Home ›

Understanding a Context Switching Benchmark

Issue 57

From Issue #57
January 1999

Jan 01, 1999  By Randy Appleton
 in
A look at the Linux kernel scheduler.
The Search Loop

There is probably no way to make the search loop run faster; it is well-written code. However, it could be eliminated by simply keeping contexts in the ready queue in sorted order; then the next context to run is the context at the head of the ready queue. Keeping the ready queue in sorted order would require code to take each context being added to the ready queue and place it in the appropriate position. The time needed to find this position would add complexity to the scheduler. For large load averages (implying many contexts on the ready queue), there might be a considerable time savings, but in the more normal case of small ready queues, there is no significant savings.

The Recalc Loop

Minimizing the time needed by the recalc loop would be easy. Again, it is well-written code not likely to be improved upon, but it need not run as often as it does. By changing sched_yield, the recalc loop can run much less often.

For Linux 2.0.30, sched_yield acts as if the yielding context has used the entire time slice. Instead, what if sched_yield acted as if the yielding context had used only one tick of its time slice? Several effects would be noticed:

  • The yielding process would have its priority reduced by one, rather than temporarily set to zero.

  • The recalc loop would run much less often. Generally, it would run 1/20 as often (depending on process priority).

The new sched_yield is shown in Listing 3. Compare it to the one in Listing 2. Only one more line is included, yet a large increase in performance is shown for this benchmark.

Table 2 summarizes the performance after this change was made. Note that as the run-queue length increases, both the NT and the Linux scheduler take longer to context switch. Linux starts out being the faster context switcher, but NT does relatively better as run-queue length increases. For run-queue lengths of 20 or less (almost always the case in real life), Linux is better.

Table 2

Summary

By making a two-line change to the source code, this benchmark can be greatly improved. However, the benchmark arguably does not reflect real-life usage. Nevertheless, only a two-line change to the kernel is required for a significant benefit to a small number of users. After this change, Linux outperforms Windows NT in all aspects of process and thread creation and in context switching.

All listings referred to in this article are available by anonymous download in the file ftp.linuxjournal.com/pub/lj/listings/issue57/2941.tgz.

Randy Appleton (randy@euclid.nmu.edu) is a Professor of Computer Science at Northern Michigan University. He's been involved in Linux since the 0.99 days, and manages the largest collection of Linux computers in Michigan's Upper Peninsula. His other interests include foreign travel and flying small airplanes.

______________________

White Paper
More Resources
Fabric-Based Computing Enables Optimized Hyperscale Data Centers

Today’s modular x86 servers are compute-centric, designed as a least common denominator to support a wide range of IT workloads. Those generic, virtualized IT workloads have much different resource optimization requirements than hyperscale and cloud applications. They have resulted in a “one size fits all” enterprise IT architecture that is not optimized for a specific set of IT workloads, and especially not emerging hyperscale workloads, such as web applications, big data, and object storage. In this report, you will learn how shifting the focus from traditional compute-centric IT architectures to an innovative disaggregated fabric-based architecture can optimize and scale your data center.

Learn More

Sponsored by AMD

White Paper
More Resources
Red Hat White Paper: Using an Open Source Framework to Catch the Bad Guy

Built-in forensics, incident response, and security with Red Hat Enterprise Linux 6

Every security policy provides guidance and requirements for ensuring adequate protection of information and data, as well as high-level technical and administrative security requirements for a system in a given environment. Traditionally, providing security for a system focuses on the confidentiality of the information on it. However, protecting the data integrity and system and data availability is just as important. For example, when processing United States intelligence information, there are three attributes that require protection: confidentiality, integrity, and availability.

Learn more about catching the bad guy in this free white paper.

Learn More

Sponsored by DLT Solutions