<div dir="ltr"><div><div>Hello,<br><br></div>Could you please explain the correlation between this commands and performance issues observed by the OP ?<br><br></div>Best regards.<br><div class="gmail_extra"><br><br><br><div class="gmail_quote">2016-05-25 11:06 GMT+02:00 Tudor Capatina via foundry-nsp <span dir="ltr"><<a href="mailto:foundry-nsp@puck.nether.net" target="_blank">foundry-nsp@puck.nether.net</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">i second that,<br>
<br>
no ip icmp redirects - in global config mode or<br>
no ip redirect - in interface config mode<br>
<br>
and you are good to go.<br>
<br>
Tudor<br>
--------------------------------------------<br>
On Wed, 5/25/16, Mike Allen <<a href="mailto:mkallen@gmail.com">mkallen@gmail.com</a>> wrote:<br>
<br>
Subject: Re: [f-nsp] MLXe slow on 10G doing inter-vlan routing<br>
To: "George B." <<a href="mailto:georgeb@gmail.com">georgeb@gmail.com</a>><br>
Cc: <a href="mailto:foundry-nsp@puck.nether.net">foundry-nsp@puck.nether.net</a><br>
Date: Wednesday, May 25, 2016, 1:07 AM<br>
<div><div class="h5"><br>
Turn off<br>
ICMP redirects. Common problem in one arm routing configs.<br>
IMO it should be the default setting but it's not.<br>
Mike<br>
On May 24, 2016 2:00 PM,<br>
"George B" <<a href="mailto:georgeb@gmail.com">georgeb@gmail.com</a>><br>
wrote:<br>
Do you notice the same behavior with both UDP and<br>
TCP streams?<br>
<br>
<br>
On Tue, May 24, 2016 at<br>
1:42 PM, Steven Raymond <<a href="mailto:sraymond@acedatacenter.com">sraymond@acedatacenter.com</a>><br>
wrote:<br>
MLXe,<br>
very lightly loaded, with only one card BR-MLX-10Gx8-X. <br>
Simplest of configuration, layer 2 link with VE<br>
interfaces. During inter-vlan routing where the ingress<br>
traffic and egress traffic are on the same port, say e1/2,<br>
the input traffic level will be fine, but the output traffic<br>
is effectively maxed out at about 50Mbps (on a 10GigE<br>
port). Shift hosts around so that the egress is a<br>
different port on the same card, bang problem gone and full<br>
expected traffic rates achieved.<br>
<br>
<br>
<br>
Tried numerous code versions, from 05800a to 05900a to<br>
06000. No improvement.<br>
<br>
<br>
<br>
Of course tried rebooting, new optics, new cabling. No<br>
errors incrementing on the interface. This is the silliest<br>
dumb problem in a long time. Any ideas are appreciated.<br>
<br>
<br>
<br>
Thanks!<br>
<br>
<br>
<br>
<br>
<br>
<br>
<br>
_______________________________________________<br>
<br>
foundry-nsp mailing list<br>
<br>
<a href="mailto:foundry-nsp@puck.nether.net">foundry-nsp@puck.nether.net</a><br>
<br>
<a href="http://puck.nether.net/mailman/listinfo/foundry-nsp" rel="noreferrer" target="_blank">http://puck.nether.net/mailman/listinfo/foundry-nsp</a><br>
<br>
<br>
<br>
<br>
_______________________________________________<br>
<br>
foundry-nsp mailing list<br>
<br>
<a href="mailto:foundry-nsp@puck.nether.net">foundry-nsp@puck.nether.net</a><br>
<br>
<a href="http://puck.nether.net/mailman/listinfo/foundry-nsp" rel="noreferrer" target="_blank">http://puck.nether.net/mailman/listinfo/foundry-nsp</a><br>
<br>
</div></div> -----Inline Attachment Follows-----<br>
<div class="HOEnZb"><div class="h5"><br>
_______________________________________________<br>
foundry-nsp mailing list<br>
<a href="mailto:foundry-nsp@puck.nether.net">foundry-nsp@puck.nether.net</a><br>
<a href="http://puck.nether.net/mailman/listinfo/foundry-nsp" rel="noreferrer" target="_blank">http://puck.nether.net/mailman/listinfo/foundry-nsp</a><br>
_______________________________________________<br>
foundry-nsp mailing list<br>
<a href="mailto:foundry-nsp@puck.nether.net">foundry-nsp@puck.nether.net</a><br>
<a href="http://puck.nether.net/mailman/listinfo/foundry-nsp" rel="noreferrer" target="_blank">http://puck.nether.net/mailman/listinfo/foundry-nsp</a></div></div></blockquote></div><br><br clear="all"><br>-- <br><div class="gmail_signature">Youssef BENGELLOUN-ZAHR<br></div>
</div></div>