For optimal performance average disk queue length really shouldn't be above the number of spindles that are backing the disk, anything above that line means you are I/O bound at the disks and average ...

We implemented a vSphere at the beginning of the year using a VNXe3100 as the storage device presented to the servers. The initial plan was to get it up and running and migrate some of the lower end ...

Sun Microsystems releases a video about a source of disk latency that is at once funny and a nice demonstration of the underlying technologies, including DTrace. Gordon Haff is Red Hat's cloud ...

While data-center managers have long used heat maps to help determine where to best position racks of servers and cooling units, this mode of visualization can also be handy for better understanding ...