Using DCIM to Identify Data Center Efficiencies and Cost Savings Chuck Kramer, RCDD, NTS Charles.kramer@emerson.com
Data Center Eco-System (A 3 layer cake) Physical Layer IT Layer Application Layer DECOMMISIONING The data center has evolved from a static homogeneous environment to a complex heterogeneous eco-system 2
DCIM From Grid to Chip.. Process Templates Form Project Device Placement DL380 Dell 1850 Dismiss Alarm Tasks 3
DCIM Excellence Curve Do it for me! Capability -> Expertise What do I have? Basic Platform Installation Inventory Manager What is it doing? Reactive Site Manager Monitored Devices Basic Energy Mgmt What do I need to do? Proactive Process Management Tailored Reporting Advanced Energy How do I do it better? Optimized Integration with ITSM Tools Advanced Asset Mgmt Process Maturity Autonomic Advanced Event Configuration and Management Inventory Audit Training Value -> ROI
Reasons for Using DCIM Capacity Understand Current Utilization Project Future Requirements Align Supply and Demand Right-size Infrastructure Assets/Changes Inventory, Location Chargeback Improved Staff Efficiency Reduce Human Error Visibility Availability Equipment Operating Status Understand Impact of Incidents Root Cause Analysis Reduce Mean-Time-to-Repair Energy Measure and Manage PUE Manage Redundancy Equipment Utilization Cost of Power (Chargeback)
Reasons to Adopt DCIM Reduce operational costs Accurate data for design Maintain high availability Manage energy efficiency Increase agility Drive value across the business Availability + Capacity + Efficiency Today s high-density computing environments require a greater level of visibility and control than ever before
Remote IT Management What are my options for remote access and control of this rack of equipment? SSH Telnet RDP VNC KVM over IP Serial Console over IP Intelligent Power ILOM DRAC/iDRAC RSAII/IMM ilo2/3 IPMI Virtual Server Console What are my options for consolidated remote access and control of this rack of equipment AND all of my other IT infrastructure across multiple sites?
What s the Value of DCIM to the Enterprise? Proactive Operations Correlation Action Analytics Intelligence Aggregation Matches Facilities capacity (supply side) with IT requirements around availability, capacity and efficiency (demand side) Automated notification of warning/failure alarms Real-Time data aggregation Power and Cooling usage, trending, monitoring and alerting Server/Service Processor Monitoring Virtual machines (VMs) mapping to physical devices Leak Detection Data analytics for developing actionable intelligence (say, capacity management, uptime) Integration to existing BMS and systems management software tools for presenting Data Events
Traditional Solution : Add Buffer To Increase Availability Data Center Power Allocation Actual Capacity Power Stranded Capacity Buffer Limit Dynamic Changes Power Usage Time Dynamic Changes Data center power capacity includes buffers intended to absorb spikes in power use caused by peaks in resource utilization. These buffers are typically based on either nameplate or nominal server power consumption or power consumption measured at peak utilization with specific workloads. Space Power Cooling Static Source: Intel White Paper - Increasing Data Center Efficiency with Server Power Measurements
Traditional Solution : Add Buffer To Increase Availability Data Center Power Allocation Power Stranded Capacity Time Actual Capacity Buffer Limit Power Usage Data center power capacity includes buffers intended to absorb spikes in power use caused by peaks in resource utilization. These buffers are typically based on either nameplate or nominal server power consumption or power consumption measured at peak utilization with specific workloads. According to Emerson calculations, if every U.S. data center could utilize 10% MORE of their Space Power Cooling Dynamic Changes CAPACITY, the need to build more than 2 million square feet of new data center space could be eliminated each year.... SAVING MORE THAN $10B Dynamic Changes Static Source: Intel White Paper - Increasing Data Center Efficiency with Server Power Measurements
Stages of DCIM DCIM is a Process Not an Event! Data Capture and Planning Monitor and Access Analyze and Diagnose Recommend and Automate What and where are assets in the data center? How are they interconnected? Do we have space, cooling and power to meet future needs? How can I efficiently commission decommission? How are my assets operating? Am I getting real-time notification of alarms and alerts? How do I get my server back up and running? Can I populate my planning tools with actual performance data? How do I extend the life of the data center? How do I reduce mean time to repair (MTTR)? How do I synch infrastructure with virtualization automation? How are we doing against SLAs? How do I anticipate potential failures and automatically shift compute and physical load to eliminate downtime? How can I optimize efficiency across my data center? Improved Planning Early Warning (Reactive) Reduced MTTR and Effort Availability at Optimal Performance (Proactive) Different Entry Points Based On Customer Requirements To enable ability to SEE DECIDE - ACT
Manage Allocations and Equipment Features: Track data center inventory Visually track configuration of assets Manage power and data connections Manage capacities for space, power, cooling Extendable symbol library for all device types Search and locate within the data center Graphical floor and rack elevation plans Manage Projects with future reservations through Change Planner module Benefits: Allows a data center operator to find equipment quicker Allows the data center engineer to make quicker decisions on placement of new equipment Gives the data center manager an overview of the inventory deployed, the capacity available and the capacity remaining based on de-rated consumption data
Monitoring Features: Alarm/event management and notifications Collect and analyze realtime data Device operating status and data trends Set and report on energy limits by zone or rack Discover and import new devices Benefits: Provides effective and efficient use of personnel through focused attention on primary issues Reduces time required to identify and resolve issues with critical infrastructure devices
Manage the Power Infrastructure Features: Dependencies of the complete power system Power system resource utilization and capacity Active power path status Benefits: Comprehensive view of power system resource utilization and capacity Awareness of the active power path and the status of each device in the power system Understand the dependencies of the complete power system Visualization of aggregate status and capacity of paralleled power devices One-line Diagram
Mobile Suite Features: Image recognition for devices, bar code scanning Updates server in real time, manages changes when off-line Updates plan as actions are taken 3D Rendering Benefits: Audit at the rack, on the floor. Reduce human error See the impact of changes in real time to reduce the risk associated with change Connectivity to reporting and diagram information regardless of location Increase the agility and flexibility of staff
Process Manager Features: Automated ticketing system for task process management ability to assign, claim, suspend, withdraw Best Practice processes Process Configuration Ability to alter the flow of processes along with customizing and configuring your own processes Benefits: Improve data center efficiency and reduce errors saving cost and time Proactively plan for managing changes Continuous improvement of process
Chuck Kramer RCDD/NTS/CDCP/CDFOM Solutions Engineer Manager Emerson Network Power charles.kramer@emerson.com 484-467-0137 Questions