From nobody Mon Dec 15 22:08:16 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 0D8A020F999; Tue, 14 Jan 2025 21:22:58 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1736889779; cv=none; b=ewqwC/i5c4DvnQdFjygnuICEcG0DbvG6FfdL8yy6jlgqEAUvUWXT1LkhQ2Mgko772vlXVPqBSiyQIRl88jwkLoWZKOe1AUQ4OSoRBvkrul3kWnsZMVO7j2BfFH1jiFC9vEW5fpKVJP14HzINY7JdeHZJyAufKfC5lo21fX/z9p4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1736889779; c=relaxed/simple; bh=NxSCJ2syR3YYbNJ3uryk3tsjg2K+IpnX1WSFOL5GHws=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=evIgiUy4x4IJG9v3pVT9kQDMoY/QLlTnzJyXojslA0uJtpMcybVZAo4Uj3pwul5i06ikT/7UwYthEYDfQeIhwtjjJDa5OPbDNAfQS6mklrPZDcCKQU65MHSga8MHcZRWYVDOkh7DfI2rCk+LzGMghUFZQSuHIuWIQXkfPGm2lD8= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=CG3y5Zcx; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="CG3y5Zcx" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 3C30CC4CEE5; Tue, 14 Jan 2025 21:22:58 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1736889778; bh=NxSCJ2syR3YYbNJ3uryk3tsjg2K+IpnX1WSFOL5GHws=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=CG3y5ZcxG9BSLqun5CgVmuEpdF7+XsGqtk90xQWfaoCTbB+dCo0ih7GWXroHd/mJE JdayuVNXjuIoxoVi6+J2YVlyflAuOlxqozqn31N8xmZOmvcqe06rwLCX2UNXy8cZ7w oZaKlObMWZ8xRSDQfXEkMB0Q4hasAbhuGAY89oyHsIlvDNOkKh14FUga036kh+SaSD FTJh13wWIYWgMiMnK/WO2KvGBzr+5cOoDsSXMuIxrbuVH4b3tiSe2sFxnyLcheyXZL 7zC042A3asN9xrnfw/OCeOxx8bhHdQKyge5RvNvFGzmSpjjADMzoGLQ+klbMY0jnUH 5CldJpnTNDt8w== From: Namhyung Kim To: Arnaldo Carvalho de Melo , Ian Rogers , Kan Liang Cc: Jiri Olsa , Adrian Hunter , Peter Zijlstra , Ingo Molnar , LKML , linux-perf-users@vger.kernel.org, Howard Chu Subject: [PATCH 1/4] perf trace: Allocate syscall stats only if summary is on Date: Tue, 14 Jan 2025 13:22:53 -0800 Message-ID: <20250114212256.160730-2-namhyung@kernel.org> X-Mailer: git-send-email 2.48.0.rc2.279.g1de40edade-goog In-Reply-To: <20250114212256.160730-1-namhyung@kernel.org> References: <20250114212256.160730-1-namhyung@kernel.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" The syscall stats are used only when summary is requested. Let's avoid unnecessary operations. Pass 'trace' pointer to check summary and give output file together. Signed-off-by: Namhyung Kim --- tools/perf/builtin-trace.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 40dd2dd1320d37a9..0691e817c15b4136 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1523,13 +1523,14 @@ struct thread_trace { struct intlist *syscall_stats; }; =20 -static struct thread_trace *thread_trace__new(void) +static struct thread_trace *thread_trace__new(struct trace *trace) { struct thread_trace *ttrace =3D zalloc(sizeof(struct thread_trace)); =20 if (ttrace) { ttrace->files.max =3D -1; - ttrace->syscall_stats =3D intlist__new(NULL); + if (trace->summary) + ttrace->syscall_stats =3D intlist__new(NULL); } =20 return ttrace; @@ -1551,7 +1552,7 @@ static void thread_trace__delete(void *pttrace) free(ttrace); } =20 -static struct thread_trace *thread__trace(struct thread *thread, FILE *fp) +static struct thread_trace *thread__trace(struct thread *thread, struct tr= ace *trace) { struct thread_trace *ttrace; =20 @@ -1559,7 +1560,7 @@ static struct thread_trace *thread__trace(struct thre= ad *thread, FILE *fp) goto fail; =20 if (thread__priv(thread) =3D=3D NULL) - thread__set_priv(thread, thread_trace__new()); + thread__set_priv(thread, thread_trace__new(trace)); =20 if (thread__priv(thread) =3D=3D NULL) goto fail; @@ -1569,7 +1570,7 @@ static struct thread_trace *thread__trace(struct thre= ad *thread, FILE *fp) =20 return ttrace; fail: - color_fprintf(fp, PERF_COLOR_RED, + color_fprintf(trace->output, PERF_COLOR_RED, "WARNING: not enough memory, dropping samples!\n"); return NULL; } @@ -2623,7 +2624,7 @@ static int trace__sys_enter(struct trace *trace, stru= ct evsel *evsel, return -1; =20 thread =3D machine__findnew_thread(trace->host, sample->pid, sample->tid); - ttrace =3D thread__trace(thread, trace->output); + ttrace =3D thread__trace(thread, trace); if (ttrace =3D=3D NULL) goto out_put; =20 @@ -2700,7 +2701,7 @@ static int trace__fprintf_sys_enter(struct trace *tra= ce, struct evsel *evsel, return -1; =20 thread =3D machine__findnew_thread(trace->host, sample->pid, sample->tid); - ttrace =3D thread__trace(thread, trace->output); + ttrace =3D thread__trace(thread, trace); /* * We need to get ttrace just to make sure it is there when syscall__scnp= rintf_args() * and the rest of the beautifiers accessing it via struct syscall_arg to= uches it. @@ -2772,7 +2773,7 @@ static int trace__sys_exit(struct trace *trace, struc= t evsel *evsel, return -1; =20 thread =3D machine__findnew_thread(trace->host, sample->pid, sample->tid); - ttrace =3D thread__trace(thread, trace->output); + ttrace =3D thread__trace(thread, trace); if (ttrace =3D=3D NULL) goto out_put; =20 @@ -2961,7 +2962,7 @@ static int trace__sched_stat_runtime(struct trace *tr= ace, struct evsel *evsel, struct thread *thread =3D machine__findnew_thread(trace->host, sample->pid, sample->tid); - struct thread_trace *ttrace =3D thread__trace(thread, trace->output); + struct thread_trace *ttrace =3D thread__trace(thread, trace); =20 if (ttrace =3D=3D NULL) goto out_dump; @@ -3215,7 +3216,7 @@ static int trace__pgfault(struct trace *trace, } } =20 - ttrace =3D thread__trace(thread, trace->output); + ttrace =3D thread__trace(thread, trace); if (ttrace =3D=3D NULL) goto out_put; =20 --=20 2.48.0.rc2.279.g1de40edade-goog From nobody Mon Dec 15 22:08:16 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 6CEAA211488; Tue, 14 Jan 2025 21:22:59 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1736889779; cv=none; b=HwOH+XY9bRFt9mN6FzztAIzHd1ucQWIBGjpZZMHz5SD0OF+18OnkkcZ6Jg7PvnC3sf3YivA1+Gb5Z8UCtfhFbUD3SzJ5LUQvs0K520FWZ7ayAAaZ1DXWFePlrHHUaQ6owe9DQRD7gf5sUMPfT9csXCzzyAAqcoJeNl1NhIzxwqo= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1736889779; c=relaxed/simple; bh=WgvjHs7NLmVM3gvH/RBtwDrLLCqYxYPoraCQmLF9lZk=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=V9G4t/XW/sDb/qoKkdjRZmdts62wrUQxZzq7+MsxFV2PIXQtgF4QrBQ0LG6dMKbPdDmRbNVfJJ+wUC3esumdi5GsO1lfcQHVOo9lpV31KaEaZu79cocaNCRoNDhwKRse+AEjSWcuJYFjIDZbA2ttE3UhCdEjtaLvTvMdtsf/ApQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=dLdZ727s; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="dLdZ727s" Received: by smtp.kernel.org (Postfix) with ESMTPSA id AEDC9C4CEE0; Tue, 14 Jan 2025 21:22:58 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1736889779; bh=WgvjHs7NLmVM3gvH/RBtwDrLLCqYxYPoraCQmLF9lZk=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=dLdZ727sGEovAM/zyhfrfqr9KciQZjXbZiaP0W+l8BCOVISe0b7tx7LHpYXApTlBP 8rF+0WNp/d4meh7TWwd+NeT1efm1aG+kfOA/tzWONSlfXm0fV9Fzka9TOubxHpam1L zIthnGq19EVt7Tb/UCSAUilpQ8krrRwDvXBp6iFW0rQpKYeViZxEjq9wCTmGNUNv3S S/i7n8SktutMwoNT0yumGMQjBtIYdTzTRWmz+83AuJd2ucUunQs3XzoCtflaJFahDE DQFJcsl7IqgIIQd2t7mJUogWmmacdJaaQYVZra7R8E3SZSOslbad/ywJHBtCXUmFYg jfgy3HxN8HlSw== From: Namhyung Kim To: Arnaldo Carvalho de Melo , Ian Rogers , Kan Liang Cc: Jiri Olsa , Adrian Hunter , Peter Zijlstra , Ingo Molnar , LKML , linux-perf-users@vger.kernel.org, Howard Chu Subject: [PATCH 2/4] perf trace: Convert syscall_stats to hashmap Date: Tue, 14 Jan 2025 13:22:54 -0800 Message-ID: <20250114212256.160730-3-namhyung@kernel.org> X-Mailer: git-send-email 2.48.0.rc2.279.g1de40edade-goog In-Reply-To: <20250114212256.160730-1-namhyung@kernel.org> References: <20250114212256.160730-1-namhyung@kernel.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" It was using a RBtree-based int-list as a hash and a custome resort logic for that. As we have hashmap, let's convert to it and add a sorting function using an array. It's also to prepare supporting system-wide syscall stats. No functional changes intended. Signed-off-by: Namhyung Kim --- tools/perf/builtin-trace.c | 121 ++++++++++++++++++++++++++++--------- 1 file changed, 92 insertions(+), 29 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 0691e817c15b4136..ad7f7fcd0d80b9df 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -39,6 +39,7 @@ #include "util/synthetic-events.h" #include "util/evlist.h" #include "util/evswitch.h" +#include "util/hashmap.h" #include "util/mmap.h" #include #include @@ -63,7 +64,6 @@ #include "print_binary.h" #include "string2.h" #include "syscalltbl.h" -#include "rb_resort.h" #include "../perf.h" #include "trace_augment.h" =20 @@ -1520,17 +1520,55 @@ struct thread_trace { struct file *table; } files; =20 - struct intlist *syscall_stats; + struct hashmap *syscall_stats; }; =20 +static size_t id_hash(long key, void *ctx __maybe_unused) +{ + return key; +} + +static bool id_equal(long key1, long key2, void *ctx __maybe_unused) +{ + return key1 =3D=3D key2; +} + +static struct hashmap *alloc_syscall_stats(void) +{ + struct hashmap *stats =3D hashmap__new(id_hash, id_equal, NULL); + + /* just for simpler error check */ + if (IS_ERR_OR_NULL(stats)) + stats =3D NULL; + return stats; +} + +static void delete_syscall_stats(struct hashmap *syscall_stats) +{ + struct hashmap_entry *pos; + size_t bkt; + + if (syscall_stats =3D=3D NULL) + return; + + hashmap__for_each_entry(syscall_stats, pos, bkt) + free(pos->pvalue); + hashmap__free(syscall_stats); +} + static struct thread_trace *thread_trace__new(struct trace *trace) { struct thread_trace *ttrace =3D zalloc(sizeof(struct thread_trace)); =20 if (ttrace) { ttrace->files.max =3D -1; - if (trace->summary) - ttrace->syscall_stats =3D intlist__new(NULL); + if (trace->summary) { + ttrace->syscall_stats =3D alloc_syscall_stats(); + if (ttrace->syscall_stats =3D=3D NULL) { + free(ttrace); + ttrace =3D NULL; + } + } } =20 return ttrace; @@ -1545,7 +1583,7 @@ static void thread_trace__delete(void *pttrace) if (!ttrace) return; =20 - intlist__delete(ttrace->syscall_stats); + delete_syscall_stats(ttrace->syscall_stats); ttrace->syscall_stats =3D NULL; thread_trace__free_files(ttrace); zfree(&ttrace->entry_str); @@ -2464,22 +2502,19 @@ struct syscall_stats { static void thread__update_stats(struct thread *thread, struct thread_trac= e *ttrace, int id, struct perf_sample *sample, long err, bool errno_summary) { - struct int_node *inode; - struct syscall_stats *stats; + struct syscall_stats *stats =3D NULL; u64 duration =3D 0; =20 - inode =3D intlist__findnew(ttrace->syscall_stats, id); - if (inode =3D=3D NULL) - return; - - stats =3D inode->priv; - if (stats =3D=3D NULL) { + if (!hashmap__find(ttrace->syscall_stats, id, &stats)) { stats =3D zalloc(sizeof(*stats)); if (stats =3D=3D NULL) return; =20 init_stats(&stats->stats); - inode->priv =3D stats; + if (hashmap__add(ttrace->syscall_stats, id, stats) < 0) { + free(stats); + return; + } } =20 if (ttrace->entry_time && sample->time > ttrace->entry_time) @@ -4618,18 +4653,45 @@ static size_t trace__fprintf_threads_header(FILE *f= p) return printed; } =20 -DEFINE_RESORT_RB(syscall_stats, a->msecs > b->msecs, +struct syscall_entry { struct syscall_stats *stats; double msecs; int syscall; -) +}; + +static int entry_cmp(const void *e1, const void *e2) +{ + const struct syscall_entry *entry1 =3D e1; + const struct syscall_entry *entry2 =3D e2; + + return entry1->msecs > entry2->msecs ? -1 : 1; +} + +static struct syscall_entry *thread__sort_stats(struct thread_trace *ttrac= e) { - struct int_node *source =3D rb_entry(nd, struct int_node, rb_node); - struct syscall_stats *stats =3D source->priv; + struct syscall_entry *entry; + struct hashmap_entry *pos; + unsigned bkt, i, nr; + + nr =3D ttrace->syscall_stats->sz; + entry =3D malloc(nr * sizeof(*entry)); + if (entry =3D=3D NULL) + return NULL; =20 - entry->syscall =3D source->i; - entry->stats =3D stats; - entry->msecs =3D stats ? (u64)stats->stats.n * (avg_stats(&stats->stats= ) / NSEC_PER_MSEC) : 0; + i =3D 0; + hashmap__for_each_entry(ttrace->syscall_stats, pos, bkt) { + struct syscall_stats *ss =3D pos->pvalue; + struct stats *st =3D &ss->stats; + + entry[i].stats =3D ss; + entry[i].msecs =3D (u64)st->n * (avg_stats(st) / NSEC_PER_MSEC); + entry[i].syscall =3D pos->key; + i++; + } + assert(i =3D=3D nr); + + qsort(entry, nr, sizeof(*entry), entry_cmp); + return entry; } =20 static size_t thread__dump_stats(struct thread_trace *ttrace, @@ -4637,10 +4699,10 @@ static size_t thread__dump_stats(struct thread_trac= e *ttrace, { size_t printed =3D 0; struct syscall *sc; - struct rb_node *nd; - DECLARE_RESORT_RB_INTLIST(syscall_stats, ttrace->syscall_stats); + struct syscall_entry *entries; =20 - if (syscall_stats =3D=3D NULL) + entries =3D thread__sort_stats(ttrace); + if (entries =3D=3D NULL) return 0; =20 printed +=3D fprintf(fp, "\n"); @@ -4649,8 +4711,9 @@ static size_t thread__dump_stats(struct thread_trace = *ttrace, printed +=3D fprintf(fp, " (msec) = (msec) (msec) (msec) (%%)\n"); printed +=3D fprintf(fp, " --------------- -------- ------ -------- --= ------- --------- --------- ------\n"); =20 - resort_rb__for_each_entry(nd, syscall_stats) { - struct syscall_stats *stats =3D syscall_stats_entry->stats; + for (size_t i =3D 0; i < ttrace->syscall_stats->sz; i++) { + struct syscall_entry *entry =3D &entries[i]; + struct syscall_stats *stats =3D entry->stats; if (stats) { double min =3D (double)(stats->stats.min) / NSEC_PER_MSEC; double max =3D (double)(stats->stats.max) / NSEC_PER_MSEC; @@ -4661,10 +4724,10 @@ static size_t thread__dump_stats(struct thread_trac= e *ttrace, pct =3D avg ? 100.0 * stddev_stats(&stats->stats) / avg : 0.0; avg /=3D NSEC_PER_MSEC; =20 - sc =3D &trace->syscalls.table[syscall_stats_entry->syscall]; + sc =3D &trace->syscalls.table[entry->syscall]; printed +=3D fprintf(fp, " %-15s", sc->name); printed +=3D fprintf(fp, " %8" PRIu64 " %6" PRIu64 " %9.3f %9.3f %9.3f", - n, stats->nr_failures, syscall_stats_entry->msecs, min, avg); + n, stats->nr_failures, entry->msecs, min, avg); printed +=3D fprintf(fp, " %9.3f %9.2f%%\n", max, pct); =20 if (trace->errno_summary && stats->nr_failures) { @@ -4678,7 +4741,7 @@ static size_t thread__dump_stats(struct thread_trace = *ttrace, } } =20 - resort_rb__delete(syscall_stats); + free(entries); printed +=3D fprintf(fp, "\n\n"); =20 return printed; --=20 2.48.0.rc2.279.g1de40edade-goog From nobody Mon Dec 15 22:08:16 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EC1DC212D68; Tue, 14 Jan 2025 21:22:59 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1736889780; cv=none; b=j+THmlI9eFr89cPU0CW6vHElaGmPU5okkesHCVejk24ioaDE5TlM/HRbI2uP1lCa/nW1mqZJ9bQbTaoS3y84vhgPUkEkBVdzvtir1hN18KrB12J85b+5UfPo+b3nfP16Z5f0cAARAMA28dzo1BnWmXvgAtAxg6E97eZ3vnmuV1M= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1736889780; c=relaxed/simple; bh=nBmh0jHXDzsPATnybjr3Yztiyvze95lpiIP2lWDKf1k=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=NfzmR4ghTuZ0IzBAs1nn19nebtfyahCPibEba8BJ+ytWq9iXG35orWeSu4YpV7+bZ5YqPwi0rWDAEBhsR2wngD9BbMVuP1r7pgSxZvH5o8UBQDEjnG89LNm0xYJjQUhIPBYxMudGHQxJ+T04Qhj08e7NTI7dDIgN3IgHZe1pntE= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=nkPd4tJe; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="nkPd4tJe" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 2CE0AC4CEE6; Tue, 14 Jan 2025 21:22:59 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1736889779; bh=nBmh0jHXDzsPATnybjr3Yztiyvze95lpiIP2lWDKf1k=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=nkPd4tJedxYFBJDFRQCGtfqamxBk/UUblufJS5N7mZ85Pswro/CKnXhsFJSFHTpkl xSgHLywMSVaCI/y9PLPrukm8g5RvNFXJ9fE5zI+Q/x0W5FW/Eg5wIH7qrUZWROHOri dG7Se5WOGaYxvUQ7yptUtxx8wgQr6ZyNf4ny4pMRxK7aQp8XHR/SW9PD0UDsr3iGkT nsq5sn5K7sIrPxandaHGrGZx36JjJzLQgPz8ShF8dMpoR9CR5QREb8vHPbPLX0K4qd ZAj+K/M8v9uRDsH3siGHbTvf9Jp18jmdpN8Y0S+8JIi7fnVpHrILgZ2UpSt8awI5yE W1OzbjpPyACBA== From: Namhyung Kim To: Arnaldo Carvalho de Melo , Ian Rogers , Kan Liang Cc: Jiri Olsa , Adrian Hunter , Peter Zijlstra , Ingo Molnar , LKML , linux-perf-users@vger.kernel.org, Howard Chu Subject: [PATCH 3/4] perf tools: Get rid of now-unused rb_resort.h Date: Tue, 14 Jan 2025 13:22:55 -0800 Message-ID: <20250114212256.160730-4-namhyung@kernel.org> X-Mailer: git-send-email 2.48.0.rc2.279.g1de40edade-goog In-Reply-To: <20250114212256.160730-1-namhyung@kernel.org> References: <20250114212256.160730-1-namhyung@kernel.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" It was only used in perf trace and it switched to use hashmap instead. Let's delete the code. Signed-off-by: Namhyung Kim --- tools/perf/util/rb_resort.h | 146 ------------------------------------ 1 file changed, 146 deletions(-) delete mode 100644 tools/perf/util/rb_resort.h diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h deleted file mode 100644 index f4aaee33fe70dd81..0000000000000000 --- a/tools/perf/util/rb_resort.h +++ /dev/null @@ -1,146 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _PERF_RESORT_RB_H_ -#define _PERF_RESORT_RB_H_ -/* - * Template for creating a class to resort an existing rb_tree according to - * a new sort criteria, that must be present in the entries of the source - * rb_tree. - * - * (c) 2016 Arnaldo Carvalho de Melo - * - * Quick example, resorting threads by its shortname: - * - * First define the prefix (threads) to be used for the functions and data - * structures created, and provide an expression for the sorting, then the - * fields to be present in each of the entries in the new, sorted, rb_tree. - * - * The body of the init function should collect the fields, maybe - * pre-calculating them from multiple entries in the original 'entry' from - * the rb_tree used as a source for the entries to be sorted: - -DEFINE_RB_RESORT_RB(threads, strcmp(a->thread->shortname, - b->thread->shortname) < 0, - struct thread *thread; -) -{ - entry->thread =3D rb_entry(nd, struct thread, rb_node); -} - - * After this it is just a matter of instantiating it and iterating it, - * for a few data structures with existing rb_trees, such as 'struct machi= ne', - * helpers are available to get the rb_root and the nr_entries: - - DECLARE_RESORT_RB_MACHINE_THREADS(threads, machine_ptr); - - * This will instantiate the new rb_tree and a cursor for it, that can be = used as: - - struct rb_node *nd; - - resort_rb__for_each_entry(nd, threads) { - struct thread *t =3D threads_entry; - printf("%s: %d\n", t->shortname, t->tid); - } - - * Then delete it: - - resort_rb__delete(threads); - - * The name of the data structures and functions will have a _sorted suffix - * right before the method names, i.e. will look like: - * - * struct threads_sorted_entry {} - * threads_sorted__insert() - */ - -#define DEFINE_RESORT_RB(__name, __comp, ...) \ -struct __name##_sorted_entry { \ - struct rb_node rb_node; \ - __VA_ARGS__ \ -}; \ -static void __name##_sorted__init_entry(struct rb_node *nd, \ - struct __name##_sorted_entry *entry); \ - \ -static int __name##_sorted__cmp(struct rb_node *nda, struct rb_node *ndb) \ -{ \ - struct __name##_sorted_entry *a, *b; \ - a =3D rb_entry(nda, struct __name##_sorted_entry, rb_node); \ - b =3D rb_entry(ndb, struct __name##_sorted_entry, rb_node); \ - return __comp; \ -} \ - \ -struct __name##_sorted { \ - struct rb_root entries; \ - struct __name##_sorted_entry nd[0]; \ -}; \ - \ -static void __name##_sorted__insert(struct __name##_sorted *sorted, \ - struct rb_node *sorted_nd) \ -{ \ - struct rb_node **p =3D &sorted->entries.rb_node, *parent =3D NULL; \ - while (*p !=3D NULL) { \ - parent =3D *p; \ - if (__name##_sorted__cmp(sorted_nd, parent)) \ - p =3D &(*p)->rb_left; \ - else \ - p =3D &(*p)->rb_right; \ - } \ - rb_link_node(sorted_nd, parent, p); \ - rb_insert_color(sorted_nd, &sorted->entries); \ -} \ - \ -static void __name##_sorted__sort(struct __name##_sorted *sorted, \ - struct rb_root *entries) \ -{ \ - struct rb_node *nd; \ - unsigned int i =3D 0; \ - for (nd =3D rb_first(entries); nd; nd =3D rb_next(nd)) { \ - struct __name##_sorted_entry *snd =3D &sorted->nd[i++]; \ - __name##_sorted__init_entry(nd, snd); \ - __name##_sorted__insert(sorted, &snd->rb_node); \ - } \ -} \ - \ -static struct __name##_sorted *__name##_sorted__new(struct rb_root *entrie= s, \ - int nr_entries) \ -{ \ - struct __name##_sorted *sorted; \ - sorted =3D malloc(sizeof(*sorted) + sizeof(sorted->nd[0]) * nr_entries); \ - if (sorted) { \ - sorted->entries =3D RB_ROOT; \ - __name##_sorted__sort(sorted, entries); \ - } \ - return sorted; \ -} \ - \ -static void __name##_sorted__delete(struct __name##_sorted *sorted) \ -{ \ - free(sorted); \ -} \ - \ -static void __name##_sorted__init_entry(struct rb_node *nd, \ - struct __name##_sorted_entry *entry) - -#define DECLARE_RESORT_RB(__name) \ -struct __name##_sorted_entry *__name##_entry; \ -struct __name##_sorted *__name =3D __name##_sorted__new - -#define resort_rb__for_each_entry(__nd, __name) \ - for (__nd =3D rb_first(&__name->entries); \ - __nd && (__name##_entry =3D rb_entry(__nd, struct __name##_sorted_en= try, \ - rb_node)); \ - __nd =3D rb_next(__nd)) - -#define resort_rb__delete(__name) \ - __name##_sorted__delete(__name), __name =3D NULL - -/* - * Helpers for other classes that contains both an rbtree and the - * number of entries in it: - */ - -/* For 'struct intlist' */ -#define DECLARE_RESORT_RB_INTLIST(__name, __ilist) \ - DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries.rb_root, \ - __ilist->rblist.nr_entries) - -#endif /* _PERF_RESORT_RB_H_ */ --=20 2.48.0.rc2.279.g1de40edade-goog From nobody Mon Dec 15 22:08:16 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 2508A212D94; Tue, 14 Jan 2025 21:23:00 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1736889780; cv=none; b=MfLsT1gB2COIF5aF0GZeQs6g6Jt9CHQBx4RLLxFYVYnQryTwO4rRuXIJkR66w2FycdAfRfkoSS0g+nEiRkqGEkQZKJvVYgnoIWoRcFT1PAUF55yKMExDLfOh8fpT9vT+7YmFNhYk3HxQ0MSqxKCiJuTIRGv7r6eezjTX1aAnUeg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1736889780; c=relaxed/simple; bh=RfBaj4PbSnE3Ns3yNkpZJWdF4poiD2WjKo9y2CbPgkY=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=g7bqKgi9ea2nkgOBSnSLwGwvY80zuqt/SymU0uy5+dmorxZB/X6u1yZeGn3DD4TB3nmZD5b7Hz8mRV5OCh9z2WSHMUb4NJz/oHP0jtTZ5yuJLocZ+FH4RHVXmiTewaPC9sk7yQgfbVeItD4QcTV3Uvda6MXFeL8gCAL1pCm4bVE= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=aeUhnXaZ; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="aeUhnXaZ" Received: by smtp.kernel.org (Postfix) with ESMTPSA id A43DDC4CEE4; Tue, 14 Jan 2025 21:22:59 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1736889780; bh=RfBaj4PbSnE3Ns3yNkpZJWdF4poiD2WjKo9y2CbPgkY=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=aeUhnXaZYdONGwyBxrEeWyiQsH3+NVf7W/kfnsCLRl6GZFosGvkcVA1FxfJHpOz0r sLp8uxRBVAKe4S9V4fABAoGS2oPZIOBBULO+V0Q7OAWtROBGAtIakf9oaTwXuNl9Q2 f1v/ZQeK3lVUkk2OFgH+WkjWITzpR6rtJ8UJaJEwlHz3iXfE2cHVQJF2ls9g9jhJMm 5nC4xdWvtn5VPk3Gc4GBcXEUptfW9Nx5Y/t2O71+ISemIBvFUoQL9YqABgGJS4KLvN ipVOOEN7R02lDsINJ55/7dJ43VUsQTQS+RIbSK/aBYexCf4UMG53lL8WEfRHda9cjl uyA1wLlbbfRqQ== From: Namhyung Kim To: Arnaldo Carvalho de Melo , Ian Rogers , Kan Liang Cc: Jiri Olsa , Adrian Hunter , Peter Zijlstra , Ingo Molnar , LKML , linux-perf-users@vger.kernel.org, Howard Chu Subject: [PATCH 4/4] perf trace: Add --system-summary option Date: Tue, 14 Jan 2025 13:22:56 -0800 Message-ID: <20250114212256.160730-5-namhyung@kernel.org> X-Mailer: git-send-email 2.48.0.rc2.279.g1de40edade-goog In-Reply-To: <20250114212256.160730-1-namhyung@kernel.org> References: <20250114212256.160730-1-namhyung@kernel.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" $ sudo ./perf trace -as --system-summary sleep 1 Summary of events: total, 21580 events syscall calls errors total min avg max = stddev (msec) (msec) (msec) (msec)= (%) --------------- -------- ------ -------- --------- --------- --------= - ------ epoll_wait 1305 0 14716.712 0.000 11.277 551.52= 9 8.87% futex 1256 89 13331.197 0.000 10.614 733.72= 2 15.49% poll 669 0 6806.618 0.000 10.174 459.31= 6 11.77% ppoll 220 0 3968.797 0.000 18.040 516.77= 5 25.35% clock_nanosleep 1 0 1000.027 1000.027 1000.027 1000.02= 7 0.00% epoll_pwait 21 0 592.783 0.000 28.228 522.29= 3 88.29% nanosleep 16 0 60.515 0.000 3.782 10.12= 3 33.33% ioctl 510 0 4.284 0.001 0.008 0.18= 2 8.84% recvmsg 1434 775 3.497 0.001 0.002 0.17= 4 6.37% write 1393 0 2.854 0.001 0.002 0.01= 7 1.79% read 1063 100 2.236 0.000 0.002 0.08= 3 5.11% ... Signed-off-by: Namhyung Kim --- tools/perf/Documentation/perf-trace.txt | 3 + tools/perf/builtin-trace.c | 100 +++++++++++++++++++----- 2 files changed, 85 insertions(+), 18 deletions(-) diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documenta= tion/perf-trace.txt index 2620c4f4601c8701..72f29f82649e320a 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -150,6 +150,9 @@ the thread executes on the designated CPUs. Default is = to monitor all CPUs. To be used with -s or -S, to show stats for the errnos experienced by syscalls, using only this option will trigger --summary. =20 +--system-summary:: + To be used with -s or -S, to show system-wide summary instead of per-thre= ad. + --tool_stats:: Show tool stats such as number of times fd->pathname was discovered thru hooking the open syscall return + vfs_getname or via reading /proc/pid/fd= , etc. diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index ad7f7fcd0d80b9df..00a20052f676847c 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -177,8 +177,10 @@ struct trace { pid_t *entries; struct bpf_map *map; } filter_pids; + struct hashmap *syscall_stats; double duration_filter; double runtime_ms; + unsigned long pfmaj, pfmin; struct { u64 vfs_getname, proc_getname; @@ -198,6 +200,7 @@ struct trace { bool summary; bool summary_only; bool errno_summary; + bool system_summary; bool failure_only; bool show_comm; bool print_sample; @@ -2500,18 +2503,23 @@ struct syscall_stats { }; =20 static void thread__update_stats(struct thread *thread, struct thread_trac= e *ttrace, - int id, struct perf_sample *sample, long err, bool errno_summary) + int id, struct perf_sample *sample, long err, + struct trace *trace) { + struct hashmap *syscall_stats =3D ttrace->syscall_stats; struct syscall_stats *stats =3D NULL; u64 duration =3D 0; =20 - if (!hashmap__find(ttrace->syscall_stats, id, &stats)) { + if (trace->system_summary) + syscall_stats =3D trace->syscall_stats; + + if (!hashmap__find(syscall_stats, id, &stats)) { stats =3D zalloc(sizeof(*stats)); if (stats =3D=3D NULL) return; =20 init_stats(&stats->stats); - if (hashmap__add(ttrace->syscall_stats, id, stats) < 0) { + if (hashmap__add(syscall_stats, id, stats) < 0) { free(stats); return; } @@ -2525,7 +2533,7 @@ static void thread__update_stats(struct thread *threa= d, struct thread_trace *ttr if (err < 0) { ++stats->nr_failures; =20 - if (!errno_summary) + if (!trace->errno_summary) return; =20 err =3D -err; @@ -2817,7 +2825,7 @@ static int trace__sys_exit(struct trace *trace, struc= t evsel *evsel, ret =3D perf_evsel__sc_tp_uint(evsel, ret, sample); =20 if (trace->summary) - thread__update_stats(thread, ttrace, id, sample, ret, trace->errno_summa= ry); + thread__update_stats(thread, ttrace, id, sample, ret, trace); =20 if (!trace->fd_path_disabled && sc->is_open && ret >=3D 0 && ttrace->file= name.pending_open) { trace__set_fd_pathname(thread, ret, ttrace->filename.name); @@ -3255,10 +3263,13 @@ static int trace__pgfault(struct trace *trace, if (ttrace =3D=3D NULL) goto out_put; =20 - if (evsel->core.attr.config =3D=3D PERF_COUNT_SW_PAGE_FAULTS_MAJ) + if (evsel->core.attr.config =3D=3D PERF_COUNT_SW_PAGE_FAULTS_MAJ) { ttrace->pfmaj++; - else + trace->pfmaj++; + } else { ttrace->pfmin++; + trace->pfmin++; + } =20 if (trace->summary_only) goto out; @@ -3417,6 +3428,7 @@ static int trace__record(struct trace *trace, int arg= c, const char **argv) } =20 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); +static size_t trace__fprintf_system_summary(struct trace *trace, FILE *fp); =20 static bool evlist__add_vfs_getname(struct evlist *evlist) { @@ -4329,6 +4341,12 @@ static int trace__run(struct trace *trace, int argc,= const char **argv) goto out_delete_evlist; } =20 + if (trace->system_summary) { + trace->syscall_stats =3D alloc_syscall_stats(); + if (trace->syscall_stats =3D=3D NULL) + goto out_delete_evlist; + } + evlist__config(evlist, &trace->opts, &callchain_param); =20 if (forks) { @@ -4489,8 +4507,12 @@ static int trace__run(struct trace *trace, int argc,= const char **argv) ordered_events__flush(&trace->oe.data, OE_FLUSH__FINAL); =20 if (!err) { - if (trace->summary) - trace__fprintf_thread_summary(trace, trace->output); + if (trace->summary) { + if (trace->system_summary) + trace__fprintf_system_summary(trace, trace->output); + else + trace__fprintf_thread_summary(trace, trace->output); + } =20 if (trace->show_tool_stats) { fprintf(trace->output, "Stats:\n " @@ -4502,6 +4524,7 @@ static int trace__run(struct trace *trace, int argc, = const char **argv) } =20 out_delete_evlist: + delete_syscall_stats(trace->syscall_stats); trace__symbols__exit(trace); evlist__free_syscall_tp_fields(evlist); evlist__delete(evlist); @@ -4629,6 +4652,12 @@ static int trace__replay(struct trace *trace) evsel->handler =3D trace__pgfault; } =20 + if (trace->system_summary) { + trace->syscall_stats =3D alloc_syscall_stats(); + if (trace->syscall_stats =3D=3D NULL) + goto out; + } + setup_pager(); =20 err =3D perf_session__process_events(session); @@ -4639,12 +4668,13 @@ static int trace__replay(struct trace *trace) trace__fprintf_thread_summary(trace, trace->output); =20 out: + delete_syscall_stats(trace->syscall_stats); perf_session__delete(session); =20 return err; } =20 -static size_t trace__fprintf_threads_header(FILE *fp) +static size_t trace__fprintf_summary_header(FILE *fp) { size_t printed; =20 @@ -4667,19 +4697,19 @@ static int entry_cmp(const void *e1, const void *e2) return entry1->msecs > entry2->msecs ? -1 : 1; } =20 -static struct syscall_entry *thread__sort_stats(struct thread_trace *ttrac= e) +static struct syscall_entry *syscall__sort_stats(struct hashmap *syscall_s= tats) { struct syscall_entry *entry; struct hashmap_entry *pos; unsigned bkt, i, nr; =20 - nr =3D ttrace->syscall_stats->sz; + nr =3D syscall_stats->sz; entry =3D malloc(nr * sizeof(*entry)); if (entry =3D=3D NULL) return NULL; =20 i =3D 0; - hashmap__for_each_entry(ttrace->syscall_stats, pos, bkt) { + hashmap__for_each_entry(syscall_stats, pos, bkt) { struct syscall_stats *ss =3D pos->pvalue; struct stats *st =3D &ss->stats; =20 @@ -4694,14 +4724,14 @@ static struct syscall_entry *thread__sort_stats(str= uct thread_trace *ttrace) return entry; } =20 -static size_t thread__dump_stats(struct thread_trace *ttrace, - struct trace *trace, FILE *fp) +static size_t syscall__dump_stats(struct trace *trace, FILE *fp, + struct hashmap *syscall_stats) { size_t printed =3D 0; struct syscall *sc; struct syscall_entry *entries; =20 - entries =3D thread__sort_stats(ttrace); + entries =3D syscall__sort_stats(syscall_stats); if (entries =3D=3D NULL) return 0; =20 @@ -4711,7 +4741,7 @@ static size_t thread__dump_stats(struct thread_trace = *ttrace, printed +=3D fprintf(fp, " (msec) = (msec) (msec) (msec) (%%)\n"); printed +=3D fprintf(fp, " --------------- -------- ------ -------- --= ------- --------- --------- ------\n"); =20 - for (size_t i =3D 0; i < ttrace->syscall_stats->sz; i++) { + for (size_t i =3D 0; i < syscall_stats->sz; i++) { struct syscall_entry *entry =3D &entries[i]; struct syscall_stats *stats =3D entry->stats; if (stats) { @@ -4747,6 +4777,17 @@ static size_t thread__dump_stats(struct thread_trace= *ttrace, return printed; } =20 +static size_t thread__dump_stats(struct thread_trace *ttrace, + struct trace *trace, FILE *fp) +{ + return syscall__dump_stats(trace, fp, ttrace->syscall_stats); +} + +static size_t system__dump_stats(struct trace *trace, FILE *fp) +{ + return syscall__dump_stats(trace, fp, trace->syscall_stats); +} + static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struc= t trace *trace) { size_t printed =3D 0; @@ -4800,7 +4841,7 @@ static int trace_nr_events_cmp(void *priv __maybe_unu= sed, =20 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp) { - size_t printed =3D trace__fprintf_threads_header(fp); + size_t printed =3D trace__fprintf_summary_header(fp); LIST_HEAD(threads); =20 if (machine__thread_list(trace->host, &threads) =3D=3D 0) { @@ -4815,6 +4856,27 @@ static size_t trace__fprintf_thread_summary(struct t= race *trace, FILE *fp) return printed; } =20 +static size_t trace__fprintf_system_summary(struct trace *trace, FILE *fp) +{ + size_t printed =3D trace__fprintf_summary_header(fp); + + printed +=3D fprintf(fp, " total, "); + printed +=3D fprintf(fp, "%lu events", trace->nr_events); + + if (trace->pfmaj) + printed +=3D fprintf(fp, ", %lu majfaults", trace->pfmaj); + if (trace->pfmin) + printed +=3D fprintf(fp, ", %lu minfaults", trace->pfmin); + if (trace->sched) + printed +=3D fprintf(fp, ", %.3f msec\n", trace->runtime_ms); + else if (fputc('\n', fp) !=3D EOF) + ++printed; + + printed +=3D system__dump_stats(trace, fp); + + return printed; +} + static int trace__set_duration(const struct option *opt, const char *str, int unset __maybe_unused) { @@ -5233,6 +5295,8 @@ int cmd_trace(int argc, const char **argv) "Show all syscalls and summary with statistics"), OPT_BOOLEAN(0, "errno-summary", &trace.errno_summary, "Show errno stats per syscall, use with -s or -S"), + OPT_BOOLEAN(0, "system-summary", &trace.system_summary, + "Show system-wide summary instead of per-thread, use with -s or -S"), OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min", "Trace pagefaults", parse_pagefaults, "maj"), OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"), --=20 2.48.0.rc2.279.g1de40edade-goog