For a long time at Red Hat, all executables in RPMs were built with debuginfo enabled. While this practice makes it easier for people in support to investigate issues reported using tools such as GDB and crash, there are other important non-debugging uses for the resulting debuginfo.
Continue reading Debuginfo is not just for debugging programs
This blog is the third in a series on stapbpf, SystemTap’s BPF (Berkeley Packet Filter) backend. In the first post, Introducing stapbpf – SystemTap’s new BPF backend, I explain what BPF is and what features it brings to SystemTap. In the second post, What are BPF Maps and how are they used in stapbpf, I examine BPF maps, one of BPF’s key components, and their role in stapbpf’s implementation.
In this post, I introduce stapbpf’s recently added support for tracepoint probes. Tracepoints are statically-inserted hooks in the Linux kernel onto which user-defined probes can be attached. Tracepoints can be found in a variety of locations throughout the Linux kernel, including performance-critical subsystems such as the scheduler. Therefore, tracepoint probes must terminate quickly in order to avoid significant performance penalties or unusual behavior in these subsystems. BPF’s lack of loops and limit of 4k instructions means that it’s sufficient for this task.
Continue reading “SystemTap’s BPF Backend Introduces Tracepoint Support”
Each day I get off the elevator and walk to my desk at Red Hat I am greeted by a very large sign that says “Release early, release often.” This sign encourages us to get incremental results and get feedback on the software that we are working on early rather than uncovering a fatal flaw in design or implementation late in the process.
Continue reading “Monitoring: Corollary to "Release Early and Often"”
One common idiom in performance monitoring is how long did it take for a program to do something. For example you may want to know the time taken for database queries in PostgreSQL or just-in-time translations in a Java Virtual Machine. SystemTap and user-space markers in Linux packages make it much easier to determine the duration of those operations.
The user-space markers compiled into Linux packages mark key points in the code where particular actions occur. The user-space markers also provide arguments that provide additional information about the action. For example, the markers and the available arguments in PostgreSQL can be listed using using the SystemTap command:
$ stap -L 'process("postgres").mark("*")'
The two user-space markers related to the start and completion of a query are:
Continue reading “How Long Does It Take to …”