From mboxrd@z Thu Jan 1 00:00:00 1970 From: khali@linux-fr.org (Jean Delvare) Date: Sat, 02 Sep 2006 20:57:03 +0000 Subject: [lm-sensors] TODO: "dynamic" sysfs callbacks Message-Id: <20060902225703.ee2ea946.khali@linux-fr.org> List-Id: References: <44F1E5B6.1080105@gmail.com> In-Reply-To: <44F1E5B6.1080105@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: lm-sensors@vger.kernel.org > On Sat, Sep 02, 2006 at 04:24:01PM +0200, Jean Delvare wrote: > > I don't have the time to even try measuring it. I just thought I would > > mention performance in the conversation, after I noticed with a user > > some days ago that logging sensors data using "sensors" every other > > second would put 15% of load on the system, while I expected it > > to be unnoticeable. > > This is probably just due to an interruptable sleep happening, which > artificially increases the load average. I would be supprised if the > CPU usage really goes up by that much. The bus driver msleep()s, so it's rather an uninterruptible sleep? Not that I know what different it makes in that context. And there's the userspace part probably taking a great deal of CPU as well, but I did not bother analyzing in detail where the time was spent back then. -- Jean Delvare