Re: SCSI vs. IDE performance test - Mailing list pgsql-general

From Dennis Gearon
Subject Re: SCSI vs. IDE performance test
Date
Msg-id 3F9935EF.9090509@fireserve.net
Whole thread Raw
In response to Re: SCSI vs. IDE performance test  ("Dann Corbit" <DCorbit@connx.com>)
List pgsql-general
Dann Corbit wrote:

>Unwrap this link (if your newsreader folds it) and click on it for hard
>drive performance:
>http://www.storagereview.com/php/benchmark/compare_rtg_2001.php?typeID=1
>0&testbedID=3&osID=4&raidconfigID=1&numDrives=1&devID_0=232&devID_1=237&
>devID_2=213&devID_3=221&devID_4=216&devID_5=249&devID_6=250&devCnt=7
>
>The important part for database is "Server Suite"
>
>---------------------------(end of broadcast)---------------------------
>TIP 9: the planner will ignore your desire to choose an index scan if your
>      joining column's datatypes do not match
>
>
>
Fairly old data, but it shows AMAZING differences in head seek time. I
didn't know head seeks were below 8ms for anything, even today. Also,
from what I've read, the SATA drives of those days were non existent?
The earliest SATA drives I've read about were just SATA interfaces on
OLDER IDE hardware - the manufacutrers had not really signed up on the
concept enough to put their good hardware underneath the interface.

--
"You are behaving like a man",
is an insult from some women,
a compliment from an good woman.



pgsql-general by date:

Previous
From: Adam Witney
Date:
Subject: Re: shared memory on OS X - 7.4beta4
Next
From: Greg Stark
Date:
Subject: Re: VACUUM degrades performance significantly. Database