SlideShare a Scribd company logo
1 of 20
Download to read offline
1




Auto-Scaling to Minimize Cost and
  Meet Application Deadlines in
        Cloud Workflows

                        SC 11
                   (Nov 16, TCC 305)




        Ming Mao, Marty Humphrey
        CS Department, University of Virginia
Introduction
2


       Resource provisioning questions are not trivial
           Under-provisioning → hurt performance
           Over-provisioning → pay more than necessary

         How much resources?
         What types of resources?

         When to acquire or release?

         How to use them?

       A performance-resource mapping problem
Auto-Scaling
3


       Schedule-based and rule-based auto-scaling
           E.g. “run 10 instances between 8AM to 6PM everyday and
            2 instances all the other time.”
           E.g. “add (remove) 2 instances when the average CPU
            utilization is above 70% (below 20%) for 5 minutes.”
           Simple and convenient, works well for simple applications
           What if the relationship between the performance and
            resources utilization indicators is complex
           The resource utilization indicators are low-level and may
            not be expressive enough
           They do not consider the user budgets well
Auto-Scaling
4


       Goals of auto-scaling mechanisms
             Balance performance and cost
                   E.g. meet performance goals with minimum cost or maximize
                    utilities with the limited budget
             Reflect different options for computing resources
                   E.g. VMs have different processing power and price
             Be aware of practical considerations
                   E.g. VM may takes several min to be ready to use
             Be aware of the cloud billing model
                   E.g. billed by instance-hours
             Support specific application performance requirements
                   E.g. deadlines, the number of concurrent users, communication
                    latency
Cloud application model
5

                                                                                            Credit
                                                                 Cloud                      History
                                                                                                      Third Party
                                                                                                      Evaluation
                                                                                                                      Complete
                                                                                                                       Model
                         Gold                                                                 (5)         (8)
                                                                                                                        (10)
                        Members                          Authentication
                                                                            Loading
                                                                             Profile        Health
                                                              (2)
                                                                               (4)          Record
                                                                                                      Advanced
                                                                                              (6)      Model
                         Silver           Entry
                        Members          Point (1)                                                       (9)                     Response
                                                                                                                                   (11)
                                                                       Data                 Base
                                                                     Validation             Model
                         Non-                                            (3)                 (7)
                        Member
                                                                                                      Auto-Scaling


                             Non-Member Job          Silver Member Job            Gold Member Job

                                                                                                                    Cloud VMs
       App consists of service units
       Job consists of tasks
       Jobs are categorized into classes (deadline and processing flow)
       Cloud offers multiple VM types (price and processing power)
       App has no knowledge on the workload info in advance
       VM takes time to start up (VM acquisition delay) and are billed by hours
Problem definition
6

        Cloud application
            app = {Si}
                                                    Job class
                                                        J = {DAG(Si), deadline | Si ∈ app}
        Cloud VM
                          𝑆
            VMv = {[𝑗 𝐽 𝑖 ]v , cv , lagv}
                                                    Workload
                                                                         𝑆𝑖
                                                        Wt =   𝑆𝑖   𝐽 𝑗𝐽
        Scaling plan
            Scalingt = {VMv , Nv}

                                                    Scheduling plan
                                                                              𝑆
                                                        Schedulet = { 𝑗 𝐽 𝑖 →VMv}
        Goal
            Min(C) = Min(        𝑣   𝑐 𝑣 𝑁 𝑣)
Solution
7


       SCS (Scaling – Consolidation - Scheduling)
         Task bundling
         Deadline assignment

         Scaling

         Instance consolidation

         Scheduling
Solution – Step 1
8


       Task bundling
         Idea – force tasks run on the same instance to improve
          performance and save data transfer cost

         Example

                      T6                T8       T6                     T8
                                                   Bundle task as T6'


                    Server 1        Server 2   Server 1           Server 1
                               Before                     After
Solution – Step 2
9


       Deadline assignment
         Idea – to break task dependencies, assign deadlines
          proportionally based on task running time (on their cost-
          efficient machines)
         Example
                                                                          T3
                           T3                                                  T7
                                T7
                                                                          T4                        T11
                           T4              T11

                                                 T13        T1    T2           T8      T10                   T13
                 T1   T2        T8   T10
                           T5              T12                            T5                        T12
                                T9                                             T9

                           T6                                             T6


            3:00PM
              3:00                                4:30   3:00 3:10 3:20         3:50         4:00         4:20 4:30
                           Before                                                   After
           Task upgrading
                                                   𝑚𝑎𝑘𝑒𝑠𝑝𝑎𝑛 𝑏𝑒𝑓𝑜𝑟𝑒 −𝑚𝑎𝑘𝑒𝑠𝑝𝑎𝑛 𝑎𝑓𝑡𝑒𝑟
                                      𝑟𝑎𝑛𝑘 =
                                                         𝑐𝑜𝑠𝑡 𝑎𝑓𝑡𝑒𝑟 −𝑐𝑜𝑠𝑡 𝑏𝑒𝑓𝑜𝑟𝑒
Solution – Step 3
10


        Determine the number of instances
          From   deadline assignment, we have
            Task running time – tm
            Task execution interval – [T0 ,T1 ]

          Load   vector
            LVm =  [tm/( T1 – T0 )]
            # of instances = [LVm]

          Example

                    T1     0   0                     0.25            0   0
                    T2     0   0          0           0.5      0     0   0
                                   3:00       3:15          3:45 4:00
                                                                             VM1
                    All    0   0      0.25           0.75     0.25   0   0
Solution – Step 5
11


        Instance consolidation
          Idea – put tasks on the same instance even if some
           task may not run the most cost-efficiently on that
           machine

          Example
                                      T11                                  Idle
                                            High-CPU 3:00 PM                      4:00 PM
                       Before
                                      T12                        Idle
                                                       3:00 PM                    4:00 PM
                                            Standard

                      After     T11   T12                               Idle
                                            Standard   3:00 PM                    4:00 PM
Solution – Step 6
12


        Scheduling – Earliest Deadline First
          The dynamic scaling feature can make sure that the
           tasks facing missed deadlines can be found in time

                                       𝑡𝑖
                                                  <1
                          𝑖   𝑇 𝑒𝑛𝑑_𝑖 − 𝑇 𝑠𝑡𝑎𝑟𝑡_𝑖
Solution – Overview
13


                            Parallelism   reduction
Evaluation
14

        Workload patterns




        Application models
                                                        VM Type            Price
                                                          Micro         $0.02/hour
                                                        Standard        $0.085/hour
                                                        High-CPU        $0.68/hour
                                                      High-Memory       $0.50/hour

      Base line     Time            Task   execution         VM        lag
        Greedy          72 hours       Randomly generated           8 min
        GAIN
Evaluation
15




      SCS cost saving ranges from 6.8% to 40.4%
      The performance difference is larger with longer deadlines
Evaluation – High volume V.S. Low volume
16


        High workload (10X ) V.S. low workload (X)
          Pipeline,        1-hour deadline
            Cost ($)
                         High Volume V.S. Low Volume
           120                                            Greedy-
                                                          High
           100                                            GAIN-
                                                          High
            80
                                                          SCS-High
            60
                                                          Greedy-
            40                                            Low
                                                          GAIN-
            20
                                                          Low
              0                                           SCS-Low
                       Stable   Growing   Cycle   OnOff
Evaluation – Imprecise parameters
17

                 Deadline(0.5hour) Non-Miss Rate for           Pipeline application, 20% variance
     Non-miss
     Rate (%)    Imprecise Task Execution Estimation
     100.0%                                                     in estimated execution time, 0.5-
      90.0%
      80.0%
                                                                hour deadline
                                                     Greedy
                                                               SCS can finish jobs before
      70.0%
      60.0%
      50.0%                                          GAIN
      40.0%                                          SCS
                                                                deadlines for more than 90%,
      30.0%
      20.0%                                                     much better than Greedy(40%)
      10.0%
       0.0%
                                                                and GAIN(50%)
                 Stable    Growing   Cycle   OnOff


                 Deadeline(1 hour) Non-Miss Rate for           Pipeline application, 20% variance
      Non-miss
      Rate(%)     Imprecise Instance Acquisition Lag            in the estimate VM acquisition
     100.0%
      90.0%                                                     time, 1-hour deadline
      80.0%
      70.0%                                          Greedy    SCS beats Greedy and GAIN
      60.0%
      50.0%
                                                     GAIN
                                                               The performance is more affected
      40.0%                                          SCS
      30.0%                                                     by the VM acquisition time
      20.0%
      10.0%
       0.0%
                  Stable   Growing   Cycle   OnOff
Related work
18


        Dynamic resource provisioning in virtualized
         environment
              Multi-tier web applications, queuing theory, control theory
        Workflow scheduling in Grid environment with
         deadline and budget constraints
            Single workflow instance
            Resource pool is limited
        Cloud economics
              Cloud provider side V.S. cloud user side
        Current cloud auto-scaling mechanisms
              E.g. AWS auto-scaling, RightScale, enStratus, Scalr, AzureScale
               project, etc.
Conclusion and future work
19

        Conclusions
            SCS cost saving ranges from 6.8% to 40.4%
            SCS can better handle different workload volume and imprecise
             parameters
            Choosing proper VM types based on the workload saves cost
            Instance consolidation can help save partial instance hours
            VM acquisition time plays a very important role

        Future work
            Different scheduling approaches
            Real scientific applications
            Insufficient budget cases - maximize cloud user benefits/utilities
             under budget constraints
            Data-intensive applications
20




     Thank you!

More Related Content

What's hot

virtualization and hypervisors
virtualization and hypervisorsvirtualization and hypervisors
virtualization and hypervisorsGaurav Suri
 
BriMor Labs Live Response Collection - OSDFCON
BriMor Labs Live Response Collection - OSDFCONBriMor Labs Live Response Collection - OSDFCON
BriMor Labs Live Response Collection - OSDFCONBriMorLabs
 
Chapter 02: Introduction to compute virtualization
Chapter 02: Introduction to compute virtualizationChapter 02: Introduction to compute virtualization
Chapter 02: Introduction to compute virtualizationSsendiSamuel
 
Hypervisor seminar
Hypervisor seminarHypervisor seminar
Hypervisor seminar용환 노
 
Virtualization security
Virtualization securityVirtualization security
Virtualization securityAhmed Nour
 
Cloud architecture
Cloud architectureCloud architecture
Cloud architectureAdeel Javaid
 
VMware Tanzu Application Service as an Integration Platform
VMware Tanzu Application Service as an Integration PlatformVMware Tanzu Application Service as an Integration Platform
VMware Tanzu Application Service as an Integration PlatformVMware Tanzu
 
virtualization-vs-containerization-paas
virtualization-vs-containerization-paasvirtualization-vs-containerization-paas
virtualization-vs-containerization-paasrajdeep
 
Infrastructure Security: Your Minimum Security Baseline
Infrastructure Security: Your Minimum Security BaselineInfrastructure Security: Your Minimum Security Baseline
Infrastructure Security: Your Minimum Security BaselineAmazon Web Services
 
Cloud computing using Eucalyptus
Cloud computing using EucalyptusCloud computing using Eucalyptus
Cloud computing using EucalyptusAbhishek Dey
 
Hypervisors and Virtualization - VMware, Hyper-V, XenServer, and KVM
Hypervisors and Virtualization - VMware, Hyper-V, XenServer, and KVMHypervisors and Virtualization - VMware, Hyper-V, XenServer, and KVM
Hypervisors and Virtualization - VMware, Hyper-V, XenServer, and KVMvwchu
 
NSX-T Architecture and Components.pptx
NSX-T Architecture and Components.pptxNSX-T Architecture and Components.pptx
NSX-T Architecture and Components.pptxAtif Raees
 
SaaS Challenges & Security Concerns
SaaS Challenges & Security ConcernsSaaS Challenges & Security Concerns
SaaS Challenges & Security ConcernsKannan Subbiah
 
IBM MQ: Managing Workloads, Scaling and Availability with MQ Clusters
IBM MQ: Managing Workloads, Scaling and Availability with MQ ClustersIBM MQ: Managing Workloads, Scaling and Availability with MQ Clusters
IBM MQ: Managing Workloads, Scaling and Availability with MQ ClustersDavid Ware
 

What's hot (20)

Spnego configuration
Spnego configurationSpnego configuration
Spnego configuration
 
virtualization and hypervisors
virtualization and hypervisorsvirtualization and hypervisors
virtualization and hypervisors
 
Unit 4
Unit 4Unit 4
Unit 4
 
BriMor Labs Live Response Collection - OSDFCON
BriMor Labs Live Response Collection - OSDFCONBriMor Labs Live Response Collection - OSDFCON
BriMor Labs Live Response Collection - OSDFCON
 
Chapter 02: Introduction to compute virtualization
Chapter 02: Introduction to compute virtualizationChapter 02: Introduction to compute virtualization
Chapter 02: Introduction to compute virtualization
 
Hypervisor seminar
Hypervisor seminarHypervisor seminar
Hypervisor seminar
 
Virtualization security
Virtualization securityVirtualization security
Virtualization security
 
Cloud architecture
Cloud architectureCloud architecture
Cloud architecture
 
VMware Tanzu Application Service as an Integration Platform
VMware Tanzu Application Service as an Integration PlatformVMware Tanzu Application Service as an Integration Platform
VMware Tanzu Application Service as an Integration Platform
 
virtualization-vs-containerization-paas
virtualization-vs-containerization-paasvirtualization-vs-containerization-paas
virtualization-vs-containerization-paas
 
IBM MQ Basics
IBM MQ BasicsIBM MQ Basics
IBM MQ Basics
 
Infrastructure Security: Your Minimum Security Baseline
Infrastructure Security: Your Minimum Security BaselineInfrastructure Security: Your Minimum Security Baseline
Infrastructure Security: Your Minimum Security Baseline
 
Cloud computing using Eucalyptus
Cloud computing using EucalyptusCloud computing using Eucalyptus
Cloud computing using Eucalyptus
 
Hypervisors and Virtualization - VMware, Hyper-V, XenServer, and KVM
Hypervisors and Virtualization - VMware, Hyper-V, XenServer, and KVMHypervisors and Virtualization - VMware, Hyper-V, XenServer, and KVM
Hypervisors and Virtualization - VMware, Hyper-V, XenServer, and KVM
 
NSX-T Architecture and Components.pptx
NSX-T Architecture and Components.pptxNSX-T Architecture and Components.pptx
NSX-T Architecture and Components.pptx
 
SaaS Challenges & Security Concerns
SaaS Challenges & Security ConcernsSaaS Challenges & Security Concerns
SaaS Challenges & Security Concerns
 
IBM MQ: Managing Workloads, Scaling and Availability with MQ Clusters
IBM MQ: Managing Workloads, Scaling and Availability with MQ ClustersIBM MQ: Managing Workloads, Scaling and Availability with MQ Clusters
IBM MQ: Managing Workloads, Scaling and Availability with MQ Clusters
 
Presence cloud
Presence cloudPresence cloud
Presence cloud
 
CloudStack Architecture
CloudStack ArchitectureCloudStack Architecture
CloudStack Architecture
 
Cloud computing architectures
Cloud computing architecturesCloud computing architectures
Cloud computing architectures
 

Similar to Auto-Scaling to Minimize Cost in Cloud Workflows

IRJET- Time and Resource Efficient Task Scheduling in Cloud Computing Environ...
IRJET- Time and Resource Efficient Task Scheduling in Cloud Computing Environ...IRJET- Time and Resource Efficient Task Scheduling in Cloud Computing Environ...
IRJET- Time and Resource Efficient Task Scheduling in Cloud Computing Environ...IRJET Journal
 
VMworld 2013: Moving Enterprise Application Dev/Test to VMware’s Internal Pri...
VMworld 2013: Moving Enterprise Application Dev/Test to VMware’s Internal Pri...VMworld 2013: Moving Enterprise Application Dev/Test to VMware’s Internal Pri...
VMworld 2013: Moving Enterprise Application Dev/Test to VMware’s Internal Pri...VMworld
 
Serenity Project: Security in Software Enginering
Serenity Project: Security in Software EngineringSerenity Project: Security in Software Enginering
Serenity Project: Security in Software EngineringFrancisco Sanchez Cid
 
Cloud computing and CloudStack
Cloud computing and CloudStackCloud computing and CloudStack
Cloud computing and CloudStackMahbub Noor Bappy
 
SaaS transformation with OCE - uEngineCloud
SaaS transformation with OCE - uEngineCloudSaaS transformation with OCE - uEngineCloud
SaaS transformation with OCE - uEngineClouduEngine Solutions
 
Spring boot microservice metrics monitoring
Spring boot   microservice metrics monitoringSpring boot   microservice metrics monitoring
Spring boot microservice metrics monitoringOracle Korea
 
Spring Boot - Microservice Metrics Monitoring
Spring Boot - Microservice Metrics MonitoringSpring Boot - Microservice Metrics Monitoring
Spring Boot - Microservice Metrics MonitoringDonghuKIM2
 
Dc architecture for_cloud
Dc architecture for_cloudDc architecture for_cloud
Dc architecture for_cloudAlain Geenrits
 
IRJET- Scheduling of Independent Tasks over Virtual Machines on Computati...
IRJET-  	  Scheduling of Independent Tasks over Virtual Machines on Computati...IRJET-  	  Scheduling of Independent Tasks over Virtual Machines on Computati...
IRJET- Scheduling of Independent Tasks over Virtual Machines on Computati...IRJET Journal
 
Performance and Cost Analysis of Modern Public Cloud Services
Performance and Cost Analysis of Modern Public Cloud ServicesPerformance and Cost Analysis of Modern Public Cloud Services
Performance and Cost Analysis of Modern Public Cloud ServicesMd.Saiedur Rahaman
 
RTC/CLM 5.0 Adoption Paths: Deploying in 16 Steps
 RTC/CLM 5.0 Adoption Paths: Deploying in 16 Steps RTC/CLM 5.0 Adoption Paths: Deploying in 16 Steps
RTC/CLM 5.0 Adoption Paths: Deploying in 16 StepsStéphane Leroy
 
Eci Service Architecture Evolution 1
Eci Service Architecture Evolution 1Eci Service Architecture Evolution 1
Eci Service Architecture Evolution 1David Sprott
 
Vulnerability Advisor: DevSecOps Integration
Vulnerability Advisor: DevSecOps IntegrationVulnerability Advisor: DevSecOps Integration
Vulnerability Advisor: DevSecOps IntegrationCanturk Isci
 
Building your private cloud the ncs experience harrison lee
Building your private cloud the ncs experience harrison leeBuilding your private cloud the ncs experience harrison lee
Building your private cloud the ncs experience harrison leeMicrosoft Singapore
 
Muves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 FinalMuves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 FinalElastic Grid, LLC.
 
Distributed Block-level Storage Management for OpenStack, by Danile lee
Distributed Block-level Storage Management for OpenStack, by Danile leeDistributed Block-level Storage Management for OpenStack, by Danile lee
Distributed Block-level Storage Management for OpenStack, by Danile leeHui Cheng
 
Danile lee -open stackblocklevelstorage
Danile lee -open stackblocklevelstorageDanile lee -open stackblocklevelstorage
Danile lee -open stackblocklevelstorageOpenCity Community
 
AWS re:Invent 2016: Fueling Migration: Shortcutting your Application Portfoli...
AWS re:Invent 2016: Fueling Migration: Shortcutting your Application Portfoli...AWS re:Invent 2016: Fueling Migration: Shortcutting your Application Portfoli...
AWS re:Invent 2016: Fueling Migration: Shortcutting your Application Portfoli...Amazon Web Services
 
RTC/CLM 2012 Adoption Paths : Deploying in 16 Steps
RTC/CLM 2012 Adoption Paths : Deploying in 16 StepsRTC/CLM 2012 Adoption Paths : Deploying in 16 Steps
RTC/CLM 2012 Adoption Paths : Deploying in 16 StepsStéphane Leroy
 

Similar to Auto-Scaling to Minimize Cost in Cloud Workflows (20)

IRJET- Time and Resource Efficient Task Scheduling in Cloud Computing Environ...
IRJET- Time and Resource Efficient Task Scheduling in Cloud Computing Environ...IRJET- Time and Resource Efficient Task Scheduling in Cloud Computing Environ...
IRJET- Time and Resource Efficient Task Scheduling in Cloud Computing Environ...
 
VMworld 2013: Moving Enterprise Application Dev/Test to VMware’s Internal Pri...
VMworld 2013: Moving Enterprise Application Dev/Test to VMware’s Internal Pri...VMworld 2013: Moving Enterprise Application Dev/Test to VMware’s Internal Pri...
VMworld 2013: Moving Enterprise Application Dev/Test to VMware’s Internal Pri...
 
Serenity Project: Security in Software Enginering
Serenity Project: Security in Software EngineringSerenity Project: Security in Software Enginering
Serenity Project: Security in Software Enginering
 
Cloud computing and CloudStack
Cloud computing and CloudStackCloud computing and CloudStack
Cloud computing and CloudStack
 
SaaS transformation with OCE - uEngineCloud
SaaS transformation with OCE - uEngineCloudSaaS transformation with OCE - uEngineCloud
SaaS transformation with OCE - uEngineCloud
 
Spring boot microservice metrics monitoring
Spring boot   microservice metrics monitoringSpring boot   microservice metrics monitoring
Spring boot microservice metrics monitoring
 
Spring Boot - Microservice Metrics Monitoring
Spring Boot - Microservice Metrics MonitoringSpring Boot - Microservice Metrics Monitoring
Spring Boot - Microservice Metrics Monitoring
 
Dc architecture for_cloud
Dc architecture for_cloudDc architecture for_cloud
Dc architecture for_cloud
 
IRJET- Scheduling of Independent Tasks over Virtual Machines on Computati...
IRJET-  	  Scheduling of Independent Tasks over Virtual Machines on Computati...IRJET-  	  Scheduling of Independent Tasks over Virtual Machines on Computati...
IRJET- Scheduling of Independent Tasks over Virtual Machines on Computati...
 
Performance and Cost Analysis of Modern Public Cloud Services
Performance and Cost Analysis of Modern Public Cloud ServicesPerformance and Cost Analysis of Modern Public Cloud Services
Performance and Cost Analysis of Modern Public Cloud Services
 
RTC/CLM 5.0 Adoption Paths: Deploying in 16 Steps
 RTC/CLM 5.0 Adoption Paths: Deploying in 16 Steps RTC/CLM 5.0 Adoption Paths: Deploying in 16 Steps
RTC/CLM 5.0 Adoption Paths: Deploying in 16 Steps
 
Eci Service Architecture Evolution 1
Eci Service Architecture Evolution 1Eci Service Architecture Evolution 1
Eci Service Architecture Evolution 1
 
Vulnerability Advisor: DevSecOps Integration
Vulnerability Advisor: DevSecOps IntegrationVulnerability Advisor: DevSecOps Integration
Vulnerability Advisor: DevSecOps Integration
 
Building your private cloud the ncs experience harrison lee
Building your private cloud the ncs experience harrison leeBuilding your private cloud the ncs experience harrison lee
Building your private cloud the ncs experience harrison lee
 
Muves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 FinalMuves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 Final
 
Resume_Mohan Selvamoorthy_Sec
Resume_Mohan Selvamoorthy_SecResume_Mohan Selvamoorthy_Sec
Resume_Mohan Selvamoorthy_Sec
 
Distributed Block-level Storage Management for OpenStack, by Danile lee
Distributed Block-level Storage Management for OpenStack, by Danile leeDistributed Block-level Storage Management for OpenStack, by Danile lee
Distributed Block-level Storage Management for OpenStack, by Danile lee
 
Danile lee -open stackblocklevelstorage
Danile lee -open stackblocklevelstorageDanile lee -open stackblocklevelstorage
Danile lee -open stackblocklevelstorage
 
AWS re:Invent 2016: Fueling Migration: Shortcutting your Application Portfoli...
AWS re:Invent 2016: Fueling Migration: Shortcutting your Application Portfoli...AWS re:Invent 2016: Fueling Migration: Shortcutting your Application Portfoli...
AWS re:Invent 2016: Fueling Migration: Shortcutting your Application Portfoli...
 
RTC/CLM 2012 Adoption Paths : Deploying in 16 Steps
RTC/CLM 2012 Adoption Paths : Deploying in 16 StepsRTC/CLM 2012 Adoption Paths : Deploying in 16 Steps
RTC/CLM 2012 Adoption Paths : Deploying in 16 Steps
 

Recently uploaded

TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.Curtis Poe
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfPrecisely
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningLars Bell
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 

Recently uploaded (20)

TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine Tuning
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 

Auto-Scaling to Minimize Cost in Cloud Workflows

  • 1. 1 Auto-Scaling to Minimize Cost and Meet Application Deadlines in Cloud Workflows SC 11 (Nov 16, TCC 305) Ming Mao, Marty Humphrey CS Department, University of Virginia
  • 2. Introduction 2  Resource provisioning questions are not trivial  Under-provisioning → hurt performance  Over-provisioning → pay more than necessary  How much resources?  What types of resources?  When to acquire or release?  How to use them?  A performance-resource mapping problem
  • 3. Auto-Scaling 3  Schedule-based and rule-based auto-scaling  E.g. “run 10 instances between 8AM to 6PM everyday and 2 instances all the other time.”  E.g. “add (remove) 2 instances when the average CPU utilization is above 70% (below 20%) for 5 minutes.”  Simple and convenient, works well for simple applications  What if the relationship between the performance and resources utilization indicators is complex  The resource utilization indicators are low-level and may not be expressive enough  They do not consider the user budgets well
  • 4. Auto-Scaling 4  Goals of auto-scaling mechanisms  Balance performance and cost  E.g. meet performance goals with minimum cost or maximize utilities with the limited budget  Reflect different options for computing resources  E.g. VMs have different processing power and price  Be aware of practical considerations  E.g. VM may takes several min to be ready to use  Be aware of the cloud billing model  E.g. billed by instance-hours  Support specific application performance requirements  E.g. deadlines, the number of concurrent users, communication latency
  • 5. Cloud application model 5 Credit Cloud History Third Party Evaluation Complete Model Gold (5) (8) (10) Members Authentication Loading Profile Health (2) (4) Record Advanced (6) Model Silver Entry Members Point (1) (9) Response (11) Data Base Validation Model Non- (3) (7) Member Auto-Scaling Non-Member Job Silver Member Job Gold Member Job Cloud VMs  App consists of service units  Job consists of tasks  Jobs are categorized into classes (deadline and processing flow)  Cloud offers multiple VM types (price and processing power)  App has no knowledge on the workload info in advance  VM takes time to start up (VM acquisition delay) and are billed by hours
  • 6. Problem definition 6  Cloud application  app = {Si}  Job class  J = {DAG(Si), deadline | Si ∈ app}  Cloud VM 𝑆  VMv = {[𝑗 𝐽 𝑖 ]v , cv , lagv}  Workload 𝑆𝑖  Wt = 𝑆𝑖 𝐽 𝑗𝐽  Scaling plan  Scalingt = {VMv , Nv}  Scheduling plan 𝑆  Schedulet = { 𝑗 𝐽 𝑖 →VMv}  Goal  Min(C) = Min( 𝑣 𝑐 𝑣 𝑁 𝑣)
  • 7. Solution 7  SCS (Scaling – Consolidation - Scheduling)  Task bundling  Deadline assignment  Scaling  Instance consolidation  Scheduling
  • 8. Solution – Step 1 8  Task bundling  Idea – force tasks run on the same instance to improve performance and save data transfer cost  Example T6 T8 T6 T8 Bundle task as T6' Server 1 Server 2 Server 1 Server 1 Before After
  • 9. Solution – Step 2 9  Deadline assignment  Idea – to break task dependencies, assign deadlines proportionally based on task running time (on their cost- efficient machines)  Example T3 T3 T7 T7 T4 T11 T4 T11 T13 T1 T2 T8 T10 T13 T1 T2 T8 T10 T5 T12 T5 T12 T9 T9 T6 T6 3:00PM 3:00 4:30 3:00 3:10 3:20 3:50 4:00 4:20 4:30 Before After  Task upgrading 𝑚𝑎𝑘𝑒𝑠𝑝𝑎𝑛 𝑏𝑒𝑓𝑜𝑟𝑒 −𝑚𝑎𝑘𝑒𝑠𝑝𝑎𝑛 𝑎𝑓𝑡𝑒𝑟 𝑟𝑎𝑛𝑘 = 𝑐𝑜𝑠𝑡 𝑎𝑓𝑡𝑒𝑟 −𝑐𝑜𝑠𝑡 𝑏𝑒𝑓𝑜𝑟𝑒
  • 10. Solution – Step 3 10  Determine the number of instances  From deadline assignment, we have  Task running time – tm  Task execution interval – [T0 ,T1 ]  Load vector  LVm = [tm/( T1 – T0 )]  # of instances = [LVm]  Example T1 0 0 0.25 0 0 T2 0 0 0 0.5 0 0 0 3:00 3:15 3:45 4:00 VM1 All 0 0 0.25 0.75 0.25 0 0
  • 11. Solution – Step 5 11  Instance consolidation  Idea – put tasks on the same instance even if some task may not run the most cost-efficiently on that machine  Example T11 Idle High-CPU 3:00 PM 4:00 PM Before T12 Idle 3:00 PM 4:00 PM Standard After T11 T12 Idle Standard 3:00 PM 4:00 PM
  • 12. Solution – Step 6 12  Scheduling – Earliest Deadline First  The dynamic scaling feature can make sure that the tasks facing missed deadlines can be found in time 𝑡𝑖 <1 𝑖 𝑇 𝑒𝑛𝑑_𝑖 − 𝑇 𝑠𝑡𝑎𝑟𝑡_𝑖
  • 13. Solution – Overview 13  Parallelism reduction
  • 14. Evaluation 14  Workload patterns  Application models VM Type Price Micro $0.02/hour Standard $0.085/hour High-CPU $0.68/hour High-Memory $0.50/hour  Base line  Time  Task execution  VM lag  Greedy  72 hours  Randomly generated  8 min  GAIN
  • 15. Evaluation 15  SCS cost saving ranges from 6.8% to 40.4%  The performance difference is larger with longer deadlines
  • 16. Evaluation – High volume V.S. Low volume 16  High workload (10X ) V.S. low workload (X)  Pipeline, 1-hour deadline Cost ($) High Volume V.S. Low Volume 120 Greedy- High 100 GAIN- High 80 SCS-High 60 Greedy- 40 Low GAIN- 20 Low 0 SCS-Low Stable Growing Cycle OnOff
  • 17. Evaluation – Imprecise parameters 17 Deadline(0.5hour) Non-Miss Rate for  Pipeline application, 20% variance Non-miss Rate (%) Imprecise Task Execution Estimation 100.0% in estimated execution time, 0.5- 90.0% 80.0% hour deadline Greedy  SCS can finish jobs before 70.0% 60.0% 50.0% GAIN 40.0% SCS deadlines for more than 90%, 30.0% 20.0% much better than Greedy(40%) 10.0% 0.0% and GAIN(50%) Stable Growing Cycle OnOff Deadeline(1 hour) Non-Miss Rate for  Pipeline application, 20% variance Non-miss Rate(%) Imprecise Instance Acquisition Lag in the estimate VM acquisition 100.0% 90.0% time, 1-hour deadline 80.0% 70.0% Greedy  SCS beats Greedy and GAIN 60.0% 50.0% GAIN  The performance is more affected 40.0% SCS 30.0% by the VM acquisition time 20.0% 10.0% 0.0% Stable Growing Cycle OnOff
  • 18. Related work 18  Dynamic resource provisioning in virtualized environment  Multi-tier web applications, queuing theory, control theory  Workflow scheduling in Grid environment with deadline and budget constraints  Single workflow instance  Resource pool is limited  Cloud economics  Cloud provider side V.S. cloud user side  Current cloud auto-scaling mechanisms  E.g. AWS auto-scaling, RightScale, enStratus, Scalr, AzureScale project, etc.
  • 19. Conclusion and future work 19  Conclusions  SCS cost saving ranges from 6.8% to 40.4%  SCS can better handle different workload volume and imprecise parameters  Choosing proper VM types based on the workload saves cost  Instance consolidation can help save partial instance hours  VM acquisition time plays a very important role  Future work  Different scheduling approaches  Real scientific applications  Insufficient budget cases - maximize cloud user benefits/utilities under budget constraints  Data-intensive applications
  • 20. 20 Thank you!