HP3000-L Archives

May 1999, Week 2

HP3000-L@RAVEN.UTC.EDU

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Mark Klein <[log in to unmask]>
Reply To:
Date:
Thu, 13 May 1999 11:16:19 -0700
Content-Type:
text/plain
Parts/Attachments:
text/plain (25 lines)
Donna writes:

>Edward Jordan wrote:

>> What is the system overhead (performance issues) with mirroring?

>way back when...mirroring was the recommended solution because it was faster
>than raid.  imo, mirroring is still a good solution because disc mechs are
>*so* inexpensive.  it's probably a 'ymmv' kind of thing.

Take that one step further ... hardware mirroring has become quite cost
effective today and the performance has become much better. You need to
answer the question as to whether or not the CPU and the IO paths have
the bandwidth to support software mirroring. If not, absolutely don't
consider it. IMHO, hardware mirroring is the way to go.

>>>MY opinions, not Longs Drug Stores'<<<

And these are mine, not ORBiT's.

Regards,


M.

ATOM RSS1 RSS2