Re: Socket destroy delayed/3c590 woes., etc.

kernel@hobbes.disi.unige.it
Sun, 24 Mar 1996 19:39:17 +0100 (MET)


On Sun, 24 Mar 1996, Chris Evans wrote:

> The first transmit timeout occurred when I telnetted in to the machine
> and ran lastcomm, the fast output of the command was enough to cause the
> timeout (!). Subseqent timeouts were caused by my attempts to get
> /etc/XF86Config (~11k) off the server via ftp.
>
> Hope you can get the 3c590 driver working soon. Incidentally, did the
> fixing patch posted here a few days ago work? And without my loss of my
> 800k+/sec performance?

I measured the performance of my revised version of the "Vortex" driver.
I have two 3c590 cards, one with 8K buffer and one with 32K buffer. In the
former case I had 510 KB/sec, in the latter case I had 650 KB/sec. With
the old "Vortex" driver I had nothing significant in the former case, since
it didn't work, and 650 KB/sec in the latter case.

These values were obtained by FTP "put"ting a 30 MB file through the
local network at my Department. I had 750 KB/sec by FTPing between two
machines in isolation, with the 32K adapter.

I think that if you have a 3c590 equipped with a buffer of 32KB, my patch
won't hurt your performance. If you have a buffer of 8K, the loss of
performance will be significant.

Giuseppe

|----------------------------------------------------------------------|
| Giuseppe Ciaccio e-mail : ciaccio@disi.unige.it |
| phone, address: finger ciaccio@disi.unige.it |
|----------------------------------------------------------------------|