Tag: SSD

Posted on

EMC VMAX 10K, looks like high-end storage systems are still alive (part III)

StorageIO industry trends cloud, virtualization and big data

This is the third in a multi-part series of posts (read first post here and second post here) looking at what else EMC announced today in addition to an enhanced VMAX 10K and dispelling the myth that large storage arrays are dead (or at least for now).

In addition to the VMAX 10K specific updates, EMC also announced the release of a new version of their Enginuity storage software (firmware, storage operating system). Enginuity is supported across all VMAX platforms and features the following:

  • Replication enhancements include TimeFinder clone refresh, restore and four site SRDF for the VMAX 10K, along with think or thin support. This capability enables functionality across VMAX 10K, 40K or 20K using synchronous or asynchronous and extends earlier 3 site to 4 site and mix modes. Note that larger VMAX systems had the extended replication feature support with VMAX 10K now on par with those. Note that the VMAX can be enhanced with VPLEX in front of storage systems (local or wide area, in region HA and out of region DR) and RecoverPoint behind the systems supporting bi-synchronous (two-way), synchronous and asynchronous data protection (CDP, replication, snapshots).
  • Unisphere for VMAX 1.5 manages DMX along with VMware VAAI UNMAP and space reclamation, block zero and hardware clone enhancements, IPV6, Microsoft Server 2012 support and VFCache 1.5.
  • Support for mix of 2.5 inch and 3.5 inch DAEs (disk array enclosures) along with new SAS drive support (high-performance and high-capacity, and various flash-based SSD or EFD).
  • The addition of a fourth dynamic tier within FAST for supporting third-party virtualized storage, along with compression of in-active, cold or stale data (manual or automatic) with 2 to 1 data footprint reduction (DFR) ratio. Note that EMC was one of early vendors to put compression into its storage systems on a block LUN basis in the CLARiiON (now VNX) along with NetApp and IBM (via their Storwize acquisition). The new fourth tier also means that third-party storage does not have to be the lowest tier in terms of performance or functionality.
  • Federated Tiered Storage (FTS) is now available on all EMC block storage systems including those with third-party storage attached in virtualization mode (e.g. VMAX). In addition to supporting tiering across its own products, and those of other vendors that have been virtualized when attached to a VMAX, ANSI T10 Data Integrity Field (DIF) is also supported. Read more about T10 DIF here, and here.
  • Front-end performance enhancements with host I/O limits (Quality of Service or QoS) for multi tenant and cloud environments to balance or prioritize IO across ports and users. This feature can balance based on thresholds for IOPS, bandwidth or both from the VMAX. Note that this feature is independent of any operating system based tool, utility, pathing driver or feature such as VMware DRS and Storage I/O control. Storage groups are created and mapped to specific host ports on the VMAX with the QoS performance thresholds applied to meet specific service level requirements or objectives.

For discussion (or entertainment) purpose, how about the question of if Enginuity qualifies or can be considered as a storage hypervisors (or storage virtualization or virtual storage)? After all, the VMAX is now capable of having third-party storage from other vendors attached to it, something that HDS has done for many years now. For those who feel a storage hypervisor, virtual storage or storage virtualization requires software running on Intel or other commodity based processors, guess what the VMAX uses for CPU processors (granted, you can’t simply download Enginuity software and run on a Dell, HP, IBM, Oracle or SuperMicro server).

I am guessing some of EMC competitors and their surrogates or others who like to play the storage hypervisor card game will be quick to tell you it is not based on various reasons or product comparisons, however you be the judge.

 

Back to the question of if, traditional high-end storage arrays are dead or dying (from part one in this series).

IMHO as mentioned not yet.

Granted like other technologies that have been declared dead or dying yet still in use (technology zombies), they continue to be enhanced, finding new customers, or existing customers using them in new ways, their roles are evolving, this still alive.

For some environments as has been the case over the past decade or so, there will be a continued migration from large legacy enterprise class storage systems to midrange or modular storage arrays with a mix of SSD and HDD. Thus, watch out for having a death grip not letting go of the past, while being careful about flying blind into the future. Do not be scared, be ready, do your homework with clouds, virtualization and traditional physical resources.

Likewise, there will be the continued migration for some from traditional mid-range class storage arrays to all flash-based appliances. Yet others will continue to leverage all the above in different roles aligned to where their specific features best serve the applications and needs of an organization.

In the case of high-end storage systems such as EMC VMAX (aka formerly known as DMX and Symmetrix before that) based on its Enginuity software, the hardware platforms will continue to evolve as will the software functionality. This means that these systems will evolve to handling more workloads, as well as moving into new environments from service providers to mid-range organizations where the systems were before out of their reach.

Smaller environments have grown larger as have their needs for storage systems while higher end solutions have scaled down to meet needs in different markets. What this means is a convergence of where smaller environments have bigger data storage needs and can afford the capabilities of scaled down or Right-sized storage systems such as the VMAX 10K.

Thus while some of the high-end systems may fade away faster than others, for those that continue to evolve being able to move into different adjacent markets or usage scenarios, they will be around for some time, at least in some environments.

Avoid confusing what is new and cool falling under industry adoption vs. what is productive and practical for customer deployment. Systems like the VMAX 10K are not for all environments or applications; however, for those who are open to exploring alternative solutions and approaches, it could open new opportunities.

If there is a high-end storage system platform (e.g. Enginuity) that continues to evolve, re-invent itself in terms of moving into or finding new uses and markets the EMC VMAX would be at or near the top of such list. For the other vendors of high-end storage system that are also evolving, you can have an Atta boy or Atta girl as well to make you feel better, loved and not left out or off of such list. ;)

Ok, nuff said for now.

Disclosure: EMC is not a StorageIO client; however, they have been in the past directly and via acquisitions that they have done. I am however a customer of EMC via my Iomega IX4 NAS (I never did get the IX2 that I supposedly won at EMCworld ;) ) that I bought on Amazon.com and indirectly via VMware products that I have, oh, and they did sent me a copy of the new book Human Face of Big Data (read more here).

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

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

Posted on

EMC VMAX 10K, looks like high-end storage systems are still alive (part II)

StorageIO industry trends cloud, virtualization and big data

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

Thus on January 14 2013 it is time for a new EMC Virtual Matrix (VMAX) model 10,000 (10K) storage system. EMC has been promoting their January 14 live virtual event for a while now. January significance is that is when (along with May or June) is when many new systems, solutions or upgrades are made on a staggered basis.

Historically speaking, January and February, along with May and June is when you have seen many of the larger announcements from EMC being made. Case in point, back in February of 2012 VFCache was released, then May (2012) in Las Vegas at EMCworld there were 42 announcements made and others later in the year.

Click here to see images of the car stuffing or click here to watch a video.

Let’s not forget back in February of 2012 VFCache was released, and go back to January 2011 there was the record-setting event in New York City complete with 26 people being compressed, deduped, singled instanced, optimized, stacked and tiered into a mini cooper (Coop) automobile (read and view more here).

Now back to the VMAX 10K enhancements

As an example of a company, product family and specific storage system model, still being alive is the VMAX 10K. Although this announcement by EMC is VMAX 10K centric, there is also a new version of the Enginuity software (firmware, storage operating system, valueware) that runs across all VMAX based systems including VMAX 20K and VMAX 40K. Read here, here and here and here to learn more about VMAX and Enginuity systems in general.

Some main themes of this announcement include Tier 1 reliability, availability and serviceability (RAS) storage systems functionality at tier 2 pricing for traditional, virtual and cloud data centers.

Some other themes of this announcement by EMC:

  • Flexible, scalable and resilient with performance to meet dynamic needs
  • Support private, public and hybrid cloud along with federated storage models
  • Simplified decision-making, acquisition, installation and ongoing management
  • Enable traditional, virtual and cloud workloads
  • Complement its siblings VMAX 40K, 20K and SP (Service Provider) models

Note that the VMAX SP is a model configured and optimized for easy self-service and private cloud, storage as a service (SaaS), IT as a Service (ITaaS) and public cloud service providers needing multi-tenant capabilities with service catalogs and associated tools.

So what is new with the VMAX 10K?

It is twice as fast (per EMC performance results) as earlier VMAX 10K by leveraging faster 2.8GHz Intel westmere vs. earlier 2.5GHz westmere processors. In addition to faster cores, there are more, from 4 to 6 on directors, from 8 to 12 on VMAX 10K engines. The PCIe (Gen 2) IO busses remain unchanged as does the RapidIO interconnect.  RapidIO  used for connecting nodes and engines,  while PCIe is used for adapter and device connectivity. Memory stays the same at up to 128GB of global DRAM cache, along with dual virtual matrix interfaces (how the nodes are connected). Note that there is no increase in the amount of DRAM based cache memory in this new VMAX 10K model.

This should prompt the question of for traditional cache centric or dependent for performance storage systems such as VMAX, how much are they now CPU and their associated L1 / L2 cache dependent or effective? Also how much has the Enginuity code under the covers been enhanced to leverage the multiple cores and threads thus shifting from being cache memory dependent processor hungry.

Also new with the updated VMAX 10K include:

  • Support for dense 2.5 inch drives, along with mixed 2.5 inch and 3.5 inch form factor devices with a maximum of 1,560 HDDs. This means support for 2.5 inch 1TB 7,200 RPM SAS HDDs, along with fast SAS HDDs, SLC/MLC and eMLC solid state devices (SSD) also known as electronic flash devices (EFD). Note that with higher density storage configurations, good disk enclosures become more important to counter or prevent the effects of drive vibration, something that leading vendors are paying attention to and so should customers.
  • EMC is also with the VMAX 10K adding support for certain 3rd party racks or cabinets to be used for mounting the product. This means being able to mount the VMAX main system and DAE components into selected cabinets or racks to meet specific customer, colo or other environment needs for increased flexibility.
  • For security, VMAX 10K also supports Data at Rest Encryption or (D@RE) which is implemented within the VMAX platform. All data encrypted on every drive, every drive type (drive independent) within the VMAX platform to avoid performance impacts. AES 256 fixed block encryption with FIPS 140-2 validation (#1610) using embedded or external key management including RSA Key Manager. Note that since the storage system based encryption is done within the VMAX platform or controller, not only is the encrypt / decrypt off-loaded from servers, it also means that any device from SSD to HDD to third-party storage arrays can be encrypted. This is in contrast to drive based approaches such as self encrypting devices (SED) or other full drive encryption approaches. With embedded key management, encryption keys kept and managed within the VMAX system while external mode leverages RSA key management as part of a broader security solution approach.
  • In terms of addressing ease of decision-making and acquisition, EMC has bundled core Enginuity software suite (virtual provisioning, FTS and FLM, DCP (dynamic cache partitioning), host I/O limits, Optimizer/virtual LUN and integrated RecoverPoint splitter). In addition are bundles for optimization (FAST VP, EMC Unisphere for VMAX with heat map and dashboards), availability (TimeFinder for VMAX 10K) and migration (Symmetrix migration suite, Open Replicator, Open Migrator, SRDF/DM, Federated Live Migration). Additional optional software include RecoverPoint CDP, CRR and CLR, Replication Manager, PowerPath, SRDF/S, SRDF/A and SRDF/DM, Storage Configuration Advisor, Open Replicator with Dynamic Mobility and ControlCenter/ProSphere package.

Who needs a VMAX 10K or where can it be used?

As the entry-level model of the VMAX family, certain organizations who are growing and looking for an alternative to traditional mid-range storage systems should be a primary opportunity. Assuming the VMAX 10K can sell at tier-2 prices with a focus of tier-1 reliability, feature functionality, and simplification while allowing their channel partners to make some money, then EMC can have success with this product. The challenge however will be helping their direct and channel partner sales organizations to avoid competing with their own products (e.g. high-end VNX) vs. those of others.

Consolidation of servers with virtualization, along with storage system consolidation to remove complexity in management and costs should be another opportunity with the ability to virtualize third-party storage. I would expect EMC and their channel partners to place the VMAX 10K with its storage virtualization of third-party storage as an alternative to HDS VSP (aka USP/USPV) and the HP XP P9000 (Hitachi based) products, or for block storage needs the NetApp V-Series among others. There could be some scenarios where the VMAX 10K could be positioned as an alternative to the IBM V7000 (SVC based) for virtualizing third-party storage, or for larger environments, some of the software based appliances where there is a scaling with stability (performance, availability, capacity, ease of management, feature functionality) concerns.

Another area where the VMAX 10K could see action which will fly in the face of some industry thinking is for deployment in new and growing managed service providers (MSP), public cloud, and community clouds (private consortiums) looking for an alternative to open source based, or traditional mid-range solutions. Otoh, I cant wait to hear somebody think outside of both the old and new boxes about how a VMAX 10K could be used beyond traditional applications or functionality. For example filling it up with a few SSDs, and then balance with 1TB 2.5 inch SAS HDD and 3.5 inch 3TB (or larger when available) HDDs as an active archive target leveraging the built-in data compression.

How about if EMC were to support cloud optimized HDDs such as the Seagate Constellation Cloud Storage (CS) HDDs that were announced late in 2012 as well as the newer enterprise class HDDs for opening up new markets? Also keep in mind that some of the new 2.5 inch SAS 10,000 (10K) HDDs have the same performance capabilities as traditional 3.5 inch 15,000 (15K) RPM drives in a smaller footprint to help drive and support increased density of performance and capacity with improved energy effectiveness.

How about attaching a VMAX 10K with the right type of cost-effective (aligned to a given scenario) SSD or HDDs or third-party storage to a cluster or grid of servers that are running OpenStack including Swift, CloudStack, Basho Riak CS, Celversafe, Scality, Caringo, Ceph or even EMCs own ATMOS (that supports external storage) for cloud storage or object based storage solutions? Granted that would be thinking outside of the current or new box thinking to move away from RAID based systems in favor or low-cost JBOD storage in servers, however what the heck, let’s think in pragmatic ways.

Will EMC be able to open new markets and opportunities by making the VMAX and its Enginuity software platform and functionality more accessible and affordable leveraging the VMAX 10K as well as the VMAX SP? Time will tell, after all, I recall back in the mid to late 90s, and then again several times during the 2000s similar questions or conversations not to mention the demise of the large traditional storage systems.

Continue reading about what else EMC announced on January 14 2013 in addition to VMAX 10K updates here in the next post in this series. 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

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

Posted on

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

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

Posted on

December 2012 StorageIO Update news letter

StorageIO News Letter Image
December 2012 News letter

Welcome to the December 2012 year end edition of the StorageIO Update news letter including a new format and added content.

You can get access to this news letter via various social media venues (some are shown below) in addition to StorageIO web sites and subscriptions.

Click on the following links to view the December 2012 edition as brief (short HTML sent via Email) version, or the full HTML or PDF versions.

Visit the news letter page to view previous editions of the StorageIO Update.

You can subscribe to the news letter by clicking here.

Enjoy this edition of the StorageIO Update news letter, let me know your comments and feedback.

Nuff said for 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)
twitter @storageio

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

Posted on

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

Posted on

Ceph Day Amsterdam 2012 (Object and cloud storage)

StorageIO industry trends cloud, virtualization and big data

Recently while I was in Europe presenting some sessions at conferences and doing some seminars, I was invited by Ed Saipetch (@edsai) of Inktank.com to attend the first Ceph Day in Amsterdam.

Ceph day image

As luck or fate would turn out, I was in Nijkerk which is about an hour train ride from Amsterdam central station plus a free day in my schedule. After a morning train ride and nice walk from Amsterdam Central I arrived at the Tobacco Theatre (a former tobacco trading venue) where Ceph Day was underway, and in time for lunch of Krokettens sandwich.

Attendees at Ceph Day

Lets take a quick step back and address for those not familiar what is Ceph (Cephalanthera) and why it was worth spending a day to attend this event. Ceph is an open source distributed object scale out (e.g. cluster or grid) software platform running on industry standard hardware.

Dell server supporting ceph demoSketch of ceph demo configuration

Ceph is used for deploying object storage, cloud storage and managed services, general purpose storage for research, commercial, scientific, high performance computing (HPC) or high productivity computing (commercial) along with backup or data protection and archiving destinations. Other software similar in functionality or capabilities to Ceph include OpenStack Swift, Basho Riak CS, Cleversafe, Scality and Caringo among others. There are also the tin wrapped software (e.g. appliances or pre-packaged) solutions such as Dell DX (Caringo), DataDirect Networks (DDN) WOS, EMC ATMOS and Centera, Amplidata and HDS HCP among others. From a service standpoint, these solutions can be used to build services similar Amazon S3 and Glacier, Rackspace Cloud files and Cloud Block, DreamHost DreamObject and HP Cloud storage among others.

Ceph cloud and object storage architecture image

At the heart of Ceph is RADOS a distributed object store that consists of peer nodes functioning as object storage devices (OSD). Data can be accessed via REST (Amazon S3 like) APIs, Libraries, CEPHFS and gateway with information being spread across nodes and OSDs using a CRUSH based algorithm (note Sage Weil is one of the authors of CRUSH: Controlled, Scalable, Decentralized Placement of Replicated Data). Ceph is scalable in terms of performance, availability and capacity by adding extra nodes with hard disk drives (HDD) or solid state devices (SSDs). One of the presentations pertained to DreamHost that was an early adopter of Ceph to make their DreamObjects (cloud storage) offering.

Ceph cloud and object storage deployment image

In addition to storage nodes, there are also an odd number of monitor nodes to coordinate and manage the Ceph cluster along with optional gateways for file access. In the above figure (via DreamHost), load balancers sit in front of gateways that interact with the storage nodes. The storage node in this example is a physical server with 12 x 3TB HDDs each configured as a OSD.

Ceph dreamhost dreamobject cloud and object storage configuration image

In the DreamHost example above, there are 90 storage nodes plus 3 management nodes, the total raw storage capacity (no RAID) is about 3PB (12 x 3TB = 36TB x 90 = 3.24PB). Instead of using RAID or mirroring, each objects data is replicated or copied to three (e.g. N=3) different OSDs (on separate nodes), where N is adjustable for a given level of data protection, for a usable storage capacity of about 1PB.

Note that for more usable capacity and lower availability, N could be set lower, or a larger value of N would give more durability or data protection at higher storage capacity overhead cost. In addition to using JBOD configurations with replication, Ceph can also be configured with a combination of RAID and replication providing more flexibility for larger environments to balance performance, availability, capacity and economics.

Ceph dreamhost and dreamobject cloud and object storage deployment image

One of the benefits of Ceph is the flexibility to configure it how you want or need for different applications. This can be in a cost-effective hardware light configuration using JBOD or internal HDDs in small form factor generally available servers, or high density servers and storage enclosures with optional RAID adapters along with SSD. This flexibility is different from some cloud and object storage systems or software tools which take a stance of not using or avoiding RAID vs. providing options and flexibility to configure and use the technology how you see fit.

Here are some links to presentations from Ceph Day:
Introduction and Welcome by Wido den Hollander
Ceph: A Unified Distributed Storage System by Sage Weil
Ceph in the Cloud by Wido den Hollander
DreamObjects: Cloud Object Storage with Ceph by Ross Turk
Cluster Design and Deployment by Greg Farnum
Notes on Librados by Sage Weil

Presentations during ceph day

While at Ceph day, I was able to spend a few minutes with Sage Weil Ceph creator and founder of inktank.com to record a pod cast (listen here) about what Ceph is, where and when to use it, along with other related topics. Also while at the event I had a chance to sit down with Curtis (aka Mr. Backup) Preston where we did a simulcast video and pod cast. The simulcast involved Curtis recording this video with me as a guest discussing Ceph, cloud and object storage, backup, data protection and related themes while I recorded this pod cast.

One of the interesting things I heard, or actually did not hear while at the Ceph Day event that I tend to hear at related conferences such as SNW is a focus on where and how to use, configure and deploy Ceph along with various configuration options, replication or copy modes as opposed to going off on erasure codes or other tangents. In other words, instead of focusing on the data protection protocol and algorithms, or what is wrong with the competition or other architectures, the Ceph Day focused was removing cloud and object storage objections and enablement.

Where do you get Ceph? You can get it here, as well as via 42on.com and inktank.com.

Thanks again to Sage Weil for taking time out of his busy schedule to record a pod cast talking about Ceph, as well 42on.com and inktank for hosting, and the invitation to attend the first Ceph Day in Amsterdam.

View of downtown Amsterdam on way to train station to return to Nijkerk
Returning to Amsterdam central station after Ceph Day

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

Posted on

SSD, flash and DRAM, DejaVu or something new?

StorageIO industry trends cloud, virtualization and big data

Recently I was in Europe for a couple of weeks including stops at Storage Networking World (SNW) Europe in Frankfurt, StorageExpo Holland, Ceph Day in Amsterdam (object and cloud storage), and Nijkerk where I delivered two separate 2 day, and a single 1 day seminar.

Image of Frankfurt transtationImage of inside front of ICE train going from Frankfurt to Utrecht

At the recent StorageExpo Holland event in Utrecht, I gave a couple of presentations, one on cloud, virtualization and storage networking trends, the other taking a deeper look at Solid State Devices (SSD’s). As in the past, StorageExpo Holland was great in a fantastic venue, with many large exhibits and great attendance which I heard was over 6,000 people over two days (excluding exhibitor vendors, vars, analysts, press and bloggers) which was several times larger than what was seen in Frankfurt at the SNW event.

Image of Ilja Coolen (twitter @@iCoolen) who was session host for SSD presentation in UtrechtImage of StorageExpo Holland exhibit show floor in Utrecht

Both presentations were very well attended and included lively interactive discussion during and after the sessions. The theme of my second talk was SSD, the question is not if, rather what to use where, how and when which brings us up to this post.

For those who have been around or using SSD for more than a decade outside of cell phones, camera, SD cards or USB thumb drives, that probably means DRAM based with some form of data persistency mechanisms. More recently mention SSD and that implies nand flash-based, either MLC or eMLC or SLC or perhaps emerging mram or PCM. Some might even think of NVRAM or other forms of SSD including emerging mram or mem-resistors among others, however lets stick to nand flash and dram for now.

image of ssd technology evolution

Often in technology what is old can be new, what is new can be seen as old, if you have seen, experienced or done something before you will have a sense of DejaVu and it might be evolutionary. On the other hand, if you have not seen, heard, experienced, or found a new audience, then it can be  revolutionary or maybe even an industry first ;).

Technology evolves, gets improved on, matures, and can often go in cycles of adoption, deployment, refinement, retirement, and so forth. SSD in general has been an on again, off again type cycle technology for the past several decades except for the past six to seven years. Normally there is an up cycle tied to different events, servers not being fast enough or affordable so use SSD to help address performance woes, or drives and storage systems not being fast enough and so forth.

Btw, for those of you who think that the current SSD focused technology (nand flash) is new, it is in fact 25 years old and still evolving and far from reaching its full potential in terms of customer deployment opportunities.

StorageIO industry trends cloud, virtualization and big data

Nand flash memory has helped keep SSD practical for the past several years riding the similar curve that is keeping hard disk drives (HDD’s) that they were supposed  to replace alive. That is improved reliability, endurance or duty cycle, better annual failure rate (AFR), larger space capacity, lower cost, and enhanced interfaces, packaging, power and functionality.

Where SSD can be used and options

DRAM historically at least for enterprise has been the main option for SSD based solutions using some form of data persistency. Data persistency options include battery backup combined with internal HDD’s to de stage information from the DRAM before power was lost. TMS (recently bought by IBM) was one of the early SSD vendors from the DRAM era that made the transition to flash including being one of the first many years ago to combine DRAM as a cache layer over nand flash as a persistency or de-stage layer. This would be an example of if you were not familiar with TMS back then and their capacities, you might think or believe that some more recent introductions are new and revolutionary, and perhaps they are in their own right or with enough caveats and qualifiers.

An emerging trend, which for some will be Dejavu, is that of using more DRAM in combination with nand flash SSD.

Oracle is one example of a vendor who IMHO rather quietly (intentionally or accidentally) has done this in the 7000 series storage systems as well as ExaData based database storage systems. Rest assured they are not alone and in fact many of the legacy large storage vendors have also piled up large amounts of DRAM based cache in their storage systems. For example EMC with 2TByte of DRAM cache in their VMAX 40K, or similar systems from Fujitsu HP, HDS, IBM and NetApp (including recent acquisition of DRAM based CacheIQ) among others. This has also prompted the question of if SSD has been successful in traditional storage arrays, systems or appliances as some would have you believe not, click here to learn more and cast your vote.

SSD, IO, memory and storage hirearchy

So is the future in the past? Some would say no, some will say yes, however IMHO there are lessons to learn and leverage from the past while looking and moving forward.

Early SSD’s were essentially RAM disks, that is a portion of main random access memory (RAM) or what we now call DRAM set aside as a non persistent (unless battery backed up) cache or device. Using a device driver, applications could use the RAM disk as though it were a normal storage system. Different vendors springing up with drivers for various platforms and disappeared as their need were reduced with faster storage systems, interfaces and ram disks drives supplied by vendors, not to mention SSD devices.

Oh, for you tech trivia types, there was also database machines from the late 80’s such as Briton Lee that would offload your database processing functions to a specialized appliance. Sound like Oracle ExaData  I, II or III to anybody?

Image of Oracle ExaData storage system

Ok, so we have seen this movie before, no worries, old movies or shows get remade, and unless you are nostalgic or cling to the past, sure some of the remakes are duds, however many can be quite good.

Same goes with the remake of some of what we are seeing now. Sure there is a generation that does not know nor care about the past, its full speed ahead and leverage what will get them there.

Thus we are seeing in memory databases again, some of you may remember the original series (pick your generation, platform, tool and technology) with each variation getting better. With 64 bit processor, 128 bit and beyond file system and addressing, not to mention ability for more DRAM to be accessed directly, or via memory address extension, combined with memory data footprint reduction or compression, there is more space to put things (e.g. no such thing as a data or information recession).

Lets also keep in mind that the best IO is the IO that you do not have to do, and that SSD which is an extension of the memory map plays by the same rules of real estate. That is location matters.

Thus, here we go again for some of you (DejaVu), while for others get ready for a new and exciting ride (new and revolutionary). We are back to the future with in memory database which while for a time will take some pressure from underlying IO systems until they once again out grow server memory addressing limits (or IT budgets).

However for those who do not fall into a false sense of security, no fear, as there is no such thing as a data or information recession. Sure as the sun rises in the east and sets in the west, sooner or later those IO’s that were or are being kept in memory will need to be de-staged to persistent storage, either nand flash SSD, HDD or somewhere down the road PCM, mram and more.

StorageIO industry trends cloud, virtualization and big data

There is another trend that with more IOs being cached, reads are moving to where they should resolve which is closer to the application or via higher up in the memory and IO pyramid or hierarchy (shown above).

Thus, we could see a shift over time to more writes and ugly IOs being sent down to the storage systems. Keep in mind that any cache historically provides temporal relieve, question is how long of a temporal relief or until the next new and revolutionary or DejaVu technology shows up.

Ok, go have fun now, 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

Posted on

Is SSD only for performance?

StorageIO industry trends cloud, virtualization and big data

Normally solid state devices (SSD) including non-persistent DRAM, and persistent nand flash are thought of in the context of performance including bandwidth or throughput, response time or latency, and IOPS or transactions. However there is another role where SSD are commonly used where the primary focus is not performance. Besides consumer devise such as iPhones, iPads, iPods, Androids, MP3, cell phones and digital cameras, the other use is for harsh environments.

Harsh environments include those (both commercial and government) where use of SSDs are a solution to vibration or other rough handling. These include commercial and military aircraft, telemetry and mobile command, control and communications, energy exploration among others.

What’s also probably not commonly thought about is that the vendors or solution providers for the above specialized environments include mainstream vendors including IBM (via their TMS acquisition) and EMC among others. Yes, EMC is involved with deploying SSD in different environments including all nand flash-based VNX systems.

In a normal IT environment, vibration should not be an issue for storage devices assuming quality solutions with good enclosures are used. However some environments that are pushing the limits on density may become more susceptible to vibration. Not all of those use cases will be SSD opportunities, however some that can leverage IO density along with tolerance to vibration will be a good fit.

Does that mean HDDs can not or should not be used in high density environments where vibration can be an issue?

That depends.

If the right drive enclosures, type of drive are used  following manufactures recommendations, then all should be good. Keep in mind that there are many options to leverage SSD for various scenarios.

Which tool or technology to use when, where or how much will depend on the specific situation, or perhaps your preferences for a given product or approach.

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

Posted on

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)

StorageIO industry trends cloud, virtualization and big data

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.

StorageIO podcast

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

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

Posted on

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

Storage I/O Industry Trends and Perspectives

I hear people talking about how Solid State Devices (SSDs) have not been successful with or for vendors of storage arrays, particular legacy storage systems. Some people have also asserted that large storage arrays are dead at the hands of new purpose-built SSD appliances or storage systems (read more here).

As a reference, legacy storage systems include those from EMC (VMAX and VNX), IBM (DS8000, DCS3700, XIV, and V7000), and NetApp FAS along with those from Dell, Fujitsu, HDS, HP, NEC and Oracle among others.

Granted EMC have launched new SSD based solutions in addition to buying startup eXtremeIO (aka Project X), and IBM bought SSD industry veteran TMS. IMHO, neither of those actions by either vendor signals an early retirement for their legacy storage solutions, instead opening up new markets giving customers more options for addressing data center and IO performance challenges. Keep in mind that the best IO is the one that you do not have to do with the second best being the least impact to applications in a cost-effective way.

SSD, IO, memory and storage hirearchy

Sometimes I even hear people citing or using some other person or source to attribute or make their assertions sound authoritative. You know the game, according to XYZ or, ABC said blah blah blah blah. Of course if you say or repeat something often enough, or hear it again and again, it can become self-convincing (e.g. industry adoption vs. customer deployments). Likewise depending on how many degrees of separation exists between you and the information you get, the more that it can change from what it originally was.

So what about it, has SSD not been successful for legacy storage system vendors and is the only place that SSD has had success is with startups or non-array based solutions?

While there have been some storage systems (arrays and appliances) that may not perform up to their claimed capabilities due to various internal architecture or implementation bottlenecks. For the most part the large vendors including EMC, HP, HDS, IBM, NetApp and Oracle have done very well shipping SSD drives in their solutions. Likewise some of the clean sheet new design based startup systems, as well as some of the startups with hybrid solutions combing HDDs  and SSDs have done well while others are still emerging.

Where SSD can be used and options

This could also be an example where myth becomes reality based on industry adoption vs. customer deployment. What this means is that the myth is that it is the startups that are having success vs. the legacy vendors from an industry adoption conversation standpoint and thus believed by some.

On the other hand, the myth is that vendors such as EMC or NetApp have not had success with their arrays and SSD yet their customer deployments prove otherwise. There is also a myth that only PCIe based SSD can be of value and that drive based SSDs are not worth using which I have a good idea where that myth comes from.

IMHO it is a depends, however safe to say from what I have seen directly that there are some vendors of storage arrays, including so-called legacy systems that have had very good success with SSD. Likewise have seen where some startups have done ok with their new clean sheet designs, including EMC (Project X). Oh, at least for now I am not a believer that with the all SSD based project “X” over at EMC that the venerable VMAX  formerly known as DMX and its predecessors Symmetric have finally hit the end of the line. Rather they will be positioned and play to different markets for some time yet.

Over at IBM I don’t think the DS8000 or XIV or V7000 and SVC folks are winding things down now that they bought SSD vendor TMS who has SSD appliances and PCIe cards. Rest assured there have been success by PCIe flash card vendors both as targets (FusionIO) and cache or hybrid cache and target systems such as those from Intel, LSI, Micron, and TMS (now IBM) among others. Oh, and if you have not noticed, check out what Qlogic, Emulex and some of the other traditional HBA vendors have done with and around SSD caching.

So where does the FUD that storage systems have not had success with SSD come from?

I suspect from those who would rather not see or hear about those who have had success taking away attention from them or their markets. In other words, using Fear, Uncertainty and Doubt (FUD) or some community peer pressure, there is a belief by some that if you hear enough times that something is dead or not of a benefit; you will look at the alternatives.

Care to guess what the preferred alternative is for some? If you guessed a PCIe card or SSD based appliance from your favorite startup that would be a fair assumption.

On the other hand, my educated guess (ok, its much more informed than a guess ;) ) is that if you ask a vendor such as EMC or NetApp they would disagree, while at the same time articulate benefits of different approaches and tools. Likewise, my educated guess is that if you ask some others, they will say mixed things and of course if you talk with the pure plays, take a wild yet educated guess what they will say.

Here is my point.

SSD, DRAM, PCM and storage adoption timeline

The SSD market, including DRAM, nand flash (SLC or MLC or any other xLC), emerging PCM or future mram among other technologies and packaging options is still in its relative infancy. Yes, I know there have been significant industry adoption and many early customer deployments, however talking with IT organizations of all size as well as with vendors and vars, customer deployment of SSD is far from reaching its full potential meaning a bright future.

Simply putting an SSD, card or drive into a solution does not guarantee results.

Likewise having a new architecture does not guarantee things will be faster.

Fast storage systems need fast devices (HDD, HHDD and SSDs) along with fast interfaces to connect with fast servers. Put a fast HDD, HHDD or SSD into a storage system that has bottlenecks (hardware, software, architectural design) and you may not see the full potential of the technology. Likewise put fast ports or interfaces on a storage system that has fast devices however also a bottleneck in its controller has or system architecture and you will not realize the full potential of that solution.

This is not unique to legacy or traditional storage systems, arrays or appliances as it is also the case with new clean sheet designs.

There are many new solutions that are or should be as fast as their touted marketing stories present, however just because something looks impressive in a YouTube video or slide deck or WebEx does not mean it will be fast in your environment. Some of these new design SSD based solutions will displace some legacy storage systems or arrays while many others will find new opportunities. Similar to how previous generation SSD storage appliances found roles complementing traditional storage systems, so to will many of these new generation of products.

What this all means is to navigate your way through the various marketing and architecture debates, benchmarks battles, claims and counter claims to understand what fits your needs and requires.

StorageIO industry trends cloud, virtualization and big data

What say you?

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

Posted on

Industry trends and perspectives: Chatting with Karl Chen at SNW 2012

This is the second (here is the first SNW 2012 Waynes World) in a series of StorageIO industry trends and perspective audio blog and pod cast about Storage Networking World (SNW) Fall 2012 in Santa Clara California.

StorageIO industry trends cloud, virtualization and big data

Given how at conference conversations tend to occur in the hallways, lobbies and bar areas of venues, what better place to have candid conversations with people from throughout the industry, some you know, some you will get to know better.

In this episode, I’m joined by my co-host Bruce Rave aka Bruce Ravid of Ravid & Associates as we catch up and visit with Chief Marketing Officer (CMO) of Starboard Storage Systems Karl Chen in the Santa Clara Hyatt (event venue) lobby bar area.

Click here (right-click to download MP3 file) or on the microphone image to listen to the conversation with Karl and Bruce. Our conversations covers SNW, VMworld, Americas Cup Yacht racing, storage technology and networking with people during these events.

StorageIO podcast

Also available via

Watch (and listen) for more StorageIO industry trends and perspectives audio blog posts pod casts from SNW and other upcoming events.

Enjoy listening to catching up with Karl Chen from the Fall SNW 2012 pod cast.

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

Posted on

RAID and IOPS and IO observations

Storage I/O trends

There are at least two different meanings for IOPs, which for those not familiar with the information technology (IT) and data storage meaning is Input/output Operations Per second (e.g. data movement activity). Another meaning for IOP that is the international organization for a participatory society (iopsociety.org), and their fundraising activity found here.

I recently came across a piece (here and here) talking about RAID and IOPs that had some interesting points; however, some generalizations could use some more comments. One of the interesting comments and assertions is that RAID writes increase with the number of drives in the parity scheme. Granted the specific implementation and configuration could result in an it depends type response.

StorageIO industry trends cloud, virtualization and big data

Here are some more perspectives to the piece (here and here) as the sites comments seem to be restricted.

Keep in mind that such as with RAID 5 (or 6) performance, your IO size will have a bearing on if you are doing those extra back-end IOs. For example if you are writing a 32KB item that is accomplished by a single front-end IO from an applications server, and your storage system, appliance, adapter, software implementing and performing the RAID (or erasure coding for that matter) has a chunk size of say 8KB (e.g. the amount of data written to each back-end drive). Then a 5 drive R5 (e.g. 4+1) would in fact have five back-end IOPS (32KB / 8KB = 4 + 1 (8KB Parity)).

StorageIO industry trends cloud, virtualization and big data

Otoh of the front end IOP were only 16KB (using whole numbers for simplicity, otherwise round-up), in the case of a write, there would be three back-end writes with the R5 (e.g. 2 + 1). Keep in mind the controller/software managing the RAID would (or should) try to schedule back-end IO with cache, read-head, write-behind, write-back, other forms of optimization etc.

In the piece (here and here), a good point is the understanding and factoring in IOPS is important, as is also latency or response time in addition to bandwidth or throughput, along with availability, they are all inter-related.

Also very important is to keep in mind the size of the IOP, read and write, random, sequential etc.

RAID along with erasure coding is a balancing act between performance, availability, space capacity and economics aligned to different application needs.

RAID 0 (R0) actually has a big impact on performance, no penalty on writes; however, it has no availability protection benefit and in fact can be a single point of failure (e.g. loss of a HDD or SSD) impacts the entire R0 group. However, for static items, or items that are being journaled and protected on some other medium/RAID/protection scheme, R0 is used more than people realize for scratch/buffer/transient/read cache types of applications. Keep in mind that it is a balance of all performance and capacity with the exposure of no availability as opposed to other approaches. Thus, do not be scared of R0, however also do not get burned or hurt with it either, treat it with respect and can be effective for something’s.

Also mentioned in the piece was that SSD based servers will perform vastly better than SATA or SAS based ones. I am assuming that the authors meant to say better than SAS or SATA DAS based HDDs?

Storage I/O trends

Keep in mind that unless you are using a PCIe nand flash SSD card as a target or cache or RAID card, most SSD drives today are either SAS or SATA (being the more common) along with moving from 3Gb SAS or SATA to 6Gb SAS & SATA.

Also while HDD and SSDs can do a given number of reads or writes per second, those will vary based on the size of the IO, read, write, random, sequential. However what can have the biggest impact and where I have seen too many people or environments get into a performance jam is when assuming that those IOP numbers per HDD or SSD are a given. For example assuming that 100-140, IOPs (regardless of size, type, etc.) can be achieved as a limiting factor is the type of interface and controller/adapter being used.

I have seen fast HDDs and SSDs deliver sub-par performance or not meeting expectations fast interfaces such as iSCSI/SAS/SATA/FC/FCoE/IBA or other interfaces due to bottlenecks in the adapter card, storage system / appliance / controller / software. In some cases you may see more effective IOPs or reads, writes or both, while on other implementations you may see lower than expected due to internal implementation bottlenecks or architectural designs. Hint, watch out for solutions where the vendor tries to blame poor performance on the access network (e.g. SAS, iSCSI, FC, etc.) particular if you know that those are not bottlenecks.

Here are some related content:
Are Hard Disk Drives (HDDs) getting too big?
How can direct attached storage (DAS) make a comeback if it never left?
EMC VFCache re spinning SSD and intelligent caching
SSD and Green IT moving beyond green washing
Optimize Data Storage for Performance and Capacity Efficiency
Is SSD dead? No, however some vendors might be
RAID Relevance Revisited
Industry Trends and Perspectives: RAID Rebuild Rates
What is the best kind of IO? The one you do not have to do
More storage and IO metrics that matter
IBM buys flash solid state device (SSD) industry veteran TMS

In terms of fund-raising, if you feel so compelled, send a gift, donation, sponsorship, project, buy some books, piece of work, assignment, research project, speaking, keynote, web cast, video or seminar event my way and just like professional fund-raisers, or IOPS vendors, StorageIO accept visa, Master Card, American express, Pay Pal, check and traditional POs.

As for this site and comments, outside of those caught in the spam trap, courteous perspectives and discussions are welcome.

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 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Amazon cloud storage options enhanced with Glacier

StorageIO industry trend for storage IO

In case you missed it, Amazon Web Services (AWS) has enhanced their cloud services (Elastic Cloud Compute or EC2) along with storage offerings. These include Relational Database Service (RDS), DynamoDB, Elastic Block Store (EBS), and Simple Storage Service (S3). Enhancements include new functionality along with availability or reliability in the wake of recent events (outages or service disruptions). Earlier this year AWS announced their Cloud Storage Gateway solution that you can read an analysis here. More recently AWS announced provisioned IOPS among other enhancements (see AWS whats new page here).

Amazon Web Services logo

Before announcing Glacier, options for Amazon storage services relied on general purpose S3, or EBS with other Amazon services. S3 has provided users the ability to select different availability zones (e.g. geographical regions where data is stored) along with level of reliability for different price points for their applications or services being offered.

Note that AWS S3 flexibility lends itself to individuals or organizations using it for various purposes. This ranges from storing backup or file sharing data to being used as a target for other cloud services. S3 pricing options vary depending on which availability zones you select as well as if standard or reduced redundancy. As its name implies, reduced redundancy trades lower availability recovery time objective (RTO) in exchange for lower cost per given amount of space capacity.

AWS has now announced a new class or tier of storage service called Glacier, which as its name implies moves very slow and capable of supporting large amounts of data. In other words, targeting inactive or seldom accessed data where emphasis is on ultra-low cost in exchange for a longer RTO. In exchange for an RTO that AWS is stating that it can be measured in hours, your monthly storage cost can be as low as 1 cent per GByte or about 12 cents per year per GByte plus any extra fees (See here).

Here is a note that I received from the Amazon Web Services (AWS) team:

Dear Amazon Web Services Customer,
We are excited to announce the immediate availability of Amazon Glacier – a secure, reliable and extremely low cost storage service designed for data archiving and backup. Amazon Glacier is designed for data that is infrequently accessed, yet still important to keep for future reference. Examples include digital media archives, financial and healthcare records, raw genomic sequence data, long-term database backups, and data that must be retained for regulatory compliance. With Amazon Glacier, customers can reliably and durably store large or small amounts of data for as little as $0.01/GB/month. As with all Amazon Web Services, you pay only for what you use, and there are no up-front expenses or long-term commitments.

Amazon Glacier is:

  • Low cost– Amazon Glacier is an extremely low-cost, pay-as-you-go storage service that can cost as little as $0.01 per gigabyte per month, irrespective of how much data you store.
  • Secure – Amazon Glacier supports secure transfer of your data over Secure Sockets Layer (SSL) and automatically stores data encrypted at rest using Advanced Encryption Standard (AES) 256, a secure symmetrix-key encryption standard using 256-bit encryption keys.
  • Durable– Amazon Glacier is designed to give average annual durability of 99.999999999% for each item stored.
  • Flexible -Amazon Glacier scales to meet your growing and often unpredictable storage requirements. There is no limit to the amount of data you can store in the service.
  • Simple– Amazon Glacier allows you to offload the administrative burdens of operating and scaling archival storage to AWS, and makes long term data archiving especially simple. You no longer need to worry about capacity planning, hardware provisioning, data replication, hardware failure detection and repair, or time-consuming hardware migrations.
  • Designed for use with other Amazon Web Services – You can use AWS Import/Export to accelerate moving large amounts of data into Amazon Glacier using portable storage devices for transport. In the coming months, Amazon Simple Storage Service (Amazon S3) plans to introduce an option that will allow you to seamlessly move data between Amazon S3 and Amazon Glacier using data lifecycle policies.

Amazon Glacier is currently available in the US-East (N. Virginia), US-West (N. California), US-West (Oregon), EU-West (Ireland), and Asia Pacific (Japan) Regions.

A few clicks in the AWS Management Console are all it takes to setup Amazon Glacier. You can learn more by visiting the Amazon Glacier detail page, reading Jeff Barrs blog post, or joining our September 19th webinar.
Sincerely,
The Amazon Web Services Team

StorageIO industry trend for storage IO

What is AWS Glacier?

Glacier is low-cost for lower performance (e.g. access time) storage suited to data applications including archiving, inactive or idle data that you are not in a hurry to retrieve. Pay as you go pricing that can be as low as $0.01 USD per GByte per month (and other optional fees may apply, see here) depending on availability zone. Availability zone or regions include US West coast (Oregon or Northern California), US East Coast (Northern Virginia), Europe (Ireland) and Asia (Tokyo).

Amazon Web Services logo

Now what is understood should have to be discussed, however just to be safe, pity the fool who complains about signing up for AWS Glacier due to its penny per month per GByte cost and it being too slow for their iTunes or videos as you know its going to happen. Likewise, you know that some creative vendor or their surrogate is going to try to show a miss-match of AWS Glacier vs. their faster service that caters to a different usage model; it is just a matter of time.

StorageIO industry trend for storage IO

Lets be clear, Glacier is designed for low-cost, high-capacity, slow access of infrequently accessed data such as an archive or other items. This means that you will be more than disappointed if you try to stream a video, or access a document or photo from Glacier as you would from S3 or EBS or any other cloud service. The reason being is that Glacier is designed with the premise of low-cost, high-capacity, high availability at the cost of slow access time or performance. How slow? AWS states that you may have to wait several hours to reach your data when needed, however that is the tradeoff. If you need faster access, pay more or find a different class and tier of storage service to meet that need, perhaps for those with the real need for speed, AWS SSD capabilities ;).

Here is a link to a good post over at Planforcloud.com comparing Glacier vs. S3, which is like comparing apples and oranges; however, it helps to put things into context.

Amazon Web Services logo

In terms of functionality, Glacier security includes secure socket layer (SSL), advanced encryption standard (AES) 256 (256-bit encryption keys) data at rest encryption along with AWS identify and access management (IAM) policies.

Persistent storage designed for 99.999999999% durability with data automatically placed in different facilities on multiple devices for redundancy when data is ingested or uploaded. Self-healing is accomplished with automatic background data integrity checks and repair.

Scale and flexibility are bound by the size of your budget or credit card spending limit along with what availability zones and other options you choose. Integration with other AWS services including Import/Export where you can ship large amounts of data to Amazon using different media and mediums. Note that AWS has also made a statement of direction (SOD) that S3 will be enhanced to seamless move data in and out of Glacier using data policies.

Part of stretching budgets for organizations of all size is to avoid treating all data and applications the same (key theme of data protection modernization). This means classifying and addressing how and where different applications and data are placed on various types of servers, storage along with revisiting modernizing data protection.

While the low-cost of Amazon Glacier is an attention getter, I am looking for more than just the lowest cost, which means I am also looking for reliability, security among other things to gain and keep confidence in my cloud storage services providers. As an example, a few years ago I switched from one cloud backup provider to another not based on cost, rather functionality and ability to leverage the service more extensively. In fact, I could switch back to the other provider and save money on the monthly bills; however I would end up paying more in lost time, productivity and other costs.

StorageIO industry trend for storage IO

What do I see as the barrier to AWS Glacier adoption?

Simple, getting vendors and other service providers to enhance their products or services to leverage the new AWS Glacier storage category. This means backup/restore, BC and DR vendors ranging from Amazon (e.g. releasing S3 to Glacier automated policy based migration), Commvault, Dell (via their acquisitions of Appassure and Quest), EMC (Avamar, Networker and other tools), HP, IBM/Tivoli, Jungledisk/Rackspace, NetApp, Symantec and others, not to mention cloud gateway providers will need to add support for this new capabilities, along with those from other providers.

As an Amazon EC2 and S3 customer, it is great to see Amazon continue to expand their cloud compute, storage, networking and application service offerings. I look forward to actually trying out Amazon Glacier for storing encrypted archive or inactive data to compliment what I am doing. Since I am not using the Amazon Cloud Storage Gateway, I am looking into how I can use Rackspace Jungledisk to manage an Amazon Glacier repository similar to how it manages my S3 stores.

Some more related reading:
Only you can prevent cloud data loss
Data protection modernization, more than swapping out media
Amazon Web Services (AWS) and the NetFlix Fix?
AWS (Amazon) storage gateway, first, second and third impressions

As of now, it looks like I will have to wait for either Jungledisk adds native support as they do today for managing my S3 storage pool today, or, the automated policy based movement between S3 and Glacier is transparently enabled.

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

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

Posted on

IBM buys flash solid state device (SSD) industry veteran TMS

How much flash (or DRAM) based Solid State Device (SSD) do you want or need?

IBM recently took a flash step announcing it wants and needs more SSD capabilities in different packaging and functionality capabilities to meet the demands and opportunities of customers, business partners and prospects by acquiring Texas Memory Systems (TMS).

IBM buys SSD flash vendor TMS

Unlike most of the current generation of SSD vendors besides those actually making the dies (chips or semiconductors) or SSD drives that are startups or relatively new, TMS is the industry veteran. Where most of the current SSD vendors experiences (as companies) is measured in months or at best years, TMS has seen several generations and SSD adoption cycles during its multi-decade existence.

IBM buys SSD vendor Texas Memory Systems TMS

What this means is that TMS has been around during past dynamic random access memory (DRAM) based SSD cycles or eras, as well as being an early adopter and player in the current nand flash SSD era or cycle.

Granted, some in the industry do not consider the previous DRAM based generation of products as being SSD, and vice versa, some DRAM era SSD aficionados do not consider nand flash as being real SSD. Needless to say that there are many faces or facets to SSD ranging in media (DRAM, and nand flash among others) along with packaging for different use cases and functionality.

IBM along with some other vendors recognize that the best type of IO is the one that you do not have to do. However reality is that some type of Input Output (IO) operations need to be done with computer systems. Hence the second best type of IO is the one that can be done with the least impact to applications in a cost-effective way to meet specific service level objectives (SLO) requirements. This includes leveraging main memory or DRAM as cache or buffers along with server-based PCIe SSD flash cards as cache or target devices, along with internal SSD drives, as well as external SSD drives and SSD drives and flash cards in traditional storage systems or appliances as well as purpose-built SSD storage systems.

While TMS does not build the real nand flash single level cell (SLC) or multi-level cell (MLC) SSD drives (like those built by Intel, Micron, Samsung, SANdisk, Seagate, STEC and Western Digital (WD) among others), TMS does incorporate nand flash chips or components that are also used by others who also make nand flash PCIe cards and storage systems.

StorageIO industry trend for storage IO

IMHO this is a good move for both TMS and IBM, both of whom have been StorageIO clients in the past (here, here and here) that was a disclosure btw ;) as it gives TMS, their partners and customers a clear path and large organization able to invest in the technologies and solutions on a go forward basis. In other words, TMS who had looked to be bought gets certainty about their future as do they clients.

IBM who has used SSD based components such as PCIe flash SSD cards and SSD based drives from various suppliers gets a PCIe SSD card of their own, along with purpose-built mature SSD storage systems that have lineages to both DRAM and nand flash-based experiences. Thus IBM controls some of their own SSD intellectual property (e.g. IP) for PCIe cards that can go in theory into their servers, as well as storage systems and appliances that use Intel based (e.g. xSeries from IBM) and IBM Power processor based servers as a platform such. For example DS8000 (Power processor), and Intel based XIV, SONAS, V7000, SVC, ProtecTier and Pursystems (some are Power based).

In addition IBM also gets a field proven purpose-built all SSD storage system to compete with those from startups (Kaminario, Purestorage, Solidfire, Violin and Whiptail among others), as well as those being announced from competitors such as EMC (e.g. project X and project thunder) in addition to SSD drives that can go into servers and storage systems.

The question should not be if SSD is in your future, rather where will you be using it, in the server or a storage system, as a cache or a target, as a PCIe target or cache card or as a drive or as a storage system. This also means the question of how much SSD do you need along with what type (flash or DRAM), for what applications and how configured among other topics.

Storage and Memory Hirearchy diagram where SSD fits

What this means is that there are many locations and places where SSD fits, one type of product or model does not fit or meet all requirements and thus IBM with their acquisition of TMS, along with presumed partnership with other SSD based components will be able to offer a diverse SSD portfolio.

StorageIO industry trend for storage IO

The industry trend is for vendors such as Cisco, Dell, EMC, IBM, HP, NetApp, Oracle and others all of whom are either physical server and storage vendors, or in the case of EMC, virtual servers partnered with Cisco (vBlock and VCE) and Lenovo for physical servers.

Different types and locations for SSD

Thus it only makes sense for those vendors to offer diverse SSD product and solution offerings to meet different customer and application needs vs. having a single solution that users adapt to. In other words, if all you have is a hammer, everything needs to look like a nail, however if you have a tool box of various technologies, then it comes down to being able to leverage including articulating what to use when, where, why and how for different situations.

I think this is a good move for both IBM and TMS. Now lets watch how IBM and TMS can go beyond the press release, slide decks and webex briefings covering why it is a good move to justify their acquisition and plans, moving forward and to see the results of what is actually accomplished near and long-term.

Read added industry trends and perspective commentary about IBM buying TMS here and here, as well as check out these related posts and content:

How much SSD do you need vs. want?
What is the best kind of IO? The one you do not have to do
Is SSD dead? No, however some vendors might be
Has SSD put Hard Disk Drives (HDDs) On Endangered Species List?
Why SSD based arrays and storage appliances can be a good idea (Part I)
EMC VFCache respinning SSD and intelligent caching (Part I)
SSD options for Virtual (and Physical) Environments: Part I Spinning up to speed on SSD
Speaking of speeding up business with SSD storage
Is SSD dead? No, however some vendors might be
Part I: PureSystems, something old, something new, something from big blue
The Many Faces of Solid State Devices/Disks (SSD)
SSD and Green IT moving beyond green washing

Meanwhile, congratulations to both IBM and TMS, 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

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