Re: [pcp] URGENT potentially serious regression in 3.7.0

[Nathan Scott <nathans@xxxxxxxxxx>]

----- Original Message -----
> Ah, looks like the crazy level of diagnostics is coming from here
> in pmcd...
> 
> 671   #ifdef PCP_DEBUG
> 672               if (pmDebug & DBG_TRACE_APPL0)
> 673                   for (i = 0; i <= maxClientFd; i++)

Yeah, so thinking about it a bit - its because with NSS, we have
this sparse fd number space where the "native" fds are from zero
through FD_SETSIZE, and the nspr fds are numbered starting above
that range.  Everything in-between is space-junk, we should just
skip over it ... just need to a way to do that without exposing
these low-level libpcp details up at the pmcd/higher levels.

cheers.

--
Nathan