LevelDB now attempts to reuse the preceding MANIFEST and log file when re-opened.

(Based on a suggestion by cmumford.)

"open" benchmark on my workstation speeds up significantly since we
can now avoid three fdatasync calls and a compaction per open:

  Before: ~80000 microseconds
  After:    ~130 microseconds

Details:

(1) Added Options::reuse_logs (currently defaults to false) to control
new behavior.  The intention is to change the default to true after some
baking.

(2) Added Env::NewAppendableFile() whose default implementation returns
a not-supported error.

(3) VersionSet::Recovery attempts to reuse the MANIFEST from which
it is recovering.

(4) DBImpl recovery attempts to reuse the last log file and memtable.

(5) db_test.cc now tests a new configuration that sets reuse_logs to true.

(6) fault_injection_test also tests a reuse_logs==true config.

(7) Added a new recovery_test.

1 files changed, 36 insertions, 1 deletions

diff --git a/db/version_set.cc b/db/version_set.cc
index aa83df5..a07e7ec 100644
--- a/db/version_set.cc
+++ b/db/version_set.cc
@@ -893,7 +893,7 @@ Status VersionSet::LogAndApply(VersionEdit* edit, port::Mutex* mu) {
   return s;
 }
 
-Status VersionSet::Recover() {
+Status VersionSet::Recover(bool *save_manifest) {
   struct LogReporter : public log::Reader::Reporter {
     Status* status;
     virtual void Corruption(size_t bytes, const Status& s) {
@@ -1003,11 +1003,46 @@ Status VersionSet::Recover() {
     last_sequence_ = last_sequence;
     log_number_ = log_number;
     prev_log_number_ = prev_log_number;
+
+    // See if we can reuse the existing MANIFEST file.
+    if (ReuseManifest(dscname, current)) {
+      // No need to save new manifest
+    } else {
+      *save_manifest = true;
+    }
   }
 
   return s;
 }
 
+bool VersionSet::ReuseManifest(const std::string& dscname,
+                               const std::string& dscbase) {
+  FileType manifest_type;
+  uint64_t manifest_number;
+  uint64_t manifest_size;
+  if (!ParseFileName(dscbase, &manifest_number, &manifest_type) ||
+      manifest_type != kDescriptorFile ||
+      !env_->GetFileSize(dscname, &manifest_size).ok() ||
+      // Make new compacted MANIFEST if old one is too big
+      manifest_size >= kTargetFileSize) {
+    return false;
+  }
+
+  assert(descriptor_file_ == NULL);
+  assert(descriptor_log_ == NULL);
+  Status r = env_->NewAppendableFile(dscname, &descriptor_file_);
+  if (!r.ok()) {
+    Log(options_->info_log, "Reuse MANIFEST: %s\n", r.ToString().c_str());
+    assert(descriptor_file_ == NULL);
+    return false;
+  }
+
+  Log(options_->info_log, "Reusing MANIFEST %s\n", dscname.c_str());
+  descriptor_log_ = new log::Writer(descriptor_file_, manifest_size);
+  manifest_file_number_ = manifest_number;
+  return true;
+}
+
 void VersionSet::MarkFileNumberUsed(uint64_t number) {
   if (next_file_number_ <= number) {
     next_file_number_ = number + 1;