From mboxrd@z Thu Jan 1 00:00:00 1970 References: <1392993075.52404.YahooMailNeo@web140605.mail.bf1.yahoo.com> <530766CD.3060707@xenomai.org> <1393198348.29895.YahooMailNeo@web140605.mail.bf1.yahoo.com> <530A862C.1060805@xenomai.org> <1393204287.98060.YahooMailNeo@web140606.mail.bf1.yahoo.com> <530B374B.1080507@xenomai.org> <1393298793.43978.YahooMailNeo@web140605.mail.bf1.yahoo.com> <530C6AC6.6030200@xenomai.org> <1393335358.33826.YahooMailNeo@web140603.mail.bf1.yahoo.com> <530C9D87.60805@xenomai.org> <1393871535.96739.YahooMailNeo@web140604.mail.bf1.yahoo.com> <5314CDDA.4030308@xenomai.org> <1393904852.42577.YahooMailNeo@web140603.mail.bf1.yahoo.com> <5315ED1F.60602@xenomai.org> Message-ID: <1394499114.45142.YahooMailNeo@web140602.mail.bf1.yahoo.com> Date: Mon, 10 Mar 2014 17:51:54 -0700 (PDT) From: Bruno Tunes de Mello In-Reply-To: <5315ED1F.60602@xenomai.org> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Subject: Re: [Xenomai] User Space Problems Reply-To: Bruno Tunes de Mello List-Id: Discussions about the Xenomai project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Gilles Chanteperdrix Cc: "xenomai@xenomai.org" Hi Gilles,=0A=0AI understand. I have a beaglebone too and as soon as possib= le I will make some test on it.=0A=0AThank you for all help and attention,= =0ABruno=0A=0A=0A=0A=0A=0AEm Ter=E7a-feira, 4 de Mar=E7o de 2014 12:13, Gil= les Chanteperdrix escreveu:=0A =0AOn 03/= 04/2014 04:47 AM, Bruno Tunes de Mello wrote:=0A> Hi Gilles,=0A> =0A> You a= re right, in the first test, I executed both latency and xeno-test commands= . Sorry.=0A> The others test I executed only latency command.=0A> =0A> I tr= ied to enable the discard service on /etc/inetd.conf, I don't know if I did= it right, but in /etc/services file I found 'discard 9/tcp sink null' and = 'discard 9/udp sink null'.=0A> Then I used the command you said:=0A> xeno-t= est -l "dohell -s 192.168.0.5 -m /media/linaro/PENDRIVE -l /opt/ltp" -c 0 -= p 100 -g histo=0A> =0A> I tested a few times and the better result is: http= ://pt-br.tinypic.com/r/206mmvn/8=0A> This result is not so good like that y= ou showed.=0A> =0A> My doubt is if this result is satisfactory (the platfor= m is ready for develop applications) or do you think that I need to do some= correction?=0A=0A70us is a bit high, but on the other hand:=0A- the mx6q i= s a quad-core, whereas the omap4 is a dual core, the latency=0Aincreases wi= th the number of cores;=0A- the tests I make on omap4 do not use much of th= e processor=0Aperipherals, such as the graphic co-processor, so, if you use= the=0Agraphic co-processor, you may observe an increase in latencies as we= ll.=0A=0AFinally, whether this is satisfactory depends on your application.= =0A=0AThe only way to improve latency is to enable the I-pipe tracer, and t= ry=0Aand understand where the maximum latency come from, but this is time= =0Aconsuming.=0A=0AAlso, some settings are known to result in an improvemen= t in latencies:=0A- turn off CONFIG_PREEMPT (i.e. enable CONFIG_PREEMPT_NON= E), this looks=0Acontradictory, as the menu entry says "low latency", but i= t is talking=0Aabout Linux latencies, not Xenomai's=0A- build kernel and us= er-space in thumb2=0A- disable Xenomai unlocked context switch=0A=0ABut do = not expect these settings to reduce the latency by more than say 5us.=0A=0A= =0A=0A-- =0A=A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0= =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 Gilles.