* Throughput is very low
@ 2014-07-09 14:22 Mamun Abu-Tair
2014-07-16 16:01 ` Bart Jooris
0 siblings, 1 reply; 30+ messages in thread
From: Mamun Abu-Tair @ 2014-07-09 14:22 UTC (permalink / raw)
To: ath10k
Dear all,
I am trying to do throughput test with copmex AC cards Model (WLE900VX 7AA) .,using hostapd running on the server and one client.
I used Kalle sitting for the hostapd. However, the maximum throughput i can get is around 70Mbit/s which is far away from the throughput achieved by many users (UDP traffic).
I have notice that Bit Rate keeps fixed 6 Mb/s . and it dose not responding to any commands to change it.
The machines used:
Ubuntu 12.04, Kerenl 3.16 , updated regulatory to cover 80Mhz channels , and the latest firmware
Your help is appreciated .
Kind regards
Mamun
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: Throughput is very low
2014-07-09 14:22 Throughput is very low Mamun Abu-Tair
@ 2014-07-16 16:01 ` Bart Jooris
2014-07-17 5:21 ` Michal Kazior
0 siblings, 1 reply; 30+ messages in thread
From: Bart Jooris @ 2014-07-16 16:01 UTC (permalink / raw)
To: Mamun Abu-Tair, ath10k
Dear Mamum,
On 07/09/2014 04:22 PM, Mamun Abu-Tair wrote:
> Dear all,
> I am trying to do throughput test with copmex AC cards Model (WLE900VX 7AA) .,using hostapd running on the server and one client.
I have some cards with the same label. Hostapd on the server, on the
station we use wpa_supplicant.
>
> I used Kalle sitting for the hostapd. However, the maximum throughput i can get is around 70Mbit/s which is far away from the throughput achieved by many users (UDP traffic).
In a setup with those cards we can observe a UDP throughput of approx.
640Mbps.
>
> I have notice that Bit Rate keeps fixed 6 Mb/s . and it dose not responding to any commands to change it.
While running iperf client on the station I can also retrieve the Tx
bitrate of 6Mbps with both iwconfig and 'iw wlanX station dump'. Version
of iw has some impact on the output too, I have version 3.15. I don't
know a tool which shows the right info on the transmitting node...
But a third node which is configured as a sniffer shows Tx bitrate of
1299.99Mbps :-)
>
> The machines used:
> Ubuntu 12.04, Kerenl 3.16 , updated regulatory to cover 80Mhz channels , and the latest firmware
Our nodes are also running 12.04 but still with the default kernel
3.11.0-15-generic.
dmesg | grep qca98 shows
[ 4.594975] ath10k: qca988x hw2.0 (0x4100016c) fw 10.1.467.2-1 api 2
htt 2.1
Further, as Kalle suggested, we installed the ath10k driver from
backports-3.15.1-1.
Best regards,
Bart
--
Bart Jooris
Department of Information Technology
Internet Based Communication Networks and Services (IBCN)
Ghent University - iMinds
Gaston Crommenlaan 8 (Bus 201), B-9050 Gent, Belgium
E-mail: bart.jooris@intec.UGent.be
M: +32 474 59 53 42
Tel. +32 9 33 14900
Fax +32 9 33 14899
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: Throughput is very low
2014-07-16 16:01 ` Bart Jooris
@ 2014-07-17 5:21 ` Michal Kazior
2014-07-17 10:40 ` Trouble shooting low rate MCS9 in 802.11ac Vu Hai NGUYEN
0 siblings, 1 reply; 30+ messages in thread
From: Michal Kazior @ 2014-07-17 5:21 UTC (permalink / raw)
To: Bart.Jooris; +Cc: Mamun Abu-Tair, ath10k@lists.infradead.org
On 16 July 2014 18:01, Bart Jooris <Bart.Jooris@intec.ugent.be> wrote:
> On 07/09/2014 04:22 PM, Mamun Abu-Tair wrote:
[...]
>> I have notice that Bit Rate keeps fixed 6 Mb/s . and it dose not
>> responding to any commands to change it.
>
> While running iperf client on the station I can also retrieve the Tx bitrate
> of 6Mbps with both iwconfig and 'iw wlanX station dump'. Version of iw has
> some impact on the output too, I have version 3.15. I don't know a tool
> which shows the right info on the transmitting node...
> But a third node which is configured as a sniffer shows Tx bitrate of
> 1299.99Mbps :-)
The 6mbps tx rate reporting is due to firmware limitation.
You might want to check
/sys/kernel/debug/ieee80211/phyX/ath10k/fw_stats (replace phyX with
according phy of your ath10k device) instead.
Michał
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Trouble shooting low rate MCS9 in 802.11ac
2014-07-17 5:21 ` Michal Kazior
@ 2014-07-17 10:40 ` Vu Hai NGUYEN
2014-07-17 10:53 ` Bartosz Markowski
2014-07-17 10:57 ` Michal Kazior
0 siblings, 2 replies; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-17 10:40 UTC (permalink / raw)
To: ath10k@lists.infradead.org; +Cc: Patrick CARNEIRO RODRIGUEZ
[-- Attachment #1: Type: text/plain, Size: 752 bytes --]
Hi all,
I'm using ath10k with official firmware (10.1, 467-2-1), my module of wifi is Compex WLE900VX.
In theory MCS9 should give better rate than MCS 7.
But when running test with Iperf, I notice that if I force rate (using command "iw") to MCS9 or MCS8,
the rate result from iperf are always lower than MCS 7 (even NSS1,2 or 3).
Though I check RX rate report from "iw station dump" and it matches with the rate that I want to force.
You can see in the attached file a report of my test.
Any one has done the test and get better rate in MCS9 than in MCS7 with this wifi module ???
PS: The rate increases normally from MCS1 to MCS6.
Thanks,
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
[-- Attachment #2: Selection_004.png --]
[-- Type: image/png, Size: 15261 bytes --]
[-- Attachment #3: Type: text/plain, Size: 146 bytes --]
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: Trouble shooting low rate MCS9 in 802.11ac
2014-07-17 10:40 ` Trouble shooting low rate MCS9 in 802.11ac Vu Hai NGUYEN
@ 2014-07-17 10:53 ` Bartosz Markowski
2014-07-17 12:22 ` RE : " Vu Hai NGUYEN
2014-07-17 10:57 ` Michal Kazior
1 sibling, 1 reply; 30+ messages in thread
From: Bartosz Markowski @ 2014-07-17 10:53 UTC (permalink / raw)
To: Vu Hai NGUYEN; +Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org
On 17 July 2014 12:40, Vu Hai NGUYEN <vh.nguyen@actiasodielec.fr> wrote:
> Hi all,
> I'm using ath10k with official firmware (10.1, 467-2-1), my module of wifi is Compex WLE900VX.
> In theory MCS9 should give better rate than MCS 7.
> But when running test with Iperf, I notice that if I force rate (using command "iw") to MCS9 or MCS8,
> the rate result from iperf are always lower than MCS 7 (even NSS1,2 or 3).
> Though I check RX rate report from "iw station dump" and it matches with the rate that I want to force.
> You can see in the attached file a report of my test.
> Any one has done the test and get better rate in MCS9 than in MCS7 with this wifi module ???
Did you use cables or measured OTA? What platform it is? Did you use
hostapd? Is it AP mode (bridge)?
(You did not provide basically any details on what exacly you've measured).
In open AP mode (bridge), CUS223 HW (not WLE900VX however) and on
AP135 platform (customized openwrt SW + bleeding edge of
ath10k/wireless subsystem souces - private backports tarball).. for
UDP (last time I measured) I have around 820Mpbs for UCP both ways and
720Mbps TCP.
-Bartosz
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-17 10:53 ` Bartosz Markowski
@ 2014-07-17 12:22 ` Vu Hai NGUYEN
2014-07-17 12:42 ` Bartosz Markowski
0 siblings, 1 reply; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-17 12:22 UTC (permalink / raw)
To: Bartosz Markowski; +Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org
>Did you use cables or measured OTA?
My system is like this:
PC1 - Device 1 (AP) <= Wifi => Device 2 (STA) - PC2
Each PC connects to the device by a Gigabit Ethernet cable.
>What platform it is?
My platform is a PC built with an ARMv7 1.2GHz.
> Did you use hostapd? Is it AP mode (bridge)?
I'm using hostapd for AP and wpa_supplicant for STA. AP is in mode bridge
but STA isn't (the official firmware crashed in bridge mode, I can set up bridged STA
using the firmware of Candelatech but the rate is slower a little bit when I do iperf test.
>(You did not provide basically any details on what exacly you've measured).
Sorry, please feel free to ask me more details.
I obtained that result table when I did iperf test in TCP, option -w256K and 10 streams (-P10)
If I did the test in UDP, with the same bandwidth (option -b), I lost more packets
in MCS 8 and 9 compared to MCS7, which also means that MCS7 has better performance.
>In open AP mode (bridge), CUS223 HW (not WLE900VX however) and on
>AP135 platform (customized openwrt SW + bleeding edge of
>ath10k/wireless subsystem souces - private backports tarball).. for
>UDP (last time I measured) I have around 820Mpbs for UCP both ways and
>720Mbps TCP.
This is in NSS3 -MCS9? Did you get better or worse rate if you clear the mask
(iw wlanX set bitrates) cause if I don't config rate, from AP to STA I have the best rate
(ie same as MCS7) but from STA to AP my rate is much lower than MCS7 (240 Mbps
vs 370 Mbps in TCP).
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-17 12:22 ` RE : " Vu Hai NGUYEN
@ 2014-07-17 12:42 ` Bartosz Markowski
2014-07-17 13:19 ` RE : " Vu Hai NGUYEN
2014-08-26 8:32 ` Vu Hai NGUYEN
0 siblings, 2 replies; 30+ messages in thread
From: Bartosz Markowski @ 2014-07-17 12:42 UTC (permalink / raw)
To: Vu Hai NGUYEN; +Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org
On 17 July 2014 14:22, Vu Hai NGUYEN <vh.nguyen@actiasodielec.fr> wrote:
>>Did you use cables or measured OTA?
>
> My system is like this:
> PC1 - Device 1 (AP) <= Wifi => Device 2 (STA) - PC2
> Each PC connects to the device by a Gigabit Ethernet cable.
I ment RF cables and attenuation to get around 30dBm signal lvl.
PC ---(eth)--- [AP135 - APUT]ath10k - - - (RF cable) - - -
[AP135]Station ---(eth)--- PC
>>What platform it is?
> My platform is a PC built with an ARMv7 1.2GHz.
>
>> Did you use hostapd? Is it AP mode (bridge)?
> I'm using hostapd for AP and wpa_supplicant for STA. AP is in mode bridge
> but STA isn't (the official firmware crashed in bridge mode, I can set up bridged STA
> using the firmware of Candelatech but the rate is slower a little bit when I do iperf test.
>
>>(You did not provide basically any details on what exacly you've measured).
> Sorry, please feel free to ask me more details.
> I obtained that result table when I did iperf test in TCP, option -w256K and 10 streams (-P10)
> If I did the test in UDP, with the same bandwidth (option -b), I lost more packets
> in MCS 8 and 9 compared to MCS7, which also means that MCS7 has better performance.
So probably the air condition you have forces the rate control to pick
MCS7 as the most suitable rates.
>>In open AP mode (bridge), CUS223 HW (not WLE900VX however) and on
>>AP135 platform (customized openwrt SW + bleeding edge of
>>ath10k/wireless subsystem souces - private backports tarball).. for
>>UDP (last time I measured) I have around 820Mpbs for UCP both ways and
>>720Mbps TCP.
>
> This is in NSS3 -MCS9? Did you get better or worse rate if you clear the mask
> (iw wlanX set bitrates) cause if I don't config rate, from AP to STA I have the best rate
> (ie same as MCS7) but from STA to AP my rate is much lower than MCS7 (240 Mbps
> vs 370 Mbps in TCP).
Yes, NSS-3; Over the RF-cables I'm easily able to get MCS9 rates
transmitions without any forced settings (the rate control is picking
the highest rates).
--
Bartosz
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-17 12:42 ` Bartosz Markowski
@ 2014-07-17 13:19 ` Vu Hai NGUYEN
2014-07-17 19:18 ` Adrian Chadd
2014-08-26 8:32 ` Vu Hai NGUYEN
1 sibling, 1 reply; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-17 13:19 UTC (permalink / raw)
To: Bartosz Markowski; +Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org
>So probably the air condition you have forces the rate control to pick
>MCS7 as the most suitable rates.
What could I do to improve this? (Change the air conditioner LOL?)
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-17 13:19 ` RE : " Vu Hai NGUYEN
@ 2014-07-17 19:18 ` Adrian Chadd
2014-07-21 12:10 ` Vu Hai NGUYEN
0 siblings, 1 reply; 30+ messages in thread
From: Adrian Chadd @ 2014-07-17 19:18 UTC (permalink / raw)
To: Vu Hai NGUYEN
Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org,
Bartosz Markowski
On 17 July 2014 06:19, Vu Hai NGUYEN <vh.nguyen@actiasodielec.fr> wrote:
>>So probably the air condition you have forces the rate control to pick
>>MCS7 as the most suitable rates.
>
> What could I do to improve this? (Change the air conditioner LOL?)
>
Heh, he meant the RF environment in the location you are. :)
And ugh - this is why we need an open source ART already.
-a
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-17 19:18 ` Adrian Chadd
@ 2014-07-21 12:10 ` Vu Hai NGUYEN
2014-07-25 12:22 ` Vu Hai NGUYEN
0 siblings, 1 reply; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-21 12:10 UTC (permalink / raw)
To: Adrian Chadd
Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org,
Bartosz Markowski
>>>So probably the air condition you have forces the rate control to pick
>>>MCS7 as the most suitable rates.
>> What could I do to improve this? (Change the air conditioner LOL?)
>Heh, he meant the RF environment in the location you are. :)
>And ugh - this is why we need an open source ART already.
Thanks, I captured log from Wireshark and saw in the frame of broadcast of my AP that VHT Supported MCS 0-9 with NSS1,2,3 (both TX and RX MCS map)
but VHT Operation basic MCS map only indicate MCS 0-7 with NSS1 (strange cause if NSS1 I can not go up to 410 Mbps).
I might move my devices to a closed room to do the test so that I can avoid other RF effects.
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-21 12:10 ` Vu Hai NGUYEN
@ 2014-07-25 12:22 ` Vu Hai NGUYEN
2014-07-25 12:51 ` Ben Greear
0 siblings, 1 reply; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-25 12:22 UTC (permalink / raw)
To: Vu Hai NGUYEN, Adrian Chadd
Cc: Patrick CARNEIRO RODRIGUEZ, Bartosz Markowski,
ath10k@lists.infradead.org
>>>So probably the air condition you have forces the rate control to pick
>>>MCS7 as the most suitable rates.
>> What could I do to improve this? (Change the air conditioner LOL?)
>Heh, he meant the RF environment in the location you are. :)
>And ugh - this is why we need an open source ART already.
My 2 devices have an ARM processor 1200MHz.
If I connect these two devices by an Ethernet cable and doing iperf (in TCP)
I can obtain 880 Mbps, it means that my processor can deal with that speed
of data transfer. But if I use Wi-fi instead of Ethernet to test rate between these
devices, my processor is exhausted, I run command top and see that 0~1%
idle only, ksoftirqd and kworker take most of my processor resource.
Last week I discovered by chance that the module loaded in kernel can create
effects to performance of rate, in my case it is "iptables". If I unload all module
that related to iptables I can improve the performance.
So I wonder if I can do some thing with the Wi-fi driver to improve rate?
Or the only solution is overclock/change my processor?
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-25 12:22 ` Vu Hai NGUYEN
@ 2014-07-25 12:51 ` Ben Greear
2014-07-28 7:32 ` Vu Hai NGUYEN
2014-07-28 11:53 ` RE : " Vu Hai NGUYEN
0 siblings, 2 replies; 30+ messages in thread
From: Ben Greear @ 2014-07-25 12:51 UTC (permalink / raw)
To: Vu Hai NGUYEN, Adrian Chadd
Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org,
Bartosz Markowski
On 07/25/2014 05:22 AM, Vu Hai NGUYEN wrote:
>>>> So probably the air condition you have forces the rate control to pick
>>>> MCS7 as the most suitable rates.
>
>>> What could I do to improve this? (Change the air conditioner LOL?)
>
>> Heh, he meant the RF environment in the location you are. :)
>> And ugh - this is why we need an open source ART already.
>
> My 2 devices have an ARM processor 1200MHz.
> If I connect these two devices by an Ethernet cable and doing iperf (in TCP)
> I can obtain 880 Mbps, it means that my processor can deal with that speed
> of data transfer. But if I use Wi-fi instead of Ethernet to test rate between these
> devices, my processor is exhausted, I run command top and see that 0~1%
> idle only, ksoftirqd and kworker take most of my processor resource.
>
> Last week I discovered by chance that the module loaded in kernel can create
> effects to performance of rate, in my case it is "iptables". If I unload all module
> that related to iptables I can improve the performance.
> So I wonder if I can do some thing with the Wi-fi driver to improve rate?
> Or the only solution is overclock/change my processor?
Can you run 'perf top' on your system when it is under load so we can
see where the CPU is being used the most?
Thanks,
Ben
>
> NGUYEN Vu Hai
> Acita-Sodielec
> Route de Mayres - B.P. 9
> 12100 St GEORGES DE LUZENCON
> FRANCE
>
>
>
>
> _______________________________________________
> ath10k mailing list
> ath10k@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/ath10k
>
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-25 12:51 ` Ben Greear
@ 2014-07-28 7:32 ` Vu Hai NGUYEN
2014-07-28 11:53 ` RE : " Vu Hai NGUYEN
1 sibling, 0 replies; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-28 7:32 UTC (permalink / raw)
To: Ben Greear, Adrian Chadd
Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org,
Bartosz Markowski
>> My 2 devices have an ARM processor 1200MHz.
>> If I connect these two devices by an Ethernet cable and doing iperf (in TCP)
>> I can obtain 880 Mbps, it means that my processor can deal with that speed
>> of data transfer. But if I use Wi-fi instead of Ethernet to test rate between these
>> devices, my processor is exhausted, I run command top and see that 0~1%
>> idle only, ksoftirqd and kworker take most of my processor resource.
>>
>> Last week I discovered by chance that the module loaded in kernel can create
>> effects to performance of rate, in my case it is "iptables". If I unload all module
>> that related to iptables I can improve the performance.
>> So I wonder if I can do some thing with the Wi-fi driver to improve rate?
>> Or the only solution is overclock/change my processor?
>Can you run 'perf top' on your system when it is under load so we can
>see where the CPU is being used the most?
It's complicated for me to install "perf" cause it depends on the package linux-tools (please
correct me if I'm wrong :D)and our linux kernel is provided from the processor's producer.
I don't see the option to build "perf" form the menuconfig of our linux. I've enabled these parameters
but still when I run perf from shell there is no program found.
CONFIG_HAVE_PERF_EVENTS=y
CONFIG_EVENT_TRACING=y
CONFIG_PERF_EVENTS=y
CONFIG_PERF_COUNTERS=y
I can only run "top" to see what process used most of out CPU, they are ksoftirqd and kworker.
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-25 12:51 ` Ben Greear
2014-07-28 7:32 ` Vu Hai NGUYEN
@ 2014-07-28 11:53 ` Vu Hai NGUYEN
2014-07-28 16:08 ` Ben Greear
1 sibling, 1 reply; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-28 11:53 UTC (permalink / raw)
To: Ben Greear, Adrian Chadd
Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org,
Bartosz Markowski
>> My 2 devices have an ARM processor 1200MHz.
>> If I connect these two devices by an Ethernet cable and doing iperf (in TCP)
>> I can obtain 880 Mbps, it means that my processor can deal with that speed
>> of data transfer. But if I use Wi-fi instead of Ethernet to test rate between these
>> devices, my processor is exhausted, I run command top and see that 0~1%
>> idle only, ksoftirqd and kworker take most of my processor resource.
>>
>> Last week I discovered by chance that the module loaded in kernel can create
>> effects to performance of rate, in my case it is "iptables". If I unload all module
>> that related to iptables I can improve the performance.
>> So I wonder if I can do some thing with the Wi-fi driver to improve rate?
>> Or the only solution is overclock/change my processor?
>Can you run 'perf top' on your system when it is under load so we can
>see where the CPU is being used the most?
I follow a tutorial to cross compile perf so here is my result
PerfTop: 70 irqs/sec kernel:98.6% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
-------------------------------------------------------------------------------
39.43% [kernel] [k] csum_partial_copy_nocheck
5.54% [kernel] [k] __kmalloc_track_caller
4.93% [kernel] [k] kfree
4.31% [mac80211] [k] ieee80211_tx_status
4.31% [kernel] [k] memcpy
3.49% [kernel] [k] __memzero
3.29% [kernel] [k] mv_eth_poll
3.29% [kernel] [k] __kfree_skb
2.05% [ath10k_pci] [k] ath10k_ce_send_nolock
1.44% [mac80211] [k] $a
1.44% [kernel] [k] dev_gro_receive
1.44% [kernel] [k] napi_gro_receive
1.44% [kernel] [k] eth_type_trans
1.44% [kernel] [k] inet_gro_receive
1.44% [kernel] [k] skb_copy_and_csum_bits
1.44% [kernel] [k] skb_segment
1.44% [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
1.44% [ath10k_core] [k] ath10k_txrx_tx_unref
1.23% [kernel] [k] local_bh_enable
1.23% [kernel] [k] kmem_cache_alloc
1.23% [kernel] [k] dev_hard_start_xmit
Thank you in advance for your response,
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
Thanks,
Ben
>
> NGUYEN Vu Hai
> Acita-Sodielec
> Route de Mayres - B.P. 9
> 12100 St GEORGES DE LUZENCON
> FRANCE
>
>
>
>
> _______________________________________________
> ath10k mailing list
> ath10k@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/ath10k
>
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-28 11:53 ` RE : " Vu Hai NGUYEN
@ 2014-07-28 16:08 ` Ben Greear
2014-07-29 8:02 ` Vu Hai NGUYEN
0 siblings, 1 reply; 30+ messages in thread
From: Ben Greear @ 2014-07-28 16:08 UTC (permalink / raw)
To: Vu Hai NGUYEN
Cc: Patrick CARNEIRO RODRIGUEZ, Adrian Chadd,
ath10k@lists.infradead.org, Bartosz Markowski
On 07/28/2014 04:53 AM, Vu Hai NGUYEN wrote:
>>> My 2 devices have an ARM processor 1200MHz.
>>> If I connect these two devices by an Ethernet cable and doing iperf (in TCP)
>>> I can obtain 880 Mbps, it means that my processor can deal with that speed
>>> of data transfer. But if I use Wi-fi instead of Ethernet to test rate between these
>>> devices, my processor is exhausted, I run command top and see that 0~1%
>>> idle only, ksoftirqd and kworker take most of my processor resource.
>>>
>>> Last week I discovered by chance that the module loaded in kernel can create
>>> effects to performance of rate, in my case it is "iptables". If I unload all module
>>> that related to iptables I can improve the performance.
>>> So I wonder if I can do some thing with the Wi-fi driver to improve rate?
>>> Or the only solution is overclock/change my processor?
>
>> Can you run 'perf top' on your system when it is under load so we can
>> see where the CPU is being used the most?
>
> I follow a tutorial to cross compile perf so here is my result
>
>
> PerfTop: 70 irqs/sec kernel:98.6% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
> -------------------------------------------------------------------------------
>
> 39.43% [kernel] [k] csum_partial_copy_nocheck
Looks like your ethernet driver is not doing checksum offloading?
I am pretty sure ath10k does support this unless you have managed
to disabled it somehow?
Thanks,
Ben
> 5.54% [kernel] [k] __kmalloc_track_caller
> 4.93% [kernel] [k] kfree
> 4.31% [mac80211] [k] ieee80211_tx_status
> 4.31% [kernel] [k] memcpy
> 3.49% [kernel] [k] __memzero
> 3.29% [kernel] [k] mv_eth_poll
> 3.29% [kernel] [k] __kfree_skb
> 2.05% [ath10k_pci] [k] ath10k_ce_send_nolock
> 1.44% [mac80211] [k] $a
> 1.44% [kernel] [k] dev_gro_receive
> 1.44% [kernel] [k] napi_gro_receive
> 1.44% [kernel] [k] eth_type_trans
> 1.44% [kernel] [k] inet_gro_receive
> 1.44% [kernel] [k] skb_copy_and_csum_bits
> 1.44% [kernel] [k] skb_segment
> 1.44% [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
> 1.44% [ath10k_core] [k] ath10k_txrx_tx_unref
> 1.23% [kernel] [k] local_bh_enable
> 1.23% [kernel] [k] kmem_cache_alloc
> 1.23% [kernel] [k] dev_hard_start_xmit
>
>
> Thank you in advance for your response,
>
> NGUYEN Vu Hai
> Acita-Sodielec
> Route de Mayres - B.P. 9
> 12100 St GEORGES DE LUZENCON
> FRANCE
>
>
>
> Thanks,
> Ben
>
>>
>> NGUYEN Vu Hai
>> Acita-Sodielec
>> Route de Mayres - B.P. 9
>> 12100 St GEORGES DE LUZENCON
>> FRANCE
>>
>>
>>
>>
>> _______________________________________________
>> ath10k mailing list
>> ath10k@lists.infradead.org
>> http://lists.infradead.org/mailman/listinfo/ath10k
>>
>
> --
> Ben Greear <greearb@candelatech.com>
> Candela Technologies Inc http://www.candelatech.com
>
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-28 16:08 ` Ben Greear
@ 2014-07-29 8:02 ` Vu Hai NGUYEN
2014-07-29 15:04 ` RE : " Vu Hai NGUYEN
0 siblings, 1 reply; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-29 8:02 UTC (permalink / raw)
To: Ben Greear
Cc: Patrick CARNEIRO RODRIGUEZ, Adrian Chadd, Bartosz Markowski,
ath10k@lists.infradead.org
>> I follow a tutorial to cross compile perf so here is my result
>>
>>
>> PerfTop: 70 irqs/sec kernel:98.6% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
>> -------------------------------------------------------------------------------
>>
>> 39.43% [kernel] [k] csum_partial_copy_nocheck
>Looks like your ethernet driver is not doing checksum offloading?
>I am pretty sure ath10k does support this unless you have managed
>to disabled it somehow?
I'm using ath10k from master branch (generated by backport), My only hack is changing the default country of regulatory domain from US to France.
The checksum patch is implemented by Michal Kazior since july 2013 and I also check that there is function checksum state in htt_rx.c file so it should be in my
driver module.
But I install ethtool and here is the ouput of my interface wlan0:
#ethtool --show-offload wlan0
Features for wlan0:
rx-checksumming: off [fixed]
tx-checksumming: on
tx-checksum-ipv4: off [fixed]
tx-checksum-unneeded: off [fixed]
tx-checksum-ip-generic: on [fixed]
tx-checksum-ipv6: off [fixed]
tx-checksum-fcoe-crc: off [fixed]
tx-checksum-sctp: off [fixed]
scatter-gather: off
tx-scatter-gather: off [fixed]
tx-scatter-gather-fraglist: off [fixed]
tcp-segmentation-offload: off
tx-tcp-segmentation: off [fixed]
tx-tcp-ecn-segmentation: off [fixed]
tx-tcp6-segmentation: off [fixed]
udp-fragmentation-offload: off [fixed]
generic-segmentation-offload: off [requested on]
generic-receive-offload: on
large-receive-offload: off [fixed]
rx-vlan-offload: off [fixed]
tx-vlan-offload: off [fixed]
ntuple-filters: off [fixed]
receive-hashing: off [fixed]
highdma: off [fixed]
rx-vlan-filter: off [fixed]
vlan-challenged: off [fixed]
tx-lockless: off [fixed]
netns-local: on [fixed]
tx-gso-robust: off [fixed]
tx-fcoe-segmentation: off [fixed]
fcoe-mtu: off [fixed]
tx-nocache-copy: on
loopback: off [fixed]
And I cannot enable these function, as it show [fixed] like above.
# ethtool --offload wlan0 rx on tx on
Cannot change rx-checksumming
Cannot change tx-checksumming
>> 5.54% [kernel] [k] __kmalloc_track_caller
>> 4.93% [kernel] [k] kfree
>> 4.31% [mac80211] [k] ieee80211_tx_status
>> 4.31% [kernel] [k] memcpy
>> 3.49% [kernel] [k] __memzero
>> 3.29% [kernel] [k] mv_eth_poll
>> 3.29% [kernel] [k] __kfree_skb
>> 2.05% [ath10k_pci] [k] ath10k_ce_send_nolock
>> 1.44% [mac80211] [k] $a
>> 1.44% [kernel] [k] dev_gro_receive
>> 1.44% [kernel] [k] napi_gro_receive
>> 1.44% [kernel] [k] eth_type_trans
>> 1.44% [kernel] [k] inet_gro_receive
>> 1.44% [kernel] [k] skb_copy_and_csum_bits
>> 1.44% [kernel] [k] skb_segment
>> 1.44% [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
>> 1.44% [ath10k_core] [k] ath10k_txrx_tx_unref
>> 1.23% [kernel] [k] local_bh_enable
>> 1.23% [kernel] [k] kmem_cache_alloc
>> 1.23% [kernel] [k] dev_hard_start_xmit
>>
>>
>> Thank you in advance for your response,
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-29 8:02 ` Vu Hai NGUYEN
@ 2014-07-29 15:04 ` Vu Hai NGUYEN
2014-07-29 15:55 ` Ben Greear
2014-07-30 6:26 ` Michal Kazior
0 siblings, 2 replies; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-29 15:04 UTC (permalink / raw)
To: Vu Hai NGUYEN, Ben Greear
Cc: Patrick CARNEIRO RODRIGUEZ, Adrian Chadd,
ath10k@lists.infradead.org, Bartosz Markowski
>>> I follow a tutorial to cross compile perf so here is my result
>>>
>>>
>>> PerfTop: 70 irqs/sec kernel:98.6% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
>>> -------------------------------------------------------------------------------
>>>
>>> 39.43% [kernel] [k] csum_partial_copy_nocheck
>>Looks like your ethernet driver is not doing checksum offloading?
>>I am pretty sure ath10k does support this unless you have managed
>>to disabled it somehow?
>I'm using ath10k from master branch (generated by backport), My only hack is changing the default country of regulatory domain from US to France.
>The checksum patch is implemented by Michal Kazior since july 2013 and I also check that there is function checksum state in htt_rx.c file so it should be in my
>driver module.
>But I install ethtool and here is the ouput of my interface wlan0:
>#ethtool --show-offload wlan0
>Features for wlan0:
>rx-checksumming: off [fixed]
>tx-checksumming: on
> tx-checksum-ipv4: off [fixed]
> tx-checksum-unneeded: off [fixed]
> tx-checksum-ip-generic: on [fixed]
> tx-checksum-ipv6: off [fixed]
> tx-checksum-fcoe-crc: off [fixed]
> tx-checksum-sctp: off [fixed]
>scatter-gather: off
> tx-scatter-gather: off [fixed]
> tx-scatter-gather-fraglist: off [fixed]
>tcp-segmentation-offload: off
> tx-tcp-segmentation: off [fixed]
> tx-tcp-ecn-segmentation: off [fixed]
> tx-tcp6-segmentation: off [fixed]
>udp-fragmentation-offload: off [fixed]
>generic-segmentation-offload: off [requested on]
>generic-receive-offload: on
>large-receive-offload: off [fixed]
>rx-vlan-offload: off [fixed]
>tx-vlan-offload: off [fixed]
>ntuple-filters: off [fixed]
>receive-hashing: off [fixed]
>highdma: off [fixed]
>rx-vlan-filter: off [fixed]
>vlan-challenged: off [fixed]
>tx-lockless: off [fixed]
>netns-local: on [fixed]
>tx-gso-robust: off [fixed]
>tx-fcoe-segmentation: off [fixed]
>fcoe-mtu: off [fixed]
>tx-nocache-copy: on
>loopback: off [fixed]
>
>And I cannot enable these function, as it show [fixed] like above.
># ethtool --offload wlan0 rx on tx on
>Cannot change rx-checksumming
>Cannot change tx-checksumming
I used ethtool to disable Checksum offloading on my Ethernet interface and increase rate from
400 Mbps to 500 Mbps, now the thread "csum_partial_copy_nocheck" has disappeared and there
is no more particular thread which takes most of the processor resource. But my processor is
always exhausted.
I notice some warning when starting perf top
[ath10k_core] with build id f31b98301ddea35e320bacaef048e4adbae00a6d not found, continuing without symbols
[ath10k_pci] with build id a1303b5587ceef676d03d5a68fa5c7d717861c5d not found, continuing without symbols
[mac80211] with build id f73251a940dedf51ac599141e5edefe05da2cb6f not found, continuing without symbols
[cfg80211] with build id 94dd0809b98902252ce78cc3bc4ae385dd5e8fdf not found, continuing without symbols
This may cause some unknown thread like the 2nd thread $a below of [mac80211]?
PerfTop: 51 irqs/sec kernel:98.0% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
-------------------------------------------------------------------------------
8.79% [mac80211] [k] ieee80211_tx_status
5.02% [mac80211] [k] $a
5.02% [kernel] [k] __memzero
4.60% [kernel] [k] memcpy
4.60% [kernel] [k] mv_eth_poll
4.18% [kernel] [k] dev_queue_xmit
4.18% [kernel] [k] br_parse_ip_options
3.77% [kernel] [k] dev_hard_start_xmit
3.77% [kernel] [k] nf_hook_slow
3.35% [kernel] [k] local_bh_enable
3.35% [kernel] [k] nf_iterate
3.35% [kernel] [k] br_nf_forward_ip
2.93% [kernel] [k] kfree
2.93% [kernel] [k] br_nf_pre_routing
2.93% [kernel] [k] mv_eth_tx
2.93% [kernel] [k] br_handle_frame_finish
2.93% [ath10k_pci] [k] ath10k_ce_send_nolock
2.93% [ath10k_core] [k] ath10k_txrx_tx_unref
2.51% [kernel] [k] eth_type_trans
2.51% [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
I notice that ieee80211_tx_status takes much of resource too, but because of firmware
issue we don't get true information from tx_status, should we deactivate it to improve
the performance?
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-29 15:04 ` RE : " Vu Hai NGUYEN
@ 2014-07-29 15:55 ` Ben Greear
2014-07-30 6:26 ` Michal Kazior
1 sibling, 0 replies; 30+ messages in thread
From: Ben Greear @ 2014-07-29 15:55 UTC (permalink / raw)
To: Vu Hai NGUYEN
Cc: Patrick CARNEIRO RODRIGUEZ, Adrian Chadd,
ath10k@lists.infradead.org, Bartosz Markowski
On 07/29/2014 08:04 AM, Vu Hai NGUYEN wrote:
>>>> I follow a tutorial to cross compile perf so here is my result
>>>>
>>>>
>>>> PerfTop: 70 irqs/sec kernel:98.6% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
>>>> -------------------------------------------------------------------------------
>>>>
>>>> 39.43% [kernel] [k] csum_partial_copy_nocheck
>
>>> Looks like your ethernet driver is not doing checksum offloading?
>
>>> I am pretty sure ath10k does support this unless you have managed
>>> to disabled it somehow?
>
>> I'm using ath10k from master branch (generated by backport), My only hack is changing the default country of regulatory domain from US to France.
>> The checksum patch is implemented by Michal Kazior since july 2013 and I also check that there is function checksum state in htt_rx.c file so it should be in my
>> driver module.
>> But I install ethtool and here is the ouput of my interface wlan0:
>> #ethtool --show-offload wlan0
>> Features for wlan0:
>> rx-checksumming: off [fixed]
>> tx-checksumming: on
>> tx-checksum-ipv4: off [fixed]
>> tx-checksum-unneeded: off [fixed]
>> tx-checksum-ip-generic: on [fixed]
>> tx-checksum-ipv6: off [fixed]
>> tx-checksum-fcoe-crc: off [fixed]
>> tx-checksum-sctp: off [fixed]
>> scatter-gather: off
>> tx-scatter-gather: off [fixed]
>> tx-scatter-gather-fraglist: off [fixed]
>> tcp-segmentation-offload: off
>> tx-tcp-segmentation: off [fixed]
>> tx-tcp-ecn-segmentation: off [fixed]
>> tx-tcp6-segmentation: off [fixed]
>> udp-fragmentation-offload: off [fixed]
>> generic-segmentation-offload: off [requested on]
>> generic-receive-offload: on
>> large-receive-offload: off [fixed]
>> rx-vlan-offload: off [fixed]
>> tx-vlan-offload: off [fixed]
>> ntuple-filters: off [fixed]
>> receive-hashing: off [fixed]
>> highdma: off [fixed]
>> rx-vlan-filter: off [fixed]
>> vlan-challenged: off [fixed]
>> tx-lockless: off [fixed]
>> netns-local: on [fixed]
>> tx-gso-robust: off [fixed]
>> tx-fcoe-segmentation: off [fixed]
>> fcoe-mtu: off [fixed]
>> tx-nocache-copy: on
>> loopback: off [fixed]
>>
>> And I cannot enable these function, as it show [fixed] like above.
>> # ethtool --offload wlan0 rx on tx on
>> Cannot change rx-checksumming
>> Cannot change tx-checksumming
>
> I used ethtool to disable Checksum offloading on my Ethernet interface and increase rate from
> 400 Mbps to 500 Mbps, now the thread "csum_partial_copy_nocheck" has disappeared and there
> is no more particular thread which takes most of the processor resource. But my processor is
> always exhausted.
Strange that disabling checksum helped things. Maybe your ethernet driver
has issues?
Looks like removing netfilter (and maybe ebtables?) would
also help your performance...
tx status is needed for bookkeping at least, even if you don't
get useful status info in stock firmware.
CT firmware will give you proper status if you apply some of the
ath10k driver patches from my tree, but that is unlikely to help
performance.
Thanks,
Ben
> I notice some warning when starting perf top
> [ath10k_core] with build id f31b98301ddea35e320bacaef048e4adbae00a6d not found, continuing without symbols
> [ath10k_pci] with build id a1303b5587ceef676d03d5a68fa5c7d717861c5d not found, continuing without symbols
> [mac80211] with build id f73251a940dedf51ac599141e5edefe05da2cb6f not found, continuing without symbols
> [cfg80211] with build id 94dd0809b98902252ce78cc3bc4ae385dd5e8fdf not found, continuing without symbols
> This may cause some unknown thread like the 2nd thread $a below of [mac80211]?
>
> PerfTop: 51 irqs/sec kernel:98.0% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
> -------------------------------------------------------------------------------
>
> 8.79% [mac80211] [k] ieee80211_tx_status
> 5.02% [mac80211] [k] $a
> 5.02% [kernel] [k] __memzero
> 4.60% [kernel] [k] memcpy
> 4.60% [kernel] [k] mv_eth_poll
> 4.18% [kernel] [k] dev_queue_xmit
> 4.18% [kernel] [k] br_parse_ip_options
> 3.77% [kernel] [k] dev_hard_start_xmit
> 3.77% [kernel] [k] nf_hook_slow
> 3.35% [kernel] [k] local_bh_enable
> 3.35% [kernel] [k] nf_iterate
> 3.35% [kernel] [k] br_nf_forward_ip
> 2.93% [kernel] [k] kfree
> 2.93% [kernel] [k] br_nf_pre_routing
> 2.93% [kernel] [k] mv_eth_tx
> 2.93% [kernel] [k] br_handle_frame_finish
> 2.93% [ath10k_pci] [k] ath10k_ce_send_nolock
> 2.93% [ath10k_core] [k] ath10k_txrx_tx_unref
> 2.51% [kernel] [k] eth_type_trans
> 2.51% [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
>
> I notice that ieee80211_tx_status takes much of resource too, but because of firmware
> issue we don't get true information from tx_status, should we deactivate it to improve
> the performance?
>
> NGUYEN Vu Hai
> Acita-Sodielec
> Route de Mayres - B.P. 9
> 12100 St GEORGES DE LUZENCON
> FRANCE
>
>
>
>
> NGUYEN Vu Hai
> Acita-Sodielec
> Route de Mayres - B.P. 9
> 12100 St GEORGES DE LUZENCON
> FRANCE
>
>
>
> _______________________________________________
> ath10k mailing list
> ath10k@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/ath10k
>
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-29 15:04 ` RE : " Vu Hai NGUYEN
2014-07-29 15:55 ` Ben Greear
@ 2014-07-30 6:26 ` Michal Kazior
2014-07-31 10:02 ` Vu Hai NGUYEN
2014-08-18 9:45 ` Vu Hai NGUYEN
1 sibling, 2 replies; 30+ messages in thread
From: Michal Kazior @ 2014-07-30 6:26 UTC (permalink / raw)
To: Vu Hai NGUYEN
Cc: Patrick CARNEIRO RODRIGUEZ, Ben Greear, Adrian Chadd,
ath10k@lists.infradead.org, Bartosz Markowski
On 29 July 2014 17:04, Vu Hai NGUYEN <vh.nguyen@actiasodielec.fr> wrote:
[...]
> I used ethtool to disable Checksum offloading on my Ethernet interface and increase rate from
> 400 Mbps to 500 Mbps, now the thread "csum_partial_copy_nocheck" has disappeared and there
> is no more particular thread which takes most of the processor resource. But my processor is
> always exhausted.
> I notice some warning when starting perf top
> [ath10k_core] with build id f31b98301ddea35e320bacaef048e4adbae00a6d not found, continuing without symbols
> [ath10k_pci] with build id a1303b5587ceef676d03d5a68fa5c7d717861c5d not found, continuing without symbols
> [mac80211] with build id f73251a940dedf51ac599141e5edefe05da2cb6f not found, continuing without symbols
> [cfg80211] with build id 94dd0809b98902252ce78cc3bc4ae385dd5e8fdf not found, continuing without symbols
> This may cause some unknown thread like the 2nd thread $a below of [mac80211]?
>
> PerfTop: 51 irqs/sec kernel:98.0% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
> -------------------------------------------------------------------------------
>
> 8.79% [mac80211] [k] ieee80211_tx_status
> 5.02% [mac80211] [k] $a
> 5.02% [kernel] [k] __memzero
> 4.60% [kernel] [k] memcpy
> 4.60% [kernel] [k] mv_eth_poll
> 4.18% [kernel] [k] dev_queue_xmit
> 4.18% [kernel] [k] br_parse_ip_options
> 3.77% [kernel] [k] dev_hard_start_xmit
> 3.77% [kernel] [k] nf_hook_slow
> 3.35% [kernel] [k] local_bh_enable
> 3.35% [kernel] [k] nf_iterate
> 3.35% [kernel] [k] br_nf_forward_ip
> 2.93% [kernel] [k] kfree
> 2.93% [kernel] [k] br_nf_pre_routing
> 2.93% [kernel] [k] mv_eth_tx
> 2.93% [kernel] [k] br_handle_frame_finish
> 2.93% [ath10k_pci] [k] ath10k_ce_send_nolock
> 2.93% [ath10k_core] [k] ath10k_txrx_tx_unref
> 2.51% [kernel] [k] eth_type_trans
> 2.51% [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
This accounts for 76.58% of CPU usage. You've most likely trimmed down
the remaining entries accounting for 24% before posting.
By the looks of it you might be able to strip down netfilter
(iptables) rules to none on all chains and tables if you just want to
max out the performance at the cost of having no firewall whatsoever.
You also might want to change qdisc (`tc` command) on all interfaces
involved to pfifo in case you're using codel to further reduce CPU
load at the cost of buffer bloating the system.
> I notice that ieee80211_tx_status takes much of resource too, but because of firmware
> issue we don't get true information from tx_status, should we deactivate it to improve
> the performance?
Even though tx rate isn't reported by ath10k it is still necessary to
report ack/no ack for frames and allow mac80211 to further process
frame completion.
Michał
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-30 6:26 ` Michal Kazior
@ 2014-07-31 10:02 ` Vu Hai NGUYEN
2014-08-18 9:45 ` Vu Hai NGUYEN
1 sibling, 0 replies; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-31 10:02 UTC (permalink / raw)
To: Michal Kazior
Cc: Patrick CARNEIRO RODRIGUEZ, Ben Greear, Adrian Chadd,
ath10k@lists.infradead.org, Bartosz Markowski
>Strange that disabling checksum helped things. Maybe your ethernet driver
>has issues?
I've no idea about this. Do you have any suggest how to check it? :D
>Looks like removing netfilter (and maybe ebtables?) would
>also help your performance...
I don't enable ebtables in my kernel config, so it shoud not be built in my kernel
>tx status is needed for bookkeping at least, even if you don't
>get useful status info in stock firmware.
>
>CT firmware will give you proper status if you apply some of the
>ath10k driver patches from my tree, but that is unlikely to help
>performance.
>This accounts for 76.58% of CPU usage. You've most likely trimmed down
>the remaining entries accounting for 24% before posting.
I saw there is option -a when running perf top but I did it and still, it doesn't
print all processes :(
>By the looks of it you might be able to strip down netfilter
>(iptables) rules to none on all chains and tables if you just want to
>max out the performance at the cost of having no firewall whatsoever.
I'd cleaned all rules of iptables and removed all modules of iptables from kernel by command modprobe -r
But there's still some process of netfilter process running. I disabled netfilter on bridge interface by writing 0 to these files:
/proc/sys/net/bridge/bridge-nf-call-arptables
/proc/sys/net/bridge/bridge-nf-call-iptables
/proc/sys/net/bridge/bridge-nf-call-ip6tables
and the performance increases from 500 to 550 Mbps (iperf in tcp reports between 530 ~ 570Mbps).
There is no more process like "br_nf_pre_routing" and "br_nf_forward_ip".
Do you think I can do anything more to strip down netfilter?
Now the processor of my AP (about 20% idle) is no more exhausted but not the same on STA (about 4.5 % idle)
Here is my perf top result on AP:
PerfTop: 99 irqs/sec kernel:96.0% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
-------------------------------------------------------------------------------
24.40% [kernel] [k] armadaxp_enter_idle
6.04% [mac80211] [k] ieee80211_tx_status
5.07% [kernel] [k] memcpy
3.38% [kernel] [k] mv_eth_poll
3.38% [mac80211] [k] $a
2.66% [kernel] [k] __memzero
2.54% [ath10k_pci] [k] ath10k_ce_send_nolock
2.17% [ath10k_core] [k] ath10k_txrx_tx_unref
2.05% [kernel] [k] dev_queue_xmit
2.05% [kernel] [k] br_handle_frame
1.69% [kernel] [k] local_bh_enable
1.69% [kernel] [k] eth_type_trans
1.69% [ath10k_core] [k] ath10k_htt_tx
1.69% ld-2.13.so [.] 0xf120
1.69% [ath10k_pci] [k] ath10k_ce_completed_send_next
1.57% [kernel] [k] __netif_receive_skb
1.45% [kernel] [k] dev_hard_start_xmit
1.45% [kernel] [k] nf_iterate
1.33% [kernel] [k] dev_gro_receive
1.21% [kernel] [k] kfree
1.21% [kernel] [k] __kfree_skb
And on STA:
PerfTop: 51 irqs/sec kernel:94.1% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
-------------------------------------------------------------------------------
7.51% [kernel] [k] memcpy
6.65% [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
5.49% [kernel] [k] mv_eth_tx
4.91% [kernel] [k] kfree
4.91% [kernel] [k] __memzero
4.05% [kernel] [k] armadaxp_enter_idle
4.05% [kernel] [k] __kmalloc_track_caller
4.05% [kernel] [k] dev_queue_xmit
4.05% [kernel] [k] ip_rcv
3.76% [mac80211] [k] ieee80211_rx
3.76% [kernel] [k] __kfree_skb
3.76% [ath10k_core] [k] $a
2.89% [mac80211] [k] ieee80211_rx_handlers
2.60% [mac80211] [k] $a
2.60% [kernel] [k] ip_forward
2.60% [cfg80211] [k] ieee80211_data_to_8023
2.60% [ath10k_pci] [k] ath10k_ce_completed_send_next
2.31% ld-2.13.so [.] 0x9d8c
2.31% [cfg80211] [k] ieee80211_hdrlen
2.02% [mac80211] [k] $a
>You also might want to change qdisc (`tc` command) on all interfaces
>involved to pfifo in case you're using codel to further reduce CPU
>load at the cost of buffer bloating the system.
I installed tc from package iproute2 and did : tc qdisc but it doesn't improve the performance :D
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread* RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-30 6:26 ` Michal Kazior
2014-07-31 10:02 ` Vu Hai NGUYEN
@ 2014-08-18 9:45 ` Vu Hai NGUYEN
2014-08-19 18:26 ` Ben Greear
1 sibling, 1 reply; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-08-18 9:45 UTC (permalink / raw)
To: Michal Kazior
Cc: Patrick CARNEIRO RODRIGUEZ, Ben Greear, Adrian Chadd,
ath10k@lists.infradead.org, Bartosz Markowski
[-- Attachment #1: Type: text/plain, Size: 3848 bytes --]
>> I used ethtool to disable Checksum offloading on my Ethernet interface and increase rate from
>> 400 Mbps to 500 Mbps, now the thread "csum_partial_copy_nocheck" has disappeared and there
>> is no more particular thread which takes most of the processor resource. But my processor is
>> always exhausted.
>> I notice some warning when starting perf top
>> [ath10k_core] with build id f31b98301ddea35e320bacaef048e4adbae00a6d not found, continuing without symbols
>> [ath10k_pci] with build id a1303b5587ceef676d03d5a68fa5c7d717861c5d not found, continuing without symbols
>> [mac80211] with build id f73251a940dedf51ac599141e5edefe05da2cb6f not found, continuing without symbols
>> [cfg80211] with build id 94dd0809b98902252ce78cc3bc4ae385dd5e8fdf not found, continuing without symbols
>> This may cause some unknown thread like the 2nd thread $a below of [mac80211]?
>>
>> PerfTop: 51 irqs/sec kernel:98.0% exact: 0.0% [1000Hz cycles], (all, 1 CPU)
>> -------------------------------------------------------------------------------
>>
>> 8.79% [mac80211] [k] ieee80211_tx_status
>> 5.02% [mac80211] [k] $a
>> 5.02% [kernel] [k] __memzero
>> 4.60% [kernel] [k] memcpy
>> 4.60% [kernel] [k] mv_eth_poll
>> 4.18% [kernel] [k] dev_queue_xmit
>> 4.18% [kernel] [k] br_parse_ip_options
>> 3.77% [kernel] [k] dev_hard_start_xmit
>> 3.77% [kernel] [k] nf_hook_slow
>> 3.35% [kernel] [k] local_bh_enable
>> 3.35% [kernel] [k] nf_iterate
>> 3.35% [kernel] [k] br_nf_forward_ip
>> 2.93% [kernel] [k] kfree
>> 2.93% [kernel] [k] br_nf_pre_routing
>> 2.93% [kernel] [k] mv_eth_tx
>> 2.93% [kernel] [k] br_handle_frame_finish
>> 2.93% [ath10k_pci] [k] ath10k_ce_send_nolock
>> 2.93% [ath10k_core] [k] ath10k_txrx_tx_unref
>> 2.51% [kernel] [k] eth_type_trans
>> 2.51% [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
>This accounts for 76.58% of CPU usage. You've most likely trimmed down
>the remaining entries accounting for 24% before posting.
You can find in the attached file the report of perf using in my AP and STA. Thank you in advance for the review or any comment
>By the looks of it you might be able to strip down netfilter
>(iptables) rules to none on all chains and tables if you just want to
>max out the performance at the cost of having no firewall whatsoever.
I'd cleaned all rules of iptables and removed all modules of iptables from kernel by command modprobe -r
But there's still some process of netfilter process running. I disabled netfilter on bridge interface by writing 0 to these files:
/proc/sys/net/bridge/bridge-nf-call-arptables
/proc/sys/net/bridge/bridge-nf-call-iptables
/proc/sys/net/bridge/bridge-nf-call-ip6tables
and the performance increases from 500 to 550 Mbps (iperf in tcp reports between 530 ~ 570Mbps).
There is no more process like "br_nf_pre_routing" and "br_nf_forward_ip".
Do you think I can do anything more to strip down netfilter?
>You also might want to change qdisc (`tc` command) on all interfaces
>involved to pfifo in case you're using codel to further reduce CPU
>load at the cost of buffer bloating the system.
I installed tc from package iproute2 and did : tc qdisc but it doesn't improve the performance
One more question: Could the antennas create any effect on the MCS in use?
We are using this antenna from PCTEL:
http://www.antenna.com/apg_products.cgi?id_num=11395
And in the specification, I saw that it supports the standard 802.11n, so may be this is the reason
that the best rate for me is MCS7?
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
[-- Attachment #2: ap.txt --]
[-- Type: text/plain, Size: 65395 bytes --]
10.95% swapper [kernel.kallsyms] [k] armadaxp_enter_idle
2.01% swapper [mac80211] [k] ieee80211_tx_status
1.34% swapper [kernel.kallsyms] [k] memcpy
1.27% swapper [kernel.kallsyms] [k] mv_eth_poll
1.04% swapper [kernel.kallsyms] [k] __netif_receive_skb
0.97% swapper [mac80211] [k] $a
0.94% swapper [kernel.kallsyms] [k] __memzero
0.90% swapper [kernel.kallsyms] [k] br_handle_frame
0.90% kworker/u:2 [kernel.kallsyms] [k] __delay
0.84% swapper [kernel.kallsyms] [k] local_bh_enable
0.77% swapper [kernel.kallsyms] [k] br_handle_frame_finish
0.74% swapper [kernel.kallsyms] [k] dev_queue_xmit
0.74% swapper [ath10k_core] [k] $a
0.70% swapper [mac80211] [k] invoke_tx_handlers
0.67% swapper [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.67% sh ld-2.13.so [.] 0x18804
0.64% swapper [kernel.kallsyms] [k] br_nf_pre_routing
0.64% swapper [ath10k_core] [k] ath10k_txrx_tx_unref
0.60% swapper [kernel.kallsyms] [k] mv_eth_tx
0.60% swapper [kernel.kallsyms] [k] dev_gro_receive
0.60% swapper [kernel.kallsyms] [k] dev_hard_start_xmit
0.60% swapper [kernel.kallsyms] [k] eth_type_trans
0.57% sh [mac80211] [k] ieee80211_tx_status
0.54% swapper [mac80211] [k] ieee80211_tx_prepare
0.54% swapper [kernel.kallsyms] [k] nf_iterate
0.50% swapper [mac80211] [k] sta_info_get
0.50% swapper [ath10k_pci] [k] ath10k_ce_send_nolock
0.47% swapper [kernel.kallsyms] [k] skb_recycle_check
0.47% swapper [ath10k_core] [k] ath10k_tx
0.44% swapper [mac80211] [k] ieee80211_rx
0.44% swapper [ath10k_pci] [k] ath10k_ce_completed_send_next
0.40% swapper [kernel.kallsyms] [k] __do_softirq
0.40% swapper [kernel.kallsyms] [k] kfree
0.40% swapper [kernel.kallsyms] [k] __kfree_skb
0.40% swapper [kernel.kallsyms] [k] br_fdb_update
0.40% sh [kernel.kallsyms] [k] __memzero
0.37% swapper [kernel.kallsyms] [k] __kmalloc_track_caller
0.37% swapper [kernel.kallsyms] [k] netif_receive_skb
0.37% swapper [kernel.kallsyms] [k] inet_gro_receive
0.37% swapper [ath10k_core] [k] ath10k_tx_htt
0.33% swapper [mac80211] [k] ieee80211_rx_handlers
0.33% swapper [mac80211] [k] ieee80211_tx
0.33% swapper [kernel.kallsyms] [k] dma_pool_alloc
0.33% swapper [kernel.kallsyms] [k] __br_forward
0.33% swapper [ath10k_core] [k] ath10k_htt_tx
0.33% sh [kernel.kallsyms] [k] memcpy
0.33% sh [kernel.kallsyms] [k] mv_eth_poll
0.30% swapper [mac80211] [k] $a
0.30% swapper [mac80211] [k] $a
0.30% swapper [kernel.kallsyms] [k] nf_hook_slow
0.30% swapper [kernel.kallsyms] [k] br_dev_queue_push_xmit
0.30% sh [mac80211] [k] $a
0.27% swapper [kernel.kallsyms] [k] local_bh_disable
0.27% swapper [kernel.kallsyms] [k] skb_push
0.27% swapper [kernel.kallsyms] [k] sch_direct_xmit
0.27% swapper [cfg80211] [k] ieee80211_hdrlen
0.27% swapper [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.27% swapper [ath10k_core] [k] $a
0.27% modprobe [ath10k_core] [k] ath10k_txrx_tx_unref
0.27% ksoftirqd/0 [mac80211] [k] $a
0.27% iw ld-2.13.so [.] 0x9a7c
0.27% iw [kernel.kallsyms] [k] __memzero
0.23% swapper [mac80211] [k] $a
0.23% swapper [kernel.kallsyms] [k] _find_first_zero_bit_le
0.23% swapper [kernel.kallsyms] [k] mv_eth_skb_recycle
0.23% swapper [kernel.kallsyms] [k] skb_recycle
0.23% swapper [kernel.kallsyms] [k] skb_put
0.23% swapper [kernel.kallsyms] [k] skb_gro_reset_offset
0.23% swapper [kernel.kallsyms] [k] br_forward_finish
0.23% swapper [kernel.kallsyms] [k] br_forward
0.23% swapper [kernel.kallsyms] [k] br_nf_post_routing
0.23% swapper [kernel.kallsyms] [k] br_nf_forward_arp
0.23% swapper [cfg80211] [k] ieee80211_data_to_8023
0.23% sh [kernel.kallsyms] [k] __netif_receive_skb
0.23% sh [kernel.kallsyms] [k] dev_queue_xmit
0.23% monitor [mac80211] [k] ieee80211_tx_status
0.23% ksoftirqd/0 [kernel.kallsyms] [k] dev_gro_receive
0.23% ksoftirqd/0 [kernel.kallsyms] [k] nf_iterate
0.23% egrep [mac80211] [k] ieee80211_tx_status
0.20% swapper [mac80211] [k] ieee80211_select_queue
0.20% swapper [kernel.kallsyms] [k] br_nf_forward_ip
0.20% swapper [ath10k_pci] [k] ath10k_pci_ce_send_done
0.20% sh [kernel.kallsyms] [k] skb_recycle_check
0.20% sh [kernel.kallsyms] [k] netif_receive_skb
0.20% sh [kernel.kallsyms] [k] dev_gro_receive
0.20% sh [kernel.kallsyms] [k] nf_iterate
0.20% sh [ath10k_core] [k] $a
0.20% sh [ath10k_core] [k] ath10k_txrx_tx_unref
0.20% modprobe libc-2.13.so [.] _IO_getc
0.20% modprobe [mac80211] [k] ieee80211_tx_status
0.20% modprobe [kernel.kallsyms] [k] __memzero
0.20% modprobe [kernel.kallsyms] [k] __netif_receive_skb
0.20% kworker/u:2 [mac80211] [k] ieee80211_tx_status
0.20% ksoftirqd/0 [kernel.kallsyms] [k] mv_eth_poll
0.20% iw [kernel.kallsyms] [k] mv_eth_tx
0.20% cut [mac80211] [k] ieee80211_tx_status
0.17% wc ld-2.13.so [.] 0xfe04
0.17% swapper [mac80211] [k] ieee80211_tx_h_michael_mic_add
0.17% swapper [mac80211] [k] ieee80211_frame_allowed
0.17% swapper [mac80211] [k] ieee80211_deliver_skb
0.17% swapper [mac80211] [k] ieee80211_set_qos_hdr
0.17% swapper [kernel.kallsyms] [k] memmove
0.17% swapper [kernel.kallsyms] [k] skb_pull
0.17% sh [kernel.kallsyms] [k] cpu_pj4bv7_dcache_clean_area
0.17% sh [kernel.kallsyms] [k] mv_eth_skb_recycle
0.17% sh [kernel.kallsyms] [k] nf_hook_slow
0.17% sh [kernel.kallsyms] [k] br_fdb_update
0.17% sh [cfg80211] [k] ieee80211_data_to_8023
0.17% sh [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.17% sh [ath10k_core] [k] ath10k_htt_tx
0.17% monitor [mac80211] [k] $a
0.17% modprobe [kernel.kallsyms] [k] memcpy
0.17% modprobe [kernel.kallsyms] [k] __br_fdb_get
0.17% kworker/u:2 [kernel.kallsyms] [k] mv_eth_poll
0.17% ksoftirqd/0 [mac80211] [k] $a
0.17% iw [mac80211] [k] ieee80211_tx_status
0.17% iw [kernel.kallsyms] [k] mv_eth_poll
0.17% iw [kernel.kallsyms] [k] dev_queue_xmit
0.17% iw [kernel.kallsyms] [k] nf_iterate
0.17% egrep ld-2.13.so [.] 0xc0a8
0.17% cut ld-2.13.so [.] 0x9be4
0.13% wc [kernel.kallsyms] [k] mv_eth_poll
0.13% swapper [mac80211] [k] ieee80211_skb_resize
0.13% swapper [mac80211] [k] ieee80211_xmit
0.13% swapper [kernel.kallsyms] [k] dma_pool_free
0.13% swapper [kernel.kallsyms] [k] consume_skb
0.13% swapper [kernel.kallsyms] [k] harmonize_features
0.13% swapper [kernel.kallsyms] [k] netif_skb_features
0.13% swapper [cfg80211] [k] cfg80211_classify8021d
0.13% swapper [ath10k_pci] [k] ath10k_pci_tasklet
0.13% sh [mac80211] [k] $a
0.13% sh [kernel.kallsyms] [k] local_bh_enable
0.13% sh [kernel.kallsyms] [k] kfree
0.13% sh [kernel.kallsyms] [k] mv_eth_tx
0.13% sh [kernel.kallsyms] [k] dev_hard_start_xmit
0.13% sh [kernel.kallsyms] [k] eth_type_trans
0.13% sh [kernel.kallsyms] [k] br_handle_frame_finish
0.13% sh [kernel.kallsyms] [k] br_handle_frame
0.13% sh [cfg80211] [k] cfg80211_classify8021d
0.13% sh [ath10k_pci] [k] ath10k_ce_completed_send_next
0.13% sh [ath10k_core] [k] ath10k_tx_htt
0.13% sh [ath10k_core] [k] $a
0.13% rm [kernel.kallsyms] [k] __memzero
0.13% rm [kernel.kallsyms] [k] eth_type_trans
0.13% monitor monitor [.] 0xf44
0.13% monitor [mac80211] [k] $a
0.13% monitor [kernel.kallsyms] [k] mv_eth_poll
0.13% monitor [kernel.kallsyms] [k] dev_queue_xmit
0.13% modprobe [mac80211] [k] $a
0.13% modprobe [kernel.kallsyms] [k] __do_softirq
0.13% modprobe [kernel.kallsyms] [k] mv_eth_poll
0.13% modprobe [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.13% kworker/u:2 [kernel.kallsyms] [k] dma_pool_alloc
0.13% kworker/u:2 [kernel.kallsyms] [k] dev_gro_receive
0.13% kworker/u:2 [kernel.kallsyms] [k] inet_gro_receive
0.13% ksoftirqd/0 [kernel.kallsyms] [k] dev_hard_start_xmit
0.13% ksoftirqd/0 [kernel.kallsyms] [k] inet_gro_receive
0.13% ksoftirqd/0 [kernel.kallsyms] [k] __br_fdb_get
0.13% ksoftirqd/0 [ath10k_core] [k] $a
0.13% iw [kernel.kallsyms] [k] kfree
0.13% iw [kernel.kallsyms] [k] memcpy
0.13% iw [ath10k_pci] [k] ath10k_ce_send_nolock
0.13% grep [kernel.kallsyms] [k] dev_queue_xmit
0.13% egrep [kernel.kallsyms] [k] br_dev_queue_push_xmit
0.10% wc [mac80211] [k] ieee80211_tx_status
0.10% wc [kernel.kallsyms] [k] memcpy
0.10% wc [kernel.kallsyms] [k] dev_queue_xmit
0.10% wc [ath10k_pci] [k] ath10k_ce_send_nolock
0.10% wc [ath10k_core] [k] ath10k_htt_tx
0.10% touch [kernel.kallsyms] [k] memcpy
0.10% swapper [mac80211] [k] $a
0.10% swapper [mac80211] [k] $a
0.10% swapper [kernel.kallsyms] [k] __br_fdb_get
0.10% swapper [ath10k_pci] [k] ath10k_pci_fw_interrupt_handler
0.10% swapper [ath10k_core] [k] ath10k_htt_tx_alloc_msdu_id
0.10% swapper [ath10k_core] [k] ath10k_htt_tx_free_msdu_id
0.10% sh busybox [.] 0x379ec
0.10% sh [mac80211] [k] ieee80211_rx_handlers
0.10% sh [kernel.kallsyms] [k] filemap_fault
0.10% sh [kernel.kallsyms] [k] _find_first_zero_bit_le
0.10% sh [kernel.kallsyms] [k] __kfree_skb
0.10% sh [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.10% rm ld-2.13.so [.] 0x9758
0.10% rm [mac80211] [k] ieee80211_tx_status
0.10% rm [kernel.kallsyms] [k] br_handle_frame
0.10% rm [ath10k_pci] [k] ath10k_ce_send_nolock
0.10% monitor libc-2.13.so [.] vfprintf
0.10% monitor [kernel.kallsyms] [k] memmove
0.10% monitor [kernel.kallsyms] [k] __memzero
0.10% monitor [kernel.kallsyms] [k] mv_eth_tx
0.10% monitor [kernel.kallsyms] [k] nf_iterate
0.10% monitor [ath10k_pci] [k] ath10k_ce_send_nolock
0.10% monitor [ath10k_core] [k] ath10k_txrx_tx_unref
0.10% modprobe libc-2.13.so [.] strchr
0.10% modprobe ld-2.13.so [.] 0x9b14
0.10% modprobe [mac80211] [k] $a
0.10% modprobe [kernel.kallsyms] [k] kfree
0.10% modprobe [kernel.kallsyms] [k] eth_type_trans
0.10% modprobe [kernel.kallsyms] [k] nf_hook_slow
0.10% kworker/u:2 [mac80211] [k] $a
0.10% kworker/u:2 [kernel.kallsyms] [k] br_handle_frame
0.10% kworker/u:2 [ath10k_core] [k] ath10k_htt_tx
0.10% ksoftirqd/0 [mac80211] [k] ieee80211_rx_handlers
0.10% ksoftirqd/0 [mac80211] [k] ieee80211_tx_prepare
0.10% ksoftirqd/0 [kernel.kallsyms] [k] __netif_receive_skb
0.10% ksoftirqd/0 [kernel.kallsyms] [k] eth_type_trans
0.10% ksoftirqd/0 [kernel.kallsyms] [k] sch_direct_xmit
0.10% ksoftirqd/0 [ath10k_pci] [k] ath10k_ce_send_nolock
0.10% ksoftirqd/0 [ath10k_pci] [k] ath10k_ce_completed_send_next
0.10% ksoftirqd/0 [ath10k_core] [k] ath10k_tx_htt
0.10% ksoftirqd/0 [ath10k_core] [k] ath10k_tx
0.10% iw [mac80211] [k] invoke_tx_handlers
0.10% iw [mac80211] [k] $a
0.10% iw [mac80211] [k] ieee80211_tx
0.10% iw [kernel.kallsyms] [k] local_bh_disable
0.10% iw [kernel.kallsyms] [k] local_bh_enable
0.10% iw [kernel.kallsyms] [k] __netif_receive_skb
0.10% iw [kernel.kallsyms] [k] dev_hard_start_xmit
0.10% iw [cfg80211] [k] ieee80211_hdrlen
0.10% iw [ath10k_core] [k] ath10k_tx_htt
0.10% iw [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.10% iw [ath10k_core] [k] $a
0.10% grep [kernel.kallsyms] [k] local_bh_enable
0.10% egrep libc-2.13.so [.] 0x16ba0
0.10% egrep [kernel.kallsyms] [k] memcpy
0.10% egrep [kernel.kallsyms] [k] skb_push
0.10% egrep [kernel.kallsyms] [k] eth_type_trans
0.10% egrep [ath10k_pci] [k] ath10k_ce_completed_send_next
0.10% egrep [ath10k_core] [k] ath10k_tx_htt
0.10% cut [kernel.kallsyms] [k] dev_hard_start_xmit
0.10% cut [kernel.kallsyms] [k] dev_queue_xmit
0.10% cut [kernel.kallsyms] [k] br_handle_frame_finish
0.10% cgi_fh [mac80211] [k] ieee80211_tx_status
0.10% cgi_fh [kernel.kallsyms] [k] memcpy
0.07% wc [mac80211] [k] ieee80211_tx_prepare
0.07% wc [mac80211] [k] $a
0.07% wc [kernel.kallsyms] [k] local_bh_enable
0.07% wc [kernel.kallsyms] [k] kmem_cache_free
0.07% wc [kernel.kallsyms] [k] __alloc_skb
0.07% wc [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.07% wc [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.07% touch [mac80211] [k] ieee80211_tx_status
0.07% touch [mac80211] [k] $a
0.07% touch [ath10k_pci] [k] ath10k_ce_send_nolock
0.07% swapper [mac80211] [k] ieee80211_rx_h_michael_mic_verify
0.07% swapper [mac80211] [k] $a
0.07% swapper [mac80211] [k] ieee80211_prepare_and_rx_handle
0.07% swapper [mac80211] [k] $a
0.07% swapper [mac80211] [k] ieee80211_subif_start_xmit
0.07% swapper [mac80211] [k] ieee80211_downgrade_queue.isra.1
0.07% swapper [kernel.kallsyms] [k] kmem_cache_alloc
0.07% swapper [kernel.kallsyms] [k] mv_eth_select_txq
0.07% swapper [kernel.kallsyms] [k] __alloc_skb
0.07% swapper [kernel.kallsyms] [k] dev_alloc_skb
0.07% swapper [kernel.kallsyms] [k] net_rx_action
0.07% swapper [kernel.kallsyms] [k] napi_gro_receive
0.07% swapper [kernel.kallsyms] [k] tcp4_gro_receive
0.07% swapper [ath10k_pci] [k] ath10k_ce_per_engine_service_any
0.07% swapper [ath10k_core] [k] ath10k_htt_rx_get_csum_state
0.07% swapper [ath10k_core] [k] 0x8828
0.07% sh libc-2.13.so [.] _dl_addr
0.07% sh [mac80211] [k] ieee80211_tx_h_michael_mic_add
0.07% sh [mac80211] [k] ieee80211_tx_prepare
0.07% sh [mac80211] [k] $a
0.07% sh [mac80211] [k] ieee80211_tx
0.07% sh [kernel.kallsyms] [k] __sync_icache_dcache
0.07% sh [kernel.kallsyms] [k] cpu_pj4bv7_set_pte_ext
0.07% sh [kernel.kallsyms] [k] local_bh_disable
0.07% sh [kernel.kallsyms] [k] __wake_up_bit
0.07% sh [kernel.kallsyms] [k] anon_vma_clone
0.07% sh [kernel.kallsyms] [k] dma_pool_alloc
0.07% sh [kernel.kallsyms] [k] __kmalloc_track_caller
0.07% sh [kernel.kallsyms] [k] memmove
0.07% sh [kernel.kallsyms] [k] __alloc_skb
0.07% sh [kernel.kallsyms] [k] napi_skb_finish
0.07% sh [kernel.kallsyms] [k] napi_gro_receive
0.07% sh [kernel.kallsyms] [k] inet_gro_receive
0.07% sh [kernel.kallsyms] [k] br_forward_finish
0.07% sh [kernel.kallsyms] [k] br_forward
0.07% sh [kernel.kallsyms] [k] br_nf_post_routing
0.07% sh [kernel.kallsyms] [k] br_nf_forward_ip
0.07% sh [kernel.kallsyms] [k] br_nf_pre_routing
0.07% sh [ath10k_pci] [k] ath10k_pci_tasklet
0.07% rm [mac80211] [k] ieee80211_rx_handlers
0.07% rm [mac80211] [k] $a
0.07% rm [mac80211] [k] ieee80211_tx_prepare
0.07% rm [mac80211] [k] ieee80211_tx
0.07% rm [mac80211] [k] ieee80211_subif_start_xmit
0.07% rm [mac80211] [k] $a
0.07% rm [kernel.kallsyms] [k] __do_softirq
0.07% rm [kernel.kallsyms] [k] local_bh_enable
0.07% rm [kernel.kallsyms] [k] __kmalloc_track_caller
0.07% rm [kernel.kallsyms] [k] memcpy
0.07% rm [kernel.kallsyms] [k] mv_eth_tx
0.07% rm [kernel.kallsyms] [k] dev_queue_xmit
0.07% rm [kernel.kallsyms] [k] nf_iterate
0.07% rm [kernel.kallsyms] [k] br_handle_frame_finish
0.07% rm [ath10k_pci] [k] ath10k_ce_completed_send_next
0.07% rm [ath10k_core] [k] ath10k_tx_htt
0.07% rm [ath10k_core] [k] ath10k_tx
0.07% rm [ath10k_core] [k] ath10k_htt_tx
0.07% principal [mac80211] [k] ieee80211_tx_status
0.07% principal [mac80211] [k] $a
0.07% monitor libc-2.13.so [.] _IO_default_xsputn
0.07% monitor libc-2.13.so [.] strcmp
0.07% monitor [mac80211] [k] invoke_tx_handlers
0.07% monitor [mac80211] [k] ieee80211_subif_start_xmit
0.07% monitor [mac80211] [k] ieee80211_set_qos_hdr
0.07% monitor [kernel.kallsyms] [k] vma_wants_writenotify
0.07% monitor [kernel.kallsyms] [k] kfree
0.07% monitor [kernel.kallsyms] [k] memcpy
0.07% monitor [kernel.kallsyms] [k] netif_receive_skb
0.07% monitor [kernel.kallsyms] [k] sch_direct_xmit
0.07% monitor [kernel.kallsyms] [k] tcp4_gro_receive
0.07% monitor [kernel.kallsyms] [k] inet_gro_receive
0.07% monitor [kernel.kallsyms] [k] br_fdb_update
0.07% monitor [kernel.kallsyms] [k] br_dev_queue_push_xmit
0.07% monitor [kernel.kallsyms] [k] br_handle_frame
0.07% monitor [cfg80211] [k] ieee80211_hdrlen
0.07% monitor [ath10k_core] [k] $a
0.07% modprobe libc-2.13.so [.] strchrnul
0.07% modprobe libc-2.13.so [.] _dl_addr
0.07% modprobe libc-2.13.so [.] 0x6b974
0.07% modprobe [mac80211] [k] $a
0.07% modprobe [mac80211] [k] ieee80211_tx
0.07% modprobe [kernel.kallsyms] [k] __kmalloc_track_caller
0.07% modprobe [kernel.kallsyms] [k] memmove
0.07% modprobe [kernel.kallsyms] [k] br_forward_finish
0.07% modprobe [kernel.kallsyms] [k] br_handle_frame_finish
0.07% modprobe [kernel.kallsyms] [k] md5_transform
0.07% modprobe [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.07% modprobe [ath10k_pci] [k] ath10k_ce_send_nolock
0.07% modprobe [ath10k_core] [k] $a
0.07% lighttpd [kernel.kallsyms] [k] eth_type_trans
0.07% kworker/u:2 [kernel.kallsyms] [k] __do_softirq
0.07% kworker/u:2 [kernel.kallsyms] [k] local_bh_enable
0.07% kworker/u:2 [kernel.kallsyms] [k] kmem_cache_alloc
0.07% kworker/u:2 [kernel.kallsyms] [k] memcpy
0.07% kworker/u:2 [kernel.kallsyms] [k] __memzero
0.07% kworker/u:2 [kernel.kallsyms] [k] mv_eth_tx
0.07% kworker/u:2 [kernel.kallsyms] [k] harmonize_features
0.07% kworker/u:2 [kernel.kallsyms] [k] __netif_receive_skb
0.07% kworker/u:2 [kernel.kallsyms] [k] net_rx_action
0.07% kworker/u:2 [kernel.kallsyms] [k] napi_gro_receive
0.07% kworker/u:2 [kernel.kallsyms] [k] dev_queue_xmit
0.07% kworker/u:2 [kernel.kallsyms] [k] __br_fdb_get
0.07% kworker/u:2 [kernel.kallsyms] [k] br_fdb_update
0.07% kworker/u:2 [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.07% kworker/u:2 [ath10k_core] [k] ath10k_tx_htt
0.07% ksoftirqd/0 [mac80211] [k] sta_info_get
0.07% ksoftirqd/0 [mac80211] [k] ieee80211_downgrade_queue.isra.1
0.07% ksoftirqd/0 [mac80211] [k] $a
0.07% ksoftirqd/0 [kernel.kallsyms] [k] dma_pool_alloc
0.07% ksoftirqd/0 [kernel.kallsyms] [k] __kmalloc_track_caller
0.07% ksoftirqd/0 [kernel.kallsyms] [k] kmem_cache_alloc
0.07% ksoftirqd/0 [kernel.kallsyms] [k] memcpy
0.07% ksoftirqd/0 [kernel.kallsyms] [k] __memzero
0.07% ksoftirqd/0 [kernel.kallsyms] [k] __kfree_skb
0.07% ksoftirqd/0 [kernel.kallsyms] [k] skb_recycle_check
0.07% ksoftirqd/0 [kernel.kallsyms] [k] dev_queue_xmit
0.07% ksoftirqd/0 [kernel.kallsyms] [k] tcp4_gro_receive
0.07% ksoftirqd/0 [kernel.kallsyms] [k] br_forward
0.07% ksoftirqd/0 [kernel.kallsyms] [k] br_handle_frame_finish
0.07% ksoftirqd/0 [kernel.kallsyms] [k] br_nf_pre_routing
0.07% ksoftirqd/0 [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.07% iw libnl-3.so.200.19.0 [.] 0x6a80
0.07% iw [mac80211] [k] ieee80211_tx_h_michael_mic_add
0.07% iw [mac80211] [k] ieee80211_rx_handlers
0.07% iw [mac80211] [k] ieee80211_subif_start_xmit
0.07% iw [mac80211] [k] $a
0.07% iw [kernel.kallsyms] [k] __do_softirq
0.07% iw [kernel.kallsyms] [k] dma_pool_alloc
0.07% iw [kernel.kallsyms] [k] __kmalloc_track_caller
0.07% iw [kernel.kallsyms] [k] skb_recycle_check
0.07% iw [kernel.kallsyms] [k] skb_put
0.07% iw [kernel.kallsyms] [k] harmonize_features
0.07% iw [kernel.kallsyms] [k] dev_gro_receive
0.07% iw [kernel.kallsyms] [k] eth_type_trans
0.07% iw [kernel.kallsyms] [k] sch_direct_xmit
0.07% iw [kernel.kallsyms] [k] nf_hook_slow
0.07% iw [kernel.kallsyms] [k] br_dev_queue_push_xmit
0.07% iw [kernel.kallsyms] [k] br_nf_post_routing
0.07% iw [cfg80211] [k] ieee80211_data_to_8023
0.07% iw [ath10k_core] [k] $a
0.07% iw [ath10k_core] [k] ath10k_txrx_tx_unref
0.07% grep libc-2.13.so [.] _dl_addr
0.07% grep [mac80211] [k] $a
0.07% grep [kernel.kallsyms] [k] memcpy
0.07% grep [ath10k_pci] [k] ath10k_ce_send_nolock
0.07% egrep libc-2.13.so [.] _dl_addr
0.07% egrep [mac80211] [k] $a
0.07% egrep [mac80211] [k] $a
0.07% egrep [kernel.kallsyms] [k] local_bh_enable
0.07% egrep [kernel.kallsyms] [k] __memzero
0.07% egrep [kernel.kallsyms] [k] mv_eth_tx
0.07% egrep [kernel.kallsyms] [k] mv_eth_poll
0.07% egrep [kernel.kallsyms] [k] skb_recycle_check
0.07% egrep [kernel.kallsyms] [k] skb_put
0.07% egrep [kernel.kallsyms] [k] dev_queue_xmit
0.07% egrep [kernel.kallsyms] [k] br_handle_frame_finish
0.07% egrep [kernel.kallsyms] [k] br_handle_frame
0.07% egrep [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.07% egrep [ath10k_core] [k] $a
0.07% egrep [ath10k_core] [k] ath10k_txrx_tx_unref
0.07% cut [mac80211] [k] $a
0.07% cut [kernel.kallsyms] [k] unmap_vmas
0.07% cut [kernel.kallsyms] [k] fput
0.07% cut [kernel.kallsyms] [k] memcpy
0.07% cut [kernel.kallsyms] [k] __memzero
0.07% cut [kernel.kallsyms] [k] mv_eth_tx
0.07% cut [kernel.kallsyms] [k] mv_eth_poll
0.07% cut [kernel.kallsyms] [k] nf_iterate
0.07% cut [kernel.kallsyms] [k] br_dev_queue_push_xmit
0.07% cut [kernel.kallsyms] [k] br_handle_frame
0.07% cut [kernel.kallsyms] [k] do_page_fault.part.8
0.07% cut [cfg80211] [k] cfg80211_classify8021d
0.07% cgi_fh ld-2.13.so [.] 0x8c58
0.07% cgi_fh [mac80211] [k] $a
0.07% cgi_fh [mac80211] [k] ieee80211_set_qos_hdr
0.07% cgi_fh [kernel.kallsyms] [k] skb_recycle_check
0.07% cgi_fh [kernel.kallsyms] [k] br_fdb_update
0.07% cgi_fh [kernel.kallsyms] [k] br_handle_frame_finish
0.03% wc libc-2.13.so [.] _IO_getc
0.03% wc ld-2.13.so [.] __libc_memalign
0.03% wc [mac80211] [k] sta_info_get
0.03% wc [mac80211] [k] ieee80211_deliver_skb
0.03% wc [mac80211] [k] ieee80211_rx_handlers
0.03% wc [mac80211] [k] ieee80211_rx
0.03% wc [mac80211] [k] $a
0.03% wc [kernel.kallsyms] [k] cpu_pj4bv7_dcache_clean_area
0.03% wc [kernel.kallsyms] [k] find_get_page
0.03% wc [kernel.kallsyms] [k] page_evictable
0.03% wc [kernel.kallsyms] [k] shmem_recalc_inode
0.03% wc [kernel.kallsyms] [k] unmap_vmas
0.03% wc [kernel.kallsyms] [k] dma_pool_free
0.03% wc [kernel.kallsyms] [k] kfree
0.03% wc [kernel.kallsyms] [k] kmem_cache_alloc
0.03% wc [kernel.kallsyms] [k] mntput_no_expire
0.03% wc [kernel.kallsyms] [k] copy_page
0.03% wc [kernel.kallsyms] [k] mv_eth_skb_recycle
0.03% wc [kernel.kallsyms] [k] mv_eth_tx
0.03% wc [kernel.kallsyms] [k] skb_pull
0.03% wc [kernel.kallsyms] [k] consume_skb
0.03% wc [kernel.kallsyms] [k] skb_trim
0.03% wc [kernel.kallsyms] [k] __netif_receive_skb
0.03% wc [kernel.kallsyms] [k] dev_gro_receive
0.03% wc [kernel.kallsyms] [k] napi_gro_receive
0.03% wc [kernel.kallsyms] [k] dev_hard_start_xmit
0.03% wc [kernel.kallsyms] [k] nf_iterate
0.03% wc [kernel.kallsyms] [k] inet_gro_receive
0.03% wc [kernel.kallsyms] [k] br_fdb_update
0.03% wc [kernel.kallsyms] [k] br_dev_queue_push_xmit
0.03% wc [kernel.kallsyms] [k] __br_forward
0.03% wc [kernel.kallsyms] [k] br_handle_frame_finish
0.03% wc [kernel.kallsyms] [k] br_handle_frame
0.03% wc [kernel.kallsyms] [k] ret_from_exception
0.03% wc [ath10k_core] [k] ath10k_tx
0.03% wc [ath10k_core] [k] $a
0.03% wc [ath10k_core] [k] $a
0.03% touch ld-2.13.so [.] 0xbba4
0.03% touch [mac80211] [k] ieee80211_rx_handlers
0.03% touch [mac80211] [k] $a
0.03% touch [mac80211] [k] $a
0.03% touch [mac80211] [k] $a
0.03% touch [mac80211] [k] ieee80211_tx
0.03% touch [kernel.kallsyms] [k] arch_get_unmapped_area
0.03% touch [kernel.kallsyms] [k] local_bh_disable
0.03% touch [kernel.kallsyms] [k] up_read
0.03% touch [kernel.kallsyms] [k] __alloc_pages_nodemask
0.03% touch [kernel.kallsyms] [k] mv_eth_skb_recycle
0.03% touch [kernel.kallsyms] [k] mv_eth_tx
0.03% touch [kernel.kallsyms] [k] skb_recycle_check
0.03% touch [kernel.kallsyms] [k] skb_push
0.03% touch [kernel.kallsyms] [k] dev_gro_receive
0.03% touch [kernel.kallsyms] [k] dev_queue_xmit
0.03% touch [ath10k_pci] [k] ath10k_pci_tasklet
0.03% touch [ath10k_core] [k] ath10k_tx
0.03% touch [ath10k_core] [k] $a
0.03% touch [ath10k_core] [k] ath10k_txrx_tx_unref
0.03% swapper [mac80211] [k] ieee80211_report_used_skb
0.03% swapper [mac80211] [k] ieee80211_netdev_select_queue
0.03% swapper [mac80211] [k] remove_monitor_info
0.03% swapper [mac80211] [k] ieee80211_rx_handlers_result
0.03% swapper [mac80211] [k] $a
0.03% swapper [mac80211] [k] ieee80211_get_bssid
0.03% swapper [mac80211] [k] 0x2354
0.03% swapper [kernel.kallsyms] [k] cpu_idle
0.03% swapper [kernel.kallsyms] [k] tasklet_action
0.03% swapper [kernel.kallsyms] [k] tick_nohz_stop_sched_tick
0.03% swapper [kernel.kallsyms] [k] ksize
0.03% swapper [kernel.kallsyms] [k] kmem_cache_free
0.03% swapper [kernel.kallsyms] [k] _find_next_bit_le
0.03% swapper [kernel.kallsyms] [k] ewma_add
0.03% swapper [kernel.kallsyms] [k] napi_complete
0.03% swapper [kernel.kallsyms] [k] dev_kfree_skb_any
0.03% swapper [cfg80211] [k] 0x391c
0.03% swapper [ath10k_pci] [k] ath10k_pci_hif_send_complete_check
0.03% swapper [ath10k_pci] [k] ath10k_pci_post_rx_pipe
0.03% swapper [ath10k_pci] [k] $a
0.03% swapper [ath10k_pci] [k] ath10k_ce_recv_buf_enqueue
0.03% swapper [ath10k_pci] [k] ath10k_ce_per_engine_service
0.03% swapper [ath10k_core] [k] ath10k_htc_rx_completion_handler
0.03% swapper [ath10k_core] [k] ath10k_htt_rx_free_msdu_chain
0.03% swapper [ath10k_core] [k] $a
0.03% swapper [ath10k_core] [k] ath10k_htt_txrx_compl_task
0.03% swapper [ath10k_core] [k] $a
0.03% swapper [ath10k_core] [k] $a
0.03% sh libc-2.13.so [.] 0x6c9e8
0.03% sh [mac80211] [k] sta_info_get
0.03% sh [mac80211] [k] ieee80211_netdev_select_queue
0.03% sh [mac80211] [k] $a
0.03% sh [mac80211] [k] $a
0.03% sh [mac80211] [k] $a
0.03% sh [mac80211] [k] ieee80211_rx
0.03% sh [mac80211] [k] invoke_tx_handlers
0.03% sh [mac80211] [k] __ieee80211_beacon_get
0.03% sh [mac80211] [k] ieee80211_subif_start_xmit
0.03% sh [mac80211] [k] ieee80211_get_bssid
0.03% sh [kernel.kallsyms] [k] vfp_reload_hw
0.03% sh [kernel.kallsyms] [k] flush_cache_range
0.03% sh [kernel.kallsyms] [k] release_task
0.03% sh [kernel.kallsyms] [k] __do_softirq
0.03% sh [kernel.kallsyms] [k] __perf_event_header__init_id
0.03% sh [kernel.kallsyms] [k] perf_event_mmap
0.03% sh [kernel.kallsyms] [k] find_get_page
0.03% sh [kernel.kallsyms] [k] get_pageblock_flags_group
0.03% sh [kernel.kallsyms] [k] get_page_from_freelist
0.03% sh [kernel.kallsyms] [k] lru_add_drain
0.03% sh [kernel.kallsyms] [k] next_zones_zonelist
0.03% sh [kernel.kallsyms] [k] free_pgd_range
0.03% sh [kernel.kallsyms] [k] unmap_vmas
0.03% sh [kernel.kallsyms] [k] handle_pte_fault
0.03% sh [kernel.kallsyms] [k] __vma_link_file
0.03% sh [kernel.kallsyms] [k] remove_vma
0.03% sh [kernel.kallsyms] [k] mmap_region
0.03% sh [kernel.kallsyms] [k] memblock_search
0.03% sh [kernel.kallsyms] [k] ksize
0.03% sh [kernel.kallsyms] [k] kmem_cache_free
0.03% sh [kernel.kallsyms] [k] kmem_cache_alloc
0.03% sh [kernel.kallsyms] [k] fget_light
0.03% sh [kernel.kallsyms] [k] unlazy_walk
0.03% sh [kernel.kallsyms] [k] follow_managed
0.03% sh [kernel.kallsyms] [k] prepend
0.03% sh [kernel.kallsyms] [k] __d_lookup_rcu
0.03% sh [kernel.kallsyms] [k] copy_page
0.03% sh [kernel.kallsyms] [k] _find_next_bit_le
0.03% sh [kernel.kallsyms] [k] __up_read
0.03% sh [kernel.kallsyms] [k] strlen
0.03% sh [kernel.kallsyms] [k] put_dec_trunc
0.03% sh [kernel.kallsyms] [k] ewma_add
0.03% sh [kernel.kallsyms] [k] extract_buf
0.03% sh [kernel.kallsyms] [k] skb_pull
0.03% sh [kernel.kallsyms] [k] skb_recycle
0.03% sh [kernel.kallsyms] [k] skb_push
0.03% sh [kernel.kallsyms] [k] skb_put
0.03% sh [kernel.kallsyms] [k] harmonize_features
0.03% sh [kernel.kallsyms] [k] netif_skb_features
0.03% sh [kernel.kallsyms] [k] sch_direct_xmit
0.03% sh [kernel.kallsyms] [k] tcp4_gro_receive
0.03% sh [kernel.kallsyms] [k] __br_fdb_get
0.03% sh [kernel.kallsyms] [k] br_dev_queue_push_xmit
0.03% sh [kernel.kallsyms] [k] __br_forward
0.03% sh [kernel.kallsyms] [k] br_nf_forward_arp
0.03% sh [kernel.kallsyms] [k] md5_transform
0.03% sh [kernel.kallsyms] [k] do_page_fault.part.8
0.03% sh [kernel.kallsyms] [k] do_page_fault
0.03% sh [cfg80211] [k] ieee80211_hdrlen
0.03% sh [ath10k_pci] [k] ath10k_pci_post_rx_pipe
0.03% sh [ath10k_pci] [k] ath10k_ce_send_nolock
0.03% sh [ath10k_core] [k] ath10k_htc_rx_completion_handler
0.03% sh [ath10k_core] [k] $a
0.03% sh [ath10k_core] [k] $a
0.03% sh [ath10k_core] [k] ath10k_htt_rx_h_protected.isra.16
0.03% sh [ath10k_core] [k] ath10k_htt_tx_free_msdu_id
0.03% rm libc-2.13.so [.] _dl_addr
0.03% rm [mac80211] [k] $a
0.03% rm [mac80211] [k] $a
0.03% rm [mac80211] [k] ieee80211_rx
0.03% rm [mac80211] [k] ieee80211_xmit
0.03% rm [mac80211] [k] $a
0.03% rm [mac80211] [k] ieee80211_set_qos_hdr
0.03% rm [kernel.kallsyms] [k] __sync_icache_dcache
0.03% rm [kernel.kallsyms] [k] tasklet_action
0.03% rm [kernel.kallsyms] [k] filemap_fault
0.03% rm [kernel.kallsyms] [k] release_pages
0.03% rm [kernel.kallsyms] [k] __do_fault
0.03% rm [kernel.kallsyms] [k] unmap_vmas
0.03% rm [kernel.kallsyms] [k] find_vma_prepare
0.03% rm [kernel.kallsyms] [k] do_munmap
0.03% rm [kernel.kallsyms] [k] memblock_search
0.03% rm [kernel.kallsyms] [k] dma_pool_free
0.03% rm [kernel.kallsyms] [k] kfree
0.03% rm [kernel.kallsyms] [k] kmem_cache_free
0.03% rm [kernel.kallsyms] [k] load_elf_binary
0.03% rm [kernel.kallsyms] [k] copy_page
0.03% rm [kernel.kallsyms] [k] radix_tree_lookup_slot
0.03% rm [kernel.kallsyms] [k] skb_recycle_check
0.03% rm [kernel.kallsyms] [k] __alloc_skb
0.03% rm [kernel.kallsyms] [k] dev_alloc_skb
0.03% rm [kernel.kallsyms] [k] netif_skb_features
0.03% rm [kernel.kallsyms] [k] dev_gro_receive
0.03% rm [kernel.kallsyms] [k] skb_gro_reset_offset
0.03% rm [kernel.kallsyms] [k] sch_direct_xmit
0.03% rm [kernel.kallsyms] [k] nf_hook_slow
0.03% rm [kernel.kallsyms] [k] tcp4_gro_receive
0.03% rm [kernel.kallsyms] [k] br_fdb_update
0.03% rm [kernel.kallsyms] [k] br_nf_post_routing
0.03% rm [kernel.kallsyms] [k] br_nf_forward_arp
0.03% rm [kernel.kallsyms] [k] br_nf_pre_routing
0.03% rm [kernel.kallsyms] [k] md5_transform
0.03% rm [kernel.kallsyms] [k] do_page_fault.part.8
0.03% rm [cfg80211] [k] ieee80211_hdrlen
0.03% rm [cfg80211] [k] cfg80211_classify8021d
0.03% rm [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.03% rm [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.03% rm [ath10k_core] [k] ath10k_htt_rx_msdu_buff_replenish
0.03% rm [ath10k_core] [k] ath10k_htt_tx_alloc_msdu_id
0.03% rm [ath10k_core] [k] $a
0.03% principal libc-2.13.so [.] _IO_fgets
0.03% principal [kernel.kallsyms] [k] dev_queue_xmit
0.03% principal [kernel.kallsyms] [k] eth_type_trans
0.03% principal [kernel.kallsyms] [k] nf_iterate
0.03% principal [ath10k_pci] [k] ath10k_ce_send_nolock
0.03% principal [ath10k_pci] [k] ath10k_ce_completed_send_next
0.03% monitor libc-2.13.so [.] strtol
0.03% monitor libc-2.13.so [.] _IO_vfscanf
0.03% monitor libc-2.13.so [.] _IO_setb
0.03% monitor libc-2.13.so [.] strcat
0.03% monitor libc-2.13.so [.] strlen
0.03% monitor libc-2.13.so [.] strpbrk
0.03% monitor libc-2.13.so [.] memchr
0.03% monitor libc-2.13.so [.] 0x339a4
0.03% monitor [mac80211] [k] ieee80211_report_used_skb
0.03% monitor [mac80211] [k] ieee80211_netdev_select_queue
0.03% monitor [mac80211] [k] ieee80211_deliver_skb
0.03% monitor [mac80211] [k] $a
0.03% monitor [mac80211] [k] ieee80211_rx
0.03% monitor [mac80211] [k] $a
0.03% monitor [mac80211] [k] $a
0.03% monitor [mac80211] [k] ieee80211_tx
0.03% monitor [kernel.kallsyms] [k] local_bh_disable
0.03% monitor [kernel.kallsyms] [k] local_bh_enable
0.03% monitor [kernel.kallsyms] [k] __init_waitqueue_head
0.03% monitor [kernel.kallsyms] [k] find_vma
0.03% monitor [kernel.kallsyms] [k] mmap_region
0.03% monitor [kernel.kallsyms] [k] unlink_anon_vmas
0.03% monitor [kernel.kallsyms] [k] dma_pool_alloc
0.03% monitor [kernel.kallsyms] [k] put_filp
0.03% monitor [kernel.kallsyms] [k] link_path_walk
0.03% monitor [kernel.kallsyms] [k] try_atomic_semop
0.03% monitor [kernel.kallsyms] [k] blk_finish_plug
0.03% monitor [kernel.kallsyms] [k] _test_and_set_bit
0.03% monitor [kernel.kallsyms] [k] mv_eth_skb_recycle
0.03% monitor [kernel.kallsyms] [k] skb_recycle_check
0.03% monitor [kernel.kallsyms] [k] __alloc_skb
0.03% monitor [kernel.kallsyms] [k] skb_put
0.03% monitor [kernel.kallsyms] [k] __netif_receive_skb
0.03% monitor [kernel.kallsyms] [k] eth_type_trans
0.03% monitor [kernel.kallsyms] [k] __br_fdb_get
0.03% monitor [kernel.kallsyms] [k] __br_forward
0.03% monitor [kernel.kallsyms] [k] br_handle_frame_finish
0.03% monitor [kernel.kallsyms] [k] br_nf_forward_ip
0.03% monitor [kernel.kallsyms] [k] br_nf_pre_routing
0.03% monitor [ath10k_pci] [k] ath10k_pci_ce_recv_data
0.03% monitor [ath10k_pci] [k] ath10k_pci_fw_interrupt_handler
0.03% monitor [ath10k_pci] [k] ath10k_ce_completed_send_next
0.03% monitor [ath10k_core] [k] ath10k_tx_htt
0.03% monitor [ath10k_core] [k] ath10k_tx
0.03% monitor [ath10k_core] [k] ath10k_htt_tx
0.03% modprobe libc-2.13.so [.] fclose
0.03% modprobe [mac80211] [k] sta_info_get
0.03% modprobe [mac80211] [k] ieee80211_frame_allowed
0.03% modprobe [mac80211] [k] ieee80211_rx_handlers_result
0.03% modprobe [mac80211] [k] ieee80211_rx_handlers
0.03% modprobe [mac80211] [k] $a
0.03% modprobe [mac80211] [k] $a
0.03% modprobe [mac80211] [k] ieee80211_tx_prepare
0.03% modprobe [mac80211] [k] invoke_tx_handlers
0.03% modprobe [mac80211] [k] ieee80211_select_queue
0.03% modprobe [kernel.kallsyms] [k] local_bh_disable
0.03% modprobe [kernel.kallsyms] [k] local_bh_enable
0.03% modprobe [kernel.kallsyms] [k] __wake_up_bit
0.03% modprobe [kernel.kallsyms] [k] up_read
0.03% modprobe [kernel.kallsyms] [k] generic_file_aio_read
0.03% modprobe [kernel.kallsyms] [k] get_page_from_freelist
0.03% modprobe [kernel.kallsyms] [k] mmap_region
0.03% modprobe [kernel.kallsyms] [k] __page_set_anon_rmap
0.03% modprobe [kernel.kallsyms] [k] anon_vma_clone
0.03% modprobe [kernel.kallsyms] [k] dma_pool_alloc
0.03% modprobe [kernel.kallsyms] [k] vfs_read
0.03% modprobe [kernel.kallsyms] [k] alloc_fd
0.03% modprobe [kernel.kallsyms] [k] seq_read
0.03% modprobe [kernel.kallsyms] [k] proc_root_lookup
0.03% modprobe [kernel.kallsyms] [k] copy_page
0.03% modprobe [kernel.kallsyms] [k] _find_first_zero_bit_le
0.03% modprobe [kernel.kallsyms] [k] mv_eth_select_txq
0.03% modprobe [kernel.kallsyms] [k] mv_eth_skb_recycle
0.03% modprobe [kernel.kallsyms] [k] skb_recycle
0.03% modprobe [kernel.kallsyms] [k] skb_put
0.03% modprobe [kernel.kallsyms] [k] harmonize_features
0.03% modprobe [kernel.kallsyms] [k] netif_skb_features
0.03% modprobe [kernel.kallsyms] [k] dev_gro_receive
0.03% modprobe [kernel.kallsyms] [k] dev_hard_start_xmit
0.03% modprobe [kernel.kallsyms] [k] sch_direct_xmit
0.03% modprobe [kernel.kallsyms] [k] nf_iterate
0.03% modprobe [kernel.kallsyms] [k] tcp4_gro_receive
0.03% modprobe [kernel.kallsyms] [k] inet_gro_receive
0.03% modprobe [kernel.kallsyms] [k] br_fdb_update
0.03% modprobe [kernel.kallsyms] [k] __br_forward
0.03% modprobe [kernel.kallsyms] [k] br_nf_forward_ip
0.03% modprobe [ath10k_pci] [k] ath10k_ce_per_engine_service_any
0.03% modprobe [ath10k_core] [k] $a
0.03% modprobe [ath10k_core] [k] ath10k_htt_tx_free_msdu_id
0.03% modprobe [ath10k_core] [k] ath10k_htt_tx
0.03% lighttpd [mac80211] [k] invoke_tx_handlers
0.03% lighttpd [mac80211] [k] ieee80211_select_queue
0.03% lighttpd [kernel.kallsyms] [k] cpu_pj4bv7_dcache_clean_area
0.03% lighttpd [kernel.kallsyms] [k] local_bh_disable
0.03% lighttpd [kernel.kallsyms] [k] __do_softirq
0.03% lighttpd [kernel.kallsyms] [k] anon_vma_fork
0.03% lighttpd [kernel.kallsyms] [k] generic_drop_inode
0.03% lighttpd [kernel.kallsyms] [k] __copy_from_user
0.03% lighttpd [kernel.kallsyms] [k] _find_next_bit_le
0.03% lighttpd [kernel.kallsyms] [k] mv_eth_tx
0.03% lighttpd [kernel.kallsyms] [k] __netif_receive_skb
0.03% lighttpd [kernel.kallsyms] [k] br_handle_frame_finish
0.03% lighttpd [kernel.kallsyms] [k] br_handle_frame
0.03% lighttpd [kernel.kallsyms] [k] mutex_unlock
0.03% lighttpd [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.03% kworker/u:2 [mac80211] [k] sta_info_get
0.03% kworker/u:2 [mac80211] [k] $a
0.03% kworker/u:2 [mac80211] [k] ieee80211_tx_prepare
0.03% kworker/u:2 [mac80211] [k] $a
0.03% kworker/u:2 [mac80211] [k] ieee80211_tx
0.03% kworker/u:2 [mac80211] [k] $a
0.03% kworker/u:2 [mac80211] [k] $a
0.03% kworker/u:2 [mac80211] [k] ieee80211_set_qos_hdr
0.03% kworker/u:2 [kernel.kallsyms] [k] _find_first_zero_bit_le
0.03% kworker/u:2 [kernel.kallsyms] [k] memmove
0.03% kworker/u:2 [kernel.kallsyms] [k] mv_eth_select_txq
0.03% kworker/u:2 [kernel.kallsyms] [k] mv_eth_skb_recycle
0.03% kworker/u:2 [kernel.kallsyms] [k] __kfree_skb
0.03% kworker/u:2 [kernel.kallsyms] [k] skb_recycle
0.03% kworker/u:2 [kernel.kallsyms] [k] skb_push
0.03% kworker/u:2 [kernel.kallsyms] [k] dev_hard_start_xmit
0.03% kworker/u:2 [kernel.kallsyms] [k] nf_iterate
0.03% kworker/u:2 [kernel.kallsyms] [k] nf_hook_slow
0.03% kworker/u:2 [kernel.kallsyms] [k] br_handle_frame_finish
0.03% kworker/u:2 [kernel.kallsyms] [k] br_nf_pre_routing
0.03% kworker/u:2 [kernel.kallsyms] [k] schedule
0.03% kworker/u:2 [cfg80211] [k] cfg80211_classify8021d
0.03% kworker/u:2 [ath10k_pci] [k] ath10k_ce_send_nolock
0.03% kworker/u:2 [ath10k_pci] [k] ath10k_ce_completed_send_next
0.03% kworker/u:2 [ath10k_core] [k] ath10k_tx
0.03% kworker/u:2 [ath10k_core] [k] $a
0.03% ksoftirqd/0 [mac80211] [k] ieee80211_tx_h_michael_mic_add
0.03% ksoftirqd/0 [mac80211] [k] ieee80211_frame_allowed
0.03% ksoftirqd/0 [mac80211] [k] invoke_tx_handlers
0.03% ksoftirqd/0 [mac80211] [k] $a
0.03% ksoftirqd/0 [mac80211] [k] $a
0.03% ksoftirqd/0 [kernel.kallsyms] [k] local_bh_disable
0.03% ksoftirqd/0 [kernel.kallsyms] [k] local_bh_enable
0.03% ksoftirqd/0 [kernel.kallsyms] [k] __free_pages_ok
0.03% ksoftirqd/0 [kernel.kallsyms] [k] dma_pool_free
0.03% ksoftirqd/0 [kernel.kallsyms] [k] file_free_rcu
0.03% ksoftirqd/0 [kernel.kallsyms] [k] _find_next_bit_le
0.03% ksoftirqd/0 [kernel.kallsyms] [k] memmove
0.03% ksoftirqd/0 [kernel.kallsyms] [k] mv_eth_skb_recycle
0.03% ksoftirqd/0 [kernel.kallsyms] [k] __alloc_skb
0.03% ksoftirqd/0 [kernel.kallsyms] [k] skb_put
0.03% ksoftirqd/0 [kernel.kallsyms] [k] harmonize_features
0.03% ksoftirqd/0 [kernel.kallsyms] [k] netif_receive_skb
0.03% ksoftirqd/0 [kernel.kallsyms] [k] napi_gro_receive
0.03% ksoftirqd/0 [kernel.kallsyms] [k] nf_hook_slow
0.03% ksoftirqd/0 [kernel.kallsyms] [k] br_fdb_update
0.03% ksoftirqd/0 [kernel.kallsyms] [k] br_handle_frame
0.03% ksoftirqd/0 [kernel.kallsyms] [k] br_nf_post_routing
0.03% ksoftirqd/0 [kernel.kallsyms] [k] br_nf_forward_arp
0.03% ksoftirqd/0 [kernel.kallsyms] [k] br_nf_forward_ip
0.03% ksoftirqd/0 [kernel.kallsyms] [k] __schedule
0.03% ksoftirqd/0 [cfg80211] [k] ieee80211_data_to_8023
0.03% ksoftirqd/0 [cfg80211] [k] cfg80211_classify8021d
0.03% ksoftirqd/0 [ath10k_pci] [k] ath10k_pci_ce_recv_data
0.03% ksoftirqd/0 [ath10k_pci] [k] 0x2ed0
0.03% ksoftirqd/0 [ath10k_core] [k] $a
0.03% ksoftirqd/0 [ath10k_core] [k] ath10k_htt_tx_alloc_msdu_id
0.03% ksoftirqd/0 [ath10k_core] [k] ath10k_htt_tx
0.03% ksoftirqd/0 [ath10k_core] [k] ath10k_txrx_tx_unref
0.03% jdb [mac80211] [k] ieee80211_tx_status
0.03% jdb [mac80211] [k] sta_info_get
0.03% jdb [mac80211] [k] $a
0.03% jdb [kernel.kallsyms] [k] kfree
0.03% jdb [kernel.kallsyms] [k] mv_eth_tx
0.03% jdb [kernel.kallsyms] [k] mv_eth_poll
0.03% jdb [kernel.kallsyms] [k] inet_gro_receive
0.03% jdb [kernel.kallsyms] [k] br_handle_frame_finish
0.03% jdb [cfg80211] [k] ieee80211_hdrlen
0.03% jdb [ath10k_core] [k] $a
0.03% iw libnl-3.so.200.19.0 [.] _init
0.03% iw libnl-3.so.200.19.0 [.] nla_get_u16
0.03% iw libnl-3.so.200.19.0 [.] nl_recvmsgs_report
0.03% iw libc-2.13.so [.] vfprintf
0.03% iw libc-2.13.so [.] strchr
0.03% iw libc-2.13.so [.] _dl_addr
0.03% iw ld-2.13.so [.] __libc_memalign
0.03% iw busybox [.] 0x2f844
0.03% iw [mac80211] [k] ieee80211_deliver_skb
0.03% iw [mac80211] [k] $a
0.03% iw [mac80211] [k] ieee80211_rx
0.03% iw [mac80211] [k] ieee80211_skb_resize
0.03% iw [mac80211] [k] $a
0.03% iw [mac80211] [k] ieee80211_select_queue
0.03% iw [kernel.kallsyms] [k] pfn_valid
0.03% iw [kernel.kallsyms] [k] cpu_pj4bv7_set_pte_ext
0.03% iw [kernel.kallsyms] [k] put_pid
0.03% iw [kernel.kallsyms] [k] __wake_up_bit
0.03% iw [kernel.kallsyms] [k] filemap_fault
0.03% iw [kernel.kallsyms] [k] free_hot_cold_page
0.03% iw [kernel.kallsyms] [k] lru_add_drain
0.03% iw [kernel.kallsyms] [k] unmap_vmas
0.03% iw [kernel.kallsyms] [k] kmem_cache_alloc
0.03% iw [kernel.kallsyms] [k] __dentry_open.isra.13
0.03% iw [kernel.kallsyms] [k] path_init
0.03% iw [kernel.kallsyms] [k] inode_has_buffers
0.03% iw [kernel.kallsyms] [k] copy_page
0.03% iw [kernel.kallsyms] [k] memmove
0.03% iw [kernel.kallsyms] [k] radix_tree_lookup_element
0.03% iw [kernel.kallsyms] [k] __rb_rotate_left
0.03% iw [kernel.kallsyms] [k] __down_read_trylock
0.03% iw [kernel.kallsyms] [k] __up_read
0.03% iw [kernel.kallsyms] [k] mv_eth_skb_recycle
0.03% iw [kernel.kallsyms] [k] consume_skb
0.03% iw [kernel.kallsyms] [k] skb_recycle
0.03% iw [kernel.kallsyms] [k] skb_trim
0.03% iw [kernel.kallsyms] [k] skb_push
0.03% iw [kernel.kallsyms] [k] memcpy_toiovec
0.03% iw [kernel.kallsyms] [k] netif_receive_skb
0.03% iw [kernel.kallsyms] [k] inet_gro_receive
0.03% iw [kernel.kallsyms] [k] br_forward_finish
0.03% iw [kernel.kallsyms] [k] __br_forward
0.03% iw [kernel.kallsyms] [k] br_nf_pre_routing
0.03% iw [kernel.kallsyms] [k] md5_transform
0.03% iw [kernel.kallsyms] [k] do_page_fault.part.8
0.03% iw [kernel.kallsyms] [k] do_page_fault
0.03% iw [ath10k_pci] [k] ath10k_pci_tasklet
0.03% iw [ath10k_core] [k] ath10k_tx
0.03% iw [ath10k_core] [k] ath10k_htt_rx_replenish_task
0.03% iw [ath10k_core] [k] ath10k_htt_tx_free_msdu_id
0.03% iw [ath10k_core] [k] ath10k_htt_tx
0.03% hostapd libc-2.13.so [.] vsnprintf
0.03% grep busybox [.] 0x2e944
0.03% grep [mac80211] [k] ieee80211_report_used_skb
0.03% grep [mac80211] [k] ieee80211_tx_h_michael_mic_add
0.03% grep [mac80211] [k] ieee80211_rx_handlers
0.03% grep [mac80211] [k] $a
0.03% grep [mac80211] [k] ieee80211_rx
0.03% grep [mac80211] [k] ieee80211_tx_prepare
0.03% grep [mac80211] [k] $a
0.03% grep [kernel.kallsyms] [k] sys_mmap2
0.03% grep [kernel.kallsyms] [k] local_bh_disable
0.03% grep [kernel.kallsyms] [k] filemap_fault
0.03% grep [kernel.kallsyms] [k] handle_pte_fault
0.03% grep [kernel.kallsyms] [k] dma_pool_free
0.03% grep [kernel.kallsyms] [k] extract_buf
0.03% grep [kernel.kallsyms] [k] mv_eth_skb_recycle
0.03% grep [kernel.kallsyms] [k] mv_eth_poll
0.03% grep [kernel.kallsyms] [k] __kfree_skb
0.03% grep [kernel.kallsyms] [k] __alloc_skb
0.03% grep [kernel.kallsyms] [k] skb_put
0.03% grep [kernel.kallsyms] [k] dev_gro_receive
0.03% grep [kernel.kallsyms] [k] eth_type_trans
0.03% grep [kernel.kallsyms] [k] nf_iterate
0.03% grep [kernel.kallsyms] [k] br_forward_finish
0.03% grep [kernel.kallsyms] [k] br_handle_frame_finish
0.03% grep [kernel.kallsyms] [k] ret_from_exception
0.03% grep [kernel.kallsyms] [k] do_page_fault.part.8
0.03% grep [ath10k_pci] [k] ath10k_pci_fw_interrupt_handler
0.03% grep [ath10k_core] [k] $a
0.03% grep [ath10k_core] [k] ath10k_htt_tx
0.03% egrep libc-2.13.so [.] strchr
0.03% egrep libc-2.13.so [.] __libc_fork
0.03% egrep [mac80211] [k] ieee80211_tx_h_michael_mic_add
0.03% egrep [mac80211] [k] ieee80211_rx_handlers
0.03% egrep [mac80211] [k] $a
0.03% egrep [mac80211] [k] ieee80211_rx
0.03% egrep [mac80211] [k] invoke_tx_handlers
0.03% egrep [mac80211] [k] ieee80211_tx
0.03% egrep [mac80211] [k] $a
0.03% egrep [mac80211] [k] ieee80211_set_qos_hdr
0.03% egrep [kernel.kallsyms] [k] __sync_icache_dcache
0.03% egrep [kernel.kallsyms] [k] lru_cache_add_lru
0.03% egrep [kernel.kallsyms] [k] handle_pte_fault
0.03% egrep [kernel.kallsyms] [k] handle_mm_fault
0.03% egrep [kernel.kallsyms] [k] kfree
0.03% egrep [kernel.kallsyms] [k] __kmalloc_track_caller
0.03% egrep [kernel.kallsyms] [k] __d_lookup
0.03% egrep [kernel.kallsyms] [k] fsnotify
0.03% egrep [kernel.kallsyms] [k] locks_remove_flock
0.03% egrep [kernel.kallsyms] [k] memmove
0.03% egrep [kernel.kallsyms] [k] extract_buf
0.03% egrep [kernel.kallsyms] [k] __kfree_skb
0.03% egrep [kernel.kallsyms] [k] __alloc_skb
0.03% egrep [kernel.kallsyms] [k] __netif_receive_skb
0.03% egrep [kernel.kallsyms] [k] dev_gro_receive
0.03% egrep [kernel.kallsyms] [k] __br_forward
0.03% egrep [kernel.kallsyms] [k] br_nf_pre_routing
0.03% egrep [cfg80211] [k] ieee80211_data_to_8023
0.03% egrep [cfg80211] [k] cfg80211_classify8021d
0.03% egrep [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.03% egrep [ath10k_core] [k] ath10k_tx
0.03% cut busybox [.] 0x3dd8
0.03% cut [mac80211] [k] ieee80211_deliver_skb
0.03% cut [mac80211] [k] $a
0.03% cut [mac80211] [k] $a
0.03% cut [mac80211] [k] ieee80211_tx_prepare
0.03% cut [mac80211] [k] invoke_tx_handlers
0.03% cut [mac80211] [k] ieee80211_subif_start_xmit
0.03% cut [kernel.kallsyms] [k] v6_clear_user_highpage_nonaliasing
0.03% cut [kernel.kallsyms] [k] local_bh_disable
0.03% cut [kernel.kallsyms] [k] __do_softirq
0.03% cut [kernel.kallsyms] [k] __do_fault
0.03% cut [kernel.kallsyms] [k] sys_brk
0.03% cut [kernel.kallsyms] [k] memblock_search
0.03% cut [kernel.kallsyms] [k] dma_pool_alloc
0.03% cut [kernel.kallsyms] [k] kfree
0.03% cut [kernel.kallsyms] [k] __kmalloc_track_caller
0.03% cut [kernel.kallsyms] [k] file_update_time
0.03% cut [kernel.kallsyms] [k] touch_atime
0.03% cut [kernel.kallsyms] [k] copy_page
0.03% cut [kernel.kallsyms] [k] _find_first_zero_bit_le
0.03% cut [kernel.kallsyms] [k] memmove
0.03% cut [kernel.kallsyms] [k] radix_tree_lookup_element
0.03% cut [kernel.kallsyms] [k] __kfree_skb
0.03% cut [kernel.kallsyms] [k] skb_recycle
0.03% cut [kernel.kallsyms] [k] harmonize_features
0.03% cut [kernel.kallsyms] [k] net_rx_action
0.03% cut [kernel.kallsyms] [k] dev_gro_receive
0.03% cut [kernel.kallsyms] [k] napi_gro_receive
0.03% cut [kernel.kallsyms] [k] eth_type_trans
0.03% cut [kernel.kallsyms] [k] inet_gro_receive
0.03% cut [kernel.kallsyms] [k] __br_forward
0.03% cut [kernel.kallsyms] [k] br_nf_forward_arp
0.03% cut [cfg80211] [k] ieee80211_hdrlen
0.03% cut [cfg80211] [k] ieee80211_data_to_8023
0.03% cut [ath10k_pci] [k] ath10k_pci_ce_recv_data
0.03% cut [ath10k_pci] [k] ath10k_ce_send_nolock
0.03% cut [ath10k_pci] [k] ath10k_ce_completed_send_next
0.03% cut [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.03% cut [ath10k_core] [k] $a
0.03% cgi_fh libc-2.13.so [.] vfprintf
0.03% cgi_fh libc-2.13.so [.] strpbrk
0.03% cgi_fh cgi_fh [.] 0x4077c
0.03% cgi_fh [mac80211] [k] ieee80211_rx_handlers
0.03% cgi_fh [mac80211] [k] $a
0.03% cgi_fh [mac80211] [k] $a
0.03% cgi_fh [mac80211] [k] ieee80211_rx
0.03% cgi_fh [mac80211] [k] ieee80211_tx_prepare
0.03% cgi_fh [kernel.kallsyms] [k] tasklet_action
0.03% cgi_fh [kernel.kallsyms] [k] local_bh_disable
0.03% cgi_fh [kernel.kallsyms] [k] local_bh_enable
0.03% cgi_fh [kernel.kallsyms] [k] mmap_region
0.03% cgi_fh [kernel.kallsyms] [k] ptep_clear_flush
0.03% cgi_fh [kernel.kallsyms] [k] __kmalloc
0.03% cgi_fh [kernel.kallsyms] [k] path_put
0.03% cgi_fh [kernel.kallsyms] [k] do_last.isra.35
0.03% cgi_fh [kernel.kallsyms] [k] mntput
0.03% cgi_fh [kernel.kallsyms] [k] cap_vm_enough_memory
0.03% cgi_fh [kernel.kallsyms] [k] copy_page
0.03% cgi_fh [kernel.kallsyms] [k] _find_first_zero_bit_le
0.03% cgi_fh [kernel.kallsyms] [k] __strnlen_user
0.03% cgi_fh [kernel.kallsyms] [k] mv_eth_skb_recycle
0.03% cgi_fh [kernel.kallsyms] [k] mv_eth_tx
0.03% cgi_fh [kernel.kallsyms] [k] __kfree_skb
0.03% cgi_fh [kernel.kallsyms] [k] skb_recycle
0.03% cgi_fh [kernel.kallsyms] [k] skb_push
0.03% cgi_fh [kernel.kallsyms] [k] __netif_receive_skb
0.03% cgi_fh [kernel.kallsyms] [k] dev_gro_receive
0.03% cgi_fh [kernel.kallsyms] [k] napi_gro_receive
0.03% cgi_fh [kernel.kallsyms] [k] dev_hard_start_xmit
0.03% cgi_fh [kernel.kallsyms] [k] nf_iterate
0.03% cgi_fh [kernel.kallsyms] [k] tcp4_gro_receive
0.03% cgi_fh [kernel.kallsyms] [k] inet_gro_receive
0.03% cgi_fh [kernel.kallsyms] [k] __br_fdb_get
0.03% cgi_fh [kernel.kallsyms] [k] __br_forward
0.03% cgi_fh [kernel.kallsyms] [k] br_handle_frame
0.03% cgi_fh [kernel.kallsyms] [k] do_page_fault.part.8
0.03% cgi_fh [cfg80211] [k] ieee80211_hdrlen
0.03% cgi_fh [cfg80211] [k] ieee80211_data_to_8023
0.03% cgi_fh [ath10k_pci] [k] ath10k_pci_tasklet
0.03% cgi_fh [ath10k_pci] [k] ath10k_ce_send_nolock
0.03% cgi_fh [ath10k_core] [k] ath10k_tx
0.03% cgi_fh [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.03% cgi_fh [ath10k_core] [k] $a
0.03% cgi_fh [ath10k_core] [k] ath10k_htt_tx
0.03% cgi_fh [ath10k_core] [k] ath10k_txrx_tx_unref
0.03% :15092 [kernel.kallsyms] [k] nf_iterate
0.03% :15058 [kernel.kallsyms] [k] do_exit
0.03% :15010 [kernel.kallsyms] [k] mv_eth_poll
0.03% :14673 [kernel.kallsyms] [k] do_exit
0.03% :14645 [kernel.kallsyms] [k] nf_iterate
0.03% :14641 [ath10k_pci] [k] ath10k_ce_send_nolock
0.03% :14503 [kernel.kallsyms] [k] kmem_cache_alloc
0.03% :14474 [kernel.kallsyms] [k] memcpy
[-- Attachment #3: sta.txt --]
[-- Type: text/plain, Size: 39675 bytes --]
3.82% swapper [kernel.kallsyms] [k] armadaxp_enter_idle
2.18% ksoftirqd/0 [kernel.kallsyms] [k] memcpy
1.48% ksoftirqd/0 [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
1.33% ksoftirqd/0 [mac80211] [k] ieee80211_rx
1.25% ksoftirqd/0 [kernel.kallsyms] [k] kfree
1.25% ksoftirqd/0 [kernel.kallsyms] [k] mv_eth_tx
1.01% ksoftirqd/0 [kernel.kallsyms] [k] dev_queue_xmit
1.01% ksoftirqd/0 [ath10k_core] [k] $a
0.94% kworker/u:1 [kernel.kallsyms] [k] __delay
0.86% iw ld-2.13.so [.] 0x63a8
0.70% swapper [kernel.kallsyms] [k] __memzero
0.70% swapper [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.70% ksoftirqd/0 [mac80211] [k] ieee80211_rx_handlers
0.70% ksoftirqd/0 [kernel.kallsyms] [k] mv_eth_poll
0.70% ksoftirqd/0 [kernel.kallsyms] [k] __netif_receive_skb
0.70% ksoftirqd/0 [ath10k_pci] [k] ath10k_ce_completed_send_next
0.62% swapper [kernel.kallsyms] [k] memcpy
0.62% swapper [kernel.kallsyms] [k] dev_queue_xmit
0.62% ksoftirqd/0 [mac80211] [k] ieee80211_tx_status
0.62% ksoftirqd/0 [kernel.kallsyms] [k] ip_finish_output
0.55% swapper [mac80211] [k] ieee80211_rx_handlers
0.55% sh ld-2.13.so [.] 0x9758
0.55% sh [kernel.kallsyms] [k] memcpy
0.55% ksoftirqd/0 [kernel.kallsyms] [k] __kmalloc_track_caller
0.55% ksoftirqd/0 [kernel.kallsyms] [k] dev_hard_start_xmit
0.55% ksoftirqd/0 [cfg80211] [k] ieee80211_data_to_802--More--3
0.47% swapper [mac80211] [k] $a
0.47% swapper [kernel.kallsyms] [k] __netif_receive_skb
0.47% sh [kernel.kallsyms] [k] kfree
0.47% sh [ath10k_core] [k] $a
0.47% modprobe [kernel.kallsyms] [k] mv_eth_tx
0.47% ksoftirqd/0 [mac80211] [k] ieee80211_tx_prepare
0.47% ksoftirqd/0 [mac80211] [k] $a
0.47% ksoftirqd/0 [kernel.kallsyms] [k] local_bh_enable
0.47% ksoftirqd/0 [kernel.kallsyms] [k] __memzero
0.47% ksoftirqd/0 [kernel.kallsyms] [k] __kfree_skb
0.47% ksoftirqd/0 [kernel.kallsyms] [k] consume_skb
0.47% ksoftirqd/0 [kernel.kallsyms] [k] sch_direct_xmit
0.47% ksoftirqd/0 [kernel.kallsyms] [k] ip_rcv_finish
0.47% ksoftirqd/0 [kernel.kallsyms] [k] ip_output
0.47% ksoftirqd/0 [cfg80211] [k] ieee80211_hdrlen
0.47% iw [mac80211] [k] ieee80211_rx
0.39% wc [kernel.kallsyms] [k] mv_eth_tx
0.39% swapper [mac80211] [k] ieee80211_rx
0.39% swapper [kernel.kallsyms] [k] __do_softirq
0.39% sh [mac80211] [k] ieee80211_rx
0.39% sh [kernel.kallsyms] [k] __memzero
0.39% sh [kernel.kallsyms] [k] mv_eth_tx
0.39% sh [kernel.kallsyms] [k] dev_queue_xmit
0.39% ksoftirqd/0 [mac80211] [k] $a
0.39% ksoftirqd/0 [mac80211] [k] $a
0.39% ksoftirqd/0 [kernel.kallsyms] [k] local_bh_disable
0.39% ksoftirqd/0 [kernel.kallsyms] [k] skb_put
0.39% ksoftirqd/0 [kernel.kallsyms] [k] nf_iterate
0.39% ksoftirqd/0 [kernel.kallsyms] [k] ip_rcv
0.39% ksoftirqd/0 [ath10k_pci] [k] ath10k_pci_ce_recv_data
0.39% ksoftirqd/0 [ath10k_pci] [k] ath10k_pci_tasklet
0.39% iw [kernel.kallsyms] [k] memcpy
0.39% iw [kernel.kallsyms] [k] __netif_receive_skb
0.31% swapper [mac80211] [k] $a
0.31% swapper [kernel.kallsyms] [k] mv_eth_tx
0.31% swapper [kernel.kallsyms] [k] skb_put
0.31% swapper [kernel.kallsyms] [k] ip_rcv_finish
0.31% swapper [ath10k_pci] [k] ath10k_ce_completed_send_next
0.31% sh [mac80211] [k] ieee80211_tx_prepare
0.31% sh [kernel.kallsyms] [k] ip_forward
0.31% sh [ath10k_pci] [k] ath10k_pci_fw_interrupt_handler
0.31% sh [ath10k_pci] [k] ath10k_ce_completed_send_next
0.31% monitor [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.31% modprobe [mac80211] [k] ieee80211_rx_handlers
0.31% kworker/u:1 [kernel.kallsyms] [k] kfree
0.31% kworker/u:1 [kernel.kallsyms] [k] __kmalloc_track_caller
0.31% ksoftirqd/0 [mac80211] [k] ieee80211_prepare_and_rx_handle
0.31% ksoftirqd/0 [mac80211] [k] $a
0.31% ksoftirqd/0 [mac80211] [k] ieee80211_set_qos_hdr
0.31% ksoftirqd/0 [kernel.kallsyms] [k] ksize
0.31% ksoftirqd/0 [kernel.kallsyms] [k] __alloc_skb
0.31% ksoftirqd/0 [kernel.kallsyms] [k] skb_push
0.31% ksoftirqd/0 [kernel.kallsyms] [k] ip_route_input_common
0.31% ksoftirqd/0 [ath10k_pci] [k] ath10k_ce_send_nolock
0.23% swapper [mac80211] [k] $a
0.23% swapper [kernel.kallsyms] [k] local_bh_disable
0.23% swapper [kernel.kallsyms] [k] tick_nohz_stop_sched_tick
0.23% swapper [kernel.kallsyms] [k] __kmalloc_track_caller
0.23% swapper [kernel.kallsyms] [k] __kfree_skb
0.23% swapper [kernel.kallsyms] [k] dev_hard_start_xmit
0.23% swapper [kernel.kallsyms] [k] ip_rcv
0.23% swapper [cfg80211] [k] ieee80211_data_to_8023
0.23% swapper [ath10k_pci] [k] ath10k_pci_ce_recv_data
0.23% swapper [ath10k_pci] [k] ath10k_ce_send_nolock
0.23% swapper [ath10k_core] [k] $a
0.23% sh [mac80211] [k] $a
0.23% sh [mac80211] [k] $a
0.23% sh [kernel.kallsyms] [k] __kmalloc_track_caller
0.23% sh [kernel.kallsyms] [k] __kfree_skb
0.23% sh [kernel.kallsyms] [k] ip_rcv
0.23% sh [kernel.kallsyms] [k] ip_output
0.23% rm [kernel.kallsyms] [k] __memzero
0.23% modprobe libc-2.13.so [.] _IO_getc
0.23% modprobe [mac80211] [k] ieee80211_tx_prepare
0.23% modprobe [kernel.kallsyms] [k] dev_queue_xmit
0.23% modprobe [ath10k_pci] [k] ath10k_ce_completed_send_next
0.23% modprobe [ath10k_core] [k] $a
0.23% kworker/u:1 [mac80211] [k] ieee80211_tx_status
0.23% kworker/u:1 [kernel.kallsyms] [k] dev_queue_xmit
0.23% ksoftirqd/0 [mac80211] [k] $a
0.23% ksoftirqd/0 [mac80211] [k] invoke_tx_handlers
0.23% ksoftirqd/0 [mac80211] [k] ieee80211_get_bssid
0.23% ksoftirqd/0 [kernel.kallsyms] [k] kmem_cache_alloc
0.23% ksoftirqd/0 [kernel.kallsyms] [k] __aeabi_uidiv
0.23% ksoftirqd/0 [kernel.kallsyms] [k] ewma_add
0.23% ksoftirqd/0 [kernel.kallsyms] [k] skb_pull
0.23% ksoftirqd/0 [kernel.kallsyms] [k] netif_receive_skb
0.23% ksoftirqd/0 [kernel.kallsyms] [k] eth_type_trans
0.23% ksoftirqd/0 [kernel.kallsyms] [k] nf_hook_slow
0.23% ksoftirqd/0 [kernel.kallsyms] [k] ipv4_validate_peer
0.23% ksoftirqd/0 [kernel.kallsyms] [k] ip_forward
0.23% ksoftirqd/0 [ath10k_core] [k] ath10k_tx
0.23% ksoftirqd/0 [ath10k_core] [k] ath10k_htt_tx
0.23% iw [mac80211] [k] ieee80211_tx_status
0.23% iw [mac80211] [k] ieee80211_rx_handlers
0.23% iw [mac80211] [k] $a
0.23% iw [kernel.kallsyms] [k] __kmalloc_track_caller
0.23% iw [kernel.kallsyms] [k] ip_forward
0.23% iw [cfg80211] [k] ieee80211_hdrlen
0.23% egrep libc-2.13.so [.] _dl_addr
0.23% egrep [kernel.kallsyms] [k] local_bh_enable
0.23% egrep [ath10k_core] [k] $a
0.16% wc ld-2.13.so [.] 0x94a8
0.16% wc busybox [.] 0x4e04
0.16% wc [kernel.kallsyms] [k] __alloc_skb
0.16% wc [ath10k_pci] [k] ath10k_ce_completed_send_next
0.16% swapper [mac80211] [k] ieee80211_tx_status
0.16% swapper [mac80211] [k] ieee80211_prepare_and_rx_handle
0.16% swapper [mac80211] [k] ieee80211_tx
0.16% swapper [kernel.kallsyms] [k] local_bh_enable
0.16% swapper [kernel.kallsyms] [k] round_jiffies_up
0.16% swapper [kernel.kallsyms] [k] ewma_add
0.16% swapper [kernel.kallsyms] [k] mv_eth_poll
0.16% swapper [kernel.kallsyms] [k] dev_alloc_skb
0.16% swapper [kernel.kallsyms] [k] dev_gro_receive
0.16% swapper [kernel.kallsyms] [k] eth_type_trans
0.16% swapper [kernel.kallsyms] [k] ipv4_validate_peer
0.16% swapper [kernel.kallsyms] [k] ip_forward
0.16% swapper [ath10k_pci] [k] ath10k_pci_fw_interrupt_handler
0.16% swapper [ath10k_pci] [k] ath10k_pci_tasklet
0.16% swapper [ath10k_pci] [k] ath10k_ce_per_engine_service_any
0.16% sh libc-2.13.so [.] _dl_addr
0.16% sh [mac80211] [k] ieee80211_tx_status
0.16% sh [mac80211] [k] ieee80211_rx_handlers
0.16% sh [mac80211] [k] $a
0.16% sh [kernel.kallsyms] [k] local_bh_enable
0.16% sh [kernel.kallsyms] [k] mod_timer
0.16% sh [kernel.kallsyms] [k] __wake_up_bit
0.16% sh [kernel.kallsyms] [k] mv_eth_poll
0.16% sh [kernel.kallsyms] [k] skb_put
0.16% sh [kernel.kallsyms] [k] __netif_receive_skb
0.16% sh [kernel.kallsyms] [k] ip_route_input_common
0.16% sh [kernel.kallsyms] [k] ip_finish_output
0.16% sh [cfg80211] [k] ieee80211_hdrlen
0.16% sh [cfg80211] [k] ieee80211_data_to_8023
0.16% sh [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.16% sh [ath10k_core] [k] ath10k_txrx_tx_unref
0.16% rm libc-2.13.so [.] _dl_addr
0.16% rm ld-2.13.so [.] 0x188f0
0.16% rm [mac80211] [k] ieee80211_rx
0.16% rm [kernel.kallsyms] [k] mv_eth_tx
0.16% rm [ath10k_core] [k] $a
0.16% monitor [kernel.kallsyms] [k] memcpy
0.16% monitor [kernel.kallsyms] [k] __netif_receive_skb
0.16% modprobe libc-2.13.so [.] 0x6bbf8
0.16% modprobe ld-2.13.so [.] 0x971c
0.16% modprobe [kernel.kallsyms] [k] dev_hard_start_xmit
0.16% modprobe [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.16% lighttpd [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.16% kworker/u:1 [kernel.kallsyms] [k] memcpy
0.16% kworker/u:1 [ath10k_pci] [k] ath10k_ce_completed_send_next
0.16% kworker/u:1 [ath10k_core] [k] ath10k_txrx_tx_unref
0.16% ksoftirqd/0 [mac80211] [k] ieee80211_get_mmie_keyidx
0.16% ksoftirqd/0 [mac80211] [k] remove_monitor_info
0.16% ksoftirqd/0 [mac80211] [k] ieee80211_rx_handlers_result
0.16% ksoftirqd/0 [mac80211] [k] ieee80211_sta_reset_conn_monitor
0.16% ksoftirqd/0 [kernel.kallsyms] [k] msecs_to_jiffies
0.16% ksoftirqd/0 [kernel.kallsyms] [k] tasklet_action
0.16% ksoftirqd/0 [kernel.kallsyms] [k] mod_timer
0.16% ksoftirqd/0 [kernel.kallsyms] [k] dma_pool_alloc
0.16% ksoftirqd/0 [kernel.kallsyms] [k] kmem_cache_free
0.16% ksoftirqd/0 [kernel.kallsyms] [k] net_rx_action
0.16% ksoftirqd/0 [kernel.kallsyms] [k] napi_gro_receive
0.16% ksoftirqd/0 [kernel.kallsyms] [k] ipv4_mtu
0.16% ksoftirqd/0 [kernel.kallsyms] [k] ip_forward_finish
0.16% ksoftirqd/0 [ath10k_pci] [k] $a
0.16% ksoftirqd/0 [ath10k_core] [k] ath10k_htc_rx_completion_handler
0.16% ksoftirqd/0 [ath10k_core] [k] ath10k_htt_rx_get_csum_state
0.16% ksoftirqd/0 [ath10k_core] [k] $a
0.16% ksoftirqd/0 [ath10k_core] [k] $a
0.16% iw [mac80211] [k] $a
0.16% iw [kernel.kallsyms] [k] local_bh_enable
0.16% iw [kernel.kallsyms] [k] __kfree_skb
0.16% iw [kernel.kallsyms] [k] skb_put
0.16% iw [kernel.kallsyms] [k] dev_gro_receive
0.16% iw [kernel.kallsyms] [k] dev_hard_start_xmit
0.16% iw [kernel.kallsyms] [k] dev_queue_xmit
0.16% iw [ath10k_pci] [k] ath10k_ce_per_engine_service_any
0.16% iw [ath10k_core] [k] $a
0.16% egrep [kernel.kallsyms] [k] __do_fault
0.16% egrep [kernel.kallsyms] [k] mv_eth_tx
0.16% egrep [kernel.kallsyms] [k] skb_put
0.16% cgi_fh [mac80211] [k] ieee80211_tx
0.08% wpa_supplicant [mac80211] [k] $a
0.08% wc libc-2.13.so [.] _IO_file_close_it
0.08% wc libc-2.13.so [.] _dl_addr
0.08% wc [mac80211] [k] ieee80211_frame_allowed
0.08% wc [mac80211] [k] remove_monitor_info
0.08% wc [kernel.kallsyms] [k] local_bh_disable
0.08% wc [kernel.kallsyms] [k] local_bh_enable
0.08% wc [kernel.kallsyms] [k] mod_timer
0.08% wc [kernel.kallsyms] [k] perf_output_begin
0.08% wc [kernel.kallsyms] [k] handle_pte_fault
0.08% wc [kernel.kallsyms] [k] dma_pool_alloc
0.08% wc [kernel.kallsyms] [k] kfree
0.08% wc [kernel.kallsyms] [k] path_lookupat
0.08% wc [kernel.kallsyms] [k] memcpy
0.08% wc [kernel.kallsyms] [k] __up_read
0.08% wc [kernel.kallsyms] [k] mv_eth_poll
0.08% wc [kernel.kallsyms] [k] __kfree_skb
0.08% wc [kernel.kallsyms] [k] net_rx_action
0.08% wc [kernel.kallsyms] [k] dev_queue_xmit
0.08% wc [kernel.kallsyms] [k] nf_hook_slow
0.08% wc [kernel.kallsyms] [k] ipv4_mtu
0.08% wc [kernel.kallsyms] [k] ip_route_input_common
0.08% wc [kernel.kallsyms] [k] ip_forward
0.08% wc [kernel.kallsyms] [k] md5_transform
0.08% wc [cfg80211] [k] ieee80211_hdrlen
0.08% wc [cfg80211] [k] ieee80211_data_to_8023
0.08% wc [ath10k_pci] [k] ath10k_ce_send_nolock
0.08% wc [ath10k_core] [k] $a
0.08% touch libc-2.13.so [.] strcmp
0.08% touch [mac80211] [k] ieee80211_deliver_skb
0.08% touch [mac80211] [k] ieee80211_get_bssid
0.08% touch [kernel.kallsyms] [k] local_bh_enable
0.08% touch [kernel.kallsyms] [k] kmem_cache_free
0.08% touch [kernel.kallsyms] [k] memcpy
0.08% touch [kernel.kallsyms] [k] netif_receive_skb
0.08% touch [kernel.kallsyms] [k] dev_gro_receive
0.08% touch [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.08% swapper [mac80211] [k] ieee80211_netdev_select_queue
0.08% swapper [mac80211] [k] ieee80211_deliver_skb
0.08% swapper [mac80211] [k] $a
0.08% swapper [mac80211] [k] $a
0.08% swapper [mac80211] [k] $a
0.08% swapper [mac80211] [k] ieee80211_set_qos_hdr
0.08% swapper [mac80211] [k] 0x1e4c4
0.08% swapper [kernel.kallsyms] [k] tasklet_action
0.08% swapper [kernel.kallsyms] [k] round_jiffies_common
0.08% swapper [kernel.kallsyms] [k] mod_timer
0.08% swapper [kernel.kallsyms] [k] dma_pool_alloc
0.08% swapper [kernel.kallsyms] [k] kfree
0.08% swapper [kernel.kallsyms] [k] kmem_cache_free
0.08% swapper [kernel.kallsyms] [k] __aeabi_uidiv
0.08% swapper [kernel.kallsyms] [k] find_last_bit
0.08% swapper [kernel.kallsyms] [k] skb_recycle_check
0.08% swapper [kernel.kallsyms] [k] skb_push
0.08% swapper [kernel.kallsyms] [k] netif_receive_skb
0.08% swapper [kernel.kallsyms] [k] dev_kfree_skb_any
0.08% swapper [kernel.kallsyms] [k] nf_iterate
0.08% swapper [kernel.kallsyms] [k] nf_hook_slow
0.08% swapper [kernel.kallsyms] [k] ipv4_mtu
0.08% swapper [kernel.kallsyms] [k] ip_finish_output
0.08% swapper [kernel.kallsyms] [k] ip_output
0.08% swapper [kernel.kallsyms] [k] inet_gro_receive
0.08% swapper [cfg80211] [k] ieee80211_hdrlen
0.08% swapper [cfg80211] [k] 0x3210
0.08% swapper [ath10k_pci] [k] ath10k_pci_ce_send_done
0.08% swapper [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.08% swapper [ath10k_pci] [k] ath10k_pci_post_rx_pipe
0.08% swapper [ath10k_core] [k] ath10k_tx
0.08% swapper [ath10k_core] [k] ath10k_htc_rx_completion_handler
0.08% swapper [ath10k_core] [k] ath10k_htt_rx_get_csum_state
0.08% swapper [ath10k_core] [k] $a
0.08% swapper [ath10k_core] [k] ath10k_txrx_tx_unref
0.08% sh libc-2.13.so [.] memcpy
0.08% sh libc-2.13.so [.] strchrnul
0.08% sh busybox [.] 0x34604
0.08% sh [mac80211] [k] ieee80211_netdev_select_queue
0.08% sh [mac80211] [k] $a
0.08% sh [mac80211] [k] ieee80211_prepare_and_rx_handle
0.08% sh [mac80211] [k] $a
0.08% sh [mac80211] [k] ieee80211_xmit
0.08% sh [mac80211] [k] ieee80211_get_bssid
0.08% sh [mac80211] [k] ieee80211_set_qos_hdr
0.08% sh [mac80211] [k] ieee80211_sta_reset_conn_monitor
0.08% sh [mac80211] [k] ieee80211_sta_rx_notify
0.08% sh [kernel.kallsyms] [k] __sync_icache_dcache
0.08% sh [kernel.kallsyms] [k] __new_context
0.08% sh [kernel.kallsyms] [k] mmput
0.08% sh [kernel.kallsyms] [k] timespec_trunc
0.08% sh [kernel.kallsyms] [k] local_bh_disable
0.08% sh [kernel.kallsyms] [k] __do_softirq
0.08% sh [kernel.kallsyms] [k] pid_nr_ns
0.08% sh [kernel.kallsyms] [k] perf_event_task
0.08% sh [kernel.kallsyms] [k] get_page_from_freelist
0.08% sh [kernel.kallsyms] [k] __alloc_pages_nodemask
0.08% sh [kernel.kallsyms] [k] __lru_cache_add
0.08% sh [kernel.kallsyms] [k] lru_cache_add_lru
0.08% sh [kernel.kallsyms] [k] __pte_alloc
0.08% sh [kernel.kallsyms] [k] do_wp_page.isra.74
0.08% sh [kernel.kallsyms] [k] free_pages_and_swap_cache
0.08% sh [kernel.kallsyms] [k] kmem_cache_free
0.08% sh [kernel.kallsyms] [k] kmem_cache_alloc
0.08% sh [kernel.kallsyms] [k] filp_close
0.08% sh [kernel.kallsyms] [k] do_last.isra.35
0.08% sh [kernel.kallsyms] [k] touch_atime
0.08% sh [kernel.kallsyms] [k] copy_page
0.08% sh [kernel.kallsyms] [k] __aeabi_uidiv
0.08% sh [kernel.kallsyms] [k] memmove
0.08% sh [kernel.kallsyms] [k] skb_recycle_check
0.08% sh [kernel.kallsyms] [k] netif_skb_features
0.08% sh [kernel.kallsyms] [k] skb_dst_set_noref
0.08% sh [kernel.kallsyms] [k] nf_iterate
0.08% sh [kernel.kallsyms] [k] ipv4_validate_peer
0.08% sh [kernel.kallsyms] [k] inet_gro_receive
0.08% sh [kernel.kallsyms] [k] md5_transform
0.08% sh [kernel.kallsyms] [k] down_read
0.08% sh [ath10k_pci] [k] ath10k_pci_ce_recv_data
0.08% sh [ath10k_pci] [k] ath10k_pci_tasklet
0.08% sh [ath10k_core] [k] ath10k_tx
0.08% sh [ath10k_core] [k] $a
0.08% rm [mac80211] [k] $a
0.08% rm [mac80211] [k] invoke_tx_handlers
0.08% rm [mac80211] [k] ieee80211_sta_reset_conn_monitor
0.08% rm [kernel.kallsyms] [k] mod_timer
0.08% rm [kernel.kallsyms] [k] find_vma
0.08% rm [kernel.kallsyms] [k] __vma_link_file
0.08% rm [kernel.kallsyms] [k] do_mmap_pgoff
0.08% rm [kernel.kallsyms] [k] kfree
0.08% rm [kernel.kallsyms] [k] mv_eth_poll
0.08% rm [kernel.kallsyms] [k] consume_skb
0.08% rm [kernel.kallsyms] [k] __alloc_skb
0.08% rm [kernel.kallsyms] [k] skb_put
0.08% rm [kernel.kallsyms] [k] dev_kfree_skb_any
0.08% rm [kernel.kallsyms] [k] ip_route_input_common
0.08% rm [kernel.kallsyms] [k] ip_rcv
0.08% rm [cfg80211] [k] ieee80211_hdrlen
0.08% rm [ath10k_pci] [k] ath10k_pci_ce_recv_data
0.08% rm [ath10k_pci] [k] ath10k_pci_tasklet
0.08% rm [ath10k_core] [k] ath10k_htt_rx_msdu_buff_replenish
0.08% rm [ath10k_core] [k] ath10k_htt_rx_h_protected.isra.16
0.08% rm [ath10k_core] [k] $a
0.08% principal [mac80211] [k] ieee80211_rx_h_michael_mic_verify
0.08% principal [kernel.kallsyms] [k] do_smart_update
0.08% principal [kernel.kallsyms] [k] memcpy
0.08% principal [ath10k_pci] [k] ath10k_ce_completed_send_next
0.08% monitor libc-2.13.so [.] memchr
0.08% monitor libc-2.13.so [.] __rawmemchr
0.08% monitor [mac80211] [k] ieee80211_deliver_skb
0.08% monitor [mac80211] [k] ieee80211_rx
0.08% monitor [mac80211] [k] ieee80211_get_bssid
0.08% monitor [kernel.kallsyms] [k] __kunmap_atomic
0.08% monitor [kernel.kallsyms] [k] release_task
0.08% monitor [kernel.kallsyms] [k] local_bh_disable
0.08% monitor [kernel.kallsyms] [k] local_bh_enable
0.08% monitor [kernel.kallsyms] [k] round_jiffies_up
0.08% monitor [kernel.kallsyms] [k] get_signal_to_deliver
0.08% monitor [kernel.kallsyms] [k] unlink_anon_vmas
0.08% monitor [kernel.kallsyms] [k] kfree
0.08% monitor [kernel.kallsyms] [k] free_fdtable_rcu
0.08% monitor [kernel.kallsyms] [k] __aeabi_uidiv
0.08% monitor [kernel.kallsyms] [k] skb_trim
0.08% monitor [kernel.kallsyms] [k] harmonize_features
0.08% monitor [ath10k_pci] [k] ath10k_ce_recv_buf_enqueue
0.08% monitor [ath10k_core] [k] $a
0.08% monitor [ath10k_core] [k] ath10k_htt_tx
0.08% modprobe libc-2.13.so [.] malloc
0.08% modprobe libc-2.13.so [.] realloc
0.08% modprobe libc-2.13.so [.] strchr
0.08% modprobe libc-2.13.so [.] memcpy
0.08% modprobe busybox [.] 0x6bd08
0.08% modprobe [mac80211] [k] ieee80211_tx_status
0.08% modprobe [mac80211] [k] $a
0.08% modprobe [mac80211] [k] ieee80211_rx
0.08% modprobe [mac80211] [k] $a
0.08% modprobe [mac80211] [k] $a
0.08% modprobe [kernel.kallsyms] [k] local_bh_enable
0.08% modprobe [kernel.kallsyms] [k] round_jiffies_up
0.08% modprobe [kernel.kallsyms] [k] filemap_fault
0.08% modprobe [kernel.kallsyms] [k] __alloc_pages_nodemask
0.08% modprobe [kernel.kallsyms] [k] expand_downwards
0.08% modprobe [kernel.kallsyms] [k] ksize
0.08% modprobe [kernel.kallsyms] [k] kmem_cache_free
0.08% modprobe [kernel.kallsyms] [k] kmem_cache_alloc
0.08% modprobe [kernel.kallsyms] [k] __d_lookup_rcu
0.08% modprobe [kernel.kallsyms] [k] copy_page
0.08% modprobe [kernel.kallsyms] [k] __aeabi_uidiv
0.08% modprobe [kernel.kallsyms] [k] memcpy
0.08% modprobe [kernel.kallsyms] [k] __memzero
0.08% modprobe [kernel.kallsyms] [k] mv_eth_select_txq
0.08% modprobe [kernel.kallsyms] [k] skb_push
0.08% modprobe [kernel.kallsyms] [k] skb_put
0.08% modprobe [kernel.kallsyms] [k] __netif_receive_skb
0.08% modprobe [kernel.kallsyms] [k] eth_type_trans
0.08% modprobe [kernel.kallsyms] [k] ip_rcv
0.08% modprobe [kernel.kallsyms] [k] ip_forward
0.08% modprobe [kernel.kallsyms] [k] ip_output
0.08% modprobe [kernel.kallsyms] [k] do_page_fault.part.8
0.08% modprobe [cfg80211] [k] ieee80211_data_to_8023
0.08% modprobe [ath10k_pci] [k] ath10k_ce_send_nolock
0.08% modprobe [ath10k_pci] [k] ath10k_ce_per_engine_service_any
0.08% modprobe [ath10k_core] [k] ath10k_tx
0.08% modprobe [ath10k_core] [k] ath10k_htc_rx_completion_handler
0.08% modprobe [ath10k_core] [k] $a
0.08% modprobe [ath10k_core] [k] $a
0.08% lighttpd [mac80211] [k] ieee80211_tx_status
0.08% lighttpd [mac80211] [k] ieee80211_rx
0.08% lighttpd [kernel.kallsyms] [k] kfree
0.08% lighttpd [kernel.kallsyms] [k] __kmalloc_track_caller
0.08% lighttpd [kernel.kallsyms] [k] kmem_cache_alloc
0.08% lighttpd [kernel.kallsyms] [k] do_sys_poll
0.08% lighttpd [kernel.kallsyms] [k] memcpy
0.08% lighttpd [kernel.kallsyms] [k] __memzero
0.08% lighttpd [kernel.kallsyms] [k] rb_insert_color
0.08% lighttpd [kernel.kallsyms] [k] __netif_receive_skb
0.08% lighttpd [kernel.kallsyms] [k] netif_receive_skb
0.08% lighttpd [kernel.kallsyms] [k] dev_gro_receive
0.08% lighttpd [kernel.kallsyms] [k] ip_local_deliver_finish
0.08% lighttpd [kernel.kallsyms] [k] ip_forward
0.08% lighttpd [kernel.kallsyms] [k] ip_finish_output
0.08% kworker/u:2 [kernel.kallsyms] [k] dev_hard_start_xmit
0.08% kworker/u:1 [mac80211] [k] ieee80211_netdev_select_queue
0.08% kworker/u:1 [mac80211] [k] ieee80211_deliver_skb
0.08% kworker/u:1 [mac80211] [k] $a
0.08% kworker/u:1 [mac80211] [k] ieee80211_prepare_and_rx_handle
0.08% kworker/u:1 [mac80211] [k] ieee80211_rx
0.08% kworker/u:1 [mac80211] [k] ieee80211_tx_prepare
0.08% kworker/u:1 [mac80211] [k] ieee80211_rx_mgmt_beacon
0.08% kworker/u:1 [kernel.kallsyms] [k] msecs_to_jiffies
0.08% kworker/u:1 [kernel.kallsyms] [k] kmem_cache_free
0.08% kworker/u:1 [kernel.kallsyms] [k] kmem_cache_alloc
0.08% kworker/u:1 [kernel.kallsyms] [k] __memzero
0.08% kworker/u:1 [kernel.kallsyms] [k] mvsd_request
0.08% kworker/u:1 [kernel.kallsyms] [k] __kfree_skb
0.08% kworker/u:1 [kernel.kallsyms] [k] dev_alloc_skb
0.08% kworker/u:1 [kernel.kallsyms] [k] harmonize_features
0.08% kworker/u:1 [kernel.kallsyms] [k] dev_gro_receive
0.08% kworker/u:1 [kernel.kallsyms] [k] dev_hard_start_xmit
0.08% kworker/u:1 [kernel.kallsyms] [k] nf_hook_slow
0.08% kworker/u:1 [kernel.kallsyms] [k] ip_route_input_common
0.08% kworker/u:1 [kernel.kallsyms] [k] ip_rcv
0.08% kworker/u:1 [cfg80211] [k] ieee80211_hdrlen
0.08% kworker/u:1 [cfg80211] [k] ieee80211_data_to_8023
0.08% kworker/u:1 [ath10k_core] [k] $a
0.08% ksoftirqd/0 [mac80211] [k] sta_info_get
0.08% ksoftirqd/0 [mac80211] [k] ieee80211_rx_h_michael_mic_verify
0.08% ksoftirqd/0 [mac80211] [k] ieee80211_netdev_select_queue
0.08% ksoftirqd/0 [mac80211] [k] ieee80211_deliver_skb
0.08% ksoftirqd/0 [mac80211] [k] $a
0.08% ksoftirqd/0 [mac80211] [k] $a
0.08% ksoftirqd/0 [mac80211] [k] ieee80211_tx
0.08% ksoftirqd/0 [mac80211] [k] ieee80211_xmit
0.08% ksoftirqd/0 [mac80211] [k] ieee80211_subif_start_xmit
0.08% ksoftirqd/0 [mac80211] [k] ieee80211_downgrade_queue.isra.1
0.08% ksoftirqd/0 [mac80211] [k] ieee80211_select_queue
0.08% ksoftirqd/0 [mac80211] [k] $a
0.08% ksoftirqd/0 [kernel.kallsyms] [k] vfp_notifier
0.08% ksoftirqd/0 [kernel.kallsyms] [k] __do_softirq
0.08% ksoftirqd/0 [kernel.kallsyms] [k] run_ksoftirqd
0.08% ksoftirqd/0 [kernel.kallsyms] [k] round_jiffies_common
0.08% ksoftirqd/0 [kernel.kallsyms] [k] round_jiffies_up
0.08% ksoftirqd/0 [kernel.kallsyms] [k] memmove
0.08% ksoftirqd/0 [kernel.kallsyms] [k] mv_eth_select_txq
0.08% ksoftirqd/0 [kernel.kallsyms] [k] mv_eth_skb_recycle
0.08% ksoftirqd/0 [kernel.kallsyms] [k] skb_recycle
0.08% ksoftirqd/0 [kernel.kallsyms] [k] skb_recycle_check
0.08% ksoftirqd/0 [kernel.kallsyms] [k] dev_alloc_skb
0.08% ksoftirqd/0 [kernel.kallsyms] [k] dev_gro_receive
0.08% ksoftirqd/0 [kernel.kallsyms] [k] skb_gro_reset_offset
0.08% ksoftirqd/0 [kernel.kallsyms] [k] skb_dst_set_noref
0.08% ksoftirqd/0 [kernel.kallsyms] [k] inet_gro_receive
0.08% ksoftirqd/0 [kernel.kallsyms] [k] __schedule
0.08% ksoftirqd/0 [cfg80211] [k] cfg80211_classify8021d
0.08% ksoftirqd/0 [ath10k_pci] [k] ath10k_pci_ce_send_done
0.08% ksoftirqd/0 [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.08% ksoftirqd/0 [ath10k_pci] [k] ath10k_pci_fw_interrupt_handler
0.08% ksoftirqd/0 [ath10k_pci] [k] ath10k_ce_per_engine_service
0.08% ksoftirqd/0 [ath10k_pci] [k] 0x3384
0.08% ksoftirqd/0 [ath10k_core] [k] $a
0.08% ksoftirqd/0 [ath10k_core] [k] $a
0.08% ksoftirqd/0 [ath10k_core] [k] ath10k_htt_txrx_compl_task
0.08% ksoftirqd/0 [ath10k_core] [k] $a
0.08% ksoftirqd/0 [ath10k_core] [k] 0x76d4
0.08% iw libc-2.13.so [.] __libc_calloc
0.08% iw libc-2.13.so [.] _dl_addr
0.08% iw libc-2.13.so [.] 0x32124
0.08% iw [mac80211] [k] ieee80211_rx_h_michael_mic_verify
0.08% iw [mac80211] [k] ieee80211_tx_prepare
0.08% iw [mac80211] [k] ieee80211_tx
0.08% iw [mac80211] [k] ieee80211_subif_start_xmit
0.08% iw [kernel.kallsyms] [k] __sync_icache_dcache
0.08% iw [kernel.kallsyms] [k] v6_clear_user_highpage_nonaliasing
0.08% iw [kernel.kallsyms] [k] v7wbi_flush_user_tlb_range
0.08% iw [kernel.kallsyms] [k] msecs_to_jiffies
0.08% iw [kernel.kallsyms] [k] down_read_trylock
0.08% iw [kernel.kallsyms] [k] local_clock
0.08% iw [kernel.kallsyms] [k] filemap_fault
0.08% iw [kernel.kallsyms] [k] __do_fault
0.08% iw [kernel.kallsyms] [k] dma_pool_alloc
0.08% iw [kernel.kallsyms] [k] kfree
0.08% iw [kernel.kallsyms] [k] kmem_cache_alloc
0.08% iw [kernel.kallsyms] [k] get_empty_filp
0.08% iw [kernel.kallsyms] [k] __aeabi_uidiv
0.08% iw [kernel.kallsyms] [k] __aeabi_uidivmod
0.08% iw [kernel.kallsyms] [k] mv_eth_tx
0.08% iw [kernel.kallsyms] [k] sock_recvmsg
0.08% iw [kernel.kallsyms] [k] skb_pull
0.08% iw [kernel.kallsyms] [k] consume_skb
0.08% iw [kernel.kallsyms] [k] skb_push
0.08% iw [kernel.kallsyms] [k] harmonize_features
0.08% iw [kernel.kallsyms] [k] netif_receive_skb
0.08% iw [kernel.kallsyms] [k] skb_gro_reset_offset
0.08% iw [kernel.kallsyms] [k] dev_kfree_skb_any
0.08% iw [kernel.kallsyms] [k] eth_type_trans
0.08% iw [kernel.kallsyms] [k] nf_hook_slow
0.08% iw [kernel.kallsyms] [k] ip_route_input_common
0.08% iw [kernel.kallsyms] [k] ip_rcv
0.08% iw [kernel.kallsyms] [k] ip_output
0.08% iw [kernel.kallsyms] [k] ip_sabotage_in
0.08% iw [kernel.kallsyms] [k] __schedule
0.08% iw [kernel.kallsyms] [k] do_page_fault.part.8
0.08% iw [cfg80211] [k] ieee80211_data_to_8023
0.08% iw [cfg80211] [k] cfg80211_classify8021d
0.08% iw [ath10k_pci] [k] ath10k_pci_fw_interrupt_handler
0.08% iw [ath10k_pci] [k] ath10k_ce_send_nolock
0.08% iw [ath10k_pci] [k] ath10k_ce_recv_buf_enqueue
0.08% iw [ath10k_core] [k] ath10k_tx
0.08% iw [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.08% grep ld-2.13.so [.] 0xfc24
0.08% grep [kernel.kallsyms] [k] mod_timer
0.08% grep [kernel.kallsyms] [k] memblock_is_memory
0.08% grep [kernel.kallsyms] [k] kmem_cache_alloc
0.08% grep [kernel.kallsyms] [k] memcpy
0.08% grep [kernel.kallsyms] [k] __kfree_skb
0.08% grep [kernel.kallsyms] [k] dev_queue_xmit
0.08% grep [kernel.kallsyms] [k] eth_type_trans
0.08% grep [kernel.kallsyms] [k] ipv4_validate_peer
0.08% grep [kernel.kallsyms] [k] ip_rcv
0.08% grep [ath10k_pci] [k] ath10k_pci_ce_recv_data
0.08% grep [ath10k_core] [k] $a
0.08% egrep ld-2.13.so [.] 0x9b14
0.08% egrep [mac80211] [k] ieee80211_get_mmie_keyidx
0.08% egrep [mac80211] [k] ieee80211_rx_handlers_result
0.08% egrep [mac80211] [k] ieee80211_rx_handlers
0.08% egrep [mac80211] [k] $a
0.08% egrep [mac80211] [k] $a
0.08% egrep [mac80211] [k] $a
0.08% egrep [mac80211] [k] ieee80211_sta_reset_conn_monitor
0.08% egrep [kernel.kallsyms] [k] mod_timer
0.08% egrep [kernel.kallsyms] [k] rw_verify_area
0.08% egrep [kernel.kallsyms] [k] __memzero
0.08% egrep [kernel.kallsyms] [k] radix_tree_lookup_element
0.08% egrep [kernel.kallsyms] [k] __down_read_trylock
0.08% egrep [kernel.kallsyms] [k] mv_eth_skb_recycle
0.08% egrep [kernel.kallsyms] [k] __kfree_skb
0.08% egrep [kernel.kallsyms] [k] __alloc_skb
0.08% egrep [kernel.kallsyms] [k] dev_hard_start_xmit
0.08% egrep [kernel.kallsyms] [k] nf_hook_slow
0.08% egrep [kernel.kallsyms] [k] ip_forward_finish
0.08% egrep [kernel.kallsyms] [k] ip_finish_output
0.08% egrep [kernel.kallsyms] [k] ip_output
0.08% egrep [kernel.kallsyms] [k] do_page_fault.part.8
0.08% egrep [ath10k_pci] [k] ath10k_pci_hif_tx_sg
0.08% egrep [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
0.08% egrep [ath10k_core] [k] ath10k_htt_tx
0.08% cut [mac80211] [k] ieee80211_rx
0.08% cut [kernel.kallsyms] [k] local_bh_enable
0.08% cut [kernel.kallsyms] [k] do_sync_read
0.08% cut [kernel.kallsyms] [k] memset
0.08% cut [kernel.kallsyms] [k] dev_kfree_skb_any
0.08% cut [kernel.kallsyms] [k] ip_route_input_common
0.08% cut [kernel.kallsyms] [k] do_page_fault.part.8
0.08% cut [cfg80211] [k] ieee80211_hdrlen
0.08% cut [cfg80211] [k] ieee80211_data_to_8023
0.08% cut [ath10k_core] [k] $a
0.08% cgi_fh libc-2.13.so [.] putchar
0.08% cgi_fh ld-2.13.so [.] 0x9abc
0.08% cgi_fh [mac80211] [k] ieee80211_tx_status
0.08% cgi_fh [mac80211] [k] ieee80211_rx_handlers
0.08% cgi_fh [kernel.kallsyms] [k] current_kernel_time
0.08% cgi_fh [kernel.kallsyms] [k] perf_event_mmap_output
0.08% cgi_fh [kernel.kallsyms] [k] filemap_fault
0.08% cgi_fh [kernel.kallsyms] [k] __kmalloc
0.08% cgi_fh [kernel.kallsyms] [k] expand_files
0.08% cgi_fh [kernel.kallsyms] [k] __memzero
0.08% cgi_fh [kernel.kallsyms] [k] skb_put
0.08% cgi_fh [kernel.kallsyms] [k] eth_type_trans
0.08% cgi_fh [kernel.kallsyms] [k] do_page_fault.part.8
0.08% cgi_fh [ath10k_core] [k] $a
0.08% :2577 [mac80211] [k] $a
0.08% :2532 [ath10k_core] [k] ath10k_htt_rx_amsdu_pop
[-- Attachment #4: Type: text/plain, Size: 146 bytes --]
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-08-18 9:45 ` Vu Hai NGUYEN
@ 2014-08-19 18:26 ` Ben Greear
2014-08-20 14:13 ` Vu Hai NGUYEN
0 siblings, 1 reply; 30+ messages in thread
From: Ben Greear @ 2014-08-19 18:26 UTC (permalink / raw)
To: Vu Hai NGUYEN
Cc: Patrick CARNEIRO RODRIGUEZ, Adrian Chadd, Michal Kazior,
ath10k@lists.infradead.org, Bartosz Markowski
On 08/18/2014 02:45 AM, Vu Hai NGUYEN wrote:
> I'd cleaned all rules of iptables and removed all modules of iptables from kernel by command modprobe -r
> But there's still some process of netfilter process running. I disabled netfilter on bridge interface by writing 0 to these files:
> /proc/sys/net/bridge/bridge-nf-call-arptables
> /proc/sys/net/bridge/bridge-nf-call-iptables
> /proc/sys/net/bridge/bridge-nf-call-ip6tables
>
> and the performance increases from 500 to 550 Mbps (iperf in tcp reports between 530 ~ 570Mbps).
> There is no more process like "br_nf_pre_routing" and "br_nf_forward_ip".
> Do you think I can do anything more to strip down netfilter?
What do you get for UDP? That seems like pretty good TCP throughput.
Also, do you get different results if you use Open v/s WPA2 encryption?
A test I just ran showed decreased performance on one of my systems
when I ran with open v/s wpa2 (400Mbps v/s 350Mbps, UDP goodput).
This was using hardware-crypt, so I expected it to be as fast as Open.
I'm running customized firmware and driver, so maybe that is cause of
slowdown...curious what results others are seeing though!
> I installed tc from package iproute2 and did : tc qdisc but it doesn't improve the performance
> One more question: Could the antennas create any effect on the MCS in use?
> We are using this antenna from PCTEL:
> http://www.antenna.com/apg_products.cgi?id_num=11395
> And in the specification, I saw that it supports the standard 802.11n, so may be this is the reason
> that the best rate for me is MCS7?
Antenna and orientation matter, but the one you list advertises itself
as dual-band, so it looks like it should work well in the 5Ghz band
that AC uses.
You might try changing orientation and/or trying some different
antenna.
Thanks,
Ben
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-08-19 18:26 ` Ben Greear
@ 2014-08-20 14:13 ` Vu Hai NGUYEN
2014-08-20 14:51 ` Kalle Valo
0 siblings, 1 reply; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-08-20 14:13 UTC (permalink / raw)
To: Ben Greear
Cc: Patrick CARNEIRO RODRIGUEZ, Adrian Chadd, Michal Kazior,
ath10k@lists.infradead.org, Bartosz Markowski
>> I'd cleaned all rules of iptables and removed all modules of iptables from kernel by command modprobe -r
>> But there's still some process of netfilter process running. I disabled netfilter on bridge interface by writing 0 to these files:
>> /proc/sys/net/bridge/bridge-nf-call-arptables
>> /proc/sys/net/bridge/bridge-nf-call-iptables
>> /proc/sys/net/bridge/bridge-nf-call-ip6tables
>>
>> and the performance increases from 500 to 550 Mbps (iperf in tcp reports between 530 ~ 570Mbps).
>> There is no more process like "br_nf_pre_routing" and "br_nf_forward_ip".
>> Do you think I can do anything more to strip down netfilter?
>What do you get for UDP? That seems like pretty good TCP throughput.
In VHT80 mode and rate forced to NSS3:MCS7, I can obtain 750 Mbps with less than 1% data lost (in both way, AP to STA and vice versa).
Normally I can obtain 2/3 theory rate in practical (for expl NSS3:MCS3 has 390 Mbps in theory, and if I force to that rate, my TCP throughput
is around 270 Mbps). So I should obtain 650 Mbps in practical for TCP with NSS3:MCS7 (975 Mbps in theory).
570 Mbps is so far to 650 Mbps :(
>Also, do you get different results if you use Open v/s WPA2 encryption?
>A test I just ran showed decreased performance on one of my systems
>when I ran with open v/s wpa2 (400Mbps v/s 350Mbps, UDP goodput).
>This was using hardware-crypt, so I expected it to be as fast as Open.
>I'm running customized firmware and driver, so maybe that is cause of
>slowdown...curious what results others are seeing though!
In my case, I don't get much differences between Open vs WPA2 encryption, rate is almost the same (different around 10 ~ 20 Mbps and hard to see)
>> I installed tc from package iproute2 and did : tc qdisc but it doesn't improve the performance
>> One more question: Could the antennas create any effect on the MCS in use?
>> We are using this antenna from PCTEL:
>> http://www.antenna.com/apg_products.cgi?id_num=11395
>> And in the specification, I saw that it supports the standard 802.11n, so may be this is the reason
>> that the best rate for me is MCS7?
>Antenna and orientation matter, but the one you list advertises itself
>as dual-band, so it looks like it should work well in the 5Ghz band
>that AC uses.
>You might try changing orientation and/or trying some different antenna.
That antenna has 6 access so I connect my AP and STA to that antenna, it means
that they are very close to each other. I've tried to connect my STA with others 3 smalls
antennas dual band (http://www.senetic.fr/product/AIR-ANT2524DB-R?gclid=Cj0KEQjwjtGfBRCN4-LU9ODG1-wBEiQAy_Xp73JtC1W_cG1EyI_mft_OrR5qBD_qqDzslQMB8BMaXQQaAkAq8P8HAQ)
and change direction but the rate I obtain is much lower, I can not reach high throughput as above.
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-08-20 14:13 ` Vu Hai NGUYEN
@ 2014-08-20 14:51 ` Kalle Valo
2014-08-21 12:23 ` Vu Hai NGUYEN
0 siblings, 1 reply; 30+ messages in thread
From: Kalle Valo @ 2014-08-20 14:51 UTC (permalink / raw)
To: Vu Hai NGUYEN
Cc: Adrian Chadd, ath10k@lists.infradead.org, Michal Kazior,
Patrick CARNEIRO RODRIGUEZ, Ben Greear, Bartosz Markowski
Vu Hai NGUYEN <vh.nguyen@actiasodielec.fr> writes:
>>> I'd cleaned all rules of iptables and removed all modules of
>>> iptables from kernel by command modprobe -r But there's still some
>>> process of netfilter process running. I disabled netfilter on
>>> bridge interface by writing 0 to these files:
>>> /proc/sys/net/bridge/bridge-nf-call-arptables
>>> /proc/sys/net/bridge/bridge-nf-call-iptables
>>> /proc/sys/net/bridge/bridge-nf-call-ip6tables
>>> and the performance increases from 500 to 550 Mbps (iperf in tcp
>>> reports between 530 ~ 570Mbps). There is no more process like
>>> "br_nf_pre_routing" and "br_nf_forward_ip". Do you think I can do
>>> anything more to strip down netfilter?
>
>>What do you get for UDP? That seems like pretty good TCP throughput.
>
> In VHT80 mode and rate forced to NSS3:MCS7, I can obtain 750 Mbps with
> less than 1% data lost (in both way, AP to STA and vice versa).
> Normally I can obtain 2/3 theory rate in practical (for expl NSS3:MCS3
> has 390 Mbps in theory, and if I force to that rate, my TCP throughput
> is around 270 Mbps). So I should obtain 650 Mbps in practical for TCP
> with NSS3:MCS7 (975 Mbps in theory). 570 Mbps is so far to 650 Mbps :(
Forcing the data rate isn't really optimal. Have you tried 10.2
firmware? I was told it has improvements in the rate control algorithm.
--
Kalle Valo
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-08-20 14:51 ` Kalle Valo
@ 2014-08-21 12:23 ` Vu Hai NGUYEN
2014-08-21 12:41 ` Michal Kazior
0 siblings, 1 reply; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-08-21 12:23 UTC (permalink / raw)
To: Kalle Valo
Cc: Adrian Chadd, ath10k@lists.infradead.org, Michal Kazior,
Patrick CARNEIRO RODRIGUEZ, Ben Greear, Bartosz Markowski
>>>What do you get for UDP? That seems like pretty good TCP throughput.
>> In VHT80 mode and rate forced to NSS3:MCS7, I can obtain 750 Mbps with
>> less than 1% data lost (in both way, AP to STA and vice versa).
>> Normally I can obtain 2/3 theory rate in practical (for expl NSS3:MCS3
>> has 390 Mbps in theory, and if I force to that rate, my TCP throughput
>> is around 270 Mbps). So I should obtain 650 Mbps in practical for TCP
>> with NSS3:MCS7 (975 Mbps in theory). 570 Mbps is so far to 650 Mbps :(
>Forcing the data rate isn't really optimal. Have you tried 10.2
>firmware? I was told it has improvements in the rate control algorithm.
Yes but it doesn't help, even worse.
With 10.1 firmware, I can go up to 610 Mbps TCP (NSS3:MCS7 and checksum off load disabled on interface ethernet
of the PC which connects to my station's device, I just discover it, before my rate was ~ 570 Mbps).
With 10.2 firmware and the same config, my highest through put is only around 560 Mbps. But there is an improvement
that the rate of MCS8 and MCS9 is not much lower than MCS7 as in 10.1 firmware. Here is a small compare between 10.1
and 10.2 (always with NSS3)
MCS 7: 610 vs 560 Mbps
MCS 8: 530 vs 560 Mbps (MCS8 got the same rate as MCS7 with 10.2 firmware)
MCS 9: 410 vs 510 Mbps
But captured log from Wireshark still shows me VHT capab is between MCS 0-9 but VHT operation is only between MCS 0-7.
And the 10.2 firmware still crashed with station on promiscuous mode. There is another bug that I also saw in 10.2 firmware,
after a moment that my STA connected to the AP, I lost the connection (pinging non success) and this message keeps printing:
ath10k: failed to flush transmit queue (skip 0 ar-state 1): 0
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: RE : RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-08-21 12:23 ` Vu Hai NGUYEN
@ 2014-08-21 12:41 ` Michal Kazior
0 siblings, 0 replies; 30+ messages in thread
From: Michal Kazior @ 2014-08-21 12:41 UTC (permalink / raw)
To: Vu Hai NGUYEN
Cc: Adrian Chadd, ath10k@lists.infradead.org, Kalle Valo,
Patrick CARNEIRO RODRIGUEZ, Ben Greear, Bartosz Markowski
On 21 August 2014 14:23, Vu Hai NGUYEN <vh.nguyen@actiasodielec.fr> wrote:
>>>>What do you get for UDP? That seems like pretty good TCP throughput.
>
>>> In VHT80 mode and rate forced to NSS3:MCS7, I can obtain 750 Mbps with
>>> less than 1% data lost (in both way, AP to STA and vice versa).
>>> Normally I can obtain 2/3 theory rate in practical (for expl NSS3:MCS3
>>> has 390 Mbps in theory, and if I force to that rate, my TCP throughput
>>> is around 270 Mbps). So I should obtain 650 Mbps in practical for TCP
>>> with NSS3:MCS7 (975 Mbps in theory). 570 Mbps is so far to 650 Mbps :(
>
>>Forcing the data rate isn't really optimal. Have you tried 10.2
>>firmware? I was told it has improvements in the rate control algorithm.
>
> Yes but it doesn't help, even worse.
> With 10.1 firmware, I can go up to 610 Mbps TCP (NSS3:MCS7 and checksum off load disabled on interface ethernet
> of the PC which connects to my station's device, I just discover it, before my rate was ~ 570 Mbps).
> With 10.2 firmware and the same config, my highest through put is only around 560 Mbps. But there is an improvement
> that the rate of MCS8 and MCS9 is not much lower than MCS7 as in 10.1 firmware. Here is a small compare between 10.1
> and 10.2 (always with NSS3)
> MCS 7: 610 vs 560 Mbps
> MCS 8: 530 vs 560 Mbps (MCS8 got the same rate as MCS7 with 10.2 firmware)
> MCS 9: 410 vs 510 Mbps
>
> But captured log from Wireshark still shows me VHT capab is between MCS 0-9 but VHT operation is only between MCS 0-7.
The 10.2 seems to perform slower in my cabled test environment
(~900mbps on 10.1 vs ~820mbps on 10.2) as well so far.
> And the 10.2 firmware still crashed with station on promiscuous mode. There is another bug that I also saw in 10.2 firmware,
> after a moment that my STA connected to the AP, I lost the connection (pinging non success) and this message keeps printing:
> ath10k: failed to flush transmit queue (skip 0 ar-state 1): 0
Yeah. There seems to be a bug in 10.2: 8 (that's the max I've seen so
far; never more) txed frames get stuck and are never completed by
firmware. Once you get at least 1 frame stuck you'll start getting
"failed to flush" until you stop all ath10k's interfaces.
Michał
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-17 12:42 ` Bartosz Markowski
2014-07-17 13:19 ` RE : " Vu Hai NGUYEN
@ 2014-08-26 8:32 ` Vu Hai NGUYEN
2014-08-26 8:55 ` Bartosz Markowski
1 sibling, 1 reply; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-08-26 8:32 UTC (permalink / raw)
To: Bartosz Markowski; +Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org
>So probably the air condition you have forces the rate control to pick
>MCS7 as the most suitable rates.
>>>In open AP mode (bridge), CUS223 HW (not WLE900VX however) and on
>>>AP135 platform (customized openwrt SW + bleeding edge of
>>>ath10k/wireless subsystem souces - private backports tarball).. for
>>>UDP (last time I measured) I have around 820Mpbs for UCP both ways and
>>>720Mbps TCP.
>>
>> This is in NSS3 -MCS9? Did you get better or worse rate if you clear the mask
>> (iw wlanX set bitrates) cause if I don't config rate, from AP to STA I have the best rate
>> (ie same as MCS7) but from STA to AP my rate is much lower than MCS7 (240 Mbps
>> vs 370 Mbps in TCP).
>Yes, NSS-3; Over the RF-cables I'm easily able to get MCS9 rates
>transmitions without any forced settings (the rate control is picking
>the highest rates).
Hi Bartosz,
I connect 2 antennas on my 2 devices together by a RF-cables with an attenuator around -60dBm, config
each device to use one antenna and force rate to NSS1. But the TCP through put of MCS7 (230 Mbps) is
always slightly higher than MCS8 (210Mbps) and 9 (190Mbps).
Can you give me some detail about your RF-cables test-bed? (for example which attenuator did you use?,etc...)
Thank you in advance.
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: RE : RE : Trouble shooting low rate MCS9 in 802.11ac
2014-08-26 8:32 ` Vu Hai NGUYEN
@ 2014-08-26 8:55 ` Bartosz Markowski
0 siblings, 0 replies; 30+ messages in thread
From: Bartosz Markowski @ 2014-08-26 8:55 UTC (permalink / raw)
To: Vu Hai NGUYEN; +Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org
On 26 August 2014 10:32, Vu Hai NGUYEN <vh.nguyen@actiasodielec.fr> wrote:
>>So probably the air condition you have forces the rate control to pick
>>MCS7 as the most suitable rates.
>
>>>>In open AP mode (bridge), CUS223 HW (not WLE900VX however) and on
>>>>AP135 platform (customized openwrt SW + bleeding edge of
>>>>ath10k/wireless subsystem souces - private backports tarball).. for
>>>>UDP (last time I measured) I have around 820Mpbs for UCP both ways and
>>>>720Mbps TCP.
>>>
>>> This is in NSS3 -MCS9? Did you get better or worse rate if you clear the mask
>>> (iw wlanX set bitrates) cause if I don't config rate, from AP to STA I have the best rate
>>> (ie same as MCS7) but from STA to AP my rate is much lower than MCS7 (240 Mbps
>>> vs 370 Mbps in TCP).
>
>>Yes, NSS-3; Over the RF-cables I'm easily able to get MCS9 rates
>>transmitions without any forced settings (the rate control is picking
>>the highest rates).
>
> Hi Bartosz,
> I connect 2 antennas on my 2 devices together by a RF-cables with an attenuator around -60dBm, config
> each device to use one antenna and force rate to NSS1. But the TCP through put of MCS7 (230 Mbps) is
> always slightly higher than MCS8 (210Mbps) and 9 (190Mbps).
> Can you give me some detail about your RF-cables test-bed? (for example which attenuator did you use?,etc...)
> Thank you in advance.
I have a custom made QCA programmable attenuator and besides this
nothing facy: 2.4GHz and 5GHz RF cables (Nm connectors, u.fl cables +
adaptors etc.)
-Bartosz
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: Trouble shooting low rate MCS9 in 802.11ac
2014-07-17 10:40 ` Trouble shooting low rate MCS9 in 802.11ac Vu Hai NGUYEN
2014-07-17 10:53 ` Bartosz Markowski
@ 2014-07-17 10:57 ` Michal Kazior
2014-07-17 12:42 ` RE : " Vu Hai NGUYEN
1 sibling, 1 reply; 30+ messages in thread
From: Michal Kazior @ 2014-07-17 10:57 UTC (permalink / raw)
To: Vu Hai NGUYEN; +Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org
On 17 July 2014 12:40, Vu Hai NGUYEN <vh.nguyen@actiasodielec.fr> wrote:
> Hi all,
Hi,
> I'm using ath10k with official firmware (10.1, 467-2-1), my module of wifi is Compex WLE900VX.
> In theory MCS9 should give better rate than MCS 7.
> But when running test with Iperf, I notice that if I force rate (using command "iw") to MCS9 or MCS8,
> the rate result from iperf are always lower than MCS 7 (even NSS1,2 or 3).
> Though I check RX rate report from "iw station dump" and it matches with the rate that I want to force.
> You can see in the attached file a report of my test.
> Any one has done the test and get better rate in MCS9 than in MCS7 with this wifi module ???
The higher the MCS rate the more symbols are packed up per baud which
means it is more susceptible to interference and corruption.
You probably don't have an environment clean enough to pull off MCS8
and MCS9 and you end up with a lot of retransmissions.
If you're sure you have a clean environment then try putting your
devices (or them antenna) at different angles against each other and
different distances.
Michał
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
* RE : Trouble shooting low rate MCS9 in 802.11ac
2014-07-17 10:57 ` Michal Kazior
@ 2014-07-17 12:42 ` Vu Hai NGUYEN
0 siblings, 0 replies; 30+ messages in thread
From: Vu Hai NGUYEN @ 2014-07-17 12:42 UTC (permalink / raw)
To: Michal Kazior; +Cc: Patrick CARNEIRO RODRIGUEZ, ath10k@lists.infradead.org
>The higher the MCS rate the more symbols are packed up per baud which
>means it is more susceptible to interference and corruption.
>You probably don't have an environment clean enough to pull off MCS8
>and MCS9 and you end up with a lot of retransmissions.
>If you're sure you have a clean environment then try putting your
>devices (or them antenna) at different angles against each other and
>different distances.
What did you mean by clean environment? (There's no other 5Ghz wifi in the room,
no radar or device that emit in 5Ghz frequency? I may have other 2.4Ghz wifi in my room,
hope that it doesn't create any effects)
I'm using an Omnidirectional antennas of PCTEL so I guess it doesn't change anything
if I change the angle.
One more thing, my processor is already exhausted (0-1% idle) when I obtain 410Mbps in NSS3 -MCS7,
so if I force it to MCS8 or 9, is it possible that a reverse effects is created? The processor gets a lot of work
to do and then I end up with retransmissions like you said?
I hope not cause even in VHT40 or VHT20 my processor is not exhausted and MCS9 is still lower than MCS 8 or 7.
NGUYEN Vu Hai
Acita-Sodielec
Route de Mayres - B.P. 9
12100 St GEORGES DE LUZENCON
FRANCE
_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k
^ permalink raw reply [flat|nested] 30+ messages in thread
end of thread, other threads:[~2014-08-26 8:55 UTC | newest]
Thread overview: 30+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-07-09 14:22 Throughput is very low Mamun Abu-Tair
2014-07-16 16:01 ` Bart Jooris
2014-07-17 5:21 ` Michal Kazior
2014-07-17 10:40 ` Trouble shooting low rate MCS9 in 802.11ac Vu Hai NGUYEN
2014-07-17 10:53 ` Bartosz Markowski
2014-07-17 12:22 ` RE : " Vu Hai NGUYEN
2014-07-17 12:42 ` Bartosz Markowski
2014-07-17 13:19 ` RE : " Vu Hai NGUYEN
2014-07-17 19:18 ` Adrian Chadd
2014-07-21 12:10 ` Vu Hai NGUYEN
2014-07-25 12:22 ` Vu Hai NGUYEN
2014-07-25 12:51 ` Ben Greear
2014-07-28 7:32 ` Vu Hai NGUYEN
2014-07-28 11:53 ` RE : " Vu Hai NGUYEN
2014-07-28 16:08 ` Ben Greear
2014-07-29 8:02 ` Vu Hai NGUYEN
2014-07-29 15:04 ` RE : " Vu Hai NGUYEN
2014-07-29 15:55 ` Ben Greear
2014-07-30 6:26 ` Michal Kazior
2014-07-31 10:02 ` Vu Hai NGUYEN
2014-08-18 9:45 ` Vu Hai NGUYEN
2014-08-19 18:26 ` Ben Greear
2014-08-20 14:13 ` Vu Hai NGUYEN
2014-08-20 14:51 ` Kalle Valo
2014-08-21 12:23 ` Vu Hai NGUYEN
2014-08-21 12:41 ` Michal Kazior
2014-08-26 8:32 ` Vu Hai NGUYEN
2014-08-26 8:55 ` Bartosz Markowski
2014-07-17 10:57 ` Michal Kazior
2014-07-17 12:42 ` RE : " Vu Hai NGUYEN
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.
![[-- Attachment #2: Selection_004.png --] [-- Type: image/png, Size: 15261 bytes --]](../../EE97821C81277E459BEA5C6384C6F241012F15C1D7EB@srvexch01.SODIELEC.local/2-Selection_004.png){kind=link}