DATA
Generated by scripts/gen-format-pages.py from docs/data/format-metadata/, FILE_FORMATS.csv and docs/formats-master.csv. Do not edit by hand: change the source, then run the script.
perf.data Preview.
At a glance
| Purpose | A Linux perf.data recording from perf record: a header, event attributes and a stream of records. |
| Extensions | .data |
| Poka parser | poka-perf |
| Viewer | poka-metadata-card-viewer |
| Depth tier | Metadata card (see Depth tiers) |
| Breadth tier | B4 Summary (see Breadth tiers) |
How much Poka reads
B4 Summary. The container and metadata are read and summarised (counts, properties, structure), but the main content is not rendered.
Confidence: medium (the reviewer read the code). Basis: Reviewed 2026-10-26: read parsers/poka-perf/src/main.rs (335 lines) and plugin.json. No unit tests or tests/samples.rs; the corpus has no .data sample. Covers .data. The card reads the header (magic, sizes, attributes, data and event-type sections), walks the records and shows their count and the most common types (samples, mmap, comm), the features bitmap and named features. Judgement: B4: the recording is summarised, but no sample is decoded or attributed.
What Poka does not read
- Samples are not decoded or attributed to functions
- Feature sections (build IDs, hostname, CPU description, command line) are named, not read
- Event attributes are counted, not decoded
- Other formats that use .data are refused as not perf (judgement from the code)
Libraries
Libraries Poka uses or has assessed for this format, with the status, licence and language the registry records.
- linux-perf-data (candidate; MIT OR Apache-2.0; Rust; https://github.com/mstange/linux-perf-data) — Parses perf.data files (file and pipe modes) and jitdump
Sources
- parsers/poka-perf/src/main.rs
- parsers/poka-perf/plugin.json