From f22aaf8b3f46022c016ae5bcd52d77a3e71ce9c9 Mon Sep 17 00:00:00 2001
From: sdong <siying.d@fb.com>
Date: Tue, 29 Oct 2019 18:15:04 -0700
Subject: [PATCH] db_stress: CF Consistency check to use random CF to validate
 iterator results (#5983)

Summary:
Right now, in db_stress's iterator tests, we always use the same CF to validate iterator results. This commit changes it so that a randomized CF is used in Cf consistency test, where every CF should have exactly the same data. This would help catch more bugs.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5983

Test Plan: Run "make crash_test_with_atomic_flush".

Differential Revision: D18217643

fbshipit-source-id: 3ac998852a0378bb59790b20c5f236f6a5d681fe
---
 tools/db_stress_tool.cc | 34 ++++++++++++++++++++++++++--------
 1 file changed, 26 insertions(+), 8 deletions(-)

diff --git a/tools/db_stress_tool.cc b/tools/db_stress_tool.cc
index 7e1fa3f3a..ab2c9d7d0 100644
--- a/tools/db_stress_tool.cc
+++ b/tools/db_stress_tool.cc
@@ -2400,6 +2400,14 @@ class StressTest {
       const std::vector<int64_t>& rand_keys,
       std::unique_ptr<MutexLock>& lock) = 0;
 
+  // Return a column family handle that mirrors what is pointed by
+  // `column_family_id`, which will be used to validate data to be correct.
+  // By default, the column family itself will be returned.
+  virtual ColumnFamilyHandle* GetControlCfh(ThreadState* /* thread*/,
+                                            int column_family_id) {
+    return column_families_[column_family_id];
+  }
+
   // Given a key K, this creates an iterator which scans to K and then
   // does a random sequence of Next/Prev operations.
   virtual Status TestIterate(ThreadState* thread, const ReadOptions& read_opts,
@@ -2458,13 +2466,15 @@ class StressTest {
       ReadOptions cmp_ro;
       cmp_ro.snapshot = snapshot;
       cmp_ro.total_order_seek = true;
-      std::unique_ptr<Iterator> cmp_iter(db_->NewIterator(cmp_ro, cfh));
+      ColumnFamilyHandle* cmp_cfh =
+          GetControlCfh(thread, rand_column_families[0]);
+      std::unique_ptr<Iterator> cmp_iter(db_->NewIterator(cmp_ro, cmp_cfh));
       bool diverged = false;
 
       iter->Seek(key);
       cmp_iter->Seek(key);
-      VerifyIterator(thread, readoptionscopy, iter.get(), cmp_iter.get(), key,
-                     &diverged);
+      VerifyIterator(thread, cmp_cfh, readoptionscopy, iter.get(),
+                     cmp_iter.get(), key, &diverged);
 
       bool no_reverse =
           (FLAGS_memtablerep == "prefix_hash" && !read_opts.total_order_seek &&
@@ -2483,8 +2493,8 @@ class StressTest {
             cmp_iter->Prev();
           }
         }
-        VerifyIterator(thread, readoptionscopy, iter.get(), cmp_iter.get(), key,
-                       &diverged);
+        VerifyIterator(thread, cmp_cfh, readoptionscopy, iter.get(),
+                       cmp_iter.get(), key, &diverged);
       }
 
       if (s.ok()) {
@@ -2506,9 +2516,9 @@ class StressTest {
   // Will flag failure if the verification fails.
   // diverged = true if the two iterator is already diverged.
   // True if verification passed, false if not.
-  void VerifyIterator(ThreadState* thread, const ReadOptions& ro,
-                      Iterator* iter, Iterator* cmp_iter, const Slice& seek_key,
-                      bool* diverged) {
+  void VerifyIterator(ThreadState* thread, ColumnFamilyHandle* cmp_cfh,
+                      const ReadOptions& ro, Iterator* iter, Iterator* cmp_iter,
+                      const Slice& seek_key, bool* diverged) {
     if (*diverged) {
       return;
     }
@@ -2601,6 +2611,7 @@ class StressTest {
       }
     }
     if (*diverged) {
+      fprintf(stderr, "Control CF %s\n", cmp_cfh->GetName().c_str());
       thread->stats.AddErrors(1);
       // Fail fast to preserve the DB state.
       thread->shared->SetVerificationFailure();
@@ -4376,6 +4387,13 @@ class CfConsistencyStressTest : public StressTest {
     return s;
   }
 
+  virtual ColumnFamilyHandle* GetControlCfh(ThreadState* thread,
+                                            int /*column_family_id*/
+  ) {
+    // All column families should contain the same data. Randomly pick one.
+    return column_families_[thread->rand.Next() % column_families_.size()];
+  }
+
 #ifdef ROCKSDB_LITE
   virtual Status TestCheckpoint(
       ThreadState* /* thread */,