dcsimg
Linux Today: Linux News On Internet Time.





More on LinuxToday


ClusterMonkey: Cluster Interconnects: Real Application Performance and Beyond

Jan 11, 2007, 19:15 (1 Talkback[s])
(Other stories by Gilad Shainer)

WEBINAR:
On-Demand

Re-Imagining Linux Platforms to Meet the Needs of Cloud Service Providers


[ Thanks to Douglas Eadline for this link. ]

"The difference between theoretical power and what is actually delivered is measured as processor efficiency. The more CPU cycles used to get the data out the door by "filling the wire" due to protocol and data transfer inefficiencies, the less cycles are available for the application. When comparing latencies of different interconnects, one needs to pay attention to the interconnect architecture. 1usec latency "on-loading" interconnect versus 2usec latency "off-load" solution is similar to a case when one needs to decide between two cars that show the same horsepower (i.e. CPU). Both engines are capable of 200 miles per hour, but the first car, due to "on-loading", limits the actual engine power to 75 miles per hour (the engine power must be used for other tasks). The Second car has no limitations on the engine, but its wheels can tolerate only 150 miles per hour. The knowledge on the wheels tolerance (i.e. latency), as a single point of data, is definitely misleading."



Complete Story

Related Stories: