From 280ff97494e0fef4124bee5c52e39b23a18dd283 Mon Sep 17 00:00:00 2001 From: "Hong H. Pham" Date: Thu, 4 Jun 2009 02:10:11 -0700 Subject: sparc64: fix and optimize irq distribution irq_choose_cpu() should compare the affinity mask against cpu_online_map rather than CPU_MASK_ALL, since irq_select_affinity() sets the interrupt's affinity mask to cpu_online_map "and" CPU_MASK_ALL (which ends up being just cpu_online_map). The mask comparison in irq_choose_cpu() will always fail since the two masks are not the same. So the CPU chosen is the first CPU in the intersection of cpu_online_map and CPU_MASK_ALL, which is always CPU0. That means all interrupts are reassigned to CPU0... Distributing interrupts to CPUs in a linearly increasing round robin fashion is not optimal for the UltraSPARC T1/T2. Also, the irq_rover in irq_choose_cpu() causes an interrupt to be assigned to a different processor each time the interrupt is allocated and released. This may lead to an unbalanced distribution over time. A static mapping of interrupts to processors is done to optimize and balance interrupt distribution. For the T1/T2, interrupts are spread to different cores first, and then to strands within a core. The following is some benchmarks showing the effects of interrupt distribution on a T2. The test was done with iperf using a pair of T5220 boxes, each with a 10GBe NIU (XAUI) connected back to back. TCP | Stock Linear RR IRQ Optimized IRQ Streams | 2.6.30-rc5 Distribution Distribution | GBits/sec GBits/sec GBits/sec --------+----------------------------------------- 1 0.839 0.862 0.868 8 1.16 4.96 5.88 16 1.15 6.40 8.04 100 1.09 7.28 8.68 Signed-off-by: Hong H. Pham Signed-off-by: David S. Miller --- arch/sparc/kernel/irq_64.c | 29 ++++------------------------- 1 file changed, 4 insertions(+), 25 deletions(-) (limited to 'arch/sparc/kernel/irq_64.c') diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index e5e78f9cfc95..bd075054942b 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -45,6 +45,7 @@ #include #include "entry.h" +#include "cpumap.h" #define NUM_IVECS (IMAP_INR + 1) @@ -256,35 +257,13 @@ static int irq_choose_cpu(unsigned int virt_irq) int cpuid; cpumask_copy(&mask, irq_desc[virt_irq].affinity); - if (cpus_equal(mask, CPU_MASK_ALL)) { - static int irq_rover; - static DEFINE_SPINLOCK(irq_rover_lock); - unsigned long flags; - - /* Round-robin distribution... */ - do_round_robin: - spin_lock_irqsave(&irq_rover_lock, flags); - - while (!cpu_online(irq_rover)) { - if (++irq_rover >= nr_cpu_ids) - irq_rover = 0; - } - cpuid = irq_rover; - do { - if (++irq_rover >= nr_cpu_ids) - irq_rover = 0; - } while (!cpu_online(irq_rover)); - - spin_unlock_irqrestore(&irq_rover_lock, flags); + if (cpus_equal(mask, cpu_online_map)) { + cpuid = map_to_cpu(virt_irq); } else { cpumask_t tmp; cpus_and(tmp, cpu_online_map, mask); - - if (cpus_empty(tmp)) - goto do_round_robin; - - cpuid = first_cpu(tmp); + cpuid = cpus_empty(tmp) ? map_to_cpu(virt_irq) : first_cpu(tmp); } return cpuid; -- cgit v1.2.3