If you're considering the move to 40/100gigabit
Ethernet, here are five things to keep in mind:
1. Check the cables. Both 40-
and 100-gigabit Ethernet use different fiber and copper cabling and
transceivers than previous versions. Simply attaching higher-speed devices to
an existing cabling plant won't work. On the plus side, moving away from link
aggregation toward single higher-speed links may actually reduce cabling
requirements.
2. Verify device distances.
In general, higher-speed Ethernet works over the same distances as previous
generations, such as the 100-meter limit across short-reach fiber optics. But
as with any deployment of new equipment, it's wise to test whether the new
devices will operate without CRC errors across their intended distances.
3. Check network management and security
device speeds. Network monitoring and security devices that worked
just fine at gigabit or 10-gigabit speeds may have trouble keeping up at 40- or
100-gigabit rates. Check with vendors (and conduct your own tests, if
necessary) to determine the highest supported lossless rate for traffic
monitoring and traffic capture.
4. Be prepared to drink from a fire hose.
At 40- and 100-gigabit rates, monitoring equipment must be prepared to capture
and analyze staggering amounts of data. For instance, a stream of 1,518-byte
frames at 100Gbps line rate will require nearly 750GB of storage per minute.
Make sure monitor ports in switches, along with any attached analyzers, can
keep up with much higher traffic rates.
5. Plan a parallel deployment.
The simplest way to get started with higher-speed technologies is a parallel
rollout alongside existing network operations. If everything works well, a
transition to the new links should be smooth.
Post a Comment