Problem of Proof Cluster: slave startup

Hello experts

I am trying to setup the proof environment for the linux-cluster that consists of 4 nodes(8 core).
The installation for 4 nodes is successful. However, I meet a problem after configuration.
node9 is the master of my Proof cluster. Error message says that the master can not recognize slave nodes.
Anybody knows about the problem ?

bash-3.2$ root

  •                                     *
  •    W E L C O M E  to  R O O T       *
  •                                     *
  • Version 5.34/08 31 May 2013 *
  •                                     *
  • You are welcome to visit our Web site *
  •      [](            *
  •                                     *

ROOT 5.34/08 (v5-34-08@v5-34-08, Aug 11 2013, 08:00:51 on linux)
CINT/ROOT C/C++ Interpreter version 5.18.00, July 2, 2010
Type ? for help. Commands must be C++ statements.
Enclose multiple statements between { }.
root [0] TProof::Open(“”)
Starting master: opening connection …
Error in TSlave::SetupServ:failed to receive slave startup message
Starting master: failure
PROOF set to sequential mode
Warning in TProof::TProof: could not find 'const char ’ string in macro log: using local default yhkang
(class TProof
root [1] SysError in TUnixSystem::DispatchOneEvent: select: read error on 25
(Bad file descriptor)


Can you please post the configuration file?

G. Ganis

I solved my problem with PoD.

Thank you everyone.