dsos__add would add at the end of the dso array possibly requiring a
later find to re-sort the array. Patterns of find then add were
becoming O(n*log n) due to the sorts. Change the add routine to be
O(n) rather than O(1) but to maintain the sorted-ness of the dsos
array so that later finds don't need the O(n*log n) sort.

Reported-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/dsos.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index 5e5e05f86dd3..d4acdb37f046 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -206,11 +206,27 @@ int __dsos__add(struct dsos *dsos, struct dso *dso)
 		dsos->dsos = temp;
 		dsos->allocated = to_allocate;
 	}
-	dsos->dsos[dsos->cnt++] = dso__get(dso);
-	if (dsos->cnt >= 2 && dsos->sorted) {
-		dsos->sorted = dsos__cmp_long_name_id_short_name(&dsos->dsos[dsos->cnt - 2],
-								 &dsos->dsos[dsos->cnt - 1])
-			<= 0;
+	if (!dsos->sorted) {
+		dsos->dsos[dsos->cnt++] = dso__get(dso);
+	} else {
+		int low = 0, high = dsos->cnt - 1;
+		int insert = dsos->cnt; /* Default to inserting at the end. */
+
+		while (low <= high) {
+			int mid = low + (high - low) / 2;
+			int cmp = dsos__cmp_long_name_id_short_name(&dsos->dsos[mid], &dso);
+
+			if (cmp < 0) {
+				low = mid + 1;
+			} else {
+				high = mid - 1;
+				insert = mid;
+			}
+		}
+		memmove(&dsos->dsos[insert + 1], &dsos->dsos[insert],
+			(dsos->cnt - insert) * sizeof(struct dso *));
+		dsos->cnt++;
+		dsos->dsos[insert] = dso__get(dso);
 	}
 	dso__set_dsos(dso, dsos);
 	return 0;
-- 
2.45.2.803.g4e1b14247a-goog

On Wed, Jul 03, 2024 at 10:21:17AM -0700, Ian Rogers wrote:
> dsos__add would add at the end of the dso array possibly requiring a
> later find to re-sort the array. Patterns of find then add were
> becoming O(n*log n) due to the sorts. Change the add routine to be
> O(n) rather than O(1) but to maintain the sorted-ness of the dsos
> array so that later finds don't need the O(n*log n) sort.
> 
> Reported-by: Namhyung Kim <namhyung@kernel.org>
> Signed-off-by: Ian Rogers <irogers@google.com>

It works well for me too!

Tested-by: Namhyung Kim <namhyung@kernel.org>

Thanks,
Namhyung

> ---
>  tools/perf/util/dsos.c | 26 +++++++++++++++++++++-----
>  1 file changed, 21 insertions(+), 5 deletions(-)
> 
> diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
> index 5e5e05f86dd3..d4acdb37f046 100644
> --- a/tools/perf/util/dsos.c
> +++ b/tools/perf/util/dsos.c
> @@ -206,11 +206,27 @@ int __dsos__add(struct dsos *dsos, struct dso *dso)
>  		dsos->dsos = temp;
>  		dsos->allocated = to_allocate;
>  	}
> -	dsos->dsos[dsos->cnt++] = dso__get(dso);
> -	if (dsos->cnt >= 2 && dsos->sorted) {
> -		dsos->sorted = dsos__cmp_long_name_id_short_name(&dsos->dsos[dsos->cnt - 2],
> -								 &dsos->dsos[dsos->cnt - 1])
> -			<= 0;
> +	if (!dsos->sorted) {
> +		dsos->dsos[dsos->cnt++] = dso__get(dso);
> +	} else {
> +		int low = 0, high = dsos->cnt - 1;
> +		int insert = dsos->cnt; /* Default to inserting at the end. */
> +
> +		while (low <= high) {
> +			int mid = low + (high - low) / 2;
> +			int cmp = dsos__cmp_long_name_id_short_name(&dsos->dsos[mid], &dso);
> +
> +			if (cmp < 0) {
> +				low = mid + 1;
> +			} else {
> +				high = mid - 1;
> +				insert = mid;
> +			}
> +		}
> +		memmove(&dsos->dsos[insert + 1], &dsos->dsos[insert],
> +			(dsos->cnt - insert) * sizeof(struct dso *));
> +		dsos->cnt++;
> +		dsos->dsos[insert] = dso__get(dso);
>  	}
>  	dso__set_dsos(dso, dsos);
>  	return 0;
> -- 
> 2.45.2.803.g4e1b14247a-goog
>