Tag:

HPE

HP/HPE Physical to VMware conversion for Windows 2008 R2 blue screens

by Philip Sellers June 9, 2019

written by Philip Sellers

Recently, I was converting an HP/HPE Windows 2008 R2 physical server into VMware (yes, P2V still happens), when I hit a blue screen on boot. Turned out I was getting an Inaccessible Boot Volume stop error – a partial screenshot is below.

bluescreen 151

Problem was, the blue screen went by so quickly that I had a difficult time capturing what the stop code or issue was before the VM rebooted. Turns out it was a simple boot issue to solve. The VM was moving to an LSI Logic SAS controller in VMware. That driver was not enabled in the image. The following steps will walk you through enabling LSI SAS to allow the VM to boot.

Launch recovery mode – this was automatically available on the menu after my failed boot.
On the welcome screen, select Next.
Launch Command Prompt.

Run regedit.
Select HKEY_LOCAL_MACHINE, then select File > Load Hive from Menu.
Navigate to C:\Windows\System32\Config\SYSTEM.

Give the Hive a temporary name. The temporary name will be added under HKLM. I called mine TEMP.
Expand your new temporary name.
Find key HKEY_LOCAL_MACHINE/TEMP/System/CurrentControlSet001/Services/LSI_SAS

Change Start to 0. (mine was set to 3).
Select HKEY_LOCAL_MACHINE/TEMP, then select File > Unload Hive from Menu.
Reboot.

Thanks to this older post over on serverfault for the steps.

June 9, 2019 0 comments

Cloud Datacenter

HPE’s strategy for hybrid-IT is simple, cloud-like operation on-prem and in new architectures

by Philip Sellers December 4, 2018

written by Philip Sellers

I have had a long relationship with Hewlett Packard and now Hewlett Packard Enterprise. Today, I sat in a strategy session with Paul Miller and Mark Linesch. It is an interesting time as these two guys have transitioned into marketing roles for the whole of HPE – reacting to the transition of IT purchasing away from silos and into an holistic strategy.

Creating a good strategy can be tough and marketing a strategy is even tougher. These two guys have been engaged for several years creating solutions within HPE that move towards a vision of hybrid IT. What has evolved is the desire from customers to operate on-premises infrastructure as a cloud – with the same acceleration and benefits that cloud brings in terms of agility. This was echoed in a later session with research from Futurum Research saying that customers, given the choice, would continue to operate on-premises or in their own colocation if they can operate it like the cloud. So, its finally confirmed from customers – cloud is a method of operation and not a destination.

Two major things emerged from the session – HPE and Hewlett Packard Labs may be heavily invested in research for new technologies and architectures, but it is trying to bring along the industry with partnerships. HPE worked diligently with other compute vendors to establish RedFish specification – a common programmatic way to interact with IP management interfaces across the industry. More recently, with the research around memory-centric computing architectures, the company is working with partners in the Gen-Z Consortium. HPE released early that memory-centric computing would require a lot of changes and innovations that would take time for software vendors and customers to adopt – meaning it needed to create a pipeline and support with other companies for this technology. Production products in this sector are around 2 years away from release.

This week’s Composable Cloud announcement is another step towards the operation of on-premises resources as cloud. Composable Cloud take the technology acquired with Plexxi and marries it with rack-mount ProLiant servers (specific SKUs currently) to be able to create a composable network fabric. Plexxi creates flat networks that are programmable through a controller management console. That leaves the company with a slightly split strategy currently between HPE Synergy which uses traditional networking and the Plexxi-based Composable Cloud for rack mount servers.

These guys also did something that many at HPE do not often know how to do – they admitted that there were mistakes and missteps in their strategy over the last 5 years. Helion Cloud, CloudSystem and others come to mind. These were not the right way to do hybrid IT. Do they have the right strategy now? Time will tell.

December 4, 2018 0 comments

Datacenter News Storage

HPE Discover 2018 – Work with OEMs continues HPE’s tradition of innovation

by Philip Sellers December 4, 2018

written by Philip Sellers

Hewlett Packard has a tradition of innovation – from its inventions in a Palo Alto, CA, garage to the current iteration of Hewlett Packard Labs. But one area of innovation exists outside of the research labs and it involves collaboration with original equipment manufacturers (OEMs). OEMs work with HPE to integrate HPE technology into their solution, packaging or final-product.

OEM solutions at HPE uses the off-the-shelf solutions and may slightly modify them for specific use cases. Traditional OEM relationships that may come to mind include video companies that need compute and storage for their software and want to sell a package. Another great example are your traditional appliance OEM relationship – their software on HPE’s rebranded hardware.

But the actual breath of OEM solutions is much greater than I realized. HPE works with lots of companies that are creating their own hardware designs and integrates its compute and storage technologies into the OEM’s original designs.

HPE works with all verticals of business – from fitting servers into medical equipment like MRI machines to infrastructure for video analytic platforms. Some deals fit into traditional racks but require some special considerations – like placing servers into dusty environments or humid environments.

One example on display in the show floor at HPE Discover was a flight simulator. Most traditional flight simulators are built into buildings and cost millions of dollars each. They are fixed and typically only work for a single model of plane. Enter Avion Group. Avion Group set out to create simulators that could easily be transported, repurposed and reused. They worked with HPE to outfit the simulator with traditional IT servers in an integrated rack. The gallery below shows off one of the final products.

Another example was a Konica Minolta multi-function printer. Konica Minolta wanted to make their fancy copier become a server in the office. They dedicated to some of the space in the bottom of the copier to place a full DL380 server to be utilized as a branch server. Most of the adaptation was around heat and fans. The OEM team worked with Konica Minolta to fit the DL380 into the bottom of the copier by adapting the size of the chassis and the fans to be able to make this idea work.

When asked if the Konica Minolta partnership would have been possible pre-split (since HP makes printers), Mike __ said that it certainly was and this particular product was already in creation before the split occurred.

Not only is there a multifunction copier that works as a branch server, Konica is working to create a stand-alone branch server decoupled from the copier concept. In this case, HPE utilized the card form from the Moonshot platform within an appliance that resembles a clock (seen to the side).

December 4, 2018 0 comments

Cloud Datacenter Networking

HPE shows off Composable Cloud, networking based on Plexxi acquisition

by Philip Sellers December 3, 2018

written by Philip Sellers

Composable Cloud is the next step in HPE’s vision of the future in hybrid IT – enabling on-premises IT to operate like cloud and manage cloud consumption across multiple clouds. The major news during the conference is Composable Fabric – the new branding of Plexxi within the HPE portfolio. Composable Fabric was the missing piece that allows HPE to compose rack-mount servers, in addition to the HPE Synergy platform.

While HPE has been talking about Composable Fabric for a while on the Synergy platform, it didn’t have a product that allowed its rack servers to have composed networking. HPE OneView has been a great addition to the automation portfolio for HPE, but the lack of networking support is glaring in the lineup, until now. Synergy has a narrowly defined number of ways that it can be installed and connected, so networking in Synergy is somewhat easier for the company to handle. So, for now, HPE has two Composable Fabric solutions – one in its Synergy chassis and one based on Plexxi for rackmount.

Composable Fabric/Plexxi is a very cool solution. It is intended to be used all the ways that a rack-mount installation may be created. With Plexxi switches, you take the switches out of the box and cable them together in any way you desire and they form a base broadcast network that knows all the elements and can load balance traffic across the fabric. Add cabling to your Plexxi enabled DL380’s and you can begin to build a fully automated pool of systems.

Plexxi OS, the switch software, runs on HPE/Plexxi certified switches, which are open standard switches (aka whitebox switches). The Plexxi folks I spoke with said the code would likely run on other open switch platform, however, it would not be certified and supported. Like all other open networking solutions, the secret is in the software. A controller is used to define the configuration of the network and then handle all of the ways that interconnection can occur.

In some ways, it seems that Cisco’s network-centric design that encompassed both blades and rack mount servers was the right approach and the Plexxi acquisition is a step to correct this. Albiet, the two approaches are different – one with open hardware (HPE Composable Fabric) and specific software versus the Cisco method of tightly coupled hardware and software. Also glaring at this point is that Cisco has a single management plane and HPE’s solution has two – the Plexxi management and HPE OneView.

Unfortunately, Plexxi is HPE’s solution for rack-mount servers only currently, though I expect to see something similar introduced on Synergy – it is just logical (but I have no inside information). I also wonder how long the Plexxi controller will exist separate from OneView – again I think it is a logical step to merge those two functions together. While the composable cloud includes the newly rebranded Plexxi code and release, HPE also introduced a Simplivity/Plexxi package also during the conference based on the latest 4.x release.

For more information, check out the news release from HPE.

December 3, 2018 0 comments

Datacenter Networking

Composable Fabric is HPE’s solution to resilient, programmable datacenter plumbing

by Philip Sellers December 3, 2018

written by Philip Sellers

Composable Fabric is the newest addition to HPE’s networking portfolio. Officially the branding given to the Plexxi acquisition, Composable Fabric is being billed as an integral part of the Composable Cloud concept. HPE announced two product forms for the Composable Fabric – one with SimpliVity HCI and the other on rack-mount ProLiant servers at HPE Discover last week in Mardrid.

The SimpliVity offering is the current GA version of Plexxi bundled with HPE SimpliVity 380 servers. The Plexxi provides basically a networking pipe for the HCI to run on and expand. Plexxi has a strong integration with NSX, so in some ways this offering is HyperConverged along with NSX plumbing.

For the Composable Cloud offering, the next generation of Plexxi with the official Composable Fabric branding is being released along with specific SKU’s of ProLiant DL380 servers. These servers are specifically designed to interconnect with the Composable Fabric switches running the PlexxiOS. These are the same whitebox switches that Plexxi has sold with the HPE nameplate on them. (See this related post about that solution.)

Let us dig into Composable Fabric and understand what it is.

Flat, Connected How you Want

Out of the box, HPE Converged Fabric switches will plug into one another and auto-create a broadcast domain. These switches will figure how they are related and you can cable them in any fashion that you want. Once you’ve completed the physical connectivity between switches, then you are able to attach to the new fabric using a controller VM. The controller is used as a management plane to define and create the networking profile that will run your actual workloads. All of these are software defined and that allows the system to reconfigure the underlying connectivity between switches on the fly.

The PlexxiOS allows you to ignore common problems that networking folks have been trained to pay attention to – like network loops. Not only will it allow multiple connections between switches without creating a problem – those multiple connections will be used actively and load balanced with traffic flowing across all links. Optimal and offering the best utilization of all links.

Reactive Recomposition

The PlexxiOS allows these network switches to react to problems within the fabric. If a switch or link fails, the underlying OS is able to dynamic recreate a new topology to continue operation. It is a built-in feature of the switches operating system to determine the state and react to changes or failures.

Interconnection

When I talked with folks on the show floor about interconnection, they assured me that all the normal border protocols would need to be configured and that your Composable Fabric would need to be connected to your Cisco gear onsite – or wherever your upstream traffic is served from. OSPF or BGP and the like are all still required to be defined for the interconnection with other networks.

In much the same way that NSX becomes a network overlay inside of VMware, the Composable Fabric is a self-contained and controlled fabric that can then interconnect with other networks. For many customers, they may choose to completely abandon the traditional switching stack and go to a flat datacenter network for growth and program-ability reasons, but for others, the Composable Fabric may be just one of many networks in their portfolio. Either way works.

More Info

To find out more, check out these resources – the official HPE Composable Fabric page and specifically the Video Webinar under Resources on the page.

December 3, 2018 0 comments

Datacenter Storage

HPE introduces Optane in 3PAR and Nimble, skips over NVMe drives

by Philip Sellers November 27, 2018

written by Philip Sellers

This week I’m onsite at HPE Discover and I have had some interesting discussions with folks from HPE about NVMe and their choices around array architecture in 3PAR and Nimble. HPE announced Memory-Driven Flash that is available for 3PAR arrays now and coming to Nimble arrays in 2019. Memory-Driven Flash is storage class memory as a caching layer in its existing array architectures and is based on the Intel Optane storage class memory in an add-in card (AIC). 3PAR and Nimble are not utilizing NVDIMM forms of Intel Optane in the release, though that difference should not be a detriment in the current designs.

For the management at HPE, their talking points are around latency analysis and pinpointing the bottlenecks within the IO pipeline. Both product management teams (3PAR and Nimble) insist that their current bottlenecks are not around the backend storage, but rather the front-end controllers in today’s arrays. So simply enabling NVMe based drives in the array does little to address customers real concern, which is lower latency storage IO. With controller bottlenecks in play, a lot of this ceiling is created because of the extra processing of data services on the controllers.

In testing, the teams discovered that using storage class memory as a caching layer – which the company showed as a technical preview in 3PAR last year at Discover – greatly accelerated workloads and reduced latency. The released products are based around the same design as the technical preview.

So why not also enable NVMe drives at this point? HPE says it is waiting out the emergence of standards and protocol maturity around NMVe before moving to NVMe drives – and because the backend is not where they see the latency introduced in the storage stack. They reiterate the point that the backend drives are NOT where arrays are constrained – and that is an industry-wide assertion, as I understood it – but rather at the controllers.

NVMe as a protocol lacks support for multipathing and failover and other essential resiliency features taken for granted in the SCSI protocol. The short answer is simply that SCSI is robust and NVMe is new with lots of growth. From personal testing of an NVMe over Fabric array, driver support is spotty at best with just a few Linux distributions offering support for NVMe over Fabric. Microsoft has taken the stance that it is not even offering driver support at this time for NVMe over Fabric. The lack of multipathing means that NVMe over Fabric LUNs cannot be used for things like VMware VMFS datastores or clustering use cases – many of the high-profile, high-importance use cases typically associated with super-fast, low latency storage arrays.

That led me to ask them about their data services adding to latency that might otherwise be avoided in future iterations of their arrays. Product managers agreed and said that was the thinking behind the introduction of adaptive data services in the Nimble platform. By making the data services selective, you can achieve the full potential of the hardware, but you also have the choice to enable those data services where desired to improve the cost-effectiveness of the array.

November 27, 2018 1 comment

Datacenter Storage

Do you own HPE 3PAR and StoreOnce? You should look at Recovery Manager Central

by Philip Sellers December 21, 2017

written by Philip Sellers

For every StoreOnce customer out there who also uses 3PAR storage, I think you owe it to yourself to take a look at HPE’s Recovery Manager Central (RMC) product and specifically at its Express Protect. RMC Express Protect offers the potential of significantly faster backups, longer term retention, and a huge improvement to the workflow and capabilities of your backup and DR strategies.

What is RMC?

Recovery Manager Central is a product that has existed with 3PAR for a long time. It provides the ability to take application consistent snapshots with a 3PAR array – utilizing built-in software features, like VSS on Microsoft, to coordinate the snapshot ensuring data integrity. HPE currently offers RMC for VMware vSphere, Oracle database, SAP HANA, Microsoft SQL and now Exchange.

Express Protect is a feature of RMC that offers direct integration between the 3PAR and StoreOnce arrays allowing 3PAR snapshots to be offloaded directly to StoreOnce backup storage arrays for longer term backups than array-based snapshots allow using deduplication and Catalyst compression. Once a volume is protected with Express Protect, only the delta changes of a volume need to be transmitted to StoreOnce to create a new recovery point.

HPE says that they are seeing up to 23x better backup speeds and up to 15x better restore speeds compared to traditional backups.

Why is RMC so good?

RMC is just an enabling product, to me, in a customer environment that already includes StoreOnce and 3PAR. It provides the application consistent snapshots needed for data integrity in a DR or backup scenario on 3PAR arrays. And RMC unlocks a native pathway between 3PAR and StoreOnce for direct, fast backups.

With the current threat landscape from ransomware, it can be hard to determine when an infection occurred. To lessen the potential impact of a ransomware attack, a lot of companies are turning to backups and snapshots as mitigating steps. Express Protect gives you both capabilities in the same package – on steroids. Its faster both to backup and restore than traditional methods.

Native replication exists in both the 3PAR and StoreOnce platforms, meaning you can easily leverage this technology in multiple locations for DR purposes. StoreOnce provides a number of other alternatives that 3PAR doesn’t have. Because StoreOnce is software defined, customers can spin up a low-cost StoreOnce virtual appliance in another datacenter on cheap-and-deep storage or even in Microsoft Azure. This can become an offsite replication target.

In DR scenarios, your replicated data can be mounted as a read-only copy from the StoreOnce and data can be pulled and restored from this read-only copy – but this will be SLOW. StoreOnce is not intended to run primary storage workloads and the read-only copy would allow for a restore but not for a workload to run. This means you wouldn’t need a 3PAR on the remote end, however it would work best with a 3PAR on the remote side.

HPE also has an offering called Cloud Bank Storage, which is cloud object storage as another target for StoreOnce replication. This can be Amazon Web Services object store, Azure object store or an on-premises Scality object store as a target.

Integrations with third-party software vendors, like Veaam and Symantec, can also leverage native capabilities of StoreOnce and RMC to orchestrate jobs.

December 21, 2017 0 comments

Cloud Datacenter Storage

3PAR gets InfoSight and HPE InfoSight gets an upgrade

by Philip Sellers November 27, 2017

written by Philip Sellers

HPE has announced support for 3PAR storage with its HPE InfoSight cloud analytics product, acquired with Nimble, along with new updates to InfoSight focused on proactive recommendations. Even before the conference officially begins, HPE is releasing announcements that customers can dig into more during the Discover event in Madrid this week.

As promised earlier, the InfoSight support for 3PAR is coming to all existing customers with active support contracts on their 3PAR arrays. Since 3PAR already had a rich set of telemetry built into the platform, the main hurdle of integration was letting the InfoSight Data Scientists loose on the raw data to map and make sense of it. HPE leveraged existing code and analytical models against the 3PAR data to do this quickly [HPE completed the Nimble acquisition just 7 months ago].

The first iteration of InfoSight for 3PAR includes three feature sets:

analytics between the storage and virtualization platform to find root cause of problems that existing between storage and virtual machines
a unified cloud portal combining the HPE StoreFront Remote capabilities with InfoSight for trending, capacity predictions and health checks
the foundations of predictive support, which in the future will eliminate most tier 1 and 2 support cases, instead routing cases directly to level 3 (aka. adoption of the Nimble Storage support model for 3PAR)

Not resting on past accomplishments, the InfoSight team also has a new set of capabilities it is unleashing to customers – Preemptive Recommendations. For these, HPE is drawing insights from the data it is getting from the storage and virtualization platform to make recommendations that prevent issues, improve performance and optimize the environment.

To a large degree, what HPE is talking about in preemptive analytics in InfoSight sounds a lot like the problems VMware is trying to solve in vSphere with proactive recommendations from vRealize Operations Manager (vROPS). Where these recommendations can potentially shine in InfoSight are in the deeper insights that correlate between the hardware and the software since InfoSight has deeper visibility into that platform. Clearly, all tech companies are realizing that there is tremendous value in machine learning applied to IT support.

HPE is using machine learning and expert defined conditions to generate preemptive recommendations. Since the learning engine is cloud based, the refinement and self-learning should power a number of wins for customers as the install-base widens and customers adopt this support tool, making it difficult to replicate for on-premises prediction engines.

November 27, 2017 0 comments

Datacenter Storage

Post acquisition, Nimble is finding its place in HPE’s portfolio

by Philip Sellers October 20, 2017

written by Philip Sellers

I had the chance this week to attend HPE’s Storage Tech Day in Anaheim, CA. I’ve been fortunate to get updates about the storage portfolio and direction during HPE Discover events each year, but its been a while since I’ve had a full day devoted just to storage topics with HPE. Going into the event, I hoped that it would clarify the position of Nimble in the storage portfolio and I was glad to come away with some answers.

HPE is quick to point out that in acquiring Nimble, they acquired Infosight, the cloud analytics platform that Nimble had created. Infosight is not just an analytics tool for the Nimble storage arrays. Nimble realized early on that many of the perceived “storage problems” were never actually the storage array. As a startup trying to make its way in the market, it needed a way to help diagnose and pinpoint these other problems. Thus, Infosight was born out of the Nimble support organization.

Infosight combines the telemetry it gets from Nimble storage arrays along side of data it extracts from vCenter using vSphere API’s. It correlates this data and tries to identify patterns of activity not only for a single customer, but for its entire customer base. The Nimble team gave one great example of the power of these correlations. A customer called in with a problem that was determined to be an iSCSI issue in vSphere 6.5 that occurs under certain circumstances and with certain vSphere drivers. With this data, Nimble was able to identify all of the customers who fit the same conditions and issue a proactive alert to them and also work with VMware directly to address the iSCSI bug that was found. Incidentally, although I’m not a Nimble customer – I was one of those customers affected that Nimble helped VMware to fix.

Nimble quotes impressive numbers when it comes to Infosight. Some 86% of all cases for Nimble are autogenerated and solved by Infosight. And 54% of cases are not actual Nimble array issues at all. In fact, Nimble says Infosight is such a good analytic tool that many of its customers use it as first line support for more than just storage problems. (Is that a good thing? Yes, it proves Infosight is good, but… )

So, point #1 – HPE acquired Infosight and has big plans for it – so much so that its already branded HPE Infosight. The first order of business is getting Infosight and 3PAR married together. HPE says this is coming in the near future, but stopped short of quoting timelines. 3PAR already has rich telemetry within its arrays and has since its inception, but there is still work to be done to integrate it. HPE’s StoreFront Remote will be folded into Infosight at some point, due to overlapping capabilities. HPE also warned that we shouldn’t expect full capabilities in the initial release of 3PAR support for Infosight.

But, where do Nimble arrays fit?

But beyond the analytic cloud that Nimble created, Nimble also makes storage arrays. They seem to be good arrays (never have run them, so I say seem), but there isn’t a striking differentiation between the Nimble Hybrid Flash or All Flash storage arrays and any other dual controller array on the market – except for Infosight. So that begs the question, where does it fit in HPE’s portfolio.

For that answer, there are a few things I took away from the event this week.

Nimble All-Flash is a very competitive flash offering in the small to medium business and enterprise markets. It is priced below what HPE can sell a 3PAR array. It makes it an excellent entry all-flash array, also. That’s not to pigeon hole the array, because it fits nicely in many larger enterprise business, also. Nimble All Flash provides deduplication and compression, as expected with any all-flash array.

Nimble Hybrid-Flash is highly competitive in the small to medium business markets. These make great lower tiers of storage in enterprise customers and fantastic starting points for small customers with less demanding IO requirements. Its much better than an MSA, but below a 3PAR. HPE admits there is overlap, but they don’t see it as a bad thing – they simply see it as choice.

And then, there is the Nimble Secondary Storage arrays. Targeted at backup, I knew the least about these going into the tech day. A Nimble Secondary Storage array is simply a Hybrid Flash array with global dedupe. The downside to enabling global dedupe is performance impact – the Secondary Storage array is slower than the Hybrid-Flash array, however, this makes it well suited to backup applications and deduplicating mostly-cold datasets. It also provides higher performance than most disk-to-disk storage arrays, like StoreOnce, allowing flash-boot capabilities and the ability to run some workloads on the array for recovery or dev/test – directly from the backup repository. This is a killer feature for many virtual backup solutions like Veaam, Nakivo, Vembu and others.

Disclaimer: HPE provided the travel, lodging and meal expenses for my trip. The information in this blog post comes only from me based on the observations and information shared during the Tech Day event, but was not dictated or reviewed by HPE.

October 20, 2017 0 comments

Datacenter Storage

New 3PAR 9450 offers higher performance & scale for the mid-range

by Philip Sellers June 20, 2017

written by Philip Sellers

A few weeks ago, HPE introduced a brand new 9450 all-flash model of its 3PAR storage arrays leading up to HPE Discover and the company showed off the new arrays during the event. The 9450 joins the current offering of 8000 and 20000 series arrays and is the first in a new 9000 series of arrays. The new model is targeted at the mid-range, the same as the 8000 series arrays, with up to 4 controllers in an active mesh configuration. HPE is quick to say that the 9450 is not a replacement for the 8450 all-flash model, positioning the new array for customers who want larger scale, the ability to utilize NVMe and higher performance.

The new 9450 is an all-flash offering and HPE is saying that it will deliver double the scale and double the horsepower of its 8450 with the 9450 array. The 9450 is based on the same HPE Gen5 ASICs that power the 8000 series arrays but will offer greater scale for the processors that power the array and more DRAM for operation. In terms of resiliency, HPE says the new array boasts six 9’s availability.

Digging into the announcement, what are the highlights?

Scale to 18 PB of usable all-flash capacity on 6PB raw capacity (standard 3 to 1 efficiencies)
1.8 million IOPs at sub millisecond latency (70% increase)
Up to 34 Gb/s in bandwidth

Storage Class Memory and NVMe ready
80 host ports, more than 3x more than the 8450

Details on the processors is not yet available, so an assumption can be made that it will be the new Intel processors set to release in the coming weeks.

Density Differences

The 3PAR StoreServ 9450 utilizes the same controller design as the 20000 series arrays. This 8U chassis for its 4 controllers lacks any SSD drive bays, meaning that the 8000 series models with controllers integrated into a drive shelf can accommodate more SSD drives in less rack units. The trade off is the ability to accommodate NVMe storage in the controller on the 9450 which the 8000 series controllers do no have space to accommodate, meaning in the 9450, you can get some storage in the controllers.

With the new 9000 series and 20000 series controllers, they’re a 2U size, meaning more room for processors, memory and half-height PCI cards. All of this equates to the ability to push the high-end limits of the mid-range 3PAR higher than ever.

June 20, 2017 0 comments