Posts by: dstrebel
The cost of Cisco UCS?
Lately I have been having a lot of discussions around Cisco UCS and the common theme of these meetings tends to be "My traditional servers cost much less."
A lot of times there is a misconception of what's included with Cisco UCS compared to what's included when purchasing traditional servers. UCS is more about a server architecture and less about just your typical server blade, so you need to factor in more components when comparing it to a traditional servers.
Below is a summary of components that you should consider when comparing the cost of Cisco UCS to traditional servers.
Comments Off
EMC VFCache the new face of “EMC Project Lightning”
EMC debuted VFcache today, which was codenamed "Project Lightning." So what is this thing they call VFCache? VFCache is a server Flash caching technology that reduces latency and increases throughput by moving the active dataset up to the server-side PCI-e cache. It accelerates block I/O reads and also protects data by using a write-throughcache to the back-end storage.
First thought is how is VFCache different from similar products currently in the marketplace? Well let’s first look at how it compares to a DAS based cache solution.
DAS-based PCIe Flash technology stores the application directly on the Flash card, so in this architecture it doesn't provide protection if the card were to fail. With VFCache write-through cache, you have protection against data loss as it ...
Read More
Comments Off
Read More
VMware Datastore Clusters and SDRS
New to VMware vSphere 5 is a feature called “Datastore Clusters”. Datastore clusters allow you to aggreagate storage resources, which enables you to set different resource policies on the Datastore Cluster. Datastores within a Datastore Cluster can be thought of as a hosts in a vSphere cluster.
Whenever you add datastore to a Datastore Cluster that datastore’s resources become shared resources within the Datastore cluster. Once your Datastore Cluster is setup you can then enable a new feature called Storage DRS.
Storage DRS
Storage DRS has extended the Distributed Resource Scheduler to the storage resources. SDRS enables VMDK to be placed on the optimal datastores within a Datastore Cluster based on set policies. SDRS can be set to manual or to automatic. Manual mode SDRS will make recommendations ...
Read More
Comments Off
Read More
Tintri VMstore T440 Product Demo
A few months ago Tintri released it's VMstor T440 appliance. The T440 is a 4U, multi-processor, X86 storage appliance. The T440 serves up a single NFS datastore to your vSphere host through gigabit or 10GbE ethernet interface.
The Tintri T440 is not the VM admins usual storage. Tintri takes a different approach to storage and uses VM abstractions, where as traditional storage abstracts volumes and LUNs. With Tintri you are now managing VM's and not volumes or LUNs.
Tintri's approach really comes out in it's management interface as you can see metrics such as latency, flash-hit ratio, throughput and etc. Below is a demo of the Tintri's management interface that will get you a little more familiar with the Tintri approach to storage.
http://youtu.be/3PmFVsrHj08
Comments Off
Virtual End-User Computing: It’s all in the Design
If I had a dollar for every time I heard "This is the year of desktop virtualization" I could probably buy that new set of Callaway golf clubs I've been eyeing. As we've seen in the industry, there really hasn't been a year of the virtual desktop. So the question is "Why?" I mean, it provides many benefits—security, flexibility, manageability, and so on. However, many companies are falling into the typical VEUC pitfalls such as never ending POC phases, ROI justifications, capital cost, and not truly understanding the use cases for their environment.
Here are some tips for designing a VEUC environment that will help you bypass the pitfalls of deploying a VEUC environment.
1. Include the End-Users
The number-one goal when deploying a virtual desktop environment is ...
Read More
Comments Off
Read More
“Total vEngineer”
With the IT landscape changing and the stack becoming more integrated than ever, we need to create more of what I call the "Total vEngineer." If you look at many IT departments, their engineers are siloed into various different groups--Virtualization, Storage, Networking, Platform, etc. This causes issues such as miscommunication, coordination problems, and delays. At the end of the day, we need to integrate our teams in every possible way.
The thought of a "Total vEngineer" came to me when watching a clip from the 74 World Cup between Holland and Argentina. You're probably already asking what the heck does football (soccer) have to do with an engineer I'll get to that in a second? The 74 Holland team played a different style of football. They ...
Read More
Comments Off
Read More
Who is Isilon?
Isilon is the global leader in scale-out storage solutions and was recently acquired by EMC. Isilon takes a different approach to storage than the traditional architecture, by creating the OneFS OS to create a efficient and simple storage architecture.
One of the major differences between OneFS and traditional storage is that OneFS creates a single file system that spans an entire Isilon cluster. With traditional storage when you start scaling your environment you start creating islands of storage systems, volumes, and management points. This leads to a lot of management overhead and increases operational cost. By taking the approach of a single file system that spans an entire cluster you are eliminating management points and allowing for more efficient use of the storage.You are no ...
Read More
Comments Off
Read More