EMC New VNX MCx doing more storage I/O work vs. just being more

Storage I/O trends

It’s not how much you have, its how storage I/O work gets done that matters

Following last weeks VMworld event in San Francisco where among other announcements including this one around Virtual SAN (VSAN) along with Software Defined Storage (SDS), EMC today made several announcements.

Today’s EMC announcements include:

  • The new VNX MCx (Multi Core optimized) family of storage systems
  • VSPEX proven infrastructure portfolio enhancements
  • Availability of ViPR Software Defined Storage (SDS) platform (read more from earlier posts here, here and here)
  • Statement of direction preview of Project Nile for elastic cloud storage platform
  • XtremSW server cache software version 2.0 with enhanced management and support for VMware, AIX and Oracle RAC

EMC ViPREMC XtremSW cache software

Summary of the new EMC VNX MCx storage systems include:

  • More processor cores, PCIe Gen 3 (faster bus), front-end and back-end IO ports, DRAM and flash cache (as well as drives)
  • More 6Gb/s SAS back-end ports to use more storage devices (SAS and SATA flash SSD, fast HDD and high-capacity HDD)
  • MCx – Multi-core optimized with software rewritten to make use of threads and resources vs. simply using more sockets and cores at higher clock rates
  • Data Footprint Reduction (DFR) capabilities including block compression and dedupe, file dedupe and thin provisioning
  • Virtual storage pools that include flash SSD, fast HDD and high-capacity HDD
  • Block (iSCSI, FC and FCoE) and NAS file (NFS, pNFS, CIFS) front-end access with object access via Atmos Virtual Edition (VE) and ViPR
  • Entry level pricing starting at below $10,000 USD

EMC VNX MCx systems

What is this MCx stuff, is it just more hardware?

While there is more hardware that can be used in different configurations, the key or core (pun intended) around MCx is that EMC has taken the time and invested in reworking the internal software of the VNX that has its roots going back to the Data General CLARRiON EMC acquired. This is similar to an effort EMC made a few years back when it overhauled what is now known as the VMAX from the Symmetric into the DMX. That effort expanded from a platform or processor port to re-architecting and software optimizing (rewrite portions) to leverage new and emerging hardware capabilities more effectively.

EMC VNX MCx

With MCx EMC is doing something similar in that core portions of the VNX software have been re-architected and written to take advantage of more threads and cores being available to do work more effectively. This is not all that different from what occurs (or should) with upper level applications that eventually get rewritten to leverage underlying new capabilities to do more work faster and leverage technologies in a more cost-effective way. MCx also leverages flash as a primary medium with data than being moved (256MB chunks) down into lower tiers of storage (SSD and HDD drives).

Storage I/O trends

ENC VNX has had in the past FLASH Cache which enables SSD drives to be used as an extension of main cache as well as using drive targets. Thus while MCx can and does leverage more and faster core as would most any software, it is also able to leverage those cores and threads in a more effective way. After all, it’s not just how many processors, sockets, cores, threads, L1/L2 cache, DRAM, flash SSD and other resources, its how effective you use them. Also keep in mind that a bit of flash in the right place used effectively can go a long way vs. having a lot of cache in the wrong place or not used optimally that will end up costing a lot of cash.

Moving forward this means that EMC should be able to further refine and optimize other portions of the VNX software not yet updated to make further benefit of new hardware platforms and capabilities.

Does this mean EMC is catching up with newer vendors?

Similar to more of something is not always better, its how those items are used that matters, just because something is new does not mean its better or faster. That will manifest itself when they are demonstrated and performance results shown. However key is showing the performance across different workloads that have relevance to your needs and that convey metrics that matter with context.

Storage I/O trends

Context matters including type and size of work being done, number of transactions, IOPs, files or videos served, pages processed or items rendered per unit of time, or response time and latency (aka wait or think time), along with others. Thus some newer systems may be faster on paper, powerpoint, WebEx, You tube or via some benchmarks, however what is the context and how do they compare to others on an apples to apples basis.

What are some other enhancements or features?

Leveraging of FAST VP (Fully Automated Storage Tiering for Virtual Pools) with improved MCx software

Increases the effectiveness of available hardware resources (processors, cores, DRAM, flash, drives, ports)

Active active LUNs accessible by both controllers as well as legacy AULA support

Data sheets and other material for the new VNX MCx storage systems can be found here, with software options and bundles here, and general speeds and feeds here.

Learn more here at the EMC VNX MCx storage system landing page and compare VNX systems here.

What does then new VNX MCx family look like?

EMC VNX MCx family image

Is VNX MCx all about supporting VMware?

Interesting that if you read behind the lines, listen closely to the conversations, ask the right questions you will realize that while VMware is an important workload or environment to support, it is not the only one targeted for VNX. Likewise if you listen and look beyond what is normally amplified in various conversations you will find that systems such as VNX are being deployed as back-end storage in cloud (public, private, hybrid) environments for use with technologies such as OpenStack or object based solutions (visit www.objectstoragecenter.com for more on object storage systems and access)..

There is a common myth that the cloud and service providers all use white box commodity hardware including JBOD for their systems which some do, however some are also using systems such as VNX among others. In some of these scenarios the VNX type systems are or will be deployed in large numbers essentially consolidating the functions of what had been done by even larger number of JBOD based systems. This is where some of you will have a DejaVu or back to the future moment from the mid 90s when there was an industry movement to combine all the DAS and JBOD into larger storage systems. Don’t worry if you are not yet reading about this trend in your favorite industry rag or analyst briefing notes, however ask or look around and you might be surprised at what is occurring, granted it might be another year or two before you read about it (just saying ;).

Storage I/O trends

What that means is that VNX MCx is also well positioned for working with ViPR or Atmos Virtual Edition among other cloud and object storage stacks. VNX MCx is also well positioned for its new low-cost of entry for general purpose workloads and applications ranging from file sharing, email, web, database along with demanding high performance, low latency with large amounts of flash SSD. In addition to being used for general purpose storage, VNX MCx will also complement data protection solutions for backup/restore, BC, DR and archiving such as Data Domain, Avamar and Networker among others. Speaking of server virtualization, EMC also has tools for working with Hyper-V, Xen and KVM in addition to VMware.

If there is an all flash VNX MCx doesn’t that compete with XtremIO?

Yes there are all flash VNX MCx just as there have been all flash VNX before, however these will be positioned for different use case scenarios by EMC and their partners to avoid competing head to head with XtremIO. Thus EMC will need to be diligent in being very clear to its own sales and marketing forces as well as those of partners and customers of what to use when, where, why and how.

General thoughts and closing comments

The VNX MCx is a good set of enhancements by EMC and an example of how it’s not as important of how more you have, rather how you can use it to be more effective.

Ok, nuff said (fow now).

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Storage comments from the field and customers in the trenches

StorageIO industry trends cloud, virtualization and big data

When I was in Europe presenting some sessions at conferences and doing some seminars last month I meet and spoke with one of the attendees at the StorageExpo Holland event. The persons name (Han Breemer) came up to visit with me after one of my presentations that include SSD is in your future: When, where, with what and how, and Cloud and Virtual Data Storage Networking industry trends and perspectives. Note you can find additional material from various conferences and events on the backup, restore, BC, DR and archiving accessible via the resources menu on the StorageIO web site.

As I always do, I invite attendees to feel free and follow-up via email, twitter, Linked In, Google+ or other venue with questions, comments, discussions and what they are seeing or running into in their environments.

Some of the many different items discussed during my StorageExpo presentations included:

Recently Hans followed up and sent me some comments and asked if I would be willing to share them with others such as who ever happens to read this. I also suggested to Hans that he also start a blog (here is link to his new blog), and that I would be happy to post his comments for others to see and join in the conversation which are shown below.

Hans Breemer wrote:

Hi Greg,

we met each other recently at the Dutch Storage Expo after one of your sessions. We briefly discussed the current trends in the storage market, and the “risks” or “threats” (read: challenges) it means to “us”, the storage guys. Often neglected by the sales guys…

Please allow me a few lines to elaborate a bit more and share some thoughts from the field. :-)

1. Bigger is not better?

Each iteration in the new disk technologies (SATA or SAS) means we get less IOPS for the bucks. Pound for pound that is. Of course the absolute amount of IOPS we can get from a HDD increases all the time. where 175 IOPS was top speed a few years ago, we sometimes see figures close to 220 IOPS per physical drive now. This looks good in the brochure, just as the increased capacity does. However, what the brochure doesn’t tell us that if we look at the IOPS/capacity ratio, we’re walking backwards. a few years ago we could easily sell over 1000 IOPS/TB. Currently we can’t anymore. We’re happy to reach 500 IOPS/TB. I know this has always been like that. However with the introduction of SATA in the enterprise storage world, I feel things have gotten even worse.

2. But how about SSD’s then?

True and agree. In the world of HDD’s growing bigger and bigger, we actually need SSD’s, and this technology is the way forward in an IOPS perspective. SSD’s have a great future ahead of them (despite being with us already for some time). I do doubt that at the moment SSD’s already have the economical ability to fill the gap though. They offer many of thousands of IOPS, and for dedicated high-end solutions they offer what we weren’t able to deliver for decades. More IOPS than you need! But what about the “1000 IOPS/TB” market? Let’s call it the middle market.

3. SSD’s as a lubricant?

You must have heard every vendor about Adaptive Storage Tiering, Auto Tiering etc. All based on the theorem that most of our IO’s come from a relative small disk section. Thus we can improve the total performance of our array by only adding a few percent of SSD. Smart technology identifies the hot tracks on our disks, and promotes these to SSD’s. We can even demote cold tracks to big SATA drives. Think green, think ecological footprint, etc. For many applications this works well. Regular Windows server, file servers, VMWare ESX server actually seems to like adaptive storage tiering ,and I think I know why, a positive tradeoff of using VMDK’s. (I might share a few lines about FAST VP do’s and dont’s next time if you don’t mind)

4. How about the middle market them you might ask? or, SSD’s as a band-aid?

For the middle market, the above developments is sort of disaster. Think SAP running on Sun Solaris, think the average Microsoft SQL Server, think Oracle databases. These are the typical applications that need “middle market” IOPS. Many of these applications have a freakish IO pattern. OLTP during daytime, backup in the evening and batch jobs at night. Not to mention end of month runs, DTA (Dev-Test-Acceptance) streets that sleep for two weeks or are constantly upgraded or restored. These applications hardly benefit from “smart technologies”. The IO behavior is too random, too unpredictable leading to saturated SATA pools, and EFD’s that are hardly doing more IO’s than the FC drives they’re supposed to relief. Add more SSD’s we’re told. Use less SATA we’re told. but it hardly works. Recently we acquired a few new Vmax arrays without EFD or FASTVP, for the sole purpose of hosting these typical middle market applications. Affordable, predictable performance. But then again, our existing Vmax 20k had full size 600GB 15rpm drives, with the Vmax 40k we’re “encouraged” to use small form factor 600GB 10krpm drives. Again a small step backwards?

5. The storage tiering debacle.

Last but not least, some words I’d like to share with you about storage tiering. We’re encouraged (again) to sell storage in different tiers. Makes sense. To some extent it does yes. Host you most IO eager application on expensive, SSD based storage. And host your DTA or other less business critical application on FC or SATA quality HDD’s. But what if the less business critical application needs to be backed up in the evening, and while doing so completely saturates your SATA pool? Or what if the Dev server creates just as many IO’s as the Prod environment does? People don’t seem to care it seems. To have people realize how much IO’s they actually need and use, we are reporting IO graphs for all servers in our environment. Our tiering model is based on IOPS/TB and IO response time.

Tier X would be expensive, offering 800 IOPS/TB @ avg 10ms
Tier Y would be the cheaper option offering 400 IOPS/TB @ avg 15 ms

The next step will be to implement front end controls an actually limit a host to some ceiling. for instance, 2 times the limit described in the tier description. thus allowing for peak loads and backups.

Do we need to? I think so…

Greg, this small message is slowly turning into a plea. And that is actually what it is, a plea to our storage vendors, and to our evangelists. If they want us to deliver, I feel they should talk to us, and listen to us (and you!).

Cheers,

Hans Breemer 

ps, I love my job, this world and my role to translate promises and demands into solutions that work for my customers. I do take care though not to create solution that will not work, despite what the brochure said.

pps, please feel free to share the above if needed.

Here is my response to Hans:

Hello Hans good to hear from you and thanks for the comments.

Great perspectives and in the course of talking with your peers around the world, you are not alone in your thinking.

Often I see disconnects between customers and vendors. Vendors (often driven by their market research) they know what the customer needs and issues are, and many actually do. However I often see a reliance on market research data with many degrees of separation as opposed to direct and candied insight. Likewise some vendors spend more time talking about how they listen to the customer vs. how time they actually do so.

On the other hand, I routinely see customers fall into the trap of communicating wants (nice to haves) instead of articulating needs (what is required). Then there is confusing industry adoption with customer deployment, not to mention concerns over vendor, technology or services lock-in.

Hope all else is well.

Cheers
gs

Check out Hans new blog and feel free to leave your comments and perspectives here or via other venues.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

EMC Storage and Management Software Getting FAST

EMC has announced the availability of the first phase of FAST (Fully Automated Storage Tiering) functionality for their Symmetrix VMAX, CLARiiON and Celerra storage systems.

FAST was first previewed earlier this year (see here and here).

Key themes of FAST are to leverage policies for enabling automation to support large scale environments, doing more with what you have along with enabling virtual data centers for traditional, private and public clouds as well as enhancing IT economics.

This means enabling performance and capacity planning analysis along with facilitating load balancing or other infrastructure optimization activities to boost productivity, efficiency and resource usage effectiveness not to mention enabling Green IT.

Is FAST revolutionary? That will depend on who you talk or listen to.

Some vendors will jump up and down similar to donkey in shrek wanting to be picked or noticed claiming to have been the first to implement LUN or file movement inside of storage systems, or, as operating system or file system or volume manager built in. Others will claim to have done it via third party information lifecycle management (ILM) software including hierarchal storage management (HSM) tools among others. Ok, fair enough, than let their games begin (or continue) and I will leave it up to the variou vendors and their followings to debate whos got what or not.

BTW, anyone remember system manage storage on IBM mainframes or array based movement in HP AutoRAID among others?

Vendors have also in the past provided built in or third party add on tools for providing insight and awareness ranging from capacity or space usage and allocation storage resource management (SRM) tools, performance advisory activity monitors or charge back among others. For example, hot files analysis and reporting tool have been popular in the past, often operating system specific for identifying candidate files for placement on SSD or other fast storage. Granted the tools provided insight and awareness, there was still the time and error prone task of decision making and subsequently data movement, not to mention associated down time.

What is new here with FAST is the integrated approach, tools that are operating system independent, functionality in the array, available for different product family and price bands as well as that are optimized for improving user and IT productivity in medium to high-end enterprise scale environments.

One of the knocks on previous technology is either the performance impact to an application when data was moved, or, impact to other applications when data is being moved in the background. Another issue has been avoiding excessive thrashing due to data being moved at the expense of taking performance cycles from production applications. This would also be similar to having too many snapshots or raid rebuild that are not optimized running in the background on a storage system lacking sufficient performance capability. Another knock has been that historically, either 3rd party host or appliance based software was needed, or, solutions were designed and targeted for workgroup, departmental or small environments.

What is FAST and how is it implemented
FAST is technology for moving data within storage systems (and external for Celerra) for load balancing, capacity and performance optimization to meet quality of service (QoS) performance, availability, capacity along with energy and economic initiatives (figure1) across different tiers or types of storage devices. For example, moving data from slower SATA disks where a performance bottleneck exists to faster Fibre Channel or SSD devices. Similarly, cold or infrequently data on faster more expensive storage devices can be marked as candidates for migration to lower cost SATA devices based on customer policies.

EMC FAST
Figure 1 FAST big picture Source EMC

The premise is that policies are defined based on activity along with capacity to determine when data becomes a candidate for movement. All movement is performed in the background concurrently while applications are accessing data without disruptions. This means that there are no stub files or application pause or timeouts that occur or erratic I/O activity while data is being migrated. Another aspect of FAST data movement which is performed in the actual storage systems by their respective controllers is the ability for EMC management tools to identify hot or active LUNs or volumes (files in the case of Celerra) as candidates for moving (figure 2).

EMC FAST
Figure 2 FAST what it does Source EMC

However, users specify if they want data moved on its own or under supervision enabling a deterministic environment where the storage system and associated management tools makes recommendations and suggestions for administrators to approve before migration occurs. This capacity can be a safeguard as well as a learn mode enabling organizations to become comfortable with the technology along with its recommendations while applying knowledge of current business dynamics (figure 3).

EMC FAST
Figure 3 The Value proposition of FAST Source EMC

FAST is implemented as technology resident or embedded in the EMC VMAX (aka Symmetrix), CLARiiON and Cellera along with external management software tools. In the case of the block (figure 4) storage systems including DMX/VMAX and CLARiiON family of products that support FAST, data movement is on a LUN or volume basis and within a single storage system. For NAS or file based Cellera storage systems, FAST is implanted using FMA technology enabling either in the box or externally to other storage systems on a file basis.

EMC FAST
Figure 4 Example of FAST activity Source EMC

What this means is that data at the LUN or volume level can be moved across different tiers of storage or disk drives within a CLARiiON instance, or, within a VMAX instance (e.g. amongst the nodes). For example, Virtual LUNs are a building block that is leveraged for data movement and migration combined with external management tools including Navisphere for the CLARiiON and Symmetrix management console along with Ionix all of which has been enhanced.

Note however that initially data is not moved externally between different CLARiiONs or VMAX systems. For external data movement, other existing EMC tools would be deployed. In the case of Celerra, files can be moved within a specific CLARiiON as well as externally across other storage systems. External storage systems that files can be moved across using EMC FMA technology includes other Celleras, Centera and ATMOS solutions based upon defined policies.

What do I like most and why?

Integration of management tools providing insight with ability for user to setup polices as well as approve or intercede with data movement and placement as their specific philosophies dictate. This is key, for those who want to, let the system manage it self with your supervision of course. For those who prefer to take their time, then take simple steps by using the solution for initially providing insight into hot or cold spots and then helping to make decisions on what changes to make. Use the solution and adapt it to your specific environment and philosophy approach, what a concept, a tool that works for you, vs you working for it.

What dont I like and why?

There is and will remain some confusion about intra and inter box or system data movement and migration, operations that can be done by other EMC technology today for those who need it. For example I have had questions asking if FAST is nothing more than EMC Invista or some other data mover appliance sitting in front of Symmetrix or CLARiiONs and the answer is NO. Thus EMC will need to articulate that FAST is both an umbrella term as well as a product feature set combining the storage system along with associated management tools unique to each of the different storage systems. In addition, there will be confusion at least with GA of lack of support for Symmetrix DMX vs supported VMAX. Of course with EMC pricing is always a question so lets see how this plays out in the market with customer acceptance.

What about the others?

Certainly some will jump up and down claiming ratification of their visions welcoming EMC to the game while forgetting that there were others before them. However, it can also be said that EMC like others who have had LUN and volume movement or cloning capabilities for large scale solutions are taking the next step. Thus I would expect other vendors to continue movement in the same direction with their own unique spin and approach. For others who have in the past made automated tiering their marketing differentiation, I would suggest they come up with some new spins and stories as those functions are about to become table stakes or common feature functionality on a go forward basis.

When and where to use?

In theory, anyone with a Symmetrix/VMAX, CLARiiON or Celerra that supports the new functionality should be a candidate for the capabilities, that is, at least the insight, analysis, monitoring and situation awareness capabilities Note that does not mean actually enabling the automated movement initially.

While the concept is to enable automated system managed storage (Hmmm, Mainframe DejaVu anyone), for those who want to walk before they run, enabling the insight and awareness capabilities can provide valuable information about how resources are being used. The next step would then to look at the recommendations of the tools, and if you concur with the recommendations, then take remedial action by telling the system when the movement can occur at your desired time.

For those ready to run, then let it rip and take off as FAST as you want. In either situation, look at FAST for providing insight and situational awareness of hot and cold storage, where opportunities exist for optimizing and gaining efficiency in how resources are used, all important aspects for enabling a Green and Virtual Data Center not to mention as well as supporting public and private clouds.

FYI, FTC Disclosure and FWIW

I have done content related projects for EMC in the past (see here), they are not currently a client nor have they sponsored, underwritten, influenced, renumerated, utilize third party off shore swiss, cayman or south american unnumbered bank accounts, or provided any other reimbursement for this post, however I did personally sign and hand to Joe Tucci a copy of my book The Green and Virtual Data Center (CRC) ;).

Bottom line

Do I like what EMC is doing with FAST and this approach? Yes.

Do I think there is room for improvement and additional enhancements? Absolutely!

Whats my recommendation? Have a look, do your homework, due diligence and see if its applicable to your environment while asking others vendors what they will be doing (under NDA if needed).

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved