{"id":8473,"date":"2022-12-04T14:48:33","date_gmt":"2022-12-04T12:48:33","guid":{"rendered":"https:\/\/tekmart.co.za\/t-blog\/?p=8473"},"modified":"2022-12-04T14:48:34","modified_gmt":"2022-12-04T12:48:34","slug":"what-works-best-with-solid-state-on-raid-flash-and-erasure-coding","status":"publish","type":"post","link":"https:\/\/tekmart.co.za\/t-blog\/what-works-best-with-solid-state-on-raid-flash-and-erasure-coding\/","title":{"rendered":"What works best with solid state on RAID, flash and erasure coding?"},"content":{"rendered":"Reading Time-approximately:<\/span> 4<\/span> minutes<\/span><\/span>\n

We look at RAID and flash to highlight key choices when it comes to drive data protection. What RAID levels work best with solid state and when is erasure coding a good choice?<\/strong><\/h2>\n\n\n\n

By Stephen Pritchard<\/a><\/p>\n\n\n\n

RAID systems\u00a0have been the building blocks of enterprise storage since the 1990s.\u00a0But\u00a0RAID\u00a0\u2013 redundant array of inexpensive disks \u2013 originated the decade before that in research from the University of California, Berkeley.<\/p>\n\n\n\n

Researchers at Berkeley pioneered the use of low-cost personal computer drives for critical data. By combining drives in an array, they overcame the speed and reliability limitations of PC hard disks, and brought them closer to the performance of vastly more expensive mainframe drives.<\/p>\n\n\n\n

For three decades,\u00a0RAID-based disk\u00a0has provided most storage for servers, backup and archiving, and even cloud computing. But with flash storage falling in cost, and growing in capacity, is RAID still relevant?<\/strong><\/p><\/blockquote><\/figure>\n\n\n\n

Increasingly, suppliers have developed more complex RAID levels to suit SSD media, while alternative data protection protocols such as\u00a0erasure coding\u00a0have gained ground among cloud providers and operators of hybrid and object storage.<\/p>\n\n\n\n

RAID levels<\/strong><\/h3>\n\n\n\n

RAID systems protect data in two main ways \u2013 either by\u00a0mirroring a physical disk in its entirety, or by storing\u00a0parity data\u00a0on one or more disks that is used\u00a0to rebuild a failed drive.<\/p>\n\n\n\n

System designers that build RAID arrays need to balance performance, resiliency and the capacity overhead of either the mirror or the parity data. At its simplest, RAID 1, or mirroring, simultaneously copies all data to two or three drives. The capacity overhead \u2013 the amount of additional storage needed for the mirrors \u2013 is therefore either 100% or 200% of the usable storage.<\/p>\n\n\n\n

Other RAID levels\u00a0aim to reduce the storage overhead and therefore the cost without an undue performance penalty. RAID 1 provides the best performance and, critically, the fastest rebuild times with no need to recreate data using parity bits.<\/p>\n\n\n\n

RAID 4 uses block-level striping, and stores parity data on a single drive. RAID 5 uses striping with distributed parity without the need for a dedicated parity disk. RAID 6 uses dual distributed parity for additional data protection.\u00a0RAID 10\u00a0combines mirroring and\u00a0striping.<\/p>\n\n\n\n

RAID levels 2 and 3 are rarely used today in enterprise systems. A number of suppliers now have proprietary RAID systems, with the goal of reducing the capacity overhead still further than RAID 5 or RAID 6.<\/p>\n\n\n\n

Is RAID relevant for flash storage?<\/strong><\/h3>\n\n\n\n

In performance terms alone, RAID is not an obvious choice for flash-based storage. Single media performance easily beats RAID in almost all common enterprise scenarios.<\/p>\n\n\n\n

\n

\u201cSAS SSDs using NAND flash offer an order of magnitude lower latency and one to two orders of magnitude higher throughput, depending on whether we\u2019re talking about random or sequential reads,\u201d says Eric Burgener, research vice-president in IDC\u2019s enterprise infrastructure practice.<\/p>\n<\/blockquote>\n\n\n\n

But in terms of cost, flash media is still significantly more expensive than spinning disk.<\/p>\n\n\n\n

Leaving aside flash media\u2019s generally lower capacity per drive, which necessitates the use of larger arrays, SSDs are\u00a0seven to eight times more expensive than equivalent spinning disks.<\/p>\n\n\n\n

Although this does not rule out RAID 1 or RAID 10 for flash-based arrays, it will limit it to applications with little tolerance for data loss, and a need for short restore times.<\/p>\n\n\n\n

\u201cRAID 1 provides the best performance if you\u2019re using it locally \u2013 you only have two writes, or three if you\u2019re running three mirrors,\u201d says Burgener. \u201cIt provides the least impact in recovery mode, as you only have to read from one device and don\u2019t have to perform any computation to \u2018reconstruct\u2019 the data. But it\u2019s the most expensive.\u201d<\/p>\n\n\n\n

RAID 5 and 6: A practical option for flash<\/strong><\/h3>\n\n\n\n

Those high costs prompted researchers to develop RAID 4, 5 and 6. The technologies are now mature because storage system suppliers cut their teeth when spinning disks were smaller and costlier than they are today. Much of that work translates well to the flash storage world.<\/p>\n\n\n\n

\u201cThis high cost of redundancy is one of the reasons RAID levels like RAID 4, 5 or 6 or erasure coding approaches were developed,\u201d says Burgener. \u201cThey offer a much lower capacity overhead, but they tend to have more of an impact in recovery mode, as data must be read from multiple devices and computation must be performed on that data using one or more parity stripes.\u201d<\/p>\n\n\n\n

However, these disadvantages are overcome, to an extent, by flash storage\u2019s higher performance, especially in reads. The downside remains that a significant percentage of expensive flash storage is set aside for the parity data. In a RAID 6 system, with a standard layout of 4+2 (four data bits and two parity bits), the overhead is one-third of the storage.<\/p>\n\n\n\n

For mainstream systems, and where data storage needs are relatively modest \u2013 up to around 20TB \u2013 RAID 6 is likely to suffice. Most IT architects calculate that the greater resilience of\u00a0RAID 6\u00a0is worth the cost increase or capacity penalty over\u00a0RAID 5. RAID 10 is also an option, typically for the most latency-sensitive applications and for high availability.<\/p>\n\n\n\n

Data protection for all-flash arrays and the cloud<\/strong><\/h3>\n\n\n\n

Even so, suppliers are developing new forms of data protection that are better suited to flash-based storage, by cutting the capacity overhead. These systems also exploit the smaller average drive size for flash, to distribute parity data across more volumes.<\/p>\n\n\n\n

Vendors of all-flash arrays have largely offered RAID 6 to date, but a number of companies have challenged this with new technologies.<\/p>\n\n\n\n

Kaminario, for example, uses a 22+2 format for its all-flash arrays. This cuts the overhead, but only works with arrays with 24 or more drives.<\/p>\n\n\n\n

VAST Data combines Intel Optane SSDs and QLC SSDs and uses a very economical 150+4 design, which works out at an overhead of around 2%. But the minimum system capacity is 1PB.<\/p>\n\n\n\n

Erasure coding<\/strong><\/h3>\n\n\n\n

Adoption of\u00a0erasure coding\u00a0has been driven by the large cloud platforms, but it is becoming more common in hybrid and on-premise object storage. Erasure coding is likely to be more common, not least because it gives enterprises more control over the level of protection they want, as well as physical redundancy.<\/p>\n\n\n\n

The downside of erasure coding has largely been performance, although with all-flash storage performance, that gap has narrowed.<\/p>\n\n\n\n

Data decay: Different architectures<\/strong><\/h3>\n\n\n\n

Flash systems do, however, have some key technical differences that affect the design of RAID schemes.<\/p>\n\n\n\n

Flash storage deteriorates the more it is used, and that is more the case with writes than reads. Newer but cheaper flash media, such as\u00a0quad-level cell (QLC), has a shorter write life than previous generations of NAND flash. But enterprise applications can be write-intensive, so hardware designers have to create techniques to minimise the writes and extend the system\u2019s working life.<\/p>\n\n\n\n

This is not something that happens with spinning disk, so IT departments cannot simply \u201clift and shift\u201d workloads from conventional to flash arrays and expect the same levels of protection.<\/p>\n\n\n\n

\u201cWhen designing data protection algorithms for flash-based data, you have some new inputs \u2013 much lower latency and higher throughput, but much lower endurance,\u201d says Burgener. \u201cSo schemes that minimise writes are more interesting.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"

Reading Time-approximately:<\/span> 4<\/span> minutes<\/span><\/span>We look at RAID and flash to highlight key choices when it comes to drive data protection. What RAID levels work best with solid state and when is erasure coding a good choice? By Stephen Pritchard RAID systems\u00a0have been the building blocks of enterprise storage since the 1990s.\u00a0But\u00a0RAID\u00a0\u2013 redundant array of inexpensive disks \u2013 originated the decade before that in<\/p>\n

Read More<\/a><\/p>\n","protected":false},"author":115,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[121,38,150,334,35,8,258,4,30,3,123,284],"tags":[],"class_list":["post-8473","post","type-post","status-publish","format-standard","hentry","category-archiving-and-backup","category-best-practices-for-data-center-operations","category-cloud-storage","category-cloud-storage-management-and-standards","category-data-center-facilities","category-data-center-hardware","category-data-protection-backup-and-archiving","category-datacenter-news","category-expert-advise-and-opinion","category-industry-news-and-expert-advise","category-it-compliance-and-governance-strategies","category-web-application-and-api-security-best-practices"],"_links":{"self":[{"href":"https:\/\/tekmart.co.za\/t-blog\/wp-json\/wp\/v2\/posts\/8473","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/tekmart.co.za\/t-blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/tekmart.co.za\/t-blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/tekmart.co.za\/t-blog\/wp-json\/wp\/v2\/users\/115"}],"replies":[{"embeddable":true,"href":"https:\/\/tekmart.co.za\/t-blog\/wp-json\/wp\/v2\/comments?post=8473"}],"version-history":[{"count":1,"href":"https:\/\/tekmart.co.za\/t-blog\/wp-json\/wp\/v2\/posts\/8473\/revisions"}],"predecessor-version":[{"id":8474,"href":"https:\/\/tekmart.co.za\/t-blog\/wp-json\/wp\/v2\/posts\/8473\/revisions\/8474"}],"wp:attachment":[{"href":"https:\/\/tekmart.co.za\/t-blog\/wp-json\/wp\/v2\/media?parent=8473"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/tekmart.co.za\/t-blog\/wp-json\/wp\/v2\/categories?post=8473"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/tekmart.co.za\/t-blog\/wp-json\/wp\/v2\/tags?post=8473"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}