Posts Tagged ‘data center’
Posted August 6th, 2012
 |
Is SSD Really a Bad Idea?
BE CAREFUL WHOSE ADVICE YOU TAKE
By Eyal Markovich
|
A recent SeachStorage blog by Phil Goodwin, When Using SSD is a Bad Idea, offers some interesting advice on when and where you should avoid using solid state drive (SSD) solutions in the data center. I felt some of these tips could use some serious insight and elaboration so here goes.
Tip1: Don’t Use SSD when applications are not read intensive? Goodwin backs up this tip with the assertions that SSD write performance is poor and SSD wear is accelerated by lots of writes. He then cites a 90/10 read/write ratio as an arbitrary ideal for an SSD candidate.
First of all, I would argue that memory cell wear is really a function of average write IOPS, not simply whether an application is write heavy or not. To cite an extreme example, an application whose work is 100 percent writes is clearly not a good fit for SSD based on the Tip 1. However, SSD will last many years if this write-heavy application averages 100 writes per second. If it averages 10,000 write IOPS, your SSD will wear out 100 times faster.
Read the rest of this entry »
Tags:cache, data center, EMLC, I/O bottleneck, IOP, K2, Kaminario, memory cell wear, MLC, Phil Goodwin, random, read intensive, read/write ratio, Searchstorage, sequential, SLC, solid-state drive, SSD, virtualize, write intensive, write IOPS
Posted in SSD Architectures | No Comments »
Posted June 4th, 2012
 |
Solid-State Storage TCO and Simplicity
GETTING MORE OUT OF YOUR SSD INVESTMENT
By Gareth Taube, Vice President Marketing, Kaminario
|
Two blog posts have appeared in the past month with similar interesting themes. In the Storage Soup blog, TCO vs. ROI: Remember transition costs, Randy Kerns discusses the importance of total cost of ownership (TCO) in any storage decision and the role of transition costs, product lifespan, and operational and administrative costs in TCO calculations. Similarly, in the Wikibon blog, Simplicity and transparency are becoming standard features in storage, Scott Lowe talks about the growing importance of product simplicity in taming the storage beast. I particularly like this quote: “IT organizations need to spend less time touching the infrastructure and more time on the business.”
These are important factors to consider when deciding whether to take the SSD plunge, because many people still have the perception that SSD arrays like the Kaminario K2 are expensive. When you consider TCO and simplicity, however, they start to look more like bargains.
Read the rest of this entry »
Tags:cooling, data center, data migration, disk, DRAM, Flash, K2, Kaminario, LUNs, management interface, parallelization, power, RAID, Randy Kerns, ROI, scale, Scott Lowe, simplicity, snapshots, SPEAR, spindles, SSD, Storage Soup, TCO, total cost of ownership, Wikibon
Posted in SSD TCO | No Comments »
Posted April 8th, 2012
|
Murphy’s Law and Home-Grown SSD HA
BAKED IN BEATS WRAP AROUND
By Gareth Taube, Vice President Marketing, Kaminario
|
In his recent StorageSearch blog, High Availability Enterprise SSD’s, Zsolt Kerekes discusses why building a do-it-yourself HA solution typical of data center Fibre Channel or IP SAN hard disk array installations is not a viable option for an enterprise SSD array. The reasons, according to Zsolt, boil down to performance, flexibility of use, risk, complexity, and scalability. I would add Murphy’s Law.
Zsolt points out that any home-grown HA solution sitting in front of an SSD storage controller is likely to introduce considerable latency and time to the recovery process. When it comes to the mission critical applications typically running on SSD arrays, such as online transaction processing, time really is money and simply not something you want to sacrifice. “Wrap around” HA, as Zsolt calls it, also introduces architectural complexity and controller configuration issues that can gum up the works.
Read the rest of this entry »
Tags:cluster, data center, data corruption, DataProtect, enterprise SSD array, Fibre Channel, high availability, IP SAN, K2, Kaminario, latency, Murphy's Law, N+1, Online Transaction Processing, outage, SSD, Storage, storage node, StorageSearch, Zsolt Kerekes
Posted in SSD Storage Performance | No Comments »
Posted February 2nd, 2012
|
Goodbye Spinning Disks
MAKE WAY FOR THE TOTAL SSD DATA CENTER
By Gareth Taube, Vice President Marketing, Kaminario
|
In two blog entries on storagesearch.com, Zsolt Kerekes delivers an interesting take on the future domination of SSD in the data center. In SSDs Replacing HDDs? That’s Not Exactly the Way it Happened, Zsolt predicts a time just five or six years from now when hard disks will simply be unacceptable in the data center, even if they’re given away free. In This Way to the Petabyte SSD, he goes into more detail, laying out how he expects SSD to eliminate hard drives from their last data center bastion: bulk storage.
The key driver for bulk SSD, according to Zerekes, will be the increasing value of archived data, which companies will harness to provide profitable customer data services. In such an environment, offline storage will no longer be an option. Instead there will be a need for massive amounts of very high-density, high-performance near-line storage. Data center space and operating budget limitations will mandate the most compact, power-efficient storage solution possible. Hence SSD. Kerekes predicts that bulk SSD storage will have the ability to keep most of its memory blocks in a powered-off sleep mode until they’re required. Bulk SSD won’t be the fastest SSD available, but it will be many times faster than disk, and will virtually pay for itself in power cost savings, reduced data center real estate, and longer life and reliability than hard disks.
Read the rest of this entry »
Tags:analytics, archived data, backup, bulk storage, business intelligence, CRM, data center, HDD, K2, Kaminario, Kerekes, machine logs, memory blocks, near line storage, offline storage, OLTP, petabyte, sleep mode, social network, SSD, storagesearch.com, Zsolt
Posted in SSD Architectures | 1 Comment »
Posted January 20th, 2012
|
Kaminario for Cloud Speed and Reliability
NO DARK CLOUDS HERE!
By Gareth Taube, Vice President Marketing, Kaminario
|
In his December 18 SSD Guy blog entry, Jim Handy of Objective Analysis, citing SandForce’s new SSD processor, discusses why cloud providers need to choose their SSD solutions carefully. He discusses some of the capabilities cloud computing data centers need from SSD, including very low latency, high capacity at a low price, and high reliability.
Kaminario agrees with many of these cloud requirements. However, sometimes we go about providing them in slightly different and multiple ways. Here’s our take on SSD in the cloud and how Kaminario provides the features cloud data centers require.
Read the rest of this entry »
Tags:cloud computing, data center, DRAM, Flash, freedom of choice, FusionIO, high availability, Jim Handy, K2, Kaminario, latency, MLC, Objective Analysis, parallel processing, reliability, Scalability, SPEAR architecture, SSD, SSD Guy, the cloud, UPS
Posted in SSD Storage Performance | No Comments »
