[Previo por Fecha] [Siguiente por Fecha] [Previo por Hilo] [Siguiente por Hilo]
[Hilos de Discusión] [Fecha] [Tema] [Autor]Aca les forwardeo este mensaje. Recuerdan los mensajes sobre clusters, mosix, etc. Creo que esta es una buena descripcion de las caracteristicas y propiedades del mosix y sirve para aclarar las dudas al repecto. saludos. ---------- Forwarded message ---------- Date: Thu, 7 Nov 2002 16:45:43 -0500 (EST) From: Donald Becker <becker en scyld com> To: Timothy H. Keitt <tkeitt en mail utexas edu> Cc: "'beowulf en beowulf org'" <beowulf en beowulf org> Subject: Re: Beowulf [& VMWare] > On Thu, 2002-10-31 at 13:30, Donald Becker wrote: > > On 31 Oct 2002, Timothy H. Keitt wrote: > > > > As most list readers know, I consider Mosix to be an academically > > interesting system and its transparent process migration an excellent > > touchstone to compare process migration approachs. > > > > Mosix is not a good system for scalable or performance-oriented > > clustering, and I agree with your conclustion that Mosix+VMware > > application serving is not a good match. > Mosix > moves the migration policy into the kernel, > has (deliberately) slow job migration to avoid scheduling hot-spots > uses in-kernel communication forwarding > While these allow unaware, and unmodified, applications to be migrated, > they are exactly the wrong decisions for MPI and PVM applications. > MPI and PVM > explicitly and simultaneously starts a known number of subprocesses, > knows where those subprocesses should be, and > builds new, explicit communication paths > The total effect is that Mosix takes much longer to start MPI/PVM jobs, > and has much higher overhead. > The features Mosix provides are > single point application updates > single process space view > Scyld Beowulf provides these at much lower CPU overhead. _______________________________________________ Ayuda mailing list Ayuda en linux org mx Para salir de la lista: http://mail.linux.org.mx/mailman/listinfo/ayuda/