Why systemtap loses events and what can be done about it?

[Frank Ch. Eigler]

Hi -

> <zzh@ncic.ac.cn> wrote:

> [...]  To make my question clear, I have to introduce my work in
> more detail.  I am trying to use systemtap to analyze the
> communication pattern of internet service. One basic issue is to
> correlate every pair of tcp_sendmsg and tcp_recvmsg.

(For what it's worth, there may not be a one-to-one correlation,
considering signals, packet loss, buffered delivery, ...)


> Usually I will run a workload to emulate 100-200 clients explore the
> web site simultaneously. In the workload of 200 clients, staprun
> often displays the warning messages about skipped probes(Why?).

I'd have to see your script to give a better guess.  return probes
have some dynamic resource constraints that can cause a skip; normal
probes skip in only a few cases (e.g., reentrancy, but that's unlikely
here).


> And in the workload of 100 clients, no warning occurred, but
> sometimes I find some events failed to be recorded. [...]

It is possible that there are some bugs in the system someplace.  It
is possible that the skipped probes account for the missing events.


- FChE