The Virtualization Practice

Performance Management

Performance Management covers monitoring the physical infrastructure, the virtual infrastructure and applications for end-to-end performance and service levels. It covers Application Performance Management, Infrastructure Performance Management, Operations Management, Capacity Planning, and Capacity Management. ...
Environments covered include Virtualization Performance Management, Software Defined Data Center Performance Management, and Cloud Performance Management. Key issues include ensuring the performance of virtualized and cloud based data centers, ensuring the performance of software defined data centers (SDDC performance management), ensuring virtualized application performance, cloud application performance, and SDDC application performance. Key vendors covered include VMware, AppDynamics, AppEnsure, AppFirst, AppNeta, Astute Networks, Aternity, BlueStripe, Boundary, Cirba, CloudPhysics, Correlsense, Compuware, Dell, Embotics, ExtraHop, GigaMon, Hotlink, HP, Intigua, ManageEngine, New Relic, Prelert, Puppet Labs, Riverbed, Splunk, Tintri, Virtual Instruments, Virtustream, VMTurbo, Xangati, and Zenoss.

In my last post I was Exploring a Limitation of VMware DRS and I have encountered another situation that had similar symptoms but the resolution was quite different. This problem was occurring on a VMware ESX 3.5 cluster that was specifically affecting Windows 2008 R2 64bit virtual machines that were configured with four processors and eight gigabits of RAM. These virtual machines were taking an extreme amount of time to perform a reboot. During the reboot ESXTOP was showing insane %RDY with spikes climbing over 200. When the reboot would finally finish several services would have failed to start.

While we may well be on the road towards VMware becoming the layer of software that talks to the hardware in the data center – removing Microsoft from that role, this is not the end of Windows. If Windows were just an OS, it would be severely threatened VMware insertion into the data center stack. But Windows is not just an OS. Windows is also a market leading applications platform with .NET have a far greater market share and base of developers than vFabric. Windows is also in the process of becoming a PaaS cloud – one that will be living at Microsoft, at thousands of hosting providers, and at probably every enterprise that is a significant Microsoft customer. This incarnation of Windows is at the beginning of its life, not the end.

I have been a big fan of VMware’s Distributed Resource Scheduler (DRS). VMware DRS is a service or feature that will dynamically allocate and balance computing resources across the hosts in a cluster. In all of the environments I have work with so far, DRS has been a fantastic tool for getting and maintaining that balance across all the hosts in a cluster. Recently though I have come across a limitation of VMware’s DRS that is worth mentioning.

Monitoring from the Cloud

I have started the year 2011 out by looking at some of the different monitoring solutions available for us to have an insight into the health and welfare of the systems that we support. In your typical monitoring solution you would install the monitoring server in your environment and let the system discover all the devices in your infrastructure and or to control the licenses we would manually enter the devices that we want to monitor. Some of these monitoring servers solutions have to have a beefy box to begin with and all solutions will need a great deal of “tweaking” to control the number of false positives as well as time put in to be able to report on what exactly we care to be alerted about.

Given the VNXe’s expandability to include fibre channel cards in the future. This storage looks very attractive to those SMBs who have made the investment previously to move towards fibre. Making use of your existing infrastructure whether fabric or Ethernet would lower the cost of adoption for the low-end EMC product. The VNXe’s expandability is one of those items that makes it an attractive tool for other uses. What are those other uses with respect to security, DR, BC, and disaster avoidance?

If synthetic transactions are dead as an approach for determining availability and performance from the perspective of the end users of an application then something has to take their place. The two candidates are approaches that analyse data on the IP network, and client side agents. Both will likely rise in prominence as more applications become more dynamic.