[RocksDB] Unit test to show Seek key comparison number

Summary: Added SeekKeyComparison to show the uer key comparison incurred by Seek.

Test Plan:
make perf_context_test
export LEVELDB_TESTS=DBTest.SeekKeyComparison
./perf_context_test --write_buffer_size=500000 --total_keys=10000
./perf_context_test --write_buffer_size=250000 --total_keys=10000

Reviewers: dhruba, xjin

Reviewed By: xjin

CC: leveldb

Differential Revision: https://reviews.facebook.net/D12843

db/perf_context_test.cc

@@ -1,3 +1,4 @@
+#include <algorithm>
 #include <iostream>
 #include <vector>
 
@@ -7,17 +8,25 @@
 #include "util/stop_watch.h"
 #include "util/testharness.h"
 
+bool FLAGS_random_key = false;
+int FLAGS_total_keys = 100;
+int FLAGS_write_buffer_size = 1000000000;
+int FLAGS_max_write_buffer_number = 8;
+int FLAGS_min_write_buffer_number_to_merge = 7;
+
+// Path to the database on file system
+const std::string kDbName = leveldb::test::TmpDir() + "/perf_context_test";
 
 namespace leveldb {
 
-// Path to the database on file system
-const std::string kDbName = test::TmpDir() + "/perf_context_test";
-
-std::shared_ptr<DB> OpenDb(size_t write_buffer_size) {
+std::shared_ptr<DB> OpenDb() {
     DB* db;
     Options options;
     options.create_if_missing = true;
-    options.write_buffer_size = write_buffer_size;
+    options.write_buffer_size = FLAGS_write_buffer_size;
+    options.max_write_buffer_number = FLAGS_max_write_buffer_number;
+    options.min_write_buffer_number_to_merge =
+      FLAGS_min_write_buffer_number_to_merge;
     Status s = DB::Open(options, kDbName,  &db);
     ASSERT_OK(s);
     return std::shared_ptr<DB>(db);
@@ -25,8 +34,6 @@ std::shared_ptr<DB> OpenDb(size_t write_buffer_size) {
 
 class PerfContextTest { };
 
-int kTotalKeys = 100;
-
 TEST(PerfContextTest, StopWatchNanoOverhead) {
   // profile the timer cost by itself!
   const int kTotalIterations = 1000000;
@@ -68,7 +75,7 @@ TEST(PerfContextTest, StopWatchOverhead) {
 void ProfileKeyComparison() {
   DestroyDB(kDbName, Options());    // Start this test with a fresh DB
 
-  auto db = OpenDb(1000000000);
+  auto db = OpenDb();
 
   WriteOptions write_options;
   ReadOptions read_options;
@@ -77,9 +84,9 @@ void ProfileKeyComparison() {
   uint64_t total_user_key_comparison_put = 0;
   uint64_t max_user_key_comparison_get = 0;
 
-  std::cout << "Inserting " << kTotalKeys << " key/value pairs\n...\n";
+  std::cout << "Inserting " << FLAGS_total_keys << " key/value pairs\n...\n";
 
-  for (int i = 0; i < kTotalKeys; ++i) {
+  for (int i = 0; i < FLAGS_total_keys; ++i) {
     std::string key = "k" + std::to_string(i);
     std::string value = "v" + std::to_string(i);
 
@@ -102,28 +109,97 @@ void ProfileKeyComparison() {
             << "max user key comparison get: "
             << max_user_key_comparison_get << "\n"
             << "avg user key comparison get:"
-            << total_user_key_comparison_get/kTotalKeys << "\n";
+            << total_user_key_comparison_get/FLAGS_total_keys << "\n";
+
 }
 
 TEST(PerfContextTest, KeyComparisonCount) {
-  SetPerfLevel(kDisable);
+  SetPerfLevel(kEnableCount);
   ProfileKeyComparison();
 
-  SetPerfLevel(kEnableCount);
+  SetPerfLevel(kDisable);
   ProfileKeyComparison();
 
   SetPerfLevel(kEnableTime);
   ProfileKeyComparison();
 }
 
+// make perf_context_test
+// export LEVELDB_TESTS=PerfContextTest.SeekKeyComparison
+// For one memtable:
+// ./perf_context_test --write_buffer_size=500000 --total_keys=10000
+// For two memtables:
+// ./perf_context_test --write_buffer_size=250000 --total_keys=10000
+// Specify --random_key=1 to shuffle the key before insertion
+// Results show that, for sequential insertion, worst-case Seek Key comparison
+// is close to the total number of keys (linear), when there is only one
+// memtable. When there are two memtables, even the avg Seek Key comparison
+// starts to become linear to the input size.
+
+TEST(PerfContextTest, SeekKeyComparison) {
+  DestroyDB(kDbName, Options());
+  auto db = OpenDb();
+  WriteOptions write_options;
+  ReadOptions read_options;
+
+  std::cout << "Inserting " << FLAGS_total_keys << " key/value pairs\n...\n";
+
+  std::vector<int> keys;
+  for (int i = 0; i < FLAGS_total_keys; ++i) {
+    keys.push_back(i);
+  }
+
+  if (FLAGS_random_key) {
+    std::random_shuffle(keys.begin(), keys.end());
+  }
+
+  for (const int i : keys) {
+    std::string key = "k" + std::to_string(i);
+    std::string value = "v" + std::to_string(i);
+
+    db->Put(write_options, key, value);
+  }
+
+  HistogramImpl histogram;
+  for (int i = 0; i < FLAGS_total_keys; ++i) {
+    std::string key = "k" + std::to_string(i);
+    std::string value = "v" + std::to_string(i);
+
+    std::unique_ptr<Iterator> iter(db->NewIterator(read_options));
+    perf_context.Reset();
+    iter->Seek(key);
+    ASSERT_TRUE(iter->Valid());
+    ASSERT_EQ(iter->value().ToString(), value);
+    histogram.Add(perf_context.user_key_comparison_count);
+  }
+  std::cout << histogram.ToString();
+}
+
 }
 
 int main(int argc, char** argv) {
 
-  if (argc > 1) {
-    leveldb::kTotalKeys = std::stoi(argv[1]);
+  for (int i = 1; i < argc; i++) {
+    int n;
+    char junk;
+
+    if (sscanf(argv[i], "--write_buffer_size=%d%c", &n, &junk) == 1) {
+      FLAGS_write_buffer_size = n;
+    }
+
+    if (sscanf(argv[i], "--total_keys=%d%c", &n, &junk) == 1) {
+      FLAGS_total_keys = n;
+    }
+
+    if (sscanf(argv[i], "--random_key=%d%c", &n, &junk) == 1 &&
+        (n == 0 || n == 1)) {
+      FLAGS_random_key = n;
+    }
+
   }
 
+  std::cout << kDbName << "\n";
+
   leveldb::test::RunAllTests();
   return 0;
 }