oracle benchmarks on VMS

oracle benchmarks on VMS

Post by Tim Smi » Tue, 04 Mar 2003 15:39:05



I see Oracle publishes some benchmarks at
http://www.oracle.com/apps_benchmark/, but notably there is nothing
for VMS - is that because Oracle writes to the filesystem, not direct
to device file files directly i.e. VMS filesystem is a lot slower than
raw devices?

If anyone has older benchmarks that include VMS I would like to see
them.

thanks!

Tim

 
 
 

oracle benchmarks on VMS

Post by Hein van den Heuve » Wed, 05 Mar 2003 06:15:21



> I see Oracle publishes some benchmarks at
> http://www.oracle.com/apps_benchmark/, but notably there is nothing
> for VMS - is that because Oracle writes to the filesystem, not direct
> to device file files directly i.e. VMS filesystem is a lot slower than
> raw devices?

It has nothing to do with (potential) speed.
It is just a commercial / marketing decision mostly from Oracle.
They decided there was not enough critical mass to maintain support for
the Oracle Applicaiton suite on VMS. The database itself is and will be
supported at one of the higher tier levels. Details are not up to me, but
it used to be product release on VMS 90 days after first release. Please
verify with Oracle. They may also choose to skip 'dot' releases. Dunno,
let's say they had 9.0, skipped 9.1 but released 9.2. Again, this is not a
statement of support, just a line of thinking. Check with Oracle.

The VMS Filesystem is actually an advantage! The VMS filesystem does NOT
buffer data.
On Unix systems the OS tends to waste time and memory buffering Oracle
data pages which are better managerd by Oracle in its buffer pool (SGA).
On many Unix implementation, for ultimate Oracle perfromance once has to
deal with hard-to-manage 'Raw Devices' to avoid said buffering.
On VMS you have the comfort of a file system for Alloaction, Naming and
backups yet the speed of a raw device. On HP Tru64 Unix Oracle can (and
will) use the DIRECT IO feature to get the same effect on single systems
as well as in clusters.

Quote:> If anyone has older benchmarks that include VMS I would like to see
> them.

It would be nice to see some VMS / Oracle benchmark, but I will not hold
my breath.
Benchmarks require major investment which both companies believe is better
spend on the products itself. VMS will offer comparable (ballpark)
performance as Unix on the same platform.
It will not be 2x slower. It might be a little slower or a a little faster
depending on the application.
The performance will be close enough to focus on other, more important,
platform decision factors: Cost-of-ownership, Reliability, Availability,
Experience, Applications, Installed base,..

Hope this helps some, but it is just an opinion from a guy in the
sidelines.
Be sure to contact officials at Oracle and HP for the official positions.

Cheers,
    Hein.

 
 
 

oracle benchmarks on VMS

Post by Bill Tod » Wed, 05 Mar 2003 08:47:03




...

Quote:> On Unix systems the OS tends to waste time and memory buffering Oracle
> data pages which are better managerd by Oracle in its buffer pool (SGA).
> On many Unix implementation, for ultimate Oracle perfromance once has to
> deal with hard-to-manage 'Raw Devices' to avoid said buffering.

Not on the most common Unixes.  Veritas' VxFS file system supports direct
(unbuffered) file I/O, and it's available pretty widely (it may even be the
standard file system on HP-UX - they had their fingers in some part of the
HP-UX data management pie, anyway).  VxFS runs on Solaris, and IIRC Sun's
own file system also supports direct I/O (not too surprising, given how
important Oracle is to them).  Linux has some form of direct I/O in 2.4,
though it may be scheduled for more massaging to eliminate some kludgery.
VxFS was recently ported to AIX (I don't know whether their native JFS
supports direct I/O, though).

(Many Unixes support asynchronous I/O too, but AFAIK none as well as VMS:
they - and the POSIX asynchrony model - never seemed to understand how
completion processing should work.)

- bill

 
 
 

oracle benchmarks on VMS

Post by John Smit » Wed, 05 Mar 2003 11:21:47





> > I see Oracle publishes some benchmarks at
> > http://www.oracle.com/apps_benchmark/, but notably there is
nothing
> > for VMS - is that because Oracle writes to the filesystem, not
direct
> > to device file files directly i.e. VMS filesystem is a lot slower
than
> > raw devices?

> It has nothing to do with (potential) speed.
> It is just a commercial / marketing decision mostly from Oracle.
> They decided there was not enough critical mass to maintain support
for
> the Oracle Applicaiton suite on VMS.

Sorry Hein, nothing against you.....
Once again HP self-limits the market for VMS by not advertising, and
by doing so, makes it easy for sales to go to Sun/IBM/Dell.

Quote:> It would be nice to see some VMS / Oracle benchmark, but I will not
hold
> my breath.
> Benchmarks require major investment which both companies believe is
better
> spend on the products itself. VMS will offer comparable (ballpark)
> performance as Unix on the same platform.

They'll never benchmark (ie. spend the money) on what they consider to
be a 'fringe' platform.

Just thinking about HP's lack of advertising and marketing of VMS
makes me think of the event horizon of a black hole - VMS keeps
spinning around just microns above the event horizon, with a minor
perturbation in the gravitational flux ready to send it slipping below
the event horizon for good.

 
 
 

oracle benchmarks on VMS

Post by Andrew Harrison SUNUK Consultanc » Wed, 05 Mar 2003 20:37:25






>>>I see Oracle publishes some benchmarks at
>>>http://www.oracle.com/apps_benchmark/, but notably there is

> nothing

>>>for VMS - is that because Oracle writes to the filesystem, not

> direct

>>>to device file files directly i.e. VMS filesystem is a lot slower

> than

>>>raw devices?

>>It has nothing to do with (potential) speed.
>>It is just a commercial / marketing decision mostly from Oracle.
>>They decided there was not enough critical mass to maintain support

> for

>>the Oracle Applicaiton suite on VMS.

> Sorry Hein, nothing against you.....
> Once again HP self-limits the market for VMS by not advertising, and
> by doing so, makes it easy for sales to go to Sun/IBM/Dell.

Well in this case its just as well that HP does self limit
the market by not advertising because the point that Hein
is making is incorrect and has been for 6-7 years on most
UNIX platforms.

regards
Andrew Harrison

 
 
 

oracle benchmarks on VMS

Post by Andrew Harrison SUNUK Consultanc » Wed, 05 Mar 2003 20:35:36




>>I see Oracle publishes some benchmarks at
>>http://www.oracle.com/apps_benchmark/, but notably there is nothing
>>for VMS - is that because Oracle writes to the filesystem, not direct
>>to device file files directly i.e. VMS filesystem is a lot slower than
>>raw devices?
> The VMS Filesystem is actually an advantage! The VMS filesystem does NOT
> buffer data.
> On Unix systems the OS tends to waste time and memory buffering Oracle
> data pages which are better managerd by Oracle in its buffer pool (SGA).
> On many Unix implementation, for ultimate Oracle perfromance once has to
> deal with hard-to-manage 'Raw Devices' to avoid said buffering.
> On VMS you have the comfort of a file system for Alloaction, Naming and
> backups yet the speed of a raw device. On HP Tru64 Unix Oracle can (and
> will) use the DIRECT IO feature to get the same effect on single systems
> as well as in clusters.

On most UNIX's you now have direct I/O which avoids the buffer
cache. Solaris UFS+ supports direct I/O, VxFS does, IBM JFS does
etc.

And the buffer cache isn't always a disadvantage since it can
act as a cache for reads but it doesn't help writes and it
does consume VM resources.

Because most UNIX filesystems support DIRECT I/O and because
differential between RAW and COOKED is now negligable very few
people use RAW devices anymore.

With COOKED obviously giving you the advantages of log based
filesystems, snapshots, growing filesystems, shrinking filesystems
(VxFS) etc but with the performance of RAW.

Regards
Andrew Harrison

 
 
 

oracle benchmarks on VMS

Post by Tim Smi » Fri, 07 Mar 2003 08:08:19




> > I see Oracle publishes some benchmarks at
> > http://www.oracle.com/apps_benchmark/, but notably there is nothing
> > for VMS - is that because Oracle writes to the filesystem, not direct
> > to device file files directly i.e. VMS filesystem is a lot slower than
> > raw devices?

> It has nothing to do with (potential) speed.
> It is just a commercial / marketing decision mostly from Oracle.
> They decided there was not enough critical mass to maintain support for
> the Oracle Applicaiton suite on VMS. The database itself is and will be
> supported at one of the higher tier levels. Details are not up to me, but
> it used to be product release on VMS 90 days after first release. Please
> verify with Oracle. They may also choose to skip 'dot' releases. Dunno,
> let's say they had 9.0, skipped 9.1 but released 9.2. Again, this is not a
> statement of support, just a line of thinking. Check with Oracle.

> The VMS Filesystem is actually an advantage! The VMS filesystem does NOT
> buffer data.
> On Unix systems the OS tends to waste time and memory buffering Oracle
> data pages which are better managerd by Oracle in its buffer pool (SGA).
> On many Unix implementation, for ultimate Oracle perfromance once has to
> deal with hard-to-manage 'Raw Devices' to avoid said buffering.
> On VMS you have the comfort of a file system for Alloaction, Naming and
> backups yet the speed of a raw device. On HP Tru64 Unix Oracle can (and
> will) use the DIRECT IO feature to get the same effect on single systems
> as well as in clusters.

> > If anyone has older benchmarks that include VMS I would like to see
> > them.

> It would be nice to see some VMS / Oracle benchmark, but I will not hold
> my breath.
> Benchmarks require major investment which both companies believe is better
> spend on the products itself. VMS will offer comparable (ballpark)
> performance as Unix on the same platform.
> It will not be 2x slower. It might be a little slower or a a little faster
> depending on the application.
> The performance will be close enough to focus on other, more important,
> platform decision factors: Cost-of-ownership, Reliability, Availability,
> Experience, Applications, Installed base,..

> Hope this helps some, but it is just an opinion from a guy in the
> sidelines.
> Be sure to contact officials at Oracle and HP for the official positions.

> Cheers,
>     Hein.

That makes sense, and I appreciate your comments.  The only problem I
have is that I find that simple I/O operations are much slower on VMS
than AIX.  I understand that this is a complex topic dependent on disk
subsystems, disk speeds, etc etc but take this for example:

I have two systems, one a Alpha 4100 with VMS 7.1 and a RS6000 H-50
both with 2GB RAM and 2 processors.  These systems were purchased
around the same time for the same purpose and I would term them as
comparable.  I did simple file copies from the same disk to same disk.
 While I do not have the disk speeds, I used an older disk on the AIX
(4GB) and a newer disk on VMS (12GB).   I don't believe there was any
fragmentation to consider.

AIX: 297MB - 2MB/second, if repeated -  2.84MB/second

VMS: 297MB - 1.02MB/second, if repeated - 1.19MB/second

I don't mean to bash VMS, I just am trying to understand if it really
comes close for I/O performance.  I've seen several places that have
to through a lot of hardware at performance bound applications.  Any
time I've done SQLPlus inserts they have been a lot faster on AIX.  I
know that many people still prefer VMS so I am trying to figure out
why...

Tim

 
 
 

oracle benchmarks on VMS

Post by Robert Deining » Fri, 07 Mar 2003 22:39:43




>That makes sense, and I appreciate your comments.  The only problem I
>have is that I find that simple I/O operations are much slower on VMS
>than AIX.  I understand that this is a complex topic dependent on disk
>subsystems, disk speeds, etc etc but take this for example:

>I have two systems, one a Alpha 4100 with VMS 7.1 and a RS6000 H-50
>both with 2GB RAM and 2 processors.  These systems were purchased
>around the same time for the same purpose and I would term them as
>comparable.  I did simple file copies from the same disk to same disk.
> While I do not have the disk speeds, I used an older disk on the AIX
>(4GB) and a newer disk on VMS (12GB).   I don't believe there was any
>fragmentation to consider.

>AIX: 297MB - 2MB/second, if repeated -  2.84MB/second

>VMS: 297MB - 1.02MB/second, if repeated - 1.19MB/second

I know nothing about the RS6000 hardware, and only a little about the
AlphaServer 4100.  But your result leaves so many variables unspecified
that I think it says NOTHING about the capabilities of either operating
system.

Details of the disks are important.  Alphaserver disks are usually
selected for performance, at least in part.  Aftermarket add-on disks are
more often selected for low cost.  Your 12GB disk is an odd size for a
4100, so I guess it's aftermarket.  It could easily be slower than the
older, smaller disk.

Were the disks on the same SCSI bus?  Were the SCSI adapters in the same
PCI bus?

The fact that both systems showed significant changes for the "repeat"
tests indicates that there is some caching happening somewhere.  To
account for that, you have to account for all the cache- and
memory-related adjustments on both systems.

On VMS, there are many variables in how you do the I/O, and how you tune
certain knobs in the process.  The defaults are very often far from
optimal, and this is a real and legitimate complaint against VMS.  RMS has
some well-known bottlenecks.  But a little well-placed tuning can have a
huge benefit.

And you might not have the defaults, you might have inherited something
even worse.

Similar comments may apply to AIX, but I dunno about that.

Your VMS version is antiquated, and in some situations isn't a very good
predictor of how current VMS (V7.3-1) would perform.

Quote:>I don't mean to bash VMS, I just am trying to understand if it really
>comes close for I/O performance.  I've seen several places that have
>to through a lot of hardware at performance bound applications.  Any
>time I've done SQLPlus inserts they have been a lot faster on AIX.  I
>know that many people still prefer VMS so I am trying to figure out
>why...

The area where VMS shines is reliability.  For many, that is worth more
than a moderate boost in performance.

It is good that you are trying to understand.  Tests of other people's
workloads aren't too helpful; it is your own workload that matters.  Spend
a bit of time finding your bottlenecks.  There is a VMS performance manual
in the doc set.  If you find a bottleneck, you can usually get advice
(here and elsewhere) that will help you eliminate it.

For your disk-to-disk file copy on VMS, what where your process quotas and
RMS parameters?

 
 
 

oracle benchmarks on VMS

Post by Andrew Harrison SUNUK Consultanc » Sat, 08 Mar 2003 00:15:42





>>That makes sense, and I appreciate your comments.  The only problem I
>>have is that I find that simple I/O operations are much slower on VMS
>>than AIX.  I understand that this is a complex topic dependent on disk
>>subsystems, disk speeds, etc etc but take this for example:

>>I have two systems, one a Alpha 4100 with VMS 7.1 and a RS6000 H-50
>>both with 2GB RAM and 2 processors.  These systems were purchased
>>around the same time for the same purpose and I would term them as
>>comparable.  I did simple file copies from the same disk to same disk.
>>While I do not have the disk speeds, I used an older disk on the AIX
>>(4GB) and a newer disk on VMS (12GB).   I don't believe there was any
>>fragmentation to consider.

>>AIX: 297MB - 2MB/second, if repeated -  2.84MB/second

>>VMS: 297MB - 1.02MB/second, if repeated - 1.19MB/second

> I know nothing about the RS6000 hardware, and only a little about the
> AlphaServer 4100.  But your result leaves so many variables unspecified
> that I think it says NOTHING about the capabilities of either operating
> system.

 From a CPU standpoint it depends on which Alpha CPU you have
in the 4100. The H50 has a 332 Mhz Power PC 604e CPU that
does 14.4 SPECint95. The 4100 ranged from 7.5 to 18.8 SPECint95
depending the CPU used.

Like the 4100 the H50 supported up to 4 CPU's.

- Show quoted text -

Quote:> Details of the disks are important.  Alphaserver disks are usually
> selected for performance, at least in part.  Aftermarket add-on disks are
> more often selected for low cost.  Your 12GB disk is an odd size for a
> 4100, so I guess it's aftermarket.  It could easily be slower than the
> older, smaller disk.

> Were the disks on the same SCSI bus?  Were the SCSI adapters in the same
> PCI bus?

> The fact that both systems showed significant changes for the "repeat"
> tests indicates that there is some caching happening somewhere.  To
> account for that, you have to account for all the cache- and
> memory-related adjustments on both systems.

> On VMS, there are many variables in how you do the I/O, and how you tune
> certain knobs in the process.  The defaults are very often far from
> optimal, and this is a real and legitimate complaint against VMS.  RMS has
> some well-known bottlenecks.  But a little well-placed tuning can have a
> huge benefit.

> And you might not have the defaults, you might have inherited something
> even worse.

> Similar comments may apply to AIX, but I dunno about that.

> Your VMS version is antiquated, and in some situations isn't a very good
> predictor of how current VMS (V7.3-1) would perform.

>>I don't mean to bash VMS, I just am trying to understand if it really
>>comes close for I/O performance.  I've seen several places that have
>>to through a lot of hardware at performance bound applications.  Any
>>time I've done SQLPlus inserts they have been a lot faster on AIX.  I
>>know that many people still prefer VMS so I am trying to figure out
>>why...

> The area where VMS shines is reliability.  For many, that is worth more
> than a moderate boost in performance.

> It is good that you are trying to understand.  Tests of other people's
> workloads aren't too helpful; it is your own workload that matters.  Spend
> a bit of time finding your bottlenecks.  There is a VMS performance manual
> in the doc set.  If you find a bottleneck, you can usually get advice
> (here and elsewhere) that will help you eliminate it.

> For your disk-to-disk file copy on VMS, what where your process quotas and
> RMS parameters?

 
 
 

oracle benchmarks on VMS

Post by Main, Kerr » Sat, 08 Mar 2003 01:38:44


Tim,

As previous reply indicated, the OpenVMS OS version (7.1) is very old -
probably about 6-7 years old right now.

Is your version of AIX also this old?

As an example of recent improvements for OpenVMS and RMS, a previous
noter on comp.os.vms was able to achieve 80% better numbers by not using
the default RMS and quota parameters and taking advantage of the
following VMS V7.3-1 info:

http://h71000.www7.hp.com/doc/731FINAL/6657/6657pro_007.html (see RMS
New features which includes write-back capability that is similar to
what UNIX systems handle IO)

http://h71000.www7.hp.com/doc/731FINAL/6657/6657pro.html (See section
1.1)

Regards

Kerry Main
Senior Consultant
Hewlett-Packard (Canada) Co.
Consulting & Integration Services
Voice: 613-592-4660
Fax   : 613-591-4477

    (remove the DOT's and replace with "."'s)
OpenVMS DCL - the original .COM

-----Original Message-----

Sent: March 5, 2003 6:08 PM

Subject: Re: oracle benchmarks on VMS




> > I see Oracle publishes some benchmarks at
> > http://www.oracle.com/apps_benchmark/, but notably there is nothing
> > for VMS - is that because Oracle writes to the filesystem, not
> > direct to device file files directly i.e. VMS filesystem is a lot
> > slower than raw devices?

> It has nothing to do with (potential) speed.
> It is just a commercial / marketing decision mostly from Oracle. They
> decided there was not enough critical mass to maintain support for the

> Oracle Applicaiton suite on VMS. The database itself is and will be
> supported at one of the higher tier levels. Details are not up to me,
> but it used to be product release on VMS 90 days after first release.
> Please verify with Oracle. They may also choose to skip 'dot'
> releases. Dunno, let's say they had 9.0, skipped 9.1 but released 9.2.

> Again, this is not a statement of support, just a line of thinking.
> Check with Oracle.

> The VMS Filesystem is actually an advantage! The VMS filesystem does
> NOT buffer data. On Unix systems the OS tends to waste time and memory

> buffering Oracle data pages which are better managerd by Oracle in its

> buffer pool (SGA). On many Unix implementation, for ultimate Oracle
> perfromance once has to deal with hard-to-manage 'Raw Devices' to
> avoid said buffering. On VMS you have the comfort of a file system for

> Alloaction, Naming and backups yet the speed of a raw device. On HP
> Tru64 Unix Oracle can (and
> will) use the DIRECT IO feature to get the same effect on single
> systems as well as in clusters.

> > If anyone has older benchmarks that include VMS I would like to see
> > them.

> It would be nice to see some VMS / Oracle benchmark, but I will not
> hold my breath. Benchmarks require major investment which both
> companies believe is better spend on the products itself. VMS will
> offer comparable (ballpark) performance as Unix on the same platform.
> It will not be 2x slower. It might be a little slower or a a little
faster
> depending on the application.
> The performance will be close enough to focus on other, more
important,
> platform decision factors: Cost-of-ownership, Reliability,
Availability,
> Experience, Applications, Installed base,..

> Hope this helps some, but it is just an opinion from a guy in the
> sidelines. Be sure to contact officials at Oracle and HP for the
> official positions.

> Cheers,
>     Hein.

That makes sense, and I appreciate your comments.  The only problem I
have is that I find that simple I/O operations are much slower on VMS
than AIX.  I understand that this is a complex topic dependent on disk
subsystems, disk speeds, etc etc but take this for example:

I have two systems, one a Alpha 4100 with VMS 7.1 and a RS6000 H-50 both
with 2GB RAM and 2 processors.  These systems were purchased around the
same time for the same purpose and I would term them as comparable.  I
did simple file copies from the same disk to same disk.  While I do not
have the disk speeds, I used an older disk on the AIX
(4GB) and a newer disk on VMS (12GB).   I don't believe there was any
fragmentation to consider.

AIX: 297MB - 2MB/second, if repeated -  2.84MB/second

VMS: 297MB - 1.02MB/second, if repeated - 1.19MB/second

I don't mean to bash VMS, I just am trying to understand if it really
comes close for I/O performance.  I've seen several places that have to
through a lot of hardware at performance bound applications.  Any time
I've done SQLPlus inserts they have been a lot faster on AIX.  I know
that many people still prefer VMS so I am trying to figure out why...

Tim

 
 
 

oracle benchmarks on VMS

Post by Kingsley Ideh » Sat, 08 Mar 2003 02:09:44





> > > I see Oracle publishes some benchmarks at
> > > http://www.oracle.com/apps_benchmark/, but notably there is nothing
> > > for VMS - is that because Oracle writes to the filesystem, not direct
> > > to device file files directly i.e. VMS filesystem is a lot slower than
> > > raw devices?

> > It has nothing to do with (potential) speed.
> > It is just a commercial / marketing decision mostly from Oracle.
> > They decided there was not enough critical mass to maintain support for
> > the Oracle Applicaiton suite on VMS. The database itself is and will be
> > supported at one of the higher tier levels. Details are not up to me, but
> > it used to be product release on VMS 90 days after first release. Please
> > verify with Oracle. They may also choose to skip 'dot' releases. Dunno,
> > let's say they had 9.0, skipped 9.1 but released 9.2. Again, this is not a
> > statement of support, just a line of thinking. Check with Oracle.

> > The VMS Filesystem is actually an advantage! The VMS filesystem does NOT
> > buffer data.
> > On Unix systems the OS tends to waste time and memory buffering Oracle
> > data pages which are better managerd by Oracle in its buffer pool (SGA).
> > On many Unix implementation, for ultimate Oracle perfromance once has to
> > deal with hard-to-manage 'Raw Devices' to avoid said buffering.
> > On VMS you have the comfort of a file system for Alloaction, Naming and
> > backups yet the speed of a raw device. On HP Tru64 Unix Oracle can (and
> > will) use the DIRECT IO feature to get the same effect on single systems
> > as well as in clusters.

> > > If anyone has older benchmarks that include VMS I would like to see
> > > them.

> > It would be nice to see some VMS / Oracle benchmark, but I will not hold
> > my breath.
> > Benchmarks require major investment which both companies believe is better
> > spend on the products itself. VMS will offer comparable (ballpark)
> > performance as Unix on the same platform.
> > It will not be 2x slower. It might be a little slower or a a little faster
> > depending on the application.
> > The performance will be close enough to focus on other, more important,
> > platform decision factors: Cost-of-ownership, Reliability, Availability,
> > Experience, Applications, Installed base,..

> > Hope this helps some, but it is just an opinion from a guy in the
> > sidelines.
> > Be sure to contact officials at Oracle and HP for the official positions.

> > Cheers,
> >     Hein.

> That makes sense, and I appreciate your comments.  The only problem I
> have is that I find that simple I/O operations are much slower on VMS
> than AIX.  I understand that this is a complex topic dependent on disk
> subsystems, disk speeds, etc etc but take this for example:

> I have two systems, one a Alpha 4100 with VMS 7.1 and a RS6000 H-50
> both with 2GB RAM and 2 processors.  These systems were purchased
> around the same time for the same purpose and I would term them as
> comparable.  I did simple file copies from the same disk to same disk.
>  While I do not have the disk speeds, I used an older disk on the AIX
> (4GB) and a newer disk on VMS (12GB).   I don't believe there was any
> fragmentation to consider.

> AIX: 297MB - 2MB/second, if repeated -  2.84MB/second

> VMS: 297MB - 1.02MB/second, if repeated - 1.19MB/second

> I don't mean to bash VMS, I just am trying to understand if it really
> comes close for I/O performance.  I've seen several places that have
> to through a lot of hardware at performance bound applications.  Any
> time I've done SQLPlus inserts they have been a lot faster on AIX.  I
> know that many people still prefer VMS so I am trying to figure out
> why...

> Tim

There is a new Free and Open Source benchmark utility that allows you
to perform objective industry standard benchmarks against any SQL
database via ODBC or JDBC. It is available for download from:
<http://www.openlinksw.com> . Note that you can perform real-time
comparative benchmarks side by side (Oracle vs SQL Server for
instance) via a visual interface.
 
 
 

1. Alpha VMS 7.1 Tape Backup vs. Oracle - Oracle wins...

We've upgraded Oracle from 7.1 to 7.3 when we also (had to ) upgrade
Alpha VMS from 6.2 to 7.1 - after that, our disk to tape backups run a
lot slower when oracle jobs (usually complex queries) are running,
mainly on the same node, but not always. Our disk to disk backups are
not usually affected.

We are running in a 4-node "FDDI" cluster, where two nodes serve all
the disks (shadowed) to the other two nodes, where we run both the
Oracle parallel server, and the backup jobs.

We've tried all the usual troubleshooting  (without Polycenter DC, no
thanks to CA), so anyone know if Oralce did optomize their code for
VMS 7.1 to really take control of I/O in a VMS cluster?

Thanks in advance!
--Gary McCready

2. Iomega ZIP drives

3. oracle for VMS vs oracle for UNIX

4. BREAK and Kermit

5. Sun new cluster comparison ommitted VMS (but VMS was their benchmark)

6. A question about faxes - it's slightly urgent!

7. VMS transactions per minute-C benchmarks

8. cdiff 1.1 patch #1

9. VMS/AXP benchmarking

10. Oracle RDB 8.0 = Oracle RDB for Itanium ????

11. Oracle V7.1 vs Oracle V7.3 performance

12. Oracle Universal Installer info/question (Oracle 8i)