Anyway, the problem is that the sending TCP continues to
accumulate data in the send buffer (which has been increased
to 2 MB) w/o sending it. This is causing our custom application
to hang, and we expect to see (but haven't yet seen) the buffer
The scenario is that the sending TCP has stops sending, plain
and simple. This only seems to occur with packets of about 4K
I am not the developer who recognized this issue, but I am
trying to find out if anyone else has noticed this type of
behavior and how we might deal with it.
If more information is required, let me know and I"ll see what I
can do. I am planning on integrating a kernel debugger and maybe
even SGI's kernel profiling, but I don't know how effective either
of these approaches could be in solving this problem.
Thoughts, suggestions and questions welcome, as I have no idea
how to attack this problem correctly.
Key fingerprint = 53BB 08CA 6A4B 8AF8 DF9B 7E71 2D20 AD30 6684 E82D
"Drama free in 2001!"
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to email@example.com
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/