Re: [patch] latency tracer, 2.6.15-rc7

[Lee Revell]

On Thu, 2005-12-29 at 21:28 +0100, Ingo Molnar wrote:
> * Lee Revell <rlrevell@xxxxxxxxxxx> wrote:
> 
> > > Still does not quite work for me on i386.  I applied all the patches as
> > > I'm using 4K stacks.
> 
> oops!
> 
> > > LD      .tmp_vmlinux1
> > > init/built-in.o: In function `start_kernel':
> > > : undefined reference to `preempt_max_latency'
> > > make: *** [.tmp_vmlinux1] Error 1
> > > 
> > 
> > This patch fixes the problem.
> 
> thanks, applied - new version uploaded.

It seems that debug_smp_processor_id is being called a lot, even though
I have a UP config, which I didn't see with the -rt kernel:

$ grep debug_smp_processor_id /proc/latency_trace | head -20
evolutio-4568  0d.H1    3us : debug_smp_processor_id (do_IRQ)
evolutio-4568  0d.h.   25us : debug_smp_processor_id (netif_rx)
evolutio-4568  0d.h.   28us : debug_smp_processor_id (kmem_cache_alloc)
evolutio-4568  0d.h.   31us+: debug_smp_processor_id (__kmalloc)
evolutio-4568  0d.s.   46us : debug_smp_processor_id (__do_softirq)
evolutio-4568  0d.s.   47us : debug_smp_processor_id (__do_softirq)
evolutio-4568  0d.s1   54us+: debug_smp_processor_id (kmem_cache_alloc)
evolutio-4568  0d.s1   65us : debug_smp_processor_id (kmem_cache_free)
evolutio-4568  0d.s3  109us : debug_smp_processor_id (kmem_cache_alloc)
evolutio-4568  0d.s3  111us+: debug_smp_processor_id (__kmalloc)
evolutio-4568  0d.s3  140us : debug_smp_processor_id (kfree)
evolutio-4568  0d.s3  141us : debug_smp_processor_id (kmem_cache_free)
evolutio-4568  0d.s3  158us : debug_smp_processor_id (kfree)
evolutio-4568  0d.s3  160us : debug_smp_processor_id (kmem_cache_free)
evolutio-4568  0d.s3  192us : debug_smp_processor_id (kfree)
evolutio-4568  0d.s3  193us : debug_smp_processor_id (kmem_cache_free)
evolutio-4568  0d.s3  210us : debug_smp_processor_id (kfree)
evolutio-4568  0d.s3  211us : debug_smp_processor_id (kmem_cache_free)
evolutio-4568  0d.s3  216us : debug_smp_processor_id (kmem_cache_alloc)
evolutio-4568  0d.s3  217us+: debug_smp_processor_id (__kmalloc)

etc.

Was this optimized out on UP before?

Lee

-
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/