Tag Archives: Data

6 Ways to Transform Legacy Data Storage Infrastructure


So you have a bunch of EMC RAID arrays and a couple of Dell iSCSI SAN boxes, topped with a NetApp filer or two. What do you say to the CEO who reads my articles and knows enough to ask about solid-state drives, all-flash appliances, hyperconverged infrastructure, and all the other new innovations in storage? “Er, er, we should start over” doesn’t go over too well! Thankfully, there are some clever — and generally inexpensive — ways to answer the question, keep your job, and even get a pat on the back.

SSD and flash are game-changers, so they need to be incorporated into your storage infrastructure. SSDs are better than enterprise-class hard drives from a cost perspective because they will speed up your workload and reduce the number of storage appliances and servers needed. It’s even better if your servers support NVMe, since the interface is becoming ubiquitous and will replace both SAS and (a bit later) SATA, simply because it’s much faster and lower overhead.

As far as RAID arrays, we have to face up to the harsh reality that RAID controllers can only keep up with a few SSDs. The answer is either an all-flash array and keeping the RAID arrays for cool or cold secondary storage usage, or a move to a new architecture based on either hyperconverged appliances or compact storage boxes tailored for SSDs.

All-flash arrays become a fast storage tier, today usually Tier 1 storage in a system. They are designed to bolt onto an existing SAN and require minimal change in configuration files to function. Typically, all-flash boxes have smaller capacities than the RAID arrays, since they have enough I/O cycles to do near-real-time compression coupled with the ability to down-tier (compress) data to the old RAID arrays.

With an all-flash array, which isn’t outrageously expensive, you can boast to the CEO about 10-fold boosts in I/O speed, much lower latency , and as a bonus a combination of flash and secondary storage that usually has 5X effective capacity due to compression. Just tell the CEO how many RAID arrays and drives you didn’t buy. That’s worth a hero badge!

The idea of a flash front-end works for desktops, too. Use a small flash drive for the OS (C-drive) and store colder data on those 3.5” HDDs. Your desktop will boot really quickly, especially with Windows 10 and program loads will be a snap.

Within servers, the challenge is to make the CPU, rather than the rest of the system, the bottleneck. Adding SSDs as primary drives makes sense, with HDDs in older arrays doing duty as bulk secondary storage, just as with all-flash solutions, This idea has fleshed out into the hyperconverged infrastructure (HCI) concept where the drives in each node are shared with other servers in lieu of dedicated storage boxes. While HCI is a major philosophical change, the effort to get there isn’t that huge.

For the savvy storage admin, RAID arrays and iSCSI storage can both be turned into powerful object storage systems. Both support a JBOD (just a bunch of drives) mode, and if the JBODs are attached across a set of server nodes running “free” Ceph or Scality Ring software, the result is a decent object-storage solution, especially if compression and global deduplication are supported.

Likely by now, you are using public clouds for backup. Consider “perpetual “storage using a snapshot tool or continuous backup software to reduce your RPO and RTO. Use multi-zone operations in the public cloud to converge DR onto the perpetual storage setup, as part of a cloud-based DR process. Going to the cloud for backup should save a lot of capital expense money.

On the software front, the world of IT is migrating to a services-centric software-defined storage (SDS), which allows scaling and chaining of data services via a virtualized microservice concept. Even older SANs and server drives can be pulled into the methodology, with software making all legacy boxes in a data center operate as a single pool of storage. This simplifies storage management and makes data center storage more flexible.

Encryption ought to be added to any networked storage or backup. If this prevents even one hacker from reading your files in the next five years, you’ll look good! If you are running into a space crunch and the budget is tight, separate out your cold data, apply one of the “Zip” programs and choose the encrypted file option. This saves a lot of space and gives you encryption!

Let’s take a closer look at what you can do to transform your existing storage infrastructure and extend its life.

(Image: Production Perig/Shutterstock)



Source link

What NVMe over Fabrics Means for Data Storage


NVMe-oF will speed adoption of Non-Volatile Memory Express in the data center.

The last few years have seen Non-Volatile Memory Express (NVMe) completely revolutionize the storage industry. Its wide adoption has driven down flash memory prices. With lower prices and better performance, more enterprises and hyper-scale data centers are migrating to NVMe. The introduction of NVMe over Fabrics (NVMe-oF) promises to accelerate this trend.

The original base specification of NVMe is designed as a protocol for storage on flash memory that uses existing, unmodified PCIe as a local transport. This layered approach is very important. NVMe does not create a new electrical or frame layer; instead it takes advantage of what PCIe already offers. PCIe has a well-known history as a high speed interoperable bus technology. However, while it has those qualities, it’s not well suited for building a large storage fabric or covering distances longer than a few meters. With that limitation, NVMe would be limited to being used as a direct attached storage (DAS) technology, essentially connecting SSDs to the processor inside a server, or perhaps to connect all-flash arrays (AFA) within a rack. NVMe-oF allows things to be taken much further.

Connecting storage nodes over a fabric is important as it allows multiple paths to a given storage resource. It also enables concurrent operations to distributed storage, and a means to manage potential congestion. Further, it allows thousands of drives to be connected in a single pool of storage, since it is no longer limited by the reach of PCIe, but can also take advantage of a fabric technology like RoCE or Fibre Channel.

NVMe-oF describes a means of binding regular NVMe protocol over a chosen fabric technology, a simple abstraction enabling native NVMe commands to be transported over a fabric with minimal processing to map the fabric transport to PCIe and back.  Product demonstrations have shown that the latency penalty for accessing an NVMe SSD over a fabric as opposed to a direct PCIe link can be as low as 10 microseconds.

The layered approach means that a binding specification can be created for any fabric technology, although some fabrics may be better suited for certain applications. Today there are bindings for RDMA (RoCE, iWARP, Infiniband) and Fibre Channel. Work on a binding specification for TCP/IP has also begun.

Different products will use this layered capability in different ways. A simple NVMe-oF target, consisting of an array of NVMe SSDs, may expose all of its drives individually to the NVMe-oF host across the fabric, allowing the host to access and manage each drive individually. Other solutions may take a more integrated approach, using the drives within the array to create one big pool of storage offered that to the NVMe-oF initiator. With this approach, management of drives can be done locally within the array, without requiring the attention of the NVMe-oF initiator, or any higher layer software application. This also allows for the NVMe-oF target to implement and offer NVMe protocol features that may not be supported by drives within the array.

A good example of this is a secure erase feature. A lower cost drive may not support the feature, but if that drive is put into a NVMe-oF AFA target, the AFA can implement that secure erase feature and communicate to the initiator. The NVMe-oF target will handle the operations to the lower cost drive in order to properly support the feature from the perspective of the initiator. This provides implementers with a great deal of flexibility to meet customer needs by varying hardware vs. software feature implementation, drive cost, and performance.

The recent plugfest at UNH-IOL focused on testing simple RoCE and Fibre Channel fabrics. In these tests, a single initiator and target pair were connected over a simple two switch fabric. UNH-IOL performed NVMe protocol conformance testing, generating storage traffic  to ensure data could be transferred error-free. Additionally, testing involved inducing network disruptions to ensure the fabric could recover properly and transactions could resume.

In the data center, storage is used to support many different types of applications with an unending variety of workloads. NVMe-oF has been designed to enable flexibility in deployment, offering choices for drive cost and features support, local or remote management, and fabric connectivity. This flexibility will enable wide adoption. No doubt, we’ll continue to see expansion of the NVMe ecosystem.



Source link

How Spectre and Meltdown Impact Data Center Storage


IT news over the last few weeks has been dominated by stories of vulnerabilities found in Intel x86 chips and almost all modern processors. The two exposures, Spectre and Meltdown, are a result of the speculative execution that all CPUs use to anticipate the flow of execution of code and ensure that internal instruction pipelines are filled as optimally as possible. It’s been reported that Spectre/Meltdown can have an impact on I/O and that means storage products could be affected. So, what are the impacts and what should data center operators and storage pros do?

Speculative execution

Speculative execution is a performance-improvement process used by modern processors where instructions are executed before the processor knows whether they will be needed. Imagine some code that branches as the result of a logic comparison. Without speculative execution, the processor needs to wait for the completion of that logic comparison before continuing to read ahead, resulting in a drop in performance. Speculative execution allows both (or all) branches of the logic to be followed; those that aren’t executed are simply discarded and the processor is kept active.

Both Spectre and Meltdown pose the risk of unauthorized access to data in this speculative execution process. A more detailed breakdown of the problem is available in two papers covering the vulnerabilities (here and here). Vendors have released O/S and BIOS workarounds for the exposures. Meltdown fixes have noticeably impacted performance on systems with high I/O activity due to the extra code needed to isolate user and system memory during context switches (syscalls). Reports range from 5%-50% additional CPU overhead, depending on the specific platform and workload.

Storage repercussions

How could this impact storage appliances and software? Over the last few years, almost all storage appliances and arrays have migrated to the Intel x86 architecture. Many are now built on Linux or Unix kernels and that means they are directly impacted by the processor vulnerabilities, which if patched, result in increased system load and higher latency.

Software-defined storage products are also potentially impacted, as they run on generic operating systems like Linux and Windows. The same applies for virtual storage appliances run in VMs and hyperconverged infrastructure, and of course either public cloud storage instances or high-intensity I/O cloud applications. Quantifying the impact is difficult as it depends on the amount of system calls the storage software has to make. Some products may be more affected than others.  

Vendor response

Storage vendors have had mixed responses to the CPU vulnerabilities. For appliances or arrays that are deemed to be “closed systems” and not able to run user code, their stance is that these systems are unaffected and won’t be patched.

Where appliances can run external code like Pure Storage’s FlashArray, which can execute user code via a feature called Purity Run, there will be a need to patch. Similarly, end users running SDS solutions on generic operating systems will need to patch. HCI and hypervisor vendors have already started to make announcements about patching, although the results have been varied. VMware for instance, released a set of patches only to recommend not installing them due to customer issues. Intel’s advisory earlier this week warning of problems with its patches has added to the confusion.

Some vendors such as Dell EMC haven’t made public statements about the impact of the vulnerabilities for all of their products. For example, Dell legacy storage product information is openly available, while information about Dell EMC products is only available behind support firewalls. I guess if you’re a user of those platforms, then you will have access, however, for wider market context it would have been helpful to see a consolidated response in order to assess the risk.

Reliability

So far, the patches released don’t seem to be very stable. Some have been withdrawn, others have crashed machines or made them unbootable. Vendors are in a difficult position, because the details of the vulnerabilities weren’t widely circulated in the community before they subsequently were made public. Some storage vendors only found out about the issue when the news broke in the press. This means some of the patches may be being rushed to market without full testing of the impact when they are applied.

To patch or not?

What should end users do? First, it’s worth evaluating the risk and impact of either applying or not applying patches. Computers that are regularly exposed to the internet like desktops and public cloud instances (including virtual storage appliances running in a cloud instance)) are likely to be most at risk, whereas storage appliances behind a corporate firewall on a dedicated storage management network are at lowest risk. Measure this risk against the impact of applying the patches and what could go wrong. Applying patches to a storage platform supporting hundreds or thousands of users, for example, is a process that needs thinking through.

Action plan

Start by talking to your storage vendors. Ask them why they believe their platforms are exposed or not. Ask what testing of patching has been performed, from both a stability and performance perspective. If you have a lab environment, do some before/after testing with standard workloads. If you don’t have a lab, ask your vendor for support.

As there are no known exploits in the wild for Spectre/Meltdown, a wise approach is probably to wait a little before applying patches. Let the version 1 fixes be tested in the wild by other folks first. Invariably issues are found that then get corrected by another point release. Waiting a little also gives time for vendors to develop more efficient patches, rather than ones that simply act as a workaround. In any event, your approach will depend on your particular set of circumstances.



Source link

8 Ways Data Center Storage Will Change in 2018


The storage industry was on a roller coaster in 2017, with the decline of traditional SAN gear offset by enterprise interest in hyperconverged infrastructure, software-only solutions, and solid-state drives. We have seen enterprises shift from hard disks to solid-state as the boost in performance with SSDs transforms data center storage.

2018 will build on these trends and also add some new items to the storage roadmap. SSD is still evolving rapidly on four fronts:  core technology, performance, capacity and price. NVMe has already boosted flash IOPS and GB per second into the stratosphere and we stand on the brink of mainstream adoption of NVMe over Ethernet, with broad implications for how storage systems are configured going forward.

Vendors are shipping 32TB SSDs, leaving the largest HDD far behind at 16TB. With 3D die technology hitting its stride, we should see 50TB and 100TB drives in 2018, especially if 4-bit storage cells hit their goals. Much of the supply shortage in flash die is behind us, and prices should begin to drop again, though demand may grow faster than expected and slow the price drop.

Outside of the drives themselves, RAID arrays are in trouble. With an inherent performance bottleneck in the controller design, handling more than a few SSDs is a real challenge. Meanwhile, small storage appliances, which are essentially inexpensive commercial off-the-shelf servers, meet the need of object stores and hyperconverged nodes. This migration is fueled by startups like Excelero, which connect drives directly to the cluster fabric at RDMA speeds using NVMe over Ethernet.

A look at recent results reflects the industry’s shift to COTS. With the exception of NetApp, traditional storage vendors are experiencing single-digit revenue growth, while original design manufacturers, which supply huge volumes of COTS to cloud providers, are collectively seeing growth of 44%. Behind that growth is the increasing availability of unbundled storage software. The combination of cheap storage platforms and low-cost software is rapidly commoditizing the storage market. This trend will accelerate in 2018 as software-defined storage (SDS) begins to shape the market.

SDS is a broad concept, but inherently unbundles control and service software from hardware platforms. The concept has been very successful in networking and in cloud servers, so extending it to storage is not only logical, but required. We’ll see more SDS solutions and competition in 2018 than we’ve had in any year of the last decade.

NVMe will continue to replace SAS and SATA as the interface for enterprise drives. Over and above the savings in CPU overhead that it brings, NVMe supports new form-factor drives. We can expect 32TB+ SSDs in a 2.5 inch size in 2018, as well as servers using M.2 storage variants.

This has massive implications. Intel has showcased an M.2 “ruler” blade drive with 33+ TB capacities that can be mounted in a 1U server with 32 slots. That gives us a 1 Petabyte, ultra-fast 1U storage solution. Other vendors are talking up similar densities, signaling an important trend. Storage boxes will get smaller, hold huge capacities, and, due to SSD speed, outperform acres of HDD arrays. You’ll be able to go to the CIO and say, “I  really can shrink the data center!”

There’s more, though! High-performance SSDs enable deduplication and compression of data as an invisible background job. The services doing this use the excess bandwidth of the storage drives. For most commercial use cases, the effective capacity is multiplied 5X or more compared with raw capacity. Overall, compression reduces the number of small appliances needed, making SSD storage much cheaper overall than hard drives.

Let’s delve into the details of all these storage trends we can expect to see in the data center this year.

(Image: Olga Salt/Shutterstock)



Source link

Software-Defined Data Centers: VMware Designs


These are best practices and proven practices for how a design for all components in the SDDC might look. It will highlight a possible cluster layout, including a detailed description of what needs to be put where, and why a certain configuration needs to be made.

Typically, every design should have an overview to quickly understand what the solution is going to look like and how the major components are related. In the SDDC one could start drawing the vSphere Clusters, including their functions.

Logical overview of the SDDC clusters

This following image describes an SDDC that is going to be run on the three-cluster approach:

 

The three clusters are as follows:

  • The management cluster for all SDDC managing services
  • The NSX edge cluster where all the north-south network traffic is flowing through
  • The actual payload cluster where the production VMs get deployed

Tip: Newer best practices from VMware, as described in the VMware validated designs (VVD) version 3.0, also propose a two-cluster approach. In this case, the edge cluster is not needed anymore and all edge VMs are deployed directly onto the payload cluster. This can be a better choice from a cost and scalability perspective. However, it is important to choose the model according to the requirements and constraints found in the design.

The overview should be only as complex as necessary since its purpose is to give a quick impression over the solution and its configuration. Typically, there are a few of these overviews for each section.

This forms a basic SDDC design where the edge and the management cluster are separated. According to the latest VMware best practices, payload and edge VMs can also run on the same cluster. This basically is a decision based on scale and size of the entire environment. Often it is also a decision based on a limit or a requirement — for example, edge hosts need to be physically separated from management hosts.

Logical overview of solution components

This is as important as the cluster overview and should describe the basic structure of the SDDC components, including some possible connections to third-party integration like IPAM.

Also, it should provide a basic understanding for the relationship between the different solutions.

 

It is important to have an understanding of these components and how they work together. This will become important during the deployment of the SDDC since none of these components should be left out or configured wrong. For the vRealize Log Insight connects, that is especially important.

Note: If not all components are configured to send their logs into vRealize Log Insight, there will be gaps, which can make troubleshooting very difficult or even impossible. A plan, which describes the relation, can be very helpful during this step of the SDDC configuration.

These connections should also be reflected in a table to show the relationship and confirm that everything has been set up correctly. The better the detail is in the design, the lower the chance that something gets configured wrong or is forgotten during the installation.

The vRealize Automation design

Based on the use case, there are two setup methods/designs vRealize Automation 7 supports when being installed.

Small: Small stands for a very dense and easy-to-deploy design. It is not recommended for any enterprise workloads or even for production. But it is ideal for a proof of concept (PoC) environment, or for a small dev/test environment to play around with SDDC principles and functions.

The key to the small deployment is that all the IaaS components can reside on one single Windows VM. Optionally, there can be additional DEMs attached which eases future scale. However, this setup has one fundamental disadvantage: There is no built-in resilience or HA for the portal or DEM layer. This means that every glitch in one of these components will always affect the entire SDDC.

Enterprise: Although this is a more complex way to install vRealize Automation, this option will be ready for production use cases and is meant to serve big environments. All the components in this design will be distributed across multiple VMs to enable resiliency and high availability.

 

In this design, the vRealize Automation OVA (vApp) is running twice. To enable true resilience a load balancer needs to be configured. The users access the load balancer and get forwarded to one of the portals. VMware has good documentation on configuring NSX as a load balancer for this purpose, as well as the F5 load balancer. Basically, any load balancer can be used, as long as it supports HTML protocol checks.

Note: DNS alias or MS load-balancing should not be used for this, since these methods cannot prove if the target server is still alive. According to VMware, there are checks required for the load balancer to understand if each of the vRA Apps is still available. If these checks are not implemented, the user will get an error while trying to access the broken vRA

In addition to the vRealize Automation portal, there has to be a load balancer for the web server components. Also, these components will be installed on a separate Windows VM. The load balancer for these components has the same requirements as the one for the vRealize Automation instances.

The active web server must only contain one web component of vRA, while the second (passive) web server can contain component 2, 3, and more.

Finally, the DEM workers have to be doubled and put behind a load balancer to ensure that the whole solution is resilient and can survive an outage of any one of the components.

Tip: If this design is used, the VMs for the different solutions need to run on different ESXi hosts in order to guarantee full resiliency and high availability. Therefore, VM affinity must be used to ensure that the DEMs, web servers or vRA appliances never run on the same ESXi host. It is very important to set this rule, otherwise, a single ESXi outage might affect the entire SDDC.

This is one of VMware’s suggested reference designs in order to ensure vRA availability for users requesting services. Although it is only a suggestion it is highly recommended for a production environment. Despite all the complexity, it offers the highest grade of availability and ensures that the SDDC can stay operative even if the management stack might have troubles.

Tip: vSphere HA cannot deliver this grade of availability since the VM would power off and on again. This can be harmful in an SDDC environment. Also, to bring back up operations, the startup order is important. Since HA can’t really take care of that, it might power the VM back on at a surviving host, but the SDDC might still be unusable due to connection errors (wrong order, stalled communication, and so on).

Once the decision is made for one of these designs, it should be documented as well in the setup section. Also, take care that none of the limits, assumptions, or requirements are violated with that decision.

Another mechanism of resiliency is to ensure that the required vRA SQL database is configured as an SQL cluster. This would ensure that no single point of failure could affect this component. Typically, big organizations have already some form of SQL cluster running, where the vRA database could be installed. If this isn’t a possibility, it is strongly recommended to set up such a cluster in order to protect the database as well. This fact should be documented in the design as a requirement when it comes to the vRA installation.

This tutorial is a chapter excerpt from “Building VMware Software-Defined Data Centers” by Valentin Hamburger. Use the code ORSCP50 at checkout to save 50% on the recommended retail price until Dec. 15.



Source link