Windows Scheduling on I/O bound systems with >2 cores/processors/h

Tech-Archive recommends: Speed Up your PC by fixing your registry



Hi,

We are running Load test on our PCI IO card(WDF driver), we find differnt
observations on >2cores/processor/hyper thread systems, here are the
observations:

The test spawns multiple processes and allows them to run a continuous read
write loop for a fixed period of time.

On machines with <= 2 processors, cores or hyper threads the system would
schedule the process in a round robin fashion. A process would get scheduled
and run a pass of the read loop, then another process would do the same thing.
==> This is working perfectly fine for dual core & tested till 256 processes.

On machines with >2 processors a single process would execute its read loop
for several passes taking up to 10 seconds with the other process idle.
==> Not sure about why the windows XP os scheduling is differ on these
systems?

Using a PCI analyzer and an instrumented driver it was shown that on the
failing system some process where getting starved

Any clues, suggestions are welocme.
This is tested only on XP-32 OS only, but we definetely wanted to work on
xp-32 also.
Kindly let me know, if you need any more info.

Thanks,
Kota
.



Relevant Pages

  • Re: PROBLEM: 2.6.23-rc "NETDEV WATCHDOG: eth0: transmit timed out"
    ... 2.6.23-rc1 I have trouble with my network connection. ... # Bus options (PCI, PCMCIA, EISA, MCA, ISA) ... # PCCARD support ... # Generic Driver Options ...
    (Linux-Kernel)
  • IDE:PORTS ALREADY IN USE | USB: irq 11: nobody cared! | loop pcmcia_core.ko which needs pcmcia_core.
    ... VP_IDE: IDE controller at PCI slot 0000:00:11.1 ... USB no longer working. ... irq 11: nobody cared! ... 15 nodes reported by PnP BIOS; 15 recorded by driver ...
    (Linux-Kernel)
  • only a single core (out of 8) initialized
    ... this is 2.6.30-rc7 with a patch added to debug a nv sata driver incompatibility with the Intel SSDs on a tyan motherboard ... kernel direct mapping tables up to d7fd0000 @ 10000-16000 ... Allocating PCI resources starting at f1000000 ... CPU: L2 Cache: 1024K ...
    (Linux-Kernel)
  • 2.6.15-rc5-mm2 does not boot on AMD64 with sata_sil
    ... Using ACPI for IRQ routing ... Uniform CD-ROM driver Revision: 3.20 ... Using ACPI for SMP configuration information Allocating PCI resources starting at e2000000 Checking aperture... ... Real Time Clock Driver v1.12 hw_random: AMD768 system management I/O registers at 0x8000. ...
    (Linux-Kernel)
  • kernel error
    ... but USB mouse is detected ... card driver dont work correctly) ... Failure registering Root Plug module with the kernel ... PCI: MCFG area at f0000000 reserved in E820 ...
    (Linux-Kernel)