diff mbox series

[1/2] scripts/resulttool: limit the number of changes displayed per test

Message ID 20231019095352.25923-2-alexis.lothore@bootlin.com
State Accepted, archived
Commit cec118406f3ad81cb4709f6e6ae1cef65799658e
Headers show
Series Add a display limit for regression report generation | expand

Commit Message

Alexis Lothoré Oct. 19, 2023, 9:53 a.m. UTC 
From: Alexis Lothoré <alexis.lothore@bootlin.com>

Most of the changes list generated in regression reports fall in one
of the two following categories:
- there is only a few (<10) changes listed and the info is
  valuable/relevant
- the list is huge (> 100 ? 1000 ?) and basically tells us that the whole
  tests category suffers the same status (test missing, test failing, test
  skipped, etc)

Prevent those huge, worthless lists by limiting the output for each test
result pair:
- current default limit is arbitrarily set to 50
- limit can still be overriden with a new "-l"/"--limit" flag, either with
  custom value, or with 0 to print the whole lists of changes

Signed-off-by: Alexis Lothoré <alexis.lothore@bootlin.com>
---
 scripts/lib/resulttool/regression.py | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/scripts/lib/resulttool/regression.py b/scripts/lib/resulttool/regression.py
index 3d64b8f4af7c..5c5ed6e6a670 100644
--- a/scripts/lib/resulttool/regression.py
+++ b/scripts/lib/resulttool/regression.py
@@ -78,6 +78,8 @@  STATUS_STRINGS = {
     "None": "No matching test result"
 }
 
+REGRESSIONS_DISPLAY_LIMIT=50
+
 def test_has_at_least_one_matching_tag(test, tag_list):
     return "oetags" in test and any(oetag in tag_list for oetag in test["oetags"])
 
@@ -181,11 +183,12 @@  def get_status_str(raw_status):
     raw_status_lower = raw_status.lower() if raw_status else "None"
     return STATUS_STRINGS.get(raw_status_lower, raw_status)
 
-def compare_result(logger, base_name, target_name, base_result, target_result):
+def compare_result(logger, base_name, target_name, base_result, target_result, display_limit):
     base_result = base_result.get('result')
     target_result = target_result.get('result')
     result = {}
     new_tests = 0
+    regressions_count = 0
 
     if base_result and target_result:
         for k in base_result:
@@ -212,7 +215,14 @@  def compare_result(logger, base_name, target_name, base_result, target_result):
             resultstring = "Regression:  %s\n             %s\n" % (base_name, target_name)
             for k in sorted(result):
                 if not result[k]['target'] or not result[k]['target'].startswith("PASS"):
-                    resultstring += '    %s: %s -> %s\n' % (k, get_status_str(result[k]['base']), get_status_str(result[k]['target']))
+                    # Count regressions only if we have to limit the number of
+                    # displayed regressions
+                    if display_limit > 0:
+                        regressions_count = regressions_count + 1
+                    if regressions_count <= display_limit:
+                        resultstring += '    %s: %s -> %s\n' % (k, get_status_str(result[k]['base']), get_status_str(result[k]['target']))
+            if regressions_count > display_limit:
+                resultstring += f'    [...]\n    (In total, {regressions_count} regressions/status changes detected)\n'
             if new_pass_count > 0:
                 resultstring += f'    Additionally, {new_pass_count} previously failing test(s) is/are now passing\n'
         else:
@@ -263,6 +273,10 @@  def regression_common(args, logger, base_results, target_results):
     if args.target_result_id:
         target_results = resultutils.filter_resultsdata(target_results, args.target_result_id)
 
+    display_limit=REGRESSIONS_DISPLAY_LIMIT
+    if args.limit:
+        display_limit=int(args.limit)
+
     fixup_ptest_names(base_results, logger)
     fixup_ptest_names(target_results, logger)
 
@@ -280,7 +294,7 @@  def regression_common(args, logger, base_results, target_results):
                 for b in target.copy():
                     if not can_be_compared(logger, base_results[a][c], target_results[a][b]):
                         continue
-                    res, resstr = compare_result(logger, c, b, base_results[a][c], target_results[a][b])
+                    res, resstr = compare_result(logger, c, b, base_results[a][c], target_results[a][b], display_limit)
                     if not res:
                         matches.append(resstr)
                         base.remove(c)
@@ -291,7 +305,7 @@  def regression_common(args, logger, base_results, target_results):
                 for b in target:
                     if not can_be_compared(logger, base_results[a][c], target_results[a][b]):
                         continue
-                    res, resstr = compare_result(logger, c, b, base_results[a][c], target_results[a][b])
+                    res, resstr = compare_result(logger, c, b, base_results[a][c], target_results[a][b], display_limit)
                     if res:
                         regressions.append(resstr)
         else:
@@ -403,4 +417,5 @@  def register_commands(subparsers):
     parser_build.add_argument('--commit-number', help="Revision number to search for, redundant if --commit is specified")
     parser_build.add_argument('--commit2', help="Revision to compare with")
     parser_build.add_argument('--commit-number2', help="Revision number to compare with, redundant if --commit2 is specified")
+    parser_build.add_argument('-l', '--limit', default=REGRESSIONS_DISPLAY_LIMIT, help="Maximum number of changes to display per test. Can be set to 0 to print all changes")