You are currently browsing the tag archive for the ‘2010’ tag.
Short Answer: Yes!
In my dealings with customers I’ve been requesting performance data from their storage systems whenever I can to see how different applications and environments react to new features. Today I’m going to give you some more real-world data, straight from a customer’s production EMC NS480.
I’ve pulled various stats out of Analyzer for this customer’s Exchange server, which has 3 mail databases totaling about 1TB of mail stored on the NS480 via FibreChannel connect. Since this customer is not extremely large (similar to most of our customers) they are using this NS480 for pretty much everything from VMWare, SQL, and Exchange, to NAS, web/app content, and Business Intelligence systems. There is about 30TB of block data and another 100TB of NAS data. FASTCache is enabled for all LUNs and Pools with just 183GB of usable FASTCache space (4 x 100GB SSDs). So in this environment, with a modest amount of FASTCache and very mixed workload, how does Exchange fare?
Let’s first take a look at the Exchange workload itself for a 24 hour period: (Note: There were no reads from the Exchange log LUNs to speak of so I left that out of this analysis.)
Total Read IOPS for the 3 databases: (the largest peak is a result of database maintenance jobs and the smaller peaks are due to backup jobs) Here it’s tough to see due to the maintenance and backup peaks, but production IO during the work day is about 200-400IOPS. By the way, a source-deduplicating incremental-forever backup technology, such as Avamar, could drastically reduce the IO Load and duration of the nightly backup
Total Write IOPS for the 3 databases: Obviously more changes to the database occurring during the work day.
Total Write IOPS for the 3 Log files: Log data is typically cached easily in the SP cache so FAST Cache isn’t terribly required here but I’m including it to show whether there is any value to using FASTCache with Exchange logs.
Now let’s look at the FASTCache hit ratios for this same set of data: (average of all 3 DBs)
First, the Read Activity: Here you can see that aside from the maintenance and backup jobs, FASTCache is servicing 70-90% of the Read IOPs. Keep in mind that a FASTCache miss could still be a Cache Hit if the data is in SP Cache. What’s interesting about this is that it looks like the nightly maintenance job is pushing the highest load.
And the Write Activity: The beauty of EMC’s FASTCache implementation being a read/write cache, the benefit extends beyond just read IO. Here you see that FASTCache is servicing 60-80% of the writes for these Exchange Databases. That’s a huge load off the backend disks.
And the Log Writes: Since Log writes are usually not a performance problem, I would say that FASTCache is not necessary here, and the average 30% hit ratio shown here is not great. If you wanted to spend the time to tune FASTCache a bit, you might consider disabling FASTCache for Log LUNs to devote the FASTCache capacity to more cache friendly workloads.
All in all you can see that for the database data, FASTCache is servicing a significant portion of the user generated workload, reducing the backend disk load and improving overall performance.
Hopefully this gives you a sense of what FASTCache could do for your Exchange environment, reducing backend disk workload for reads AND writes. I must reiterate, since an SP Cache hit is shown as a FASTCache miss, an 80% FASTCache hit ratio does not mean that 20% of the IOs are hitting disk. To illustrate this, I’ve graphed the sum of SP Cache Hits and FAST Cache Hits for a single database. You can see that in many cases we’re hitting a total of 100% cache hits.
Most interesting is the backup window where SP Cache is really handling a huge amount of the load. This is actually due to the Prefetch algorithms kicking in for the sequential read profile of a backup, something CX/VNX is very good at.
WordPress sent me an email with overall stats for 2010 and I thought I’d share a few things I noticed.
First, thank you to all of my readers as well as those who have linked to and otherwise shared my posts with others. I know that many of my peer bloggers have much higher numbers than I, but I still think 22,000 views is pretty respectable.
For 2010, my most popular post was Resiliency vs Redundancy: Using VPLEX for SQL HA. The top 5 posts are listed here..
EMC CLARiiON and Celerra Updates – Defining Unified Storage May 2010
NetApp and EMC: Real world comparisons October 2009
While EMC users benefit from Replication Manager, NetApp users NEED SnapManager June 2010
NetApp and EMC: Replication Management Tools Comparison June 2010
You may notice a theme here. First, Midrange Storage is HOT, and any comparisons between EMC and it’s competitors seem to get more attention compared to most other topics. Note #3 was written in 2009 and it’s the 3rd most viewed post on my blog in 2010. A secondary theme in these top 5 posts might be disaster recovery as well since most of these posts have DR concepts in the content as well.
Looking at search engine results the it looks like emc flare 30, clariion, and mirrorview network qos requirements were the hottest terms. The MirrorView one is pretty specific so I may do some blogging on that topic in the future.
With these stats in mind, I’ll keep working to hone my blogging skills through 2011 and sharing as much real-world information as I can, especially as I work with my customers to implement solutions. One thing I’ll do is try and provide the comparisons people seem to be interested in, but focusing on the advantages of products, while steering clear of negativity as much as possible.
Welcome to 2011! It’s going to be fun!
A Year Ago Today:
2010 has been a year of significant change for me. This time last year I was on my cell phone in the basement troubleshooting Exchange cluster problems at Nintendo. Since I was one of only two people managing storage, replication, and backups there, I was perpetually on-call and as many of you who manage storage already know, the SAN (similar to the IP network) is the first to be blamed for application issues.
In January, many months of work designing and building a warm disaster recovery site culminated in a successful recovery test, proving the value of data de-duplication and SAN replication vs. tape backups.
A Career Change:
As February wrapped up I said goodbye to Nintendo after nearly 5 years there, and 12 total years working in internal IT, to make a significant change and become a Technology Consultant within EMC’s Telco, Media, and Entertainment division.
Moving from the customer side over to a manufacturer/vendor is a pretty big change. I still have to deal with politics within IT projects, but the politics are different. I still have to worry about financial concerns with IT projects, but those concerns are different. I still work with customers, but they are external customers instead of internal customers. For the customers I work with, I have become a knowledgeable consultant, a friend, and a scapegoat — anything they need me to be at the time.
My first 10 months at EMC have been a whirlwind tour. In the midst of new hire training in Boston, followed by EMC World 2010, also in Boston, I began meeting with customers, attempting to learn about their business and environments. Some customers want to tell you everything they can about their environment; others give up as little information as possible.
Phases of Transition:
I don’t know if this is typical of other people who move from being a customer to working for a vendor, but looking back I see distinct phases that I went through as I adjusted to this new career.
- The Fire Hose Phase – For the first couple months, in addition to the new hire training and technical training, I had to learn how to use all of the internal tools, meet my customers, and try to glean as much information as possible about their IT infrastructures. I took lots of notes and my Livescribe pen proved its worth in short order.
- The Overcompensation Phase – My predecessor was well liked by customers and coworkers, so I set out to try and be as helpful as possible to try and build up a similar relationship with my customers. This backfired in some ways, worked in others, and eventually taught me that I really should just focus on what my customers need and the rest will fall in place.
- The Competency Phase – As I finally settled in to the new job and got comfortable I was able to start taking on more complex requests from customers. I had a better understanding of the capabilities of EMC products and how the capabilities really mapped to business problems. At this point I had really figured out my role within EMC as well as with EMC’s customers.
Working for EMC:
Now, as I look back at the past 10 months at EMC, I’m amazed at what I was able to accomplish coming into a sales organization for the first time. EMC has immense amounts of training available; and the people are all extremely helpful and forgiving. One of the things that amazed me is how accessible everyone is for a 45,000-person company. If I need detailed technical information on Symmetrix, I can email an engineer in Hopkinton, MA and within minutes get a very detailed reply, or in many cases a call back. In the past 6 months, I’ve had Product Managers, VP’s, Engineers, and even technical folks from other divisions on the phone, after hours, helping me get information together for my customers.
While I was getting used to my new job, my wife and I had our first child in August and even though I’d only been with EMC for 6 months at the time, my management was so helpful, covering for me longer than they really needed to and ensuring that my workload was reasonable enough to manage as I adjusted to being a new father.
I even achieved EMC Proven Professional certification along the way. EMC has a way of giving you the tools to succeed, and then allowing you to make the decision on how and whether to use them. It’s a competitive environment in a very positive way, where everyone wants everyone else to be successful as opposed to succeeding at another’s peril.
As this 2010 year comes to an incredible close for myself, my division, and EMC as a whole, 2011 is shaping up to be great as well. There are some changes coming on January 1st for my division that will affect me a little but I believe they will be positive changes overall. Next year I hope to continue honing my skills as a blogger and in my official role as Technical Consultant. Happy Holidays and New Year to you all.