From e729aa16b168fb202d1a20f936028cb7c2a0278d Mon Sep 17 00:00:00 2001 From: Ravikiran G Thirumalai Date: Tue, 8 May 2007 00:29:13 -0700 Subject: Pad irq_desc to internode cacheline size We noticed a drop in n/w performance due to the irq_desc being cacheline aligned rather than internode aligned. We see 50% of expected performance when two e1000 nics local to two different nodes have consecutive irq descriptors allocated, due to false sharing. Note that this patch does away with cacheline padding for the UP case, as it does not seem useful for UP configurations. Signed-off-by: Ravikiran Thirumalai Signed-off-by: Shai Fultheim Cc: "Siddha, Suresh B" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irq.h | 4 +--- kernel/irq/handle.c | 2 +- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/include/linux/irq.h b/include/linux/irq.h index a6899402b522..1695054e8c63 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -147,8 +147,6 @@ struct irq_chip { * @dir: /proc/irq/ procfs entry * @affinity_entry: /proc/irq/smp_affinity procfs entry on SMP * @name: flow handler name for /proc/interrupts output - * - * Pad this out to 32 bytes for cache and indexing reasons. */ struct irq_desc { irq_flow_handler_t handle_irq; @@ -175,7 +173,7 @@ struct irq_desc { struct proc_dir_entry *dir; #endif const char *name; -} ____cacheline_aligned; +} ____cacheline_internodealigned_in_smp; extern struct irq_desc irq_desc[NR_IRQS]; diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index aff1f0fabb0d..515ad40bde15 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -48,7 +48,7 @@ handle_bad_irq(unsigned int irq, struct irq_desc *desc) * * Controller mappings for all interrupt sources: */ -struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned = { +struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { [0 ... NR_IRQS-1] = { .status = IRQ_DISABLED, .chip = &no_irq_chip, -- cgit v1.2.3