Recommended Reading : Hybrid IT Cloud Infrastructure Solution for Enterprise IT (Microsoft)

These document “outlines the hybrid IT cloud computing infrastructure  decisions that were made by a fictional organization based on a common set of enterprise IT requirements.  These articles also explains the rationale for why the company made the design decisions that they did.”  The four docs cover everything from the conceptual design to the the physical design and implementation.





Data Points : Delphix & Pure Storage Database Benchmark Shows 10x Price/Performance Gain

Delphix is teaming with Pure Storage to provide virtualized databases on flash storage.  What I found interesting was that they announced they had benchmarked the performance of an all-flash solution comparing  running databases on ordinary spinning  disks to the flash solution.  The test simulation workloads from a leading e-commerce company where the company makes 25-30 copies of its product databases for development and test.  Using traditional disks consumes 1 TB per copy and completes 35,000 transactions per minute.  Each copy requires a full duplicate. As a result,  supporting 26 copies requires 26 TBs of storage and to achieve 910,000 TPM (26 x 35k). The cost for this was about $2 million. Using Delphix Pure Storage solution created and supported the same 26 copies but was able to leverage in-line de-depulication to use only 1.5 TB total, each copy had full data at 1 million transactions per minute.  The cost of this solution was 1/10 the cost of the the disk solution. This great example of where de-duplication really makes a difference.



gotostorageGo to more posts on storage and flash storage at


VMworld 2013 Talks : Keynotes and Sessions on Software-Defined Datacenters

If you are interested in the VMworld 2013 talks … some are now available on YouTube now. Here are a number of interesting talks from the conference.

Monday General Session Keynote

Tuesday General Session Keynote

VMworld 2013: Session STO5715-S – The Next Phase in the Evolution of Enterprise Storage

In the area of Software-Defined Datacenter talks, there were a number of interesting talks. Two interesting ones.

VMworld 2013: Session VAPP4679- Software-Defined Datacenter Design Panel

VMworld 2013: Session EUC7370-S – The Software-Defined Data Center Meets End User Computer


gotostorageGo to more posts on storage and flash storage blogs at


SolidFire Demos VMware/CloudStack Cluster QoS Configured by CloudStack Plugin

SolidFire has put out an excellent, short video showing how SolidFire flash storage system integrates with the latest version CloudStack.  They show how to use their CloudStack plugin to connect a SolidFire array to two VMware clusters .  They show how to use quality-of-service in conjunction with them.  Here is the technical demo video:

A detailed guide to configuring SolidFire Storage in CloudStack gives technical details on how to create volumes, adjust performance IOPS on the volumes, adding volumes to VMware, adding volumes to XenServer, defining a volume as primary storage in CloudStack, advanced QoS configurations in CloudStack and much more.


You can catch part two of this – which is the reference architecture by checking out this page.


gotostorageGo to more posts on storage and flash storage blogs at


Data Points : Microsoft SQL Server on Flash Storage – Data Reduction Matters


Data Points is a type of post on this blog focused on showing use cases and metrics that suggest a point. Previously I mentioned how important in-line de-duplication and compression are in saving considerable space. These are two data reduction technologies found in many flash storage systems. A third is thin-provisioning. 

The company, Mattersight, is an software-as-a-service enterprise analytics company. They help customers capture analyze millions of human interactions.  They improved the overall performance of their analytics process by 9.6 times. But consider this, if they had not been able to leverage data reduction (which takes the form of in-line de-duplication, compression and thin-provisioning) they would not have made another significant saving – their database before was a 600 GB database. After they put it on a Pure Storage array that leveraged in-line  data reduction – it was reduced to 65 GB.  You can find more information here.

Pure Storage, like SolidFire and Hitachi, has a good story to tell on data reduction and it advertises this strength pointing out that the array suddenly becomes 5 to 10 times larger with in-line data reduction. And they are right. They highlight this with a de-dup ticker which shows the savings across every Pure Storage flash array and a comparison with other competitors. It is worth looking at their data reduction page because it highlights what many people overlook – these technologies dramatically increase the size of the array’s storage capacity.



gotostorageGo to more posts on storage and flash storage blogs at


NetBeans 7.4 RC1 Is Available, Adds Lots Features

My favorite software development environment, NetBeans, has released a new early access version – NetBeans 7.4 RC1.  There are a number of new features including support for HTML 5. Included in the new support for :

  • Cordova application development.
  • Support for Android and IOS browsers.
  • Editing support for SASS and LESS stylesheet language
  • HTML 5 features available in Java EE projects
  • HTML 5 features in PHP applications

Also better support for JavaScript – editing support for AngularJS, Knockout and ExtJS frameworks, navigator and code folding in JSON files and enhanced code completion. A lot of work went into improving PHP  and C/C++ support.  Considerable effort has also gone into providing hints (guidance) around Java exception handling.

NetBeans development environment provides wide support for Java (ME, SE, EE), C/C++, PHP, JavaScript, Groovy and a number of other languages.

You can see all the new changes in the Information page and release notes.

You can download the new release here.

There are some nice videos showing how to use Knockout  with NetBeans :


Recommended Reading : Oracle (RAC) Cluster on Virident FlashMAX II and vShare Solution Brief

In a previous post, Recommended Reading : Reference Architecture for Oracle RAC with Fusion IO’s ION Data Accelerator Software and Dell r720 ServersI provided an example of using PCIe flash cards to provide the storage for Oracle RAC.  Artem Danielov, a Solution Architect at Virident, pointed out that Virident’s PCIe cards provide similar functionality but don’t require a separation between storage and database servers.  You can see in more detail how Virident provides this functionality.


They provide an example of a 3 node Oracle RAC architecture with FlashMAX II and vShare. A three node Oracle RAC used Oracle 11g release 2 using six FlashMAX II 2.2 TB devices, two per each node.  When running Oracle Calibrate IO was run a database with a 4KB block size it yielded 1,434,268 IOPS and zero latency.


gotostorageGo to more posts on storage and flash storage blogs at


Accelerating VDI with Flash Storage : Super-Charging Your VDI Deployments

In this post we look at some of the great work being done at Pure Storage around supporting VDI deployments.  They have produced a four part series in which they demonstrate a VDI cloud under stress and running on Pure Storage flash-based arrays. A lot of the flash vendors have demonstrated similar high performance characteristics for VDI.  One aspect that sets apart different vendors is their support for in-line deduplication, thin-provisioning and compression, as well as, clones and snapshots.

In this  VDI demo (which is part two of four)  Pure Storage shows testing  they did in their labs. They show a VDI cluster with eight nodes with DRS and HA turned on. (You may want to look at the first part (of four) of these Pure Storage VDI videos. ) They created a linked clone desktop pool with 1000 linked clones and another persistent desktop pool with another 1000 desktops.  They provisioned 30 TB for the persistent desktops (30 GB/desktop).  The linked clone desktops they provision 4 TB volumes of 10 each.  They provisioned 80 TB with half of the storage used.  Many of the desktop are thin-provisioned.  They were getting about a data reduction of 22 to 1 which is on the high side – they guide customers to 6 to 1.  It is important to note that Pure Storage does data reduction in the form of : deduplication, thin provisioning and compression.  You can see what they did in this video (part two) :

In part three they show what the end-user experience is like.  They talk about the City of Davenport’s VDI deployment.  Flash storage had a dramatic effect. They used the VMware View Planner tool to give them performance. They used linked clones and persistent clones. They demonstrate a boot storm (or login storm).

Finally, in the fourth session – they focused on the administrator’s experience. They do some administrative operations and show it live. They showed some interesting numbers :

  • Provision 50 GB Desktop from template (traditional disk array : 5 min  Pure : 50 sec)
  • Boot 100 desktops  (traditional disk array : 15 min    Pure : 22 sec)
  • Storage vMotion 50 GB VM (traditional disk array : 4 min Pure : 25 sec)
  • Recompose 100 VMs (traditional disk array : 45 min Pure : 3 min)


gotostorageGo to more posts on storage and flash storage blogs at


Highlighting A Key Flash Storage Feature : High Speed Cloning of Live Databases with Snapshots

Database cloning with snapshots is an important feature.  Many flash/SSD-based storage arrays offer this feature.  Pure Storage has done a very nice job of showing off this feature.  In the first example they show how to clone a live Oracle database very easily.  Snapshots offer a quick way to copy a production database for reporting or testing or getting a copy of a database at point-in-time.

You can learn more about Snapshots with another Pure Storage video – in this video 500 snapshots are created while a performance monitor is running :



Recommended Reading : Reference Architecture for Oracle RAC with Fusion IO’s ION Data Accelerator Software and Dell r720 Servers

One basic question that is often asked is – should I use PCIe-based Flash Card or Flash/SSD array? Flash/SSD arrays are being used within enterprise and cloud settings but a considerable number of companies are also using PCIe-based flash cards inside their servers to run databases and applications.  The dominant PCIe vendor is clearly Fusion IO. Hands down.  You begin to see why when you see how much time and energy they have put into the software side of their product as well as hardware.   They have targeted some use-cases which make perfect sense for using PCIe flash cards within a cloud – for example Facebook is running MySQL on servers with PCIe flash cards.  Apple also is using PCIE cards in conjunction with database in iCloud.  Specifically around the MySQL ecosystem – Fusion IO is has been working with SkySQL to get atomic writes in MariaDB (a MySQL fork) and into the Percona Server.  This optimization on MariaDB has yielded over 50% improvement in write performance.   It is this type of value that differentiates vendors and is missing from some of the other PCIe vendors.  Another excellent use-case is around NoSQL databases like Aerospike. It is such an excellent use case that they have created a benchmark and they recommend SSDs or other flash devices.

One very interesting read is the Fusion IO whitepaper describing Reference Architecture for Oracle RAC with ION Data Accelerator and Dell r720 Servers. It shows a resilient architecture for running Oracle RAC.  The aim of this architecture is to reduce hardware costs and per-core Oracle licensing by 50% compared to an Exadata X3-2 Half Rack.  At the same time, there is a reduction of power consumption and delivering high IOPS for this architecture. When compared to an Oracle Exadata X3-2 the Fusion IO/Dell architecture consumes only a quarter rack (compared to half), 32 instead of 64 cores, requires only two database servers (compared to 4), requires only two storage servers compared to seven and provides 800,000 Read Only IOPS (compared to Exadata’s 750,000 IOPS) and provides a 50% cost reduction in licenses.  Pretty worthwhile reading is Fusion IO’s whitepaper on how they do this :