Message-ID: <BANLkTikY3NdbsZDLvHY_vhY-9c1Fo-FKPg@mail.gmail.com>
Date:	Wed, 13 Apr 2011 15:26:48 -0700
From:	Joshua Scoggins <theoretically.x64@...il.com>
To:	Justin Piszcz <jpiszcz@...idpixels.com>
Cc:	Daniel Halperin <dhalperi@...washington.edu>,
	Ivo Van Doorn <ivdoorn@...il.com>, linux-usb@...r.kernel.org,
	linux-wireless@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: 2.6.38: rt2800usb: high latency (1000ms)?

I have an ASUS N-13 USB wireless adapter (which uses the 3070 chipset)
and have never ever had an issue with it. The only thing that I had
issues with was that certain functions would act
erratically until I upgraded to 2.6.37. I'm not sure if I'm using the
staging driver or not (I can't
get to the machine right now) but I believe that the module was called
rt2800 or something like that. It connects to a DSL/wireless router
combo made by netgear that is pretty bad but works
for my parents needs. It has massive latency issues connecting to web
sites but never an issue with SSH.

I also have a WNDR3700 but that machine does not connect to that
network. I notice that you're using WPA1 instead of WPA2. In my
experience I have found that WPA1 can cause issues on certain wireless
chipsets especially atheros and broadcom so it could be WPA1 is
causing the latency issue. It could also be that you are not
connecting to the router at 802.11n speeds but 802.11g. If you look at
your log it shows supported speeds as being a max of 54.0 Megabits per
second. This translates to about 5.4 megabytes per second ideally. The
reason why windows gets better speeds is because it is actually
connected at 802.11n speeds. It seems that you have a configuration
issue going on. Try connecting the wireless adapter to the 5.0 ghz
network instead of the 2.4 gigahertz network and see if you get a
speed improvement. On the 5.0 ghz band only 802.11a/n are supported so
there is no possibility of connecting at g speeds. If your adapter
doesn't support the 5.0 ghz band then it seems the driver is limiting
the adapter to g speeds.

Josh

On Wed, Apr 13, 2011 at 1:36 PM, Justin Piszcz <jpiszcz@...idpixels.com> wrote:
>
>
> On Wed, 13 Apr 2011, Daniel Halperin wrote:
>
>> On Wed, Apr 13, 2011 at 1:13 PM, Justin Piszcz <jpiszcz@...idpixels.com>
>> wrote:
>>>>
>>>> (1) What is the AP's beacon period and DTIM? Typical values are 100
>>>> TUs for beacons (102.4 ms) and 2 for DTIM (2 beacons per power-save
>>>> wakeup) which should imply a mean of 100 and max of 200 ms delay even
>>>> on pings.
>>>
>>> I am using a WNDR3700 with default settings in terms of beacons/etc.  No
>>> issues with any device (laptop, computer, etc (in windows)), I have two
>>> wireless USB adapters (bought two) and in Windows, no problems, I don't
>>> think
>>> it is the WNDR3700.  As far as linux/wpa-supplicant, using default
>>> settings.
>>
>> Not enough info. What does "iw dev wlan1 scan dump"  (it might not be
>> wlan1 for you) say for "beacon interval"?
>
> # iw dev wlan0 scan dump
>
> BSS (hidden) (on wlan0) -- associated
>        TSF: 103430650682 usec (1d, 04:43:50)
>        freq: 2417
>        beacon interval: 100
>        capability: ESS Privacy ShortPreamble ShortSlotTime (0x0431)
>        signal: -59.00 dBm
>        last seen: 1345742 ms ago
>        SSID: (hidden)
>        Supported rates: 1.0* 2.0* 5.5* 11.0* 6.0 9.0 12.0 18.0
>        DS Parameter set: channel 2
>        RSN:     * Version: 1
>                 * Group cipher: TKIP
>                 * Pairwise ciphers: CCMP TKIP
>                 * Authentication suites: PSK
>                 * Capabilities: (0x0000)
>        WPA:     * Version: 1
>                 * Group cipher: TKIP
>                 * Pairwise ciphers: CCMP TKIP
>                 * Authentication suites: PSK
>        ERP: <no flags>
>        Extended supported rates: 24.0 36.0 48.0 54.0
>        WMM:     * Parameter version 1
>                 * u-APSD
>                 * BE: CW 15-1023, AIFSN 3
>                 * BK: CW 15-1023, AIFSN 7
>                 * VI: CW 7-15, AIFSN 2, TXOP 3008 usec
>                 * VO: acm CW 3-7, AIFSN 2, TXOP 1504 usec
>        HT capabilities:
>                Capabilities: 0x11ce
>                        HT20/HT40
>                        SM Power Save disabled
>                        RX HT40 SGI
>                        TX STBC
>                        RX STBC 1-stream
>                        Max AMSDU length: 7935 bytes
>                        DSSS/CCK HT40
>                Maximum RX AMPDU length 65535 bytes (exponent: 0x003)
>                Minimum RX AMPDU time spacing: 1/2 usec (0x02)
>                HT RX MCS rate indexes supported: 0-15
>                HT TX MCS rate indexes are undefined
>        WPS:     * Version: 1.0
>                 * Manufacturer: Netgear, Inc.
>                 * Model: WNDR3700
>                 * Device name: (hidden)
>                 * Config methods: Ethernet, Label, PBC
>>
>> Does anyone know how to get the DTIM period out of iw?
>>
>>>> (2) How long does the client wait after waking up to go back to sleep?
>>>> It should be at least a few seconds. For ssh, then, you should see
>>>> something like a 100-200 ms delay for the first key and then nothing
>>>> at all unless you stop typing for a bit.
>>>
>>> It lags with each word I type, it is terrible.  If I run something like
>>> dmesg or ps auxww, the entire session freezes for 5-10 seconds before it
>>> comes back.
>>
>> Sorry; I meant what is the software stack configured to do? Do some
>> looking around.
>>
>>>> I'm SSHing over a Wi-Fi link that uses power save right this second,
>>>> and have for years. It's not generally an issue, I suspect something
>>>> worse is going on.
>>>
>>> Maybe the wireless usb adapters do not function well in Linux with power
>>> save
>>> on.
>>>
>>> I bought them awhile ago, they had the highest reviews, and in Windows,
>>> they did do 10-15MiB/s, in Linux, I see ~4.6MiB/s (but that was with
>>> power
>>> save on) about the same, 4.5MiB/s.
>>>
>>> http://www.amazon.com/Medialink-Wireless-Adapter-802-11n-Compatible/dp/B002RM08RE
>>
>> Yeah, these might indicate a fairly sizable problem in the Linux drivers
>> IMO.
>>
>> Dan
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists