Message-ID: <4F8B0A4C.3080704@openwrt.org> (sfid-20120415_195030_894779_289E81A1)
Date: Sun, 15 Apr 2012 19:50:04 +0200
From: Gabor Juhos <juhosg@openwrt.org>
MIME-Version: 1.0
To: Felix Fietkau <nbd@openwrt.org>
CC: "John W. Linville" <linville@tuxdriver.com>,
	linux-wireless@vger.kernel.org,
	"ath9k-devel@lists.ath9k.org" <ath9k-devel@venema.h4ckr.net>
Subject: Re: [PATCH 1/3] ath9k: use consistent value for REDUCE_SCALED_POWER_BY_THREE_CHAIN
References: <1334433719-1144-1-git-send-email-juhosg@openwrt.org> <4F8AA38E.1040702@openwrt.org> <4F8B03A3.6030804@openwrt.org> <4F8B04D7.4080605@openwrt.org>
In-Reply-To: <4F8B04D7.4080605@openwrt.org>
Content-Type: text/plain; charset=ISO-8859-1
Sender: linux-wireless-owner@vger.kernel.org

2012.04.15. 19:26 keltez?ssel, Felix Fietkau ?rta:
> On 2012-04-15 7:21 PM, Gabor Juhos wrote:
>> Hi Felix,
>>
>> Thank you for the comments.
>>
>>> On 2012-04-14 10:01 PM, Gabor Juhos wrote:
>>>> The REDUCE_SCALED_POWER_BY_THREE_CHAIN symbol is
>>>> defined in different eeprom files, and the value
>>>> varies between the different files.
>>>>
>>>> In eeprom_def.c and in ar9003_eeprom.c the value
>>>> of the symbol is 9, however the comments in these
>>>> files indicates the value should be 10*log10(3)*2
>>>> which is 9.54242509439325. Replace the the value
>>>> to 10 in these files.
>>>>
>>>> Also add comments to eeprom_9287.c.
>>>>
>>>> Signed-off-by: Gabor Juhos <juhosg@openwrt.org>
>>> I think we should keep the value 9.
>>> If I understand the logic behind the power increase through chain
>>> combining properly, this value only describes the worst-case (wrt.
>>> regulatory compliance) upper limit of tx power, whereas in practice the
>>> measured combined power output will be much lower than that due to
>>> signal/phase differences.
>>> Regulatory compliance is already properly tested on all devices with the
>>> truncated value 9, so I don't think that we need to be even more
>>> conservative and round up here.
>>
>> Ok, I will rework the patch.
>>
>> Apart from the inconsistency between the REDUCE_SCALED_POWER_BY_THREE_CHAIN
>> values, there is another thing which confuses me.
>>
>> In the 'ath9k_hw_set_*_power_cal_table' functions the driver uses the
>> REDUCE_SCALED_POWER_BY_THREE_CHAIN constant to reduce the power values.
>> In the 'ath9k_hw_update_regulatory_maxpower' function it uses the
>> INCREASE_MAXPOW_BY_THREE_CHAIN constant to compensate the reduction. However the
>> two constants are different. I might be wrong, but in my opinion the driver
>> should use the same constant in both functions.
> I just checked with Atheros sources, and it seems I was wrong about
> sticking with the value 9.
> It appears that Atheros changed it to 10 at some point, and ath9k
> contains a mix of the old and the new version. Consistently using the
> value 10 for 3 chains for both increase and reduction seems to be the
> right thing to do.

Thank you for the information. I will add it to the commit message.

-Gabor