WimMark I report for 2.5.66-mm3
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).
Signature · 10 lines
"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: [email protected] Phone: (650) 506-8127
Quoted 5 lines · 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
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.
Quoted 9 lines · Joel Becker
WimMark I report for 2.5.66-mm3
Runs (deadline): 1736.51 1681.50 1010.98 Runs (antic): 579.62 496.75 517.06WimMark 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
Quoted 14 lines · Hugh Dickins
Quoted 10 lines · Joel Becker
WimMark I report for 2.5.66-mm3
Runs (deadline): 1736.51 1681.50 1010.98 Runs (antic): 579.62 496.75 517.06WimMark 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.
Quoted 4 lines
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.
Quoted 3 lines · Hugh Dickins
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
Signature · 8 lines
"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: [email protected]
Phone: (650) 506-8127