Linux Perf Users
 help / color / mirror / Atom feed
* [RFC PATCH 0/4] perf: Add perf.data tracepoint events to trace.dat conversion
@ 2026-06-08 12:59 Tanushree Shah
  2026-06-08 12:59 ` [RFC PATCH 1/4] perf/trace-dat: Add trace.dat export infrastructure Tanushree Shah
                   ` (4 more replies)
  0 siblings, 5 replies; 10+ messages in thread
From: Tanushree Shah @ 2026-06-08 12:59 UTC (permalink / raw)
  To: acme, jolsa, adrian.hunter, vmolnaro, mpetlan, tmricht, maddy,
	irogers, namhyung, linux-kernel
  Cc: linux-perf-users, linuxppc-dev, atrajeev, hbathini, Tejas.Manhas1,
	Tanushree.Shah, Shivani.Nittor, Tanushree Shah

This RFC patch series introduces support for converting perf.data files
containing tracepoint events into trace.dat format, enabling seamless
visualization and analysis using KerneShark.

======================
Background and Motivation
======================

Currently, perf and trace-cmd operate as separate tracing ecosystems with
incompatible data formats. Users who collect tracepoint data with
'perf record' cannot easily visualize it in KernelShark's graphical
timeline view or leverage trace-cmd's analysis capabilities.

This creates workflow friction when users need to:

- Visualize perf tracepoint data in KernelShark's interactive graphical
  timeline
- Share trace data between perf and trace-cmd workflows and toolchains
- Perform architecture-independent conversion and analysis of traces

This conversion bridge eliminates these barriers by enabling seamless
data exchange between perf and trace-cmd ecosystems, allowing users to
choose the best tool for each analysis phase.

======================
Implementation Overview
======================

The series implements the trace.dat file format specification (version 7)
within perf's data conversion framework.

**Patch 1/4: Core trace.dat Export Infrastructure**
Introduces util/trace-dat.c and util/trace-dat.h implementing:
- Per-CPU raw event buffer management (init, collect, free)
- Ftrace ring buffer page construction
- trace.dat section writers (strings, options, flyrecord sections)

**Patch 2/4: Metadata Integration**
Extends util/trace-event-read.c to write trace.dat metadata during
perf.data
parsing:
- Initial format header (magic, version, endian, page size, compression)
- Section 16: HEADER INFO (header_page + header_event)
- Section 17: FTRACE EVENT FORMATS
- Section 18: EVENT FORMATS (per system/event format files)
- Section 19: KALLSYMS
- Section 21: CMDLINES
- Section 15: STRINGS (written last after all sections)

**Patch 3/4: Conversion Backend**
Implements util/data-convert-trace.c with trace_convert__perf2dat()
function:
- Processes PERF_TYPE_TRACEPOINT samples via process_sample_event()
- Collects raw event data per-CPU using trace_dat__collect_cpu_event()
- Writes OPTIONS sections (CPUCOUNT, TRACECLOCK, metadata offsets)
- Writes FLYRECORD section with per-CPU ring buffer pages

**Patch 4/4: User Interface**
Extends tools/perf/builtin-data.c with --to-trace-dat option:
- Adds command-line option for trace.dat output
- Mutually exclusive with --to-ctf and --to-json
- Calls trace_convert__perf2dat() to perform conversion

======================
Current Implementation Details
======================

**trace.dat Format Version:**
The implementation currently targets trace.dat format version 7, which
is the stable version supported by current trace-cmd releases (v3.x).
This version is hardcoded to ensure compatibility with existing
trace-cmd and KernelShark installations. Future enhancements could add
version negotiation or support for newer format versions as they become
standardized.

**Compression Strategy:**
Compression is explicitly disabled (set to NONE) in the generated
trace.dat files.
This design choice:
- Simplifies the initial implementation and testing
- Ensures maximum compatibility across trace-cmd versions
- Avoids external compression library dependencies

Future work could add support for various compression algorithms (zlib,
zstd, lz4) with runtime selection via command-line options, significantly
reducing file sizes for large traces.

======================
Usage Example
======================

```bash
*Record tracepoint events with perf*
perf record -e sched:sched_switch -e sched:sched_wakeup -a sleep 10

*Convert to trace.dat format*
perf data convert --to-trace-dat=output.dat

*Verify trace.dat structure*
trace-cmd dump --summary output.dat

*Analyze with trace-cmd*
trace-cmd report output.dat

*Visualize in KernelShark*
kernelshark output.dat
```

**Conversion Output:**
```
[ perf data convert: Converted 'perf.data' into trace.dat format
'output.dat' ]
[ perf data convert: Converted 2684 events ]
```
**trace-cmd dump --summary Output:**
```
 Tracing meta data in file output.dat:
	[Initial format]
		7	[Version]
		0	[Little endian]
		8	[Bytes in a long]
		65536	[Page size, bytes]
		none	[Compression algorithm]
			[Compression version]
	[buffer "", "local" clock, 65536 page size, 16 cpus, 1048576 bytes
    flyrecord data]
	[10 options]
	[Saved command lines, 0 bytes]
	[Kallsyms, 0 bytes]
	[Ftrace format, 0 events]
	[Header page, 206 bytes]
	[Header event, 205 bytes]
	[Events format, 1 systems]
	[9 sections]
```
======================
Testing and Verification
======================

The series has been extensively tested with:
- Various tracepoint events (sched, irq, syscalls, block I/O)
- Mixed recordings containing both tracepoint and non-tracepoint events
  only tracepoints converted)
- Verification with trace-cmd report and KernelShark visualization
- Memory leak testing with Valgrind (0 bytes leaked)
- Cross-architecture testing (x86_64, ppc64le)

All generated trace.dat files successfully open in:
- trace-cmd report (v3.1+)
- KernelShark (v2.0+)

======================
Next Steps
======================

We would highly appreciate reviews, comments, and feedback on:
- The overall architectural approach and integration points
- Compatibility considerations with trace-cmd ecosystem
- Performance characteristics for large-scale traces
- Additional use cases or workflow scenarios
- Future enhancement priorities

Tanushree Shah (4):
  perf/trace-dat: Add trace.dat export infrastructure
  perf/trace-event: Write trace.dat metadata sections during parsing
  perf data-convert: Add perf.data to trace.dat conversion backend
  perf data: Add --to-trace-dat option for converting perf.data
    tracepoint events into trace.dat format

 tools/perf/builtin-data.c            |  38 +-
 tools/perf/util/Build                |   2 +
 tools/perf/util/data-convert-trace.c | 152 ++++++
 tools/perf/util/data-convert.h       |   4 +
 tools/perf/util/trace-dat.c          | 705 +++++++++++++++++++++++++++
 tools/perf/util/trace-dat.h          |  79 +++
 tools/perf/util/trace-event-read.c   | 259 +++++++++-
 7 files changed, 1230 insertions(+), 9 deletions(-)
 create mode 100644 tools/perf/util/data-convert-trace.c
 create mode 100644 tools/perf/util/trace-dat.c
 create mode 100644 tools/perf/util/trace-dat.h

-- 
2.53.0


^ permalink raw reply	[flat|nested] 10+ messages in thread

end of thread, other threads:[~2026-06-08 15:18 UTC | newest]

Thread overview: 10+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-06-08 12:59 [RFC PATCH 0/4] perf: Add perf.data tracepoint events to trace.dat conversion Tanushree Shah
2026-06-08 12:59 ` [RFC PATCH 1/4] perf/trace-dat: Add trace.dat export infrastructure Tanushree Shah
2026-06-08 13:13   ` sashiko-bot
2026-06-08 12:59 ` [RFC PATCH 2/4] perf/trace-event: Write trace.dat metadata sections during parsing Tanushree Shah
2026-06-08 13:12   ` sashiko-bot
2026-06-08 12:59 ` [RFC PATCH 3/4] perf data-convert: Add perf.data to trace.dat conversion backend Tanushree Shah
2026-06-08 13:14   ` sashiko-bot
2026-06-08 12:59 ` [RFC PATCH 4/4] perf data: Add --to-trace-dat option for converting perf.data tracepoint events into trace.dat format Tanushree Shah
2026-06-08 13:12   ` sashiko-bot
2026-06-08 15:18 ` [RFC PATCH 0/4] perf: Add perf.data tracepoint events to trace.dat conversion Ian Rogers

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox