Remove needless delay in MCA rendezvous

[patch] Remove needless delay in MCA rendezvous

While testing the MCA recovery code, noticed that some machines would have a five second delay rendezvousing cpus. What was happening is that ia64_wait_for_slaves() would check to see if all the slave CPUs had rendezvoused. If any had not, it would wait 1 millisecond then check again. If any CPUs had still not rendezvoused, it would wait 5 seconds before checking again.

On some configs the rendezvous takes more than 1 millisecond, causing the code to wait the full 5 seconds, even though the last CPU rendezvoused after only a few milliseconds.

The fix is to check every 1 millisecond to see if all the cpus have rendezvoused. After 5 seconds the code concludes the CPUs will never rendezvous (same as before).

The MCA code is, by definition, not performance critical, but a needless delay of 5 seconds is senseless. The 5 seconds also adds up quickly when running the error injection code in a loop.

This patch both simplifies the code and removes the needless delay.

---
 arch/ia64/kernel/mca.c |   41 +++++++++++++++++++----------------------
 1 file changed, 19 insertions(+), 22 deletions(-)

Index: test/arch/ia64/kernel/mca.c
=================================--- test.orig/arch/ia64/kernel/mca.c 2007-09-20 10:23:57.011455209 -0500
+++ test/arch/ia64/kernel/mca.c 2007-09-20 10:24:00.463872304 -0500
@@ -1136,30 +1136,27 @@ no_mod:
static void
ia64_wait_for_slaves(int monarch, const char *type)
{
- int c, wait = 0, missing = 0;
- for_each_online_cpu(c) {
- if (c = monarch)
- continue;
- if (ia64_mc_info.imi_rendez_checkin[c] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE) {
- udelay(1000); /* short wait first */
- wait = 1;
- break;
+ int c, i , wait;
+
+ /*
+ * wait 5 seconds total for slaves (arbitrary)
+ */
+ for (i = 0; i < 5000; i++) {
+ wait = 0;
+ for_each_online_cpu(c) {
+ if (c = monarch)
+ continue;
+ if (ia64_mc_info.imi_rendez_checkin[c]
+ = IA64_MCA_RENDEZ_CHECKIN_NOTDONE) {
+ udelay(1000); /* short wait */
+ wait = 1;
+ break;
+ }
}
+ if (!wait)
+ goto all_in;
}
- if (!wait)
- goto all_in;
- for_each_online_cpu(c) {
- if (c = monarch)
- continue;
- if (ia64_mc_info.imi_rendez_checkin[c] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE) {
- udelay(5*1000000); /* wait 5 seconds for slaves (arbitrary) */
- if (ia64_mc_info.imi_rendez_checkin[c] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE)
- missing = 1;
- break;
- }
- }
- if (!missing)
- goto all_in;
+
/*
* Maybe slave(s) dead. Print buffered messages immediately. */

Russ Anderson  RAS group  SGI  [email protected]