This is the mail archive of the
ecos-discuss@sources.redhat.com
mailing list for the eCos project.
Re: ethernet performance <TCPIP guru question>
- From: Stephen Polkowski <stephen at centtech dot com>
- To: Gary Thomas <gthomas at redhat dot com>
- Cc: eocs <ecos-discuss at sources dot redhat dot com>
- Date: Thu, 25 Apr 2002 10:14:32 -0500
- Subject: Re: [ECOS] ethernet performance <TCPIP guru question>
- References: <3CC74F46.1050502@centtech.com> <1019698792.16361.133.camel@hermes>
Thanks for the quick response! The ECOS machine is 1.1.1.3. When
data arrives, I read the data into a temp 16k buffer. Then, I write the
data into an open file on the RAMFS. Perhaps this buffer copying is too
slow.
I wish there was a to take 4k receive buffers from the kernel and pass
the memory to the RAMFS like a paging system could. Is there a better
way to this?
BTW, would the ECOS team like to have my ftpd.c code once it is
finished? The code is a simplification of the troll ftpd.c. The only
problem is that it requires "net" and "ramfs" support, so it wouldn't
work as a simple test in the "net" group.
Thanks again,
Steve
Gary Thomas wrote:
> On Wed, 2002-04-24 at 18:35, Stephen Polkowski wrote:
>
>>Hello,
>>
>> I've been working on a simple ftp server for ECOS. I have it up
>>and working on the intel pc using the 82559 ethernet card. I'm also
>>using redboot to load my application over the ethernet.
>>
>> When I ftp a file to my server application I seeing some really
>>slow ethernet speeds. I have a 100Mb ethernet running on a 2Ghz Pentium
>> IV. So, my system should be fast enough to handle the data. I'm
>>getting about 65k bytes a second transfer rate. I should be get getting
>>something close to 10M bytes a second. What's the problem?
>>
>>
>
> I've tested TCP operations with eCos, using 100Mb interfaces, and I get
> transfer rates of around 8Mbytes/sec (Linux host, sending data to an
> eCos application which simply sinks the data).
>
>
>> I did a tcpdump from my Linux machine. I've noticed two things.
>>First, the TCP window size in ECOS isn't sliding during the transfer.
>>This might be confusing the sender, I'm not sure. Also, I see a burst
>>of data packets and ACKS from ECOS which appear good. Then all of a
>>sudden, ECOS starts to ACK to the same packet over and over. After a
>>few more acks, the sequence resumes. Is this normal? Does this explain
>>the slow network performance?
>>
>>Here's the dump of the burst sequence running into the ACK sequence.
>>
>>Thanks.
>>
>>
>
> Which IP address is the eCos side?
> I assume from your description that the eCos "server" program is being
> sent the data. What does it do with it when it arrives?
>
>
>>1.1.1.2.55961 > 1.1.1.3.ftp-data: . 1507369:1508817(1448) ack 1 win 5792
>>1.1.1.2.55961 > 1.1.1.3.ftp-data: . 1508817:1510265(1448) ack 1 win 5792
>>1.1.1.2.55961 > 1.1.1.3.ftp-data: . 1510265:1511713(1448) ack 1 win 5792
>>1.1.1.2.55961 > 1.1.1.3.ftp-data: . 1511713:1513161(1448) ack 1 win 5792
>>1.1.1.2.55961 > 1.1.1.3.ftp-data: P 1513161:1514609(1448) ack 1 win 5792
>>1.1.1.3.ftp-data > 1.1.1.2.55961: . ack 1513161 win 18824
>>
>
>
>
--
Stephen Polkowski
Centaur Technology
Austin, TX
(512) 418-5730
--
Before posting, please read the FAQ: http://sources.redhat.com/fom/ecos
and search the list archive: http://sources.redhat.com/ml/ecos-discuss