Re: [PATCH tip/tracing/markers] new probes manager
- From: Ingo Molnar <mingo@xxxxxxx>
- Date: Mon, 27 Oct 2008 19:26:55 +0100
* Mathieu Desnoyers <compudj@xxxxxxxxxxxxxxxxxx> wrote:
* Mathieu Desnoyers (mathieu.desnoyers@xxxxxxxxxx) wrote:
* Lai Jiangshan (laijs@xxxxxxxxxxxxxx) wrote:
this patch use a new probes manager for marker.
the most important benefit of this patch is:
1) smp_rmb() is removed from the critical path. as we know rmb()
is very expensive.
Do you have performance measurements for this ? On x86 it's a nop,
AFAIK.
My statement above is inexact : x86_64 uses lfence for rmb(). But
numbers would still be welcome.
yes, the statement that rmb() is very expensive looks dubious. It is
absolutely cheap everywhere.
Ingo
--
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/
- Follow-Ups:
- Re: [PATCH tip/tracing/markers] new probes manager
- From: Lai Jiangshan
- Re: [PATCH tip/tracing/markers] new probes manager
- From: Paul Mackerras
- Re: [PATCH tip/tracing/markers] new probes manager
- References:
- [PATCH tip/tracing/markers] new probes manager
- From: Lai Jiangshan
- Re: [PATCH tip/tracing/markers] new probes manager
- From: Mathieu Desnoyers
- Re: [PATCH tip/tracing/markers] new probes manager
- From: Mathieu Desnoyers
- [PATCH tip/tracing/markers] new probes manager
- Prev by Date: Re: [Cbe-oss-dev] [PATCH] Cell OProfile: Incorrect local array size in activate spu profiling function
- Next by Date: Re: [PATCH] [RESEND v2] tracing/ftrace: Introduce the big kernel lock tracer
- Previous by thread: Re: [PATCH tip/tracing/markers] new probes manager
- Next by thread: Re: [PATCH tip/tracing/markers] new probes manager
- Index(es):
Relevant Pages
|
