All-Flash Arrays: The future of data storage?
In the newfound age of big data, it is no wonder that there is an ever-increasing demand for better storage and speed. With the recent introduction of All-Flash Arrays to the market - selling themselves as the perfect solution to handle big data - and the falling prices of both Flash NAND chips and SSDs (solid state disks), a few questions have arisen about this newbie storage solution...
What is an All-Flash Array?
Simply put an All-Flash Array is a solid state storage disk system that contains multiple Flash drives instead of traditional spinning hard disks.
Why should I go for an All-Flash Array?
This is not an easy question to answer as, like most things, everything in technology has its advantages and disadvantages. All Flash Arrays are used mostly for transactional or extremely high throughput applications where speed and time are crucial, for example, financial trades, large e-commerce sites and on-demand streaming services. Here the input and output (I/O) ratio the application requires is the main thing to consider, and since the I/O rates of normal, enterprise hard disk drives remain unchanged and low for a couple of years now, All-Flash Arrays seem to be the answer here.
Regarding I/O speeds per second, DellEMC quotes IDC; a system that needs 200,000 IOPS (inputs/outputs per second) to run an application on, only needs 10 high-end SSDs compared to 1,000 HDDs. This means that fewer servers in total are needed to have the same performance as before. Additionally, less energy is consumed by an All-Flash solution, as well as less storage administration time being wasted, which is the time that (in the case of a server farm), could add up to a lot of money being saved or spent elsewhere.
With newly designed storage controllers built inside modern systems, All Flash Arrays have all the necessary features that HDD based systems have, including deduplication, compression, thin provisioning, snapshots, clones, RAID, encryption, and API support. With built-in RAID support, the user is, therefore, able to construct a normal RAID 5 out of several SSDs, with the data security that such a system provides.
What are the disadvantages of All-Flash Arrays?
So, when I/O speed and time are the main benefits of All-Flash Arrays, what are the disadvantages?
That´s quite simple: the price! Even though flash and SSDs have become cheaper they’re still more expensive compared to HDDs. So, buying a new All-Flash Array can be a costly experience compared to a normal HDD system, meaning you will only see value for money after long-term usage.
The other disadvantage is that SSD based systems such as All-Flash Arrays have a technological downside: flash chips are best when data is only written on them once and then read many times. Flash chips only have a specified life-span based on data writes, so the trick is to make a few writing processes as possible to extend the lifespan of an All-Flash Array.
The other technical problem is the SSD trim command.
The SSD trim command is a technique to avoid written inputs/outputs (I/O) that makes the lifespan of a flash chip shorter. Trim allows the operating system to flag blocks of data to be erased when they have been released from the local file system. That means that the process of automatic erasing starts way in advance before new data is written on the 'empty‘ storage space.
Because of these facts and to avoid loss of data that is needed in the future, this type of storage isn’t really suitable for businesses looking to archive data for compliance or legal reasons. In most cases, flash-based systems should only be used in environments where data is only read or analysed; a great example of this is streaming servers like YouTube and Netflix.
All-Flash Array’s would also be ideal for big data analysis or running large databases. For data that needs to be either stored permanently or is being changed frequently, the best choice would be a disk-based storage, a server, or a hybrid storage solution, which consists of both media types - SSDs as well as traditional hard disk drives (HDDs).
This way, the data that is frequently analysed but not changed can run through the SSDs, while the data that is constantly amended can be stored within the disks. Or the data that is most likely to be accessed is stored on the faster flash chips, while the other data is based on a traditional HDD; this way chances that crucial data being lost is minimised.
What to do if you lose data
If data is lost on an All-Flash Array, there is still the chance that a professional data recovery service provider like Ontrack will be able to recover the files. In many cases, the data structure is the same as with a normal low-end RAID system and can, therefore, be reconstructed. Additionally, data recovery experts have special tools to rebuild a RAID-based or special high-end data structure, so that the data can be found and made accessible again.
If data is lost, you should immediately stop running the system, try to shut it down the usual way (with no sudden power outage) and then contact a data recovery specialist as fast as you can. DIY attempts to recover data from this type of storage can often make the situation worse.
However, as pointed out before, recovery is only possible when the built-in trim command system is either inactive or space where the lost data was originally located was not used for saving new data. Otherwise, even the most experienced data recovery expert cannot do anything for you in those situations.
Do you have an All-Flash Array? Is it the best storage solution for you? Tell us why by tweeting us @OntrackUKIE.
Find more information on All-Flash Arrays here: https://searchstorage.techtarget.com/essentialguide/Flash-storage-Guide-to-enterprise-all-flash-storage-arrays
Picture copyright: Sebastian von Thadden / pixelio.de
Name: Datacenter3: https://www.pixelio.de/media/33466