Re: [BProc] clustermatic: node dies with signal 11

[Daryl W. G. <dw...@la...>]

> Date: Wed, 16 Nov 2005 23:05:16 -0600
> From: Ron Senykoff <rse...@gm...>
> To: bpr...@li...
> Subject: [BProc] clustermatic: node dies with signal 11
> 
> I am working on building a cluster of thin-clients for demo purposes
> (32 nodes). I'm truly stuck, and these 8-week courses are killing us
> grad students to get solid projects completed...
> 
> Using PXE the nodes load stage2 of clustermatic fine. However, the
> nodes can't connect correctly to the server (a laptop).
> 
> A bit of info on the hardware:
> laptop = PII w/ 64MB of RAM (I reduced it to be identical to the clients)
> nodes = AMD K6-2 w/ 64 MB of RAM + DiskOnChip (we want to put the
> successful build onto that so no network booting)
> Could it be the difference between the laptop and the nodes? They are
> both i586 correct? Any help is greatly appreciated.
> 
> [root@novac root]# tail /var/log/clustermatic/node.0
> vmadlib   :     loaded /lib/libnss_bproc.so.2 (size=44922;id=0,0;mode=100755)
> vmadlib   :     loaded /usr/lib/libbproc.so.4.0.0
> (size=40697;id=0,0;mode=100755)
> vmadlib   :     loaded /usr/lib/libstdc++.so.5.0.5
> (size=732372;id=0,0;mode=100755)
> nodeup    :   Plugin vmadlib returned status 0 (ok)
> nodeup    :   No premove function for nodeinfo
                ^^^^^^^^^^^^^^^^^^^^^^^

I believe I've seen this before when the stage2 image and front-end had bproc
mismatches, i.e. I had {re-}built bproc on the front-end w/o generating a
new stage2 image.  Could that be possible in your case?

Daryl

> nodeup    : Starting 1 child processes.
> nodeup    : Finished creating child processes.
> nodeup    : I/O error talking to child
> nodeup    : Child process for node 0 died with signal 11
> nodeup    : Node setup returned status 1
> 
> [root@novac root]# cat /etc/clustermatic/config
> interface eth0
> 
> #master 192.168.46.219
> master novac
> 
> iprange 0 192.168.46.20 192.168.46.35   # Nodes 0-8 have addresses
> from this range.
> 
> bootfile /var/clustermatic/boot.img
> 
> librariesfrombinary /bin/sleep /bin/ps /bin/ping /bin/ls # get libc,resolver
> libraries /usr/lib/libstdc++*   /usr/lib64/libstdc++*    # C++ support
> libraries /usr/lib/libbproc.so* /usr/lib64/libbproc.so*  # BProc, of course.
> libraries /lib/libnss_bproc*    /lib64/libnss_bproc*     # BProc resolver
> 
> node 0 00:60:EF:21:61:AF
> node  00:60:EF:21:63:16