Thread: Re: [ADMIN] Raw devices vs. Filesystems

...and on Wed, Apr 07, 2004 at 01:26:02AM -0400, Tom Lane used the keyboard:
>
> After that, we get to implement our own filesystem-equivalent management
> of disk space allocation, disk I/O scheduling, etc.  Are we really
> smarter than all those kernel hackers doing this for a living?  I doubt it.
>
> After that, we get to re-optimize all the existing Postgres behaviors
> that are designed to sit on top of a standard Unix buffering filesystem
> layer.
>
> After that, we might reap some performance benefits.  Or maybe not.
> There's not a heck of a lot of hard evidence that we would --- and
> what there is traces to twenty-year-old assumptions about disk drive
> and OS behavior, which are quite unlikely to still apply today.
>
> Personally, I have a lot of more-promising projects to pursue...
>

Has anyone tried PostgreSQL on top of OCFS? Personally, I'm not sure it
would even work, as Oracle clearly state that OCFS was _never_ meant to
be a fully fledged UNIX filesystem with POSIX features such as correct
timestamp updates, inode changes, etc., but OCFSv2 brings some features
that might lead one into thinking they're about to make it suitable for
uses beyond that of just having Oracle databases sitting on top of it.

Furthermore, this filesystem would be a blazing one stop solution for
all replication issues PostgreSQL currently suffers from, as its main
design goal was to present "a consistent file system image across the
servers in a cluster".

Now, if both goals can be achieved in one go, hell, I'm willing to try
it out myself in an attempt to extract off of it, some performance
indicators that could be compared to other database performance tests
sent to both this and the PERFORM mailing list.

So, anyone? :)

Cheers,
--
    Grega Bremec
    Senior Administrator
    Noviforum Ltd., Software & Media
    http://www.noviforum.si/

Grega,

> Furthermore, this filesystem would be a blazing one stop solution for
> all replication issues PostgreSQL currently suffers from, as its main
> design goal was to present "a consistent file system image across the
> servers in a cluster".

Does it work, though?   Without Oracle admin tools?

> Now, if both goals can be achieved in one go, hell, I'm willing to try
> it out myself in an attempt to extract off of it, some performance
> indicators that could be compared to other database performance tests
> sent to both this and the PERFORM mailing list.

Hey, any test you wanna run is fine with us.    I'm pretty sure that OCFS
belongs to Oracle, though, patent & copyright, so we couldn't actually use it
in practice.

If your intention in this test is to show the superiority of raw devices, let
me give you a reality check: barring some major corporate backing getting
involved, we can't possibly implement our own PG-FS for database support.  We
already have a TODO list which is far too long for our developer pool, and
implementing a custom FS either takes a large team (OCFS) or several years of
development (Reiser).

Now, if you know somebody who might pay for one, then great ....

--
Josh Berkus
Aglio Database Solutions
San Francisco

On Wed, Apr 07, 2004 at 09:09:16AM -0700, Josh Berkus wrote:

> If your intention in this test is to show the superiority of raw devices, let
> me give you a reality check: barring some major corporate backing getting
> involved, we can't possibly implement our own PG-FS for database support.  We
> already have a TODO list which is far too long for our developer pool, and
> implementing a custom FS either takes a large team (OCFS) or several years of
> development (Reiser).

Is there any documentation as to what guarantees PostgreSQL requires
from the filesystem, or what posix semantics can be relaxed?

Cheers,
  Steve

...and on Wed, Apr 07, 2004 at 09:09:16AM -0700, Josh Berkus used the keyboard:
>
> Does it work, though?   Without Oracle admin tools?

Hello, Josh. :)

Well, as I said, that's why I was asking - I'm willing to give it a go
if nobody can prove me wrong. :)

> > Now, if both goals can be achieved in one go, hell, I'm willing to try
> > it out myself in an attempt to extract off of it, some performance
> > indicators that could be compared to other database performance tests
> > sent to both this and the PERFORM mailing list.
>
> Hey, any test you wanna run is fine with us.    I'm pretty sure that OCFS
> belongs to Oracle, though, patent & copyright, so we couldn't actually use it
> in practice.

I thought you knew - OCFS, OCFS-Tools and OCFSv2 have not only been open-
source for quite a while now - they're released under the GPL.

    http://oss.oracle.com/projects/ocfs/
    http://oss.oracle.com/projects/ocfs-tools/
    http://oss.oracle.com/projects/ocfs2/

I don't know what that means to you (probably nothing good, as PostgreSQL
is released under the BSD license), but it most definitely can be considered
a good thing for the end user, as she can download it, compile, and set it
up on her disks, without the need to pay Oracle royalties. :)

> If your intention in this test is to show the superiority of raw devices, let
> me give you a reality check: barring some major corporate backing getting
> involved, we can't possibly implement our own PG-FS for database support.  We
> already have a TODO list which is far too long for our developer pool, and
> implementing a custom FS either takes a large team (OCFS) or several years of
> development (Reiser).

Not really - I was just thinking about something not-entirely-a-filesystem
and POK!, OCFS sprang to mind. It omits many POSIX features that slow down
a traditional filesystem, yet it does know the concept of inodes and most
of all, it's _really_ heavy on caching. As such, it sounded quite promising
to me, but trial, I think, is the best test.

The question does spring up though, that Steve raised in another post - just
for the record, what POSIX semantics can a postmaster live without in a
filesystem?

Cheers,
--
    Grega Bremec
    Senior Administrator
    Noviforum Ltd., Software & Media
    http://www.noviforum.si/

Grega,

> Well, as I said, that's why I was asking - I'm willing to give it a go
> if nobody can prove me wrong. :)

Why not?   If you have time?

> I thought you knew - OCFS, OCFS-Tools and OCFSv2 have not only been open-
> source for quite a while now - they're released under the GPL.

Keen!   Wonder if we can make them regret it.

Seriously, if Oracle opened this stuff, it's probably becuase they used some
GPL components in it.   It also probably means that it won't work for
anything but Oracle ...

> I don't know what that means to you (probably nothing good, as PostgreSQL
> is released under the BSD license),

Well, it just means that we can't ship OCFS with PostgreSQL.

> The question does spring up though, that Steve raised in another post -
> just for the record, what POSIX semantics can a postmaster live without in
> a filesystem?

You might want to ask that question again on Hackers.  I don't know the
answer, myself.

--
Josh Berkus
Aglio Database Solutions
San Francisco