WimMark I report for 2.5.66-mm3

WimMark I report for 2.5.66-mm3

[Joel Becker]

WimMark I report for 2.5.66-mm3 

Runs (deadline):  1736.51 1681.50 1010.98
Runs (antic):  579.62 496.75 517.06

	WimMark I is a rough benchmark we have been running
here at Oracle against various kernels.  Each run tests an OLTP
workload on the Oracle database with somewhat restrictive memory
conditions.  This reduces in-memory buffering of data, allowing for
more I/O.  The I/O is read and sync write, random and seek-laden.
	The benchmark is called "WimMark I" because it has no
official standing and is only a relative benchmark useful for comparing
kernel changes.  The benchmark is normalized an arbitrary kernel, which
scores 1000.0.  All other numbers are relative to this.
	The machine in question is a 4 way 700 MHz Xeon machine with 2GB
of RAM.  CONFIG_HIGHMEM4GB is selected.  The disk accessed for data is a
10K RPM U2W SCSI of similar vintage.  The data files are living on an
ext3 filesystem.  Unless mentioned, all runs are
on this machine (variation in hardware would indeed change the
benchmark).


-- 

"Gone to plant a weeping willow
 On the bank's green edge it will roll, roll, roll.
 Sing a lulaby beside the waters.
 Lovers come and go, the river roll, roll, rolls."

Joel Becker
Senior Member of Technical Staff
Oracle Corporation
E-mail: joel.becker@oracle.com
Phone: (650) 506-8127

Re: WimMark I report for 2.5.66-mm3

[Nick Piggin]

Joel Becker wrote:

>WimMark I report for 2.5.66-mm3 
>
>Runs (deadline):  1736.51 1681.50 1010.98
>Runs (antic):  579.62 496.75 517.06
>
For the moment AS has dropped a heuristih which previously seemed
to bring it to the 1000-1500 mark. That said it is still not up
to scratch on sync write benchmarks. I will work on this after
some generic block layer stuff gets in. Probably a week or two
away.

Re: WimMark I report for 2.5.66-mm3

[Hugh Dickins]

On Fri, 4 Apr 2003, Joel Becker wrote:

> WimMark I report for 2.5.66-mm3 
> 
> Runs (deadline):  1736.51 1681.50 1010.98
> Runs (antic):  579.62 496.75 517.06
> 
> 	WimMark I is a rough benchmark we have been running
> here at Oracle against various kernels.  Each run tests an OLTP
> workload on the Oracle database with somewhat restrictive memory
> conditions.  etc. etc. etc.

No doubt the people who need to know do already know, but each time
you post this I wish that the long exegesis accompanying the numbers
would say whether a big number is better or worse than a small number.

Hugh

Re: WimMark I report for 2.5.66-mm3

[Joel Becker]

On Fri, Apr 04, 2003 at 08:45:01PM +0100, Hugh Dickins wrote:
> No doubt the people who need to know do already know, but each time
> you post this I wish that the long exegesis accompanying the numbers
> would say whether a big number is better or worse than a small number.

	Duly noted, and I'll go to it.  You are right.  In addition, I'm
still waiting on the server to post history of these numbers.

Joel

-- 

"The first thing we do, let's kill all the lawyers."
                                        -Henry VI, IV:ii

Joel Becker
Senior Member of Technical Staff
Oracle Corporation
E-mail: joel.becker@oracle.com
Phone: (650) 506-8127

Re: WimMark I report for 2.5.66-mm3

[Nick Piggin]

Hugh Dickins wrote:

>On Fri, 4 Apr 2003, Joel Becker wrote:
>
>
>>WimMark I report for 2.5.66-mm3 
>>
>>Runs (deadline):  1736.51 1681.50 1010.98
>>Runs (antic):  579.62 496.75 517.06
>>
>>	WimMark I is a rough benchmark we have been running
>>here at Oracle against various kernels.  Each run tests an OLTP
>>workload on the Oracle database with somewhat restrictive memory
>>conditions.  etc. etc. etc.
>>
>
>No doubt the people who need to know do already know, but each time
>you post this I wish that the long exegesis accompanying the numbers
>would say whether a big number is better or worse than a small number.
>
A bigger number is better. AS does have something missing
in recent mms due to a bad interaction with SCSI, but it
is still around 20% below deadline for this test. It is
being worked on.