efd Archives

September 4, 2013November 26, 2023

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 ViPR EMC 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)

January 14, 2013December 24, 2020

EMC VMAX 10K, looks like high-end storage systems are still alive

StorageIO industry trends cloud, virtualization and big data

This is the first in a multi-part series of posts looking at if large enterprise and legacy storage systems are dead, along with what todays EMC VMAX 10K updates means.

EMC has announced an upgrade, refresh or new version of their previously announced Virtual matrix (VMAX) 10,000 (10K), part of the VMAX family of enterprise class storage systems formerly known as DMX (Direct Matrix) and Symmetrix. I will get back to more coverage on the VMAX 10K and other EMC enhancements in a few moments in part two and three of this series.

Have you heard the industry myth about the demise or outright death of traditional storage systems? This has been particularly the case for high-end enterprise class systems, which by the way which were first, declared dead back in the mid-1990s then at the hands of emerging mid-range storage systems.

Enterprise class storage systems include EMC VMAX, Fujitsu Eternus DX8700, HDS, HP XP P9000 based on the HDS high-end product (OEM from HDS parent Hitachi Ltd.). Note that some HPers or their fans might argue that the P10000 (formerly known as 3PAR) declared as tier 1.5 should also be on the list; I will leave that up to you to decide.

Let us not forget the IBM DS8000 series (whose predecessors was known as the ESS and VSS before that); although some IBMers will tell you that XIV should also be in this list. High-end enterprise class storage systems such as those mentioned above are not alone in being declared dead at the hands of new all solid-state devices (SSD) and their startup vendors, or mixed and hybrid-based solutions.

Some are even declaring dead due to new SSD appliances or systems, and by storage hypervisor or virtual storage array (VSA) the traditional mid-range storage systems that were supposed to have killed off the enterprise systems a decade ago (hmm, DejaVu?).

The mid-range storage systems include among others block (SAN and DAS) and file (NAS) systems from Data Direct Networks (DDN), Dell Complement, EqualLogic and MD series (Netapp Engenio based), EMC VNX and Isilon, Fujitsu Eternus, and HDS HUS mid-range formerly known as AMS. Let us not forget about HP 3PAR or P2000 (DotHill based) or P6000 (EVA which is probably being put out to rest). Then there are the various IBM products (their own and what they OEM from others), NEC, NetApp (FAS and Engenio), Oracle and Starboard (formerly known as Reldata). Note that there are many startups that could be in the above list as well if they were not considering the above to be considered dead, thus causing themselves to also be extinct as well, how ironic ;).

What are some industry trends that I am seeing?

Some vendors and products might be nearing the ends of their useful lives

Some vendors, their products and portfolios continue to evolve and expand

Some vendors and their products are moving into new or adjacent markets

Some vendors are refining where and what to sell when and to who

Some vendors are moving up market, some down market

Some vendors are moving into new markets, others are moving out of markets

Some vendors are declaring others dead to create a new market for their products

One size or approach or technology does not fit all needs, avoid treating all the same

Leverage multiple tools and technology in creative ways

Maximize return on innovation (the new ROI) by using various tools, technologies in ways to boost productivity, effectiveness while removing complexity and cost

Realization that cutting cost can result in reduced resiliency, thus look for and remove complexity with benefit of removing costs without compromise

Storage arrays are moving into new roles, including as back-end storage for cloud, object and other software stacks running on commodity servers to replace JBOD (DejaVu anyone?).

Keep in mind that there is a difference between industry adoption (what is talked about) and customer deployment (what are actually bought and used). Likewise there is technology based on GQ (looks and image) and G2 (functionality, experience).

There is also an industry myth that SSD cannot or has not been successful in traditional storage systems which in some cases has been true with some products or vendors. Otoh, some vendors such as EMC, NetApp and Oracle (among others) are having good success with SSD in their storage systems. Some SSD startup vendors have been more successful on both the G2 and GQ front, while some focus on the GQ or image may not be as successful (or at least yet) in the industry adoption vs. customer deployment game.

For the above mentioned storage systems vendors and products (among others), or at least for most of them there is still have plenty of life in them, granted their role and usage is changing including in some cases being found as back-end storage systems behind servers running virtualization, cloud, object storage and other storage software stacks. Likewise, some of the new and emerging storage systems (hardware, software, valueware, services) and vendors have bright futures while others may end up on the where are they now list.

Are high-end enterprise class or other storage arrays and systems dead at the hands of new startups, virtual storage appliances (VSA), storage hypervisors, storage virtualization, virtual storage and SSD?

Are large storage arrays dead at the hands of SSD?

Have SSDs been unsuccessful with storage arrays (with poll)?

Here are links to two polls where you can cast your vote.

Cast your vote and see results of if large storage arrays and systems are dead here.

Cast your vote and see results of if SSD has not been successful in storage systems.

So what about it, are enterprise or large storage arrays and systems dead?

Perhaps in some tabloids or industry myths (or that some wish for) or in some customer environments, as well as for some vendors or their products that can be the case.

However, IMHO for many other environments (and vendors) the answer is no, granted some will continue to evolve from legacy high-end enterprise class storage systems to mid-range or to appliance or VSA or something else.

There is still life many of the storage systems architectures, platforms and products that have been declared dead for over a decade.

Continue reading about the specifics of the EMC VMAX 10K announcement in the next post in this series here. Also check out Chucks EMC blog to see what he has to say.

Ok, nuff said (for now).

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

December 6, 2012November 26, 2023

Storage comments from the field and customers in the trenches

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

November 14, 2012November 26, 2023

SSD past, present and future with Jim Handy

Now also available via

This is a new episode in the continuing StorageIO industry trends and perspectives pod cast series (you can view more episodes or shows along with other audio and video content here) as well as listening via iTunes or via your preferred means using this RSS feed (https://storageio.com/StorageIO_Podcast.xml)

In this episode, I talk with SSD nand flash and DRAM chip analyst Jim Handy of Objective Analysis at the LSI AIS (Accelerating Innovation Summit) 2012 in San Jose. Our conversation includes SSD past, present and future, market and industry trends, who are doing what and things to keep an eye and ear, open for along with server, storage and memory convergence.

Click here (right-click to download MP3 file) or on the microphone image to listen to the conversation with Jim and myself.

Also available via

Watch (and listen) for more StorageIO industry trends and perspectives audio blog posts pod casts and other upcoming events. Also be sure to heck out other related pod casts, videos, posts, tips and industry commentary at StorageIO.com and StorageIOblog.com.

Enjoy this episode SSD Past, Present and Future with Jim Handy.

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

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

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

Does this mean EMC is catching up with newer vendors?

What are some other enhancements or features?

What does then new VNX MCx family look like?

Is VNX MCx all about supporting VMware?

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

General thoughts and closing comments

Share this:

Share this:

Share this:

Share this: