Hi, Thomas

Unfortunately, the secure mesh throughput in multihop scenario is not
working well. Throughput is dropped to kbps when going through from MP1 to
MP2 [0a:0b:6c:b2:03:5d] to MP3 [0a:0b:6c:7d:e3:b9]. Ping is alright.

Regards,
Chun-Yeow

# iw mesh0 mpath set 0a:0b:6c:7d:e3:b9 next_hop 0a:0b:6c:b2:03:5d
# ping 10.44.29.245
PING 10.44.29.245 (10.44.29.245): 56 data bytes
64 bytes from 10.44.29.245: seq=0 ttl=64 time=2.579 ms
64 bytes from 10.44.29.245: seq=1 ttl=64 time=3.036 ms
64 bytes from 10.44.29.245: seq=2 ttl=64 time=3.096 ms
64 bytes from 10.44.29.245: seq=3 ttl=64 time=2.464 ms
^C
--- 10.44.29.245 ping statistics ---
4 packets transmitted, 4 packets received, 0% packet loss
round-trip min/avg/max = 2.464/2.793/3.096 ms
# iperf -c 10.44.29.245 -i 1 -t 10
------------------------------------------------------------
Client connecting to 10.44.29.245, TCP port 5001
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[  3] local 10.44.29.182 port 38026 connected with 10.44.29.245 port 5001
[ ID] Interval       Transfer     Bandwidth
[  3]  0.0- 1.0 sec   128 KBytes  1.05 Mbits/sec
[  3]  1.0- 2.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  2.0- 3.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  3.0- 4.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  4.0- 5.0 sec   128 KBytes  1.05 Mbits/sec
[  3]  5.0- 6.0 sec   128 KBytes  1.05 Mbits/sec
[  3]  6.0- 7.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  7.0- 8.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  8.0- 9.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  9.0-10.0 sec   128 KBytes  1.05 Mbits/sec
[  3] 10.0-11.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  0.0-13.9 sec   640 KBytes   377 Kbits/sec


On Fri, Nov 18, 2011 at 1:52 AM, Thomas Pedersen <[email protected]> wrote:

> Hi Chun-Yeow,
>
> On Wed, Nov 16, 2011 at 5:36 PM, Yeoh Chun-Yeow <[email protected]>
> wrote:
> > Hi, Javier and Thomas
> >
> > Some good news. After modify the ath9k driver to enable the hw
> acceleration,
> > I am able to achieve the throughput of ~38Mbps using single TCP stream
> and
> > upto 58Mbps using 10 TCP streams for HT20. It can reach up to 93Mbps for
> > HT40+ (limited by Fast Ethernet in my embedded board).
> >
>
> Wonderful! Does this work in a multihop topology as well? Any
> intentions of submitting upstream? :)
>
> > Attach is the patch. After applying the patch, we can load the ath9k
> kernel
> > module without nohwcrypt=1.
> >
> > --- ./drivers/net/wireless/ath/ath9k/main.c 2011-11-17 09:25:44.049131028
> > +0800
> > +++ ./drivers/net/wireless/ath/ath9k/main.c       2011-11-17
> > 08:15:59.734686963 +0800
> > @@ -1914,7 +1914,8 @@ static int ath9k_set_key(struct ieee8021
> >         if (ath9k_modparam_nohwcrypt)
> >                 return -ENOSPC;
> >
> > -       if (vif->type == NL80211_IFTYPE_ADHOC &&
> > +       if ((vif->type == NL80211_IFTYPE_ADHOC ||
> > +            vif->type == NL80211_IFTYPE_MESH_POINT) &&
> >             (key->cipher == WLAN_CIPHER_SUITE_TKIP ||
> >              key->cipher == WLAN_CIPHER_SUITE_CCMP) &&
> >             !(key->flags & IEEE80211_KEY_FLAG_PAIRWISE)) {
> >
> > Regards,
> > Chun-Yeow
> >
> > ----------
> > mtk:  hexdump
> > 4c 1e ac 72 37 3a 32 c8 26 98 20 2b 7c c6 99 da
> > ----------
> >
> > estab with 0a:0b:6b:7d:e3:b9
> > set auth flag (seq num=1315733358)
> > set plink state (seq num=1315733359)
> > mesh plink with 0a:0b:6b:7d:e3:b9 established
> > NL80211_CMD_TX_STATUS (1315733333.795799)
> > Mesh plink timer for 0a:0b:6b:7d:e3:b9 fired on state ESTAB
> > Timeout for peer 0a:0b:6b:7d:e3:b9 in state 4
> >
> > # iperf -c 10.44.29.245 -i 1 -t 10
> > ------------------------------------------------------------
> > Client connecting to 10.44.29.245, TCP port 5001
> > TCP window size: 16.0 KByte (default)
> > ------------------------------------------------------------
> > [  3] local 10.44.29.182 port 54691 connected with 10.44.29.245 port 5001
> > [ ID] Interval       Transfer     Bandwidth
> > .....
> > [  3]  0.0-10.0 sec  45.4 MBytes  37.9 Mbits/sec
> >
> >
> > On Wed, Nov 16, 2011 at 3:41 AM, Javier Cardona <[email protected]>
> wrote:
> >>
> >> Hi Yeoh,
> >>
> >> That's great info, thanks!  We'll ask our ath9k experts if they can
> >> help us enable hw acceleration in mesh mode.
> >>
> >> Cheers,
> >>
> >> Javier
> >
> >
>
_______________________________________________
Devel mailing list
[email protected]
http://open80211s.com/mailman/listinfo/devel

Reply via email to