Is it possible to get away from HDD in hosting servers?

The fact that hosting is very expensive in terms of disk space, perhaps, is no surprise to anyone. As well as the fact that the solutions used for data storage in this case should be as quickly as possible. Therefore, ideally, for such storage it would be good to use only SSD, but in very many cases this is an unattainable ideal, primarily because of the high (albeit declining) price. Especially tough price issue is for large data centers .

Hybrid solutions that combine traditional HDD and flash drives for caching can help in this situation.

This short note is devoted to two functions in the new firmware for the NytroMegaRAID controllers. We already wrote about LSI Nytro and its practical application , but I will briefly remind you what NytroMegaRAID is.
')
The MegaRAID platform is fairly well known - for many years, LSI RAID controllers have been sold under this name. About three years ago, we announced the industry's first 6Gb / s controllers. The power of the processors used in the controllers of this series, has reached such indicators that it was decided to direct the free processor resources to support advanced functions, called Advanced Software Options.

Advanced Software Options includes four storage applications: CaheCade, FastPath, Recovery, and SafeStore. The most interesting and popular among users was the CacheCade package, which allows you to create additional cache on high-speed SSD. This application experienced two releases, the first of which (CaheCade 1.1) allowed using the SSD pool only as a read cache, and the second (CacheCade 2.0) allowed using the SSD cache and writing, along with the ability to configure RAID-10 to cache group.

The main problem when using CacheCade has become an immature SSD market. Perhaps some companies still use the excellent product from Intel X25E - SLCSSD disk with remarkable characteristics, both for writing and reading. A complete surprise to many was his disappearance from the market and the replacement with cheaper, but slower (especially on record) devices of the 3rd and 5th series.

We learned a lesson from this, and released a product that already contains SSD onboard, the parameters of which allow us to use them for caching. This product is called NytroMegaRAID 1.0, and it is its firmware version 1.5 and contains two innovations in question.



So, CacheCade 2.0 offered two types of configurations for the caching group. RAID0 and RAID10. In the first case, if one of the SSDs fails, we lose the entire cache group. This means, in the case of read caching, a return to the original performance level, and in the case of a write cache, data loss. Therefore, the ability to configure the cache group in RAID-10 was introduced to enable write cache. The loss of one of the drives no longer leads to data loss when caching records.

The unpleasant fact in this case is that we only use 50% of the valuable SSD capacity. Imagine that you can divide the cache into a record and into a read. In this case, the need for duplication of information for fault tolerance is only for the write cache. The read cache can only be located on one of the devices, since its loss does not lead to data loss. We are going to implement this function in NMR 1.5 called Elastic Cache. In case the ratio of read and write caches is 50:50, the “effective volume” of the cache will be equal to 75% of the total cache group capacity. Usually, for databases (applications for which SSD caching is the most efficient), the ratio of readings to records is 70:30 (85% of the effective capacity). For Exchange and other mail systems, the number of write operations is even smaller, so you can use SSD even more efficiently.

The second innovation was the ability to boot from the regular SSD controller NytroMegaRAID. To do this, you can select the boot area in which users can place the boot image of the OS or hypervisor. That is, now it will be possible to start completely without disks. Of course, there are cheaper solutions for diskless booting, and our solution is not exactly for that.

Where can this function be applied? Many hosting companies, as well as companies implementing VDI (in both cases, caching shows itself to be very efficient), have to waste precious (especially in the case of virtualization) HDD slots for boot disks, instead of placing user data there. In such configurations, the boot function with SSD will perfectly help to solve configuration difficulties.



Answering the title question of the article, I will say the following. Of course, hard drives are still needed to store large data arrays, but we learned how to use them in conjunction with SSDs, creating hybrid arrays that combine the advantages of both technologies, HDD (price per GB) and SSD (speed of arbitrary input-output operations) . Many have become accustomed to the fact that modern laptops / ultrabooks are loaded in seconds, using the advantages of SSD, now there is a queue of servers. We recently conducted a visual demonstration of Nytro solutions, showing its capabilities on a test bench .