From 82089d59c3e262c020ba2446b4b7d6fac9ac3bd8 Mon Sep 17 00:00:00 2001
From: Siying Dong <siying.d@fb.com>
Date: Thu, 31 May 2018 12:53:43 -0700
Subject: [PATCH] DBImpl::FindObsoleteFiles() not to call GetChildren() on the
 same path

Summary:
DBImpl::FindObsoleteFiles() may call GetChildren() multiple times if different CFs are on the same path. Fix it.
Closes https://github.com/facebook/rocksdb/pull/3885

Differential Revision: D8084634

Pulled By: siying

fbshipit-source-id: b471fbc251f6a05e9243304dc14c0831060cc0b0
---
 db/db_impl_files.cc | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/db/db_impl_files.cc b/db/db_impl_files.cc
index 6d3b4b996..fa079dc25 100644
--- a/db/db_impl_files.cc
+++ b/db/db_impl_files.cc
@@ -12,6 +12,7 @@
 #define __STDC_FORMAT_MACROS
 #endif
 #include <inttypes.h>
+#include <set>
 #include <unordered_set>
 #include "db/event_helpers.h"
 #include "db/memtable_list.h"
@@ -99,10 +100,10 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
   if (doing_the_full_scan) {
     InfoLogPrefix info_log_prefix(!immutable_db_options_.db_log_dir.empty(),
         dbname_);
-    std::vector<std::string> paths;
+    std::set<std::string> paths;
     for (size_t path_id = 0; path_id < immutable_db_options_.db_paths.size();
          path_id++) {
-      paths.emplace_back(immutable_db_options_.db_paths[path_id].path);
+      paths.insert(immutable_db_options_.db_paths[path_id].path);
     }
 
     // Note that if cf_paths is not specified in the ColumnFamilyOptions
@@ -113,7 +114,11 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
     for (auto cfd : *versions_->GetColumnFamilySet()) {
       for (size_t path_id = 0; path_id < cfd->ioptions()->cf_paths.size();
            path_id++) {
-        paths.emplace_back(cfd->ioptions()->cf_paths[path_id].path);
+        auto& path = cfd->ioptions()->cf_paths[path_id].path;
+
+        if (paths.find(path) == paths.end()) {
+          paths.insert(path);
+        }
       }
     }