public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* Ext2 & Performances
@ 2000-11-21 16:58 Roberto Fichera
  2000-11-21 18:00 ` Jakob Østergaard
  2000-11-21 18:16 ` Roberto Fichera
  0 siblings, 2 replies; 6+ messages in thread
From: Roberto Fichera @ 2000-11-21 16:58 UTC (permalink / raw)
  To: linux-kernel

Hi All,

I need to know if there are some differences, in performances, between
a ext2 filesystem in a 10Gb partition and another that reside in a 130Gb,
each one have 4Kb block size.

I'm configuring a Compaq ML350 2x800PIII, 1Gb RAM, 5x36Gb UWS3 RAID 5
with Smart Array 4300, as database SQL server. So I need to chose between a 
single
partition of 130Gb or multiple small partitions, depending by the performances.

Thanks.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: Ext2 & Performances
  2000-11-21 16:58 Ext2 & Performances Roberto Fichera
@ 2000-11-21 18:00 ` Jakob Østergaard
  2000-11-21 18:16 ` Roberto Fichera
  1 sibling, 0 replies; 6+ messages in thread
From: Jakob Østergaard @ 2000-11-21 18:00 UTC (permalink / raw)
  To: Roberto Fichera; +Cc: linux-kernel

On Tue, Nov 21, 2000 at 05:58:58PM +0100, Roberto Fichera wrote:
> Hi All,
> 
> I need to know if there are some differences, in performances, between
> a ext2 filesystem in a 10Gb partition and another that reside in a 130Gb,
> each one have 4Kb block size.
> 
> I'm configuring a Compaq ML350 2x800PIII, 1Gb RAM, 5x36Gb UWS3 RAID 5
> with Smart Array 4300, as database SQL server. So I need to chose between a 
> single
> partition of 130Gb or multiple small partitions, depending by the performances.

Does your database *require* a filesystem ?   At least Oracle can do without,
but I don't know about others...

Usually, if you want performance, you let the database use the block device
without putting a filesystem on top of it.

You probably don't want a 130G ext2 if there is any chance that a power
surge etc. can cause the machine to reboot without umount()'ing the 
filesystem.  A fsck on a 130G filesystem is going to take a *long* time.

-- 
................................................................
:   jakob@unthought.net   : And I see the elder races,         :
:.........................: putrid forms of man                :
:   Jakob Østergaard      : See him rise and claim the earth,  :
:        OZ9ABN           : his downfall is at hand.           :
:.........................:............{Konkhra}...............:
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: Ext2 & Performances
  2000-11-21 16:58 Ext2 & Performances Roberto Fichera
  2000-11-21 18:00 ` Jakob Østergaard
@ 2000-11-21 18:16 ` Roberto Fichera
  2000-11-21 18:32   ` Andreas Dilger
  2000-11-21 18:36   ` Aaron Sethman
  1 sibling, 2 replies; 6+ messages in thread
From: Roberto Fichera @ 2000-11-21 18:16 UTC (permalink / raw)
  To: Jakob Østergaard; +Cc: linux-kernel

At 19.00 21/11/00 +0100, Jakob Østergaard wrote:

>On Tue, Nov 21, 2000 at 05:58:58PM +0100, Roberto Fichera wrote:
> > Hi All,
> >
> > I need to know if there are some differences, in performances, between
> > a ext2 filesystem in a 10Gb partition and another that reside in a 130Gb,
> > each one have 4Kb block size.
> >
> > I'm configuring a Compaq ML350 2x800PIII, 1Gb RAM, 5x36Gb UWS3 RAID 5
> > with Smart Array 4300, as database SQL server. So I need to chose 
> between a
> > single
> > partition of 130Gb or multiple small partitions, depending by the 
> performances.
>
>Does your database *require* a filesystem ?   At least Oracle can do without,
>but I don't know about others...

Currently I'm using PostgreSQL.

>Usually, if you want performance, you let the database use the block device
>without putting a filesystem on top of it.

Yes! I know! Oracle should be a good choice for that.

>You probably don't want a 130G ext2 if there is any chance that a power
>surge etc. can cause the machine to reboot without umount()'ing the
>filesystem.  A fsck on a 130G filesystem is going to take a *long* time.

Yes! I know :-((!!! I'm looking for other fs that are journaled like ext3 
or raiserfs
but I don't know which are a good choice for stability and performances.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: Ext2 & Performances
  2000-11-21 18:16 ` Roberto Fichera
@ 2000-11-21 18:32   ` Andreas Dilger
  2000-11-21 18:36   ` Aaron Sethman
  1 sibling, 0 replies; 6+ messages in thread
From: Andreas Dilger @ 2000-11-21 18:32 UTC (permalink / raw)
  To: Roberto Fichera; +Cc: Jakob Østergaard, linux-kernel

Roberto Fichera writes:
> I'm configuring a Compaq ML350 2x800PIII, 1Gb RAM, 5x36Gb UWS3 RAID 5
> with Smart Array 4300, as database SQL server. So I need to chose 
> between a single partition of 130Gb or multiple small partitions,
> depending by the performance.

It is usually better to have multiple small partitions for performance and
reliability, but this is more work to administer.

> Yes! I know :-((!!! I'm looking for other fs that are journaled like ext3 
> or raiserfs but I don't know which are a good choice for stability and
> performances.

The current (0.0.5b) ext3 code is doing pretty good, and if you use
metadata-only journalling it is about as fast as ext2.  I still wouldn't
use this on a production system where data loss is fatal, although I
have never had any data loss or filesystem corruption because of ext3.

Cheers, Andreas
-- 
Andreas Dilger  \ "If a man ate a pound of pasta and a pound of antipasto,
                 \  would they cancel out, leaving him still hungry?"
http://www-mddsp.enel.ucalgary.ca/People/adilger/               -- Dogbert
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: Ext2 & Performances
  2000-11-21 18:16 ` Roberto Fichera
  2000-11-21 18:32   ` Andreas Dilger
@ 2000-11-21 18:36   ` Aaron Sethman
  2000-11-22  5:41     ` Eric W. Biederman
  1 sibling, 1 reply; 6+ messages in thread
From: Aaron Sethman @ 2000-11-21 18:36 UTC (permalink / raw)
  To: Roberto Fichera; +Cc: Jakob Østergaard, linux-kernel

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: TEXT/PLAIN; charset=X-UNKNOWN, Size: 1939 bytes --]

You might want to take a look at using reiserfs on the 130GB partition, as
its is journalled and doesn't need to be fsck'ed.  Take a look a
http://devlinux.com/namesys/

Aaron

On Tue, 21 Nov 2000, Roberto Fichera wrote:

> At 19.00 21/11/00 +0100, Jakob Østergaard wrote:
> 
> >On Tue, Nov 21, 2000 at 05:58:58PM +0100, Roberto Fichera wrote:
> > > Hi All,
> > >
> > > I need to know if there are some differences, in performances, between
> > > a ext2 filesystem in a 10Gb partition and another that reside in a 130Gb,
> > > each one have 4Kb block size.
> > >
> > > I'm configuring a Compaq ML350 2x800PIII, 1Gb RAM, 5x36Gb UWS3 RAID 5
> > > with Smart Array 4300, as database SQL server. So I need to chose 
> > between a
> > > single
> > > partition of 130Gb or multiple small partitions, depending by the 
> > performances.
> >
> >Does your database *require* a filesystem ?   At least Oracle can do without,
> >but I don't know about others...
> 
> Currently I'm using PostgreSQL.
> 
> >Usually, if you want performance, you let the database use the block device
> >without putting a filesystem on top of it.
> 
> Yes! I know! Oracle should be a good choice for that.
> 
> >You probably don't want a 130G ext2 if there is any chance that a power
> >surge etc. can cause the machine to reboot without umount()'ing the
> >filesystem.  A fsck on a 130G filesystem is going to take a *long* time.
> 
> Yes! I know :-((!!! I'm looking for other fs that are journaled like ext3 
> or raiserfs
> but I don't know which are a good choice for stability and performances.
> 
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> Please read the FAQ at http://www.tux.org/lkml/
> 
> 

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: Ext2 & Performances
  2000-11-21 18:36   ` Aaron Sethman
@ 2000-11-22  5:41     ` Eric W. Biederman
  0 siblings, 0 replies; 6+ messages in thread
From: Eric W. Biederman @ 2000-11-22  5:41 UTC (permalink / raw)
  To: Aaron Sethman; +Cc: Roberto Fichera, Jakob Xstergaard, linux-kernel

Aaron Sethman <androsyn@ratbox.org> writes:

> You might want to take a look at using reiserfs on the 130GB partition, as
> its is journalled and doesn't need to be fsck'ed.  
No.

All journaling filesystems need to be fsck'ed.
A correctly operating one simply doesn't need to be fsck'ed  because
of unexpected loss of operating system.    Which brings greatly reduce
the probability.  If an error is detected in the filesystem fsck is
still what you have to do to correct it.

Eric
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/

^ permalink raw reply	[flat|nested] 6+ messages in thread

end of thread, other threads:[~2000-11-22  7:58 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2000-11-21 16:58 Ext2 & Performances Roberto Fichera
2000-11-21 18:00 ` Jakob Østergaard
2000-11-21 18:16 ` Roberto Fichera
2000-11-21 18:32   ` Andreas Dilger
2000-11-21 18:36   ` Aaron Sethman
2000-11-22  5:41     ` Eric W. Biederman

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox