There is a post by Jerry Huang , CEO of Gladinet on the problems with trying to be compatible with Amazon’s S3 API. Jerry suggest you look at OpenStack or a common library instead.

Amazon’s API (as with any cloud vendor’s API) is a moving target for sure, but the main issue is that these APIs are under the change control of a single vendor. Doesn’t matter how “open” the API is (in terms of copyright license) because the vendor can change it to disadvantage a competitor. So if you are a competitor, you would be foolish to use that API as the only interface into your cloud. So what happens? Each cloud vendor releases their own “open” API – similar but slightly different (enough to get around copyright), almost always RESTful and pretty much they all do the same thing.

So, you get the situation we have today with rapid proliferation of many different interfaces all pretty much the same. But that doesn’t help the poor clients. They have to code to N different interfaces to work with N different clouds. And since they are rapidly evolving, they have to keep up with all these API changes over time.

The Cloud Storage standard CDMI does not have this problem. CDMI is under the change control of a standards body (SNIA) and accommodates requirements from all the cloud storage players in it’s standardization process. More importantly, it was developed under the SNIA IP policy to help prevent any of the specification author companies from gaming the spec with their Intellectual Property. Thus cloud vendors can pick up the CDMI specification and implement it with confidence. They don’t need to come up with their own API. CDMI also has a standard way to extend the specification for vendor specific functions that still allows for core compatibility with other vendors. Want to do versioning? There is an example vendor extension in CDMI that shows you how.

From a client side point of view, Jerry also mentions common libraries. Jclouds is a good example of this (for Java). There also common libraries for other languages. While that can insulate a client from the many proliferating APIs, it’s a tough task to keep that library up to date with these APIs (just ask Adrian). The sooner the various cloud providers can implement the CDMI standard (even along-side of their existing ones), the sooner common libraries like Jclouds can just maintain a single adapter to a standard API.

SSSI authors have created a number of interesting and useful white papers recently. Solid State Storage Performance Test Specification (SSS PTS) White Paper describes the soon to be released SSS PTS and explains the test methodologies contained therein. SSSI Glossary is a collection of terminology that will be a valuable reference for those wishing to better understand Solid State Storage.  It will be updated with new terms regularly. SSS PTS Case Study illustrates how the SSS PTS can be used to compare the performance of SSDs by describing the test results of 17 different SSDs. These white papers and others can be found at http://www.snia.org/forums/sssi/knowledge/education/.

I continue to believe that IP based storage protocols will be preferred for future data center deployments. The future of IT is pointing to cloud based architectures, whether internal or external. At the core of the cloud is virtualization. And I believe that Ethernet and IP storage protocols offer the greatest overall value to unlock the potential of virtualization and clouds. Will other storage network technologies work? Of course. But, I’m not talking about whether a network “works”. I’m suggesting that a converged network environment with Ethernet and IP storage offers the best combined value for virtual environments and cloud deployments. I’ve written and spoken about this topic before. And I will likely continue to do so. So, let me mention a few reasons to choose IP storage, iSCSI or NAS, for use in cloud environments.

Mobility. One of the many benefits of server virtualization is the ability to non-disruptively migrate applications from one physical server to another to support load balancing, failover or redundancy, and servicing or updating of hardware. The ability to migrate applications is best achieved with networked storage since the data doesn’t have to move when a virtual machine (VM) moves. But, the network needs to maintain connectivity to the fabric when a VM moves. Ethernet offers a network technology capable of migrating or reassigning network addresses, in this case IP addresses, from one physical device to another. When a VM moves to another physical server, the IP addresses move with it. IP based storage, such as iSCSI, leverages the built in capabilities of TCP/IP over Ethernet to migrate network port addresses without interruption to applications.

Flexibility. Most data centers require a mixture of applications that access either file or block data. With server virtualization, it is likely that you’ll require access to file and block data types on the same physical server for either the guest or parent OS. The ability to use a common network infrastructure for both the guest and parent can reduce cost and simplify management. Ethernet offers support for multiple storage protocols. In addition to iSCSI, Ethernet supports NFS and CIFS/SMB resulting in greater choice to optimize application performance within your budget. FCoE is also supported on an enhanced 10Gb Ethernet network to offer access to an existing FC infrastructure. The added flexibility to interface with existing SAN resources enhances the value of 10Gb as a long-term networking solution.

Performance. Cost. Ubiquity. Other factors that enhance Ethernet storage and therefore IP storage adoption include a robust roadmap, favorable economics, and near universal adoption. The Ethernet roadmap includes 40Gb and 100Gb speeds which will support storage traffic and will be capable of addressing any foreseeable application requirements. Ethernet today offers considerable economic value as port prices continue to drop. Although Gb speeds offer sufficient bandwidth for most business applications, the cost per Gb of bandwidth with 10 Gigabit Ethernet (GbE) is now lower than GbE and therefore offers upside in cost and efficiency. Finally, nearly all new digital devices including mobile phones, cameras, laptops, servers, and even some home appliances, are being offered with WiFi connectivity over Ethernet. Consolidating onto a single network technology means that the networking infrastructure to the rest of the world is essentially already deployed. How good is that?

Some may view moving to a shared network as kind of scary. The concerns are real. But, Ethernet has been a shared networking platform for decades and continues to offer enhanced features, performance, and security to address its increased application. And just because it can share other traffic, doesn’t mean that it must. Physical isolation of Ethernet networks is just as feasible as any other networking technology. Some may choose this option. Regardless, selecting a single network technology, even if not shared across all applications, can reduce not only capital expense, but also operational expense. Your IT personnel can be trained on a single networking technology versus multiple specialized single purpose networks. You may even be able to reduce maintenance and inventory costs to boot.

Customers looking to architect their network and storage infrastructure for today and the future would do well to consider Ethernet and IP storage protocols. The advantages are pretty compelling.

The inexorable growth of the market for Ethernet storage continued in the first half of 2010 - in fact we're getting very close to Ethernet storage being the majority of networked storage in the Enterprise.

According to IDC's recent Q2 2010 Worldwide Storage Systems Hardware Tracker, Ethernet Storage (NAS plus iSCSI) revenue market share climbed to 45%, up from 39% in 2009, 32% in 2008 and 28% in 2007, as shown below.

	2007	2008	2009	Q2 2010
FC SAN	72%	68%	61%	55%
iSCSI SAN	6%	10%	13%	15%
NAS	22%	22%	26%	30%

In terms of capacity market share, we have already see the crossover point, with Ethernet Storage at 52% of the total PB shipped, up from 47% in 2009, 42% in 2008 and 37% in 2007, as shown in the following table.

	2007	2008	2009	Q2 2010
FC SAN	62%	58%	53%	48%
iSCSI SAN	8%	13%	15%	18%
NAS	29%	29%	32%	34%

The inexorable growth of the market for Ethernet storage continued in the first half of 2010 – in fact we’re getting very close to Ethernet storage being the majority of networked storage in the Enterprise.

According to IDC’s recent Q2 2010 Worldwide Storage Systems Hardware Tracker, Ethernet Storage (NAS plus iSCSI) revenue market share climbed to 45%, up from 39% in 2009, 32% in 2008 and 28% in 2007, as shown below.

	2007	2008	2009	Q2 2010
FC SAN	72%	68%	61%	55%
iSCSI SAN	6%	10%	13%	15%
NAS	22%	22%	26%	30%

In terms of capacity market share, we have already see the crossover point, with Ethernet Storage at 52% of the total PB shipped, up from 47% in 2009, 42% in 2008 and 37% in 2007, as shown in the following table.

	2007	2008	2009	Q2 2010
FC SAN	62%	58%	53%	48%
iSCSI SAN	8%	13%	15%	18%
NAS	29%	29%	32%	34%

The inexorable growth of the market for Ethernet storage continued in the first half of 2010 - in fact we're getting very close to Ethernet storage being the majority of networked storage in the Enterprise.

According to IDC's recent Q2 2010 Worldwide Storage Systems Hardware Tracker, Ethernet Storage (NAS plus iSCSI) revenue market share climbed to 45%, up from 39% in 2009, 32% in 2008 and 28% in 2007, as shown below.

	2007	2008	2009	Q2 2010
FC SAN	72%	68%	61%	55%
iSCSI SAN	6%	10%	13%	15%
NAS	22%	29%	26%	30%

In terms of capacity market share, we have already see the crossover point, with Ethernet Storage at 52% of the total PB shipped, up from 47% in 2009, 42% in 2008 and 37% in 2007, as shown in the following table.

	2007	2008	2009	Q2 2010
FC SAN	62%	58%	53%	48%
iSCSI SAN	8%	13%	15%	18%
NAS	29%	29%	32%	34%

The inexorable growth of the market for Ethernet storage continued in the first half of 2010 – in fact we’re getting very close to Ethernet storage being the majority of networked storage in the Enterprise.

According to IDC’s recent Q2 2010 Worldwide Storage Systems Hardware Tracker, Ethernet Storage (NAS plus iSCSI) revenue market share climbed to 45%, up from 39% in 2009, 32% in 2008 and 28% in 2007, as shown below.

	2007	2008	2009	Q2 2010
FC SAN	72%	68%	61%	55%
iSCSI SAN	6%	10%	13%	15%
NAS	22%	29%	26%	30%

In terms of capacity market share, we have already see the crossover point, with Ethernet Storage at 52% of the total PB shipped, up from 47% in 2009, 42% in 2008 and 37% in 2007, as shown in the following table.

	2007	2008	2009	Q2 2010
FC SAN	62%	58%	53%	48%
iSCSI SAN	8%	13%	15%	18%
NAS	29%	29%	32%	34%

DISKCON USA 2010 - Santa Clara, CA September 9 & 10, 2010 - Conference and Trade show, Hyatt Regency, Santa Clara, CA Keynote Dinner - September 9, 2010 - Santa Clara Convention Center, Ballrooms E&F, 6pm No Host Cocktails and 7pm Dinner Announcing our Keynote Dinner Speaker - Clod Barrera, Distinguished Engineer and Chief Technical Strategist for IBM's Systems Storage, "The Innovator's Dream - Storage Systems in an Age of New Requirements and New Technology" Exhibit hours: Thu 10 am - 5 pm; Fri 10 am - 4 pm Note: SNIA SSSI members will speak at the following times: Tom Coughlin - Friday, September 10, 2010 # 1:15pm - 4:30pm # Futures of Storage Tom Coughlin, Eden Kim - Friday, September 10, 2010 # 9:00am - 12:00noon # Market Analyst Session # Dr. Tom Coughlin, Founder & President, Coughlin & Associates: Invest in New Technologies or Divest in Market Share: Hard Disk Drive and Component Companies Face a Critical Decision to Grow or Die #Eden Kim, CEO, Calypso Systems, Inc.: Calypso 2010 Blind Survey of SSD Performance #Esther Spanjer, Director, SSD Technical Marketing, SMART Modular Technologies - Poster Session: Enterprise SSD vs. Client SSD

Calypso recently presented an Industry Blind Survey of SSD Performance at the Flash Memory Summit. The survey compared (9) MLC, (8) SLC, and (1) 15K RPM SAS HDD.  The Chart shows all sample drives at RND 4K IOPS x Block Size for 65:35 R/W mix.  Small Blocks are in the back, large Blocks are in the front, IOPS are the Y axis.  This Chart clearly shows the general Steady State performance of SLC and MLC SSDs while referencing a 15K RPM SAS HDD. Take aways?  There is a lot of variance in performance between SSDs, but it is nice to see an apples to apples comparison on a Device Level.  RND 4K IOPS at a 65:35 R/W mix is a good corner case benchmark.  All  numbers are Steady State and comply with the recently released SNIA SSS Performance Test Specification.   All measurements were taken on the SNIA compliant Calypso Reference Test Platform.

Few weeks ago I was invited to present the state of the pNFS to the Purdue University. They are interested to be one of the early adopters and I jumped on that opportunity to promote pNFS. The presentation included the deep dive in the protocol and the need for scalability and I continued with the current state of the protocol and the initial client implementations in Linux and Open Solaris. The presentation and the discussion that followed addressed some basic questions that I expected around why should users trust that NFSv4.1/pNFS will not have the same faith as NFSv4.0. This is a legitimate question that often the pNFS developers in Linux ask themselves and the answer that I gave was same as the developers; pNFS will address many of the HPC needs. After additional details on scalability, performance, availability all the people in the room agreed that it is worth to look closer at pNFS. I recommended them to start looking at the current Fedora distribution that has both server and client pNFS file layout. As Purdue is a heavy Lustre user, they further asked how would Lustre support pNFS. If you didn't know, there are patches available for Lustre to support pNFS. I introduced Purdue team to the chief developer of Lustre so they can be the first to test the prototype patches. This will help the promotion of pNFS in academia. We need to continue our team effort to promote everywhere in universities pNFS.