storage ICT
MONITORING INFRASTRUCTURE cost is just as challenging as managing performance. In some cases, costs and performance are intertwined, with expenditures on infrastructure increased in an attempt to address any performance concerns.
Greater storage capacity and server CPU utilisation are high on the list of data centre objectives. At the same time, the cost of the I/O connections between the server and the storage are becoming more of a significant factor in the overall infrastructure cost. Virtualisation, cloud technologies and the shift from scale-up to scale- out architectures are affecting many areas of the data
centre, adding new benefits but, at the same time, new complexities. Virtualisation now includes the rebirth of storage virtualisation, as well as the introduction of Converged Enhanced Ethernet (CEE) and PCI virtualisation (SR-IOV). All of this brings promise for a greener, more efficient and responsive data centre. It also brings a tremendous amount of complexity to the environment and hence to management.
The term I/O is no longer limited to the hardware vendor’s vocabulary. I/O has developed into an entity onto itself and become a valuable resource, and one that is shared, or contended for, among various consumers within the data centre architecture. I/O management is an emerging technology and methodology that provides insightful I/O performance, capacity and event information from the application’s perspective. This is in contrast to domain-specific solutions, including system management, platform/server management, SAN management and storage management.
It has to do with managing how
I/O operates in support of a data centre application and looking inside the various I/O layers to monitor performance, troubleshoot issues and analyse I/O data to prevent potential disruptions.
Apply I/O management in the data centre
Diagnosing application performance problems is difficult. This problem is greatly compounded by the increase in complexity associated with the infrastructure that is in place to support the application server. This infrastructure has several tiers, with several layers of virtualisation, all of which manage I/O. As a result, there is an increasing need for I/O management within today’s complex data centre.
Collecting and trending I/O response times can benefit the IT administrator during proactive and reactive analyses of performance. There are several other pieces of information that I/O management adds to the toolbox. The combination of all the data, efficiently collected and managed with the right management tool, becomes an invaluable resource to: £ Proactively address potential performance problems
£ Reactively troubleshoot the root cause of performance issues
£ Deploy and maintain an efficient I/O infrastructure
It’s not just the SAN, check the application server
Whenever there is a performance problem, the storage network is often blamed first. As the industry transitioned from DAS to NAS and SAN, the storage environment became more complex and this introduced performance problems.
The use of hypervisors in the application server has also introduced performance problems because the traffic patterns are more random than they used to be, and the use of I/O caching technologies within application servers increases complexity further. However, often a fair amount of time can be consumed proving that the storage network is, in fact, healthy. In these
November 2013 I
www.dcseurope.info 51
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56