Application Data Availability 4 3 2 1 Data Protection

Application Data Availability 4 3 2 1 Data Protection

4 3 2 1 data protection Application Data Availability Everything Is Not The Same

Application Data Availability 4 3 2 1 Data Protection

This is part two of a five-part mini-series looking at Application Data Value Characteristics everything is not the same as a companion excerpt from chapter 2 of my new book Software Defined Data Infrastructure Essentials – Cloud, Converged and Virtual Fundamental Server Storage I/O Tradecraft (CRC Press 2017). available at Amazon.com and other global venues. In this post, we continue looking at application performance, availability, capacity, economic (PACE) attributes that have an impact on data value as well as availability.

4 3 2 1 data protection  Book SDDC

Availability (Accessibility, Durability, Consistency)

Just as there are many different aspects and focus areas for performance, there are also several facets to availability. Note that applications performance requires availability and availability relies on some level of performance.

Availability is a broad and encompassing area that includes data protection to protect, preserve, and serve (backup/restore, archive, BC, BR, DR, HA) data and applications. There are logical and physical aspects of availability including data protection as well as security including key management (manage your keys or authentication and certificates) and permissions, among other things.

Availability = accessibility (can you get to your application and data) + durability (is the data intact and consistent). This includes basic Reliability, Availability, Serviceability (RAS), as well as high availability, accessibility, and durability. “Durable” has multiple meanings, so context is important. Durable means how data infrastructure resources hold up to, survive, and tolerate wear and tear from use (i.e., endurance), for example, Flash SSD or mechanical devices such as Hard Disk Drives (HDDs). Another context for durable refers to data, meaning how many copies in various places.

Server, storage, and I/O network availability topics include:

  • Resiliency and self-healing to tolerate failure or disruption
  • Hardware, software, and services configured for resiliency
  • Accessibility to reach or be reached for handling work
  • Durability and consistency of data to be available for access
  • Protection of data, applications, and assets including security

Additional server I/O and data infrastructure along with storage topics include:

  • Backup/restore, replication, snapshots, sync, and copies
  • Basic Reliability, Availability, Serviceability, HA, fail over, BC, BR, and DR
  • Alternative paths, redundant components, and associated software
  • Applications that are fault-tolerant, resilient, and self-healing
  • Non disruptive upgrades, code (application or software) loads, and activation
  • Immediate data consistency and integrity vs. eventual consistency
  • Virus, malware, and other data corruption or loss prevention

From a data protection standpoint, the fundamental rule or guideline is 4 3 2 1, which means having at least four copies consisting of at least three versions (different points in time), at least two of which are on different systems or storage devices and at least one of those is off-site (on-line, off-line, cloud, or other). There are many variations of the 4 3 2 1 rule shown in the following figure along with approaches on how to manage technology to use. We will go into deeper this subject in later chapters. For now, remember the following.

large version application server storage I/O
4 3 2 1 data protection (via Software Defined Data Infrastructure Essentials)

4    At least four copies of data (or more), Enables durability in case a copy goes bad, deleted, corrupted, failed device, or site.
3    The number (or more) versions of the data to retain, Enables various recovery points in time to restore, resume, restart from.
2    Data located on two or more systems (devices or media/mediums), Enables protection against device, system, server, file system, or other fault/failure.

1    With at least one of those copies being off-premise and not live (isolated from active primary copy), Enables resiliency across sites, as well as space, time, distance gap for protection.

Capacity and Space (What Gets Consumed and Occupied)

In addition to being available and accessible in a timely manner (performance), data (and applications) occupy space. That space is memory in servers, as well as using available consumable processor CPU time along with I/O (performance) including over networks.

Data and applications also consume storage space where they are stored. In addition to basic data space, there is also space consumed for metadata as well as protection copies (and overhead), application settings, logs, and other items. Another aspect of capacity includes network IP ports and addresses, software licenses, server, storage, and network bandwidth or service time.

Server, storage, and I/O network capacity topics include:

  • Consumable time-expiring resources (processor time, I/O, network bandwidth)
  • Network IP and other addresses
  • Physical resources of servers, storage, and I/O networking devices
  • Software licenses based on consumption or number of users
  • Primary and protection copies of data and applications
  • Active and standby data infrastructure resources and sites
  • Data footprint reduction (DFR) tools and techniques for space optimization
  • Policies, quotas, thresholds, limits, and capacity QoS
  • Application and database optimization

DFR includes various techniques, technologies, and tools to reduce the impact or overhead of protecting, preserving, and serving more data for longer periods of time. There are many different approaches to implementing a DFR strategy, since there are various applications and data.

Common DFR techniques and technologies include archiving, backup modernization, copy data management (CDM), clean up, compress, and consolidate, data management, deletion and dedupe, storage tiering, RAID (including parity-based, erasure codes , local reconstruction codes [LRC] , and Reed-Solomon , Ceph Shingled Erasure Code (SHEC ), among others), along with protection configurations along with thin-provisioning, among others.

DFR can be implemented in various complementary locations from row-level compression in database or email to normalized databases, to file systems, operating systems, appliances, and storage systems using various techniques.

Also, keep in mind that not all data is the same; some is sparse, some is dense, some can be compressed or deduped while others cannot. Likewise, some data may not be compressible or dedupable. However, identical copies can be identified with links created to a common copy.

Economics (People, Budgets, Energy and other Constraints)

If one thing in life and technology that is constant is change, then the other constant is concern about economics or costs. There is a cost to enable and maintain a data infrastructure on premise or in the cloud, which exists to protect, preserve, and serve data and information applications.

However, there should also be a benefit to having the data infrastructure to house data and support applications that provide information to users of the services. A common economic focus is what something costs, either as up-front capital expenditure (CapEx) or as an operating expenditure (OpEx) expense, along with recurring fees.

In general, economic considerations include:

  • Budgets (CapEx and OpEx), both up front and in recurring fees
  • Whether you buy, lease, rent, subscribe, or use free and open sources
  • People time needed to integrate and support even free open-source software
  • Costs including hardware, software, services, power, cooling, facilities, tools
  • People time includes base salary, benefits, training and education

Where to learn more

Learn more about Application Data Value, application characteristics, PACE along with data protection, software defined data center (SDDC), software defined data infrastructures (SDDI) and related topics via the following links:

SDDC Data Infrastructure

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What this all means and wrap-up

Keep in mind that with Application Data Value Characteristics Everything Is Not The Same across various organizations, data centers, data infrastructures spanning legacy, cloud and other software defined data center (SDDC) environments. All applications have some element of performance, availability, capacity, economic (PACE) needs as well as resource demands. There is often a focus around data storage about storage efficiency and utilization which is where data footprint reduction (DFR) techniques, tools, trends and as well as technologies address capacity requirements. However with data storage there is also an expanding focus around storage effectiveness also known as productivity tied to performance, along with availability including 4 3 2 1 data protection. Continue reading the next post (Part III Application Data Characteristics Types Everything Is Not The Same) in this series here.

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

Application Data Characteristics Types Everything Is Not The Same

Application Data Characteristics Types Everything Is Not The Same

Application Data Characteristics Types Everything Is Not The Same

Application Data Characteristics Types Everything Is Not The Same

This is part three of a five-part mini-series looking at Application Data Value Characteristics everything is not the same as a companion excerpt from chapter 2 of my new book Software Defined Data Infrastructure Essentials – Cloud, Converged and Virtual Fundamental Server Storage I/O Tradecraft (CRC Press 2017). available at Amazon.com and other global venues. In this post, we continue looking at application and data characteristics with a focus on different types of data. There is more to data than simply being big data, fast data, big fast or unstructured, structured or semistructured, some of which has been touched on in this series, with more to follow. Note that there is also data in terms of the programs, applications, code, rules, policies as well as configuration settings, metadata along with other items stored.

Application Data Value Software Defined Data Infrastructure Essentials Book SDDC

Various Types of Data

Data types along with characteristics include big data, little data, fast data, and old as well as new data with a different value, life-cycle, volume and velocity. There are data in files and objects that are big representing images, figures, text, binary, structured or unstructured that are software defined by the applications that create, modify and use them.

There are many different types of data and applications to meet various business, organization, or functional needs. Keep in mind that applications are based on programs which consist of algorithms and data structures that define the data, how to use it, as well as how and when to store it. Those data structures define data that will get transformed into information by programs while also being stored in memory and on data stored in various formats.

Just as various applications have different algorithms, they also have different types of data. Even though everything is not the same in all environments, or even how the same applications get used across various organizations, there are some similarities. Even though there are different types of applications and data, there are also some similarities and general characteristics. Keep in mind that information is the result of programs (applications and their algorithms) that process data into something useful or of value.

Data typically has a basic life cycle of:

  • Creation and some activity, including being protected
  • Dormant, followed by either continued activity or going inactive
  • Disposition (delete or remove)

In general, data can be

  • Temporary, ephemeral or transient
  • Dynamic or changing (“hot data”)
  • Active static on-line, near-line, or off-line (“warm-data”)
  • In-active static on-line or off-line (“cold data”)

Data is organized

  • Structured
  • Semi-structured
  • Unstructured

General data characteristics include:

  • Value = From no value to unknown to some or high value
  • Volume = Amount of data, files, objects of a given size
  • Variety = Various types of data (small, big, fast, structured, unstructured)
  • Velocity = Data streams, flows, rates, load, process, access, active or static

The following figure shows how different data has various values over time. Data that has no value today or in the future can be deleted, while data with unknown value can be retained.

Different data with various values over time

Application Data Value across sddc
Data Value Known, Unknown and No Value

General characteristics include the value of the data which in turn determines its performance, availability, capacity, and economic considerations. Also, data can be ephemeral (temporary) or kept for longer periods of time on persistent, non-volatile storage (you do not lose the data when power is turned off). Examples of temporary scratch include work and scratch areas such as where data gets imported into, or exported out of, an application or database.

Data can also be little, big, or big and fast, terms which describe in part the size as well as volume along with the speed or velocity of being created, accessed, and processed. The importance of understanding characteristics of data and how their associated applications use them is to enable effective decision-making about performance, availability, capacity, and economics of data infrastructure resources.

Data Value

There is more to data storage than how much space capacity per cost.

All data has one of three basic values:

  • No value = ephemeral/temp/scratch = Why keep it?
  • Some value = current or emerging future value, which can be low or high = Keep
  • Unknown value = protect until value is unlocked, or no remaining value

In addition to the above basic three, data with some value can also be further subdivided into little value, some value, or high value. Of course, you can keep subdividing into as many more or different categories as needed, after all, everything is not always the same across environments.

Besides data having some value, that value can also change by increasing or decreasing in value over time or even going from unknown to a known value, known to unknown, or to no value. Data with no value can be discarded, if in doubt, make and keep a copy of that data somewhere safe until its value (or lack of value) is fully known and understood.

The importance of understanding the value of data is to enable effective decision-making on where and how to protect, preserve, and cost-effectively store the data. Note that cost-effective does not necessarily mean the cheapest or lowest-cost approach, rather it means the way that aligns with the value and importance of the data at a given point in time.

Where to learn more

Learn more about Application Data Value, application characteristics, PACE along with data protection, software-defined data center (SDDC), software-defined data infrastructures (SDDI) and related topics via the following links:

SDDC Data Infrastructure

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What this all means and wrap-up

Data has different value at various times, and that value is also evolving. Everything Is Not The Same across various organizations, data centers, data infrastructures spanning legacy, cloud and other software defined data center (SDDC) environments. Continue reading the next post (Part IV Application Data Volume Velocity Variety Everything Not The Same) in this series here.

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

Application Data Volume Velocity Variety Everything Is Not The Same

Application Data Volume Velocity Variety Everything Not The Same

Application Data Volume Velocity Variety Everything Is Not The Same

Application Data Volume Velocity Variety Everything Not The Same

This is part four of a five-part mini-series looking at Application Data Value Characteristics everything is not the same as a companion excerpt from chapter 2 of my new book Software Defined Data Infrastructure Essentials – Cloud, Converged and Virtual Fundamental Server Storage I/O Tradecraft (CRC Press 2017). available at Amazon.com and other global venues. In this post, we continue looking at application and data characteristics with a focus on data volume velocity and variety, after all, everything is not the same, not to mention many different aspects of big data as well as little data.

Application Data Value Software Defined Data Infrastructure Essentials Book SDDC

Volume of Data

More data is growing at a faster rate every day, and that data is being retained for longer periods. Some data being retained has known value, while a growing amount of data has an unknown value. Data is generated or created from many sources, including mobile devices, social networks, web-connected systems or machines, and sensors including IoT and IoD. Besides where data is created from, there are also many consumers of data (applications) that range from legacy to mobile, cloud, IoT among others.

Unknown-value data may eventually have value in the future when somebody realizes that he can do something with it, or a technology tool or application becomes available to transform the data with unknown value into valuable information.

Some data gets retained in its native or raw form, while other data get processed by application program algorithms into summary data, or is curated and aggregated with other data to be transformed into new useful data. The figure below shows, from left to right and front to back, more data being created, and that data also getting larger over time. For example, on the left are two data items, objects, files, or blocks representing some information.

In the center of the following figure are more columns and rows of data, with each of those data items also becoming larger. Moving farther to the right, there are yet more data items stacked up higher, as well as across and farther back, with those items also being larger. The following figure can represent blocks of storage, files in a file system, rows, and columns in a database or key-value repository, or objects in a cloud or object storage system.

Application Data Value sddc
Increasing data velocity and volume, more data and data getting larger

In addition to more data being created, some of that data is relatively small in terms of the records or data structure entities being stored. However, there can be a large quantity of those smaller data items. In addition to the amount of data, as well as the size of the data, protection or overhead copies of data are also kept.

Another dimension is that data is also getting larger where the data structures describing a piece of data for an application have increased in size. For example, a still photograph was taken with a digital camera, cell phone, or another mobile handheld device, drone, or other IoT device, increases in size with each new generation of cameras as there are more megapixels.

Variety of Data

In addition to having value and volume, there are also different varieties of data, including ephemeral (temporary), persistent, primary, metadata, structured, semi-structured, unstructured, little, and big data. Keep in mind that programs, applications, tools, and utilities get stored as data, while they also use, create, access, and manage data.

There is also primary data and metadata, or data about data, as well as system data that is also sometimes referred to as metadata. Here is where context comes into play as part of tradecraft, as there can be metadata describing data being used by programs, as well as metadata about systems, applications, file systems, databases, and storage systems, among other things, including little and big data.

Context also matters regarding big data, as there are applications such as statistical analysis software and Hadoop, among others, for processing (analyzing) large amounts of data. The data being processed may not be big regarding the records or data entity items, but there may be a large volume. In addition to big data analytics, data, and applications, there is also data that is very big (as well as large volumes or collections of data sets).

For example, video and audio, among others, may also be referred to as big fast data, or large data. A challenge with larger data items is the complexity of moving over the distance promptly, as well as processing requiring new approaches, algorithms, data structures, and storage management techniques.

Likewise, the challenges with large volumes of smaller data are similar in that data needs to be moved, protected, preserved, and served cost-effectively for long periods of time. Both large and small data are stored (in memory or storage) in various types of data repositories.

In general, data in repositories is accessed locally, remotely, or via a cloud using:

  • Object and blobs stream, queue, and Application Programming Interface (API)
  • File-based using local or networked file systems
  • Block-based access of disk partitions, LUNs (logical unit numbers), or volumes

The following figure shows varieties of application data value including (left) photos or images, audio, videos, and various log, event, and telemetry data, as well as (right) sparse and dense data.

Application Data Value bits bytes blocks blobs bitstreams sddc
Varieties of data (bits, bytes, blocks, blobs, and bitstreams)

Velocity of Data

Data, in addition to having value (known, unknown, or none), volume (size and quantity), and variety (structured, unstructured, semi structured, primary, metadata, small, big), also has velocity. Velocity refers to how fast (or slowly) data is accessed, including being stored, retrieved, updated, scanned, or if it is active (updated, or fixed static) or dormant and inactive. In addition to data access and life cycle, velocity also refers to how data is used, such as random or sequential or some combination. Think of data velocity as how data, or streams of data, flow in various ways.

Velocity also describes how data is used and accessed, including:

  • Active (hot), static (warm and WORM), or dormant (cold)
  • Random or sequential, read or write-accessed
  • Real-time (online, synchronous) or time-delayed

Why this matters is that by understanding and knowing how applications use data, or how data is accessed via applications, you can make informed decisions. Also, having insight enables how to design, configure, and manage servers, storage, and I/O resources (hardware, software, services) to meet various needs. Understanding Application Data Value including the velocity of the data both for when it is created as well as when used is important for aligning the applicable performance techniques and technologies.

Where to learn more

Learn more about Application Data Value, application characteristics, performance, availability, capacity, economic (PACE) along with data protection, software-defined data center (SDDC), software-defined data infrastructures (SDDI) and related topics via the following links:

SDDC Data Infrastructure

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What this all means and wrap-up

Data has different value, size, as well as velocity as part of its characteristic including how used by various applications. Keep in mind that with Application Data Value Characteristics Everything Is Not The Same across various organizations, data centers, data infrastructures spanning legacy, cloud and other software defined data center (SDDC) environments. Continue reading the next post (Part V Application Data Access life cycle Patterns Everything Is Not The Same) in this series here.

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

Application Data Access Lifecycle Patterns Everything Is Not The Same

Application Data Access Life cycle Patterns Everything Is Not The Same(Part V)

Application Data Access Life cycle Patterns Everything Is Not The Same

Application Data Access Life cycle Patterns Everything Is Not The Same

This is part five of a five-part mini-series looking at Application Data Value Characteristics everything is not the same as a companion excerpt from chapter 2 of my new book Software Defined Data Infrastructure Essentials – Cloud, Converged and Virtual Fundamental Server Storage I/O Tradecraft (CRC Press 2017). available at Amazon.com and other global venues. In this post, we look at various application and data lifecycle patterns as well as wrap up this series.

Application Data Value Software Defined Data Infrastructure Essentials Book SDDC

Active (Hot), Static (Warm and WORM), or Dormant (Cold) Data and Lifecycles

When it comes to Application Data Value, a common question I hear is why not keep all data?

If the data has value, and you have a large enough budget, why not? On the other hand, most organizations have a budget and other constraints that determine how much and what data to retain.

Another common question I get asked (or told) it isn’t the objective to keep less data to cut costs?

If the data has no value, then get rid of it. On the other hand, if data has value or unknown value, then find ways to remove the cost of keeping more data for longer periods of time so its value can be realized.

In general, the data life cycle (called by some cradle to grave, birth or creation to disposition) is created, save and store, perhaps update and read with changing access patterns over time, along with value. During that time, the data (which includes applications and their settings) will be protected with copies or some other technique, and eventually disposed of.

Between the time when data is created and when it is disposed of, there are many variations of what gets done and needs to be done. Considering static data for a moment, some applications and their data, or data and their applications, create data which is for a short period, then goes dormant, then is active again briefly before going cold (see the left side of the following figure). This is a classic application, data, and information life-cycle model (ILM), and tiering or data movement and migration that still applies for some scenarios.

Application Data Value
Changing data access patterns for different applications

However, a newer scenario over the past several years that continues to increase is shown on the right side of the above figure. In this scenario, data is initially active for updates, then goes cold or WORM (Write Once/Read Many); however, it warms back up as a static reference, on the web, as big data, and for other uses where it is used to create new data and information.

Data, in addition to its other attributes already mentioned, can be active (hot), residing in a memory cache, buffers inside a server, or on a fast storage appliance or caching appliance. Hot data means that it is actively being used for reads or writes (this is what the term Heat map pertains to in the context of the server, storage data, and applications. The heat map shows where the hot or active data is along with its other characteristics.

Context is important here, as there are also IT facilities heat maps, which refer to physical facilities including what servers are consuming power and generating heat. Note that some current and emerging data center infrastructure management (DCIM) tools can correlate the physical facilities power, cooling, and heat to actual work being done from an applications perspective. This correlated or converged management view enables more granular analysis and effective decision-making on how to best utilize data infrastructure resources.

In addition to being hot or active, data can be warm (not as heavily accessed) or cold (rarely if ever accessed), as well as online, near-line, or off-line. As their names imply, warm data may occasionally be used, either updated and written, or static and just being read. Some data also gets protected as WORM data using hardware or software technologies. WORM (immutable) data, not to be confused with warm data, is fixed or immutable (cannot be changed).

When looking at data (or storage), it is important to see when the data was created as well as when it was modified. However, you should avoid the mistake of looking only at when it was created or modified: Instead, also look to see when it was the last read, as well as how often it is read. You might find that some data has not been updated for several years, but it is still accessed several times an hour or minute. Also, keep in mind that the metadata about the actual data may be being updated, even while the data itself is static.

Also, look at your applications characteristics as well as how data gets used, to see if it is conducive to caching or automated tiering based on activity, events, or time. For example, there is a large amount of data for an energy or oil exploration project that normally sits on slower lower-cost storage, but that now and then some analysis needs to run on.

Using data and storage management tools, given notice or based on activity, which large or big data could be promoted to faster storage, or applications migrated to be closer to the data to speed up processing. Another example is weekly, monthly, quarterly, or year-end processing of financial, accounting, payroll, inventory, or enterprise resource planning (ERP) schedules. Knowing how and when the applications use the data, which is also understanding the data, automated tools, and policies, can be used to tier or cache data to speed up processing and thereby boost productivity.

All applications have performance, availability, capacity, economic (PACE) attributes, however:

  • PACE attributes vary by Application Data Value and usage
  • Some applications and their data are more active than others
  • PACE characteristics may vary within different parts of an application
  • PACE application and data characteristics along with value change over time

Read more about Application Data Value, PACE and application characteristics in Software Defined Data Infrastructure Essentials (CRC Press 2017).

Where to learn more

Learn more about Application Data Value, application characteristics, PACE along with data protection, software defined data center (SDDC), software defined data infrastructures (SDDI) and related topics via the following links:

SDDC Data Infrastructure

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What this all means and wrap-up

Keep in mind that Application Data Value everything is not the same across various organizations, data centers, data infrastructures, data and the applications that use them.

Also keep in mind that there is more data being created, the size of those data items, files, objects, entities, records are also increasing, as well as the speed at which they get created and accessed. The challenge is not just that there is more data, or data is bigger, or accessed faster, it’s all of those along with changing value as well as diverse applications to keep in perspective. With new Global Data Protection Regulations (GDPR) going into effect May 25, 2018, now is a good time to assess and gain insight into what data you have, its value, retention as well as disposition policies.

Remember, there are different data types, value, life-cycle, volume and velocity that change over time, and with Application Data Value Everything Is Not The Same, so why treat and manage everything the same?

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

Veeam GDPR preparedness experiences Webinar walking the talk

Veeam GDPR preparedness experiences Webinar walking the talk

Veeam GDPR I/O data infrastructure trends

Veeam GDPR preparedness experiences Fireside chat Webinar

March 27, 9AM PT
This free (register here) fireside chat webinar sponsored by Veeam looks at Veeam GDPR preparedness experiences based on what Veeam did to be ready for the May 25, 2018 Global Data Protection Regulations taking effect. The format of this webinar will be fireside chat between myself and Danny Allan (@DannyAllan5) of Veeam as we discuss the experiences, lessons learned by Veeam during their journey to prepare for GDPR.

Danny has put together a five-part blog series here covering some of Veeams findings and lessons learned that you can leverage to prepare for GDPR, as well as what we will discuss among other related topics during the fireside chat webinar. Keep in mind that GDPR is commonly mistaken as just an European regulation when in fact it is global. In addition to being global, it is also inclusive of big as well as small organizations, cloud and non cloud entities, as well as spanning industries, along with different parts of an organization from human resources (HR) to accounting and finance to sales, marketing among others.

veeam gdpr SDDC Data Infrastructure Data Protection

Join me and Danny Allan as we discuss GDPR along with five key lessons learned during Veeams road to GDPR compliance, as well as how their software solutions played a critical role in managing their own environment. In other words, Veeam is not just talking the talk, they are also walking the talk, eating their own dog food among other clichés.

Register for the event, or catch the replay here.

Where to learn more

Learn more about data protection, GDPR, software defined data center (SDDC), software defined data infrastructures (SDDI), cloud and related topics via the following links:

SDDC Data Infrastructure

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What this all means and wrap-up

Now is the time to be prepared for upcoming GDPR implementation. Join me and Danny Allan to learn what you need to be doing now, as well as compare what you have done or are doing to be prepared for GDPR.

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

World Backup Day 2018 Data Protection Readiness Reminder

World Backup Day 2018 Data Protection Readiness Reminder

server storage I/O trends

It’s that time of year again, World Backup Day 2018 Data Protection Readiness Reminder.

In case you have forgotten, or were not aware, this coming Saturday March 31 is World Backup (and recovery day). The annual day is a to remember to make sure you are protecting your applications, data, information, configuration settings as well as data infrastructures. While the emphasis is on Backup, that also means recovery as well as testing to make sure everything is working properly.

data infrastructure data protection

Its time that the focus of world backup day should expand from just a focus on backup to also broader data protection and things that start with R. Some data protection (and backup) related things, tools, tradecraft techniques, technologies and trends that start with R include readiness, recovery, reconstruct, restore, restart, resume, replication, rollback, roll forward, RAID and erasure codes, resiliency, recovery time objective (RTO), recovery point objective (RPO), replication among others.

data protection threats ransomware software defined

Keep in mind that Data Protection is a broader focus than just backup and recovery. Data protection includes disaster recovery DR, business continuance BC, business resiliency BR, security (logical and physical), standard and high availability HA, as well as durability, archiving, data footprint reduction, copy data management CDM along with various technologies, tradecraft techniques, tools.

data protection 4 3 2 1 rule and 3 2 1 rule

Quick Data Protection, Backup and Recovery Checklist

  • Keep the 4 3 2 1 or shorter older 3 2 1 data protection rules in mind
  • Do you know what data, applications, configuration settings, meta data, keys, certificates are being protected?
  • Do you know how many versions, copies, where stored and what is on or off-site, on or off-line?
  • Implement data protection at different intervals and coverage of various layers (application, transaction, database, file system, operating system, hypervisors, device or volume among others)
  • data infrastructure backup data protection

  • Have you protected your data protection environment including software, configuration, catalogs, indexes, databases along with management tools?
  • Verify that data protection point in time copies (backups, snapshots, consistency points, checkpoints, version, replicas) are working as intended
  • Make sure that not only are the point in time protection copies running when scheduled, also that they are protected what’s intended
  • data infrastructure backup data protection

  • Test to see if the protection copies can actually be used, this means restoring as well as accessing the data via applications
  • Watch out to prevent a disaster in the course of testing, plan, prepare, practice, learn, refine, improve
  • In addition to verifying your data protection (backup, bc, dr) for work, also take time to see how your home or personal data is protected
  • View additional tips, techniques, checklist items in this Data Protection fundamentals series of posts here.

storageio data protection toolbox

Where To Learn More

View additional Data Infrastructure Data Protection and related tools, trends, technology and tradecraft skills topics via the following links.

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What This All Means

You can not go forward if you can not go back to a particular point in time (e.g. recovery point objective or RPO). Likewise, if you can not go back to a given RPO, how can you go forward with your business as well as meet your recovery time objective (RTO)?

data protection restore rto rpo

Backup is as important as restore, without a good backup or data protection point in time copy, how can you restore? Some will say backup is more important than recovery, however its the enablement that matters, in other words being able to provide data protection and recover, restart, resume or other things that start with R. World backup day should be a reminder to think about broader data protection which also means recovery, restore and realizing if your copies and versions are good. Keep the above in mind and this is your World Backup Day 2018 Data Protection Readiness Reminder.

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

Use Intel Optane NVMe U.2 SFF 8639 SSD drive in PCIe slot

Use NVMe U.2 SFF 8639 disk drive form factor SSD in PCIe slot

server storage I/O data infrastructure trends

Need to install or use an Intel Optane NVMe 900P or other Nonvolatile Memory (NVM) Express NVMe based U.2 SFF 8639 disk drive form factor Solid State Device (SSD) into PCIe a slot?

For example, I needed to connect an Intel Optane NVMe 900P U.2 SFF 8639 drive form factor SSD into one of my servers using an available PCIe slot.

The solution I used was an carrier adapter card such as those from Ableconn (PEXU2-132 NVMe 2.5-inch U.2 [SFF-8639] via Amazon.com among other global venues.

xxxx
Top Intel 750 NVMe PCIe AiC SSD, bottom Intel Optane NVMe 900P U.2 SSD with Ableconn carrier

The above image shows top an Intel 750 NVMe PCIe Add in Card (AiC) SSD and on the bottom an Intel Optane NVMe 900P 280GB U.2 (SFF 8639) drive form factor SSD mounted on an Ableconn carrier adapter.

NVMe server storage I/O sddc

NVMe Tradecraft Refresher

NVMe is the protocol that is implemented with different topologies including local via PCIe using U.2 aka SFF-8639 (aka disk drive form factor), M.2 aka Next Generation Form Factor (NGFF) also known as "gum stick", along with PCIe Add in Card (AiC). NVMe accessed devices can be installed in laptops, ultra books, workstations, servers and storage systems using the various form factors. U.2 drives are also refereed to by some as PCIe drives in that the NVMe command set protocol is implemented using PCIe x4 physical connection to the devices. Jump ahead if you want to skip over the NVMe primer refresh material to learn more about U.2 8639 devices.

data infrastructure nvme u.2 8639 ssd
Various SSD device form factors and interfaces

In addition to form factor, NVMe devices can be direct attached and dedicated, rack and shared, as well as accessed via networks also known as fabrics such as NVMe over Fabrics.

NVMeoF FC-NVMe NVMe fabric SDDC
The many facets of NVMe as a front-end, back-end, direct attach and fabric

Context is important with NVMe in that fabric can mean NVMe over Fibre Channel (FC-NVMe) where the NVMe command set protocol is used in place of SCSI Fibre Channel Protocol (e.g. SCSI_FCP) aka FCP or what many simply know and refer to as Fibre Channel. NVMe over Fabric can also mean NVMe command set implemented over an RDMA over Converged Ethernet (RoCE) based network.

NVM and NVMe accessed flash SCM SSD storage

Another point of context is not to confuse Nonvolatile Memory (NVM) which are the storage or memory media and NVMe which is the interface for accessing storage (e.g. similar to SAS, SATA and others). As a refresher, NVM or the media are the various persistent memories (PM) including NVRAM, NAND Flash, 3D XPoint along with other storage class memories (SCM) used in SSD (in various packaging).

Learn more about 3D XPoint with the following resources:

Learn more (or refresh) your NVMe server storage I/O knowledge, experience tradecraft skill set with this post here. View this piece here looking at NVM vs. NVMe and how one is the media where data is stored, while the other is an access protocol (e.g. NVMe). Also visit www.thenvmeplace.com to view additional NVMe tips, tools, technologies, and related resources.

NVMe U.2 SFF-8639 aka 8639 SSD

On quick glance, an NVMe U.2 SFF-8639 SSD may look like a SAS small form factor (SFF) 2.5" HDD or SSD. Also, keep in mind that HDD and SSD with SAS interface have a small tab to prevent inserting them into a SATA port. As a reminder, SATA devices can plug into SAS ports, however not the other way around which is what the key tab function does (prevents accidental insertion of SAS into SATA). Looking at the left-hand side of the following image you will see an NVMe SFF 8639 aka U.2 backplane connector which looks similar to a SAS port.

Note that depending on how implemented including its internal controller, flash translation layer (FTL), firmware and other considerations, an NVMe U.2 or 8639 x4 SSD should have similar performance to a comparable NVMe x4 PCIe AiC (e.g. card) device. By comparable device, I mean the same type of NVM media (e.g. flash or 3D XPoint), FTL and controller. Likewise generally an PCIe x8 should be faster than an x4, however more PCIe lanes does not mean more performance, its what’s inside and how those lanes are actually used that matter.

NVMe U.2 8639 2.5" 1.8" SSD driveNVMe U.2 8639 2.5 1.8 SSD drive slot pin
NVMe U.2 SFF 8639 Drive (Software Defined Data Infrastructure Essentials CRC Press)

With U.2 devices the key tab that prevents SAS drives from inserting into a SATA port is where four pins that support PCIe x4 are located. What this all means is that a U.2 8639 port or socket can accept an NVMe, SAS or SATA device depending on how the port is configured. Note that the U.2 8639 port is either connected to a SAS controller for SAS and SATA devices or a PCIe port, riser or adapter.

On the left of the above figure is a view towards the backplane of a storage enclosure in a server that supports SAS, SATA, and NVMe (e.g. 8639). On the right of the above figure is the connector end of an 8639 NVM SSD showing addition pin connectors compared to a SAS or SATA device. Those extra pins give PCIe x4 connectivity to the NVMe devices. The 8639 drive connectors enable a device such as an NVM, or NAND flash SSD to share a common physical storage enclosure with SAS and SATA devices, including optional dual-pathing.

More PCIe lanes may not mean faster performance, verify if those lanes (e.g. x4 x8 x16 etc) are present just for mechanical (e.g. physical) as well as electrical (they are also usable) and actually being used. Also, note that some PCIe storage devices or adapters might be for example an x8 for supporting two channels or devices each at x4. Likewise, some devices might be x16 yet only support four x4 devices.

NVMe U.2 SFF 8639 PCIe Drive SSD FAQ

Some common questions pertaining NVMe U.2 aka SFF 8639 interface and form factor based SSD include:

Why use U.2 type devices?

Compatibility with what’s available for server storage I/O slots in a server, appliance, storage enclosure. Ability to mix and match SAS, SATA and NVMe with some caveats in the same enclosure. Support higher density storage configurations maximizing available PCIe slots and enclosure density.

Is PCIe x4 with NVMe U.2 devices fast enough?

While not as fast as a PCIe AiC that fully supports x8 or x16 or higher, an x4 U.2 NVMe accessed SSD should be plenty fast for many applications. If you need more performance, then go with a faster AiC card.

Why not go with all PCIe AiC?

If you need the speed, simplicity, have available PCIe card slots, then put as many of those in your systems or appliances as possible. Otoh, some servers or appliances are PCIe slot constrained so U.2 devices can be used to increase the number of devices attached to a PCIe backplane while also supporting SAS, SATA based SSD or HDDs.

Why not use M.2 devices?

If your system or appliances supports NVMe M.2 those are good options. Some systems even support a combination of M.2 for local boot, staging, logs, work and other storage space while PCIe AiC are for performance along with U.2 devices.

Why not use NVMeoF?

Good question, why not, that is, if your shared storage system supports NVMeoF or FC-NVMe go ahead and use that, however, you might also need some local NVMe devices. Likewise, if yours is a software-defined storage platform that needs local storage, then NVMe U.2, M.2 and AiC or custom cards are an option. On the other hand, a shared fabric NVMe based solution may support a mixed pool of SAS, SATA along with NVMe U.2, M.2, AiC or custom cards as its back-end storage resources.

When not to use U.2?

If your system, appliance or enclosure does not support U.2 and you do not have a need for it. Or, if you need more performance such as from an x8 or x16 based AiC, or you need shared storage. Granted a shared storage system may have U.2 based SSD drives as back-end storage among other options.

How does the U.2 backplane connector attach to PCIe?

Via enclosures backplane, there is either a direct hardwire connection to the PCIe backplane, or, via a connector cable to a riser card or similar mechanism.

Does NVMe replace SAS, SATA or Fibre Channel as an interface?

The NVMe command set is an alternative to the traditional SCSI command set used in SAS and Fibre Channel. That means it can replace, or co-exist depending on your needs and preferences for access various storage devices.

Who supports U.2 devices?

Dell has supported U.2 aka PCIe drives in some of their servers for many years, as has Intel and many others. Likewise, U.2 8639 SSD drives including 3D Xpoint and NAND flash-based are available from Intel among others.

Can you have AiC, U.2 and M.2 devices in the same system?

If your server or appliance or storage system support them then yes. Likewise, there are M.2 to PCIe AiC, M.2 to SATA along with other adapters available for your servers, workstations or software-defined storage system platform.

NVMe U.2 carrier to PCIe adapter

The following images show examples of mounting an Intel Optane NVMe 900P accessed U.2 8639 SSD on an Ableconn PCIe AiC carrier. Once U.2 SSD is mounted, the Ableconn adapter inserts into an available PCIe slot similar to other AiC devices. From a server or storage appliances software perspective, the Ableconn is a pass-through device so your normal device drivers are used, for example VMware vSphere ESXi 6.5 recognizes the Intel Optane device, similar with Windows and other operating systems.

intel optane 900p u.2 8639 nvme drive bottom view
Intel Optane NVMe 900P U.2 SSD and Ableconn PCIe AiC carrier

The above image shows the Ableconn adapter carrier card along with NVMe U.2 8639 pins on the Intel Optane NVMe 900P.

intel optane 900p u.2 8639 nvme drive end view
Views of Intel Optane NVMe 900P U.2 8639 and Ableconn carrier connectors

The above image shows an edge view of the NVMe U.2 SFF 8639 Intel Optane NVMe 900P SSD along with those on the Ableconn adapter carrier. The following images show an Intel Optane NVMe 900P SSD installed in a PCIe AiC slot using an Ableconn carrier, along with how VMware vSphere ESXi 6.5 sees the device using plug and play NVMe device drivers.

NVMe U.2 8639 installed in PCIe AiC Slot
Intel Optane NVMe 900P U.2 SSD installed in PCIe AiC Slot

NVMe U.2 8639 and VMware vSphere ESXi
How VMware vSphere ESXi 6.5 sees NVMe U.2 device

Intel NVMe Optane NVMe 3D XPoint based and other SSDs

Here are some Amazon.com links to various Intel Optane NVMe 3D XPoint based SSDs in different packaging form factors:

Here are some Amazon.com links to various Intel and other vendor NAND flash based NVMe accessed SSDs including U.2, M.2 and AiC form factors:

Note in addition to carriers to adapt U.2 8639 devices to PCIe AiC form factor and interfaces, there are also M.2 NGFF to PCIe AiC among others. An example is the Ableconn M.2 NGFF PCIe SSD to PCI Express 3.0 x4 Host Adapter Card.

In addition to Amazon.com, Newegg.com, Ebay and many other venues carry NVMe related technologies.
The Intel Optane NVMe 900P are newer, however the Intel 750 Series along with other Intel NAND Flash based SSDs are still good price performers and as well as provide value. I have accumulated several Intel 750 NVMe devices over past few years as they are great price performers. Check out this related post Get in the NVMe SSD game (if you are not already).

Where To Learn More

View additional NVMe, SSD, NVM, SCM, Data Infrastructure and related topics via the following links.

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What This All Means

NVMe accessed storage is in your future, however there are various questions to address including exploring your options for type of devices, form factors, configurations among other topics. Some NVMe accessed storage is direct attached and dedicated in laptops, ultrabooks, workstations and servers including PCIe AiC, M.2 and U.2 SSDs, while others are shared networked aka fabric based. NVMe over fabric (e.g. NVMeoF) includes RDMA over converged Ethernet (RoCE) as well as NVMe over Fibre Channel (e.g. FC-NVMe). Networked fabric accessed NVMe access of pooled shared storage systems and appliances can also include internal NVMe attached devices (e.g. as part of back-end storage) as well as other SSDs (e.g. SAS, SATA).

General wrap-up (for now) NVMe U.2 8639 and related tips include:

  • Verify the performance of the device vs. how many PCIe lanes exist
  • Update any applicable BIOS/UEFI, device drivers and other software
  • Check the form factor and interface needed (e.g. U.2, M.2 / NGFF, AiC) for a given scenario
  • Look carefully at the NVMe devices being ordered for proper form factor and interface
  • With M.2 verify that it is an NVMe enabled device vs. SATA

Learn more about NVMe at www.thenvmeplace.com including how to use Intel Optane NVMe 900P U.2 SFF 8639 disk drive form factor SSDs in PCIe slots as well as for fabric among other scenarios.

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

How to Achieve Flexible Data Protection Availability with All Flash Storage Solutions

Achieve Flexible Data Protection Availability with All Flash Solutions

server storage I/O data infrastructure trends

Updated 1/21/2018

How to Achieve Flexible flash data protection and Availability with All-Flash Storage Solutions

Interactive webinar discussion (not death by power point or Ui Gui product demo ;) pertaining flash data protection )
Tuesday January 30 2018 11AM PT / 2PM ET
Via Redmond Magazine (Free with registration)

Everything is not the same across different organizations, environments, application workloads and the data infrastructures that support them. Fast application and workloads need fast protection, restoration, and resumption as well as fast flash storage. This applies across legacy, software-defined, virtual, container, cloud, hybrid, converged and HCI among other environments.

SDDC Data Infrastructure Data Protection

Join me along with representatives from Pure Storage along with Veeam for this interactive discussion as we explore how to boost the performance, availability, capacity, and economics (PACE) of your applications along with the data infrastructures that support them.

  • How all-flash storage enables faster protection and restoration of fast applications
  • Why data protection and availability should not be an afterthought
  • Ways to leverage your data protection storage to drive business change
  • How to simplify and reduce complexity to boost productivity while lowering costs
  • Why workload aggregation consolidation should not cause aggravation

Register for the live event or catch the replay here.

Where to learn more

Learn more about data protection, SSD, flash, data infrastructure and related topics via the following links:

SDDC Data Infrastructure

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What this all means and wrap-up

Fast applications need fast and resilient data infrastructures that include server, storage, I/O networking along with data protection. Likewise performance depends on availability along with durability, likewise, availability and accessibility depend on performance, they go hand in hand. Join me and others from Pure Storage as well as Veeam for this conversational discussion about How to Achieve Flexible Data Protection and Availability with All-Flash Storage Solutions.

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

2017 Holiday Seasons Greetings From Server StorageIO

2017 Holiday Seasons Greetings

Greetings from Server StorageIO wishing you, your data infrastructures as well as friends and family’s all the best for a safe, merry happy 2017 holiday season.

In the Jingle Bell

Btw, if you have not done so lately, check out storageio.tv to view various videos, podcasts and images. Some of the storageio.tv content is data infrastructure technology, tools, technique, tradecraft and trends related. Also on storageio.tv are fun content including views from the drone as well as cooking (food and recipes) among other items.

Ok, nuff said, for now.

Cheers Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2023 Server StorageIO(R) and UnlimitedIO. All Rights Reserved.

November 2017 Server StorageIO Data Infrastructure Update Newsletter

Volume 17, Issue 11 (November 2017)

Hello and welcome to the November 2017 issue of the Server StorageIO update newsletter.

Software-Defined Data Infrastructure Essentials SDDI SDDC

2017 has a few more weeks left which look to be busy with end of year, holidays and other activities. Like the rest of 2017 November saw a lot of activity in and around the industry, setting up 2018 as yet another sequel to the busiest and most exciting year ever.

This is also the time of year when predictions for the following year (e.g. 2018) start to roll out, some of which are variations from those of the past or perennial favorites (e.g. the year of flash, the year of cloud, the year of software defined, the year of <insert_your_favorite_item_here>. Look for predictions and perspectives in future posts and newsletters.

Having been a busy month, let’s get to the content…

In This Issue

Enjoy this edition of the Server StorageIO data infrastructure update newsletter.

Cheers GS

Data Infrastructure and IT Industry Activity Trends

Some recent Industry Activities, Trends, News and Announcements include:

On the heals of completing its acquisition of Brocade (note previously Avago (who bought LSI) also bought Broadcom and then changed its name to the more well-known entity. Broadcom also announced relocating it headquarters from Singapore to the US, along an over $100 Billion USD acquisition offer of Qualcomm (here is interesting perspective Apple might play). Broadcom has been focused more on server, storage, I/O and general networking technology, while Qualcomm on mobile including phones and related items. Note that Qualcomm has previously made a $38.5 Billion USD offer for NXP semiconductors waiting regularity approval. View recent Broadcom financial results here.

Also in November server storage I/O controller chip maker Marvell (not to be confused with entertainment provider Marvel) announced a merger with Cavium who had previously acquired Qlogic among others. The resulting combined entity to be called Marvell will have an estimated $16 Billion USD revenue stream focused on server, storage, I/O and networking technologies among others.

In other merger and acquisition activity, VMware announced acquisition of VeloCloud for software defined wide area networking (SD-WAN).

With Super Compute 2017 (SC17) in November there were several announcements including from ATTO, DDN, Enmotus and Micron, Everspin, along with many others. By the way, in case you missed it at end of October Microsoft and Cray announced a partnership to bring Super Compute capabilities to Azure clouds. Speaking of Microsoft, there was also an announcement of adding VMware running on top of Azure (granted without VMware support), similar in concept to VMware on AWS (read hare).

Also at the end of November was AWS Reinvent with many announcements (more on those in a follow-up newsletter and posts). Prior to Reinvent AWS announced several server, storage and other data infrastructure security enhancements including for S3. Highlights from AWS reinvent include Fargate (serverless aka containers at scale without managing infrastructure), Elastic Container Services for Kubernetes (EKS), Greengrass (machine learning [ML] data infrastructure), along with many others.

Fargate is for those who want to leverage serveless microservices containers without having to devote DevOps and related activity to the care and feeding of its data infrastructure. In other words, Fargate is for those who want to focus maximum effort on the business applications, vs. the business of setting up and maintaining the data infrastructure for serverless On the other hand, AWS also announced EKS for those who want or need to customize their serverless data infrastructure including around Kubernetes among others.

In other industry activity, Taiwanese based Foxconn who manufactures technology for the who’s who of the industry announced progress towards their future Wisconsin based factory complex.

Over at HPE, the big news announcement is that CEO Meg Whitman is stepping down. HPE also announced new AMD powered Gen 10 Proliant services, as well as multi-cloud management solutions. HPE also announced new partnerships with DDN for HPC and SC, with Rackspace for selling private cloud services, along with Cloudian EMEA partnership among others.

OwnBackup announced a new version of their data protection software, while low-cost budget bulk storage service backblaze (B2) announced their more recent quarterly drive failure (or success) reliability reports. Meanwhile over at Quantum they released former Ceo Jon Gacek and rotated in new management.

Red Hat announced Ceph Storage 3 including CephFS (POSIX compatible file system), iSCSI gateway including support for VMware and Windows that lack native Ceph drivers, daemon deployment in Linux containers for smaller hardware footprint. Also included are enhanced monitoring, troubleshooting and diagnostics to streamline deployment and ongoing management. Red Hat also announced OpenShift version 3.7 for containers.

SANblaze announced NVMf and dual port NVMe capabilities for NVMe fabrics, while Linbit won an European grant to build out a software defined storage cloud scale out solution.

I often get asked who are the hot, new, trendy or other vendors and services to keep an eye on some of which I have mentioned in previous newsletters, as well as posts such as here and here. Moving in to 2018 some to keep an eye on (not all are new or trendy, yet they can enable you to be productive, or differentiate) include the following.

AWS, Bluemedora, Chelsio, Cloudian, CloudPassage, Compuverde, Databricks, Datadog, Datos, Enmotus, Everspin, Excelero, Fluree (Blockchain database), Google, Mellonox, Microsemi, Microsoft, Marvel and Cavium, MyWorkDrive, Red Hat, Rook, Rozo, Rubrik, Strongbox, Storone, Turbonomic, Ubuntu, Veeam, Velostrata, Virtuozo, VMware, WekaIO and others.

What the above means, is that it has been a busy month as well as year, and, the year is not over yet. There are still plenty of shopping days left both for christmas and the holidays, as well as for IT year-end spending, vendors looking to do acquisitions, or other last-minute projects. Speaking of which, drop me a note if you have any end of year, or new year projects Server StorageIO can assist you with.

Check out other industry news, comments, trends perspectives here.

Server StorageIO Commentary in the news, tips and articles

Recent Server StorageIO industry trends perspectives commentary in the news.

Via HPE Insights: Comments on Public cloud versus on-prem storage
Via DataCenterKnowledge: Data Center Standards: Where’s the Value?
Via arsTechnica: Comments on cloud backup disaster recovery

View more Server, Storage and I/O trends and perspectives comments here

Server StorageIOblog Data Infrastructure Posts

Recent and popular Server StorageIOblog posts include:

In Case You Missed It #ICYMI

View other recent as well as past StorageIOblog posts here

Server StorageIO Recommended Reading (Watching and Listening) List

In addition to my own books including Software Defined Data Infrastructure Essentials (CRC Press 2017), the following are Server StorageIO data infrastructure recommended reading, watching and listening list items. The list includes various IT, Data Infrastructure and related topics. Speaking of my books, Didier Van Hoye (@WorkingHardInIt) has a good review over on his site you can view here, also check out the rest of his great content while there.

Intel Recommended Reading List (IRRL) for developers is a good resource to check out.

For those who are into Linux, container and hypervisor performance along with internals including cloud based, check out Brendan Gregg site. He has a lot of great material including some recent interesting posts ranging from dealing with workplace jerks, to whats inside AWS EC2 new KVM (switch from Xen based) hypervisors among others.

Here is a post by New York Times CIO/CTO Nick Rockwell The (Futile) Resistance to Serverless, also check out my podcast discussion with Nick here.

Over at Next Platform they have some interesting perspectives on Intel’s next Exascale architecture worth spending a few minutes to read.

Watch for more items to be added to the recommended reading list book shelf soon.

Events and Activities

Recent and upcoming event activities.

Nov. 9, 2017 – Webinar – All You Need To Know about ROBO Data Protection Backup
Nov. 2, 2017 – Webinar – Modern Data Protection for Hyper-Convergence

See more webinars and activities on the Server StorageIO Events page here.

Server StorageIO Industry Resources and Links

Useful links and pages:
Data Infrastructure Recommend Reading and watching list
Microsoft TechNet – Various Microsoft related from Azure to Docker to Windows
storageio.com/links – Various industry links (over 1,000 with more to be added soon)
objectstoragecenter.com – Cloud and object storage topics, tips and news items
OpenStack.org – Various OpenStack related items
storageio.com/downloads – Various presentations and other download material
storageio.com/protect – Various data protection items and topics
thenvmeplace.com – Focus on NVMe trends and technologies
thessdplace.com – NVM and Solid State Disk topics, tips and techniques
storageio.com/converge – Various CI, HCI and related SDS topics
storageio.com/performance – Various server, storage and I/O benchmark and tools
VMware Technical Network – Various VMware related items

Connect and Converse With Us


Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2023 Server StorageIO(R) and UnlimitedIO. All Rights Reserved.

Data Protection Diaries Fundamental Topics Tools Techniques Technologies Tips

Data Protection Fundamental Topics Tools Techniques Technologies Tips

Update 1/16/2018

Data protection fundamental companion to Software Defined Data Infrastructure Essentials – Cloud, Converged, Virtual Fundamental Server Storage I/O Tradecraft ( CRC Press 2017)

server storage I/O data infrastructure trends

By Greg Schulzwww.storageioblog.com November 26, 2017

This is Part I of a multi-part series on Data Protection fundamental tools topics techniques terms technologies trends tradecraft tips as a follow-up to my Data Protection Diaries series, as well as a companion to my new book Software Defined Data Infrastructure Essentials – Cloud, Converged, Virtual Server Storage I/O Fundamental tradecraft (CRC Press 2017).

Software Defined Data Protection Fundamental Infrastructure Essentials Book SDDC

The focus of this series is around data protection fundamental topics including Data Infrastructure Services: Availability, RAS, RAID and Erasure Codes (including LRC) ( Chapter 9), Data Infrastructure Services: Availability, Recovery Point ( Chapter 10). Additional Data Protection related chapters include Storage Mediums and Component Devices ( Chapter 7), Management, Access, Tenancy, and Performance ( Chapter 8), as well as Capacity, Data Footprint Reduction ( Chapter 11), Storage Systems and Solutions Products and Cloud ( Chapter 12), Data Infrastructure and Software-Defined Management ( Chapter 13) among others.

Post in the series includes excerpts from Software Defined Data Infrastructure (SDDI) pertaining to data protection for legacy along with software defined data centers ( SDDC), data infrastructures in general along with related topics. In addition to excerpts, the posts also contain links to articles, tips, posts, videos, webinars, events and other companion material. Note that figure numbers in this series are those from the SDDI book and not in the order that they appear in the posts.

Posts in this data protection fundamental series include:

SDDC, SDI, SDDI data infrastructure
Figure 1.5 Data Infrastructures and other IT Infrastructure Layers

Data Infrastructures

Data Infrastructures exists to support business, cloud and information technology (IT) among other applications that transform data into information or services. The fundamental role of data infrastructures is to provide a platform environment for applications and data that is resilient, flexible, scalable, agile, efficient as well as cost-effective.

Put another way, data infrastructures exist to protect, preserve, process, move, secure and serve data as well as their applications for information services delivery. Technologies that make up data infrastructures include hardware, software, or managed services, servers, storage, I/O and networking along with people, processes, policies along with various tools spanning legacy, software-defined virtual, containers and cloud. Read more about data infrastructures (its what’s inside data centers) here.

Why SDDC SDDI Need Data Protection
Various Needs Demand Drivers For Data Protection Fundamentals

Why The Need For Data Protection

Data Protection encompasses many different things, from accessibility, durability, resiliency, reliability, and serviceability ( RAS) to security and data protection along with consistency. Availability includes basic, high availability ( HA), business continuance ( BC), business resiliency ( BR), disaster recovery ( DR), archiving, backup, logical and physical security, fault tolerance, isolation and containment spanning systems, applications, data, metadata, settings, and configurations.

From a data infrastructure perspective, availability of data services spans from local to remote, physical to logical and software-defined, virtual, container, and cloud, as well as mobile devices. Figure 9.2 shows various data infrastructure availability, accessibility, protection, and security points of interest. On the left side of Figure 9.2 are various data protection and security threat risks and scenarios that can impact availability, or result in a data loss event ( DLE), data loss access ( DLA), or disaster. The right side of Figure 9.2 shows various techniques, tools, technologies, and best practices to protect data infrastructures, applications, and data from threat risks.

SDDI SDDC Data Protection Fundamental Big Picture
Figure 9.2 Various threat vectors, issues, problems, and challenges that drive the need for data protection

A fundamental role of data infrastructures (and data centers) is to protect, preserve, secure and serve information when needed with consistency. This also means that the data infrastructure resources (servers, storage, I/O networks, hardware, software, external services) and the applications (and data) they combine and are defined to protect are also accessible, durable and secure.

Data Protection topics include:

  • Maintaining availability, accessibility to information services, applications and data
  • Data include software, actual data, metadata, settings, certificates and telemetry
  • Ensuring data is durable, consistent, secure and recoverable to past points in time
  • Everything is not the same across different environments, applications and data
  • Aligning techniques and technologies to meet various service level objectives ( SLO)

Data Protection Fundamental Tradecraft Skills Experience Knowledge

Tools, technologies, trends are part of Data Protection, so to are the techniques of knowing (e.g. tradecraft) what to use when, where, why and how to protect against various threats risks (challenges, issues, problems).

Part of what is covered in this series of posts as well as in the Software Defined Data Infrastructure (SDDI) Essentials book is tradecraft skills, tips, experiences, insight into what to use, as well as how to use old and new things in new ways.

This means looking outside the technology box towards what is that you need to protect and why, then knowing how to use different skills, experiences, techniques part of your tradecraft combined with data protection toolbox tools. Read more about tradecraft here.

Where To Learn More

Continue reading additional posts in this series of Data Infrastructure Data Protection fundamentals and companion to Software Defined Data Infrastructure Essentials (CRC Press 2017) book, as well as the following links covering technology, trends, tools, techniques, tradecraft and tips.

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What This All Means

Everything is not the same across environments, data centers, data infrastructures and applications.

Likewise everything is and does not have to be the same when it comes to Data Protection. Data protection fundamentals encompasses many different hardware, software, services including cloud technologies, tools, techniques, best practices, policies and tradecraft experience skills (e.g. knowing what to use when, where, why and how).

Since everything is not the same, various data protection approaches are needed to address various application performance availability capacity economic ( PACE) needs, as well as SLO and SLAs.

Get your copy of Software Defined Data Infrastructure Essentials here at Amazon.com, at CRC Press among other locations and learn more here. Meanwhile, continue reading with the next post in this series, Part 2 Reliability, Availability, Serviceability ( RAS) Data Protection Fundamentals.

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

Data Protection Diaries Reliability, Availability, Serviceability RAS Fundamentals

Reliability, Availability, Serviceability RAS Fundamentals

Companion to Software Defined Data Infrastructure Essentials – Cloud, Converged, Virtual Fundamental Server Storage I/O Tradecraft ( CRC Press 2017)

server storage I/O data infrastructure trends

By Greg Schulzwww.storageioblog.com November 26, 2017

This is Part 2 of a multi-part series on Data Protection fundamental tools topics techniques terms technologies trends tradecraft tips as a follow-up to my Data Protection Diaries series, as well as a companion to my new book Software Defined Data Infrastructure Essentials – Cloud, Converged, Virtual Server Storage I/O Fundamental tradecraft (CRC Press 2017).

Software Defined Data Infrastructure Essentials Book SDDC

Click here to view the previous post Part 1 Data Infrastructure Data Protection Fundamentals, and click here to view the next post Part 3 Data Protection Access Availability RAID Erasure Codes (EC) including LRC.

Post in the series includes excerpts from Software Defined Data Infrastructure (SDDI) pertaining to data protection for legacy along with software defined data centers ( SDDC), data infrastructures in general along with related topics. In addition to excerpts, the posts also contain links to articles, tips, posts, videos, webinars, events and other companion material. Note that figure numbers in this series are those from the SDDI book and not in the order that they appear in the posts.

In this post the focus is around Data Protection availability from Chapter 9 which includes access, durability, RAS, RAID and Erasure Codes (including LRC), mirroring and replication along with related topics.

SDDC, SDI, SDDI data infrastructure
Figure 1.5 Data Infrastructures and other IT Infrastructure Layers

Reliability, Availability, Serviceability (RAS) Data Protection Fundamentals

Reliability, Availability Serviceability (RAS) and other access availability along with Data Protection topics are covered in chapter 9. A resilient data infrastructure (software-defined, SDDC and legacy) protects, preserves, secures and serves information involving various layers of technology. These technologies enable various layers ( altitudes) of functionality, from devices up to and through the various applications themselves.

SDDI SDDC Data Protection Big Picture
Figure 9.2 Various threat issues and challenges that drive the need for data protection

Some applications need a faster rebuild, while others need sustained performance (bandwidth, latency, IOPs, or transactions) with the slower rebuild; some need lower cost at the expense of performance; others are ok with more space if other objectives are meet. The result is that since everything is different yet there are similarities, there is also the need to tune how data Infrastructure protects, preserves, secures, and serves applications and data.

General reliability, availability, serviceability, and data protection functionality includes:

  • Manually or automatically via policies, start, stop, pause, resume protection
  • Adjust priorities of protection tasks, including speed, for faster or slower protection
  • Fast-reacting to changes, disruptions or failures, or slower cautious approaches
  • Workload and application load balancing (performance, availability, and capacity)

RAS can be optimized for:

  • Reduced redundancy for lower overall costs vs. resiliency
  • Basic or standard availability (leverage component plus)
  • High availability (use better components, multiple systems, multiple sites)
  • Fault-tolerant with no single points of failure (SPOF)
  • Faster restart, restore, rebuild, or repair with higher overhead costs
  • Lower overhead costs (space and performance) with lower resiliency
  • Lower impact to applications during rebuild vs. faster repair
  • Maintenance and planned outages or for continues operations

Common availability Data Protection related terms, technologies, techniques, trends and topics pertaining to data protection from availability and access to durability and consistency to point in time protection and security are shown below.

Data Protection Gaps and Air Gap

There are Good Data Protection Gaps that provide recovery points to a past time enabling recoverability in the future to move forward. Another good data protection gap is an Air Gap that isolates protection copies off-site or off-line so that they can not be tampered with enabling recovery from ransomware and other software defined threats. There are Bad data protection gaps including gaps in coverage where data is not protected or items are missing. Then there are Ugly data protecting gaps which include Bad gaps that result in what you think is protected are not and finding that your copies are bad when it is too late.

Data Protection Gaps Good Bad Ugly
Data Protection Gaps Good Bad and Ugly

The following figure shows good data protection gaps including recovery points (point in time protection) along with air gaps.

Good Data Protection Gaps
Figure 9.9 Air Gaps and Data Protection

Fault / Failures To Tolerate (FTT)

FTT is how many faults or failures to tolerate for a given solution or service which in turn determines what mode of protection, or fault tolerant mode ( FTM) to use.

Fault Tolerant Mode (FTM)

FTM is the mode or technique used to enable resiliency and protect against some number of faults.

Fault / Failure Domains

Fault or Failure domains are places and things that can fail from regions, data centers or availability zones, clusters, stamps, pods, servers, networks, storage, hardware (systems, components including SSD and HDDs, power supplies, adapters). Other fault domain topics and focus areas include facility power, cooling, software including applications, databases, operating systems and hypervisors among others.

SDDI SDDC Fault Domains Zones Regions
Figure 9.5 Various Fault and Failure Domains, Regions, Locations

Clustering

Clustering is a technique and technology for enabling resiliency, as well as scaling performance, availability, and capacity. Clusters can be local, remote, or wide-area to support different data infrastructure objectives, combined with replication and other techniques.

SDDI SDDC Clustering
Figure 9.12 Clustering and Replication Examples

Another characteristic of clustering and resiliency techniques is the ability to detect and react quickly to failures to isolate and contain faults, as well as invoking automatic repair if needed. Different clustering technologies enable various approaches, from proprietary hardware and software tightly coupled to loosely coupled general-purpose hardware or software.

Clustering characteristics include:

  • Application, database, file system, operating system (Windows Storage Replica)
  • Storage systems, appliances, adapters and network devices
  • Hypervisors ( Hyper-V, VMware vSphere ESXi and vSAN among others)
  • Share everything, share some things, share nothing
  • Tightly or loosely coupled with common or individual system metadata
  • Local in a data center, campus, metro, or stretch cluster
  • Wide-area in different regions and availability zones
  • Active/active for fast fail over or restart, active/passive (standby) mode

Additional clustering considerations include:

  • How does performance scale as nodes are added, or what overhead exists?
  • How is cluster resource locking in shared environments handled?
  • How many (or few) nodes are needed for quorum to exist?
  • Network and I/O interface (and management) requirements
  • Cluster partition or split-brain (i.e., cluster splits into two)?
  • Fast-reacting fail over and resiliency vs. overhead of failing back
  • Locality of where applications are located vs. storage access and clustering

Where To Learn More

Continue reading additional posts in this series of Data Infrastructure Data Protection fundamentals and companion to Software Defined Data Infrastructure Essentials (CRC Press 2017) book, as well as the following links covering technology, trends, tools, techniques, tradecraft and tips.

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What This All Means

Everything is not the same across different environments, data centers, data infrastructures and applications. There are various performance, availability, capacity economic (PACE) considerations along with service level objectives (SLO). Availability means being able to access information resources (applications, data and underlying data infrastructure resources), as well as data being consistent along with durable. Being durable means enabling data to be accessible in the event of a device, component or other fault domain item failures (hardware, software, data center).

Just as everything is not the same across different environments, there are various techniques, technologies and tools that can be used in different ways to enable availability and accessibility. These include high availability (HA), RAS, mirroring, replication, parity along with derivative erasure code (EC), LRC, RS and other RAID implementations, along with clustering. Also keep in mind that pertaining to data protection, there are good gaps (e.g. time intervals for recovery points, air gaps), bad gaps (missed coverage or lack of protection), and ugly gaps (not being able to recover from a gap in time).

Note that mirroring, replication, EC, LRC, RS or other Parity and RAID approaches are not replacements for backup, rather they are companions to time interval based recovery point protection such as snapshots, backup, checkpoints, consistency points and versioning among others (discussed in follow-up posts in this series).

Which data protection tool, technology to trend is the best depends on what you are trying to accomplish and your application workload PACE requirements along with SLOs. Get your copy of Software Defined Data Infrastructure Essentials here at Amazon.com, at CRC Press among other locations and learn more here. Meanwhile, continue reading with the next post in this series, Part 3 Data Protection Access Availability RAID Erasure Codes (EC) including LRC.

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

Data Protection Diaries Access Availability RAID Erasure Codes LRC Deep Dive

Access Availability RAID Erasure Codes including LRC Deep Dive

Companion to Software Defined Data Infrastructure Essentials – Cloud, Converged, Virtual Fundamental Server Storage I/O Tradecraft ( CRC Press 2017)

server storage I/O data infrastructure trends

By Greg Schulzwww.storageioblog.com November 26, 2017

This is Part 3 of a multi-part series on Data Protection fundamental tools topics techniques terms technologies trends tradecraft tips as a follow-up to my Data Protection Diaries series, as well as a companion to my new book Software Defined Data Infrastructure Essentials – Cloud, Converged, Virtual Server Storage I/O Fundamental tradecraft (CRC Press 2017).

Software Defined Data Infrastructure Essentials Book SDDC

Click here to view the previous post Part 2 Reliability, Availability, Serviceability (RAS) Data Protection Fundamentals, and click here to view the next post Part 4 Data Protection Recovery Points (Archive, Backup, Snapshots, Versions).

Post in the series includes excerpts from Software Defined Data Infrastructure (SDDI) pertaining to data protection for legacy along with software defined data centers ( SDDC), data infrastructures in general along with related topics. In addition to excerpts, the posts also contain links to articles, tips, posts, videos, webinars, events and other companion material. Note that figure numbers in this series are those from the SDDI book and not in the order that they appear in the posts.

In this post part of the Data Protection diaries series as well as companion to Chapter 9 of SDDI Essentials book, we are going on a longer, deeper dive. We are going to look at availability, access and durability including mirror, replication, RAID including various traditional and newer parity approaches such as Erasure Codes ( EC), Local Reconstruction Code (LRC), Reed Solomon (RS) also known as RAID 2 among others. Later posts in this series look at point in time data protection to support recovery to a given time (e.g. RPO), while this and the previous post look at maintaining access and availability.

Keep in mind that if something can fail, it probably will, also that everything is not the same meaning different environments, application workloads (along with their data). Different environments and applications have diverse performance, availability, capacity economic (PACE) attributes, along with service level objectives ( SLOs). Various SLOs include PACE attributes, recovery point objectives ( RPO), recovery time objective ( RTO) among others.

Availability, accessibility and durability (see part two in this series) along with associated RAS topics are part of what enable RTO, as well as meet Faults (or failures) to tolerate ( FTT). This means that different fault tolerance modes ( FTM) determine what technologies, tools, trends and techniques to use to meet different RTO, FTT and application PACE needs.

Maintaining access and availability along with durability (e.g. how many copies of data as well as where stored) protects against loss or failure of a component device ( SSD, HDDs, adapters, power supply, controller), node or system, appliance, server, rack, clusters, stamps, data center, availability zones, regions, or other Fault or Failure domains spanning hardware, software, and services.

SDDC, SDI, SDDI data infrastructure
Figure 1.5 Data Infrastructures and other IT Infrastructure Layers

Data Protection Access Availability RAID Erasure Codes

This is a good place to mention some context for RAID and RAID array, which can mean different things pertaining to Data Protection. Some people associate RAID with a hardware storage array, or with a RAID card. Other people consider an array to be a storage array that is a RAID enabled storage system. A trend is to refer to legacy storage systems as RAID arrays or hardware-based RAID, to differentiate from newer implementations.

Context comes into play in that a RAID group (i.e., a collection of HDDs or SSD that is part of a RAID set) can be referred to as an array, a RAID array, or a virtual array. What this means is that while some RAID implementations may not be relevant, there are many new and evolving variations extending parity based protection making at least software-defined RAID still relevant

Keep context in mind, and don’t be afraid to ask what someone is referring to: a particular vendor storage system, a RAID implementation or packaging, a storage array, or a virtual array. Also keep the context of the virtual array in perspective vs. storage virtualization and virtual storage. RAID as a term is used to refer to different modes such as mirroring or parity, and parity can be legacy RAID 4, 5, or 6 along with erasure codes (EC). Note some people refer to erasure codes in the context of not being a RAID system, which can be an inference to not being a legacy storage system running hardware RAID (e.g. not software or software defined).

The following figure (9.13) shows various availability protection schemes (e.g. not recovery point) that maintain access while protecting against loss of a component, device, system, server, site, region or other part of a fault domain. Since everything is not the same with environments and applications having different Performance Availability Capacity Economic ( PACE) attributes, there are various approaches for enabling availability along with accessibility.

Keep in mind that RAID and Erasure codes along with their various, as well as replication and mirroring by themselves are not a replacement for backup or other point in time (e.g. enable recovery point) protection.

Instead, availability technologies such as RAID and erasure code along with mirror as well as replication need to be combined with snapshots, point in time copies, consistency points, checkpoints, backups among other recovery point protection for complete data protection.

Speaking of replacement for backup, while many vendors and their pundits claIm or want to see backup as being dead, as long as they keep talking about backup instead of broader data protection backup will remain alive.

SDDC SDDI RAID Parity Erasure Code EC
Figure 9.13 Various RAID, Mirror, Parity and Erasure Code (EC) approaches

Different RAID levels (including parity, EC, LRC and RS based) will affect storage energy effectiveness, similar to various SSD or HDD performance capacity characteristics; however, a balance of performance, availability, capacity, and energy needs to occur to meet application service needs. For example, RAID 1 mirroring or RAID 10 mirroring and striping use more HDDs and, thus, power, but will yield better performance than RAID 6 and erasure code parity protection.

 

Normal performance

 

Availability

Performance overhead

Rebuild overhead

Availability overhead

RAID 0 (stripe)

Very good read & write

None

None

Full volume restore

None

RAID 1 (mirror or replicate)

Good reads; writes = device speed

Very good; two or more copies

Multiple copies can benefit reads

Re-synchronize with existing volume

2:1 for dual, 3:1 for three-way copies

RAID 4 (stripe with dedicated parity, i.e., 4 + 1 = 5 drives total)

Poor writes without cache

Good for smaller drive groups and devices

High on write without cache (i.e., parity)

Moderate to high, based on number and type of drives

Varies; 1 Parity/N, where N = number of devices

RAID 5
(stripe with rotating parity, 4 + 1 = 5 drives)

Poor writes without cache

Good for smaller drive groups and devices

High on write without cache (i.e., parity)

Moderate to high, based on number and type of drives

Varies
1 Parity/N, where N = number of devices

RAID 6
(stripe with dual parity, 4 + 2 = 6 drives)

Poor writes without cache

Better for larger drive groups and devices

High on write without cache (i.e., parity)

Moderate to high, based on number and type of drives

Varies; 2 Parity/N, where N = number of devices

RAID 10
(mirror and stripe)

Good

Good

Minimum

Re-synchronize with existing volume

Twice mirror capacity stripe drives

Reed-Solomon (RS) parity, also known as erasure code (EC), local reconstruction code (LRC), and SHEC

Ok for reads, slow writes; good for static and cold data with front-end cache

Good

High on writes (CPU for parity calculation, extra I/O operations)

Moderate to high, based on number and type of drives, how implemented, extra I/Os for reconstruction

Varies, low overhead when using large number of devices; CPU, I/O, and network overhead.

Table 9.3 Common RAID Characteristics

Besides those shown in table 9.3, other RAID including parity based approaches include 2 (Reed Solomon), 3 (synchronized stripe and dedicated parity) along with others including combinations such as 10, 01, 50, 60 among others.

Similar to legacy parity-based RAID, some erasure code implementations use narrow drive groups while others use larger ones to increase protection and reduce capacity overhead. For example, some larger enterprise-class storage systems (RAID arrays) use narrow 3 + 1 or 4 + 1 RAID 5 or 4 + 2 or 6 + 2 RAID 6, which have higher protection storage capacity overhead and fault=impact footprint.

On the other hand, many smaller mid-range and scale-out storage systems, appliances, and solutions support wide stripes such as 7 + 1, 15 + 1, or larger RAID 5, or 14 + 2 or larger RAID 6. These solutions trade the lower storage capacity protection overhead for risk of a multiple drive failures or impacts. Similarly, some EC implementations use relatively small groups such as 6, 2 (8 drives) or 4, 2 (6 drives), while others use 14, 4 (18 drives), 16, 4 (20 drives), or larger.

Table 9.4 shows options for a number of data devices (k) vs. a number of protect devices (m).

k
(data devices)

m
(protect devices)

Availability;
Resiliency

Space capacity overhead

Normal performance

FTT

Comments;
Examples

Narrow

Wide

Very good;
Low impact of rebuild

Very high

Good (R/W)

Very good

Trade space for RAS;
Larger m vs. k;
1, 1; 1, 2; 2, 2; 4, 5

Narrow

Narrow

Good

Good

Good (R/W)

Good

Use with smaller drive groups;
2, 1; 3, 1; 6, 2

Wide

Narrow

Ok to good;
With larger m value

Low as m gets larger

Good (read);
Writes can be slow

Ok to good

Smaller m can impact rebuild;
3, 1; 7, 1; 14, 2; 13, 3

Wide

Wide

Very good;
Balanced

High

Good

Very good

Trade space for RAS;
2, 2; 4, 4; 8, 4; 18, 6

Table 9.4. Comparing Various Data Device vs. Protect Device Configurations

Note that wide k with no m, such as 4, 0, would not have protection. If you are focused on reducing costs and storage space capacity overhead, then a wider (i.e., more devices) with fewer protect devices might make sense. On the other hand, if performance, availability, and minimal to no impact during rebuild or reconstruction are important, then a narrower drive set, or a smaller ratio of data to protect drives, might make sense.

Also note that the higher or larger the RAID number, or parity scheme, or number of "m" devices in a parity and erasure code group may not be better, likewise smaller may not be better. What is better is which approach meets your specific application performance, availability, capacity, economic (PACE) needs, along with SLO, RTO, RPO requirements. What can also be good is to use hybrid approaches combining different technologies and tools to facilitate both access, availability, durability along with point in time recovery across different layers of granularity (e.g. device, drive, adapter, controller, cabinet, file system, data center, etc).

Some focus on the lower level RAID as the single or primary point of protection, however watch out for that being your single point of failure as well. For example, instead of building a resilient RAID 10 and then neglecting to have adequate higher level access, as well as recovery point protection, combine different techniques including file system protection, snapshots, and backups among others.

Figure 9.14 shows various options and considerations for balancing between too many or too few data (k) and protect (m) devices. The balance is about enabling particular FTT along with PACE attributes and SLO. This means, for some environments or applications, using different failure-tolerant modes ( FTM) in various combinations as well as configurations.

SDDC SDDI Data Protection
Figure 9.14 Comparing various data drive to protection devices

Figure 9.14 top shows no protection overhead (with no protection); the bottom shows 13 data drives and three protection drives in an EC (RS or LRC among others) configuration that could tolerate three devices failing before loss of data or access occurs. In between are various options that can also be scaled up or down across a different number of devices ( HDDs, SSD, or systems).

Some solutions allow the user or administrator to configure the I/O chunk, slabs, shard, or stripe size, for example, from 8 KB to 256 KB to 1 MB (or larger), aligning with application workload and I/O profiles. Other options include the ability to set or disable read-ahead, write-through vs. write-back cache (with battery-protected cache), among other options.

The width or number of devices in a RAID parity or erasure group is based on a combination of factor, including how much data is to be stored and what your FTT objective is, along with spreading out protection overhead. Another consideration is whether you have large or small files and objects.

For example, if you have many small files and a wide stripe, parity, or erasure code set with a large chunk or shard size, you may not have an optimal configuration from a performance perspective.

The following figure shows combing various data protection availability and accessibility technologies including local as well as remote mirroring and replication, along with parity or erasure code (including LRC, RS, SHEC among others) approaches. Instead of just using one technology, a hybrid approach is used leveraging mirror (local on SSD) and replication across sites including asynchronous and synchronous. Replication modes include Asynchronous (time-delayed, eventual consistency) for longer distance, higher latency networks, and synchronous (strong consistency, real-time) for short distance or low-latency networks.

Note that the mirror and replication can be done in software deployed as part of a storage system, appliance or as tin-wrapped software, virtual machine, virtual storage appliance, container or some other deployment mode. Likewise RAID, parity and erasure code software can be deployed and packaged in different ways.

In addition to mirror and replication, solutions are also using parity based including erasure code variations for lower cost, less active data. In other words, the mirror on SSD handles active hot data, as well as any buffering or cache, while lower performance, higher capacity, lower cost data gets de-staged or migrated to a parity erasure code tier. Some vendors, service provider and solutions leveraging variations of the approach in figure 9.15 include Microsoft ( Azure and Windows) and VMware among others.

SDDC SDDI Data Protection
Figure 9.15 Combining various availability data protection techniques

A tradecraft skill is finding the balance, knowing your applications, the data, and how the data is allocated as well as used, then leveraging that insight and your experience to configure to meet your application PACE requirements.

Consider:

  • Number of drives (width) in a group, along with protection copies or parity
  • Balance rebuild performance impact and time vs. storage space overhead savings
  • Ability to mix and match various devices in different drive groups in a system
  • Management interface, tools, wizards, GUIs, CLIs, APIs, and plug-ins
  • Different approaches for various applications and environments
  • Context of a physical RAID array, system, appliance, or solution vs. logical

Erasure Codes (EC)

Erasure Codes ( EC) combines advanced protection with variable space capacity overhead over many drives, devices, or systems using large parity chunks, shards compared to traditional parity RAID approaches. There are many variations of EC as well as parity based approaches, some are tied to Reed Solomon (RS) codes while others use different approaches.

Note that some EC are optimized for reducing the overhead and cost of storing data (e.g. less space capacity) for inactive, or primarily read data. Likewise, some EC or variations are optimized for performance of reads/writes as well as reducing overhead of rebuild, reconstructions, repairs with least impact. Which EC or parity derivative approach is best depends on what you are trying to do or impact to avoid.

Reed Solomon (RS) codes

Reed Solomon (RS) codes are advanced parity protection mathematical algorithm technique that works well on large amounts of data providing protection with lower space capacity overhead depending on how configured. Many Erasure Codes (EC) are based on derivatives of RS. Btw, did you know (or remember) that RAID 2 (rarely used with few legacy implementations) has ties to RS codes? Here are some additional links to RS including via Backblaze, CMU, and Dr Dobbs.

Local Reconstruction Codes (LRC)

Microsoft leverages LRC in Azure as well as in Windows Servers. LRC are optimized for a balance of protection, space capacity savings, normal performance as well as reducing impact on running workloads during a repair, rebuild or reconstruction. One of the tradeoffs that LRC uses is to add some amount of additional space capacity in exchange for normal and abnormal (e.g. during repair) performance improvements. Where RS, EC and other parity based derivatives typically use a (k,m) nomenclature (e.g. data, protection), LRC adds an extra variable to help with constructions (k,m,n).

Some might argue that LRC are not as space efficient as other EC, RS or parity derivative variations of which the counter argument can be that some of those approaches are not as performance effective. In other words, everything is not the same, one approach does not or should not have to be applied to all, unless of course your preferred solution approach can only do one thing.

Additional LRC related material includes:

  • (PDF by Microsoft) LRC Erasure Coding in Windows Storage Spaces
  • (Microsoft Usenix Paper) Best Paper Award Erasure Coding in Azure
  • (Via MSDN Shared) Azure Storage Erasure Coding with LRC
  • (Via Microsoft) Azure Storage with Strong Consistency
  • (Paper via Microsoft) 23rd ACM Symposium on Operating Systems Principles (SOSP)
  • (Microsoft) Erasure Coding in Azure with LRC
  • (Via Microsoft) Good collection of EC, RS, LRC and related material
  • (Via Microsoft) Storage Spaces Fault Tolerance
  • (Via Microsoft) Better Way To Store Data with EC/LRC
  • (Via Microsoft) Volume resiliency and efficiency in Storage Spaces

Shingled Erasure Code (SHEC)

Shingled Erasure Codes (SHEC) are a variation of Erasure Codes leveraging shingled overlay approach similar to what is being used in Shingled Magnetic Recording (SMR) on some HDDs. Ceph has been an early promoter of SHEC, read more here, and here.

Replication and Mirroring

Replication and Mirroring create a mirror or replica copy of data across different devices, systems, servers, clusters, sites or regions. In addition to keeping a copy, mirror and replication can occur on different time intervals such as real-time ( synchronous) and time deferred (Asynchronous). Besides time intervals, mirror and replication are implemented in different locations at various altitudes or stack layers from lower level hardware adapter or storage systems and appliances, to operating systems, hypervisors, software defined storage, volume managers, databases and applications themselves.

Covered in more detail in chapters 5 and 6, synchronous provides real-time, strong consistency, although high-latency local or remote interfaces can impact primary application performance. Note there is a common myth that high-latency networks are only long distance when in fact some local networks can also be high-latency. Asynchronous (also discussed in more depth in chapters 5 and 6) enables local and remote high-latency communications to be spanned, facilitating protection over a distance without impacting primary application performance, albeit with lower consistency, time deferred, also known as eventual consistency.

Mirroring (also known as RAID 1) and replication creates a copy (a mirror or replica) across two or more storage targets (devices, systems, file systems, cloud storage service, applications such as a database). The reason for using mirrors is to provide a faster (for normal running and during recovery) failure-tolerant mode for enabling availability, resiliency, and data protection, particularly for active data.

Figure 9.10 shows general replication scenarios. Illustrated are two basic mirror scenarios: At the top, a device, volume, file system, or object bucket is replicated to two other targets (i.e., three-way or three replicas); At the bottom, is a primary storage device using a hybrid replica and dispersal technique where multiple data chunks, shards, fragments, or extents are spread across devices in different locations.

SDDC SDDI Mirror and Replication
Figure 9.10 Various Mirror and Replication Approaches

Mirroring and replication can be done locally inside a system (server, storage system, or appliance), within a cabinet, rack, or data center, or remotely, including at cloud services. Mirroring can also be implemented inside a server in software or using RAID and HBA cards to off-load the processing.

SDDC SDDI Mirror Replication Techniques
Figure 9.11 Mirror or Replication combined with Snapshots or other PiT protection

Keep in mind that mirroring and replication by themselves are not a replacement for backups, versions, snapshots, or another recovery point, time-interval (time-gap) protection. The reason is that replication and mirroring maintain a copy of the source at one or more destination targets. What this means is that anything that changes on the primary source also gets applied to the target destination (mirror or replica). However, it also means that anything changed, deleted, corrupted, or damaged on the source is also impacted on the mirror replica (assuming the mirror or replicas were or are mounted and accessible on-line).

implementations in various locations (hardware, software, cloud) include:

  • Applications and databases such as SQL Server, Oracle among others
  • File systems, volume manager, Software-defined storage managers
  • Third-party storage software utilities and drivers
  • Operating systems and hypervisors
  • Hardware adapter and off-load devices
  • Storage systems and appliances
  • Cloud and managed services

Where To Learn More

Continue reading additional posts in this series of Data Infrastructure Data Protection fundamentals and companion to Software Defined Data Infrastructure Essentials (CRC Press 2017) book, as well as the following links covering technology, trends, tools, techniques, tradecraft and tips.

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What This All Means

There are various data protection technologies, tools and techniques for enabling availability of information resources including applications, data and data Infrastructure resources. Likewise there are many different aspects of RAID as well as context from legacy hardware based to cloud, virtual, container and software defined. In other words, not all RAID is in legacy storage systems, and there is a lot of FUD about RAID in general that is probably actually targeted more at specific implementations or products.

There are different approaches to meet various needs from stripe for performance with no protection by itself, to mirror and replication, as well as many parity approaches from legacy to erasure codes including Reed Solomon based as well as LRC among others. Which approach is best depends on your objects including balancing performance, availability, capacity economic (PACE) for normal running behavior as well as during faults and failure modes.

Get your copy of Software Defined Data Infrastructure Essentials here at Amazon.com, at CRC Press among other locations and learn more here. Meanwhile, continue reading with the next post in this series, Part 4 Data Protection Recovery Points (Archive, Backup, Snapshots, Versions).

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.

Data Protection Fundamentals Recovery Points (Backup, Snapshots, Versions)

Enabling Recovery Points (Backup, Snapshots, Versions)

Updated 1/7/18

Companion to Software Defined Data Infrastructure Essentials – Cloud, Converged, Virtual Fundamental Server Storage I/O Tradecraft ( CRC Press 2017)

server storage I/O data infrastructure trends

By Greg Schulzwww.storageioblog.com November 26, 2017

This is Part 4 of a multi-part series on Data Protection fundamental tools topics techniques terms technologies trends tradecraft tips as a follow-up to my Data Protection Diaries series, as well as a companion to my new book Software Defined Data Infrastructure Essentials – Cloud, Converged, Virtual Server Storage I/O Fundamental tradecraft (CRC Press 2017).

Software Defined Data Infrastructure Essentials Book SDDC

Click here to view the previous post Part 3 Data Protection Access Availability RAID Erasure Codes (EC) including LRC, and click here to view the next post Part 5 Point In Time Data Protection Granularity Points of Interest.

Post in the series includes excerpts from Software Defined Data Infrastructure (SDDI) pertaining to data protection for legacy along with software defined data centers ( SDDC), data infrastructures in general along with related topics. In addition to excerpts, the posts also contain links to articles, tips, posts, videos, webinars, events and other companion material. Note that figure numbers in this series are those from the SDDI book and not in the order that they appear in the posts.

In this post the focus is around Data Protection Recovery Points (Archive, Backup, Snapshots, Versions) from Chapter 10 .

SDDC, SDI, SDDI data infrastructure
Figure 1.5 Data Infrastructures and other IT Infrastructure Layers

Enabling RPO (Archive, Backup, CDP, PIT Copy, Snapshots, Versions)

SDDC SDDI Data Protection Points of Interests
Figure 9.5 Data Protection and Availability Points of Interest

RAID, including parity and erasure code (EC) along with mirroring and replication, provide availability and accessibility. These by themselves, however, are not a replacement for backup (or other point in time data protection) to support recovery points. For complete data protection the solution is to combine resiliency technology with point-in-time tools enabling availability and facilitate going back to a previous consistency time.

Recovery point protection is implemented within applications using checkpoint and consistency points as well as log and journal switches or flush. Other places where recovery-point protection occurs include in middleware, database, key-value stores and repositories, file systems, volume managers, and software-defined storage, in addition to hypervisors, operating systems, containers, utilities, storage systems, appliances, and service providers.

In addition to where, there are also different approaches, technologies, techniques, and tools, including archive, backup, continuous data protection, point-in-time copies, or clones such as snapshots, along with versioning.

Common recovery point Data Protection related terms, technologies, techniques, trends and topics pertaining to data protection from availability and access to durability and consistency to point in time protection and security are shown below.

Time interval protection for example with Snapshot, backup/restore, point in time copies, checkpoints, consistency point among other approaches can be scheduled or dynamic. They can also vary by how they copy data for example full copy or clone, or incremental and differential (e.g. what has changed) among other techniques to support 4 3 2 1 data protection. Other variations include how many concurrent copies, snapshots or versions can take place, along with how many stored and for how long (retention).

Additional Data Protection Terms

Copy Data Management ( CDM) as its name implies is associated managing various data copies for data protection, analytics among other activities. This includes being able to identify what copies exist (along with versions), where they are located among other insight.

Data Protection Management ( DPM) as its name implies is the management of data protection from backup/restore, to snapshots and other recovery point in time protection, to replication. This includes configuration, monitoring, reporting, analytics, insight into what is protected, how well it is protected, versions, retention, expiration, disposition, access control among other items.

Number of 9s Availability – Availability (access or durability or access and availability) can be expressed in number of nines. For example, 99.99 (four nines), indicates the level of availability (downtime does not exceed) objective. For example, 99.99% availability means that in a 24-hour day there could be about 9 seconds of downtime, or about 52 minutes and 34 seconds per year. Note that numbers can vary depending on whether you are using 30 days for a month vs. 365/12 days, or 52 weeks vs. 365/7 for weeks, along with rounding and number decimal places as shown in Table 9.1.

Uptime

24-hour Day

Week

Month

Year

99

0 h 14 m 24 s

1 h 40 m 48 s

7 h 18 m 17 s

3 d 15 h 36 m 15 s

99.9

0 h 01 m 27 s

0 h 10 m 05 s

0 h 43 m 26 s

0 d 08 h 45 m 36 s

99.99

0 h 00 m 09 s

0 h 01 m 01 s

0 h 04 m 12 s

0 d 00 h 52 m 34 s

99.999

0 h 00 m 01s

0 h 00 m 07 s

0 h 00 m 36 s

0 d 00 h 05 m 15 s

Table 9.1 Number of 9’s Availability Shown as Downtime per Time Interval

Service Level Objectives SLOs are metrics and key performance indicators (KPI) that guide meeting performance, availability, capacity, and economic targets. For example, some number of 9’s availability or durability, a specific number of transactions per second, or recovery and restart of applications. Service-level agreement (SLA) – SLA specifies various service level objectives such as PACE requirements including RTO and RPO, among others that define the expected level of service and any remediation for loss of service. SLA can also specify availability objectives as well as penalties or remuneration should SLO be missed.

Recovery Time Objective RTO is how much time is allowed before applications, data, or data infrastructure components need to be accessible, consistent, and usable. An RTO = 0 (zero) means no loss of access or service disruption, i.e., continuous availability. One example is an application end-to-end RTO of 4 hours, meaning that all components (application server, databases, file systems, settings, associated storage, networks) must be restored, rolled back, and restarted for use in 4 hours or less.

Another RTO example is component level for different data infrastructure layers as well as cumulative or end to end. In this scenario, the 4 hours includes time to recover, restart, and rebuild a server, application software, storage devices, databases, networks, and other items. In this scenario, there are not 4 hours available to restore the database, or 4 hours to restore the storage, as some time is needed for all pieces to be verified along with their dependencies.

Data Loss Access DLA occurs when data still exists, is consistent, durable, and safe, but it cannot be accessed due to network, application, or other problem. Note that the inverse is data that can be accessed, but it is damaged. Data Loss Event DLE is an incident that results in loss or damage to data. Note that some context is needed in a scenario in which data is stolen via a copy but the data still exists, vs. the actual data is taken and is now missing (no copies exist). Also note that there can be different granularity as well as scope of DLE for example all data or just some data lost (or damaged). Data Loss Prevention DLP encompasses the activities, techniques, technologies, tools, best practices, and tradecraft skills used to protect data from DLE or DLA.

Point in Time (PiT) such as PiT copy or data protection refers to a recovery or consistency point where data can be restored from or to (i.e., RPO), such as from a copy, snapshot, backup, sync, or clone. Essentially, as its name implies, it is the state of the data at that particular point in time.

Recovery Point Objective RPO is the point in time to which data needs to be recoverable (i.e., when it was last protected). Another way of looking at RPO is how much data you can afford to lose, with RPO = 0 (zero) meaning no data loss, or, for example, RPO = 5 minutes being up to 5 minutes of lost data.

SDDC SDDI RTO RPO
Figure 9.8 Recovery Points (point in time to recover from), and Recovery Time (how long recovery takes)

Frequency refers to how often and on what time interval protection is performed.

4 3 2 1 and 3 2 1 data protection rule
Figure 9.4 Data Protection 4 3 2 1 and 3 2 1 rule

In the context of the 4 3 2 1 rule, enabling RPO is associated with durability, meaning number of copies and versions. Simply having more copies is not sufficient because if they are all corrupted, damaged, infected, or contain deleted data, or data with latent nefarious bugs or root kits, then they could all be bad. The solution is to have multiple versions and copies of the versions in different locations to provided data protection to a given point in time.

Timeline and delta or recovery points are when data can be recovered from to move forward. They are consistent points in the context of what is/was protected. Figure 10.1 shows on the left vertical axis different granularity, along with protection and consistency points that occur over time (horizontal axis). For example, data “Hello” is written to storage (A) and then (B), an update is made “Oh Hello,” followed by (C) full backup, clone, and master snapshot or a gold copy is made.

SDDC SDDI Data Protection Recovery consistency points
Figure 10.1 Recovery and consistency points

Next, data is changed (D) to “Oh, Hello,” followed by, at time-1 (E), an incremental backup, copy, snapshot. At (F) a full copy, the master snapshot, is made, which now includes (H) “Hello” and “Oh, Hello.” Note that the previous full contained “Hello” and “Oh Hello,” while the new full (H) contains “Hello” and “Oh, Hello.” Next (G) data is changed to “Oh, Hello there,” then changed (I) to “Oh, Hello there I’m here.” Next (J) another incremental snapshot or copy is made, date is changed (K) to “Oh, Hello there I’m over here,” followed by another incremental (L), and other incremental (M) made a short time later.

At (N) there is a problem with the file, object, or stored item requiring a restore, rollback, or recovery from a previous point in time. Since the incremental (M) was too close to the recovery point (RP) or consistency point (CP), and perhaps damaged or its consistency questionable, it is decided to go to (O), the previous snapshot, copy, or backup. Alternatively, if needed, one can go back to (P) or (Q).

Note that simply having multiple copies and different versions is not enough for resiliency; some of those copies and versions need to be dispersed or placed in different systems or locations away from the source. How many copies, versions, systems, and locations are needed for your applications will depend on the applicable threat risks along with associated business impact.

The solution is to combine techniques for enabling copies with versions and point-in-time protection intervals. PIT intervals enable recovering or access to data back in time, which is a RPO. That RPO can be an application, transactional, system, or other consistency point, or some other time interval. Some context here is that there are gaps in protection coverage, meaning something was not protected.

A good data protection gap is a time interval enabling RPO, or simply a physical and logical break and the distance between the active or protection copy, and alternate versions and copies. For example, a gap in coverage (e.g. bad data protection gap) means something was not protected.

A protection air or distance gap is having one of those versions and copies on another system, in a different location and not directly accessible. In other words, if you delete, or data gets damaged locally, the protection copies are safe. Furthermore, if the local protection copies are also damaged, an air or distance gap means that the remote or alternate copies, which may be on-line or off-line, are also safe.

Good Data Protection Gaps
Figure 9.9 Air Gaps and Data Protection

Figure 10.2 shows on the left various data infrastructure layers moving from low altitude (lower in the stack) host servers or bare metal (BM) physical machine (PM) and up to higher levels with applications. At each layer or altitude, there are different hardware and software components to protect, with various policy attributes. These attributes, besides PACE, FTT, RTO, RPO, and SLOs, include granularity (full or incremental), consistency points, coverage, frequency (when protected), and retention.

SDDC SDDI Data Protection Granularity
Figure 10.2 Protecting data infrastructure granularity and enabling resiliency at various stack layers (or altitude)

Also shown in the top left of Figure 10.2 are protections for various data infrastructure management tools and resources, including active directory (AD), Azure AD (AAD), domain controllers (DC), group policy objects (GPO) and organizational units (OU), network DNS, routing and firewall, among others. Also included are protecting management systems such as VMware vCenter and related servers, Microsoft System Center, OpenStack, as well as data protection tools along with their associated configurations, metadata, and catalogs.

The center of Figure 10.2 lists various items that get protected along with associated technologies, techniques, and tools. On the right-hand side of Figure 10.2 is an example of how different layers get protected at various times, granularity, and what is protected.

For example, the PM or host server BIOS and UEFI as well as other related settings seldom change, so they do not have to be protected as often. Also shown on the right of Figure 10.2 are what can be a series of full and incremental backups, as well as differential or synthetic ones.

Figure 10.3 is a variation of Figure 10.2 showing on the left different frequencies and intervals, with a granularity of focus or scope of coverage on the right. The middle shows how different layers or applications and data focus have various protection intervals, type of protection (full, incremental, snap, differentials), along with retention, as well as some copies to keep.

SDDC SDDI Data Protection Granularity
Figure 10.3 Protecting different focus areas with various granularities

Protection in Figures 10.2 and 10.3 for the PM could be as simple as documentation of what settings to configure, versions, and other related information. A hypervisors may have changes, such as patches, upgrades, or new drivers, more frequently than a PM. How you go about protecting may involve reinstalling from your standard or custom distribution software, then applying patches, drivers, and settings.

You might also have a master copy of a hypervisors on a USB thumb drive or another storage device that can be cloned, customized with the server name, IP address, log location, and other information. Some backup and data protection tools also provide protection of hypervisors (or containers and cloud machine instances) in addition to the virtual machine (VM), guest operating systems, applications, and data.

The point is that as you go up the stack, higher in altitude (layers), the granularity and frequency of protection increases. What this means is that you may have more frequent smaller protection copies and consistency points higher up at the application layer, while lower down, less frequent, yet larger full image, volume, or VM protection, combining different tools, technology, and techniques.

Where To Learn More

Continue reading additional posts in this series of Data Infrastructure Data Protection fundamentals and companion to Software Defined Data Infrastructure Essentials (CRC Press 2017) book, as well as the following links covering technology, trends, tools, techniques, tradecraft and tips.

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What This All Means

Everything is not the same across different environments, data centers, data infrastructures, applications and their workloads (along with data, and its value). Likewise there are different approaches for enabling data protection to meet various SLO needs including RTO, RPO, RAS, FTT and PACE attributes among others. What this means is that complete data protection requires using different new (and old) tools, technologies, trends, services (e.g. cloud) in new ways. This also means leveraging existing and new techniques, learning from lessons of the past to prevent making the same errors.

RAID (mirror, replicate, parity including erasure codes) regardless of where and how implemented (hardware, software, legacy, virtual, cloud) by itself is not a replacement for backup, they need to be combined with recovery point protection of some type (backup, checkpoint, consistency point, snapshots). Also protection should occur at multiple levels of granularity (device, system, application, database, table) to meet various SLO requirements as well as different time intervals enabling 4 3 2 1 data protection.

Keep in mind what is it that you are protecting, why are you protecting it and against what, what is likely to happen, also if something happens what will its impact be, what are your SLO requirements, as well as minimize impact to normal operating, as well as during failure scenarios. For example do you need to have a full system backup to support recovery of an individual database table, or can that table be protected and recovered via checkpoints, snapshots or other fine-grained routine protection? Everything is not the same, why treat and protect everything the same way?

Get your copy of Software Defined Data Infrastructure Essentials here at Amazon.com, at CRC Press among other locations and learn more here. Meanwhile, continue reading with the next post in this series, Part 5 Point In Time Data Protection Granularity Points of Interest.

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.