With the final major capability for BPF tracing (timed sampling) merging in Linux 4.9-rc1, the Linux kernel now has raw capabilities similar to those provided by DTrace, the advanced tracer from Solaris. As a long time DTrace user and expert, this is an exciting milestone! On Linux, you can now analyze the performance of applications and the kernel using production-safe low-overhead custom tracing, with latency histograms, frequency counts, and more.
There have been many tracing projects for Linux, but the technology that finally merged didn’t start out as a tracing project at all: it began as enhancements to Berkeley Packet Filter (BPF). At first, these enhancements allowed BPF to redirect packets to create software-defined networks. Later on, support for tracing events was added, enabling programmatic tracing in Linux.
Read more at Brendan Gregg’s Blog
