From 6422356a270329c740304c2b6209be897249cd9d Mon Sep 17 00:00:00 2001
From: Chinmay Kamat <ckamat@nutanix.com>
Date: Fri, 12 Oct 2018 10:40:06 -0700
Subject: [PATCH] Acquire lock on DB LOCK file before starting repair. (#4435)

Summary:
This commit adds code to acquire lock on the DB LOCK file
before starting the repair process. This will prevent
multiple processes from performing repair on the same DB
simultaneously. Fixes repair_test to work with this change.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4435

Differential Revision: D10361499

Pulled By: riversand963

fbshipit-source-id: 3c512c48b7193d383b2279ccecabdb660ac1cf22
---
 db/repair.cc      | 12 +++++++++++-
 db/repair_test.cc |  1 +
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/db/repair.cc b/db/repair.cc
index 195689418..a856de0eb 100644
--- a/db/repair.cc
+++ b/db/repair.cc
@@ -163,11 +163,18 @@ class Repairer {
   }
 
   ~Repairer() {
+    if (db_lock_ != nullptr) {
+      env_->UnlockFile(db_lock_);
+    }
     delete table_cache_;
   }
 
   Status Run() {
-    Status status = FindFiles();
+    Status status = env_->LockFile(LockFileName(dbname_), &db_lock_);
+    if (!status.ok()) {
+      return status;
+    }
+    status = FindFiles();
     if (status.ok()) {
       // Discard older manifests and start a fresh one
       for (size_t i = 0; i < manifests_.size(); i++) {
@@ -245,6 +252,9 @@ class Repairer {
   std::vector<uint64_t> logs_;
   std::vector<TableInfo> tables_;
   uint64_t next_file_number_;
+  // Lock over the persistent DB state. Non-nullptr iff successfully
+  // acquired.
+  FileLock* db_lock_;
 
   Status FindFiles() {
     std::vector<std::string> filenames;
diff --git a/db/repair_test.cc b/db/repair_test.cc
index 72abd62a5..3422532da 100644
--- a/db/repair_test.cc
+++ b/db/repair_test.cc
@@ -313,6 +313,7 @@ TEST_F(RepairTest, RepairColumnFamilyOptions) {
     ASSERT_EQ(comparator_name,
               fname_and_props.second->comparator_name);
   }
+  Close();
 
   // Also check comparator when it's provided via "unknown" CF options
   ASSERT_OK(RepairDB(dbname_, opts, {{"default", opts}},