<html>
  <head>
    <meta content="text/html; charset=utf-8" http-equiv="Content-Type">
  </head>
  <body bgcolor="#FFFFFF" text="#000000">
    <p>Thank you for your help. The problem has been overcome following
      your advices.</p>
    <p>Now, I give some notes for this problem which might be useful for
      others.</p>
    <p>1. Up to now, we must use the code in the master branch. The
      source code can be downloaded using git with:</p>
    <p>git clone <a class="moz-txt-link-freetext" href="https://bitbucket.org/petsc/petsc">https://bitbucket.org/petsc/petsc</a> petsc.</p>
    <p>2. Just the other day, I download the code using git with: git
      clone -b maint <a class="moz-txt-link-freetext" href="https://bitbucket.org/petsc/petsc">https://bitbucket.org/petsc/petsc</a> petsc. <br>
    </p>
    <p>    But, this copy of code still has such a problem. I am not
      sure whether it is available now.<br>
    </p>
    <p>3. The code downloaded from website of PETSc(Version of 3.7.3) is
      not available for this problem, although it is in the branch
      master.<br>
    </p>
    <tt></tt><br>
    Thanks for all helps again. Best wishes to you.<br>
    <br>
    leejearl<br>
    <p><br>
    </p>
    <p><br>
    </p>
    <br>
    <div class="moz-cite-prefix">On 2016年08月16日 19:34, Matthew Knepley
      wrote:<br>
    </div>
    <blockquote
cite="mid:CAMYG4G=VkWh_7wNe7q8pNmnEU6PgaJiQjQcH3Eb7vaUL-fdWSQ@mail.gmail.com"
      type="cite">
      <div dir="ltr">
        <div class="gmail_extra">
          <div class="gmail_quote">On Mon, Aug 15, 2016 at 9:28 PM,
            leejearl <span dir="ltr"><<a moz-do-not-send="true"
                href="mailto:leejearl@126.com" target="_blank">leejearl@126.com</a>></span>
            wrote:<br>
            <blockquote class="gmail_quote" style="margin:0px 0px 0px
              0.8ex;border-left:1px solid
              rgb(204,204,204);padding-left:1ex">
              <div bgcolor="#FFFFFF" text="#000000">
                <p>Thank you for all your helps. I have tried and
                  reinstalled PETSc lots of times. The error are still
                  existed.</p>
                <p>I can not find out the reasons. Now, I give the some
                  messages in this letter.</p>
                <p>1> The source code is downloaded from the website
                  of PETSc, and the version is 3.7.2.<br>
                </p>
              </div>
            </blockquote>
            <div>You will need to run in the 'master' branch, not the
              release since we have fixed some bugs. It is best to</div>
            <div>use master for very new features like this. The
              instructions are here: <a moz-do-not-send="true"
                href="http://www.mcs.anl.gov/petsc/developers/index.html">http://www.mcs.anl.gov/petsc/developers/index.html</a></div>
            <div><br>
            </div>
            <div>   Thanks,</div>
            <div><br>
            </div>
            <div>      Matt <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 bgcolor="#FFFFFF" text="#000000">
                <p>2> Configure: <br>
                </p>
                <p>>export PETSC_DIR=./</p>
                <p>>export PETSC_ARCH=arch<br>
                </p>
                <p>>./configure --prefix=$HOME/Install/petsc
                  --with-mpi-dir=/home/leejearl/<wbr>Install/mpich_3.1.4/gnu
                  --download-exodusii=../<wbr>externalpackages/exodus-5.24.<wbr>tar.bz2
                  --download-netcdf=../<wbr>externalpackages/netcdf-4.3.2.<wbr>tar.gz
                  --download-hdf5=../<wbr>externalpackages/hdf5-1.8.12.<wbr>tar.gz
                  --download-metis=../<wbr>externalpackages/git.metis.<wbr>tar.gz
                  --download-parmetis=yes<br>
                </p>
                <p>3> The process of installation has no error.</p>
                <p>4> After the installation, I added the following
                  statement into the file ~/.bashrc:</p>
                <p>export PETSC_ARCH=""</p>
                <p>export PETSC_DIR=$HOME/Install/pets/ <br>
                </p>
                <p>I wish to get some helps as follows:</p>
                <p>1> Is there any problems in my installation? <br>
                </p>
                <p>2> Can any one help me a simple code in which the
                  value of overlap used in DMPlexDistribute function is
                  greater than 1.</p>
                <p>3> I attach the code, makefile, grid and the error
                  messages again, I hope some one can help me to figure
                  out the problems.</p>
                <p>    3.1> code: cavity.c</p>
                <p>    3.2> makefile: makefile</p>
                <p>    3.3> grid: cavity.exo</p>
                <p>    3.4> error messages: error.dat</p>
                <p>    It is very strange that there is no error message
                  when I run it using "mpirun -n 3 ./cavity", but when I
                  run it using "mpirun -n 2 ./cavity", the errors
                  happed.</p>
                <p>The error messages are shown in the file error.dat.<br>
                </p>
                <p><br>
                </p>
                <p>Any helps are appreciated.</p>
                <p><br>
                </p>
                <br>
                <div>On 2016年08月13日 09:04, leejearl wrote:<br>
                </div>
                <blockquote type="cite">
                  <p>Thank you for your reply. The source code I have
                    used is from the website of PETSc, not from the git
                    repository.</p>
                  <p>I will have a test with the code from git
                    repository.<br>
                  </p>
                  <p><br>
                  </p>
                  <p>leejearl<br>
                  </p>
                  <br>
                  <div>On 2016年08月13日 08:49, Oxberry, Geoffrey Malcolm
                    wrote:<br>
                  </div>
                  <blockquote type="cite"> <br>
                    <div>
                      <blockquote type="cite">
                        <div>On Aug 12, 2016, at 5:41 PM, leejearl <<a
                            moz-do-not-send="true"
                            href="mailto:leejearl@126.com"
                            target="_blank">leejearl@126.com</a>>
                          wrote:</div>
                        <br>
                        <div>
                          <div bgcolor="#FFFFFF" text="#000000">
                            <p>Hi, Matt:<br>
                            </p>
                                <br>
                            <div><br>
                            </div>
                            > Can you verify that you are running the
                            master branch?<br>
                          </div>
                        </div>
                      </blockquote>
                      <div><br>
                      </div>
                      <div>cd ${PETSC_DIR}</div>
                      <div>git branch</div>
                      <div><br>
                      </div>
                      <div>The last command should return something like
                        a list of branch names, and the branch name with
                        an asterisk to the left of it will be the branch
                        you are currently on.</div>
                      <div><br>
                      </div>
                      <div>Geoff</div>
                      <div>
                        <div><br>
                        </div>
                      </div>
                      <blockquote type="cite">
                        <div>
                          <div bgcolor="#FFFFFF" text="#000000">I am not
                            sure, how can I verify this?<br>
                            And I configure PETSc with this command <br>
                            "./configure --prefix=$HOME/Install/petsc-<wbr>openmpi
                            --with-mpi=/home/leejearl/<wbr>Install/openmpi/gnu/1.8.4
                            --download-exodusii=yes --download-netcdf
                            --with-hdf5-dir=/home/<wbr>leejearl/Install/hdf5-1.8.14
                            --download-metis=yes".<br>
                            Is there some problem? Can you show me your
                            command for configuring PETSc?<br>
                            <br>
                            <br>
                            Thanks<br>
                            <br>
                            leejearl<br>
                            <br>
                            <br>
                            <br>
                            <br>
                            <br>
                            <div>On 2016年08月13日 01:10, Matthew Knepley
                              wrote:<br>
                            </div>
                            <blockquote type="cite">
                              <div dir="ltr">
                                <div class="gmail_extra">
                                  <div class="gmail_quote">On Thu, Aug
                                    11, 2016 at 8:00 PM, leejearl <span
                                      dir="ltr"> <<a
                                        moz-do-not-send="true"
                                        href="mailto:leejearl@126.com"
                                        target="_blank">leejearl@126.com</a>></span>
                                    wrote:<br>
                                    <blockquote class="gmail_quote"
                                      style="margin:0px 0px 0px
                                      0.8ex;border-left:1px solid
                                      rgb(204,204,204);padding-left:1ex">
                                      <div bgcolor="#FFFFFF"
                                        text="#000000">
                                        <p>Thank you for your reply. I
                                          have attached the code, grid
                                          and the error message.</p>
                                        <p>cavity.c is the code file,
                                          cavity.exo is the grid, and
                                          error.dat is the error
                                          message.</p>
                                        <p>The command is "mpirun -n 2
                                          ./cavity</p>
                                      </div>
                                    </blockquote>
                                    <div><br>
                                    </div>
                                    <div>Can you verify that you are
                                      running the master branch? I just
                                      ran this and got</div>
                                    <div><br>
                                    </div>
                                    <div>
                                      <div>DM Object: 2 MPI processes</div>
                                      <div>  type: plex</div>
                                      <div>DM_0x84000004_0 in 2
                                        dimensions:</div>
                                      <div>  0-cells: 5253 5252</div>
                                      <div>  1-cells: 10352 10350</div>
                                      <div>  2-cells: 5298 (198) 5297
                                        (198)</div>
                                      <div>Labels:</div>
                                      <div>  ghost: 2 strata of sizes
                                        (199, 400)</div>
                                      <div>  vtk: 1 strata of sizes
                                        (4901)</div>
                                      <div>  Cell Sets: 1 strata of
                                        sizes (5100)</div>
                                      <div>  Face Sets: 3 strata of
                                        sizes (53, 99, 50)</div>
                                      <div>  depth: 3 strata of sizes
                                        (5253, 10352, 5298)</div>
                                    </div>
                                    <div><br>
                                    </div>
                                    <div>  Thanks,</div>
                                    <div><br>
                                    </div>
                                    <div>     Matt</div>
                                    <div> </div>
                                    <blockquote class="gmail_quote"
                                      style="margin:0px 0px 0px
                                      0.8ex;border-left:1px solid
                                      rgb(204,204,204);padding-left:1ex">
                                      <div bgcolor="#FFFFFF"
                                        text="#000000">
                                        <div>On 2016年08月11日 23:29,
                                          Matthew Knepley wrote:<br>
                                        </div>
                                        <blockquote type="cite">
                                          <div dir="ltr">
                                            <div class="gmail_extra">
                                              <div class="gmail_quote">On
                                                Thu, Aug 11, 2016 at
                                                3:14 AM, leejearl <span
                                                  dir="ltr"> <<a
                                                    moz-do-not-send="true"
href="mailto:leejearl@126.com" target="_blank">leejearl@126.com</a>></span>
                                                wrote:<br>
                                                <blockquote
                                                  class="gmail_quote"
                                                  style="margin:0px 0px
                                                  0px
                                                  0.8ex;border-left:1px
                                                  solid
                                                  rgb(204,204,204);padding-left:1ex">
                                                  <div bgcolor="#FFFFFF"
                                                    text="#000000">
                                                    <p>Hi, <br>
                                                          Thank you for
                                                      your reply. It
                                                      help me very much.<br>
                                                          But, for
                                                      "/petsc-3.7.2/src/ts/examples/<wbr>tutorials/ex11.c",
                                                      when I set the
                                                      overlap to 2
                                                      levels, the
                                                      command is <br>
                                                      "mpirun -n 3
                                                      ./ex11 -f
                                                      annulus-20.exo
                                                      -ufv_mesh_overlap
                                                      2 -physics sw", it
                                                      suffers a error.<br>
                                                          It seems to me
                                                      that setting
                                                      overlap to 2 is
                                                      very common. Are
                                                      there issues that
                                                      I have not take
                                                      into
                                                      consideration?<br>
                                                          Any help are
                                                      appreciated.</p>
                                                  </div>
                                                </blockquote>
                                                <div>I will check this
                                                  out. I have not tested
                                                  an overlap of 2 here
                                                  since I generally use
                                                  nearest neighbor FV
                                                  methods for</div>
                                                <div>unstructured stuff.
                                                  I have test examples
                                                  that run fine for
                                                  overlap > 1. Can
                                                  you send the entire
                                                  error message?</div>
                                                <div><br>
                                                </div>
                                                <div>If the error is not
                                                  in the distribution,
                                                  but rather in the
                                                  analytics, that is
                                                  understandable because
                                                  this example is only</div>
                                                <div>intended to be run
                                                  using a nearest
                                                  neighbor FV method,
                                                  and thus might be
                                                  confused if we give it
                                                  two layers of ghost</div>
                                                <div>cells.</div>
                                                <div><br>
                                                </div>
                                                <div>   Matt</div>
                                                <div> </div>
                                                <blockquote
                                                  class="gmail_quote"
                                                  style="margin:0px 0px
                                                  0px
                                                  0.8ex;border-left:1px
                                                  solid
                                                  rgb(204,204,204);padding-left:1ex">
                                                  <div bgcolor="#FFFFFF"
                                                    text="#000000">
                                                    <p><span><font
                                                          color="#888888"><br>
                                                          leejearl</font></span></p>
                                                    <div>
                                                      <div><br>
                                                        <div>On
                                                          2016年08月11日
                                                          14:57, Julian
                                                          Andrej wrote:<br>
                                                        </div>
                                                        <blockquote
                                                          type="cite">
                                                          <div dir="ltr">Hi,
                                                          <div><br>
                                                          </div>
                                                          <div>take a
                                                          look at slide
                                                          10 of [1],
                                                          there is
                                                          visually
                                                          explained what
                                                          the overlap
                                                          between
                                                          partitions is.</div>
                                                          <div><br>
                                                          </div>
                                                          <div>[1] <a
                                                          moz-do-not-send="true"
href="https://www.archer.ac.uk/training/virtual/files/2015/06-PETSc/slides.pdf"
target="_blank">https://www.archer.ac.uk/t<wbr>raining/virtual/files/2015/06-<wbr>PETSc/slides.pdf</a></div>
                                                          </div>
                                                          <div
                                                          class="gmail_extra"><br>
                                                          <div
                                                          class="gmail_quote">On
                                                          Thu, Aug 11,
                                                          2016 at 8:48
                                                          AM, leejearl <span
                                                          dir="ltr">
                                                          <<a
                                                          moz-do-not-send="true"
href="mailto:leejearl@126.com" target="_blank">leejearl@126.com</a>></span>
                                                          wrote:<br>
                                                          <blockquote
                                                          class="gmail_quote"
style="margin:0px 0px 0px 0.8ex;border-left:1px solid
                                                          rgb(204,204,204);padding-left:1ex">
                                                          Hi, all:<br>
                                                              I want to
                                                          use PETSc to
                                                          build my FVM
                                                          code. Now, I
                                                          have a
                                                          question about<br>
                                                          the function 
DMPlexDistribute(DM dm, PetscInt overlap, PetscSF *sf, DM *dmOverlap) .<br>
                                                          <br>
                                                              In the
                                                          example
                                                          "/petsc-3.7.2/src/ts/examples/<wbr>tutorials/ex11.c".
                                                          When I set the
                                                          overlap<br>
                                                          as 0 or 1, it
                                                          works well.
                                                          But, if I set
                                                          the overlap as
                                                          2, it suffers
                                                          a problem.<br>
                                                              I am
                                                          confused about
                                                          the value of
                                                          overlap. Can
                                                          it be set as
                                                          2? What is the
                                                          meaning of<br>
                                                          the parameter
                                                          overlap?<br>
                                                              Any helps
                                                          are
                                                          appreciated!<span><font
color="#888888"><br>
                                                          <br>
                                                          leejearl<br>
                                                          <br>
                                                          <br>
                                                          <br>
                                                          </font></span></blockquote>
                                                          </div>
                                                          <br>
                                                          </div>
                                                        </blockquote>
                                                        <br>
                                                      </div>
                                                    </div>
                                                  </div>
                                                </blockquote>
                                              </div>
                                              <br>
                                              <br clear="all">
                                              <span class=""><font
                                                  color="#888888"> <span><font
                                                      color="#888888">
                                                      <div><br>
                                                      </div>
                                                      -- <br>
                                                      <div
                                                        data-smartmail="gmail_signature">What
                                                        most
                                                        experimenters
                                                        take for granted
                                                        before they
                                                        begin their
                                                        experiments is
                                                        infinitely more
                                                        interesting than
                                                        any results to
                                                        which their
                                                        experiments
                                                        lead.<br>
                                                        -- Norbert
                                                        Wiener</div>
                                                    </font></span></font></span></div>
                                            <span class=""><font
                                                color="#888888"> </font></span></div>
                                          <span class=""><font
                                              color="#888888"> </font></span></blockquote>
                                        <span class=""><font
                                            color="#888888"> <br>
                                          </font></span></div>
                                      <span class=""><font
                                          color="#888888"> </font></span></blockquote>
                                    <span class=""><font color="#888888">
                                      </font></span></div>
                                  <span class=""><font color="#888888">
                                      <br>
                                      <br clear="all">
                                      <div><br>
                                      </div>
                                      -- <br>
                                      <div
                                        data-smartmail="gmail_signature">What
                                        most experimenters take for
                                        granted before they begin their
                                        experiments is infinitely more
                                        interesting than any results to
                                        which their experiments lead.<br>
                                        -- Norbert Wiener</div>
                                    </font></span></div>
                                <span class=""><font color="#888888"> </font></span></div>
                              <span class=""><font color="#888888"> </font></span></blockquote>
                            <span class=""><font color="#888888"> <br>
                              </font></span></div>
                          <span class=""><font color="#888888"> </font></span></div>
                        <span class=""><font color="#888888"> </font></span></blockquote>
                      <span class=""><font color="#888888"> </font></span></div>
                    <span class=""><font color="#888888"> <br>
                      </font></span></blockquote>
                </blockquote>
                <br>
              </div>
            </blockquote>
          </div>
          <br>
          <br clear="all">
          <div><br>
          </div>
          -- <br>
          <div class="gmail_signature" data-smartmail="gmail_signature">What
            most experimenters take for granted before they begin their
            experiments is infinitely more interesting than any results
            to which their experiments lead.<br>
            -- Norbert Wiener</div>
        </div>
      </div>
    </blockquote>
    <br>
    <pre class="moz-signature" cols="72">
</pre>
  </body>
</html>