[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20171123124738.nj7foesbajo42t3g@dhcp22.suse.cz>
Date: Thu, 23 Nov 2017 13:47:38 +0100
From: Michal Hocko <mhocko@...nel.org>
To: peter enderborg <peter.enderborg@...y.com>
Cc: linux-kernel@...r.kernel.org, linux-mm@...ck.org,
Steven Rostedt <rostedt@...dmis.org>,
Ingo Molnar <mingo@...hat.com>,
Alex Deucher <alexander.deucher@....com>,
"David S . Miller" <davem@...emloft.net>,
Harry Wentland <Harry.Wentland@....com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Tony Cheng <Tony.Cheng@....com>,
Andrew Morton <akpm@...ux-foundation.org>,
Vlastimil Babka <vbabka@...e.cz>,
Mel Gorman <mgorman@...hsingularity.net>,
Johannes Weiner <hannes@...xchg.org>,
Pavel Tatashin <pasha.tatashin@...cle.com>
Subject: Re: [PATCH] Add slowpath enter/exit trace events
On Thu 23-11-17 13:35:15, peter enderborg wrote:
> Monitoring both enter/exit for all allocations and track down the one
> that are slow will be a very big load on mobile devices or embedded
> device consuming a lot of battery and cpu. With this we can do useful
> monitoring on devices on our field tests with real usage.
This might be true but the other POV is that the trace point with the
additional information is just too disruptive to the rest of the code
and it exposes too many implementation details.
--
Michal Hocko
SUSE Labs
Powered by blists - more mailing lists