Open MPI logo

Network Locality users Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Network Locality users mailing list

Subject: Re: [netloc-users] Trying Netloc on a small IB cluster
From: Brice Goglin (Brice.Goglin_at_[hidden])
Date: 2013-12-07 03:40:05


Le 07/12/2013 00:44, Raghu a écrit :
> Thanks for the response, Brice. I ran ibnetdiscover manually, and
> here's how the topology file from it looks:
> http://pastebin.com/raw.php?i=LiFfv4hD

Hello,

What I wanted you to check is the "filename" of these outputs. Your
outputs need to be stored like this:

$ find .
.
./ib-subnet-2222:2222:2222:2222.txt
./ibroutes-2222:2222:2222:2222
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-25.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-30.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-27.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-32.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-23.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-21.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-22.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-26.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-29.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-24.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-28.txt
./ibroutes-2222:2222:2222:2222/ibroute-2222:2222:2222:2222-31.txt
./ibroutes-3333:3333:3333:3333

First one is ibnetdiscover output.
Others are ibroute outputs for each switch lid.
2222:2222:2222:2222 is the subnet id.

Running netloc_ib_gather_raw will do all this for you. Assuming you have
all hwloc XML outputs under the "hwloc" directory and want the IB files
under "ib-raw", do netloc_ib_gather_raw --out-dir "ib-raw" --hwloc-dir
"hwloc" --sudo
There are other options, add --help to see them.

Brice

>
> Raghu
>
>
> On Fri, Dec 6, 2013 at 3:44 AM, Brice Goglin <Brice.Goglin_at_[hidden]> wrote:
>> Also
>> How did you gather the ibnetdiscover/ibroute files?
>> Did you run the netloc-gather-ib script? Or did you run
>> ibnetdiscover/ibroute manually?
>> Can you show the contents (filenames only) of the output files?
>> Brice
>>
>>
>>
>> Le 05/12/2013 18:30, Josh Hursey a écrit :
>>
>> Raghu,
>>
>> The probably is likely that the subnet has not been specified. The
>> netloc_reader_ib is not terribly user friendly at the moment. We have some
>> supporting tools that help make it easier to use. I highlighted the steps
>> for another user in the mail linked below:
>> http://www.open-mpi.org/community/lists/netloc-devel/2013/11/0005.php
>>
>> Notice that it does not call netloc_reader_ib explicitly, it is wrapped up
>> as part of the netloc-ib-extract-dats script.
>>
>>
>> You will also need to install Jansson (if you have not already) as that is
>> how netloc is currently representing the data (it may change in the future,
>> but this works well for now). It can be downloaded from:
>> http://www.digip.org/jansson/
>>
>>
>> I am currently working on some FAQs to hopefully help answer these types of
>> questions in the future. In the mean time feel free to email and we can go
>> from there.
>>
>> Thanks,
>> Josh
>>
>>
>>
>> On Thu, Dec 5, 2013 at 3:18 PM, Jeff Squyres (jsquyres) <jsquyres_at_[hidden]>
>> wrote:
>>> Adding netloc-users into the CC; this is the type of feedback we need, and
>>> the type of stuff we want to make google-able for others.
>>>
>>> FYI: Brice did most of the IB work, and he's at a conference this week.
>>> So the reply for this may be a little delayed...
>>>
>>>
>>> On Dec 5, 2013, at 2:56 PM, Raghu <rajachan_at_[hidden]> wrote:
>>>
>>>> Hi Josh, Jeff,
>>>>
>>>> I am trying out netloc (the master branch) on a small IB cluster
>>>> (which I have sudo access to). I got stuff built fine, but when I try
>>>> to generate the .ndat files, I am getting this:
>>>>
>>>> Output Directory : /home/rajachan/netloc/install/bin/output/
>>>> Subnet : unknown
>>>> ibnetdiscover File : /home/rajachan/netloc/install/bin/ibnetdata
>>>> ibroutes Directory : None Specified
>>>> Status: Querying the ibnetdiscover data for subnet unknown...
>>>> Error: Invalid network type provided
>>>> Error: Failed to create a new data file
>>>>
>>>> Here's how I am running the reader : ./netloc_reader_ib -o
>>>> /home/rajachan/netloc/install/bin/output/ -f
>>>> /home/rajachan/netloc/install/bin/ibnetdata
>>>>
>>>> Do you guys see any glaring config mistake from my end?
>>>>
>>>> Raghu
>>>
>>> --
>>> Jeff Squyres
>>> jsquyres_at_[hidden]
>>> For corporate legal information go to:
>>> http://www.cisco.com/web/about/doing_business/legal/cri/
>>>
>>> _______________________________________________
>>> netloc-users mailing list
>>> netloc-users_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/netloc-users
>>
>>
>>
>> --
>> Joshua Hursey
>> Assistant Professor of Computer Science
>> University of Wisconsin-La Crosse
>> http://cs.uwlax.edu/~jjhursey
>>
>>
>> _______________________________________________
>> netloc-users mailing list
>> netloc-users_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/netloc-users
>>
>>
>>
>> _______________________________________________
>> netloc-users mailing list
>> netloc-users_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/netloc-users
>>
> _______________________________________________
> netloc-users mailing list
> netloc-users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/netloc-users