Manage Learn to apply best practices and optimize your operations.

Data storage management: Identifying performance problems

Identify data storage performance problems with data storage management tips outlined by Enterprise Strategy Group's Tony Asaro in part three of this Gear6 podcast transcript.

The following is part three of a transcribed Gear6 storage performance podcast with Tony Asaro, senior analyst and consultant with the Enterprise Strategy Group, and Gary Orenstein, vice president of marketing at Gear6. The following table of contents will help you navigate to each part.

Storage performance podcast transcript

 Part 1: Storage performance trends and challenges
 Part 2: Tuning storage performance
 Part 3: Identifying storage performance problems

Gary Orenstein: If I'm a storage administrator how do I know if I have a storage performance problem? Where can I check and are there tools that I can use to evaluate parts of my environment?

Tony Asaro: All you have to do is either look at your emails or answer your phone. Probably one of your users is calling you up and screaming at you. That's not really a joke; that's the clearest indication. It's all about user and customer satisfaction and one of the clearest ways to measure, without getting into the technology or anything, is to see if people are complaining. You may not even have a performance problem even though you think it, but as long as your customers are happy, you don't have a performance problem. I would say that most users have very little tolerance for slow performance, so you will get people complaining to you if there is a performance problem.

The other answer is that, yes, there are storage management tools that allow you to analyze performance and then you can troubleshoot and things of that nature. Some are better than others. Some will be able to give you performance analysis from the application all the way to the disk drive. Some of them will only give you performance on what is going on in the storage system itself, which is very limited. So the notion is that if you can get a view holistically, because performance is a chain, there are a lot of variables involved in it, from the application all the way to storage.

Gary: As a storage performance expert, when someone gets on the phone with you and you begin, perhaps, one of your diagnostic interviews, what's one of the first questions that you ask people who think they have a performance storage problem?

Tony: There is a lot of complication in that. First of all we'd have to get general information. We need to understand what their environment is, we have to understand where the performance problem is. It's not something that's black and white. Performance problems will vary. It could be something as simple as an application brown out. These applications will just slow down; they are still available, but they'll just slow down. Now that could be a problem on the host side, it could be a problem with the network, it could be a problem with the storage system. . . You just have to collect a lot of information before you can begin to determine where the problem might lie. Is it a problem that they had from the initial installation? Is it a problem that happened two years into it?

Gary: Do you have general recommendations about how IT administrators can evaluate new technologies for performance and plan deployments. Any general tips or tricks?

Tony: First of all, they need to understand the performance characteristics of their data, because otherwise they may be looking at the wrong solutions. You need to understand what how your IO works. Is it something that is cache friendly? Is it something that is CPU intensive? Is it something that uses small transactions but lots of them? Or is it large transactions and very few of them?

The other thing is that you need to understand the components within the storage environment. That includes the applications, the storage system itself, your network . . . Where are the bottlenecks? What are the things, particularly, that can improve performance for you?

So first you need to understand what your IO characteristics are and what are the components within your storage environment that impact and can improve based on the IO characteristics. Then you have to ask the right questions of your storage system vendors, and you need to understand that they have an agenda; they have a particular bias and they really believe that bias, so you have to take everything they say with a grain of salt. Then you just have to ask lots of questions. You have to push back to get that information so that you're not surprised.

I'll give you just one quick thing I think is a big misunderstanding: A lot of times people will assume that because their database application has caching at the server level, at the host level, that it's not that important to have caching at the storage system level, for example. That is absolutely not true. We've seen much greater efficiency with storage systems doing that caching compared to application servers doing that caching. It's all additive, it's not like if you do caching in one place it won't provide value in another place. We see those things being actually very complimentary to one another. It's like a relay race. If a fast runner is handing off to another fast runner, then you are going to get better time in that relay race versus a fast runner handing it off to someone who is very slow. The other part of it is, too, that we've seen, pretty much on average in the different environments we work in, that even in open systems environments -- Unix, Windows, Linux -- about a 60 to 70% cache hit rate. On the storage systems side it's one of those things where again people misunderstand the characteristics of performance, and often times end users get misinformation because of the biases that come from different vendors.

Gary: Any thoughts about what we can expect to see, later this year or in 2007, that you're watching as the industry continues to move forward in terms of improving performance?

Tony: There's a lot of good news with improving performance and I think that we are seeing technology, like virtualization, really make an impact. People can stripe their data across lots of different drives. Again there's a price performance issue involved with that because the more drives you have, the more problems you have coming along with it. We are seeing more clustering technology, scalability, advancement in the network fabric itself. A lot of people trying to address performance issues with the notion that price/performance is the important key. I think that technologies are advancing in that area that are constantly making it easier to get the performance that we want, more flexible and more cost effectively.

Gary: Tony, we'll be watching your research and keeping our ear to the ground. Thanks very much for talking to us about storage performance. I was wondering whether you could give us another update on the activities ESG has planned for this Fall?

Tony: We're very excited about what we're doing on the storage performance side of things. And the best way to learn about it is to go to our website, which is You'll learn all about the storage performance elearning courses that we're putting together.

Gary: Excellent. Well, thanks again Tony.

Tony: Thank you, Gary.

Gary: For Gear6, I'm Gary Orenstein. Thanks very much to our listeners for joining us today. Today's program will be podcast. And for other podcasts in our series, visit Gear and our company blog, Thoughtput. Thanks very much.

Storage performance podcast transcript

 Part 1: Storage performance trends and challenges
 Part 2: Tuning storage performance
 Part 3: Identifying storage performance problems

Dig Deeper on Data Management Technology Services

Start the conversation

Send me notifications when other members comment.

Please create a username to comment.