From b71b4597e7da2db86eb51b2efe138ddf870d4954 Mon Sep 17 00:00:00 2001
From: Andrew Kryczka <andrewkr@fb.com>
Date: Wed, 5 May 2021 17:53:16 -0700
Subject: [PATCH] Permit stdout "fail"/"error" in whitebox crash test (#8272)

Summary:
In https://github.com/facebook/rocksdb/issues/8268, the `db_stress` stdout began containing both the strings
"fail" and "error" (case-insensitive). The whitebox crash test
failed upon seeing either of those strings.

I checked that all other occurrences of "fail" and "error"
(case-insensitive) that `db_stress` produces are printed to `stderr`. So
this PR separates the handling of `db_stress`'s stdout and stderr, and
only fails when one those bad strings are found in stderr.

The downside of this PR is `db_stress`'s original interleaving of stdout/stderr is not preserved in `db_crashtest.py`'s output.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/8272

Test Plan:
run it; see it succeeds for several runs until encountering a real error

```
$ python3 tools/db_crashtest.py whitebox --simple --random_kill_odd=8887 --max_key=1000000 --value_size_mult=33
...
db_stress: cache/clock_cache.cc:483: bool rocksdb::{anonymous}::ClockCacheShard::Unref(rocksdb::{anonymous}::CacheHandle*, bool, rocksdb::{anonymous}::CleanupContext*): Assertion `CountRefs(flags) > 0' failed.

TEST FAILED. Output has 'fail'!!!
```

Reviewed By: zhichao-cao

Differential Revision: D28239233

Pulled By: ajkr

fbshipit-source-id: 3b8602a0d570466a7e2c81bb9c49468f7716091e
---
 tools/db_crashtest.py | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/tools/db_crashtest.py b/tools/db_crashtest.py
index 0e4ed041c..09837481b 100644
--- a/tools/db_crashtest.py
+++ b/tools/db_crashtest.py
@@ -615,7 +615,7 @@ def whitebox_crash_main(args, unknown_args):
         print("Running:" + ' '.join(cmd) + "\n")  # noqa: E999 T25377293 Grandfathered in
 
         popen = subprocess.Popen(cmd, stdout=subprocess.PIPE,
-                                 stderr=subprocess.STDOUT)
+                                 stderr=subprocess.PIPE)
         stdoutdata, stderrdata = popen.communicate()
         if stdoutdata:
             stdoutdata = stdoutdata.decode('utf-8')
@@ -624,8 +624,10 @@ def whitebox_crash_main(args, unknown_args):
         retncode = popen.returncode
         msg = ("check_mode={0}, kill option={1}, exitcode={2}\n".format(
                check_mode, additional_opts['kill_random_test'], retncode))
+
         print(msg)
         print(stdoutdata)
+        print(stderrdata)
 
         expected = False
         if additional_opts['kill_random_test'] is None and (retncode == 0):
@@ -640,15 +642,16 @@ def whitebox_crash_main(args, unknown_args):
             print("TEST FAILED. See kill option and exit code above!!!\n")
             sys.exit(1)
 
-        stdoutdata = stdoutdata.lower()
-        errorcount = (stdoutdata.count('error') -
-                      stdoutdata.count('got errors 0 times'))
-        print("#times error occurred in output is " + str(errorcount) + "\n")
+        stderrdata = stderrdata.lower()
+        errorcount = (stderrdata.count('error') -
+                      stderrdata.count('got errors 0 times'))
+        print("#times error occurred in output is " + str(errorcount) +
+                "\n")
 
         if (errorcount > 0):
             print("TEST FAILED. Output has 'error'!!!\n")
             sys.exit(2)
-        if (stdoutdata.find('fail') >= 0):
+        if (stderrdata.find('fail') >= 0):
             print("TEST FAILED. Output has 'fail'!!!\n")
             sys.exit(2)