[lit] Limit parallelism of sanitizer tests on Darwin [llvm part, take 2]

Running lit tests and unit tests of ASan and TSan on macOS has very bad performance when running with a high number of threads. This is caused by xnu (the macOS kernel), which currently doesn't handle mapping and unmapping of sanitizer shadow regions (reserved VM which are several terabytes large) very well. The situation is so bad that increasing the number of threads actually makes the total testing time larger. The macOS buildbots are affected by this. Note that we can't easily limit the number of sanitizer testing threads without affecting the rest of the tests.

This patch adds a special "group" into lit, and limits the number of concurrently running tests in this group. This helps solve the contention problem, while still allowing other tests to run in full, that means running lit with -j8 will still with 8 threads, and parallelism is only limited in sanitizer tests.

Differential Revision: https://reviews.llvm.org/D28420

llvm-svn: 292548

llvm/utils/lit/lit/LitConfig.py

@@ -24,7 +24,8 @@ class LitConfig(object):
                  noExecute, debug, isWindows,
                  params, config_prefix = None,
                  maxIndividualTestTime = 0,
-                 maxFailures = None):
+                 maxFailures = None,
+                 parallelism_groups = []):
         # The name of the test runner.
         self.progname = progname
         # The items to add to the PATH environment variable.
@@ -62,6 +63,7 @@ class LitConfig(object):
 
         self.maxIndividualTestTime = maxIndividualTestTime
         self.maxFailures = maxFailures
+        self.parallelism_groups = parallelism_groups
 
     @property
     def maxIndividualTestTime(self):

llvm/utils/lit/lit/TestingConfig.py

@@ -106,7 +106,7 @@ class TestingConfig:
                  environment, substitutions, unsupported,
                  test_exec_root, test_source_root, excludes,
                  available_features, pipefail, limit_to_features = [],
-                 is_early = False):
+                 is_early = False, parallelism_group = ""):
         self.parent = parent
         self.name = str(name)
         self.suffixes = set(suffixes)
@@ -125,6 +125,7 @@ class TestingConfig:
         self.limit_to_features = set(limit_to_features)
         # Whether the suite should be tested early in a given run.
         self.is_early = bool(is_early)
+        self.parallelism_group = parallelism_group
 
     def finish(self, litConfig):
         """finish() - Finish this config object, after loading is complete."""

llvm/utils/lit/lit/main.py

@@ -335,7 +335,8 @@ def main_with_tmp(builtinParameters):
         params = userParams,
         config_prefix = opts.configPrefix,
         maxIndividualTestTime = maxIndividualTestTime,
-        maxFailures = opts.maxFailures)
+        maxFailures = opts.maxFailures,
+        parallelism_groups = {})
 
     # Perform test discovery.
     run = lit.run.Run(litConfig,

llvm/utils/lit/lit/run.py

@@ -177,9 +177,15 @@ class Run(object):
         self.tests = tests
 
     def execute_test(self, test):
+        pg = test.config.parallelism_group
+        if callable(pg): pg = pg(test)
+
         result = None
-        start_time = time.time()
+        semaphore = None
         try:
+            if pg: semaphore = self.parallelism_semaphores[pg]
+            if semaphore: semaphore.acquire()
+            start_time = time.time()
             result = test.config.test_format.execute(test, self.lit_config)
 
             # Support deprecated result from execute() which returned the result
@@ -189,6 +195,8 @@ class Run(object):
                 result = lit.Test.Result(code, output)
             elif not isinstance(result, lit.Test.Result):
                 raise ValueError("unexpected result from test execution")
+
+            result.elapsed = time.time() - start_time
         except KeyboardInterrupt:
             raise
         except:
@@ -198,7 +206,8 @@ class Run(object):
             output += traceback.format_exc()
             output += '\n'
             result = lit.Test.Result(lit.Test.UNRESOLVED, output)
-        result.elapsed = time.time() - start_time
+        finally:
+            if semaphore: semaphore.release()
 
         test.setResult(result)
 
@@ -231,6 +240,7 @@ class Run(object):
             try:
                 task_impl = multiprocessing.Process
                 queue_impl = multiprocessing.Queue
+                sem_impl = multiprocessing.Semaphore
                 canceled_flag =  multiprocessing.Value('i', 0)
                 consumer = MultiprocessResultsConsumer(self, display, jobs)
             except:
@@ -242,9 +252,13 @@ class Run(object):
         if not consumer:
             task_impl = threading.Thread
             queue_impl = queue.Queue
+            sem_impl = threading.Semaphore
             canceled_flag = LockedValue(0)
             consumer = ThreadResultsConsumer(display)
 
+        self.parallelism_semaphores = {k: sem_impl(v)
+            for k, v in self.lit_config.parallelism_groups.items()}
+
         # Create the test provider.
         provider = TestProvider(queue_impl, canceled_flag)
         handleFailures(provider, consumer, self.lit_config.maxFailures)