Re: What is better asychronous IO or multiple db_writers?

In article <34c3d97c.74764416_at_newsserver.trl.oz.au>, Steve Adams wrote:

Whilst I appreciate that RAW devices do provide a higher bandwidth, it does not necessarily follow that they actually improve performance and scalability.

Filesystems provide buffering which can negate the need to perform actual IO. I seem to recall performing some benchmarks on AIX 3.2.5 many moons ago with a DB of 5Gb and finding little to choose between RAW and AIX filesystems. I am sure that this is not the case for every UNIX flavour, HP-UX being a prime candidate for as (certainly prior to HPUX 11) their filesystems are not as well implemented as some other O/S's.

Personally I do not use RAW filesystems (except for REDO) if I can help it. You lose Oracle functionality (AUTOEXTEND) and RAW filesystems are generally more messy to manage.

regs

Neil Chandler

p.s. I hope you are right about Filesystem A/IO in HP-UX 11.

>Hello Neil, Peter, Matt and others,
>
>Here are some quotes from the "Oracle8 Server Installation Guide for
>HP 9000" under the heading "Using Asynchronous I/O":
>"The asynchronous I/O pseudo-driver on HP-UX allows the Oracle Server
>to perform I/O to raw disk partitions using an asynchronous method,
>resulting in less I/O overhead and higher throughput."
>"Oracle Corporation recommends asynchronous I/O on Series 800 systems
>if the database files are created with raw disk partitions."
>This is followed by a detailed explanation of how to set it up.
>
>There is an alternate asynchronous I/O mechanism in HP-UX (fs_async)
>which applies to filesystems and does not affect raw I/O. As you have
>stated, Neil, this is NOT a good idea. It can corrupt your database
>and your filesystems as well. However, your conculsion does not
>follow. Using async I/O on raw datafiles provides much higher write
>bandwidth and scalability than multiple DB writers on either
>filesystem based or raw datafiles.
>
>In HP-UX 11, I believe that there will be a new asynchronous I/O
>mechanism for filesystem based datafiles, which uses the same
>technology as Solaris do presently -- namely, simulating multiple
>DBWR's in the single process using threads. Nevertheless, true
>asynchronous I/O on raw devices should still outperform this
>significantly.
>
>Regards,
>Steve Adams
>steveadams_at_acslink.net.au
>
>----------
>On 19 Jan 1998 15:54:41 GMT, oracle_at_tchp2.tcamuk.stratus.com (Neil
>Chandler) wrote:
>
>>As far a I remember, if you switch on Async-IO on HP-UX (Kernel Parameter)
>>and have you datafiles in filesystems (ADFS or BSD 4.2),
>>you can corrupt your database.
>>
>>Use multiple DB Writers - (about 2 x No-of-disks works well for me)
>>
Received on Wed Jan 21 1998 - 00:00:00 CST