The best prices for official DELL PowerEdge R760 servers in Ukraine.
Free consultation by phone +38 (067) 819 38 38
Available server models from the warehouse in Kyiv:
-
Server Dell PowerEdge R760 - Intel Xeon Silver 4510 2.4-4.1Ghz 12 Cores
-
Server Dell PowerEdge R760 - Intel Xeon Silver 4514Y 2.0-3.4Ghz 16 Cores
-
Server Dell PowerEdge R760 - Intel Xeon Gold 6526Y 2.8-3.9Ghz 16 Cores
-
Server Dell PowerEdge R760 - Intel Xeon Gold 5420+ 2.0-4.1Ghz 28 Cores
SAS storage technology has been the undisputed choice for enterprise data warehousing for two decades, thanks to its balance of performance and cost, high levels of reliability, and scalability. It uses SAS expanders as a cost-effective way to grow and manage extremely large data sets.
The struggle for speed
If only it were just about storage capacity. The demands of performance-critical applications led to the emergence of NVMe, a high-speed protocol for exchanging data with flash drives. Enterprise-grade NVMe SSDs outperform SAS-based media in terms of latency and are significantly more efficient in both sequential and random-access operations. Under intensive simultaneous requests, they are unmatched, because the protocol is built into the parallelization of I/O processing, and the PCIe bus provides direct CPU access to data across multiple lanes.
Technologies do not replace each other instantly. In addition, different drives have different roles in the data storage infrastructure. Standards coexist side by side for a long time. With a mixture of SAS and SATA drives, it is easier - they are controlled by the same controllers. Disk baskets, backplanes, cable management - everything is in common. NVMe SSDs are another matter. By their nature, they do not need intermediaries (controllers on the PCIe bus) that pass the data stream through themselves. Although the U.2 standard (2.5” NVMe SSD) has taken root in mass servers - for compatibility with typical hot-swap disk baskets, the server I/O subsystem has undergone radical changes. Hybrid backplanes with two switching sets, two signaling systems, and two cable bundles have appeared in servers: separately for SAS/SATA, separately for U.2.
False path Tri - mode / U.3
At the behest of and under the influence of RAID controller developers, the industry has taken a step down the deceptive path of "universality". A new generation of tri-mode RAID controllers is capable of supporting SAS/SATA/NVMe drives. The later proposed U.3 storage standard with universal 2.5" bays and auto-detection of disk types has strengthened the binding of disk subsystems to such controllers. Three-mode platform U.3 is built on a uniform backplane design and a single connector type. Its mandatory elements are: (1) a three-mode controller; (2) universal connectors; (3) a universal management structure (Universal Bus Management).
The apparent usefulness of automatic disk type detection, single cable connection and data traffic routing turned out to be an illusion. Even the joint use of SAS and SATA disks under one controller is a rarity. Adding NVMe to this combination makes even less sense - connecting a Tri-mode controller to the PCIe bus with a maximum of 16 lines kills the performance potential (one NVMe requires four lines). There is no mention of its scalability. Such controllers are significantly more expensive than their SAS/SATA predecessors - which in itself devalues the arguments about saving on cables and user comfort.
Separation of powers
In the U.2 connector, SAS/SATA lines are separated from NVMe lines, allowing system designers to independently scale the solution using available SAS expanders and PCIe switches. For example, ASUS 2U / 24 x 2.5” server platforms are NVMe-ready, all drive bays accept U.2 or U.3 SSDs. Some of them are connected to SATA ports on the motherboard. By adding a hardware HBA or RAID controller, 8 bays can accommodate SAS/SATA SSDs (HDDs).
Since Tri-mode RAID controllers limit the capabilities of NVMe, the search for performance solutions is aimed at unlocking the potential of flash drives by increasing parallelism, bus and processing devices. Hunting for productivity excludes the unification of the SAS and NVMe worlds with common elements of utility storage. Outside the computing host, everything is separate: connection circuitry, cable management, data protection mechanisms using RAID.
NVMe above all else
Everything is going to the point where application servers with mostly “hot” data will completely switch to NVMe. There is not much of such data, and it is not difficult to get several dozen terabytes of high-capacity NVMe SSDs (and not so expensive, given the purpose of the servers). 1U / 10-12 x 2.5” platforms for U.2/U.3 SSDs, single or dual processor, are becoming the basis of database servers, high-speed computers, analytics servers, hyperconverged infrastructure nodes. There is no room for SAS/SATA SSDs there, let alone HDDs.
Fate HDD
High-capacity mechanical disks remain carriers of "cold" data: film libraries, video surveillance systems, backup storage, archives. When HDDs make up the bulk of the budget, the specific cost of storage is crucial. Typically, such systems are dominated by streaming operations with sequential data access, where the advantages of SSDs are almost imperceptible - so they are not there.
If you need to accommodate hundreds of terabytes of data, modular distribution is appropriate: the management server is separate, mechanical disks are separate - in a JBOD shelf, connected to the host via 12G SAS. This achieves high storage density and comfortable conditions for the disks are provided. JBOD anatomy resists the two main enemies of HDD - induced vibration and overheating. A modern JBOD can accommodate dozens of 3.5" hot-swappable disks, has duplicated I/O modules and several SAS ports for connecting hosts and other shelves. Storage capacity is scaled by cascading them.
An example is the popular line WD Ultrastar Data60 with a capacity of up to one and a half petabytes in 4U.
Traveling
The distribution of roles and "housing" between carriers of different types is logical when building a large, productive ZFS storage. There is no alternative to mechanical disks in bulk storage. But in addition to the main data pools, there is auxiliary data: the second-level adaptive swap cache L2ARC, the ZIL write intent log (SLOG), metadata (tables, indexes, pointers that define the address structure of the pools). Usually they are mixed with the main data on the same (slow) media. The performance drop from co-location can be reduced by storing auxiliary data on SATA SSD or NVMe. Such separation speeds up addressing, reading, and helps protect data without losing performance.
Developers of the most common (thanks to open source) storage OS TrueNAS on the OpenZFS file system give an example: "The optimal SLOG device is a small flash-based device such as an SSD or NVMe card, due to their inherent high performance, low latency, and of course, resilience in the event of a power loss. You can mirror your SLOG devices as an extra precaution and you will be surprised at the speed boost you can get with just a few gigabytes of separate log storage. Your storage pool will have the write performance of an all-flash array with the capacity of a traditional mechanical disk array. That's why we ship every TrueNAS mechanical disk system with SLOG on high-performance flash, a standard option in our FreeNAS Certified line."
So we make a capacious JBOD the "body" of storing hundreds of terabytes of data. We connect it via 12G SAS to the "head" - a 1U server with CPU, RAM, network cards and NVMe sets for auxiliary data. We configure. We enjoy the performance.
How can we help?
Server Solutions sells Dell PowerEdge R760 and Dell PowerEdge R760xs servers throughout Ukraine, our clients include small, medium and large businesses. If you or your company needs advice and the purchase of quality server equipment, then you should contact us.