slow ftp put transfer rate

Need help to solve a problem I'm having with ftp during a put operation. The
transfer rate is very slow when connected to the LAN through my wireless
card. When I execute a put operation to a second Linux workstation on the
LAN of a file that is 20MBs in size it took 352 sec to complete. When I
switched to the built-in network card of the PC the same file was put to the
same Linux workstation in 9 sec.

When I execute get through the wireless card it took 8.12 sec to complete
and with the built-in network card it took 7.56 sec to complete. So,
something is going on from the push side which I can't detect.

There nothing special about the ftp (vsftpd-2.0.5-8) configuration and the
defaults are uncommented. The PC is installed with FC6 / 2.6.18-1.2798.fc6.

--
tek

When diagnosing network performance problems I generally follow this
set of steps:

*) check for retransmissions/lost packets up at the transport layer -
that means netstat statistics for TCP when FTP is involved. On the
receiver you would likely see an increasing number of out of order
segments being received. On the sender you would see data segments
being retransmitted and perhaps retransmission timeouts.

*) if I see those, I try to check link-level statistics - in this case
that would be via ethtool on linux. (lanadmin under HP-UX, kstat
under Solaris, and knuth only knows what under Windows and the
rest...) checking stats on the switch(es) is goodness too, the
mechanism would be switch-specific.

*) if the link-level statistics show lots of _late_ collisions or
FCS/CRC errors then I look into a duplex mismatch. here is some
boilerplate about duplex and ethernet:

How 100Base-T Autoneg is supposed to work:

When both sides of the link are set to autoneg, they will "negotiate"
the duplex setting and select full-duplex if both sides can do
full-duplex.

If one side is hardcoded and not using autoneg, the autoneg process
will "fail" and the side trying to autoneg is required by spec to use
half-duplex mode.

If one side is using half-duplex, and the other is using full-duplex,
sorrow and woe is the usual result.

So, the following table shows what will happen given various settings
on each side:

Auto Half Full

Auto Happiness Lucky Sorrow

Half Lucky Happiness Sorrow

Full Sorrow Sorrow Happiness

Happiness means that there is a good shot of everything going well.
Lucky means that things will likely go well, but not because you did
anything correctly :) Sorrow means that there _will_ be a duplex
mis-match.

When there is a duplex mismatch, on the side running half-duplex you
will see various errors and probably a number of _LATE_ collisions
("normal" collisions don't count here). On the side running
full-duplex you will see things like FCS errors. Note that those
errors are not necessarily conclusive, they are simply indicators.

Further, it is important to keep in mind that a "clean" ping (or the
like - eg "linkloop" or default netperf TCP_RR) test result is
inconclusive here - a duplex mismatch causes lost traffic _only_ when
both sides of the link try to speak at the same time. A typical ping
test, being synchronous, one at a time request/response, never tries
to have both sides talking at the same time.

Finally, when/if you migrate to 1000Base-T, everything has to be set
to auto-neg anyway.


--
denial, anger, bargaining, depression, acceptance, rebirth...
where do you want to be today?
these opinions are mine, all mine; HP might not want them anyway... :)
feel free to post, OR email to rick.jones2 in hp.com but NOT BOTH...