[DTrace-devel] RELEASE: DTrace for Linux 2.0.0-1.7
Eugene Loh
eugene.loh at oracle.com
Thu Sep 30 11:43:33 PDT 2021
We am happy to announce the availability of the latest development
version of DTrace for Linux (2.0.0-1.7).
This new version is based on BPF and other Linux kernel tracing features
and is implemented entirely as a userspace application.
The functionality is still limited in comparison to the kernel module
based version of DTrace for Linux (currently at version 1.2.1-1).
Development continues in an incremental fashion to make the full feature
set of DTrace available using existing kernel features.
WHERE TO FIND IT?
The new version of DTrace for Linux is available at:
https://github.com/oracle/dtrace-utils/tree/2.0-branch-dev
The most recent release tag is 2.0.0-1.7.
FEATURES
- BEGIN and END probe (with full support for the expected semantics).
- ERROR probe support.
- Function Boundary Tracing (FBT) probes.
- System call entry and exit probes.
- Timer-based profile-* and tick-* probes.
- Statically Defined Tracing (SDT) probes for kernel tracepoints.
- [NEW] Arguments for SDT probes can be retrieved with arg0-arg9.
- pid provider support for userspace function boundary tracing.
- Aggregated data collection support.
- Aggregation functions: avg, count, llquantize, lquantize, max, min,
quantize, stddev, and sum.
- Aggregation actions: normalize() and denormalize().
- Pretty-printing for aggregations using the printa() action.
- Support for local and global variables with storage sizes greater
than 8 bytes. This adds struct and union support for local and global
variables.
- Initial support for strings: string constants in D clauses, assignment,
built-in variables, trace(), strlen().
- [NEW] The strjoin() and substr() subroutines.
- Various features to support stack tracing.
- Direct compilation of D source code into BPF programs.
- Efficient use of pre-compiled BPF functions for library functions.
- [NEW] A bpflog option to request the BPF verifier log for loaded
programs.
- BPF program linking of dynamically generated code and pre-compiled code
to facilitate code sharing and code re-use.
- Improved integrated disassembler for generated BPF code at the
clause and program level (-S in combination with the new -xdisasm=#\
option).
- Improved trace data buffer handling based on memory mapped perf event
ring-buffers.
- Deferred creation of kernel level probes. Listing available probes
does
not require them to be created at the kernel level.
DEPENDENCIES
DTrace for Linux depends on libctf (part of newer binutils) -or-
libdtrace-ctf. While libctf is preferred, building against
libdtrace-ctf is fully supported. It can be found at:
https://github.com/oracle/libdtrace-ctf
DTrace for Linux makes use of BPF library functions that are compiled at
build time. It depends on BPF support in GCC and binutils to generate
the pre-compiled BPF function library.
DTrace for Linux makes use of 3 additional features that are not
commonly available in the Linux kernel:
- CTF data generation at compile time: this provides important datatype
information for kernel and kernel module symbols.
- waitfd() system call: this provides a mechanism to monitor for state
changes of processes that are being traced.
- /proc/kallsyms module grouping support: this adds annotation with
module
names to all symbols that are part of a kernel module even if the
module
is configured to be compiled into the kernel proper. This allows for
consistent ways to refer to probes by module and function (or
probe) name.
These additional support features for tracing are available at:
https://github.com/oracle/dtrace-linux-kernel/tree/v2/5.8.1
Please consider joining our development list: dtrace-devel at oss.oracle.com
Enjoy!
More information about the DTrace-devel
mailing list