Webinar 3: HA Mantra - How DCIM Can Help
Upcoming SlideShare
Loading in...5

Webinar 3: HA Mantra - How DCIM Can Help






Total Views
Views on SlideShare
Embed Views



2 Embeds 5

https://www.linkedin.com 3
http://www.linkedin.com 2



Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
Post Comment
Edit your comment

Webinar 3: HA Mantra - How DCIM Can Help Webinar 3: HA Mantra - How DCIM Can Help Presentation Transcript

  • Webinar 3: October 31, 2012 (Wednesday):High Availability Mantra: 11:00 AM IST How DCIM Can Help 1
  • About GreenField SoftwareOur Company Our Mission Incubated by a US$ 40 million Engineering Company Pioneering Energy & Environment Founders: Management Software for• Shekhar Dasgupta, ex-MD Oracle Cost Savings & Energy Optimization India• Abhijit Sen, Director, UD GroupOur Solutions Our Partners Data Center Infrastructure Management (DCIM) Sustainability Management for Manufacturing DCIM enabled Advisory Services for Data Centers 2
  • Today’s Topics• The HA Mantra Revisited• Anatomy of a DCIM Software: GFS Crane DC• How GFS Crane DC Delivers Higher Availability• Other Benefits of GFS Crane DC• Key Factors for a Successful DCIM Implementation 3
  • The High Availability Mantra RevisitedAvailability % Downtime per year Downtime per month* Downtime per week99% ("two nines") 3.65 days 7.20 hours 1.68 hours99.5% 1.83 days 3.60 hours 50.4 minutes99.8% 17.52 hours 86.23 minutes 20.16 minutes99.9% ("three nines") 8.76 hours 43.8 minutes 10.1 minutes99.95% 4.38 hours 21.56 minutes 5.04 minutes99.99% ("four nines") 52.56 minutes 4.32 minutes 1.01 minutes99.999% ("five nines") 5.26 minutes 25.9 seconds 6.05 seconds99.9999% ("six nines") 31.5 seconds 2.59 seconds 0.605 seconds99.99999% ("seven nines") 3.15 seconds 0.259 seconds 0.0605 secondsAmazon Data Centers (built to Tier 4 standards and with an expected availability of 99.995%) has hadtwo outages already in 2012 – each over 3 hours!• Tier 3/Tier 4 just defined by hardware redundancies• Glaring gaps in operating procedures to prevent fatal human errors• Lack of purpose-built BCP software to predict failures• Lack of chain of custody to detect root cause 4
  • Did You Know? 90% of DC Failures Are From Common Preventable Causes 5
  • Did You Know? Average Failure of an Online System: 36 hours per annum. That’s only 99.6% Uptime 6
  • Did You Know? 75% of Businesses Without a BC Plan Fail Within 3 Years after a Major Disruption in their IT Systems 7
  • Anatomy of a DCIM Software: GFS Crane DC Enables a More Efficient, Higher Availability & Greener Data Center 8
  • How GFS Crane DC Delivers Higher AvailabilityAsset Tracking Alert Management Auto-discovers and maps asset base  Manages both IT & non-IT assets across all Data Centers  Tracks redundancy paths & Tracks utilization and rationalizes identifies Points of Failure across asset base the chain Tracks provisioning and Changes  Monitors performance trends of through Work Flow Management assets and predicts failures. Tracks & records Move-Add-Change  Tracks MAC and prevents (MAC) of assets disruption due to unauthorized change. Helps to reduce CAPEX.  Change Management prevents downtime due to human errors GFS Crane DC Helps to Predict Failures 9
  • GFS Crane DC – HA Features Establishes logical relationships and inter- dependencies among all data center assets. Business Helps to identify single points of failure in the dataContinuity center. Planning Maps servers with mission critical applications. Maps the applications to business functions/users. Helps impact analysis of failure of an asset and its cascading effect on the availability of other Establishes assets/services relationship maps Automatic alert mechanisms regarding (a) racks for assets by identifying various exceeding the tolerance limits of power consumption dependencies among (b) server utilization exceeding a specified threshold: them. Does impact enables proactive action to avert a potential disruption analysis and predicts failure of assets. in business continuity. Notifies possible Simulations on power and space requirement in the failure through DC for a particular change helps averting a potential proactive alerts. outage or disruption in continuity. Enabling a Higher Uptime Data Center 10
  • Defining Relationships and Dependencies Rack to Device Relationship  User can create a virtual model of the all racks in the data center by adding servers, storages and network devices.  User can do a ‘what-if’ analysis by adding proposed servers in a rack and thereby get an estimate on power and space requirements. Computing to Non-computing Relationship  User can establishes logical relationships and inter-dependencies among all data center assets which helps in doing impact analysis of scheduled/unplanned downtimes and defining maintenance window for devices – hence better problem management for the data center 11
  • Defining Relationships and Dependencies Application to Servers and SBU Relationship  Applications can be mapped to servers (both physical and virtual) on which they are hosted.  Further mapped to Business Units using those applications. 12
  • Alert Management Automatic Alerts  Automatic alert mechanisms regarding (a) racks exceeding the tolerance limits of power consumption (b) server utilization exceeding a specified threshold helps in taking proactive action so that a potential disaster and disruption in business continuity can be averted.  Alerts can be configured to be sent as emails or SMS. 13
  • GFS Crane DC Also Addresses ………….Energy Problems Operational Problems Measures power consumption up to  Maintains up-to-date asset register device level  Identifies underutilized resources Identifies non-energy efficient  Identifies old equipment and devices - recommends improvement possible replacement candidates methods  Optimizes floor and rack space Optimizes cooling utilization Measures PUE. Identifies  Optimizes Power & Cooling inefficiencies & power distribution losses  Enables accurate capacity planning on fact-based analysis. Compares DC performance metrics with global benchmarks Helps establish KPIs Reports CO2 emission GFS Crane DC Improves Energy & Operational Efficiencies 14
  • GFS Crane DC – Features Recommends ways to reduce power consumption by servers in Energy the data center. Efficiency – Calculates power consumption at VM layer: power savings due toIT & Facility virtualization is now measurable! Provides a unique Manufacturers Repository for identifying available alternatives for replacement of data center assetsIdentifies servers Provides visibility in terms of the amount of power consumed bywhich are candidatesfor virtualization, non-production and less critical servers in the data center.retirement and Calculates DC Metrics like PUE, DCiE, Watt/rack & Watt/sq.ft.replacement. and compares metrics against published standardsOptimizes powerconsumed by non- Tracks PUE at multiple levels of the of the data center’s powerproduction servers. chain and thereby identifies inefficient equipment which can beOptimizes space & replaced for improving efficiencycooling load.Calculates PUE at Tracks PUE over timemultiple levels to Recommends ways to reduce power costs by moving devicesidentify facility within the DClosses. 15
  • GFS Crane DC – Features  Provides automatic discovery of assets using SNMP and WMI.  Asset rediscovery option helps in detecting a change in Asset configuration of an asset that may have gone unregisteredManagement due to human error.& Capacity  Captures detailed attributes of all IT and facility assets and Planning maintains an exportable asset register for the entire data center.  Unique search option helps identifying an existing asset Auto discovers which can refresh a “replacement candidate”: saves CAPEX assets using SNMP on new procurement. & WMI. Captures  Provides a bird’s eye view of every rack in the data center in and manages terms of power and space utilization and available capacity. various asset  Provides option to simulate a ‘what if’ scenario such as attributes. Maintains detailed inventory of provisioning of a high performance server and predicts the both IT and facility impact on power and space utilization due to such a change. assets of the data  Identifies best place(s) where new devices can be placed in the center. Visualization data center, thereby helping in capacity planning on power of DC floor on space and cooling.. power and space capacity and simulation of ‘what if’ scenario help in capacity planning. Enabling a More Efficient Data Center 16
  • DCIM Business Flow Reduced Energy & Operating Cos t DISCOVER MANAGE High Availability & Uptime Modeling Policy Engine Analytic REPORT Tools VISUALISE GFS Crane DC: Beyond Traditional DCIM 17
  • Benefits of DCIM 18
  • What GFS Crane DC Delivers• Measures & Analyzes Power Consumption: Measures power consumption at device level; makes recommendations for lower power usage.• Calculates Key Metrics: GFS Crane DC measures PUE at all three levels, as recommended by Green Grid. Also measures other KPIs like watt per Rack.• Asset Management & Capacity Planning: Discovers and Maps all assets: computing & non- computing. Enables Visualization and simulation of entire Data Center. Power, Space & Cooling optimization wrt Capacity Planning.• Business Continuity: GFS Crane DC comes with three unique features for BCP:  Visually defining the entire chain of all asset relationships: application to back-up power, helping to identify missing or weakest links and the redundancy paths;  Simulating a MAC operation and thereby analyzing impact on power and space capacity of a data center due to an impending change.  Providing alerts when critical thresholds are breached.• Sustainability Reporting: Provides carbon footprint till the application and server level for better Sustainability Management & Reporting; Enables proactive E-Waste management through aging analysis and equipment replacement reports. 19
  • GFS Crane DC – Delivering Lean IT• Helping Cost Reductions through  Rationalization of data center asset base – IT and Facility  Server Virtualization Planner and optimizing best possible virtualization scenario  Virtualization optimization – adding more virtual machines per host  Hardware consolidation – replacing old servers with energy efficient blades  Optimizing rack and floor space utilization• Driving Efficiencies through  Technology Refresh  Retiring Zombie Servers  Optimizing power consumed by non-production systems  Optimizing Space & Cooling.  Identifying power losses in the facility infrastructure through multilevel PUE calculation 20
  • GFS Crane DC – Delivering HA & Green Data Center• Mitigating Risks through  Mapping critical asset relationships  Identifying points of failures & redundancy paths  Proactive alerts  Failure prediction from MAC simulations• Enabling Greener Data Center through:  Better power management  GHG inventory & Equipment aging analysis (E-waste)  Sustainability reporting 21
  • Key Factors for aSuccessful DCIMImplementation 22
  • Measure “As-Is” & Define “To-Be”• Document Standard Operating Procedures  DCIM Introduces business process changes in the Data Center  Get buy-in of all stakeholders. Change is never easy!  Document current SOP  Map desired SOP with desired state & timelines  Identify the variance with what contending DCIM tools have to offer  Ask for road maps• Baseline – Where Are We Today  Measure: • Asset & space utilization. • Power consumption & Costs. Heat Loads. • Uptime.  Where do we want to be? What should be my KPIs/policies?  Where can I get measurable quick wins? 23
  • DCIM for Business Support• Align with Business Objectives  DCIM is a business application: needs to support business objectives • Cost Reductions? How can DCIM help? • Need to deliver higher SLA? How can DCIM help? • Running out of space? How can DCIM help?  Avoid full-fledged implementation of “all” features: recipe for disaster• Get Management Commitment & Involvement  Data Center is the heart of the business  Chairing Steering Committee Meetings  Broadcasting Company-wide: why DCIM is being implemented  Resolving problems & conflicts, if they arise 24
  • DCIM: Benefits Summary Higher Uptime Higher Asset Utilization Better Space Utilization Reduced cooling costs Lower Power Usage & Costs 25
  • Thank You and Q&A 26
  • Next Webinar: November 28, 2012 (Wednesday): Case Study - How DCIM 11:00 AM ISTHelped in High Availability 27