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.
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.
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.
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.
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.
My guest for this episode is Curtis (Mr. Backup) Preston (@wcpreston) of Backup School and Backup Central fame where we discuss what is Ceph and object storage, cloud storage, file systems, backup and data protection along with dinner we had at an Indonesian restaurant .
Mr Backup getting ready to compress and dedupe dinner
The dinner we are referring to was at Restaurant Blauw in Utrecht Holland (click here) where Curtis and me were joined by Hans De Leenher @hansdeleenher of Veeam (thanks again for the dinner, that was a disclosure btw ;) ).
Note that this is a special episode in that while I’m recording the pod cast, Curtis is recording a video of our discussion for his truebit.tv site that you can view here.
In this episode, I am at the Ceph day in Amsterdam Holland event at the Tobacco Theatre. My guest for this episode is Ceph (Cephalanthera) creator Sage Weil who is also the founder of inktank.com that provides services and support for the open source based Ceph project.
For those not familiar with Ceph, it is an open source distributed object scale out software platform that can be used for deploying cloud 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.
During our conversation Sage presents an overview of what Ceph is (e.g. Ceph for non Dummies), where and how it can be used, some history of the project and how it fits in with or provides an alternative to other solutions. Sage also talks about the business or commercial considerations for open source based projects, importance of community and having good business mentors and partners as well as staying busy with his young family.
If you are a Ceph fan, gain more insight into Sage along with Ceph day sponsors Inktank and 42on. On the other hand, if you new to object storage, open source storage software or cloud storage, listen in to gain perspectives of where technology such as Ceph fits for public, private, hybrid or traditional environments.
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, my co-host Bruce Rave aka Bruce Ravid of Ravid and Associates (twitter @brucerave) meets up Sr. News Director Dave Raffo of TechTarget and Search Storage in the SNW trade show expo hall. Our conversation covers past and present SNWs along with other industry conferences, industry trends, software defined buzzwords, Green Bay Packers smack and more.
This is the sixth (here is the first, second,third,fourth and fifth) in a series of StorageIO industry trends and perspective audio blog and pod cast discussions from Storage Networking World (SNW) Fall 2012 in Santa Clara California.
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, my co-host Bruce Rave aka Bruce Ravid of Ravid and Associates (twitter @brucerave) meets up with Ray Lucchesi (@RayLucchesi) of Silverton Consulting and Ray on storage blog in the Santa Clara Hyatt (event venue) lobby bar area. Our conversation covers past and present SNWs along with other industry conferences, shows and events, along with social networking, technology, being a soccer dad with teenage kids who are aspiring actors and more.
This is the fifth (here is the first, second,third and fourth ) in a series of StorageIO industry trends and perspective audio blog and pod cast discussions from Storage Networking World (SNW) Fall 2012 in Santa Clara California.
In this episode, while I’m on a plane flying home above the clouds, my co-host Bruce Rave aka Bruce Ravid of Ravid and Associates (twitter @brucerave) meets up with SNIA executive director Leo Leger. Some of you may know or know of Leo, for those who do not, he is the person behind the scenes that puts SNW together as well as coordinates many other SNIA activities and events in conjunction with chair Wayne Adams (aka listen to Waynes World here) and other SNIA members and staff.
This is the fourth (here is the first, second and third) in a series of StorageIO industry trends and perspective audio blog and pod cast discussions from Storage Networking World (SNW) Fall 2012 in Santa Clara California.
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.
This is the third (here is the first and the second) in a series of StorageIO industry trends and perspective audio blog and pod cast discussions from Storage Networking World (SNW) Fall 2012 in Santa Clara California.
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 (twitter @brucerave) as we catch up and visit with David Chapa (@davidchapa) Chief Technology Evangelist (CTE) of Quantum Corporation (@quantumcorp) in the Santa Clara Hyatt (event venue) lobby bar area. Disclosure note, Quantum has in the past been a client of StorageIO.
This is the second (here is the firstSNW 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.
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.
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.
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)).
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?
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.
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.
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
This is the second of two posts (here is the first post) that are part of ongoing industry trends and perspectives cloud conversations series that looks at Dell and their cloud strategy story.
Simple, there have been some rather low-key, almost quiet or muddled announcements (also here, here and here) about Dell and Nirvanix collaborating around public cloud storage. Keep in mind that Nirvanix and IBM not too long ago also announced a partnership that some jumped to the conclusion that big blue was about to buy the startup vendor, even though IBM already has other cloud and storage as a service, or backup as a service and DR as a service offerings, what the heck, the more the merrier for big blue?
What about Dell and their partnership with Nirvanix, (more on that in the first post) did somebody jump the gun, or jump the shark?
Is Dell trying to walk the tightrope between being a supplier to major cloud providers while carefully moving into the cloud services market themselves, or are they simply addressing point customer situation or opportunities, at least for the time being?
Alternatively, is this nothing more than Dell establishing another partnership with a technology partner who also happens to be in the services business, similar to what Dell is doing with OpenStack and others?
IMHO Dell has some of the pieces and partnerships and could be a strong contender in the SMB and SME private cloud space, along with VDI and related areas with their Citrix, Microsoft and VMware partnerships. This is also also leveraging their servers and, storage, software, networking and other solutions to supply service providers.
The rest comes down to what markets or areas of focus does Dell want to target, that would in turn dictate how to extend what they already have or what they need to go out and get or partner around.
What say you, what’s your take on Dells cloud strategy story and portfolio?
This is first of a two-part post (click here for second post) that is part of ongoing industry trends and perspective cloud conversations series that looks at Dell and their cloud strategy story. For background, some previous Dell posts are found here, here, here and here. Here is a link that has video of the live Dell Storage Customer Advisory (CAP) panel that Dell asked me to moderate back in June that touches on some related themes and topics. Btw, fwiw and for disclosure Dell AppAssure is a site advertiser on storageioblog.com ;).
If you consider object based storage to be part of or a component of private clouds or at least for medical, healthcare and related focus, then Dell is already there with their DX object storage solutions (Caringo based).
If you view clouds as being part of services provided including via hosting or similar, Dell is already there via their Perot systems acquisitions.
If you view cloud as being part of VDI, or VDI being part of cloud, Dell is there with their tools including various acquisitions and solution bundles.
On the other hand if you view clouds as reference architectures across VMware vSphere, Microsoft Hyper-V and Citrix Xen among others, guess what, Dell is also there with their VIS.
Or, if you view private clouds as being a bundled solution (server, storage, hardware, software) such as EMC vBlock or NetApp FlexPod, then Dell vStart (not to be confused as being a service) is on the list with other infrastructure stack solutions.
How about being a technology supplier to what you may consider as being true cloud providers or enables including those who use OpenStack or other APIs and cloud tools, guess what, Dell is also there including at Rackspace (via public web info).
So the above all comes back to that Dell like many vendors who offer services, solutions and related items for data and information infrastructures have diverse offerings including servers, storage, networking, hardware, software and support. Dell like others similar to them has to find a balance between providing services that compete with their customers, as well as supplier such as to Rackspace. In this case Dell is no different from EMC who happened to move their Mozy backup service off to their VMware subsidiary and has managed to help define where VCE (and here) and ATMOS fit as products while being services capable. IBM has figured this out having a mix of old school services such as SmartCloud Services (or here), IBM Global Services and BCRS (business continuity recovery services), not to mention newer backup and storage cloud services, products and solutions they have acquired, or OEM or have reseller agreements with.
HP has expanded their traditional focused EDS as well as other HP services along with products being joined by their Amazon like Cloud Services including compute, storage and content distribution network (CDN) capabilities. NetApp is taking the partnering route along with Cisco staying focused for at least now on being a partner supplier. Oracle, well Oracle is Oracle and they have a mix of products and services. In fact some might say Oracle is late to the cloud game however they have been in the game since the late 90s when they came out with Oracle online, granted the cloud purist will call that application service provider (e.g. ASP) vs. today’s applications as a service (AaaS) models.
Some of the fall events include SNW (past SNW posts here, here, and here) in Santa Clara, as well as SNW Europe and Power the Cloud event (Frankfurt Deutschland aka Germany) October 30 and 31st where I will be doing some meetings and briefing, along with attending sessions and the expo activities.
On November 1st its off to Storage Expo Holland in Utrecht (here and here) where I will be presenting two sessions. One is on SSD industry trends and tips on deployment with a theme of not if, rather when, where, why and with what to use SSD. In addition I will be doing a general industry trends and perspective session on gaining confidence with clouds, virtualization, data and storage networking including object storage and backup (e.g. data protection modernization).
European travel tools and technologies
In addition to the above activities, following successful past events in Nijkerk Holland including the most recent May 2012 sessions, a new seminar has been announced focused on backup, restore, BC, DR and archiving hosted by Brouwer Consultancy on November 5th and 6th 2012. These workshop format seminars are very interactive providing independent perspectives on technology, tools, trends and what to do to address various challenges including more informed and effective IT decision-making.
In addition to the new seminar that you can learn more about here, two other sessions will also be offered in Holland. These include a backup, restore, BC, DR and archiving. The other session is a backup, restore, BC, DR and archiving covering storage and networking industry trends covering clouds, virtualization and other broad topics.
Examples of Dutch refreshments
Learn more about the dutch seminars including how to register here.
Watch for more events, seminars, live video, webinars and virtual trade shows by visiting the StorageIO events page.
Drop me a note if you would like to schedule or arrange for a meeting, webinar, seminar or other activity at an event near you. If you planning to be in or near Holland early November, and interested in scheduling a meeting or session, send me a note or contact Brouwer Consultancy (here) to make arrangements.
Time to get ready for these and other events, ok, nuff said.
