| commit | 6b8c49e8cacc4bef89ad65e52caf95503255ef17 | [log] [tgz] |
|---|---|---|
| author | Luke Chang <lukechang@google.com> | Fri Feb 11 00:42:19 2022 +0800 |
| committer | Luke Chang <lukechang@google.com> | Mon Feb 14 11:03:55 2022 +0800 |
| tree | 75d2046c1bd9430beaf11b8d7ed4974477eb8379 | |
| parent | c8de97bd2b42cd479bed29590bb5dcc8207808a3 [diff] |
trace_processor: support napi_gro_receive_entry and
napi_gro_receive_exit events
GRO aggregates packets at early stage of packet receiving path that reduce
kernel protocol stack loading. This patch use the napi_gro_receive_entry
and napi_gro_receive_exit ftrace to generate slices and make it clear to
know when packets are received from NIC to kernel and help to genreate
GRO related metrics.
Bug: 218870509
Test: ui/run-dev-server & manaul check the UI behavior
Test: tools/diff_test_trace_processor.py <trace_processor_shell> \
--query-metric-filter='napi_gro_receive'
Change-Id: I185bd5aa60441a60bb01d976b991a0f7e122ed15
Perfetto is a production-grade open-source stack for performance instrumentation and trace analysis. It offers services and libraries and for recording system-level and app-level traces, native + java heap profiling, a library for analyzing traces using SQL and a web-based UI to visualize and explore multi-GB traces.
See https://perfetto.dev/docs or the /docs/ directory for documentation.