2nd Gen AMD EPYC now available to power your favorite hyperconverged platform ;) VxRail
Mon, 27 Jul 2020 18:46:53 -0000|
Read Time: 0 minutes
Expanding the range of VxRail choices to include 64-cores of 2nd Gen AMD EPYC compute
Last month, Dell EMC expanded our very popular E Series (the E for Everything Series) with the introduction of the E665/F/N, our very first VxRail with an AMD processor, and what a processor it is! The 2nd Gen AMD EPYC processor came to market with a lot of industry-leading capabilities:
- Up to 64-cores in a single processor with 8, 12, 16, 24, 32 or 48 core offerings also available
- Eight memory channels, but not only more channels, they are also faster at 3200MT/s. The 2nd Gen EPYC can also address much more memory per processor
- 7nm transistors. Smaller transistors mean more powerful and more energy efficient processors
- Up to 128 lanes of PCIe Gen 4.0, with 2X the bandwidth of PCIe Gen 3.0.
These industry leading capabilities enable the VxRail E665 series to deliver dual socket performance in a single socket model - and can provide up to 90% greater general-purpose CPU capacity than other VxRail models when configured with single socket processors.
So, what is the sweet spot or ideal use case for the E665? As always, it depends on many things. Unlike the D Series (our D for Durable Series) that we also launched last month, which has clear rugged use cases, the E665 and the rest of the E Series very much live up to their “Everything” name, and perform admirably in a variety of use cases.
While the 2nd Gen EPYC 64-core processors grab the headlines, there are multiple AMD processor options, including the 16 core AMD 7F52 at 3.50GHz with a max boost of 3.9GHz for applications that benefit from raw clock speed, or where application licensing is core based. On the topic of licensing, I would be remiss if I didn’t mention VMware’s update to its per-CPU pricing earlier this year. This results in processors with more then 32-cores requiring a second VMware per-CPU license. This may make a 32-core processor an attractive option from an overall capacity & performance verses hardware & licensing cost perspective.
Speaking of overall costs, the E665 has dual 10Gb RJ45/SFP+ or dual 25Gb SFP28 base networking options, which can be further expanded with PCIe NICs including a dual 100Gb SFP28 option. From a cost perspective, the price delta between 10Gb and 25Gb networking is minimal. This is worth considering particularly for greenfield sites and even for brownfield sites where the networking maybe upgraded in the near future. Last year, we began offering Fibre Channel cards on VxRail, which are also available on the E665. While FC connectivity may sound strange for a hyperconverged infrastructure platform, it does make sense for many of our customers who have existing SAN infrastructure, or some applications (PowerMax for extremely large database requiring SRDF) or storage needs (Isilon for large file repository for medical files) that are more suited to SAN. While we’d prefer these SAN to be a Dell EMC product, as long as it is on the VMware SAN HCL, it can be connected. Providing this option enables customers to get the best both worlds have to offer.
The options don’t stop there. While the majority of VxRail nodes are sold with all-flash configurations, there are customers whose needs are met with hybrid configs, or who are looking towards all-NVMe options. The E665 can be configured with as little as 960GB to maximums of 14TB hybrid, 46TB all-flash, or 32TB all-NVMe of raw storage capacity. Memory options consist of 4, 8, or 16 RDIMMs of 16GB, 32GB or 64GB in size. Maximum memory performance, 3200 MT/s, is achieved with one DIMM per memory channel, adding a second matching DIMM reduces bandwidth slightly to 2933 MT/s.
VxRail and Dell Technologies, very much recognize that the needs of our customers vary greatly. A product with a single set of options cannot meet all our various customers’ different needs. Today, VxRail offers six different series, each with a different focus:
- Everything E Series a power packed 1U of choice
- Performance-focused P Series with dual or quad socket options
- VDI-focused V Series with a choice of five different NIVIDA GPUs
- Durable D Series are MIL-STD 810G certified for extreme heat, sand, dust, and vibration
- Storage-dense S Series with 96TB of hybrid storage capacity
- General purpose and compute dense G Series with 228 cores in a 2U form factor
With the highly flexible configuration choices, there is a VxRail for almost every use case, and if there isn’t, there is more than likely something in the broad Dell Technologies portfolio that is.
Author: David Glynn, Sr. Principal Engineer, VxRail Tech Marketing
Related Blog Posts
Top benefits to using Intel Optane NVMe for cache drives in VxRail
Wed, 20 May 2020 14:42:17 -0000|
Read Time: 0 minutes
Performance, endurance, and all without a price jump!
There is a saying that “A picture paints a thousand words” but let me add that a “graph can make for an awesome picture”.
Last August we at VxRail worked with ESG on a technical validation paper that included, among other things, the recent addition of Intel Optane NVMe drives for the vSAN caching layer. Figure 3 in this paper is a graph showing the results of a throughput benchmark workload (more on benchmarks later). When I do customer briefings and the question of vSAN caching performance comes up, this is my go-to whiteboard sketch because on its own it paints a very clear picture about the benefit of using Optane drives – and also because it is easy to draw.
In the public and private cloud, predictability of performance is important, doubly so for any form of latency. This is where caching comes into play, rather than having to wait on a busy system, we just leave it in the write cache inbox and get an acknowledgment. The inverse is also true. Like many parents I read almost the same bedtime stories to my young kids every night, you can be sure those books remain close to hand on my bedside “read cache” table. This write and read caching greatly helps in providing performance and consistent latency. With vSAN all-flash there no longer any read cache as the flash drives at the capacity layer provide enough random read access performance… just as my collection of bedtime story books has been replaced with a Kindle full of eBooks. Back to the write cache inbox where we’ve been dropping things off – at some point, this write cache needs to be empty, and this is where the Intel Optane NVMe drives shine. Drawing the comparison back to my kids, I no longer drive to a library to drop off books. With a flick of my finger I can return, or in cache terms de-stage, books from my Kindle back to the town library - the capacity drives if you will. This is a lot less disruptive to my day-to-day life, I don’t need to schedule it, I don’t need to stop what I’m doing, and with a bit of practice I’ve been able to do this mid story Let’s look at this in actual IT terms and business benefits.
To really show off how well the Optane drives shine, we want to stress the write cache as much as possible. This is where benchmarking tools and the right knowledge of how to apply them come into play. We had ESG design and run these benchmarking workloads for us. Now let’s be clear, this test is not reflective of a real-world workload but was designed purely to stress the write cache, in particular the de-staging from cache to capacity. The workload that created my go-to whiteboard sketch was the 100% sequential 64KB workload with a 1.2TB working set per node for 75 minutes.
The graph clearly shows the benefit of the Optane drives, they keep on chugging at 2,500MB/sec of throughput the entire time without dropping a beat. What’s not to like about that! This is usually when the techie customer in the room will try to burst my bubble by pointing out the unrealistic workload that is in no way reflective of their environment, or most environments… which is true. A more real-world workload would be a simulated relational database workload with a 22KB block size, mixing random 8K and sequential 128K I/O, with 60% reads and 40% writes, and a 600GB per node working set, which is quite a mouthful and is shown in figure 5. The results there show a steady 8.4-8.8% increase in IOPS across the board and a slower rise in latency resulting in a 10.5% lower response time under 80% load.
Those of you running OLTP workloads will appreciate the graph shown in figure 6 where HammerDB was used to emulate the database activity of a typical online brokerage firm. The Optane cache drives under that workload sustained a remarkable 61% more transactions per minute (TPM) and new orders per minute (NOPM). That can result in significant business improvement for an online brokerage firm who adopts Optane drives versus one who is using NAND SSDs.
When it comes to write cache, performance is not everything, write endurance is also extremely important. The vSAN spec requires that cache drives be SSD Endurance Class C (3,650 TBW) or above, and Intel Optane beats this hands down with an over tenfold margin at 41 PBW (41,984 TBW). The Intel Optane 3D XPoint architecture allows memory cells to be individually addressed in a dense, transistor-less, stackable design. This extremely high write endurance capability has let us spec a smaller sized cache drive, which in turn lets us maintain a similar VxRail node price point, enabling you the customer to get more performance for your dollar.
What’s not to like? Typically, you get to pick any two; faster/better/cheaper. With Intel Optane drives in your VxRail you get all three; more performance and better endurance, at roughly the same cost. Wins all around!
Author: David Glynn, Sr Principal Engineer, VxRail Tech Marketing
Building on VxRail HCI System Software: the advantages of multi-cluster active management capabilities
Tue, 29 Sep 2020 19:03:05 -0000|
Read Time: 0 minutes
The signs of autumn are all around us, from the total takeover of pumpkin-spiced everything to the beautiful fall foliage worthy of Bob Ross’s inspiration. Like the amount of change autumn brings forth, so too does the latest release of VxRail ACE, or should I preface that with ‘formerly known as’? I’ll get to that explanation shortly.
This release introduces multi-cluster update functionality that will further streamline the lifecycle management (LCM) of your VxRail clusters at scale. With this active management feature comes a new licensing structure and role-based access control to enable the active management of your clusters.
Formerly known as VxRail ACE
The colors of the leaves are changing and so is the VxRail ACE name. The brand name VxRail ACE (Analytical Consulting Engine), will no longer be used as of this release. While it had a catchy name and was easy to say, there are two reasons for this change. First, Analytical Consulting Engine no longer describes the full value or how we intend to expand the features in the future. It has grown beyond the analytics and monitoring capabilities of what was originally introduced in VxRail ACE a year ago and now includes several valuable LCM operations that greatly expand its scope. Secondly, VxRail ACE has always been part of the VxRail HCI System Software offering. Describing the functionality as part of the overall value of VxRail HCI System Software, instead of having its own name, simplifies the message of VxRail’s value differentiation.
Going forward, the capability set (that is, analytics, monitoring, and LCM operations) will be referred to as SaaS multi-cluster management -- a more accurate description. The web portal is now referred to as MyVxRail.
Cluster updates is the first active management feature offered by SaaS multi-cluster management. It builds on the existing LCM operational tools for planning cluster updates: on-demand pre-update health checks (LCM pre-check) and update bundle downloads and staging. Now you can initiate updates of your VxRail clusters at scale from MyVxRail. The benefits of cluster updates on MyVxRail tie closely with existing LCM operations. During the planning phase, you can run LCM pre-checks of the clusters you want to update. This informs you if a cluster is ready for an update and pinpoints areas for remediation for clusters that are not ready. From there, you can schedule your maintenance window to perform a cluster update and, from MyVxRail, initiate the download and staging of the VxRail update bundle onto those clusters. With this release, you can now execute cluster updates for those clusters. Now that’s operational efficiency!
When setting a cluster update operation, you have the benefit of two pieces of information – a time estimate for the update and the change data. The update time estimate will help you determine the length of the maintenance window. The estimate is generated by telemetry gathered about the install base to provide more accurate information. The change data is the list of the components that require an update to reach the target VxRail version.
Figure 1 MyVxRail Updates tab
Role-based access control
Active management requires role-based access control so that you can provide permissions to the appropriate individuals to perform configuration changes to your VxRail clusters. You don’t want anyone with access to MyVxRail to perform cluster updates on the clusters. SaaS multi-cluster management leverages vCenter Access Control for role-based access. From MyVxRail, you will be able to register MyVxRail with the vCenter Servers that are managing your VxRail clusters. The registration process will give VxRail privileges to vCenter Server to build roles with specific SaaS multi-cluster management capabilities.
MyVxRail registers the following privileges on vCenter:
- Download software bundle: downloads and stages the VxRail software bundle onto the cluster
- Execute health check: performs an on-demand pre-update health check on the cluster
- Execute cluster update: initiates the cluster update operation on the clusters
- Manage update credentials: modifies the VxRail infrastructure credentials used for active management
Figure 2 VxRail privileges for vCenter access control
VxRail Infrastructure Credentials
We’ve done more to make it easier to perform cluster updates at scale. Typically, when you’re performing a single cluster update, you have to enter the root account credentials for vCenter Server, Platform Services Controller, and VxRail Manager. That’s the same process when performing it from VxRail Manager. But that process can get tedious when you have multiple clusters to update.
VxRail Infrastructure Credentials can store those credentials so you can enter them once, at the initial setup of active management, and not have to do it again as you perform a multi-cluster update. MyVxRail can read the stored credentials that are saved on each individual cluster for security.
Big time saver! But how secure is it? More secure than hiding Halloween candy from children. For a user to perform cluster update, the administrator needs to add the ‘execute cluster update’ privilege to the role assigned to that user. Root credentials can only be managed by users assigned with a role that has the ‘manage update credentials’ privilege.
Figure 3 MyVxRail credentials manager
The last topic is licensing. While all the capabilities you have been using on MyVxRail come with the purchase of the VxRail HCI System Software license, multi-cluster update is different. This feature requires a fee-based add-on software license called ‘SaaS active multi-cluster management for VxRail HCI System Software’. All VxRail nodes come with VxRail HCI System Software and you have access to MyVxRail and SaaS multi-cluster management features, except for cluster update. For you to perform an update of a cluster on MyVxRail, all nodes in the clusters must have the add-on software license.
That is a lot to consume for one release. Hopefully, unlike your Thanksgiving meal, you can stay awake for the ending. While the brand name VxRail ACE is no more, we’re continuing to deliver value-adding capabilities. Multi-cluster update is a great feature to further your use of MyVxRail for LCM of your VxRail clusters. With role-based access and VxRail infrastructure credentials, rest assured you’re benefitting from multi-cluster update without sacrificing security.
Daniel Chiu, VxRail Technical Marketing