<html>
<head>
<meta content="text/html; charset=windows-1252"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
Out of curiosity. Dp these builds of OpenWrt for Mikrotik RBs make
usage of any possible hardware off-loads or config customizations
are CPU affinity possibility made by Mikrotik themselves in their
original RouterOS ?<br>
<br>
Thanks<br>
Fernando<br>
<br>
<div class="moz-cite-prefix">On 15/10/2015 14:48, George Chriss
wrote:<br>
</div>
<blockquote
cite="mid:CAKcQQDukGngy-xuqzHAuBV_qkXtKpge6Wj57Rg1pNgQ4U+kbmA@mail.gmail.com"
type="cite">
<div dir="ltr"><br>
On Thu, April 23, 2015 06:16:08 CEST, Toerless Eckert wrote:<br>
> This mail thread seem to have gone dark since december with
seemingly<br>
> no conclusion.<br>
> <br>
> I have tried to collect the experiences reported on the
wiki page:<br>
> <br>
> <a moz-do-not-send="true"
href="http://wiki.openwrt.org/toh/mikrotik/rb2011uias">wiki.openwrt.org/toh/mikrotik/rb2011uias</a><br>
> <br>
> As you can see from the table, for me it only works with
0x6f.<br>
> Chris, for whom both 0x3e and 0x6f work has a rev 2 AR9344.
I have<br>
> a rev 3. AR8327 is rev. 4 on both our routerboards. No info
what rev Matt<br>
> has, he is the other one reporting that only 0x6f works.<br>
><br>
> I am also observing some amount of increases in switch 0
port 0<br>
> RxBadByte (aka: from CPU to AR8327). It seems to happen for<br>
> all type of traffic sent from CPU to switch, eg: whether i
inject it from<br>
> WiFi or from a 100 Mbps port, and whether i send it out<br>
> on an untagged port (lan) or tagged one (from CPU, Wan).<br>
<br>
I'm under the impression that some of the "OK/Not OK" reports
are based on ping packet loss which provides limited insight
into actual throughput. My results with a RB2011UiAS-IN (no
WiFi, empty SFP cage, AR9344 Rev. 2, CPU @ 600MHz powered from
the DC-in jack) on patched 15.05:<br>
<br>
0x06000000 (Unpatched)<br>
No TCP/IP 2-way connection [Not OK]<br>
<br>
======<br>
<br>
0x3e000000<br>
(MikroTik Eth1 -> laptop, crossover cable)<br>
/bin/bash -c "dd if=/dev/zero bs=1M count=1000 | netcat
192.168.1.101 7777"<br>
1000+0 records in<br>
1000+0 records out<br>
1048576000 bytes (1.0 GB) copied, 1589.44 s, 660 kB/s [Not OK]<br>
<br>
(laptop -> MikroTik Eth1, crossover cable)<br>
dd if=/dev/zero bs=1M count=1000 | nc 192.168.1.121 7777<br>
1000+0 records in<br>
1000+0 records out<br>
1048576000 bytes (1.0 GB) copied, 49.6707 s, 21.1 MB/s [OK]<br>
<br>
======<br>
<br>
0x6f000000<br>
(MikroTik Eth1 -> laptop, crossover cable)<br>
/bin/bash -c "dd if=/dev/zero bs=1M count=1000 | netcat 192.168.<br>
1.101 7777"<br>
1000+0 records in<br>
1000+0 records out<br>
1048576000 bytes (1.0 GB) copied, 176.224 s, 6.0 MB/s [OK?]<br>
<br>
(laptop -> MikroTik Eth1, crossover cable)<br>
dd if=/dev/zero bs=1M count=1000 | nc 192.168.1.121 7777<br>
1000+0 records in<br>
1000+0 records out<br>
1048576000 bytes (1.0 GB) copied, 50.7454 s, 20.7 MB/s [OK]<br>
<br>
<br>
Any word on the bootloader patch? Happy to test more values as
needed.<br>
<br>
Sincerely,<br>
George<br>
<br>
<br>
> I have not really identified any noticeable performance
impact from<br>
> this effect through.<br>
> <br>
> Would be nice to hear some logic why 0x6f is the right
value.<br>
> <br>
>> From the discussion it looks a bit like trial and
error.<br>
>> <br>
> <br>
> Cheers<br>
> Toerless<br>
> <br>
> <br>
<br>
<br>
</div>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<br>
<pre wrap="">_______________________________________________
openwrt-devel mailing list
<a class="moz-txt-link-abbreviated" href="mailto:openwrt-devel@lists.openwrt.org">openwrt-devel@lists.openwrt.org</a>
<a class="moz-txt-link-freetext" href="https://lists.openwrt.org/cgi-bin/mailman/listinfo/openwrt-devel">https://lists.openwrt.org/cgi-bin/mailman/listinfo/openwrt-devel</a>
</pre>
</blockquote>
<br>
</body>
</html>