Implemented PERF_RECORD_COMPRESSED event, related data types, header feature and functions to write, read and print feature attributes from the trace header section.
comp_mmap_len preserves the size of mmaped kernel buffer that was used during collection. comp_mmap_len size is used on loading stage as the size of decomp buffer for decompression of COMPRESSED events content. Signed-off-by: Alexey Budankov <alexey.budan...@linux.intel.com> --- tools/perf/builtin-record.c | 9 ++++++ tools/perf/perf.h | 1 + tools/perf/util/env.h | 10 +++++++ tools/perf/util/event.c | 1 + tools/perf/util/event.h | 7 +++++ tools/perf/util/header.c | 55 ++++++++++++++++++++++++++++++++++++- tools/perf/util/header.h | 1 + 7 files changed, 83 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 299f484f3e30..61017fa0ee1c 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -357,6 +357,11 @@ static int record__mmap_flush_parse(const struct option *opt, return 0; } +static int record__comp_enabled(struct record *rec) +{ + return rec->opts.comp_level > 0; +} + static int process_synthesized_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -873,6 +878,9 @@ static void record__init_features(struct record *rec) if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns)) perf_header__clear_feat(&session->header, HEADER_CLOCKID); + if (!record__comp_enabled(rec)) + perf_header__clear_feat(&session->header, HEADER_COMPRESSED); + perf_header__clear_feat(&session->header, HEADER_STAT); } @@ -1211,6 +1219,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) err = -1; goto out_child; } + session->header.env.comp_mmap_len = session->evlist->mmap_len; err = bpf__apply_obj_config(); if (err) { diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 7886cc9771cf..2c6caad45b10 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -86,6 +86,7 @@ struct record_opts { int nr_cblocks; int affinity; int mmap_flush; + unsigned int comp_level; }; enum perf_affinity { diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index fb39e9af128f..7990d63ab764 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -65,6 +65,16 @@ struct perf_env { unsigned long long memory_bsize; u64 clockid_res_ns; u32 comp_ratio; + u32 comp_ver; + u32 comp_type; + u32 comp_level; + u32 comp_mmap_len; +}; + +enum perf_compress_type { + PERF_COMP_NONE = 0, + PERF_COMP_ZSTD, + PERF_COMP_MAX }; extern struct perf_env perf_env; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index ba7be74fad6e..d1ad6c419724 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -68,6 +68,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_EVENT_UPDATE] = "EVENT_UPDATE", [PERF_RECORD_TIME_CONV] = "TIME_CONV", [PERF_RECORD_HEADER_FEATURE] = "FEATURE", + [PERF_RECORD_COMPRESSED] = "COMPRESSED", }; static const char *perf_ns__names[] = { diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 36ae7e92dab1..8a13aefe734e 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -254,6 +254,7 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_EVENT_UPDATE = 78, PERF_RECORD_TIME_CONV = 79, PERF_RECORD_HEADER_FEATURE = 80, + PERF_RECORD_COMPRESSED = 81, PERF_RECORD_HEADER_MAX }; @@ -626,6 +627,11 @@ struct feature_event { char data[]; }; +struct compressed_event { + struct perf_event_header header; + char data[]; +}; + union perf_event { struct perf_event_header header; struct mmap_event mmap; @@ -659,6 +665,7 @@ union perf_event { struct feature_event feat; struct ksymbol_event ksymbol_event; struct bpf_event bpf_event; + struct compressed_event pack; }; void perf_event__print_totals(void); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index a2323d777dae..011b464fdad7 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1250,6 +1250,30 @@ static int write_mem_topology(struct feat_fd *ff __maybe_unused, return ret; } +static int write_compressed(struct feat_fd *ff __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + int ret; + + ret = do_write(ff, &(ff->ph->env.comp_ver), sizeof(ff->ph->env.comp_ver)); + if (ret) + return ret; + + ret = do_write(ff, &(ff->ph->env.comp_type), sizeof(ff->ph->env.comp_type)); + if (ret) + return ret; + + ret = do_write(ff, &(ff->ph->env.comp_level), sizeof(ff->ph->env.comp_level)); + if (ret) + return ret; + + ret = do_write(ff, &(ff->ph->env.comp_ratio), sizeof(ff->ph->env.comp_ratio)); + if (ret) + return ret; + + return do_write(ff, &(ff->ph->env.comp_mmap_len), sizeof(ff->ph->env.comp_mmap_len)); +} + static void print_hostname(struct feat_fd *ff, FILE *fp) { fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname); @@ -1537,6 +1561,13 @@ static void print_cache(struct feat_fd *ff, FILE *fp __maybe_unused) } } +static void print_compressed(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# compressed : %s, level = %d, ratio = %d\n", + ff->ph->env.comp_type == PERF_COMP_ZSTD ? "Zstd" : "Unknown", + ff->ph->env.comp_level, ff->ph->env.comp_ratio); +} + static void print_pmu_mappings(struct feat_fd *ff, FILE *fp) { const char *delimiter = "# pmu mappings: "; @@ -2379,6 +2410,27 @@ static int process_clockid(struct feat_fd *ff, return 0; } +static int process_compressed(struct feat_fd *ff, + void *data __maybe_unused) +{ + if (do_read_u32(ff, &(ff->ph->env.comp_ver))) + return -1; + + if (do_read_u32(ff, &(ff->ph->env.comp_type))) + return -1; + + if (do_read_u32(ff, &(ff->ph->env.comp_level))) + return -1; + + if (do_read_u32(ff, &(ff->ph->env.comp_ratio))) + return -1; + + if (do_read_u32(ff, &(ff->ph->env.comp_mmap_len))) + return -1; + + return 0; +} + struct feature_ops { int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); void (*print)(struct feat_fd *ff, FILE *fp); @@ -2438,7 +2490,8 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPN(CACHE, cache, true), FEAT_OPR(SAMPLE_TIME, sample_time, false), FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), - FEAT_OPR(CLOCKID, clockid, false) + FEAT_OPR(CLOCKID, clockid, false), + FEAT_OPR(COMPRESSED, compressed, false) }; struct header_print_data { diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 0d553ddca0a3..ee867075dc64 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -39,6 +39,7 @@ enum { HEADER_SAMPLE_TIME, HEADER_MEM_TOPOLOGY, HEADER_CLOCKID, + HEADER_COMPRESSED, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, };