From mboxrd@z Thu Jan 1 00:00:00 1970 Date: Thu, 27 Jan 2011 09:58:58 +0100 (CET) From: Michel Rinaldi Message-ID: <29228600.131296118733562.JavaMail.SYSTEM@PC-MRINALDI> In-Reply-To: <11269195.111296118370328.JavaMail.SYSTEM@PC-MRINALDI> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_Part_10_26484724.1296118733562" Subject: Re: [Xenomai-help] Problems with rt_task_create and rt_task_join List-Id: Help regarding installation and common use of Xenomai List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: gilles.chanteperdrix@xenomai.org Cc: xenomai@xenomai.org ------=_Part_10_26484724.1296118733562 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Posted by Gilles Chanteperdrix on January 25, 2011 - 14:27: >Well, no. dd if=/dev/zero of=/dev/null is far from being a proper load. >What you should do is at least to create some disk and network activity, >continuously. And the ideal, is to run the LTP test in parallel. If you >can not, then at least run hackbench in a loop. All this during several >hours. Ok. I run LTP test and latency test in parallel for about 15 hours continuously. I have this result at the end: RTD| 6.182| 7.627| 47.662| 0| 0| 15:04:32/15:04:32 I also run hackbench in a loop (with 100 groups) for about 14 hours and I obtain: RTD| 6.100| 8.341| 21.727| 0| 0| 13:39:24/13:39:24 >We add ids to the smi.c table when people send patches, and report that >the workaround... works. Anyway, if you suspect that the ICH workaround >does not work with SCH chipsets, you should have a look at the SCH >chipsets datasheet, to check whether the method for disabling SMIs is >the same. I'll try to check this and I'll inform you if I succeed in disabling SMIs on SCH. >In facts, same test (only without file transfer) under another system with >1GHz Intel Atom on a SCH (Poulsbo) chipset (not supported by Xenomai to >disable SMIs) reports these results: > >RTD| 11.353| 13.808| 31.264| 3| 0| 2.934| 231.539 >What I do not understand, in on which system you get the issue with your >test application. If you want to know if the system on which you run the >test has an isssue, then surely you should test this system, not another... Yes, I run test on this Atom system only to have results from another machine to compare with results from my develop host. I'm testing only my develop host, for ease I synthetize again its features: Intel Celeron M 600MHz 512MB ram ICH4 chipset (Xenomai's SMI workaround applied) Ubuntu 10.04 with compiled kernel 2.6.35.7 Xenomai 2.5.5.2 Adeos patch 2.7-04 Thank you! Mauro ------=_Part_10_26484724.1296118733562 Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: quoted-printable <= div style=3D'font-family: Times New Roman; font-size: 12pt; color: #000000'= >Posted by Gilles Chanteperdrix on January 25, 2011 - 14:27:

>Wel= l, no. dd if=3D/dev/zero of=3D/dev/null is far from being a proper load.>What you should do is at least to create some disk and network activit= y,
>continuously. And the ideal, is to run the LTP test in parallel. = If you
>can not, then at least run hackbench in a loop. All this duri= ng several
>hours.

Ok. I run LTP test and latency test in para= llel for about 15 hours continuously.
I have this result at the end:
=
RTD| 6.182| 7.627| 47.662| 0| 0| 15:04:32/15:04:32

I also run ha= ckbench in a loop (with 100 groups) for about 14 hours and I obtain:
RTD| 6.100| 8.341| 21.727| 0| 0| 13:39:24/13:39:24

>We add ids t= o the smi.c table when people send patches, and report that
>the work= around... works. Anyway, if you suspect that the ICH workaround
>does= not work with SCH chipsets, you should have a look at the SCH
>chips= ets datasheet, to check whether the method for disabling SMIs is
>the= same.

I'll try to check this and I'll inform you if I succeed in di= sabling SMIs on SCH.

    >In facts, same test (onl= y without file transfer) under another system with
    &= gt;1GHz Intel Atom on a SCH (Poulsbo) chipset (not supported by Xenomai to =
    >disable SMIs) reports these results:
 &n= bsp;  >
    >RTD| 11.353| 13.808| 31.264| 3| 0= | 2.934| 231.539

>What I do not understand, in on which system y= ou get the issue with your
>test application. If you want to know if = the system on which you run the
>test has an isssue, then surely you = should test this system, not another...

Yes, I run test on this Atom= system only to have results from another machine to compare with results f= rom my develop host.
I'm testing only my develop host, for ease I synthe= tize again its features:
Intel Celeron M 600MHz
512MB ram
ICH4 chi= pset (Xenomai's SMI workaround applied)
Ubuntu 10.04 with compiled kerne= l 2.6.35.7
Xenomai 2.5.5.2
Adeos patch 2.7-04

Thank you!
Ma= uro

------=_Part_10_26484724.1296118733562--