Polish/deflake BackupEngineTest.FileCollision (#9257)

Summary:
Use smaller and more predictable behaviors

Pull Request resolved: https://github.com/facebook/rocksdb/pull/9257

Test Plan:
gtest-parallel --repeat=N ./backupable_db_test --gtest_filter=BackupEngineTest.FileCollision

before (N=50) we see inconsistent sets of SST files

    $ find /dev/shm/rocksdb_blah/ | grep -o '/00.*sst' | grep -o '^[^_]*' | sort | uniq -c
     49 /000009
      3 /000010
      1 /000010.sst
     49 /000012
      3 /000013
      1 /000013.sst
     49 /000015
      2 /000016
      1 /000016.sst
     22 /000018
      2 /000019
      1 /000019.sst
     29 /000020
     11 /000021
      2 /000021.sst
     46 /000022
      2 /000022.sst
      4 /000023
      1 /000023.sst
     27 /000025

And after (N=5000) we see

    $ find /dev/shm/rocksdb_blah/ | grep -o '/00.*sst' | grep -o '^[^_]*' | sort | uniq -c
      10000 /000009
      10000 /000012
       5000 /000015

Reviewed By: ajkr

Differential Revision: D32888393

Pulled By: pdillinger

fbshipit-source-id: 5bfd075b3184bb66c5613758a53f431c406e9808

utilities/backupable/backupable_db_test.cc

@@ -1014,12 +1014,12 @@ class BackupEngineTestWithParam : public BackupEngineTest,
 };
 
 TEST_F(BackupEngineTest, FileCollision) {
-  const int keys_iteration = 5000;
+  const int keys_iteration = 100;
   for (const auto& sopt : kAllShareOptions) {
     OpenDBAndBackupEngine(true /* destroy_old_data */, false /* dummy */, sopt);
     FillDB(db_.get(), 0, keys_iteration);
     ASSERT_OK(backup_engine_->CreateNewBackup(db_.get()));
-    FillDB(db_.get(), 0, keys_iteration);
+    FillDB(db_.get(), keys_iteration, keys_iteration * 2);
     ASSERT_OK(backup_engine_->CreateNewBackup(db_.get()));
     CloseDBAndBackupEngine();
 
@@ -1027,10 +1027,12 @@ TEST_F(BackupEngineTest, FileCollision) {
     // collision.
     ASSERT_OK(DestroyDB(dbname_, options_));
 
-    // open with old backup
+    // open fresh DB, but old backups present
     OpenDBAndBackupEngine(false /* destroy_old_data */, false /* dummy */,
                           sopt);
-    FillDB(db_.get(), 0, keys_iteration * 2);
+    FillDB(db_.get(), 0, keys_iteration);
+    ASSERT_OK(db_->Flush(FlushOptions()));  // like backup would do
+    FillDB(db_.get(), keys_iteration, keys_iteration * 2);
     if (sopt != kShareNoChecksum) {
       ASSERT_OK(backup_engine_->CreateNewBackup(db_.get()));
     } else {