Re: [PATCH 3/6] tracing, page-allocator: Add trace event for pagetraffic related to the buddy lists

[Mel Gorman]

On Fri, Aug 07, 2009 at 09:53:17AM +0200, Ingo Molnar wrote:
> 
> * Mel Gorman <mel@xxxxxxxxx> wrote:
> 
> > +TRACE_EVENT(mm_page_pcpu_drain,
> > +
> > +	TP_PROTO(struct page *page, int order, int migratetype),
> > +
> > +	TP_ARGS(page, order, migratetype),
> > +
> > +	TP_STRUCT__entry(
> > +		__field(	struct page *,	page		)
> > +		__field(	int,		order		)
> > +		__field(	int,		migratetype	)
> > +	),
> > +
> > +	TP_fast_assign(
> > +		__entry->page		= page;
> > +		__entry->order		= order;
> > +		__entry->migratetype	= migratetype;
> > +	),
> > +
> > +	TP_printk("page=%p pfn=%lu order=%d cpu=%d migratetype=%d",
> > +		__entry->page,
> > +		page_to_pfn(__entry->page),
> > +		__entry->order,
> > +		smp_processor_id(),
> > +		__entry->migratetype)
> 
> > +	trace_mm_page_alloc_zone_locked(page, order, migratetype, order == 0);
> 
> This can be optimized further by omitting the migratetype field and 
> adding something like this:
> 
> 	TP_printk("page=%p pfn=%lu order=%d cpu=%d migratetype=%d",
> 		__entry->page,
> 		page_to_pfn(__entry->page),
> 		__entry->order,
> 		smp_processor_id(),
> 		__entry->order == 0);
> 
> The advantage is 4 bytes less in the record and a shorter tracepoint 
> fast-path - while still having the same output.
> 

Knowing you meant percpu_refill, it's now been figured out in TP_printk
instead of in the code.

-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab
--
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/