On Tue, Sep 18, 2001 at 12:50:03AM +0100, Lars Hecking wrote:
>  
> >  There appears to be some improvement. I started a download via scp and
> >  a kernel compile, and the download does continue - mostly. Looking at the
> >  modem leds, it sometimes stalls for a few seconds, but then continues.
> 
>  Also, the rate of ser0 silo overflows has increased about tenfold,
>  compared to previous log entries:
> 
> Sep 18 00:34:19 localhost /netbsd: ser0: silo overflow
> Sep 18 00:35:00 localhost /netbsd: ser0: silo overflow
> Sep 18 00:36:42 localhost last message repeated 65 times
> Sep 18 00:46:50 localhost last message repeated 264 times

This _might_ be because the serial line isn't blocked as often, so it gets
more work done....

You should look at hm netstat -I ppp0, and compare 

	Ierrs / (Ipkgt after transfer) - Ipkts before transfer)

for both kernels. I'll look at the siopng driver later; there is a small
possibility of improvement there (that is, decreasing the scsi dma to cpu
access ratio). Watch out for more patch instructions.

(Well - the real patch should depend on ser being defined and maybe
ser baud rate in use - I don't like punishing others for the few who dare
to use this hardware.)

Regards,
	-is