[ofa-general] Problem while running ib tests
Ira Weiny
weiny2 at llnl.gov
Wed Sep 23 08:29:52 PDT 2009
OK, my bad. I remember the email thread now. Ido is the maintainer and the git repo changed.
Just to complete this thread the new git tree is:
git://git.openfabrics.org/~shamoya/perftest.git
Sorry,
Ira
On Wed, 23 Sep 2009 00:52:42 -0500
Karun Sharma <karun.sharma at qlogic.com> wrote:
> I am referring to ib_send_bw, ib_read_bw, ib_write_bw etc.
>
> Usage:
> ib_read_bw start a server and wait for connection
> ib_read_bw <host> connect to server at <host>
>
> Options:
> -p, --port=<port> listen on/connect to port <port> (default 18515)
> -d, --ib-dev=<dev> use IB device <dev> (default first device found)
> -i, --ib-port=<port> use port <port> of IB device (default 1)
> -m, --mtu=<mtu> mtu size (256 - 4096. default for hermon is 2048)
> -o, --outs=<num> num of outstanding read/atom(default 4)
> -s, --size=<size> size of message to exchange (default 65536)
> -a, --all Run sizes from 2 till 2^23
> -t, --tx-depth=<dep> size of tx queue (default 100)
> -n, --iters=<iters> number of exchanges (at least 2, default 1000)
> -u, --qp-timeout=<timeout> QP timeout, timeout value is 4 usec * 2 ^(timeout), default 14
> -S, --sl=<sl> SL (default 0)
> -x, --gid-index=<index> test uses GID with GID index taken from command line (for RDMAoE index should be 0)
> -b, --bidirectional measure bidirectional bandwidth (default unidirectional)
> -V, --version display version number
> -e, --events sleep on CQ events (default poll)
> -F, --CPU-freq do not fail even if cpufreq_ondemand module is loaded
>
>
> Regards
> Karun
>
> -----Original Message-----
> From: Ira Weiny [mailto:weiny2 at llnl.gov]
> Sent: Tuesday, September 22, 2009 9:26 PM
> To: Karun Sharma
> Cc: Sneha Mistry; general at lists.openfabrics.org
> Subject: Re: [ofa-general] Problem while running ib tests
>
> On Tue, 22 Sep 2009 04:54:22 -0500
> Karun Sharma <karun.sharma at qlogic.com> wrote:
>
> > Please use "-F" option while running the tests. It will ignore the "Conflicting CPU frequency" errors. You will still see these messages on your screen, but with "-F", you will also see the results.
>
> Which commands are you referring to with the "-F" option?
>
> I just did a pull from git://git.openfabrics.org/~mst/perftest.git and I don't see a -F for the commands there. Have these tools moved? Or are you speaking of other tools?
>
> I also run into this problem and I have resorted to turning off cpuspeed.
>
> Thanks,
> Ira
>
> >
> > Regards
> > Karun
> >
> > -----Original Message-----
> > From: general-bounces at lists.openfabrics.org [mailto:general-bounces at lists.openfabrics.org] On Behalf Of Sneha Mistry
> > Sent: Tuesday, September 22, 2009 2:35 PM
> > To: general at lists.openfabrics.org
> > Subject: [ofa-general] Problem while running ib tests
> >
> > Hi,
> >
> > I have two Dual port HCAa card.Which I have installed in
> > same PC.
> >
> > I am using OpenSuse 10.3 and installed OFED 1.4.
> >
> > If I try to run any IB bandwidth test or latency test it end us with warning
> > "Conflicting CPU frequency values detected: 2394.000000 != 1596.000000".
> >
> > Is it an OFED related problem or Linux kernel problem.
> >
> > HCA are connected back to back and output of ibstat is as given below.
> > ---------------------------------------------------------------------------------------------------------
> > CA 'mthca0'
> > CA type: MT25208 (MT23108 compat mode)
> > Number of ports: 2
> > Firmware version: 4.8.200
> > Hardware version: 20
> > Node GUID: 0x0002c90200283734
> > System image GUID: 0x0002c90200283737
> > Port 1:
> > State: Active
> > Physical state: LinkUp
> > Rate: 20
> > Base lid: 1
> > LMC: 0
> > SM lid: 1
> > Capability mask: 0x02510a6a
> > Port GUID: 0x0002c90200283735
> > Port 2:
> > State: Initializing
> > Physical state: LinkUp
> > Rate: 20
> > Base lid: 0
> > LMC: 0
> > SM lid: 0
> > Capability mask: 0x02510a68
> > Port GUID: 0x0002c90200283736
> > CA 'mthca1'
> > CA type: MT25208 (MT23108 compat mode)
> > Number of ports: 2
> > Firmware version: 4.8.200
> > Hardware version: 20
> > Node GUID: 0x0002c90200283730
> > System image GUID: 0x0002c90200283733
> > Port 1:
> > State: Initializing
> > Physical state: LinkUp
> > Rate: 20
> > Base lid: 0
> > LMC: 0
> > SM lid: 0
> > Capability mask: 0x02510a68
> > Port GUID: 0x0002c90200283731
> > Port 2:
> > State: Active
> > Physical state: LinkUp
> > Rate: 20
> > Base lid: 3
> > LMC: 0
> > SM lid: 1
> > Capability mask: 0x02510a68
> > Port GUID: 0x0002c90200283732
> > --------------------------------------------------------------------------------------------------------------------------------------
> >
> > Even ibibnetdiscover is detecting one hope.
> > So there is nothing wrong if I try to test 2 HCA connected back to back.
> >
> > Please tell me what can be done for running ib tests.
> >
> > Thanks,
> > SGM
> > _______________________________________________
> > general mailing list
> > general at lists.openfabrics.org
> > http://**lists.openfabrics.org/cgi-bin/mailman/listinfo/general
> >
> > To unsubscribe, please visit http://**openib.org/mailman/listinfo/openib-general
> > _______________________________________________
> > general mailing list
> > general at lists.openfabrics.org
> > http://**lists.openfabrics.org/cgi-bin/mailman/listinfo/general
> >
> > To unsubscribe, please visit http://**openib.org/mailman/listinfo/openib-general
> >
>
>
> --
> Ira Weiny
> Math Programmer/Computer Scientist
> Lawrence Livermore National Lab
> 925-423-8008
> weiny2 at llnl.gov
>
--
Ira Weiny
Math Programmer/Computer Scientist
Lawrence Livermore National Lab
925-423-8008
weiny2 at llnl.gov
More information about the general
mailing list