From c6ff4c0b70d249d265307607e5a677961a3f2f58 Mon Sep 17 00:00:00 2001
From: Jay Zhuang <zjay@fb.com>
Date: Tue, 26 Jan 2021 17:00:17 -0800
Subject: [PATCH] Fix deadlock in `fs_test.WALWriteRetryableErrorAutoRecover1`
 (#7897)

Summary:
The recovery thread could hold the db.mutex, which is needed from sync
write in main thread.
Make sure the write is done before recovery thread starts.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/7897

Test Plan: `gtest-parallel ./error_handler_fs_test --gtest_filter=DBErrorHandlingFSTest.WALWriteRetryableErrorAutoRecover1 -r 10000 --workers=200`

Reviewed By: zhichao-cao

Differential Revision: D26082933

Pulled By: jay-zhuang

fbshipit-source-id: 226fc49228c0e5903f86ff45cc3fed3080abdb1f
---
 db/error_handler_fs_test.cc | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/db/error_handler_fs_test.cc b/db/error_handler_fs_test.cc
index 399f3651e..f344c7d16 100644
--- a/db/error_handler_fs_test.cc
+++ b/db/error_handler_fs_test.cc
@@ -2248,7 +2248,8 @@ TEST_F(DBErrorHandlingFSTest, WALWriteRetryableErrorAutoRecover1) {
       ASSERT_OK(batch.Put(Key(i), rnd.RandomString(1024)));
     }
     ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-        {{"RecoverFromRetryableBGIOError:BeforeResume0", "WALWriteError1:0"},
+        {{"WALWriteErrorDone", "RecoverFromRetryableBGIOError:BeforeStart"},
+         {"RecoverFromRetryableBGIOError:BeforeResume0", "WALWriteError1:0"},
          {"WALWriteError1:1", "RecoverFromRetryableBGIOError:BeforeResume1"},
          {"RecoverFromRetryableBGIOError:RecoverSuccess", "WALWriteError1:2"}});
 
@@ -2264,6 +2265,7 @@ TEST_F(DBErrorHandlingFSTest, WALWriteRetryableErrorAutoRecover1) {
     wopts.sync = true;
     s = dbfull()->Write(wopts, &batch);
     ASSERT_EQ(true, s.IsIOError());
+    TEST_SYNC_POINT("WALWriteErrorDone");
 
     TEST_SYNC_POINT("WALWriteError1:0");
     fault_fs_->SetFilesystemActive(true);