From 2d1d51d3856218a21f634ddf650b249e3a378e66 Mon Sep 17 00:00:00 2001
From: sdong <siying.d@fb.com>
Date: Tue, 30 Jun 2020 12:00:32 -0700
Subject: [PATCH] db_stress: deep clean directory before checkpoint (#7039)

Summary:
We see crash test occassionally fails with "A checkpoint operation failed with: Invalid argument: Directory exists". The suspicious is that the directory fails to be deleted because some trash files. Deep clean the directory after a DestroyDB() call.

Also add more debugging printf in case it fails.
Also, preserve the DB if verification fails.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/7039

Test Plan: Run db_stress with low --checkpoint_one_in value

Reviewed By: riversand963

Differential Revision: D22271694

fbshipit-source-id: 6a9b2abb664fc69a4dc666741df4f6b23703cd6d
---
 db_stress_tool/db_stress_test_base.cc | 28 +++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/db_stress_tool/db_stress_test_base.cc b/db_stress_tool/db_stress_test_base.cc
index 9c94d15e5..d2232ccfb 100644
--- a/db_stress_tool/db_stress_test_base.cc
+++ b/db_stress_tool/db_stress_test_base.cc
@@ -1335,10 +1335,34 @@ Status StressTest::TestCheckpoint(ThreadState* thread,
 
   DestroyDB(checkpoint_dir, tmp_opts);
 
+  if (db_stress_env->FileExists(checkpoint_dir).ok()) {
+    // If the directory might still exist, try to delete the files one by one.
+    // Likely a trash file is still there.
+    Status my_s = test::DestroyDir(db_stress_env, checkpoint_dir);
+    if (!my_s.ok()) {
+      fprintf(stderr, "Fail to destory directory before checkpoint: %s",
+              my_s.ToString().c_str());
+    }
+  }
+
   Checkpoint* checkpoint = nullptr;
   Status s = Checkpoint::Create(db_, &checkpoint);
   if (s.ok()) {
     s = checkpoint->CreateCheckpoint(checkpoint_dir);
+    if (!s.ok()) {
+      fprintf(stderr, "Fail to create checkpoint to %s\n",
+              checkpoint_dir.c_str());
+      std::vector<std::string> files;
+      Status my_s = db_stress_env->GetChildren(checkpoint_dir, &files);
+      if (my_s.ok()) {
+        for (const auto& f : files) {
+          fprintf(stderr, " %s\n", f.c_str());
+        }
+      } else {
+        fprintf(stderr, "Fail to get files under the directory to %s\n",
+                my_s.ToString().c_str());
+      }
+    }
   }
   std::vector<ColumnFamilyHandle*> cf_handles;
   DB* checkpoint_db = nullptr;
@@ -1391,11 +1415,11 @@ Status StressTest::TestCheckpoint(ThreadState* thread,
     checkpoint_db = nullptr;
   }
 
-  DestroyDB(checkpoint_dir, tmp_opts);
-
   if (!s.ok()) {
     fprintf(stderr, "A checkpoint operation failed with: %s\n",
             s.ToString().c_str());
+  } else {
+    DestroyDB(checkpoint_dir, tmp_opts);
   }
   return s;
 }
-- 
GitLab