This is the mail archive of the ecos-discuss@sources.redhat.com mailing list for the eCos project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: ethernet performance <TCPIP guru question>


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


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]