Re: UDP packets loss

Thanks for the commets.
I actually use UDP because I am seeking for ways to improve the
performance of IPOIB and I wanted to avoid TCP's flow control. I am really
up to making anaysis. Can you tell me more about irqbalnced? Where can I
find more info how to control it? I would like my interrupts serviced by
all CPUs in a somehow equal manner. I mentioned MSIX - the driver already
make use of MSIX and I thought this is relevant to interrupts affinity.

On Wed, 15 Nov 2006 00:15:47 +0200 (IST)
eli@xxxxxxxxxxxxxxxxxx wrote:

Hi,
I am running a client/server test app over IPOIB in which the client
sends
a certain amount of data to the server. When the transmittion ends, the
server prints the bandwidth and how much data it received. I can see
that
the server reports it received about 60% that the client sent. However,
when I look at the server's interface counters before and after the
transmittion, I see that it actually received all the data that the
client
sent. This leads me to suspect that the networking layer somehow dropped
some of the data. One thing to not - the CPU is 100% busy at the
receiver.
Could this be the reason (the machine I am using is 2 dual cores - 4
CPUs).

If receiver application can't keep up UDP drops packets. The counter
receive buffer errors (UDP_MIB_RCVBUFERRORS) is incremented.

Don't expect flow control or reliable delivery; it's a datagram service!

The secod question is how do I make the interrupts be srviced by all
CPUs?
I tried through the procfs as described by IRQ-affinity.txt but I can
set
the mask to 0F bu then I read back and see it is indeed 0f but after a
few
seconds I see it back to 02 (which means only CPU1).

Most likely, the user level irq balance daemon (irqbalanced) is adjusting
it?


One more thing - the device I am using is capable of generating MSIX
interrupts.


Look at device capabilities with:

lspci -vv


--
Stephen Hemminger <shemminger@xxxxxxxx>



-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Relevant Pages

  • Re: UDP packets loss
    ... make use of MSIX and I thought this is relevant to interrupts affinity. ... I am running a client/server test app over IPOIB in which the client ... If receiver application can't keep up UDP drops packets. ... Don't expect flow control or reliable delivery; ...
    (Linux-Kernel)
  • Re: detect bytes written on abort
    ... to implement a protocol where the sender and receiver always agree ... I only want to be able to track how many bytes were sent to the client, which equals the value that is eventually written to the server log file. ... If a failure prevents reliable delivery, the sender is informed.", Internetworking with TCP/IP Vol. ... When a writeon a socket returns, ...
    (comp.lang.php)
  • Re: detect bytes written on abort
    ... makes it unreliable, as a successful fwrite() on a socket may simply mean that the data has been placed in a buffer on the sender, not even passed to the OS yet. ... You don't know that the other end of the TCP connection is on the user's browser. ... to implement a protocol where the sender and receiver always agree ... I only want to be able to track how many bytes were sent to the client, which equals the value that is eventually written to the server log file. ...
    (comp.lang.php)
  • Re: UDP packets loss
    ... I am running a client/server test app over IPOIB in which the client sends ... server prints the bandwidth and how much data it received. ... Maybe the kernel is not designed to handle packets ... There clearly is an upper bound on the packet rate any given receiver can handle, ...
    (Linux-Kernel)
  • Re: Return receipt for Win2003 server Fax
    ... > I have just setup Windows 2003 on the network. ... > installed on both the server and the client. ... > to say the receiver ...
    (microsoft.public.win2000.fax)
Loading