Re: ASM Filter Driver Performance
From: Mladen Gogala <gogala.mladen_at_gmail.com>
Date: Thu, 25 Jan 2018 20:05:28 -0500
Message-ID: <64495b87-f33f-c634-56a9-6bd232d3ba02_at_gmail.com>
> What I found was not what I was looking for: 20% better IO
> performance over ASMLib.
Date: Thu, 25 Jan 2018 20:05:28 -0500
Message-ID: <64495b87-f33f-c634-56a9-6bd232d3ba02_at_gmail.com>
On 01/25/2018 03:47 PM, Jared Still wrote:
>
> What I found was not what I was looking for: 20% better IO
> performance over ASMLib.
To make sense, this statement needs further description. If ASM Filter Driver performs 20% better under any circumstances, then ASMLib is a piece of s...tuff. On the other hand, ASMLib is just a version of raw device driver, which bypasses limitation of having a maximum od 255. ASMLib is simple and easy to use. To make such a statement plausible, the author would need to do the following:
- In detail describe machine on which the software was tested. If it
was tested on a VM, that makes the statement more than suspicious
because the performance of virtual IO is usually much, much slower
than the performance of real disk devices.
- Describe the test and the load that was used to establish such an incredible difference.
- Explain the mechanism which makes ASM Filter Driver so much faster than ASMLib.
As I have already written, ASM Filter Driver is very new. Any bugs in the driver mechanism can bring your instance, and therefore your database, down. Such outlandish claims do not convince me on the merit of using filter driver.
-- Mladen Gogala Database Consultant Tel: (347) 321-1217 -- http://www.freelists.org/webpage/oracle-lReceived on Fri Jan 26 2018 - 02:05:28 CET