Description of problem: ath5k kernel module gets max 18 MB/s speed on 100% quality link, madwifi works on 54 MB/s Version-Release number of selected component (if applicable): kernel: 2.6.29.3-60.fc10.i686 How reproducible: Always Steps to Reproduce: 1. start networkmanager 2. check connection rate Actual results: 18 MB/s Expected results: 54 MB/s Additional info: pcmcia wifi card >lspci -vv Adapter 06:00.0 Ethernet controller: Atheros Communications Inc. Atheros AR5001X+ Wireless Network Adapter (rev 01) Subsystem: Atheros Communications Inc. TRENDnet TEW-443PI Wireless PCI Adapter Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx- Status: Cap+ 66MHz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx- Latency: 168 (2500ns min, 7000ns max), Cache Line Size: 128 bytes Interrupt: pin A routed to IRQ 16 Region 0: Memory at 50000000 (32-bit, non-prefetchable) [size=64K] Capabilities: [44] Power Management version 2 Flags: PMEClk- DSI- D1- D2- AuxCurrent=375mA PME(D0-,D1-,D2-,D3hot-,D3cold-) Status: D0 PME-Enable- DSel=0 DScale=2 PME- Kernel driver in use: ath5k Kernel modules: ath5k >iwconfig wlan0 IEEE 802.11bg ESSID:"t" Mode:Managed Frequency:2.437 GHz Access Point: 00: Bit Rate=18 Mb/s Tx-Power=27 dBm Retry min limit:7 RTS thr:off Fragment thr=2352 B Encryption key: [2] Security mode:open Power Management:off Link Quality=100/100 Signal level:-54 dBm Noise level=-91 dBm Rx invalid nwid:0 Rx invalid crypt:0 Rx invalid frag:0 Tx excessive retries:0 Invalid misc:0 Missed beacon:0 >ifconfig wlan0 Link encap:Ethernet HWaddr inet addr:1 Bcast:1 Mask:255.255.255.0 UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 RX packets:590589 errors:0 dropped:0 overruns:0 frame:0 TX packets:418998 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:660203457 (629.6 MiB) TX bytes:66231582 (63.1 MiB)
Please show me a comparison that measures actual throughput, not simply the output of iwconfig (which only reports the speed used for the last packet).
Any suggestions how to do it? Would you like me to make the download or something and show the dl speed for ath5k and madwifi?
(In reply to comment #1) > Please show me a comparison that measures actual throughput, not simply the > output of iwconfig (which only reports the speed used for the last packet). Any suggestions how to do it? Would you like me to make the download or something and show the dl speed for ath5k and madwifi?
Sure, it need not be too complex. Something like this should suffice: time wget http://www.mywebsite.com/somewhat-big-file.tar.gz The file should be big enough to be interesting, perhaps dozens or hundreds of megabytes. If possible, you may want to do several runs just to account for any network anomalies. It is certainly possible that madwifi could perform better (even significantly better) than ath5k. But, considering that the same person implemented the rate scaling algorithms used by both drivers...well, it is better to measure.
here you are, the measurements results: module ath5k as above *************** >time wget http://serwer/temp/file_126MB --2009-05-13 18:32:46-- http://serwer/temp/file_126MB 2009-05-13 18:41:43 (241 KB/s) - `file_126MB' saved [132571718/132571718] real 8m57.735s user 0m0.395s sys 0m2.487s >time wget http://serwer/temp/file_126MB --2009-05-13 18:45:06-- http://serwer/temp/file_126MB 2009-05-13 18:50:54 (372 KB/s) - `file_126MB.1' saved [132571718/132571718] real 5m48.238s user 0m0.359s sys 0m2.413s >time wget http://serwer/temp/file_126MB --2009-05-13 18:51:27-- http://serwer/temp/file_126MB 2009-05-13 18:56:15 (450 KB/s) - `file_126MB.2' saved [132571718/132571718] real 4m48.060s user 0m0.320s sys 0m2.374s %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%5 madwifi-trunk-r4022-20090513 module ath_pci **************** wlan0 IEEE 802.11g ESSID:"" Nickname:"" Mode:Managed Frequency:2.437 GHz Access Point: 00 Bit Rate:54 Mb/s Tx-Power:16 dBm Sensitivity=1/1 Retry:off RTS thr:off Fragment thr:off Encryption key: Security mode:restricted Power Management:off Link Quality=31/70 Signal level=-65 dBm Noise level=-96 dBm Rx invalid nwid:246 Rx invalid crypt:0 Rx invalid frag:0 Tx excessive retries:0 Invalid misc:0 Missed beacon:0 >time wget http://serwer/temp/file_126MB --2009-05-13 19:24:51-- http://serwer/temp/file_126MB 2009-05-13 19:26:03 (1.74 MB/s) - `file_126MB.3' saved [132571718/132571718] real 1m12.964s user 0m0.248s sys 0m2.766s >time wget http://serwer/temp/file_126MB --2009-05-13 19:28:16-- http://serwer/temp/file_126MB 2009-05-13 19:29:38 (1.54 MB/s) - `file_126MB' saved [132571718/132571718] real 1m22.558s user 0m0.246s sys 0m2.490s
Awesome, thanks! Now, can you try ath5k again after this command? iwconfig wlan0 rate 54M How does that perform?
>iwconfig wlan0 rate 54M ping serwer From 1 icmp_seq=1 Destination Host Unreachable the highest rate when connection works is 24M, but then I have massive packet loss: 13 packets transmitted, 8 received, 38% packet loss, time 12649ms rtt min/avg/max/mdev = 12.503/240.122/1451.773/460.172 ms, pipe 2 >iwconfig wlan0 rate auto sets the rate to 18Mb/s
Ok, this is good information. My first guess would be that your transmission power is not getting set as high with ath5k as with madwifi, or perhaps some other calibration or antenna configuration is poorly done for your device. Hopefully Bob will have some ideas, as he is more familiar with the internals of the ath5k driver.
The strange thing is that ath5k behaves better on poorer signal than madwifi. At 40% signal level it still keeps 18M rate while madwifi goes down to 1-2 M.
I agree it is likely a tx power issue. 2.6.31 got some work in this area, commit 7c9889f1 in wireless-testing e.g. is a likely candidate. Another thing to try is changing "AR5K_TUNE_DEFAULT_TXPOWER" which defaults to 12.5 dBm (25/2) -- madwifi seems to be using twice that power level above. The signal level reported by the driver is unlikely to be directly comparable to madwifi (i.e. I bet ath5k lies somewhat).
Actually, in the ath5k.h we have: #define AR5K_TUNE_MAX_TXPOWER 60 #define AR5K_TUNE_DEFAULT_TXPOWER 30 kernel: 2.6.29.3-60.fc10.i686
This bug appears to have been reported against 'rawhide' during the Fedora 11 development cycle. Changing version to '11'. More information and reason for this action is here: http://fedoraproject.org/wiki/BugZappers/HouseKeeping
This message is a reminder that Fedora 11 is nearing its end of life. Approximately 30 (thirty) days from now Fedora will stop maintaining and issuing updates for Fedora 11. It is Fedora's policy to close all bug reports from releases that are no longer maintained. At that time this bug will be closed as WONTFIX if it remains open with a Fedora 'version' of '11'. Package Maintainer: If you wish for this bug to remain open because you plan to fix it in a currently maintained version, simply change the 'version' to a later Fedora version prior to Fedora 11's end of life. Bug Reporter: Thank you for reporting this issue and we are sorry that we may not be able to fix it before Fedora 11 is end of life. If you would still like to see this bug fixed and are able to reproduce it against a later version of Fedora please change the 'version' of this bug to the applicable version. If you are unable to change the version, please add a comment here and someone will do it for you. Although we aim to fix as many bugs as possible during every release's lifetime, sometimes those efforts are overtaken by events. Often a more recent Fedora release includes newer upstream software that fixes bugs or makes them obsolete. The process we are following is described here: http://fedoraproject.org/wiki/BugZappers/HouseKeeping
Fedora 11 changed to end-of-life (EOL) status on 2010-06-25. Fedora 11 is no longer maintained, which means that it will not receive any further security or bug fix updates. As a result we are closing this bug. If you can reproduce this bug against a currently maintained version of Fedora please feel free to reopen this bug against that version. Thank you for reporting this bug and we are sorry it could not be fixed.