>>>>> "Jason" == Jason Thorpe <thorpej@nas.nasa.gov> writes:

Jason> On Wed, 28 Feb 1996 20:19:07 -0500 (EST) David Gilbert
Jason> <dgilbert@jaywon.pci.on.ca> wrote:

>> I don't know what people have been doing, but now, using the same
>> config file as a week ago, I get a kernel that is nearly 10x slower
>> for disk operations.
>> 
>> My Sun4/260 usually takes about 5 minutes to fsck it's 5 disks (5
>> partitions, 2 of the disks are one ccd).  With Monday's Sup, it's
>> taking nearly 45 minutes.  The whole thing 'in use' is slow, too
>> --- X and launching applications is noticably slower.

Jason> It turns out this is my fault.  The MI 5380 code did something
Jason> I didn't really expect to force *polling* (i.e. non-interrupt
Jason> driven I/O) during regular operation.  The change I made to
Jason> keep the si driver from using DVMA during a crash dump worked
Jason> on my system, because I use interrupt-driver I/O, but according
Jason> to your kernel config, you do not.

Jason> I've backed out the offending change.

	Why did it continue to be dog slow when I used flags=0x7?
Doesn't that turn on all the features including interupts?  Or... is
this something else that you're working on?

Dave.

-- 
----------------------------------------------------------------------------
|David Gilbert, PCI, Richmond Hill, Ontario.  | Two things can only be     |
|Mail:      dgilbert@jaywon.pci.on.ca         |  equal if and only if they |
|http://www.pci.on.ca/~dgilbert               |   are precisely opposite.  |
---------------------------------------------------------GLO----------------