Re: rt61pci - bad performance
From: Andreas
Date: Sat Aug 14 2010 - 04:32:13 EST
Andrew Morton wrote:
(cc's added)
On Sun, 08 Aug 2010 11:49:49 +0200
Andreas<andihartmann@xxxxxxxxxxxxxxx> wrote:
Hello!
I've got the following hardware
01:05.0 Network controller: RaLink RT2561/RT61 rev B 802.11g
Subsystem: Micro-Star International Co., Ltd. Device b833
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV+ VGASnoop-
ParErr- Stepping- SERR- FastB2B- DisINTx-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=slow>TAbort-
<TAbort-<MAbort->SERR-<PERR- INTx-
Latency: 128, Cache Line Size: 64 bytes
Interrupt: pin A routed to IRQ 21
Region 0: Memory at cc000000 (32-bit, non-prefetchable) [size=32K]
Capabilities: [40] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA
PME(D0-,D1-,D2-,D3hot-,D3cold-)
Status: D0 NoSoftRst- PME-Enable- DSel=0 DScale=0 PME-
Kernel driver in use: ndiswrapper
running on a 32bit notebook with kernel 2.6.34-12-desktop (OpenSuSE
11.3). There is no difference between the compat-wireless-modules
2010-07-20 and the original modules shipped with the openSuSE 11.3 kernel.
If the rt61-chip is connected to a AP using rt61pci, the best
throughput, which can be achieved (at the same place), is about 1,7
MBytes/s.
kernel: [ 656.112190] cfg80211: Calling CRDA to update world regulatory
domain
kernel: [ 656.112267] cfg80211: Calling CRDA for country: DE
kernel: [ 656.169518] cfg80211: Regulatory domain changed to country: DE
kernel: [ 656.169524] (start_freq - end_freq @ bandwidth),
(max_antenna_gain, max_eirp)
kernel: [ 656.169528] (2400000 KHz - 2483500 KHz @ 40000 KHz),
(N/A, 2000 mBm)
kernel: [ 656.169532] (5150000 KHz - 5350000 KHz @ 40000 KHz),
(N/A, 2000 mBm)
kernel: [ 656.169535] (5470000 KHz - 5725000 KHz @ 40000 KHz),
(N/A, 2698 mBm)
kernel: [ 656.206228] rt61pci 0000:01:05.0: PCI INT A -> GSI 21 (level,
low) -> IRQ 21
kernel: [ 656.219941] phy0: Selected rate control algorithm 'minstrel'
kernel: [ 656.222216] Registered led device: rt61pci-phy0::radio
kernel: [ 656.222658] Registered led device: rt61pci-phy0::assoc
kernel: notebook1 ifup: wlan0 device: RaLink RT2561/RT61 rev B
802.11g
wlan0 IEEE 802.11bg ESSID:"--------"
Mode:Managed Frequency:2.412 GHz Access Point: some AP
Bit Rate=1 Mb/s Tx-Power=5 dBm
Retry long limit:7 RTS thr:off Fragment thr:off
Encryption key:off
Power Management:off
Link Quality=38/70 Signal level=-72 dBm
Rx invalid nwid:0 Rx invalid crypt:0 Rx invalid frag:0
Tx excessive retries:0 Invalid misc:0 Missed beacon:0
The throughput is measured with ping -f -s 7000 and xosview -n.
If I'm using ndiswrapper with the windows driver, first of all, I can
see additional information in iwconfig:
wlan0 IEEE 802.11g ESSID:"--------"
Mode:Managed Frequency:2.412 GHz Access Point: some AP
Bit Rate=54 Mb/s Tx-Power:20 dBm Sensitivity=-121 dBm
RTS thr=2347 B Fragment thr=2346 B
Encryption key:some key Security mode:restricted
Power Management:off
Link Quality:62/100 Signal level:-56 dBm Noise level:-96 dBm
Rx invalid nwid:0 Rx invalid crypt:0 Rx invalid frag:0
Tx excessive retries:0 Invalid misc:0 Missed beacon:0
There is a switch for sensitivity (which is not supported with rt61pci)
and the link quality compared with ndiswrapper is worse (38% to 62%).
The following is remarkably too:
ndiswrapper uses a Tx-Power of 20 dBm, rt61pci only 5 dBm. I don't know,
why rt61pci uses 5 dBm. It's a hard limit and I can't set it on a value
higher than 5 unless the driver is patched. Nevertheless, setting a
higher value (of 20 dBm) by patch does not mean to get a better performance.
That's wrong. I detected, that there is a great difference, because if
you start the unpatched driver directly after the boot, the link isn't
useable at all.
I can't see any difference if the patched driver is loaded once and
removed and the unpatched is loaded afterwards without rebooting between.
The patch is:
--- rt61pci.c.orig 2010-07-20 21:03:02.000000000 +0200
+++ rt61pci.c 2010-08-14 10:27:52.708008193 +0200
@@ -2661,13 +2661,17 @@
spec->channels_info = info;
tx_power = rt2x00_eeprom_addr(rt2x00dev, EEPROM_TXPOWER_G_START);
- for (i = 0; i < 14; i++)
- info[i].tx_power1 = TXPOWER_FROM_DEV(tx_power[i]);
+ for (i = 0; i < 14; i++) {
+ // info[i].tx_power1 = TXPOWER_FROM_DEV(tx_power[i]);
+ info[i].tx_power1 = 25;
+ }
if (spec->num_channels > 14) {
tx_power = rt2x00_eeprom_addr(rt2x00dev,
EEPROM_TXPOWER_A_START);
- for (i = 14; i < spec->num_channels; i++)
- info[i].tx_power1 = TXPOWER_FROM_DEV(tx_power[i]);
+ for (i = 14; i < spec->num_channels; i++) {
+ // info[i].tx_power1 =
TXPOWER_FROM_DEV(tx_power[i]);
+ info[i].tx_power1 = 25;
+ }
}
return 0;
Kind regards,
Andreas
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/