[rt2x00-users] [PATCH] rt2x00: provide mac80211 a suitable max_rates value
Ivo Van Doorn
ivdoorn at gmail.com
Mon Jun 7 10:34:16 UTC 2010
On Mon, Jun 7, 2010 at 12:30 PM, Helmut Schaa
<helmut.schaa at googlemail.com> wrote:
> Am Montag 07 Juni 2010 schrieb Ivo Van Doorn:
>> On Fri, Jun 4, 2010 at 2:51 PM, Helmut Schaa
>> <helmut.schaa at googlemail.com> wrote:
>> > Am Freitag 04 Juni 2010 schrieb Helmut Schaa:
>> >> Set up max_rates and max_rate_tries with suitable values even if we do not
>> >> support the whole functionality.
>> >> As rt2800 has a global fallback table we cannot specify more then one tx rate
>> >> per frame but since the hw will try several different rates (based on the
>> >> fallback table) we should still initialize max_rates to the maximum number of
>> >> rates we are going to try. Otherwise mac80211 will truncate our reported tx
>> >> rates and the rc algortihm will end up with incorrect data choosing unsuitable
>> >> rates for tx.
>> >> This improves throughput on rt2800 devices considerable.
>> > Btw. this might be also applicable to other rt2x00 devices. Not sure though.
>> Is there actually a place where the fallback rates can be configured in rt2800?
> Yes, they can be configured, even more flexible then rt61pci and rt73usb ;)
> Search for HT_FBK_CFG and LG_FBK_CFG.
> Default is MCS15->MVS14->...->MCS8 for HT 2 stream
> and MCS7->MCS6->...->MCS0 for HT 1 stream
> and 54Mbps->48Mbps->...6Mbps for 11g
> and 11Mbps->5.5MBps->...->1Mbps for 11b
Ah nice. I couldn't fine them due to the weird abbrevations in the
register field names. :S
>> I just checked the other drivers, and in rt61pci/rt73usb fallback can
>> be configured
>> nicely including the number of rates to downgrade after each retry.
> Is that used already, or disabled?
No idea, my plan is to explicitely enable them, that way we can at least be sure
that it is indeed enabled.
More information about the users