[2/2] tools lib traceevent: Remove unneeded qsort and uses memmove instead

Commit Message

Steven Rostedt Aug. 28, 2019, 7:05 p.m. UTC

From: "Steven Rostedt (VMware)" <[e-mail]>

While reading a trace data file that had 100,000s of tasks, the process took
an extremely long time. I profiled it down to add_new_comm(), which was
doing a qsort() call on an array that was pretty much already sorted (all
but the last element. qsort() isn't very efficient when dealing with mostly
sorted arrays, and this definitely showed its issues.

When adding a new task to the task list, instead of using qsort(), do
another bsearch() with a function that will find the element before where
the new task will be inserted in. Then simply shift the rest of the array,
and insert the task where it belongs.

Fixes: f7d82350e597d ("tools/events: Add files to create libtraceevent.a")
Signed-off-by: Steven Rostedt (VMware) <[e-mail]>
---
 tools/lib/traceevent/event-parse.c | 55 ++++++++++++++++++++++++++----
 1 file changed, 49 insertions(+), 6 deletions(-)

Patch

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 13fd9fdf91e0..3e83636076b2 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -142,6 +142,25 @@  static int cmdline_cmp(const void *a, const void *b)
 	return 0;
 }
 
+/* Looking for where to place the key */
+static int cmdline_slot_cmp(const void *a, const void *b)
+{
+	const struct tep_cmdline *ca = a;
+	const struct tep_cmdline *cb = b;
+	const struct tep_cmdline *cb1 = cb + 1;
+
+	if (ca->pid < cb->pid)
+		return -1;
+
+	if (ca->pid > cb->pid) {
+		if (ca->pid <= cb1->pid)
+			return 0;
+		return 1;
+	}
+
+	return 0;
+}
+
 struct cmdline_list {
 	struct cmdline_list	*next;
 	char			*comm;
@@ -239,6 +258,7 @@  static int add_new_comm(struct tep_handle *tep,
 	struct tep_cmdline *cmdline;
 	struct tep_cmdline key;
 	char *new_comm;
+	int cnt;
 
 	if (!pid)
 		return 0;
@@ -271,18 +291,41 @@  static int add_new_comm(struct tep_handle *tep,
 	}
 	tep->cmdlines = cmdlines;
 
-	cmdlines[tep->cmdline_count].comm = strdup(comm);
-	if (!cmdlines[tep->cmdline_count].comm) {
+	key.comm = strdup(comm);
+	if (!key.comm) {
 		errno = ENOMEM;
 		return -1;
 	}
 
-	cmdlines[tep->cmdline_count].pid = pid;
-		
-	if (cmdlines[tep->cmdline_count].comm)
+	if (!tep->cmdline_count) {
+		/* no entries yet */
+		tep->cmdlines[0] = key;
 		tep->cmdline_count++;
+		return 0;
+	}
 
-	qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+	/* Now find where we want to store the new cmdline */
+	cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count - 1,
+			  sizeof(*tep->cmdlines), cmdline_slot_cmp);
+
+	cnt = tep->cmdline_count;
+	if (cmdline) {
+		/* cmdline points to the one before the spot we want */
+		cmdline++;
+		cnt -= cmdline - tep->cmdlines;
+
+	} else {
+		/* The new entry is either before or after the list */
+		if (key.pid > tep->cmdlines[tep->cmdline_count - 1].pid) {
+			tep->cmdlines[tep->cmdline_count++] = key;
+			return 0;
+		}
+		cmdline = &tep->cmdlines[0];
+	}
+	memmove(cmdline + 1, cmdline, (cnt * sizeof(*cmdline)));
+	*cmdline = key;
+
+	tep->cmdline_count++;
 
 	return 0;
 }