Re: [PATCH] perf report: always honor callchain order for inlined nodes
From: Milian Wolff
Date: Wed May 17 2017 - 04:04:16 EST
On Wednesday, May 17, 2017 6:26:45 AM CEST Namhyung Kim wrote:
> On Tue, May 16, 2017 at 11:54:22PM +0200, Milian Wolff wrote:
> > So far, the inlined nodes where only reversed when we built perf
> > against libbfd. If that was not available, the addr2line fallback
> > code path was missing the inline_list__reverse call.
> >
> > Now this is done at the central place inside dso__parse_addr_inlines.
>
> What about changing inline_list__append() instead to honor callchain
> order?
>
> if (ORDER_CALLEE)
> list_add_tail(...);
> else
> list_add(...);
good idea, I'll do that.
Cheers
--
Milian Wolff | milian.wolff@xxxxxxxx | Software Engineer
KDAB (Deutschland) GmbH&Co KG, a KDAB Group company
Tel: +49-30-521325470
KDAB - The Qt ExpertsAttachment:
smime.p7s
Description: S/MIME cryptographic signature