On Wed, May 03, 2000 at 11:34:06PM -0500, shane wrote:
> More Info on this is available by emailing me, unless this problem can get
> fixed, I will have to pull the linux installed servers and replace with
> FreeBSD 4.0, bacause I have tested FreeBSD and it worked out of the box at
> about the same speed talking to the Sparc, as 2 sparcs talking to each
> other, about 8-9MB/sec
I have seen linux boxes saturate 100Mbit when talking to Solaris. So
something appears broken.
> > General info: Linux is on Compaq 2500 Server, 320M/Ram, RAID disk array,
> > 100M/TX Intel Etherpro100 PCI Card. Connected to a cisco Catalyst
> > switch.
The eepro100 drivers has had *major* problems in linux 2.2.14 and lower. Now
I'm not aware of this causing any slowdowns, but never the less, an upgrade
to 2.2.15 is in order for all parties using the eepro100 - a solid lockup is
always just around the corner.
> I can summarize it as this:
>
> The Sun used a larger window (64K versus 32K).
I think you need a larger window in order to support high speed transfers on
100Mbit.
> doesn't do that. Delays were from 100 mseconds to 400 milliseconds in
> this condition. As I said, it happend 5 times (out of 14258 packets),
> but contributed to 30% of the total time..
This happened because the window was full. With a larger window, no packets
would have been dropped.
> The Sun had a 320 microsecond delay between sending two packets with
> "P" bits set. The "P" bit (PUSH) bit) is usually set at the end of a
> buffer, so this is small, but it occured 9089 times, which contributed
> to a total of 2.9 seconds. (The max was 1 millisecond). Therefore the
> Sun could be faster. This is where the bottleneck is on the Sun side
> it. Maybe a faster CPU would perform better. This is 30% of the time,
> and 63% of the packets.
The Sun TCP/IP stack knows how fast it can send data to the Linux box and
therefore needs to slow down a bit. This has nothing to do with the CPU.
My advice: check that you have Large windows turned on, both in the kernel
and in /proc/sys/net/ipv4/tcp_window_scaling. It may also be the case that
your application is setting the window size, in which case, it shouldn't :-)
Regards,
bert hubert
--
| http://www.rent-a-nerd.nl
| - U N I X -
| Inspice et cautus eris - D11T'95
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun May 07 2000 - 21:00:14 EST