Re: [PERFORMANCE] expanding to SAN: which portion best to move - Mailing list pgsql-performance

From Willy-Bas Loos
Subject Re: [PERFORMANCE] expanding to SAN: which portion best to move
Date
Msg-id BANLkTikg=2SMu5eSBNfW_K8fCXBhZk0Hog@mail.gmail.com
Whole thread Raw
In response to Re: [PERFORMANCE] expanding to SAN: which portion best to move  (Jesper Krogh <jesper@krogh.cc>)
Responses Re: [PERFORMANCE] expanding to SAN: which portion best to move  (Robert Haas <robertmhaas@gmail.com>)
List pgsql-performance
I'm asking them for (real) benchmarks, thanks for the advice. (fio is not available for us now to do it myself, grmbl)

It just occurred to me that it is not necessarily the case that reading the indexes causes a lot of random I/O (on the index itself).
I mean, maybe the index is generally read sequentially and then, when retrieving the data, there is a lot of random I/O.

if it's a long story, any tips for info about this (book or web site)?

cheers,

wbl

On Wed, May 4, 2011 at 7:33 AM, Jesper Krogh <jesper@krogh.cc> wrote:
On 2011-05-04 07:25, Willy-Bas Loos wrote:
are you saying that, generally speaking, moving the data would be better
unless the SAN performs worse than the disks?
It was more, "given all the incertainties, that seems like the least risky".
The SAN might actually be less well performing than what you currently
have, you dont know yet I guess?


besides your point that it depends on what our end looks like i mean.
(and what do you mean by "the DAS way", sry no native speaker)
DAS way => A disk array where the database has sole access
to the hardware (not shared among other systems). Examples
are Dell MD1200/1220 or similary.

--
Jesper




--
"Patriotism is the conviction that your country is superior to all others because you were born in it." -- George Bernard Shaw

pgsql-performance by date:

Previous
From: Jesper Krogh
Date:
Subject: Re: [PERFORMANCE] expanding to SAN: which portion best to move
Next
From: Jim Nasby
Date:
Subject: Re: amazon ec2