Re: A different zones question
From: Andrew Gabriel (andrew_at_cucumber.demon.co.uk)
Date: 03/24/05
- Next message: Harryzhu: "Re: on solaris 2.4.1, how to mount the shared filesystem on solaris 8?"
- Previous message: Dave: "Re: Bug in Sun compiler WS6U2? - Crashes during compile phase with-fast."
- In reply to: Rob Shepherd: "A different zones question"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Date: Thu, 24 Mar 2005 00:28:56 +0000 (UTC)
In article <d1s69r$21h$1@fantastix.bangor.ac.uk>,
Rob Shepherd <robshep@invalid.invalid> writes:
> Is there a performance defecit when using non-global zones?
> In other words is there a interpreting layer (or equiv) which would affect i/o latency?
No.
Of course, another zone performing i/o on the same disk could
be moving the head away from where your zone wants it. On the
other hand they all share the same page cache, so a user who
starts up vi in another zone before you do will have already
paged in the text you need, so from your perspective your
first invocation of vi could be faster due to reduced i/o
latency.
-- Andrew Gabriel
- Next message: Harryzhu: "Re: on solaris 2.4.1, how to mount the shared filesystem on solaris 8?"
- Previous message: Dave: "Re: Bug in Sun compiler WS6U2? - Crashes during compile phase with-fast."
- In reply to: Rob Shepherd: "A different zones question"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Relevant Pages
|
