rpcbind, rpc.statd memory footprint

[Jeremy Chadwick]

On Tue, Oct 26, 2010 at 03:23:54PM +0200, Erik Trulsson wrote:
> On Tue, Oct 26, 2010 at 03:08:06PM +0200, Ivan Voras wrote:
> > I'm not sure what to expect from these (i.e. what is "normal" in this
> > case?) but the VM sizes for the NFS-used rpc.statd and rpcbind here look
> > a bit too big, compared to their resident sizes:
> > 
> >   778 root             1  44    0 26420K  3256K select  1   0:01  0.00%
> > rpcbind
> >   891 root             1  44    0   263M  1296K select  1   0:01  0.00%
> > rpc.statd
> > 
> > This is 8-stable amd64. Could there be a memory leak somewhere,
> > especially in rpc.statd?
> 
> FAQ:  http://www.freebsd.org/doc/en_US.ISO8859-1/books/faq/admin.html#STATD-MEM-LEAK
> 
> (Short version: That is expected behaviour from rpc.statd)

Plus, that's 263MB of SIZE/VSZ, not RES/RSS.  A portion of it could also
be utilised by ELF shared object stuff (dynamic linking):

$ ldd /usr/sbin/rpc.statd
/usr/sbin/rpc.statd:
	librpcsvc.so.5 => /usr/lib/librpcsvc.so.5 (0x60648000)
	libc.so.7 => /lib/libc.so.7 (0x60750000)

Bottom line: don't worry "too" much about VSZ when it comes to
memory usage.  Bloated RSS is reason to worry.

-- 
| Jeremy Chadwick                                   jdc at parodius.com |
| Parodius Networking                       http://www.parodius.com/ |
| UNIX Systems Administrator                  Mountain View, CA, USA |
| Making life hard for others since 1977.              PGP: 4BD6C0CB |