<html><head><meta http-equiv="Content-Type" content="text/html; charset=us-ascii"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><br class=""><div><br class=""><blockquote type="cite" class=""><div class="">On Sep 18, 2020, at 10:14 AM, Satish Balay <<a href="mailto:balay@mcs.anl.gov" class="">balay@mcs.anl.gov</a>> wrote:</div><br class="Apple-interchange-newline"><div class=""><div class="">Its probably better to just run a test with gethostbyname()?<br class=""></div></div></blockquote><div><br class=""></div> I had hoped to avoid building C code and running it. The Apple manual page for gethostbyname() states: <b style="font-family: Menlo; font-size: 14px;" class="">The</b><span style="font-family: Menlo; font-size: 14px;" class=""> getaddrinfo(</span><b style="font-family: Menlo; font-size: 14px;" class="">3</b><span style="font-family: Menlo; font-size: 14px;" class="">) </span><b style="font-family: Menlo; font-size: 14px;" class="">and</b><span style="font-family: Menlo; font-size: 14px;" class=""> getnameinfo(</span><b style="font-family: Menlo; font-size: 14px;" class="">3</b><span style="font-family: Menlo; font-size: 14px;" class="">) </span><b style="font-family: Menlo; font-size: 14px;" class="">functions</b><span style="font-family: Menlo; font-size: 14px;" class=""> </span><b style="font-family: Menlo; font-size: 14px;" class="">are</b><span style="font-family: Menlo; font-size: 14px;" class=""> </span><b style="font-family: Menlo; font-size: 14px;" class="">preferred</b><span style="font-family: Menlo; font-size: 14px;" class=""> </span><b style="font-family: Menlo; font-size: 14px;" class="">over</b><span style="font-family: Menlo; font-size: 14px;" class=""> </span><b style="font-family: Menlo; font-size: 14px;" class="">the</b><span style="font-family: Menlo; font-size: 14px;" class=""> </span><b style="font-family: Menlo; font-size: 14px;" class="">gethostbyname</b><span style="font-family: Menlo; font-size: 14px;" class="">()</span><b style="font-family: Menlo; font-size: 14px;" class="">,</b><span style="font-family: Menlo; font-size: 14px;" class=""> </span><b style="font-family: Menlo; font-size: 14px;" class="">gethostbyname2</b><span style="font-family: Menlo; font-size: 14px;" class="">()</span><b style="font-family: Menlo; font-size: 14px;" class="">,</b><span style="font-family: Menlo; font-size: 14px;" class=""> </span><b style="font-family: Menlo; font-size: 14px;" class="">and</b><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""> <b class="">gethostbyaddr</b>() <b class="">functions.</b></span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><b class=""><br class=""></b></span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><b class=""><br class=""></b></span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><b class=""> I</b></span> do not know what MPICH and OpenMPI use. </div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><br class=""></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""> On the Mac </div><div class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><b class=""><br class=""></b></span></div><blockquote type="cite" class=""><div class=""><div class=""><br class="">The closest thing I can think off is:<br class=""><br class=""><br class="">I don't know if 'traceroute' or 'host' commands are universally available.<br class=""><br class=""><blockquote type="cite" class=""><blockquote type="cite" class=""><blockquote type="cite" class=""><blockquote type="cite" class=""><blockquote type="cite" class=""><blockquote type="cite" class=""><br class=""></blockquote></blockquote></blockquote></blockquote></blockquote></blockquote>balay@sb /home/balay<br class="">$ host `hostname`<br class="">sb has address 192.168.0.144<br class=""></div></div></blockquote><div><br class=""></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class="">$ host `hostname`</span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class="">Host Barrys-MacBook-Pro-3.local not found: 3(NXDOMAIN)</span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><br class=""></span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class="">Also on the Apple `hostname` is associated with multiple addresses and it seems different utilities may use different addresses produced. Some addresses may work, others may not.</span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><br class=""></span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><br class=""></span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""> I will make one more MR adding traceroute first and if any of the tests succeed continue. If that fails for users then we will likely need to drop the test.</span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><br class=""></span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""> I don't like just using a mpiexec -n 2 test because that can fail for so many reasons it is difficult to provide diagnostics to the users.</span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><br class=""></span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class="">Barry</div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><br class=""></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><br class=""></span></div><div style="margin: 0px; font-stretch: normal; font-size: 14px; line-height: normal; font-family: Menlo;" class=""><span style="font-variant-ligatures: no-common-ligatures" class=""><br class=""></span></div><blockquote type="cite" class=""><div class=""><div class="">balay@sb /home/balay<br class="">$ echo $?<br class="">0<br class="">balay@sb /home/balay<br class="">$ host foobar<br class="">Host foobar not found: 3(NXDOMAIN)<br class="">balay@sb /home/balay<br class="">$ echo $?<br class="">1<br class="">balay@sb /home/balay<br class="">$ <br class=""><<<<<<<br class=""><br class="">However - I fear if there are *any* false positives - or false negatives - this test will generate more e-mail than the actual issue [of misbehaving MPI]<br class=""><br class="">Satish<br class=""><br class="">On Fri, 18 Sep 2020, Barry Smith wrote:<br class=""><br class=""><blockquote type="cite" class=""><br class=""> try <br class=""><br class=""> /usr/sbin/traceroute `hostname`<br class=""><br class=""><br class=""><blockquote type="cite" class="">On Sep 18, 2020, at 10:07 AM, Mark Adams <<a href="mailto:mfadams@lbl.gov" class="">mfadams@lbl.gov</a>> wrote:<br class=""><br class="">Let me know if you want anything else.<br class="">Thanks,<br class="">Mark<br class=""><br class="">On Fri, Sep 18, 2020 at 11:05 AM Mark Adams <<a href="mailto:mfadams@lbl.gov" class="">mfadams@lbl.gov</a> <<a href="mailto:mfadams@lbl.gov" class="">mailto:mfadams@lbl.gov</a>>> wrote:<br class=""><br class=""><br class="">On Fri, Sep 18, 2020 at 11:04 AM Satish Balay <<a href="mailto:balay@mcs.anl.gov" class="">balay@mcs.anl.gov</a> <<a href="mailto:balay@mcs.anl.gov" class="">mailto:balay@mcs.anl.gov</a>>> wrote:<br class="">On Fri, 18 Sep 2020, Satish Balay via petsc-users wrote:<br class=""><br class=""><blockquote type="cite" class=""><blockquote type="cite" class=""><blockquote type="cite" class=""><blockquote type="cite" class="">07:41 master *= ~/Codes/petsc$ ping -c 2 MarksMac-302.local<br class="">PING marksmac-302.local (127.0.0.1): 56 data bytes<br class=""></blockquote></blockquote></blockquote><br class="">So it is resolving MarksMac-302.local as 127.0.0.1 - but ping is not responding?<br class=""><br class="">I know some machines don't respond to external ping [and firewalls can block it] but don't really know if they always respond to internal ping or not.<br class=""><br class="">If some machines don't respond to internal ping - then we can't use ping test in configure [it will create false negatives - as in this case]<br class=""></blockquote><br class="">BTW: To confirm, please try:<br class=""><br class="">ping 127.0.0.1<br class=""><br class=""><br class="">11:02 master *= ~/Codes/petsc$ sudo vi /etc/hosts<br class="">11:02 master *= ~/Codes/petsc$ ping 127.0.0.1<br class="">PING 127.0.0.1 (127.0.0.1): 56 data bytes<br class="">Request timeout for icmp_seq 0<br class="">Request timeout for icmp_seq 1<br class="">Request timeout for icmp_seq 2<br class="">Request timeout for icmp_seq 3<br class="">Request timeout for icmp_seq 4<br class="">Request timeout for icmp_seq 5<br class="">Request timeout for icmp_seq 6<br class="">Request timeout for icmp_seq 7<br class="">Request timeout for icmp_seq 8<br class="">Request timeout for icmp_seq 9<br class="">Request timeout for icmp_seq 10<br class="">Request timeout for icmp_seq 11<br class="">Request timeout for icmp_seq 12<br class="">Request timeout for icmp_seq 13<br class="">Request timeout for icmp_seq 14<br class="">Request timeout for icmp_seq 15<br class="">Request timeout for icmp_seq 16<br class="">Request timeout for icmp_seq 17<br class="">Request timeout for icmp_seq 18<br class="">Request timeout for icmp_seq 19<br class="">Request timeout for icmp_seq 20<br class="">Request timeout for icmp_seq 21<br class=""><br class="">still going ......<br class=""><br class=""><br class="">Satish<br class=""><br class=""><blockquote type="cite" class=""><br class=""><br class="">Mark, can you remove the line that you added to /etc/hosts - i.e:<br class=""><br class="">127.0.0.1 MarksMac-302.local<br class=""><br class="">And now rerun MPI tests. Do they work or fail?<br class=""><br class="">[this is to check if this test is a false positive on your machine]<br class=""><br class="">Satish<br class=""><br class=""><br class="">On Fri, 18 Sep 2020, Mark Adams wrote:<br class=""><br class=""><blockquote type="cite" class="">On Fri, Sep 18, 2020 at 7:51 AM Matthew Knepley <<a href="mailto:knepley@gmail.com" class="">knepley@gmail.com</a> <<a href="mailto:knepley@gmail.com" class="">mailto:knepley@gmail.com</a>>> wrote:<br class=""><br class=""><blockquote type="cite" class="">On Fri, Sep 18, 2020 at 7:46 AM Mark Adams <<a href="mailto:mfadams@lbl.gov" class="">mfadams@lbl.gov</a> <<a href="mailto:mfadams@lbl.gov" class="">mailto:mfadams@lbl.gov</a>>> wrote:<br class=""><br class=""><blockquote type="cite" class="">Oh you did not change my hostname:<br class=""><br class="">07:37 master *= ~/Codes/petsc$ hostname<br class="">MarksMac-302.local<br class="">07:41 master *= ~/Codes/petsc$ ping -c 2 MarksMac-302.local<br class="">PING marksmac-302.local (127.0.0.1): 56 data bytes<br class="">Request timeout for icmp_seq 0<br class=""><br class="">--- marksmac-302.local ping statistics ---<br class="">2 packets transmitted, 0 packets received, 100.0% packet loss<br class="">07:42 2 master *= ~/Codes/petsc$<br class=""><br class=""></blockquote><br class="">This does not make sense to me. You have<br class=""><br class=""> 127.0.0.1 MarksMac-302.local<br class=""><br class="">in /etc/hosts,<br class=""><br class=""></blockquote><br class="">09:07 ~/.ssh$ cat /etc/hosts<br class="">##<br class=""># Host Database<br class="">#<br class=""># localhost is used to configure the loopback interface<br class=""># when the system is booting. Do not change this entry.<br class="">##<br class="">127.0.0.1 localhost<br class="">255.255.255.255 broadcasthost<br class="">127.0.0.1 MarksMac-5.local<br class="">127.0.0.1 243.124.240.10.in-addr.arpa.private.cam.ac.uk <<a href="http://243.124.240.10.in-addr.arpa.private.cam.ac.uk/" class="">http://243.124.240.10.in-addr.arpa.private.cam.ac.uk/</a>><br class="">127.0.0.1 MarksMac-302.local<br class="">09:07 ~/.ssh$<br class=""><br class=""><br class=""><br class=""><br class=""><br class=""><blockquote type="cite" class="">but you cannot resolve that name?<br class=""><br class=""> Matt<br class=""><br class=""><br class=""><blockquote type="cite" class="">BTW, I used to get messages about some network issue and 'changing host<br class="">name to MarksMac-[x+1].local'. That is, the original hostname<br class="">was MarksMac.local, then I got a message about changing<br class="">to MarksMac-1.local, etc. I have not seen these messages for months but<br class="">apparently this process has continued unabated.<br class=""><br class=""><br class=""><br class=""><br class=""><br class=""><br class=""><br class=""><br class=""><br class="">On Thu, Sep 17, 2020 at 11:10 PM Satish Balay via petsc-users <<br class=""><a href="mailto:petsc-users@mcs.anl.gov" class="">petsc-users@mcs.anl.gov</a> <<a href="mailto:petsc-users@mcs.anl.gov" class="">mailto:petsc-users@mcs.anl.gov</a>>> wrote:<br class=""><br class=""><blockquote type="cite" class="">On Thu, 17 Sep 2020, Matthew Knepley wrote:<br class=""><br class=""><blockquote type="cite" class="">On Thu, Sep 17, 2020 at 8:33 PM Barry Smith <<a href="mailto:bsmith@petsc.dev" class="">bsmith@petsc.dev</a> <<a href="mailto:bsmith@petsc.dev" class="">mailto:bsmith@petsc.dev</a>>> wrote:<br class=""><br class=""><blockquote type="cite" class=""><blockquote type="cite" class="">On Sep 17, 2020, at 4:59 PM, Satish Balay via petsc-users <<br class=""></blockquote><a href="mailto:petsc-users@mcs.anl.gov" class="">petsc-users@mcs.anl.gov</a> <<a href="mailto:petsc-users@mcs.anl.gov" class="">mailto:petsc-users@mcs.anl.gov</a>>> wrote:<br class=""><blockquote type="cite" class=""><br class="">Here is a fix:<br class=""><br class="">echo 127.0.0.1 `hostname` | sudo tee -a /etc/hosts<br class=""></blockquote><br class=""> Satish,<br class=""><br class=""> I don't think you want to be doing this on a Mac (on anything?)<br class=""></blockquote></blockquote>On a<br class=""><blockquote type="cite" class=""><blockquote type="cite" class="">Mac based on the network configuration etc as it boots up and as<br class=""></blockquote></blockquote>networks<br class=""><blockquote type="cite" class=""><blockquote type="cite" class="">are accessible or not (wi-fi) it determines what hostname should be,<br class=""></blockquote></blockquote>one<br class=""><blockquote type="cite" class=""><blockquote type="cite" class="">should never being hardwiring it to some value.<br class=""><br class=""></blockquote><br class="">Satish is just naming the loopback interface. I did this on all my<br class=""></blockquote>former<br class=""><blockquote type="cite" class="">Macs.<br class=""></blockquote><br class=""><br class="">Yes - this doesn't change the hostname. Its just adding an entry for<br class="">gethostbyname - for current hostname.<br class=""><br class=""><blockquote type="cite" class=""><blockquote type="cite" class=""><blockquote type="cite" class=""><br class=""></blockquote></blockquote></blockquote>127.0.0.1 MarksMac-302.local<br class=""><<<<br class=""><br class="">Sure - its best to not do this when one has a proper IP name [like<br class=""><a href="http://foo.mcs.anl.gov" class="">foo.mcs.anl.gov</a> <<a href="http://foo.mcs.anl.gov/" class="">http://foo.mcs.anl.gov/</a>>] - but its useful when one has a hostname like<br class="">"MarksMac-302.local" -that is not DNS resolvable<br class=""><br class="">Even if the machine is moved to a different network with a different<br class="">name - the current entry won't cause problems [but will need another entry<br class="">for the new host name - if this new name is also not DNS resolvable]<br class=""><br class="">Its likely this file is a generated file on macos - so might get reset<br class="">on reboot - or some network change? [if this is the case - the change won't<br class="">be permanent]<br class=""><br class=""><br class="">Satish<br class=""><br class=""></blockquote><br class=""></blockquote><br class="">--<br class="">What most experimenters take for granted before they begin their<br class="">experiments is infinitely more interesting than any results to which their<br class="">experiments lead.<br class="">-- Norbert Wiener<br class=""><br class=""><a href="https://www.cse.buffalo.edu/~knepley/" class="">https://www.cse.buffalo.edu/~knepley/</a> <<a href="https://www.cse.buffalo.edu/~knepley/" class="">https://www.cse.buffalo.edu/~knepley/</a>><br class=""><<a href="http://www.cse.buffalo.edu/~knepley/" class="">http://www.cse.buffalo.edu/~knepley/</a> <<a href="http://www.cse.buffalo.edu/~knepley/" class="">http://www.cse.buffalo.edu/~knepley/</a>>><br class=""><br class=""></blockquote><br class=""></blockquote><br class=""></blockquote><br class=""></blockquote><br class=""><br class=""></blockquote><br class=""></div></div></blockquote></div><br class=""></body></html>