Re: Help understanding slow down

[Ingo Molnar]

* Andrew Morton <akpm@xxxxxxxx> wrote:

> But if you _are_ using poll_idle() and if your CPU is hyperthreaded
> then yes, one "CPU" is going to take a performance hit from the "idle"
> one.

with the patch below we will print a big fat warning. (I did not want to
deny idle=poll altogether - future HT implementations might work fine
with polling idle.)

	Ingo

Signed-off-by: Ingo Molnar <mingo@xxxxxxx>

--- linux/arch/i386/kernel/process.c.orig	
+++ linux/arch/i386/kernel/process.c	
@@ -202,6 +202,10 @@ static int __init idle_setup (char *str)
 	if (!strncmp(str, "poll", 4)) {
 		printk("using polling idle threads.\n");
 		pm_idle = poll_idle;
+#ifdef CONFIG_SMP
+		if (smp_num_siblings > 1)
+			printk("WARNING: polling idle and HT enabled, performance may degrade.\n");
+#endif
 	} else if (!strncmp(str, "halt", 4)) {
 		printk("using halt in idle threads.\n");
 		pm_idle = default_idle;
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/