[rt2x00-users] [PATCH] rt2x00: provide mac80211 a suitable max_rates value

[Ivo Van Doorn]

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.

Ivo