Re: [rtl] Stability Problems while generating 1KHz signals

["Hermann Lauer" <Hermann.Lauer@IWR.Uni-Heidelberg.De>]

On Oct 6,  7:45pm, yodaiken@chelm.cs.nmt.edu wrote:
> Subject: Re: [rtl] Stability Problems while generating 1KHz signals
>
> Which kernel patch? I have not seen such bad numbers even on our 486.
> I'd like to see more details of the problem. Do you have an old IDE/ISA
> controller?  What happens when you run sched_toggle?

Sorry, I forgot that to mention:

Linux 2.0.35

release9E and release9F (I don't like that names, maybe it could changed to
something more reasonabel, like RTlinux0.9F ?)

No IDE is used, maybe we should disable it (if possible in BIOS)? Has an
adaptec scsi controller:

Adaptec AIC7xxx driver version: 5.0.19/3.2.4
Compile Options:
  AIC7XXX_RESET_DELAY    : 15
  AIC7XXX_TAGGED_QUEUEING: Adapter Support Enabled
                             Check below to see which
                             devices use tagged queueing
  AIC7XXX_PAGE_ENABLE    : Enabled (This is no longer an option)
  AIC7XXX_PROC_STATS     : Disabled

Adapter Configuration:
           SCSI Adapter: Adaptec AHA-294X SCSI host adapter
                           Narrow Controller
    PCI MMAPed I/O Base: 0xfafff000
      Adaptec SCSI BIOS: Enabled
                    IRQ: 11
                   SCBs: Active 0, Max Active 1,
                         Allocated 30, HW 16, Page 255
             Interrupts: 1753
      BIOS Control Word: 0x10b6
   Adapter Control Word: 0x001d
   Extended Translation: Enabled
Disconnect Enable Flags: 0x00ff
 Tag Queue Enable Flags: 0x0000
Ordered Queue Tag Flags: 0x0000
Default Tag Queue Depth: 8
    Tagged Queue By Device array for aic7xxx host instance 0:
      {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
    Actual queue depth per device for aic7xxx host instance 0:
      {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}

How to figure out the ISA controller ?

Sched_toggle exhibts the same behavior - sometimes the stepper motor pops and
on the overlay on the oszilloscope you see irregularities of on to five
periods.
If I have time, i could test it on an 486 which we tried first and also don't
work - but has also an adaptec - could that be a problem ?

Many thaks for your quick answer.

Greetings Hermann

>
>
> BTW: This has nothing to do with bottom halves. No linux code can
> delay a RTLinux task.
--- [rtl] ---
To unsubscribe:
echo "unsubscribe rtl" | mail majordomo@rtlinux.cs.nmt.edu OR
echo "unsubscribe rtl <Your_email>" | mail majordomo@rtlinux.cs.nmt.edu
----
For more information on Real-Time Linux see:
http://www.rtlinux.org/~rtlinux/