Extreme Linux performance monitoring and tuning

Looking for Linux performance monitoring and tuning resources to conduct analyzing work? ufsdump.org has a wide array of resource for Unix systems. In these two part PDF provided by ufsdump.org, titled, “Extreme Linux Performance Monitoring and Tuning”, ufsdump.org highlights the various components from CPU, memory and I/O that should be monitored and tuned accordingly. Concepts such as context switches, run queue, CPU utilization, time slicing and priorities are discussed for CPU. For memory, the PDF steps through performance concerns in Virtual Memory, Virtual Size (VSZ) and Resident Set Size (RSS), Paging/ Swapping, Kernel Paging with pdflush and kswapd. Lastly in I/O, the articles walks through concepts on reading and writing data for memory pages, major and minor page faults, file buffer cache, types of memory pages and writing data pages back to disk. All these concepts are great tips for performance tester in determine the performance of the Linux servers. To download the PDF, click on link below: Read the rest of this entry »

Detecting memory leaks

Memory leaks are caused by programs that allocate virtual memory and fail to free after they are finished with it. Memory leaks are nasty program bugs that are sometimes difficult to find. A program containing memory leak bug often executes to completion and produces the correct results, so the presence of the bug is not always detected. In fact, as long as the program containing the memory leak does not impact other executing processes, the bug can go undetected for a long time. Read the rest of this entry »

How do we determine hardware functionality?

In this article, we will discuss two counters proposed by Mitch Tulloch to detect if the hardware is functioning properly. The two counters, System\Context Switches/sec and Processor(_Total)\% Privileged Time, both related to processor are great counters to use. In general, by using the two counters, what we want to determine the type of threads that the processor is currently working (or had been working on) and if it is busy handling interrupts instead of performing useful work. Read the rest of this entry »

% Disk Time may exceed 100 percent in Controller

When you are running a load test and you may have encounter that the % Disk Time exceeds 100% in Controller or when you are analyzing the graphs in Analysis. Over 100%? Weird right? And when you open perfmon to verify, and it’s still more than 100%. Is it a bug of Windows? What’s the cause behind this? Read the rest of this entry »

How do we determine which WebLogic thread is causing CPU contention using PsList?

As mentioned in the title, this is specified to WebLogic application instance. The purpose of doing this is to find out which thread is consuming the most CPU usage and what it is doing at that point of time. This is especially useful when your instance is running at 100% utilization and you want to troubleshoot the problem.

To do that, you have to download the utility, PsTools from Microsoft Sysinternals. PsTools has a command, PsList that can look at the thread level on the OS. Read the rest of this entry »