• No results found

Cheat Sheets to Data Center Infrastructure Management

N/A
N/A
Protected

Academic year: 2021

Share "Cheat Sheets to Data Center Infrastructure Management"

Copied!
8
0
0

Loading.... (view fulltext now)

Full text

(1)

Cheat Sheets to Data Center

Infrastructure Management

The Brands You Trust.

(2)

Table of Contents

Introduction ...3

How DCIM helps operations ...4

How DCIM helps planning ...5

How DCIM helps analytics ...6

(3)

Schneider Electric

3

Introduction

Once upon a time, a data center operator managed a 15 rack data center at a

small manufacturing firm. Because his facility was so small, he didn’t use any

physical infrastructure management tools. Instead, he felt confident in and relied

on the “tribal knowledge” he had acquired over the years. However, over time, his

15 racks became much denser. His energy bills went up and his cooling and power

systems drifted out of balance. At one point, when he added a new server, he

overloaded a branch circuit and took down an entire rack.

While this story begins with “once upon a time,” it is a true story, and illustrates just

one set of challenges in managing a data center without the right tools. Data center

infrastructure management (DCIM) tools enable organizations to plan, predict,

analyze, and ultimately drive down costs. Without DCIM tools, the business value

of the data center can improve only as far and as fast as the human brain will allow.

The following cheat sheets and illustrations provide a snapshot look at how DCIM

software can improve planning, operations and analytics.

Each cheat sheet addresses:

• Common questions answered by DCIM tools

• Functions that can be performed by DCIM software, and

• Examples of how DCIM can improve day-to-day operation as

well as long term planning and management

The illustrations provide examples of common workflows (ex. Load shifting,

inlet temperature setting, CRAC fan loss) that can be dramatically improved

with modern data center infrastructure management.

(4)

How DCIM helps

operations

Common questions that DCIM

operational tools answer

• What is my current workflow? • How can I address hot spots?

• What is the overall health of my data center? • I lost a fan on my CRAC. What do I do now? • My power capacity is exceeded on a rack, what

can I do?

• What is my PUE?

Operational functions that DCIM

software performs

• Track single & three phase equipment power draw, ensuring all three phases are balanced • Illustrate power path down to rack, including

measured load and rack capacity

• Report average and peak power usage by rack which helps ensure optimal placement of a new server

• Generate an audit trail for all changes to assets and work orders for a specified range of time, including a record of alarms raised and alarms removed

• Identify excess capacity and indicate which devices can either be decommissioned or used elsewhere

• Generate a power usage effectiveness (PUE) value on a daily basis and track historical PUE • Communicate power, cooling, rack and other physical infrastructure information directly to a VM manager to ensure physical hosts have “healthy” power and cooling resources

What can happen WITHOUT DCIM

software

• In a large financial data center, the provisioning and installation of servers became so complex that only highly paid engineers were able to do it.

• A data center manager in NY was concerned about provisioning a server in his London data center, and flew to London in order to place a Post-It® note on the rack position he wanted reserved, just to ensure the power and cooling could support the additional server.

• A mid-size data center was intentionally over-sizing their cooling capacity to avoid running out of cool-ing. They also had several servers underutilized. • A data center operator installed 9 new servers

in a nearly-empty rack. He checked that all the servers turned on and considered the installation a success. However, the next day the UPS had switched to bypass because the overnight load on the newly installed servers had peaked and over-loaded the UPS.

• A low criticality server was inadvertently installed in a high criticality rack (2N) instead of a rack with no redundancy. This error, discovered when decom-missioning the server, cost them 20 times more in electricity than necessary.

(5)

Schneider Electric

5

How DCIM helps

planning

Common questions that DCIM

planning tools answer

• Where does the next physical or virtual server get placed?

• Will I still have power or cooling redundancy under fault or maintenance conditions?

• Do I need to spread out my blade servers to get reliable operations?

• How will a new server impact the existing branch circuit?

• What will the impact of new equipment be on my redundancy and safety margins?

• Does the existing power and cooling equip-ment have the capacity to accommodate new technologies?

Planning functions that DCIM software

performs

• Provide graphical representations of IT equipment and its location in the rack

• Visually display the impact of pending moves and changes on power capacity and cooling distribu-tion

• Simulate the consequences of power and cooling device failure on IT equipment for identification of critical business application impacts

• Proactively manage within rack and floor tile weight limits

• Simulate cooling scenarios in the data center with computational fluid dynamics (CFD) approxima-tion

• Generate recommended installation locations for rack-mount IT equipment based on available power, cooling, space capacity, and network ports

What can happen WITHOUT DCIM

software

• A data center with no real process for deploying equipment learned through an assessment that they had numerous hotspots. The air distribution was insufficient, even though the bulk capacity was available.

• A rack of servers was lost when an IT administrator unintentionally overloaded an already maxed-out power strip.

• A data center with no asset management tool had IT equipment removed from a rack. Since no auto-mated tracking of rack assets occurred, significant time was wasted trying to locate the misappropri-ated equipment.

• A data center was using the failover mechanism of their virtualization platform (ability to migrate their virtual machines), but in their planning, they didn’t consider that the servers were all dependent on the same UPS. When the UPS failed, no UPS protect-ed servers were available to migrate the loads to. • A data center operator performed manual checks

(6)

How DCIM helps

analytics

Common questions that DCIM

planning tools answer

• What do I have in my data center?

• Who has touched which equipment and when? • Do I have stranded cooling and power capacity? • When will firmware have to be updated?

• By what date will the data center run out of power and cooling capacity? What will run out first?

• When should batteries be charged on the UPS? • When will the next large data center physical

infrastructure investment be necessary? • How can I predict the need for future

infrastruc-ture, investments and rollouts?

Analytics functions that DCIM software

performs

• Identify discrepancies between planned energy usage, based on nameplate information, and actual usage, based on actual power data • Generate inventory reports organized by device

type, age, manufacturer, and properties of the device

• Generate energy usage reports by subsystem • Provide energy use details that enable the linking

of operating costs to each business unit user group which then allows for “charge backs”

What can happen WITHOUT DCIM

software

• An air conditioner has sufficient capacity, but inad-equate air distribution to the IT load

• A PDU has sufficient capacity but no available breaker positions

• Floor space is available, but there is no remaining power

• Air conditioners are in the wrong location

• Some PDUs are overloaded while others are lightly loaded

(7)

Schneider Electric

7

Examples of how DCIM tools can improve traditional processes

Load Shifting

CRAC fan loss

(8)

References

Related documents

In Chapter V, we presents an advanced future temperature prediction model for each core to estimate the thermal behavior considering both core temperature and applications

and increase the efficiency of their compute resources in the same way that they use power usage effectiveness (PUE) to improve data center infrastructure. • CUE (Carbon

benchmark the Power Usage Effectiveness** (PUE), Data Centre Infrastructure Efficiency** (DCiE) and usage of the server room environment through direct analysis of power and

POWER USAGE EFFECTIVENESS Power Usage Effectiveness (PUE) is the measure of total data center power consumption divided by IT or ‘critical’ power, and highlights how much power

End to end data center infrastructure management software for monitoring and control of power, cooling, security and energy usage from the building through.. >

Therefore, this study aims to identify the positive and the negative politeness strategies that both genders use in making a rejection and also to compare, to what

Our methodology is based on (1) the identification and description of scientist’s points of view, (2) the construction of a generic conceptual model integrating

In fish meal no change can be found and in the main feed group of plant origin (excl. vegetable oils) and in feed additives the average dioxin and DL-PCB concentrations vary per