linux-kernel - perf: PERF_EVENT_IOC

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-ID: <alpine.DEB.2.00.1208201447150.29057@cl320.icl.utk.edu>
Date:	Mon, 20 Aug 2012 14:53:52 -0400
From:	Vince Weaver <vweaver1@...s.utk.edu>
To:	<linux-kernel@...r.kernel.org>
CC:	<mingo@...e.hu>, <a.p.zijlstra@...llo.nl>,
	Paul Mackerras <paulus@...ba.org>,
	Arnaldo Carvalho de Melo <acme@...stprotocols.net>,
	Stephane Eranian <eranian@...il.com>
Subject: perf: PERF_EVENT_IOC_RESET and multiplexing

Hello

I have a perf API question.

When I run PERF_EVENT_IOC_RESET, all it resets is the event count.
It does not reset the PERF_FORMAT_TOTAL_TIME_ENABLED or
PERF_FORMAT_TOTAL_TIME_RUNNING values.

Is this expected?  It means if I'm trying to do multiplexing and want to 
reset the counts to zero, there's no way to reset the enabled/running 
values.

I suppose I can just close/reopen the events, or allocate some space to 
store the previous values, but that seems like unncessary overhead.

As an aside while I have your attention, can someone explain the 
difference between the "inherit" and the "inherit_stat" options in
perf.attr?  I can't seem to make a test case exhibit a difference, and
the events/core.c code in the kernel is a horrible wall of uncommented 
code that is nearly impossible to follow.

Thanks,

Vince
vweaver1@...s.utk.edu

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/