From a831027f1e9f217822054966e93d9ffb070fb33a Mon Sep 17 00:00:00 2001 From: kensmith Date: Wed, 29 Sep 2004 21:39:36 +0000 Subject: We seem to have occasions where sending an IPI takes significantly longer than 'normal'. The cause is still being tracked down but in the meantime there are machines where raising IPI_RETRIES does help - it's not just a case of the machine staying locked up longer and then panic-ing anyway. Several helpful folks on sparc64@ tried a patch that helped figure out what to raise this number to. Discussed on: sparc64@ MFC after: 3 days --- sys/sparc64/include/smp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'sys') diff --git a/sys/sparc64/include/smp.h b/sys/sparc64/include/smp.h index fba9eea..3f3b0b9 100644 --- a/sys/sparc64/include/smp.h +++ b/sys/sparc64/include/smp.h @@ -45,7 +45,7 @@ #define IPI_RENDEZVOUS PIL_RENDEZVOUS #define IPI_STOP PIL_STOP -#define IPI_RETRIES 100 +#define IPI_RETRIES 5000 struct cpu_start_args { u_int csa_count; -- cgit v1.1