increase aggregated gigabit nic throughput from source to destination

[ytotk]

What methods are available to implement hash based packet port load balancing to round robin in sequence communication allowing two hosts to realize greater than gigabit speeds?

Using several intel gigabit nics I would like to increase transfer speed for zfs sending/receiving from one machine to another.

I have tested lacp-active aggregated dual nics between two opensolaris b134 machines connected by a hp procurve 2810-48g switch with lacp and flow control enabled on the aggregated links. Using mbuffer zfs send/receive transfer speeds remain constrained at 105MBytes/sec.

What is the effect of setting lacp rather than trunk? .. flow control on or off?

Thanks for any help.

P.S. This thread has been moevd from Switches, Hubs, Modems (Legacy ITRC forum) to ProCurve / ProVision-Based. - Hp Forum Moderator

[Natasha Samoylenko]

The two trunk group options (LACP and Trunk) use source-destination address pairs (SA/DA) for distributing outbound traffic over trunked links. SA/DA (source address/destination address) causes the switch to distribute outbound traffic to the links within the trunk group on the basis of source/ destination address pairs.

lacp mode active or passive allow you to use standby links if you need 8 links always in trunk.
But it also have some limitations. You can't apply some confugurations to dynamic lacp trunk.
In general it's better to use static trunking.

If you use "trunk 21-25 trk1 lacp" or "trunk 21-25 trk1 trunk" command you will get the same results. You will create a static trunk.

Dynamic and static trunking use the same SA/DA load-balancing method.


And also this discussion may help you http://forums11.itrc.hp.com/service/forums/questionanswer.do?threadId=1173151