<html>
  <head>
    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
  </head>
  <body>
    <div class="moz-cite-prefix">Hi Russell Jones, <br>
    </div>
    <div class="moz-cite-prefix"><br>
    </div>
    <div class="moz-cite-prefix">did you try to stop firewall on the
      client cluster-cn02 ?</div>
    <div class="moz-cite-prefix"><br>
    </div>
    <div class="moz-cite-prefix">Patrick<br>
    </div>
    <div class="moz-cite-prefix"><br>
    </div>
    <div class="moz-cite-prefix">Le 16/11/2020 à 19:20, Russell Jones a
      écrit :<br>
    </div>
    <blockquote type="cite"
cite="mid:CABb1d=iyAeSXY5nr3AMQtNf=d_baCPiCZG8SfBN5V2rTO6UWxw@mail.gmail.com">
      <meta http-equiv="content-type" content="text/html; charset=UTF-8">
      <div dir="ltr">Here's some debug logs from the compute node after
        launching an interactive shell with the x11 flag. I see it show
        X11 forwarding established, then it ends with a connection
        timeout.
        <div><br>
        </div>
        <div><br>
        </div>
        <div>[2020-11-16T12:12:34.097] debug:  Checking credential with
          492 bytes of sig data<br>
          [2020-11-16T12:12:34.098] _run_prolog: run job script took
          usec=1284<br>
          [2020-11-16T12:12:34.098] _run_prolog: prolog with lock for
          job 30873 ran for 0 seconds<br>
          [2020-11-16T12:12:34.111] debug:  AcctGatherEnergy NONE plugin
          loaded<br>
          [2020-11-16T12:12:34.112] debug:  AcctGatherProfile NONE
          plugin loaded<br>
          [2020-11-16T12:12:34.113] debug:  AcctGatherInterconnect NONE
          plugin loaded<br>
          [2020-11-16T12:12:34.114] debug:  AcctGatherFilesystem NONE
          plugin loaded<br>
          [2020-11-16T12:12:34.115] debug:  switch NONE plugin loaded<br>
          [2020-11-16T12:12:34.116] debug:  init: Gres GPU plugin loaded<br>
          [2020-11-16T12:12:34.116] [30873.extern] debug:  Job
          accounting gather LINUX plugin loaded<br>
          [2020-11-16T12:12:34.117] [30873.extern] debug:  cont_id
          hasn't been set yet not running poll<br>
          [2020-11-16T12:12:34.117] [30873.extern] debug:  Message
          thread started pid = 18771<br>
          [2020-11-16T12:12:34.119] [30873.extern] debug:  task NONE
          plugin loaded<br>
          [2020-11-16T12:12:34.120] [30873.extern] Munge credential
          signature plugin loaded<br>
          [2020-11-16T12:12:34.121] [30873.extern] debug:  job_container
          none plugin loaded<br>
          [2020-11-16T12:12:34.121] [30873.extern] debug:  spank:
          opening plugin stack
          /apps/slurm/cluster/20.02.0/etc/plugstack.conf<br>
          [2020-11-16T12:12:34.121] [30873.extern] debug:
           X11Parameters: (null)<br>
          [2020-11-16T12:12:34.133] [30873.extern] X11 forwarding
          established on DISPLAY=cluster-cn02.domain:66.0<br>
          [2020-11-16T12:12:34.133] [30873.extern] debug:
           jag_common_poll_data: Task 0 pid 18775 ave_freq = 4023000 mem
          size/max 6750208/6750208 vmem size/max 147521536/147521536,
          disk read size/max (7200/7200), disk write size/max (374/374),
          time 0.000000(0+0) Energy tot/max 0/0 TotPower 0 MaxPower 0
          MinPower 0<br>
          [2020-11-16T12:12:34.133] [30873.extern] debug:  x11
          forwarding local display is 66<br>
          [2020-11-16T12:12:34.133] [30873.extern] debug:  x11
          forwarding local xauthority is /tmp/.Xauthority-MkU8aA<br>
          [2020-11-16T12:12:34.202] launch task 30873.0 request from
          UID:1368 GID:512 HOST:172.21.150.10 PORT:4795<br>
          [2020-11-16T12:12:34.202] debug:  Checking credential with 492
          bytes of sig data<br>
          [2020-11-16T12:12:34.202] [30873.extern] debug:  Handling
          REQUEST_X11_DISPLAY<br>
          [2020-11-16T12:12:34.202] [30873.extern] debug:  Leaving
          _handle_get_x11_display<br>
          [2020-11-16T12:12:34.202] debug:  Leaving
          stepd_get_x11_display<br>
          [2020-11-16T12:12:34.202] debug:  Waiting for job 30873's
          prolog to complete<br>
          [2020-11-16T12:12:34.202] debug:  Finished wait for job
          30873's prolog to complete<br>
          [2020-11-16T12:12:34.213] debug:  AcctGatherEnergy NONE plugin
          loaded<br>
          [2020-11-16T12:12:34.214] debug:  AcctGatherProfile NONE
          plugin loaded<br>
          [2020-11-16T12:12:34.214] debug:  AcctGatherInterconnect NONE
          plugin loaded<br>
          [2020-11-16T12:12:34.214] debug:  AcctGatherFilesystem NONE
          plugin loaded<br>
          [2020-11-16T12:12:34.215] debug:  switch NONE plugin loaded<br>
          [2020-11-16T12:12:34.215] debug:  init: Gres GPU plugin loaded<br>
          [2020-11-16T12:12:34.216] [30873.0] debug:  Job accounting
          gather LINUX plugin loaded<br>
          [2020-11-16T12:12:34.216] [30873.0] debug:  cont_id hasn't
          been set yet not running poll<br>
          [2020-11-16T12:12:34.216] [30873.0] debug:  Message thread
          started pid = 18781<br>
          [2020-11-16T12:12:34.216] debug:
           task_p_slurmd_reserve_resources: 30873 0<br>
          [2020-11-16T12:12:34.217] [30873.0] debug:  task NONE plugin
          loaded<br>
          [2020-11-16T12:12:34.217] [30873.0] Munge credential signature
          plugin loaded<br>
          [2020-11-16T12:12:34.217] [30873.0] debug:  job_container none
          plugin loaded<br>
          [2020-11-16T12:12:34.217] [30873.0] debug:  mpi type = pmix<br>
          [2020-11-16T12:12:34.244] [30873.0] debug:  spank: opening
          plugin stack /apps/slurm/cluster/20.02.0/etc/plugstack.conf<br>
          [2020-11-16T12:12:34.244] [30873.0] debug:  mpi type = pmix<br>
          [2020-11-16T12:12:34.244] [30873.0] debug:  (null) [0]
          mpi_pmix.c:153 [p_mpi_hook_slurmstepd_prefork] mpi/pmix: start<br>
          [2020-11-16T12:12:34.244] [30873.0] debug:  mpi/pmix: setup
          sockets<br>
          [2020-11-16T12:12:34.273] [30873.0] debug:  cluster-cn02 [0]
          pmixp_client_v2.c:69 [_errhandler_reg_callbk] mpi/pmix: Error
          handler registration callback is called with status=0, ref=0<br>
          [2020-11-16T12:12:34.273] [30873.0] debug:  cluster-cn02 [0]
          pmixp_client.c:697 [pmixp_libpmix_job_set] mpi/pmix: task
          initialization<br>
          [2020-11-16T12:12:34.273] [30873.0] debug:  cluster-cn02 [0]
          pmixp_agent.c:229 [_agent_thread] mpi/pmix: Start agent thread<br>
          [2020-11-16T12:12:34.273] [30873.0] debug:  cluster-cn02 [0]
          pmixp_agent.c:330 [pmixp_agent_start] mpi/pmix: agent thread
          started: tid = 70366934331824<br>
          [2020-11-16T12:12:34.273] [30873.0] debug:  cluster-cn02 [0]
          pmixp_agent.c:335 [pmixp_agent_start] mpi/pmix: timer thread
          started: tid = 70366933283248<br>
          [2020-11-16T12:12:34.273] [30873.0] debug:  cluster-cn02 [0]
          pmixp_agent.c:267 [_pmix_timer_thread] mpi/pmix: Start timer
          thread<br>
          [2020-11-16T12:12:34.273] [30873.0] debug:    stdin uses a pty
          object<br>
          [2020-11-16T12:12:34.274] [30873.0] debug:  init pty size
          34:159<br>
          [2020-11-16T12:12:34.274] [30873.0] in _window_manager<br>
          [2020-11-16T12:12:34.274] [30873.0] debug level = 2<br>
          [2020-11-16T12:12:34.274] [30873.0] debug:  IO handler started
          pid=18781<br>
          [2020-11-16T12:12:34.275] [30873.0] starting 1 tasks<br>
          [2020-11-16T12:12:34.276] [30873.0] task 0 (18801) started
          2020-11-16T12:12:34<br>
          [2020-11-16T12:12:34.276] [30873.0] debug:
           task_p_pre_launch_priv: 30873.0<br>
          [2020-11-16T12:12:34.288] [30873.0] debug:
           jag_common_poll_data: Task 0 pid 18801 ave_freq = 4023000 mem
          size/max 9961472/9961472 vmem size/max 512557056/512557056,
          disk read size/max (0/0), disk write size/max (0/0), time
          0.000000(0+0) Energy tot/max 0/0 TotPower 0 MaxPower 0
          MinPower 0<br>
          [2020-11-16T12:12:34.288] [30873.0] debug:  Sending launch
          resp rc=0<br>
          [2020-11-16T12:12:34.288] [30873.0] debug:  mpi type = pmix<br>
          [2020-11-16T12:12:34.288] [30873.0] debug:  cluster-cn02 [0]
          mpi_pmix.c:180 [p_mpi_hook_slurmstepd_task] mpi/pmix: Patch
          environment for task 0<br>
          [2020-11-16T12:12:34.289] [30873.0] debug:  task_p_pre_launch:
          30873.0, task 0<br>
          [2020-11-16T12:12:39.475] [30873.extern] error:
          _x11_socket_read: slurm_open_msg_conn: Connection timed out<br>
        </div>
      </div>
      <br>
      <div class="gmail_quote">
        <div dir="ltr" class="gmail_attr">On Mon, Nov 16, 2020 at 11:50
          AM Russell Jones <<a href="mailto:arjones85@gmail.com"
            moz-do-not-send="true">arjones85@gmail.com</a>> wrote:<br>
        </div>
        <blockquote class="gmail_quote" style="margin:0px 0px 0px
          0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
          <div dir="ltr">Hello,
            <div><br>
            </div>
            <div>Thanks for the reply! </div>
            <div><br>
            </div>
            <div>We are using Slurm 20.02.0.</div>
          </div>
          <br>
          <div class="gmail_quote">
            <div dir="ltr" class="gmail_attr">On Mon, Nov 16, 2020 at
              10:59 AM sathish <<a
                href="mailto:sathish.sathishkumar@gmail.com"
                target="_blank" moz-do-not-send="true">sathish.sathishkumar@gmail.com</a>>
              wrote:<br>
            </div>
            <blockquote class="gmail_quote" style="margin:0px 0px 0px
              0.8ex;border-left:1px solid
              rgb(204,204,204);padding-left:1ex">
              <div dir="ltr">
                <div dir="ltr">Hi Russell Jones, 
                  <div><span
style="font-size:14px;letter-spacing:0.2px;font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif"><br>
                    </span></div>
                  <div><span
style="font-size:14px;letter-spacing:0.2px;font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif">I
                    </span>believe<span
style="font-size:14px;letter-spacing:0.2px;font-family:Roboto,RobotoDraft,Helvetica,Arial,sans-serif"> you
                      are using a slurm version older than 19.05.  X11
                      forwarding code has been revamped and it works as
                      expected starting from the 19.05.0 version. </span><br>
                  </div>
                  <div><br>
                  </div>
                  <div><br>
                  </div>
                </div>
                <div class="gmail_quote">
                  <div dir="ltr" class="gmail_attr">On Mon, Nov 16, 2020
                    at 10:02 PM Russell Jones <<a
                      href="mailto:arjones85@gmail.com" target="_blank"
                      moz-do-not-send="true">arjones85@gmail.com</a>>
                    wrote:<br>
                  </div>
                  <blockquote class="gmail_quote" style="margin:0px 0px
                    0px 0.8ex;border-left:1px solid
                    rgb(204,204,204);padding-left:1ex">
                    <div dir="ltr">Hi all,
                      <div><br>
                      </div>
                      <div>Hoping I can get pointed in the right
                        direction here. <br>
                        <br>
                        I have X11 forwarding enabled in Slurm, however
                        I cannot seem to get it working properly. It
                        works when I test with "ssh -Y" to the compute
                        node from the login node, however when I try
                        through Slurm the Display variable looks very
                        different, and I get an error. Example below:</div>
                      <div><br>
                      </div>
                      <div>[user@cluster-1 ~]$ ssh -Y cluster-cn02<br>
                        Last login: Mon Nov 16 10:09:18 2020 from
                        172.21.150.10<br>
                        -bash-4.2$ env | grep -i display<br>
                        DISPLAY=172.21.150.102:10.0<br>
                        -bash-4.2$ xclock<br>
                        Warning: Missing charsets in String to FontSet
                        conversion<br>
                        ** Clock pops up and works **<br>
                        <br>
                        [user@cluster-1 ~]$ srun -p cluster -w
                        cluster-cn02 --x11 --pty bash -l<br>
                        bash-4.2$ env | grep -i display<br>
                        DISPLAY=localhost:28.0<br>
                        bash-4.2$ xclock<br>
                        Error: Can't open display: localhost:28.0<br>
                      </div>
                      <div><br>
                      </div>
                      <div><br>
                      </div>
                      <div>Any ideas on where to begin looking? I'm not
                        sure why the display variable is being set to
                        localhost instead of the login node.</div>
                      <div><br>
                      </div>
                      <div>Thanks!</div>
                      <div><br>
                      </div>
                    </div>
                  </blockquote>
                </div>
                <br clear="all">
                <div><br>
                </div>
                -- <br>
                <div dir="ltr">Regards.....<br>
                  Sathish</div>
              </div>
            </blockquote>
          </div>
        </blockquote>
      </div>
    </blockquote>
    <p><br>
    </p>
  </body>
</html>