What is wrong with out of order packets

ethernet

when i set up adapter teaming on an HP server, one of the options i'd like to enable is round-robin for transmit load balancing because i need the full teamed throughput to a single host. (this is a live migration network for hyper-v.)

when i pick that option, i get a message saying "Packet order not guaranteed". for my use at least, i don't see a problem since my traffic is TCP. but i'm interested in knowing any general problems with out of order packets.

so, what are the potential problems with out of order packets?

Best Answer

Fibre-Channel-over-Ethernet requires, like 'regular' Fibre-Channel in-order-delivery, hence why FCoE required DataCentreEthernet (DCE) which guarantees in-order-delivery. But you're right that there's few reasons in a purely TCP environment to require in-order.

Related Solutions

Switch – Packets sent indiscriminantly out of switch

You may not be seeing what I'm going to describe, the there's a chance that you are. I've seen the symptoms you're talking about on several low-end and middle-of-the-road Netgear and Linksys switches. The switches I've seen this "crazy" behaviour happen with have been in place for awhile, working fine, but begin to flood frames out all ports. The call I normally get is "the network is slow", and subsequent bandwidth monitoring usually locates a single switch that has "gone crazy", often with its activity lights on solid, pumping out large quantities of "bogus" traffic (sometimes made up of legitimate traffic, other times seemingly random garbage).

I like Zypher's suggestion about checking on CPU utilization, but I'd also consider breaking up the "stack" (on these particular switches I don't know if a "stack" operates as a single logical unit or not) and testing each switch individually.

It seems like this problem has gotten worse in the last few years w/ no-name Ethernet switches, Linksys, and Netgear switches. I don't know if there's some silicon in common that has an issue amongst the problem switches I've seen or not. (We're recommending our Customers purchase Dell PowerConnect switches and haven't seen these kinds of problems with their switches-- yet.)

Windows Server 2008 R2 IP Address Binding order

I ran into this same issue today. It appears that Windows uses the lowest numbered IP address on an interface as the primary interface IP in the route table, no matter what ordered they are specified or added. I cannot find a source to confirm this though.

In order to add additional IPs to an interface, and be assured that they are not used as the source IP for outbound connections, you must use the following command:

netsh interface ipv4 add address "Interface Name Here or Index #" address=x.x.x.x mask=y.y.y.y skipassource=true

The key part being skipassource=true.

You can confirm this worked correctly with the following command:

netsh int ipv4 show ipaddresses level=verbose

Unfortunately, you cannot make this change on an existing IP address, so it must be deleted and re-added.

Best Answer

Related Solutions

Switch – Packets sent indiscriminantly out of switch

Windows Server 2008 R2 IP Address Binding order

Related Topic