Features Descriptions

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Features Descriptions

Richard Riggs
All,

Looking to get a better description of the new features added (i.e. "Write
IO Pattern") and what functionality they provide.

We are testing our block device driver on Linux, and need to understand how
these features may change our results, and why.  

Thanks!
Rick Riggs


------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and
threat landscape has changed and how IT managers can respond. Discussions
will include endpoint security, mobile security and the latest in malware
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Iometer-devel mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/iometer-devel
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Features Descriptions

Vedran Degoricija
Hi Rick,
 
The objective of the feature was to provide options for the write pattern randomness while maintaining backwards compatibility.  A pop-up window describes each option the first time it is selected. In general, if you want to maintain compatibility with the results of the prior editions of Iometer, choose the "pseudo random" option. If you want more randomized data, choose "full random". Even though "full random" could be better, the trade off was made between CPU overhead needed to generate the data on the fly vs the quality of the randomized data in favor of less CPU overhead.
 
Regards,
Ved

From: Richard Riggs <[hidden email]>
To: [hidden email]
Sent: Wednesday, July 18, 2012 9:55 AM
Subject: [Iometer-devel] Features Descriptions

All,

Looking to get a better description of the new features added (i.e. "Write
IO Pattern") and what functionality they provide.

We are testing our block device driver on Linux, and need to understand how
these features may change our results, and why. 

Thanks!
Rick Riggs


------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and
threat landscape has changed and how IT managers can respond. Discussions
will include endpoint security, mobile security and the latest in malware
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Iometer-devel mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/iometer-devel



------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and
threat landscape has changed and how IT managers can respond. Discussions
will include endpoint security, mobile security and the latest in malware
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Iometer-devel mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/iometer-devel
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Features Descriptions

Daniel Scheibli-2

Hi Rick,
Hi Ved,

regarding the comparison between Iometer versions dimension,
I would like to add a snippet from a reply I gave in LinkedIn
group:

-----BEGIN-----
If you are interested in the details, you can track the evolution of
the data pattern generation in the IOGrunt.cpp file. The relevant
methods are Set_Access (initialization) and Do_IOs (I/O loop).

In 2004.07.30 the behavior was to allocate a buffer and to use
(without further initialization) that one for each write. On Linux for
instance the allocation is done with malloc(), so there is no
guarantee by the language on how the memory looks like. Still the C
library or the operating system might zero out the space which is why
you will likely see all zeros.

In 2006.07.27 the behavior was changed to initializing the allocated
buffer with pseudo-random data from the Iometer internal randomizer.
This buffer was then used for each write.

In 2008.06.22 (RC1 and RC2) the behavior again changed. Here the
buffer gets repopulated before each write with a uniform pattern. This
means that the C library rand() function is used to determine the
value of a single byte which then gets repeated <block_size> number of
times (e.g. an I/O writing all A's). So the pattern changes, but each
pattern compresses well.

In 1.1.0 (RC1 and soon GA) the behavior can finally be configured in
the Disk Targets tab of the Iometer GUI. Selecting one of the three
options, you will get a pop-up outlining the details for the
particular selection.
-----END-----

If you are interested in the full discussion, then you
can have a look at [1].

Cheers,
Daniel


[1]
http://www.linkedin.com/groupItem?view=&gid=2976553&type=member&item=98229462&qid=1a8cb1bd-1d69-4359-9fc0-42c5b9feccb8&trk=group_most_popular-0-b-ttl&goback=.gmp_2976553



> Hi Rick,
>  
> The objective of the feature was to provide options for the write
> pattern randomness while maintaining backwards compatibility.  A
> pop-up window describes each option the first time it is selected. In
> general, if you want to maintain compatibility with the results of the
> prior editions of Iometer, choose the "pseudo random" option. If you
> want more randomized data, choose "full random". Even though "full
> random" could be better, the trade off was made between CPU overhead
> needed to generate the data on the fly vs the quality of the
> randomized data in favor of less CPU overhead.
>  
> Regards,
> Ved
>
>
>
>>________________________________
>>From: Richard Riggs <[hidden email]>
>>To: [hidden email]
>>Sent: Wednesday, July 18, 2012 9:55 AM
>>Subject: [Iometer-devel] Features Descriptions
>>
>>All,
>>
>>Looking to get a better description of the new features added (i.e.
>> "Write
>>IO Pattern") and what functionality they provide.
>>
>>We are testing our block device driver on Linux, and need to
>> understand how
>>these features may change our results, and why. 
>>
>>Thanks!
>>Rick Riggs
>>
>>
>>------------------------------------------------------------------------------
>>Live Security Virtual Conference
>>Exclusive live event will cover all the ways today's security and
>>threat landscape has changed and how IT managers can respond.
>> Discussions
>>will include endpoint security, mobile security and the latest in
>> malware
>>threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
>>_______________________________________________
>>Iometer-devel mailing list
>>[hidden email]
>>https://lists.sourceforge.net/lists/listinfo/iometer-devel
>>
>>
>>------------------------------------------------------------------------------
> Live Security Virtual Conference
> Exclusive live event will cover all the ways today's security and
> threat landscape has changed and how IT managers can respond.
> Discussions
> will include endpoint security, mobile security and the latest in
> malware
> threats.
> http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/_______________________________________________
> Iometer-devel mailing list
> [hidden email]
> https://lists.sourceforge.net/lists/listinfo/iometer-devel
>



------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and
threat landscape has changed and how IT managers can respond. Discussions
will include endpoint security, mobile security and the latest in malware
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Iometer-devel mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/iometer-devel
Loading...