1
play

1 (Cloud) Colocation Games Colocation Games: Questions IaaS cloud - PowerPoint PPT Presentation

Nov 08, 2022 •394 likes •481 views

Do you trust that the price is right? I n Cloud ( Markets) W e Trust Towards a Trustworthy Marketplace for Cloud Resources Holistic system (social) view is pass Azer Bestavros Tenants make resource acquisition/ control

  1. Do you trust that “the price is right”? “I n Cloud ( Markets) W e Trust” Towards a Trustworthy Marketplace for Cloud Resources  Holistic system (social) view is passé Azer Bestavros  Tenants make resource acquisition/ control Computer Science Department decisions; no incentive to optimize for, or be Boston University fair/ friendly to others – it’s a marketplace I n collaboration with  Infrastructure owners have no incentive to Vatche Ishakian (BU), Jorge Londono (BU  U Pontificia Bolivariana), minimize cost for tenants; they only react to Ray Sweha (BU), and Shanghua Teng (BU  USC) marketplace pressure  Economic utility as a dimension of trust  Challenge is to design the mechanisms that engender trust in the cloud marketplace http:/ / w w w .cs.bu.edu/ groups/ w ing DIMACS Workshop on Systems and Networking Advances in Cloud Computing December 9, 2011 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 2 Current IaaS Practice: Fixed Pricing Marketplace Implications? 0 8 :0 0 am / Am azon  $ 3 0 9 :0 0 am / Am azon  $ 3 Tasks “Pricing is per instance-hour Hosts consumed for each instance type. 1 0 :0 0 am / Am azon  $ 2 1 1 :0 0 am / Am azon  $ 2 Partial instance-hours consumed are billed as full hours.” December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 3 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 4 1

  2. (Cloud) Colocation Games Colocation Games: Questions  IaaS cloud providers offer fixed-sized  Does it reach equilibrium? instances for a fixed price  If so, how fast?  Provider’s profit = number of instances  If so, at what price (of anarchy)? sold; no incentive to colocate customers  How about multi-resource jobs/ hosts?  Virtualization enables colocation to  How about multi-job tasks? reduce costs without QoS compromises  How about job/ host dependencies?  Customers’ selfishness reduces the  How could it be implemented? colocation process to a strategic game  How would it perform in practice?  … December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 5 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 6 Colocation Game: Model The General Colocation Game (GCG)  A hosting graph G = ( V,E )  GCG is a pure strategies game:  V & E labeled by capacity vector R and fixed price P Each workload is able to make a (better response) “move” from a valid mapping M into  Workloads as task graphs T i = ( V i ,E i ) another M ′ so as to minimize its own cost  V i & E i labeled by a utilization vector W  Valid mappings  Example applications:  V i  V & E i  E : Σ W ≤ R ; supply meets demand  Overlay reservation, e.g., on PlanetLab  Shapley Cost function  CDN colocation, e.g., on CloudFront  Cost P of a resource is split among workloads mapped to it in proportion to use December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 7 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 8 2

  3. General Colocation Game: Properties Colocation Games: Variants  GCG may not converge to  Process Colocation Game (PCG): a Nash equilibrium Each workload consists of a single vertex representing an independent process that needs to be assigned to a single host with only one  Theorem: capacitated resource Determining whether a GCG has a  Multidimensional PCG (MPCG): Nash Equilibrium is NP-Complete (by reduction to 3-SAT problem) Same as PCG but with multi capacitated resources  Need more structure to  Example applications: ensure convergence  VM colocation, e.g., on a Eucalyptus cluster  Streaming server colocation December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 9 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 10 Colocation Games: Variants Colocation Games: Theoretical results  Parallel PCG (PPCG):  PCG converges to a Nash Equilibrium under better-response dynamics Task graph consists of a set of disconnected vertices (independent processes), each with  PCG converges to a Nash Equilibrium in O ( n 2 ) multidimensional resource utilization needs better-response moves, where n = | V |  Price of Anarchy for PCG is 3/ 2 when hosting  Uniform PPCG: graph is homogeneous and 2 otherwise Same as PPCG but with identical resource  MPCG converges to a Nash equilibrium under utilization for all processes better-response dynamics  Uniform PPCG converges to a Nash equilibrium  Example applications: under better-response dynamics  Map-Reduce paradigm  …  MPI scientific computing paradigm December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 11 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 12 3

  4. C LOUD C OMMONS : Architecture C LOUD C OMMONS : Benefit to Customers Planet-Lab trace-driven experiments (Overheads/ costs of all XCS services included) At most 7% of customers overpay less than 1% 50% of customers save more than 68% December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 13 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 14 Can we think of a better mechanism? Resource Supply/ Demand Model  Supply/ demand SLA types: ��, �, �, ��  Customer cost should be a function of � ~ amount available or consumed  supply and demand � ~ allocation period   Supply may vary over time  � ~ tolerable number of missed allocations in �  Supplier’s cost may vary over time � ~ window of > = 1 allocation intervals   Demand may vary over time  Examples  Demand may exhibit structure, and may be SLA type �2,5,0,1�  subject to malleable constraints 2 resource units supplied/ consumed every 5 seconds with no missed allocations allowed  Need language to specify supply and SLA type �3,30,2,5�  demand (and act as basis for SLAs) 3 resource units supplied/ consumed every 30 seconds with no more than 2 out of 5 missed allocations December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 15 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 16 4

  5. SLA Calculus Using SLA Calculus for Colocation  Models various patterns of allocation and  Not possible Job 1 Job 2 Job 3 Job 4 Job 5 to colocate consumption (e.g., RR, GPS, LB, … ) C 1 2 3 4 5 T 4 9 17 34 67  SLA types define type hierarchies �1, �, 0,1� � ��, � ∗ �, 1,0�   Possible to Job 1 Job 2 Job 3 Job 4 Job 5 ��, �, �, �� � ��, �, �’, ��, if � � �’  colocate C 1 2 3 4 5  … T 4 8 16 32 64  Possible to transform SLAs from one  SLA types and calculus provide a notion of form to another (safer) form supply & demand elasticity December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 17 Morphing SLAs for Efficiency MorphoSys: Performance Colocation Efficiency (CE) MorphoSys { S’}  { R’} Allow Relocation Morph Co-Tenants Demand Types { R} Morph Once @ Arrival Supply Types { S} December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 19 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 20 5

  6. Beyond Simple Types Workload = DAG of SLA types  A workload is a set of requests (tasks), each with its SLA, subject to constraints:  Temporal dependencies between tasks  Start and end times  Flexibilities might exist; another source of elasticity:  Min and max delays between tasks  Deadline slacks December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 21 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 22 The Customer’s Perspective Dynamic Pricing: Shapley Value  Why should customers expose the  Well defined concept for fair cost sharing elasticity of their workloads? from coalitional game theory  Marginal contribution to the total cost, averaged  Current IaaS (fixed) pricing mechanisms over every permutation, e.g., for 3 workloads do not provide proper incentives � � � � 1 2 � w � � � w � w � � �� w � � � � w � w � � �� w � � �  Implications: 6 � w � w � w � � �� w � w � � � � w � w � w � � �� w � w � �  Less efficient workload management  Impractical to calculate  Customers (should) game the marketplace  Estimate by sampling random permutations December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 23 December 9, 2011 I n Cloud (Markets) We Trust by A. Bestavros @ DI MACS 24 6

Recommend

More recommend