Lowering Latency in Linux: Introducing a Preemptible Kernel
Thus, with the preemptive kernel patch, we can reschedule tasks as soon as they need to be run, not only when they are in user space. What are the results of this?
Process-level response is improved twentyfold in some cases. (See Figure 1, a standard kernel, vs. Figure 2, a preemptible kernel.) These graphs are the output of Benno Senoner's useful latencytest tool, which simulates the buffering of an audio sample under load. The red line in the graphs represents the amount of latency beyond which audio dropouts are perceptible to humans. Notice the multiple spikes in the graph in Figure 1 compared to the smooth low graph in Figure 2.
The improvement in latencytest corresponds to a reduction in both worst-case and average latency. Further tests show that the average system latency over a range of workloads is now in the 1-2ms range.
A common complaint against the preemptible kernel centers on the added complexity. Complexity, opponents argue, decreases throughput. Fortunately, the preemptive kernel patch improves throughput in many cases (see Table 1). The theory is that when I/O data becomes available, a preemptive kernel can wake an I/O-bound process more quickly. The result is higher throughput, a nice bonus. The net result is a smoother desktop, less audio dropout under load, better application response and improved fairness to high-priority tasks.
Kernel hackers are probably thinking, “How does this affect my code?” As discussed above, the preemptible kernel leverages existing SMP support. This makes the preemptible kernel patch relatively simple and the impact to coding practices relatively minor. One change, however, is required. Currently, per-CPU data (data structures unique to each CPU) do not require locking. Because they are unique to each CPU, a task on another CPU cannot mangle the first CPU's data. With preemption, however, a process on the same CPU can find itself preempted, and a second process can then trample on the data of the first. While this normally is protected by the existing SMP locks, per-CPU data does not require locks. Data that does not have a lock, because it is protected by its nature, is considered to be “implicitly locked”. Implicitly locked data and preemption do not get along. The solution, thankfully, is simple: disable preemption around access to the data. For example:
int catface[NR_CPUS]; preempt_disable(); catface[smp_processor_id()] = 1; /* index catface by CPU number */ /* operate on catface */ preempt_enable();
The current preemption patch provides protection for the existing implicitly locked data in the kernel. Thankfully, it is relatively infrequent. New kernel code, however, will require protection if used in a preemptible kernel.
We still have work to do. Once the kernel is preemptible, work can begin on reducing the duration of long-held locks. Because the kernel is nonpreemptible when a lock is held, the duration locks are held corresponding to the system's worst-case latency. The same work that benefits SMP scalability (finer-grained locking) will lower latency. We can rewrite algorithms and locking rules to minimize lock held time. Eradicating the BKL will help too.
Identifying the long-held locks can be as difficult as rewriting them. Fortunately, there is the preempt-stats patch that measures nonpreemptibility times and reports their cause. This tool is useful for pinpointing the cause of latency for a specific workload (e.g., a game of Quake).
What is needed is a goal. Kernel developers need to consider any lock duration that extends over a certain threshold, a bug for example, 5ms on a reasonably modern system. With that goal in mind, we can pinpoint and ultimately eliminate the areas of high latency and lock contention.
|Non-Linux FOSS: libnotify, OS X Style||Jun 18, 2013|
|Containers—Not Virtual Machines—Are the Future Cloud||Jun 17, 2013|
|Lock-Free Multi-Producer Multi-Consumer Queue on Ring Buffer||Jun 12, 2013|
|Weechat, Irssi's Little Brother||Jun 11, 2013|
|One Tail Just Isn't Enough||Jun 07, 2013|
|Introduction to MapReduce with Hadoop on Linux||Jun 05, 2013|
- Containers—Not Virtual Machines—Are the Future Cloud
- Non-Linux FOSS: libnotify, OS X Style
- Lock-Free Multi-Producer Multi-Consumer Queue on Ring Buffer
- RSS Feeds
- Introduction to MapReduce with Hadoop on Linux
- Validate an E-Mail Address with PHP, the Right Way
- Weechat, Irssi's Little Brother
- Tech Tip: Really Simple HTTP Server with Python
- New Products
- Help with Designing or Debugging CORBA Applications
- Welcome to 1998
25 min 49 sec ago
- notifier shortcomings
49 min 31 sec ago
2 hours 26 min ago
- Android User
2 hours 28 min ago
- Reply to comment | Linux Journal
4 hours 21 min ago
7 hours 10 min ago
- This is a good post. This
12 hours 23 min ago
- Great, This is really amazing
12 hours 25 min ago
- These posts are really good
12 hours 27 min ago
- It’s a really great site you
12 hours 29 min ago
Free Webinar: Hadoop
How to Build an Optimal Hadoop Cluster to Store and Maintain Unlimited Amounts of Data Using Microservers
Realizing the promise of Apache® Hadoop® requires the effective deployment of compute, memory, storage and networking to achieve optimal results. With its flexibility and multitude of options, it is easy to over or under provision the server infrastructure, resulting in poor performance and high TCO. Join us for an in depth, technical discussion with industry experts from leading Hadoop and server companies who will provide insights into the key considerations for designing and deploying an optimal Hadoop cluster.
Some of key questions to be discussed are:
- What is the “typical” Hadoop cluster and what should be installed on the different machine types?
- Why should you consider the typical workload patterns when making your hardware decisions?
- Are all microservers created equal for Hadoop deployments?
- How do I plan for expansion if I require more compute, memory, storage or networking?