Dnia 12-06-2006 o godz. 8:43 Bob Breuer napisał(a): > David Miller wrote: > > From: Bob Breuer <breuerr@xxxxxx> > > Date: Sun, 11 Jun 2006 20:21:09 -0500 > > > >> David Miller wrote: > >>> But why in the world does the scheduler "lock up" just because the > >>> migration cost is too large? > >> There is an address space collision between the vmalloc area and where > >> the prom maps the framebuffer. > > I run the kernel without the framebuffer (on serial console). I saw many vmalloc warnings trigered in vmap_pte_range() [mm/vmalloc.c line 97]. I supposed they were done from measure_one() [kernel/sched.c]. I have only CG6 installed in SS20. I have not the CG14 VRAM. The warnings were triggered from the first call to measure_one(). The calls were done with the smallest size (64K) first so the size should not matter. I hope it helps, Krzysztof. ---------------------------------------------------- CIBELLE na koncertach w Sopocie (23.06) i Warszawie (24.06). Zmysłowa bossa nowa, elementy jazzu oraz odrobina elektroniki. http://klik.wp.pl/?adr=http%3A%2F%2Fadv.reklama.wp.pl%2Fas%2Fchat_cibelle.html&sid=792 - To unsubscribe from this list: send the line "unsubscribe sparclinux" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
