Re: --mx-kill
Chris Samuel <[email protected]> Tue, 19 Sep 2006 18:14:26 +1000
| Newsgroups | gmane.network.myrinet.general |
|---|---|
| Organization | VPAC - Victorian Partnership for Advanced Computing |
| Message-ID | <[email protected]> |
--===============1442127780== Content-Type: multipart/signed; boundary="nextPart6273699.2oL6Ot0tre"; protocol="application/pgp-signature"; micalg=pgp-sha1 Content-Transfer-Encoding: 7bit --nextPart6273699.2oL6Ot0tre Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline On Thursday 14 September 2006 09:34, george wm turner wrote: > =A0 =A0 =A0As SysAdmins, we're thinking of making --mx-kill 60 the > default on our mpirun commands to force clean up of orphans > left behind when user's codes error out. If you're using Torque then have you considered using Pete Wyckoff's excell= ent=20 mpiexec instead ? That will talk directly to the pbs_mom's to get its information and to star= t=20 the processes using the TM interface. Much neater all round, PBS gets to=20 monitor the processes CPU times more accurately and it is directly aware of= =20 processes dieing. cheers, Chris =2D-=20 Christopher Samuel - (03)9925 4751 - VPAC Deputy Systems Manager Victorian Partnership for Advanced Computing http://www.vpac.org/ Bldg 91, 110 Victoria Street, Carlton South, VIC 3053, Australia --nextPart6273699.2oL6Ot0tre Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.2.2 (GNU/Linux) iD8DBQBFD6biO2KABBYQAh8RAgtcAKCCD8qnc1lUmEwqspBEofoHFAPyQwCePn6F qWd8xsurW43VXkt82cLZwJQ= =lihW -----END PGP SIGNATURE----- --nextPart6273699.2oL6Ot0tre-- --===============1442127780== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Myrinet mailing list [email protected] http://email.osc.edu/mailman/listinfo/myrinet --===============1442127780==--