Is there any chance of the following patch being applied to the up
and coming 2.0.31? It is a rework of a patch sent a couple of months
ago to the smp list and it makes the time command return more sensible
user/system values for an SMP kernel...
[ Matthias Ohlenroth <Matthias.Ohlenroth@informatik.tu-chemnitz.de>
originally sent it, I've just made it apply to 2.0.31pre9 ]
PS. 2.0.31pre9 seems to be working rather well here (Dual PPro
system).
Cheers,
Andrew.
-- Andrew Pollard, Auto Simulations Ltd. UK. | home: andrew@odie.demon.co.uk 2 Milbanke Court, Milbanke Way, Bracknell | work: andrewp@autosim.com Tel:+44(0)1344 426486 Fax:+44(0)1344 426615 | http://www.odie.demon.co.ukdiff -u --recursive --new-file v2.0.31pre9/linux/include/asm/irq.h linux/include/asm/irq.h --- v2.0.31pre9/linux/include/asm/irq.h Wed Sep 10 14:28:12 1997 +++ linux/include/asm/irq.h Wed Sep 10 14:42:11 1997 @@ -239,6 +239,8 @@ "addl $8,%esp\n\t" \ "cli\n\t" \ UNBLK_##chip(mask) \ + GET_PROCESSOR_ID \ + "btrl $" STR(SMP_FROM_INT) ","SYMBOL_NAME_STR(smp_proc_in_lock)"(,%eax,4)\n\t" \ "decl "SYMBOL_NAME_STR(intr_count)"\n\t" \ "incl "SYMBOL_NAME_STR(syscall_count)"\n\t" \ "jmp ret_from_sys_call\n" \ @@ -286,6 +288,8 @@ "addl $8,%esp\n\t" \ "cli\n\t" \ UNBLK_##chip(mask) \ + GET_PROCESSOR_ID \ + "btrl $" STR(SMP_FROM_INT) ","SYMBOL_NAME_STR(smp_proc_in_lock)"(,%eax,4)\n\t" \ "decl "SYMBOL_NAME_STR(intr_count)"\n\t" \ "incl "SYMBOL_NAME_STR(syscall_count)"\n\t" \ "jmp ret_from_sys_call\n"); @@ -353,6 +357,8 @@ "call "SYMBOL_NAME_STR(smp_reschedule_irq)"\n\t" \ "addl $8,%esp\n\t" \ "cli\n\t" \ + GET_PROCESSOR_ID \ + "btrl $" STR(SMP_FROM_INT) ","SYMBOL_NAME_STR(smp_proc_in_lock)"(,%eax,4)\n\t" \ "decl "SYMBOL_NAME_STR(intr_count)"\n\t" \ "incl "SYMBOL_NAME_STR(syscall_count)"\n\t" \ "jmp ret_from_sys_call\n");