Add NAPI support for rx and tx completion. NAPI poll is scheduled
from interrupt handler. The design is as below
- on interrupt
- schedule napi and mask interrupts
- on poll
- process all pipes (no actual Tx/Rx)
- process Rx within budget
- if quota exceeds budget reschedule napi p
Rajkumar Manoharan wrote:
> Add NAPI support for rx and tx completion. NAPI poll is scheduled
> from interrupt handler. The design is as below
>
> - on interrupt
> - schedule napi and mask interrupts
> - on poll
>- process all pipes (no actual Tx/Rx)
>- process Rx within budget
>
forget about it. it was caused by another patch here on this list.
Am 28.06.2016 um 00:45 schrieb Sebastian Gottschall:
broken patch
CC [M]
/home/seg/DEV/pb42/src/router/private/compat-wireless-2016-05-12/drivers/net/wireless/ath/ath10k/htt_tx.o
/home/seg/DEV/pb42/src/router/private/compat-w
broken patch
CC [M]
/home/seg/DEV/pb42/src/router/private/compat-wireless-2016-05-12/drivers/net/wireless/ath/ath10k/htt_tx.o
/home/seg/DEV/pb42/src/router/private/compat-wireless-2016-05-12/drivers/net/wireless/ath/ath10k/htt_tx.c:
In function 'ath10k_htt_tx_free':
/home/seg/DEV/pb42/src/rou
Add NAPI support for rx and tx completion. NAPI poll is scheduled
from interrupt handler. The design is as below
- on interrupt
- schedule napi and mask interrupts
- on poll
- process all pipes (no actual Tx/Rx)
- process Rx within budget
- if quota exceeds budget reschedule napi p
Add NAPI support for rx and tx completion. NAPI poll is scheduled
from interrupt handler. The design is as below
- on interrupt
- schedule napi and mask interrupts
- on poll
- process all pipes (no actual Tx/Rx)
- process Rx within budget
- if quota exceeds budget reschedule napi p
t; === =
> TCP DL 644 Mbps (42%)645 Mbps (36%)
> TCP UL 673 Mbps (30%)675 Mbps (26%)
> UDP DL 682 Mbps (49%)680 Mbps (49%)
> UDP UL 720 Mbps (28%)717 Mbps (11%)
>
> Signed-off-by: Rajkumar Manoharan
T
I'm always rather big on people testing latency under load, and napi
tends to add some.
On Fri, 2016-08-26 at 03:48 -0700, Dave Taht wrote:
> I'm always rather big on people testing latency under load, and napi
> tends to add some.
That's a completely useless comment.
Obviously, everybody uses NAPI; it's necessary for system load and thus
performance, and lets drivers take advantage
On Fri, Aug 26, 2016 at 4:12 AM, Johannes Berg
wrote:
> On Fri, 2016-08-26 at 03:48 -0700, Dave Taht wrote:
>> I'm always rather big on people testing latency under load, and napi
>> tends to add some.
>
> That's a completely useless comment.
>
> Obviously, everybody uses NAPI; it's necessary for
On 2016-08-26 17:19, Dave Taht wrote:
On Fri, Aug 26, 2016 at 4:12 AM, Johannes Berg
wrote:
On Fri, 2016-08-26 at 03:48 -0700, Dave Taht wrote:
I'm always rather big on people testing latency under load, and napi
tends to add some.
That's a completely useless comment.
Obviously, everybody u
11 matches
Mail list logo