Datasheet

“main” (Installation and Administration) — 2004/6/25 — 13:29 — page 136 — #162
i
i
i
i
i
i
i
i
Compute Server
A compute server is generally a powerful machine that carries out exten-
sive calculations in the network. Normally, such a machine is equipped
with a large main memory (more than 512 RAM). Fast disk throughput is
only needed for the swap partitions. If possible, distribute swap partitions
to multiple hard disks.
3.9.3 Optimization
The hard disks are normally the limiting factor. To avoid this bottleneck,
combine the following three possibilities:
Distribute the load evenly to multiple disks.
Use an optimized file system, such as reiserfs.
Equip your file server with a sufficient amount of memory (at least
256 MB).
Parallel Use of Multiple Disks
The total amount of time needed for providing requested data consists of
the following elements:
1. Time elapsed until the request reaches the disk controller.
2. Time elapsed until this request is send to the hard disk.
3. Time elapsed until the hard disk positions its head.
4. Time elapsed until the media turns to the respective sector.
5. Time elapsed for the transmission.
The first item depends on the network connection and must be regulated
there. Item two is a relatively insignificant period that depends on the hard
disk controller itself. Items three and four are the main parts. The posi-
tioning time is measured in ms. Compared to the access times of the main
memory, which are measured in ns, this represents a factor of one million.
Item four depends on the disk rotation speed, which is usually several ms.
Item five depends on the rotation speed, the number of heads, and the cur-
rent position of the head (inside or outside).
136 3.9. Partitioning for Experts