Search Mailing List Archives


Limit search to: Subject & Body Subject Author
Sort by: Reverse Sort
Limit to: All This Week Last Week This Month Last Month
Select Date Range     through    

[mininet-discuss] mininet

Bob Lantz rlantz at cs.stanford.edu
Sat Mar 14 16:46:10 PDT 2015


I’ve tried to fix this in master - if you can possibly confirm that it works for you in master and in 2.2.0 that would be great:

sudo mn —host cfs,cpu=.1

Thanks!

> On Mar 14, 2015, at 1:32 PM, Bob Lantz <rlantz at cs.stanford.edu> wrote:
> 
> 1. please don’t drop the list!!!  :(
> 
> 2. Hmm, —host cfs,cpu=.1 is the correct format and works fine in 2.2.0, but it seems to be broken in master - I will look into it.
> 
> 3. —host rt,cpu=.1 also works in 2.2.0 but requires a kernel with RT_GROUP_SCHED enabled.
> 
> 
>> On Mar 13, 2015, at 2:03 AM, Diarmuid O'Briain <diarmuid.obriain at gmail.com <mailto:diarmuid.obriain at gmail.com>> wrote:
>> 
>> Bob,
>> 
>> When it comes to --host
>> 
>> - host 
>>   - cfs - Completely Fair Scheduler (CFS)
>>   - proc 
>>   - rt, - Real Time (RT)
>>     - cpu=<positive fraction, or -1> - CPU bandwidth limit 
>> 
>> 
>> $ sudo mn --topo tree,depth=1,fanout=3 --switch ovsk --controller ref --mac --host rt,cpu=0.25
>> 
>> This doesnt work, what is the format that is used on the command for --host ?
>> 
>> regards,
>> 
>> Diarmuid
>> 
>> 
>> On 11 March 2015 at 23:06, Bob Lantz <rlantz at cs.stanford.edu <mailto:rlantz at cs.stanford.edu>> wrote:
>> Most of the ones you mentioned don’t actually have options, but options are usually documented in the API for the class:
>> 
>> For example, here are the OVSSwitch options:
>> 
>> http://mininet.org/api/classmininet_1_1node_1_1OVSSwitch.html#ab5db2ef0d48302217833ce1538270310 <http://mininet.org/api/classmininet_1_1node_1_1OVSSwitch.html#ab5db2ef0d48302217833ce1538270310>
>> 
>> failMode	controller loss behavior (secure|open) 
>> datapath	userspace or kernel mode (kernel|user) 
>> inband	use in-band control (False) 
>> protocols	use specific OpenFlow version(s) (e.g. OpenFlow13) Unspecified (or old OVS version) uses OVS default 
>> reconnectms	max reconnect timeout in ms (0/None for default) 
>> stp	enable STP (False, requires failMode=standalone)
>> 
>> Note that you should use 0 for False if you wish to explicitly use False, e.g.: —switch lxbr,stp=0
>> 
>> Parameters for --host cfs and --link tc are documented here:
>> 
>> Setting Performance Parameters <https://github.com/mininet/mininet/wiki/Introduction-to-Mininet#setting>
>> 
>> Everyone is encouraged to add to the wiki documentation and/or to submit pull requests with enhancements to mn —help (which generates the mn man page) and/or additional API documentation (i.e. python docstrings through doxypy, and/or additional chapters for the doxygen docs.)
>> 
>> -Bob
>> 
>>> On Mar 11, 2015, at 12:49 PM, Diarmuid O'Briain <diarmuid.obriain at gmail.com <mailto:diarmuid.obriain at gmail.com>> wrote:
>>> 
>>> Hi,
>>> 
>>> Where do I find documentation describing mininet options like: 
>>> 
>>> ivs|lxbr|ovs|ovsbr|ovsk|ovsl|user
>>> 
>>> and the available param and their range of values ?
>>> 
>>> regards,
>>> 
>>> Diarmuid O'Briain
>>> 
>>> 
>>> 
>>> _______________________________________________
>>> mininet-discuss mailing list
>>> mininet-discuss at lists.stanford.edu <mailto:mininet-discuss at lists.stanford.edu>
>>> https://mailman.stanford.edu/mailman/listinfo/mininet-discuss <https://mailman.stanford.edu/mailman/listinfo/mininet-discuss>
>> 
>> 
>> 
>> 
>> -- 
>> Is mise le meas,
>> 
>> Diarmuid
> 
> _______________________________________________
> mininet-discuss mailing list
> mininet-discuss at lists.stanford.edu
> https://mailman.stanford.edu/mailman/listinfo/mininet-discuss

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.stanford.edu/pipermail/mininet-discuss/attachments/20150314/449d111e/attachment-0001.html>


More information about the mininet-discuss mailing list