From mboxrd@z Thu Jan 1 00:00:00 1970 From: jonathan.rajotte-julien@efficios.com (Jonathan Rajotte-Julien) Date: Tue, 19 Sep 2017 10:57:07 -0400 Subject: [lttng-dev] Babeltrace performance issue in live-reading mode In-Reply-To: References: <20170918151857.afnn5n6ntzhyzfnw@psrcode-TP-X230> Message-ID: <20170919145707.5wh3e23zet7jm3bc@psrcode-TP-X230> On Tue, Sep 19, 2017 at 03:53:27PM +0800, liguang li wrote: > Hi, > On Mon, Sep 18, 2017 at 11:18 PM, Jonathan Rajotte-Julien > <[1]jonathan.rajotte-julien at efficios.com> wrote: > > Hi, > On Mon, Sep 18, 2017 at 11:32:07AM +0800, liguang li wrote: > >    Hi, > > > >    Create a session in live-reading mode, run a application which > having very > >    high event throughput, then prints > >    the events with babeltrace. We found the live trace viewer are > viewing > >    events a few seconds ago, and as time > > Could you provide us the version used for babeltrace, lttng-tools and > lttng-ust? > >  Babeltrace: 1.5.1 Update to babeltrace 1.5.3. >  Lttng-tools: 2.8.6 Update to lttng-tools 2.8.8 >  Lttng-ust: 2.8.2 > > >    goes on, the delay will be bigger and bigger. > > A similar issues was observed a couple months ago, which implicated > multiple delayed ack > problems during communication between lttng-relayd and babeltrace. > > The following fixes were merged: > > [1] > [2]https://github.com/lttng/lttng-tools/commit/b6025e9476332b75eb8184345c3eb3e924780088 > [2] > [3]https://github.com/efficios/babeltrace/commit/de417d04317ca3bc30f59685a9d19de670e4b11d > [3] > [4]https://github.com/efficios/babeltrace/commit/4594dbd8f7c2af2446a3e310bee74ba4a2e9d648 > > In the event that you are already using an updated version of babeltrace > and > lttng-tools, it would be pertinent to provide us with a simple > reproducer so we > can assess the issue. The version you are using does not include the mentioned fixes. Please update and redo your experiment. Cheers > >   >  Steps: >  lttng create session --live -U net://* >  lttng enable-channel -s session -u ch1 >  lttng enable-event -s session -c ch1 -u -a >  lttng start >   >  Run a high event throughput application, which is multithreaded > application. >  babeltrace -i lttng-live net://* >   >  After a while, we found the timestamp of the event in the babeltrace is > different with the time in host >  which run the application. And the delay will be bigger and bigger with > time goes. >   > > Cheers > >    I checked the source code, found Babeltrace in live-reading mode > will read > >    the recorded events in the CTF > >    files, and then parse and print it in a single thread. The process > is a > >    little slow, do you have any ideas to > >    improve the process. > >    Thanks, > >    Liguang > > > _______________________________________________ > > lttng-dev mailing list > > [5]lttng-dev at lists.lttng.org > > [6]https://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev > > -- > Jonathan Rajotte-Julien > EfficiOS > > References > > Visible links > 1. mailto:jonathan.rajotte-julien at efficios.com > 2. https://github.com/lttng/lttng-tools/commit/b6025e9476332b75eb8184345c3eb3e924780088 > 3. https://github.com/efficios/babeltrace/commit/de417d04317ca3bc30f59685a9d19de670e4b11d > 4. https://github.com/efficios/babeltrace/commit/4594dbd8f7c2af2446a3e310bee74ba4a2e9d648 > 5. mailto:lttng-dev at lists.lttng.org > 6. https://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev -- Jonathan Rajotte-Julien EfficiOS