Port trunking / link aggregation problem
Bookmark this page:
 Yahoo!
 Google
 Windows Live
 del.icio.us
 digg
 Netscape
|
|
||||||||||||||||
|
Posted by Timo Neuvonen on October 8, 2006, 9:11 am
Please log in for more thread options Hello all ethernet gurus, Currently I have two offices connected with a single G.SHDSL link over a leased line, the link operates at 2.3 Mbps which is a good result with this old cable having length of appr. 6 km (~20000 ft). Now I'm trying to increase the (total) link speed, and one way would be using eg. 4 lines with 2.3 Mbps each, with similar cheap consumer-class(* modems, and combine these links with port trunking (a.k.a link aggregation?) in ethernet switches. Now, the problem: The connection is mostly used by a single computer at a time, to connect to a file servers etc located at the main office. The following citation is from Allied Telesyn's AT-FS750/16 manual: "---- A port trunk always sends packets from a particular source to a particular destination over the same link within the trunk. A single link is designated for flooding broadcasts and packets of unknown destination. ----" How I see this, it would effectively keep one line fully used, and the other lines free, since there would be only two machines communicating with each other. **** Is anyone aware of ethernet switches that I could use to overcome this limitation? In other words, switches that would effectively use all the (slow) lines in a port trunk also while there are only two computers communicating with each other? **** What I'm looking for is preferably a lower-end (less than $500 each) switch with 8 to 16 ports, not a huge modular system costing thousands of dollars. *) I would prefer using as cheap terminal equipment as possible, since in this area lightning strikes breaking any equipment connected to public telephone network cables are far too common :-( Regards, Timo | ||||||||||||||||
|
Posted by anoop on October 8, 2006, 10:56 am
Please log in for more thread options Timo Neuvonen wrote: What protocol are they using? > The following citation is from
> Allied Telesyn's AT-FS750/16 manual: > > "---- > A port trunk always sends packets from a particular source > to a particular destination over the same link within the trunk. > A single link is designated for flooding broadcasts and packets > of unknown destination. > ----" This is done so that packets from a single flow don't get reordered. This can happen when links are of unequal length, or packets within a given flow are of different size (e.g. a max sized frame which gets put on one link followed by several min-sized frames on the other links; the min-sized frames would be received before the max-sized frame). Reordering can cause problems with some protocols, and with TCP, it could potentially lead to retransmissions resulting in loss of performance. As a result typical switches allow you to do load balancing based on one or more of the following criteria: - The source/destination MAC addresses. - The source/destination IP addresses (if the packet is IP). - The source/destination transport port (if the packet is TCP or UDP). > How I see this, it would effectively keep one line fully used,
> and the other lines free, since there would be only two > machines communicating with each other. That's correct. > ****
> Is anyone aware of ethernet switches that I could use to > overcome this limitation? > > In other words, switches that would effectively use all the (slow) > lines in a port trunk also while there are only two computers > communicating with each other? > **** > > What I'm looking for is preferably a lower-end (less than $500 > each) switch with 8 to 16 ports, not a huge modular system > costing thousands of dollars. > > > *) I would prefer using as cheap terminal equipment as > possible, since in this area lightning strikes breaking > any equipment connected to public telephone network > cables are far too common :-( Cheap switches typically won't look deep enough in the packets. But regardless, if you have only two machines talking to each other with one active flow between them (defined by a combination of the 3 criteria mentioned above), then it would be hard to find a switch that will be able to load balance the traffic. You would have to find a switch that does some form of proprietary load balancing. I'm not aware of any. On the other hand, if the two machines are talking over several flows, i.e. different transport ports, then you might want to look for a switch that can load balance traffic based on the source and destination ports in addition to the IP addresses. With that you would get some amount of load balancing although it would be far from perfect. Anoop | ||||||||||||||||
|
Posted by Timo Neuvonen on October 8, 2006, 11:47 am
Please log in for more thread options
> What protocol are they using?
Definetely the most important case is a Windows workstation
> accessing Samba file shares on a Linux server. So, standard Windows file sharing with workgroups (no NT domain controller). > As a result typical switches allow you to do load balancing based
> on one or more of the following criteria: > - The source/destination MAC addresses. > - The source/destination IP addresses (if the packet is IP). > - The source/destination transport port (if the packet is TCP or UDP). > Cheap switches typically won't look deep enough in the
> packets. But regardless, if you have only two machines > talking to each other with one active flow between them > (defined by a combination of the 3 criteria mentioned above), > then it would be hard to find a switch that will be able to > load balance the traffic. You would have to find a switch > that does some form of proprietary load balancing. I'm > not aware of any. > > On the other hand, if the two machines are talking > over several flows, i.e. different transport ports, then > you might want to look for a switch that can load balance > traffic based on the source and destination ports in > addition to the IP addresses. With that you would get > some amount of load balancing although it would be > far from perfect. So, the minimum requirement would be to find switches that can spread packets sent from different transport ports from the same IP / MAC address to different links within a trunk? Any suggestions about lower-end switches (manufactures, product families) that are capable to do this? Regards, Timo | ||||||||||||||||
|
Posted by anoop on October 8, 2006, 1:07 pm
Please log in for more thread options
Timo Neuvonen wrote: > Definetely the most important case is a Windows workstation
> accessing Samba file shares on a Linux server. So, standard > Windows file sharing with workgroups (no NT domain controller). I don't know enough about how this protocol works, but my guess is that if it is running over IP, a client/server communication would happen over a single source/destination TCP port pair. > So, the minimum requirement would be to find switches that
> can spread packets sent from different transport ports from > the same IP / MAC address to different links within a trunk? Yes, that was the suggestion assuming you had multiple flows, but I really doubt that that is true in your situation. Because of issues with reordering, the load distribution algorithms work well only when you have a fairly large number of flows. > Any suggestions about lower-end switches (manufactures,
> product families) that are capable to do this? Alas, I don't know of any low-end products that do this. Anoop | ||||||||||||||||
|
Posted by Rick Jones on October 9, 2006, 1:21 pm
Please log in for more thread options
>> Definetely the most important case is a Windows workstation
>> accessing Samba file shares on a Linux server. So, standard >> Windows file sharing with workgroups (no NT domain controller). > I don't know enough about how this protocol works, but my
> guess is that if it is running over IP, a client/server communication > would happen over a single source/destination TCP port pair. And I'd wonder if the request/response nature of the protocol is able to keep the existing pipe full to begin with? Are there enough outstanding requests at at time to fill the exsiting pipe? rick jones -- Process shall set you free from the need for rational thought. these opinions are mine, all mine; HP might not want them anyway... :) feel free to post, OR email to rick.jones2 in hp.com but NOT BOTH... | ||||||||||||||||
> link over a leased line, the link operates at 2.3 Mbps
> which is a good result with this old cable having length
> of appr. 6 km (~20000 ft).
>
> Now I'm trying to increase the (total) link speed, and
> one way would be using eg. 4 lines with 2.3 Mbps each,
> with similar cheap consumer-class(* modems, and
> combine these links with port trunking (a.k.a link
> aggregation?) in ethernet switches.
>
> Now, the problem:
> The connection is mostly used by a single computer at
> a time, to connect to a file servers etc located at the
> main office.