On Thu, Feb 26, 2004 at 07:17:05PM -0800, Matt Massie wrote:
> i think brooks comment on the compressed XML is right on target.  it
> doesn't make sense to make put zlib compression on a separate port.  it
> make more sense to have a web server port (and the old style simple tcp
> socket as well).  the web port will process requests and return data
> encoded as the client requests.
> 
> the source for the embedded web server in the ./libhttpd.  it is based
> on the libhttpd but in honesty.. i don't think the author of libhttpd
> would hardly recognize the code much at all.  this web server can do
> authentication, handle POST/GET variables, can be configured with
> complex ACLs, memory management, etc... and it's still very
> light-weight, fast and multi-threaded.

This sounds like a nice approach.

> brooks... when you have time can you check it on FreeBSD?  any HPUX,
> Tru64, etc gurus should check their systems as well and let me know.
> 
> i tried to compile 2.6.0 on the freebsd box here.  it compiled great but
> then segfaulted on a call to getaddrinfo.  i googled it and found that
> it's known bug on 4.7 (actually it's a security issue).

I'll try it here as soon as it will compile for me.  It looks like
configure.in wants a tests directory that doesn't exist.  Any idea
what's up?

What's your feeling about the path changes I suggested earlier?  A bump
in minor is probalby as good as time as we're going to get soon to
change the defaults and it would be really helpful if I didn't have to
apply patches and run sed to make ganglia install in FreeBSD approved
places.

-- Brooks

-- 
Any statement of the form "X is the one, true Y" is FALSE.
PGP fingerprint 655D 519C 26A7 82E7 2529  9BF0 5D8E 8BE9 F238 1AD4

Attachment: pgpLiRMLJawqv.pgp
Description: PGP signature

Reply via email to