Arrived at non-free entry" errors in =?utf-8?q?=092=2E6=2E32?= Date: Wed, 9 Dec 2009 00:53:24 +0100 Cc: Gertjan van Wingerde , Andi Kleen , linux-wireless@vger.kernel.org, Tim Blechmann , rjw@sisk.pl, IvDoorn@gmail.com, linville@tuxdriver.com References: <20091204233202.GA13658@basil.fritz.box> <200912082339.16893.s.L-H@gmx.de> <1260312016.32227.6.camel@johannes.local> In-Reply-To: <1260312016.32227.6.camel@johannes.local> MIME-Version: 1.0 Content-Type: Text/Plain; charset="utf-8" Message-Id: <200912090053.25798.s.L-H@gmx.de> Sender: linux-wireless-owner@vger.kernel.org List-ID: Hi On Tuesday 08 December 2009, Johannes Berg wrote: > On Tue, 2009-12-08 at 23:39 +0100, Stefan Lippers-Hollmann wrote: > > > Unfortunately this fails to compile for me: > > well remove the spurious opening brace? :) yes, of course - but I have to admit that I didn't look too well at the patch, after your other subthread - sorry about the noise. with the patch applied (powersaving enabled): - Downloading a larger file and therefore keeping the interface busy works now pretty well, while I did hit connection time outs before with powersaving enabled: Fetched 89.7MB in 30s (2926kB/s) - pinging rt61pci results in rather unsteady response times (packet loss can happen, but rarely), which might be a side effect of the card trying to sleep. # ping rt61 PING rt61 (192.168.0.71): 56 data bytes 64 bytes from 192.168.0.71: seq=0 ttl=64 time=1016.131 ms 64 bytes from 192.168.0.71: seq=1 ttl=64 time=17.574 ms 64 bytes from 192.168.0.71: seq=2 ttl=64 time=906.219 ms 64 bytes from 192.168.0.71: seq=3 ttl=64 time=1.499 ms 64 bytes from 192.168.0.71: seq=4 ttl=64 time=801.945 ms 64 bytes from 192.168.0.71: seq=5 ttl=64 time=1.498 ms 64 bytes from 192.168.0.71: seq=6 ttl=64 time=644.036 ms ^C --- rt61 ping statistics --- 7 packets transmitted, 7 packets received, 0% packet loss round-trip min/avg/max = 1.498/484.128/1016.131 ms - connecting to the rt61pci through ssh now works again, but typing exposes pretty high latencies whenever the interface is otherwise idle - I'm not sure if this is to be expected with powersaving enabled, though. $ while true; do time ssh rt61 exit; sleep 5; done real 0m1.867s user 0m0.040s sys 0m0.003s real 0m0.997s user 0m0.042s sys 0m0.005s real 0m0.214s user 0m0.044s sys 0m0.003s ^C while the latency is much better when the interface is busy (downloading a large file) and therefore can't power down: $ while true; do time ssh rt61 exit; sleep 5; done real 0m0.395s user 0m0.041s sys 0m0.003s real 0m0.491s user 0m0.043s sys 0m0.001s real 0m0.518s user 0m0.044s sys 0m0.000s ^C without the patch applied (powersaving enabled): - Downloading a larger file in a loop times out pretty often and doesn't reach expected throughputs (very unsteady), if the interface is kept busy (ping in parallel), the situation improves significantly. - pinging rt61pci exposes large latencies and exposes significant packet loss # ping rt61 PING rt61 (192.168.0.71): 56 data bytes 64 bytes from 192.168.0.71: seq=3 ttl=64 time=6.415 ms 64 bytes from 192.168.0.71: seq=6 ttl=64 time=999.531 ms 64 bytes from 192.168.0.71: seq=7 ttl=64 time=2.695 ms 64 bytes from 192.168.0.71: seq=8 ttl=64 time=1.179 ms 64 bytes from 192.168.0.71: seq=9 ttl=64 time=0.974 ms 64 bytes from 192.168.0.71: seq=13 ttl=64 time=8650.425 ms 64 bytes from 192.168.0.71: seq=14 ttl=64 time=7653.903 ms 64 bytes from 192.168.0.71: seq=15 ttl=64 time=6653.707 ms 64 bytes from 192.168.0.71: seq=16 ttl=64 time=5653.463 ms 64 bytes from 192.168.0.71: seq=17 ttl=64 time=4653.132 ms 64 bytes from 192.168.0.71: seq=18 ttl=64 time=3652.887 ms 64 bytes from 192.168.0.71: seq=19 ttl=64 time=2652.628 ms 64 bytes from 192.168.0.71: seq=20 ttl=64 time=1652.377 ms 64 bytes from 192.168.0.71: seq=21 ttl=64 time=652.126 ms ^C --- rt61 ping statistics --- 23 packets transmitted, 14 packets received, 39% packet loss round-trip min/avg/max = 0.974/3063.245/8650.425 ms - ssh connections are affected accordingly and basically unusable. $ while true; do time ssh rt61 exit; sleep 5; done real 0m5.242s user 0m0.044s sys 0m0.002s real 0m1.682s user 0m0.043s sys 0m0.001s real 0m5.797s user 0m0.044s sys 0m0.002s ^C without the patch applied (powersaving disabled, see patch below which unfortunately disables powersaving for all rt2x00 devices, even though rt2500usb and rt73usb don't seem to be affected): --- a/drivers/net/wireless/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/rt2x00/rt2x00dev.c @@ -837,6 +837,15 @@ int rt2x00lib_probe_dev(struct rt2x00_de BIT(NL80211_IFTYPE_WDS); /* + * Disable power saving for the time being, it breaks at least: + * - rt61pci + * while it isn't necessary for: + * - rt2500usb + * - rt73usb + */ + rt2x00dev->hw->wiphy->ps_default = false; + + /* * Let the driver probe the device to detect the capabilities. */ retval = rt2x00dev->ops->lib->probe_hw(rt2x00dev); - Downloading a larger file in a loop works as expected, with steady results - independent of teh interface being idle or busy: Fetched 89.7MB in 30s (2903kB/s) - ping times are good, no packet loss: # ping rt61 PING rt61 (192.168.0.71): 56 data bytes 64 bytes from 192.168.0.71: seq=0 ttl=64 time=1.267 ms 64 bytes from 192.168.0.71: seq=1 ttl=64 time=1.208 ms 64 bytes from 192.168.0.71: seq=2 ttl=64 time=1.197 ms 64 bytes from 192.168.0.71: seq=3 ttl=64 time=1.106 ms 64 bytes from 192.168.0.71: seq=4 ttl=64 time=1.123 ms ^C --- rt61 ping statistics --- 5 packets transmitted, 5 packets received, 0% packet loss round-trip min/avg/max = 1.106/1.180/1.267 ms - ssh connections are snappy as expected: $ while true; do time ssh rt61 exit; sleep 5; done real 0m0.188s user 0m0.042s sys 0m0.003s real 0m0.145s user 0m0.041s sys 0m0.004s real 0m0.146s user 0m0.041s sys 0m0.003s ^C Regards Stefan Lippers-Hollmann