Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
  • Feb 24 06:51
    codecov[bot] commented #223
  • Feb 24 06:51
    codecov[bot] commented #223
  • Feb 24 06:51
    codecov[bot] commented #222
  • Feb 24 06:50
    Coverage (#undefined) +undefined%
  • Feb 24 06:50
    Coverage (#undefined) +undefined%
  • Feb 24 06:50
    Coverage (#undefined) +undefined%
  • Feb 24 06:50
    Coverage (#undefined) +undefined%
  • Feb 24 06:48
    dependabot-preview[bot] labeled #223
  • Feb 24 06:48
    dependabot-preview[bot] opened #223
  • Feb 24 06:48

    dependabot-preview[bot] on maven

    Bump mockito-core from 3.2.4 to… (compare)

  • Feb 24 06:48
    dependabot-preview[bot] labeled #222
  • Feb 24 06:48
    dependabot-preview[bot] opened #222
  • Feb 24 06:48

    dependabot-preview[bot] on maven

    Bump javaparser-core from 3.15.… (compare)

  • Feb 10 07:30
    Coverage (#undefined) +undefined%
  • Feb 10 07:26

    dependabot-preview[bot] on maven

    (compare)

  • Feb 10 07:26
    Coverage (#undefined) +undefined%
  • Feb 10 07:26

    fhermeni on master

    Bump reflections from 0.9.11 to… Merge pull request #216 from bt… (compare)

  • Feb 10 07:26
    fhermeni closed #216
  • Feb 10 07:26

    dependabot-preview[bot] on maven

    (compare)

  • Feb 10 07:26
    fhermeni milestoned #216
Fabien Hermenier
@fhermeni
ok :D
Fabien Hermenier
@fhermeni
@apatrida Do you have an interest in BtrPlace (curiosity, used for testing or in production, etc.) ?
Jayson Minard
@apatrida
@fhermeni not as-is, but the general concepts. I’m building a planner that manages the internals of a distributed system which has nodes -> sets -> shards and need to distribute and balance the shards for safety and performance. topology of network, and info such as disk, CPU and stats such as reads/writes are all important. So are migration from one plan to another. so btrplace but focused on this one domain.
currently, looking to see how “initial placement” values are set, because I’m also learning Choco not sure how this is done. If i set a var it can’t be set later? so I shouldn’t set it but I should solve for the lowest differing plan from the original plan instead. which basically favors things staying close to original position?
Jayson Minard
@apatrida
I just asked generally in #choco-solver
Fabien Hermenier
@fhermeni
Indeed, your point is more related to choco and CSP principles
Fabien Hermenier
@fhermeni
Screen Shot 2017-03-18 at 00.41.37.png
Well, that's explained while the live demo was out
It's back now
Fabien Hermenier
@fhermeni
Oh, and version 1.6.1 released last week. Less bugs, faster for resource-allocation oriented problems with tons of VMs.
Fabien Hermenier
@fhermeni
BtrPlace 1.8.0 released. Better at solving tight placements
Fabien Hermenier
@fhermeni
BtrPlace 1.9.0 is released. Fix a few bugs using SafePlace as testing framework !
ad_rien_
@alebre
Hi
We are trying to porte btrPlace to the SCHIAAS simulator (i.e. we are porting the whole VMPlaceS framework to the SCHIAAS actually)
Starting with BtrPLace
The main idea of SCHIAAS is to simulate OpenSTack like platforms.
Our goal is to enable researchers to evaluate advanced placement strategies within this framework
The first issue we met is that shareResource is expecting int whereas we using double. Actually, we can make some tricks to be able to give int but we are wondering whether there is a strong constraint for having int vs double
so any hint/advice is more than welcome
Thanks
Fabien Hermenier
@fhermeni
@alebre the point might also be why using doubles ? It requires the implementation to support float numbers and rounding issues which no one like. We are using integers but we do not force any unit which is convenient when you want to scale numbers (up to the overflow of course). What kind of resource would you like to express using double ?
ad_rien_
@alebre
FLOPS
Floatint operatin per second
Fabien Hermenier
@fhermeni
@alebre scale then round them to an amount that sufficient to differenciate 2 VMs
Fabien Hermenier
@fhermeni
BtrPlace 1.9.1 is released to fix a (tiny) performance regression
rajni-cs
@rajni-cs
@fhermeni I have not changed '-Dgpg.skip=true' argument and still facing the installation in BtrPlace scheduler
Fabien Hermenier
@fhermeni
mvn install -Dgpg.skip=true worked on my machine (and not working without the flag).
Patrick Meyer
@HerrSpace
Hey there! I'm currently reading up on btrplace and btrplace.org is broken for a few days now. The domain doesn't resolve and the whois states the domain was last updated 2018-10-04T06:10:07Z
Patrick Meyer
@HerrSpace
@fhermeni
Fabien Hermenier
@fhermeni
It's back. I forgot to renew like a noob. Thanks for the notification
Patrick Meyer
@HerrSpace
Let's say I have a resource and I'm currently over provisioning, but I want btrplace to find a placing where I no longer am over provisioning. Using ShareableResource I get something like "Usage of virtual resource cpu on node node#55851 (32) exceeds its capacity (24.0)" when modelling my current system. How would I go about this problem using btrplace?
Patrick Meyer
@HerrSpace
I probably can't model it with ShareableResource but need to use Constraints, right?
Patrick Meyer
@HerrSpace
@fhermeni Are you at 35C3 or Fosdem by any chance? :)
And the SubstitutedVM Event has an unresolved merge conflict in the example ;)
Fabien Hermenier
@fhermeni
@HerrSpace I am not attending Fosdem. What's / who's in 5C3 ?
Fabien Hermenier
@fhermeni
@HerrSpace I'll fix the doc. About your original request wrt. modelling an over-provisionning resource: ShareableResource exhibit how the resources are shared inside a node, so this indicates the node capacity is too low
here, the notion of over-provisioning does not hold, you just state what you observe. Typically, you cannot have a node loaded at 110%
in terms of CPUs for example
Patrick Meyer
@HerrSpace
35c3 is another congress I'm at this month. I just thought we could meet up would you be there https://en.wikipedia.org/wiki/Chaos_Communication_Congress
Fabien Hermenier
@fhermeni
No, there is no plan for such trips
Patrick Meyer
@HerrSpace
Okidoki. Thanks for taking care of the docs.
Fabien Hermenier
@fhermeni
@HerrSpace no pb. I don't guarantee it is perfect but it exists
Patrick Meyer
@HerrSpace
Is there some way to debug which constraint solving failed on? I'm now looping through lots and lots of fencing constraints and it's taking forever to find the broken ones.
I already set the scheduler verbosity to three but no luck.
I'm close to implement some kind of binary search ^^
Fabien Hermenier
@fhermeni
@HerrSpace You mean inferring for an unsolvable problem the constraint(s) that led to the situation ?
I did that in the past inside SafePlace but eventually I removed the code.
What I did was delta debugging. Then it is a matter of granularity. For example, delta debugging affinity constraints is fine