What are data center availability modes- Article 3

Click here to read previous - Article 2

10 Syska Hennessy Criticality Levels

ENR has ranked Syska Hennessy Group as one of the world’s top five in data-center engineering design for the last ten years. Syska’s Critical- ity Level concept is comparable in parts to data center “tier” levels used in the industry. These criticality or tier levels differentiate expected availability and reliability between sites that are designed, constructed, commissioned, maintained, and operated at different budget and priority levels. Whereas many earlier published tier classifications focused on power to the critical load, Syska’s Criticality Levels address everything that is important for availability of a critical facility. The best way to understand these 10 levels of standard is to compare with the uptime institutes tier levels. Let us understand that as below when comparing,

Syska Criticality	Uptime institute	Estimated % of availability	Expected Annual down time.
C1	Tier 1	98	20–40 hours
C2	Tier 2	99	10–25 hours
C3	Tier 3	99.9	1-15 hours
C4	Tier 4	99.99	0.25–1 hours
C5		99.999	1–20 minutes
C6		99.9999	1–15 hours
C7		99.99999
C8		99.999999
C9		99.9999999
C10		99.99999999

If you would like to understand more about Syska Hennessy standards read through here

PS: ENR specified on above notes is denoted for Engineering News-Record which is an American weekly magazine that provides news, analysis, data and opinion for the construction industry worldwide.

ANSI/BICSI Classes (F0-F4)

BICSI 002-2019 (Building Industry Consulting Service International) standard is written to be used as a standard for Data Centre Design and Implementation. Written by industry professionals from all major disciplines, this standard not only lists what a data center requires, but also provides ample recommendations on the best methods of implementing a design to fulfill your specific needs. These standards are used in conjunction with other multiple standards or publications such as ,

– TIA: 942, 568C, 569B,

– ISO/IEC:11801, 24764

– CENELEC: EN 50173, 50174

– NFPA: 70 (NEC®), 75

– ASHRAE: Datacom and Data Centre

– IEEE: 493, 1100 (Gold and Emerald Books) – EN 50600

There are 5 availability classes defined as per BICSI 002-2019 and those can be defined as below,

Availability Class 0 :The objective of Class 0 is to support the basic requirements of the IT functions without supplementary equipment. Capital cost avoidance is the major driver. There is a high risk of downtime because of planned and unplanned events.

Availability Class 1 :The objective of Class 1 is to support the basic requirements of the IT functions. There is a high risk of downtime because of planned and unplanned events. However, in Class 1 data centers, remedial maintenance can be performed during nonscheduled hours.

Availability Class 2 : The objective of Class 2 is to provide a level of reliability higher than that defined in Class 1 to reduce the risk of downtime because of component failure. In Class 2 data centers, there is a moderate risk of downtime as a result of planned and unplanned events. Maintenance activities can typically be performed during unscheduled hours.

Availability Class 3 : The objective of Class 3 is to provide additional reliability and maintainability to reduce the risk of downtime because of natural disasters, human-driven disasters, planned maintenance, and repair activities. Maintenance and repair activities will typically need to be performed during full production time with no opportunity for curtailed operations.

Availability Class 4 : The objective of Class 4 is to eliminate downtime through the application of all tactics to provide continuous operation regardless of planned or unplanned activities. All recognizable single points of failure are eliminated.

Below table is the simple representation of these fictional availability classes,

If you would like to understand more about BICSI Classesread through here 

Others: N, N+1, 2N, 2(N+1)

After all, the above are international standards that can be followed to achieve the highest redundancy and reliability for a data center infrastructure. These standard certifications are the proof to our clients that the facility achievements that you are following. The periodic auditing from certification authority will make sure that your facilities are most efficient on a frequent interval too. But what is the case when you want to  have your own small data centers that doesn’t required someone else surety for your facility? You have literally a small scale data center? Yes you can have this(the least case scenario that it will be followed on these days). 

All that you need is to have your own physical infrastructure(mainly power, cooling and connectivity)  that can be defined in terms of N, N+1, 2N, 2N+1, 2(N+1).

Concept is same as the things that we discussed in uptime institute Tier levels.

Nis simply the amount required for operation. For instance, a data center server may require one power supply operating at specific power ratings to keep the server running at optimal availability conditions.

N+Xrefers to a redundant system that contains X number of spare components to act as an independent backup when the appropriate component fails to operate as intended. N+1means that only one backup component is available to complementing the N original component(s). N+2means that two backup components are available to ensure additional resilience.

2Nmeans that you have two times the amount required for operation. You have two units of equal size, capabilities, and capacity. 2N+1means that you have two times the amount required for operation plus a backup.

Have a comment or points to be review? Knowledge is power and it increases by sharing. Feel free to comment.

What are data center availability modes - Article 1

Data center availability modes defines the availability of physical infrastructure in case of any failure. It’s quite obvious that some machines may get damage/stop working unexpectedly due to some unexpected incidents. Have you ever thought what will be the impact when this happens to a data center? Well as a computer engineer I would say that I will never imaging it incident since the impact can be nothing but stopping an entire business or partial business that are run on data center. In some instances machine damages can’t be predicted or controlled completely by humans. The best thing that we can do to avoid down time is to minimize the maximum risk factor by having multiple backup plans. Here is what the importance of data center availability modes which are the general standards to avoid any down time.

We will discuss the general standards followed by various data centers to avoid the challenges that may happen to physical infrastructure.

·     Uptime Institute Tiers (I-IV)

·     EN 50600 Availability classes (1-4)

·     TIA 942-B Ratings (1-4)

·     10 Syska Hennessy Criticality Levels

·     ANSI/BICSI Classes (F0-F4)

·     Others: N, N+1, 2N, 2(N+1)

Based on any one of the above data center standards, your DC design and operation will vary. 

Uptime Institute Tiers (I-IV)

Uptime Institute is the IT industry’s most trusted and adopted global standard for the proper design, build and operation of data centers. They evaluate data center infrastructure based on certain criteria and DC availability will be certified as per that. The Tier Classification System provides the data center industry with a consistent method to compare typically unique, customized facilities based on expected site infrastructure performance, or uptime. 

Uptime institute tier levels are mainly evaluated for 3 categories of a data center facility and namely Tier Certification Design Documents (TCDD), Tier Certification Constructed Facility (TCCF), Tier Certification Operational Sustainability (TCOS). Below are the various data center standards categorized by Uptime institute. 

Tier 1: A Tier 1 data centre have no redundant capacity components (single uplink and servers). It has an expected uptime of 99.671% (28.8 hours of downtime annually).

Tier 2: A Tier 2 data centre has a single path for power and cooling and some redundant and backup components. It has an expected uptime of 99.741% (22 hours of downtime annually).

Tier 3: A Tier 3 data centre has multiple paths for power, cooling and systems in place to update and maintain it without taking it offline. It has an expected uptime of 99.982% (1.6 hours of downtime annually). These data centers provides N+1 fault tolerant providing at least 72-hour power outage protection. This is the most adapted Tier levels that you can see throughout the world.

Tier 4: A Tier 4 data centre is built to be completely fault tolerant and has redundancy for every component including uplinks, storage, chillers, HVAC systems, servers etc. Everything is dual-powered. These data centers are 2N+1 fully redundant infrastructure. It has an expected uptime of 99.995% (26.3 minutes of downtime annually).

Have you noticed the letter ‘N’which is indicating the redundancy capability of data centers. Ever wonder what does it mean? 

Nis simply the amount required for operation. It represents the capacity that you need to operate. There is no backup system so if the system fails, it fails and downtime is the ultimate result. If you have a flat tire and no spare, you have N.

N+1represents the amount required for operation plus a backup. It ensures system availability even in the event of a component failure. It is similar to the concept of a spare time on your car. When you get a flat, you have the ability to swap out the flat with a spare tire. This simply means that you could survive one flat tire.

2N+1means that you have two times the amount required for operation plus a backup. This means that you have a full size spare tire plus a temporary spare tire just in case. That means that you could incur two flat tires and still operate.

Typically the uptime institute certifications will look like below,

Click here to continue reading - Article 2