linux-kernel - Re: [PATCH v16 14/15] perf tools: Don't warn about out of order event if write

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

Date:	Fri, 15 Jul 2016 16:59:23 +0200
From:	Jiri Olsa <jolsa@...hat.com>
To:	Wang Nan <wangnan0@...wei.com>
Cc:	acme@...nel.org, lizefan@...wei.com, linux-kernel@...r.kernel.org,
	pi3orama@....com, He Kuang <hekuang@...wei.com>,
	Arnaldo Carvalho de Melo <acme@...hat.com>,
	Jiri Olsa <jolsa@...nel.org>,
	Masami Hiramatsu <mhiramat@...nel.org>,
	Namhyung Kim <namhyung@...nel.org>,
	Nilay Vaish <nilayvaish@...il.com>
Subject: Re: [PATCH v16 14/15] perf tools: Don't warn about out of order
 event if write_backward is used

On Thu, Jul 14, 2016 at 08:34:46AM +0000, Wang Nan wrote:
> If write_backward attribute is set, records are written into kernel
> ring buffer from end to beginning, but read from beginning to end.

so IIUIC they are stored from the newest to the oldest one right?

we might want to sort them back when reading the perf.data,
or mark the area in the data section and trat it specially

or just make ordered_events__queue to recognize backward
data and buffer long enough before pushing the sample
to higher level

or any other way that would make sense ;-)

however this might come as follow up update, no reason
to hold this patchset on this

jirka