Pierangelo Masarati wrote:
> Dear ADEOS users,
>
> 2.6.25 seems to show abnormal latencies on hardware that showed good
> performances up to 2.6.24. We think we traced down the issue to x86's
> process_xx.c, which disappeared after regressing default_idle() to
> 2.6.24. The related changes are described in the attached patch.
>
This patch would badly break the runqueue statistics, and likely the Linux
scheduler tick engine too.
Actually, the hunk in default_idle() seems useless, since co-kernel activity
should be accounted as Linux idle time anyway. Does this patch also fixes
the issue you tracked down?
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8d71912..d97c8c2 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -111,7 +111,7 @@ void default_idle(void)
*/
smp_mb();
- local_irq_disable_hw();
+ local_irq_disable();
if (!need_resched()) {
ktime_t t0, t1;
u64 t0n, t1n;
@@ -123,9 +123,8 @@ void default_idle(void)
t1 = ktime_get();
t1n = ktime_to_ns(t1);
sched_clock_idle_wakeup_event(t1n - t0n);
- local_irq_enable(); /* This will force enable_hw as
well. */
- } else
- local_irq_enable_hw();
+ }
+ local_irq_enable();
current_thread_info()->status |= TS_POLLING;
} else {
/* loop is done by the caller */
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index fa242a4..a3b2fa7 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -107,7 +107,7 @@ void default_idle(void)
* test NEED_RESCHED:
*/
smp_mb();
- local_irq_disable_hw();
+ local_irq_disable();
if (!need_resched()) {
ktime_t t0, t1;
u64 t0n, t1n;
@@ -119,9 +119,8 @@ void default_idle(void)
t1 = ktime_get();
t1n = ktime_to_ns(t1);
sched_clock_idle_wakeup_event(t1n - t0n);
- local_irq_enable(); /* This will force enable_hw as well. */
- } else
- local_irq_enable_hw();
+ }
+ local_irq_enable();
current_thread_info()->status |= TS_POLLING;
}
--
Philippe.
_______________________________________________
Adeos-main mailing list
[email protected]
https://mail.gna.org/listinfo/adeos-main
