From mboxrd@z Thu Jan 1 00:00:00 1970 From: Barry Mavin Subject: Re: [ofa-general] Re: [PATCH v2] infiniband-diags/scripts: Add 'ibcheckspeed' and 'ibcheckportspeed' to scripts Date: Fri, 11 Sep 2009 11:08:15 +0530 Message-ID: References: <829ded920909102102o49f037cbhc53a849f1fcfdaa4@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <829ded920909102102o49f037cbhc53a849f1fcfdaa4@mail.gmail.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: general-bounces@lists.openfabrics.org Errors-To: general-bounces@lists.openfabrics.org To: OFED mailing list Cc: OFED mailing list List-Id: linux-rdma@vger.kernel.org I use mellanox connectx cards and switches in a cluster. When I try and use ibtracert I get this output. # ibtracert 10.10.10.1 10.10.10.3 ibwarn: [6998] _do_madrpc: recv failed: Connection timed out ibwarn: [6998] mad_rpc: _do_madrpc failed; dport (Lid 10) ibwarn: [6998] find_route: can't reach to/from ports ibtracert: iberror: failed: can't find a route to the src port Does anyone have any idea why this would be happening? --- Regards Barry Mavin Recital Corporation > From: Keshetti Mahesh > Date: Fri, 11 Sep 2009 09:32:39 +0530 > To: Ira Weiny > Cc: OFED mailing list , OFED mailing list > > Subject: Re: [ofa-general] Re: [PATCH v2] infiniband-diags/scripts: Add > 'ibcheckspeed' and 'ibcheckportspeed' to scripts >=20 > My badness. I have not used 'iblinkinfo' before. > So, I guess there is no need for the above script. Apart from that, I fee= l > there should be a program/script which will first scan the fabric to find= the > maximum common supported width/speed and then report the warning messages > of the links/ports which are configured with active width/speed less > than the found > value. Is there any tool already exists which does the same ? >=20 > - > Keshetti Mahesh >=20 > On Thu, Sep 10, 2009 at 9:32 PM, Ira Weiny wrote: >> Also, iblinkinfo will report links which it finds capable of either fast= er or >> wider operation. =A0iblinkinfo checks both ends of the link as Hal mention= s. >> =A0It reports this with output like. >>=20 >> Switch 0x0005ad0000092106 Cisco Switch SFS7000D: >> ... >> =A0 =A0 =A0 =A0 =A0 7 =A0 =A08[ =A0] =3D=3D( 4X 2.5 Gbps Active/ =A0LinkUp)=3D=3D> =A0 =A0 =A0 8 =A0 12[ =A0= ] >> "MT47396 Infiniscale-III Mellanox Technologies" ( Could be 5.0 Gbps) >> ... >>=20 >> Also the portstatus console command in OpenSM will report links which ar= e >> running at "reduced speed or width". =A0Although this does not check the r= emote >> port. >>=20 >> OpenSM $ help portstatus >> portstatus [ca|switch|router] >> summarize port status >> =A0 [ca|switch|router] -- limit the results to the node type specified >> OpenSM $ portstatus >> "ALL" port status: >> =A0 115 port(s) scanned on 9 nodes in 26 us >> =A0 85 down >> =A0 30 active >> =A0 32 at 4X >> =A0 22 at 2.5 Gbps >> =A0 8 at 5.0 Gbps >> =A0 2 at 10.0 Gbps >>=20 >> Possible issues: >> =A0 2 disabled >> =A0 =A0 =A00x0008f10400411b18 5 (ISR9024D Voltaire) >> =A0 =A0 =A00x0005ad0000092106 13 (Cisco Switch SFS7000D) >> =A0 6 with reduced speed >> =A0 =A0 =A00x0008f10500200220 33 (Voltaire 4036 - 36 QDR ports switch) >> =A0 =A0 =A00x0008f10500200220 19 (Voltaire 4036 - 36 QDR ports switch) >> =A0 =A0 =A00x0005ad0000092106 21 (Cisco Switch SFS7000D) >> =A0 =A0 =A00x0005ad0000092106 20 (Cisco Switch SFS7000D) >> =A0 =A0 =A00x0005ad0000092106 9 (Cisco Switch SFS7000D) >> =A0 =A0 =A00x0005ad0000092106 8 (Cisco Switch SFS7000D) >>=20 >>=20 >> Ira >>=20 >> On Thu, 10 Sep 2009 09:23:35 -0400 >> Hal Rosenstock wrote: >>=20 >>> On Thu, Sep 10, 2009 at 9:02 AM, Keshetti Mahesh >>> wrote: >>>=20 >>>> Added 'ibcheckspeed' and 'ibcheckportspeed': Similar to >>>> 'ibcheckwidth/ibcheckportwidth' in functionality and implementation. >>>> Reports error/warning messages if the LinkSpeedActive is configured as >>>> 2.5 Gbps when the LinkSpeedSupported is more than 2.5 Gbps. >>>>=20 >>>=20 >>> ibportstate checks for more than this in terms of speed (and width) >>> anomalies. >>>=20 >>> Would it be better for these scripts to use that tool now ? Alternative= ly, >>> the additional speed/width anomaly checks could be implemented in these >>> scripts but it does involve checking the peer port so there's a little = more >>> to it. >>>=20 >>> -- Hal >>>=20 >>>=20 >>>>=20 >>>> Signed-off-by: Keshetti Mahesh < keshetti.mahesh@gmail.com> >>>> --- >>>> =A0infiniband-diags/scripts/ibcheckportspeed.in | =A0146 >>>> ++++++++++++++++++++++++++ >>>> =A0infiniband-diags/scripts/ibcheckportwidth.in | =A0 =A02 +- >>>> =A0infiniband-diags/scripts/ibcheckspeed.in =A0 =A0 | =A0135 >>>> ++++++++++++++++++++++++ >>>> =A03 files changed, 282 insertions(+), 1 deletions(-) >>>> =A0create mode 100644 infiniband-diags/scripts/ibcheckportspeed.in >>>> =A0create mode 100644 infiniband-diags/scripts/ibcheckspeed.in >>>>=20 >>> >>>=20 >>=20 >>=20 >> -- >> Ira Weiny >> Math Programmer/Computer Scientist >> Lawrence Livermore National Lab >> 925-423-8008 >> weiny2@llnl.gov >>=20 > _______________________________________________ > general mailing list > general@lists.openfabrics.org > http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general >=20 > To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-ge= neral