Re: NT vs. Unix

Hello All,

Thanks for the big response... thanks I learned a lot from them...

The disk configuration I mentioned was: first:
RAID 5 IDE, 1 hard disk controller. This was really performing poorly. The we went to RAID1 (on Oracle's advice) and installed another 2 disk controllers.
Performance was better but this is the system I reported about.

On each of the hard disk controllers there is 16 MB of cache memory.

What amazes me is that with such a small environment we blew the CPU to 80% on average. This is no problem for the programs running on NT though. They happily share the resources and work as they should. It is the physical writes to the disk that queue up and take a lot of time to actually get done.

Thanks again for all your help.

Gerrit-Jan Linker
http://members.aol.com/gjlinker

In article <36c77413.79967261_at_news.interlog.com>, waltdnes_at_interlog.com (Walter Dnes) writes:

> One thing I don't see mentioned... does the machine have a
>full-fledged Ultra-Wide SCSI disk drive, or is drive a cheap-o
>level-1 EIDE where the CPU has to babysit each byte being
>read or written from/to the drive? SCSI drives aren't
>mechanically faster, but they do have their own chips to
>handle scatter/gather, and do requested operations on their
>own. Ideally, the main CPU issues a read or write request,
>and a pointer to an area in memory, then disconnects. The
>SCSI carries out its orders and issues an interrupt to the
>main CPU when finished. In the meantime, the main CPU can be
>number-crunching. You may not see a difference in single-
>tasking DOS, but it's quite important in a true multi-
>tasking environment.
Received on Fri Feb 19 1999 - 17:24:18 CST