From: Andrei Otcheretianski <[email protected]>
Deliver up to 128 frames during SP instead of 8 if unlimited max SP
is specified during association.
Signed-off-by: Andrei Otcheretianski <[email protected]>
Signed-off-by: Emmanuel Grumbach <[email protected]>
---
net/mac80211/sta_info.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index de494df..3352741 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1531,7 +1531,7 @@ void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta)
break;
case 0:
/* XXX: what is a good value? */
- n_frames = 8;
+ n_frames = 128;
break;
}
--
1.9.1
On Tue, Nov 4, 2014 at 2:53 PM, Otcheretianski, Andrei
<[email protected]> wrote:
> The spec doesn't require unlimited to be really "unlimited" and the AP decides when to end the SP, so any value here is ok.
> However for large traffic bursts increasing this value looks reasonable. Also looks like some certification tests expect more frames to be delivered during SP.
> 128 is still kind of arbitrary value
>
>> -----Original Message-----
>> From: Krishna Chaitanya [mailto:[email protected]]
>> Sent: Tuesday, November 04, 2014 11:03
>> To: Grumbach, Emmanuel
>> Cc: Johannes Berg; linux-wireless; Otcheretianski, Andrei
>> Subject: Re: [PATCH] mac80211: Increase uapsd max SP frames number
>>
>> On Tue, Nov 4, 2014 at 2:10 PM, Emmanuel Grumbach
>> <[email protected]> wrote:
>> > From: Andrei Otcheretianski <[email protected]>
>> >
>> > Deliver up to 128 frames during SP instead of 8 if unlimited max SP is
>> > specified during association.
>> >
>> > Signed-off-by: Andrei Otcheretianski <[email protected]>
>> > Signed-off-by: Emmanuel Grumbach <[email protected]>
>> > ---
>> > net/mac80211/sta_info.c | 2 +-
>> > 1 file changed, 1 insertion(+), 1 deletion(-)
>> >
>> > diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index
>> > de494df..3352741 100644
>> > --- a/net/mac80211/sta_info.c
>> > +++ b/net/mac80211/sta_info.c
>> > @@ -1531,7 +1531,7 @@ void ieee80211_sta_ps_deliver_uapsd(struct
>> sta_info *sta)
>> > break;
>> > case 0:
>> > /* XXX: what is a good value? */
>> > - n_frames = 8;
>> > + n_frames = 128;
>> > break;
>> > }
>> What is criteria for deciding the threshold?
>> Any specific use case for 128?
I understand, thanks for the explanation.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On Tue, Nov 4, 2014 at 2:10 PM, Emmanuel Grumbach
<[email protected]> wrote:
> From: Andrei Otcheretianski <[email protected]>
>
> Deliver up to 128 frames during SP instead of 8 if unlimited max SP
> is specified during association.
>
> Signed-off-by: Andrei Otcheretianski <[email protected]>
> Signed-off-by: Emmanuel Grumbach <[email protected]>
> ---
> net/mac80211/sta_info.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
> index de494df..3352741 100644
> --- a/net/mac80211/sta_info.c
> +++ b/net/mac80211/sta_info.c
> @@ -1531,7 +1531,7 @@ void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta)
> break;
> case 0:
> /* XXX: what is a good value? */
> - n_frames = 8;
> + n_frames = 128;
> break;
> }
What is criteria for deciding the threshold?
Any specific use case for 128?
On Tue, Nov 4, 2014 at 2:57 PM, Krishna Chaitanya
<[email protected]> wrote:
> On Tue, Nov 4, 2014 at 2:53 PM, Otcheretianski, Andrei
> <[email protected]> wrote:
>> The spec doesn't require unlimited to be really "unlimited" and the AP decides when to end the SP, so any value here is ok.
>> However for large traffic bursts increasing this value looks reasonable. Also looks like some certification tests expect more frames to be delivered during SP.
>> 128 is still kind of arbitrary value
>>
>>> -----Original Message-----
>>> From: Krishna Chaitanya [mailto:[email protected]]
>>> Sent: Tuesday, November 04, 2014 11:03
>>> To: Grumbach, Emmanuel
>>> Cc: Johannes Berg; linux-wireless; Otcheretianski, Andrei
>>> Subject: Re: [PATCH] mac80211: Increase uapsd max SP frames number
>>>
>>> On Tue, Nov 4, 2014 at 2:10 PM, Emmanuel Grumbach
>>> <[email protected]> wrote:
>>> > From: Andrei Otcheretianski <[email protected]>
>>> >
>>> > Deliver up to 128 frames during SP instead of 8 if unlimited max SP is
>>> > specified during association.
>>> >
>>> > Signed-off-by: Andrei Otcheretianski <[email protected]>
>>> > Signed-off-by: Emmanuel Grumbach <[email protected]>
>>> > ---
>>> > net/mac80211/sta_info.c | 2 +-
>>> > 1 file changed, 1 insertion(+), 1 deletion(-)
>>> >
>>> > diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index
>>> > de494df..3352741 100644
>>> > --- a/net/mac80211/sta_info.c
>>> > +++ b/net/mac80211/sta_info.c
>>> > @@ -1531,7 +1531,7 @@ void ieee80211_sta_ps_deliver_uapsd(struct
>>> sta_info *sta)
>>> > break;
>>> > case 0:
>>> > /* XXX: what is a good value? */
>>> > - n_frames = 8;
>>> > + n_frames = 128;
>>> > break;
>>> > }
>>> What is criteria for deciding the threshold?
>>> Any specific use case for 128?
> I understand, thanks for the explanation.
can we add the reason (certification) to the commit log?
It will be easy to understand the change.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