Enmotus Blog

Automating Storage Performance in Hybrid and Private Clouds

Posted by Jim O'Reilly on Jun 27, 2017 10:10:00 AM

Reading current blogs on clouds and storage it’s impossible not to conclude that most cloud users have abandoned hope on tuning system performance and are just ignoring the topic. The reality is that our cloud models struggle with performance issues. For example, a server can hold roughly 1000 virtual machines.

With an SSD giving 40K IOPS, that’s just 40 IOPS per VM. This is on the low side for many use cases, but now let’s move to Docker containers, using the next generation of server. The compute power and, more importantly, DRAM space increased to match the 4,000 containers in the system, but IOPS dropped to just 10/container.

Now this is the best that we can get with typical instances. One local instance drive and all the rest is networked I/O. The problem is that network storage is also pooled and this limits storage avail

ability to any instance. The numbers are not brilliant!

We see potential bottlenecks everywhere. Data can be halfway across a datacenter instead of localized to a rack where compute instances are accessing it. Ideally, the data is local (possible with a hyper-converged architecture) so that it avoids crossing multiple switches and routers. This may be impossible to achieve, especially if diverse datasets are being used for an app.

Networks choke and that is true of VLANs used in cloud clusters. The problem with container-based systems is that the instances and VLANs involved are often closed down by the time you get a notification. That’s the downside of agility!

Apps choke, too, and microservices likewise. The fact that these often only exist for short periods makes debug both a glorious challenge and very frustrating. Being able to understand why a given node or instance runs slower than the rest in a pack can fix a hidden bottleneck that slows completion of the whole job stream.

Hybrid clouds add a new complexity. Typically, these are heterogeneous. The cloud stack in the private segment likely is OpenStack though Azure Stack promises to be an alternative. The public cloud will be one of AWS, Azure or Google, most likely. This means two separate environments, very different from each other in operation, syntax and billing, and an interface between the two.

Read More

Topics: Data Center, data analytics, cloud storage

How To Prevent Over-Provisioning - Dynamically Match Workloads With Storage Resources

Posted by Adam Zagorski on Jun 25, 2017 10:05:00 AM

The Greek philosopher Heraclitus said, “The only thing that is constant is change.” This adage rings true today in most modern datacenters. The demands on workloads tend to be unpredictable, which creates constant change. At any given point in time, an application can have very few demands placed on it, and at a moment notice the workload demands spike. Satisfying the fluctuations in demand is a serious challenge for datacenters. Solving this challenge will translate to significant cost savings amounting to millions of dollars for data centers.

Traditionally, data centers have thrown more hardware at this problem. Ultimately, they over provision to make sure they have enough performance to satisfy peak periods of demand. This includes scaling out with more and more servers filled with hard drives, quite often short stroking the hard drives to minimize latency. While hard drive costs are reasonable, this massive scale out increases power, cooling and management costs. The figure below shows an example of the disparity between capacity requirements and performance requirements. Achieving capacity goals with HDDs is quite easy, but given that individual high performance HDDs are only able to achieve about 200 random IOPS, it takes quite a few HDDs to meet performance goals of modern database applications.

Today, storage companies are pushing all flash arrays as the solution to this challenge. This addresses both the performance issue as well as the power and cooling, but now massive amounts of non-active (cold) data are stored on your most expensive storage media. In addition, not all applications need flash performance. Adding all flash is just another form of overprovisioning with a significantly higher cost penalty.

Read More

Topics: NVMe, autotiering, big data, All Flash Array, SSD, Data Center, NVMe over Fibre, data analytics

Storage analytics impact performance and scaling

Posted by Jim O'Reilly on Jun 14, 2017 11:21:10 AM

For the last 3 decades of computer storage use, we’ve operated essentially blindfolded. What we’ve known about performance has been gleaned from artificial benchmarks such as IOMeter and guestimates of IOPS requirements during operations that depend on a sense of how fast an application is running.

The result is something like steering a car without a speedometer ... it’s a mess of close calls and inefficient operations.

On the whole, though, we muddled through. That’s no longer adequate in the storage New Age. Storage performance is stellar in comparison to those early days, with SSDs changing the level of IOPS per drive by a factor of as much as 1000X. Wait, you say, tons of IOPS…why do we have problems?

The issue is that we share much of our data across clusters of systems, while the IO demand of any given server has jumped up in response to virtualization, containers and the horsepower of the latest CPUs. In fact, that huge jump in data moving around between nodes makes driving blind impossible even for small virtualized clusters, never mind scaled-out clouds.

All of this is happening against a background of application-based resilience. System uptime is no longer measured in how long a server runs. The key measurement is how long an app runs properly. Orchestrated virtual systems recover from server failures quite quickly. The app is restarted on another instance in a different server.

Read More

Topics: All Flash Array, Data Center, hyperconverged, NVMe over Fibre, data analytics

Virtual Reality Drives Data Center Demand for Storage

Posted by Andy Mills on Feb 8, 2017 11:39:41 AM

Twenty seven years ago in 1989, I attended one of the very early virtual reality (VR) headset demonstrations in the UK. It was put on by a bunch of ex-INMOS engineers demonstrating the use of Transputers and Intel’s i860 to generate real time image rendering in VR environments, along with the first VR gloves.

Apart from the obvious VR wow factor, a significant memory of the event was someone falling off the stage as they lost their balance and orientation, which was quite impressive given the low resolution graphics at the time i.e. CGA, 640x200 pixels at 4-bit resolution. Luckily they were not seriously injured.

The killer app presented at the time was remote VR teleconferencing where individuals would magically appear across the table in front of you and be able to push an electronic document toward you which you could manipulate, read and mark up, all virtually of course. Wind forward to 2017. VR, thanks to dramatic advances in display technologies and smaller compact VR gear, is finally making it into some mainstream applications with far more realistic video and smoother graphics at a much lower cost point, along with a growing amount of web based or gaming content to fuel demand.

So why to do we care about this in the world of storage?

Read More

Topics: Data Center, virtual reality, virtualization, enmotus

Storage Automation In Next Generation Data Centers

Posted by Adam Zagorski on Jan 31, 2017 1:04:37 PM

Automation of device management and performance monitoring analytics are necessary to control costs of web scale data centers, especially as most organizations continually ask for their employees to do more with fewer resources.

Big Data and massive data growth are at the forefront of datacenter growth. Imagine what it takes to manage the datacenters that provide us with this information.

 

According to research conducted by Seagate, time consuming drive management activities represent the largest storage related pain points for datacenter managers. In addition to trying to manage potential failures of all of the disk drives, managers must monitor the performance of multiple servers as well. As indicated by Seagate, there are tremendous opportunities in cost savings if the timing of retiring disk drives can be optimized. Significant savings can also result from streamlining the management process.

 

While there is no such thing as a typical datacenter, for the purpose of discussion, we will assume that a typical micro-datacenter contains about 10,000 servers while a large scale data center contains on the order of 100,000 servers. In a webscale hyperconverged environment, if each server housed 15 devices (hard drives and/or flash drives), a datacenter contains anywhere from 150,000 to 1.5 million devices. That is an enormous amount of servers and devices to manage. Even if we scaled back by an order of a magnitude or two, to 50 servers and 750 drives for example, managing a data center is a daunting task.

 

Read More

Topics: NVMe, big data, All Flash Array, hyperconverged, NVMe over Fibre

Storage Visions 2017

Posted by Jim O'Reilly on Jan 18, 2017 2:22:42 PM

Here it is. A new year opens up in front of us. This one is going to be lively and storage is no exception. In fact, 2017 should see some real fireworks as we break away from old approaches and move on to some new technologies and software.

Read More

Topics: NVMe, SSD, Data Center, data anlytics, NVMe over Fibre

Flash Tiering: The Future of Hyper-converged Infrastructure

Posted by Adam Zagorski on Jan 12, 2017 1:04:00 PM

The Future of Hyper-converged Infrastructure

Read More

Topics: NVMe, big data, 3D Xpoint, SSD, Intel Optane, Data Center, hyperconverged

The Art of “Storage-as-a-Service”

Posted by Jim O'Reilly on Jan 9, 2017 2:24:50 PM

The Art of “Storage-as-a-Service”

Most enterprise datacenters are today considering the hybrid cloud model for their future deployments. Agile and flexible, the model is expected to yield higher efficiencies than traditional setups, while allowing a datacenter to be sized to average, as opposed to peak, workloads.

In reality, achieving portability of apps between clouds and reacting rapidly to workload increases both run up against a data placement problem. The agility idea fails when data is in the wrong cloud when a burst is needed. This is exacerbated by the new containers approach, which can start up a new instance in a few milliseconds.

Data placement is in fact the most critical issue in hybrid cloud deployment. Pre-emptively providing data in the right cloud prior to firing up the instances that use it is the only way to assure adequate those expected efficiency gains.

A number of approaches have been tried, with varying success, but none are truly easy to implement and all require heavy manual intervention. Let’s look at some of these approaches:

  1. Sharding the dataset – By identifying the hottest segment of the dataset (e.g. Names beginning with S), this approach places a snapshot of those files in the public cloud and periodically updates it. When a cloudburst is needed, locks for any files being changed are passed over to the public cloud and the in-house versions of the files are blocked from updating. The public cloud files are then updated and the locks cleared.
Read More

Topics: NVMe, autotiering, big data, SSD, hyperconverged

Hot Trends In Storage

Posted by Adam Zagorski on Dec 13, 2016 2:02:41 PM

Storage continues to be a volatile segment of IT. Hot areas trending in the news this month include NVMe over Fibre Channel, which is being hyped heavily now that the Broadcom acquisition of Brocade is a done deal. Another hot segment is the hyper-converged space, complimented by activity in software-defined storage from several vendors.

Flash is now running ahead of enterprise hard drives in the market, contributing to foundry changeovers to 3D NAND to temporarily put upward pressure on SSD pricing. High-performance storage solutions built on COTS platforms have been announced, too, which will create more pressure to reduce appliance prices.

Let’s cover these topics and more in detail:

  1. NVMe over Fibre-Channel is in full hype mode right now. This solution is a major step away from traditional FC insofar as it no longer encapsulates the SCSI block-IO protocol. Instead, it uses a now-standard direct-memory access approach to reduce overhead and speed up performance significantly.
Read More

Topics: NVMe, SSD, hyperconverged, NVMe over Fibre

The Evolution Of Storage

Posted by Jim O'Reilly on Nov 29, 2016 4:09:29 PM

The storage industry continues to evolve rapidly, which is both exciting and challenging. I intend this blog to look at the hot news in the industry, as well as taking a view of trends and occasionally long-term directions.

This promises to be an interesting effort. There are plenty of innovations to describe, while retakes on older ideas crop up quite often. I hope you will find the subject as fascinating as I do.

Trends

1.It’s clear that the high performance enterprise hard drive is a dying breed. SSDs and all-flash arrays have undercut demand. With improved wear life, flash-based products meet the stringent needs of the datacenter plus, they are cooler, quieter and smaller and of course they are much faster.

Relevant news on this includes:

Read More

Topics: All Flash Array, 3D Xpoint, SSD, Intel Optane, Data Center