From 26a33ee5bd8f2550544754036c15c3974aa1c3a2 Mon Sep 17 00:00:00 2001
From: Siying Dong <siying.d@fb.com>
Date: Fri, 15 Feb 2019 16:30:23 -0800
Subject: [PATCH] flush_job logs data size too (#4979)

Summary:
Right now when a flush is triggered, the memory consumption is logged but data size is not.
It's useful to log both when we debug unexpected small flushed file size.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4979

Differential Revision: D14071979

Pulled By: siying

fbshipit-source-id: 0cd60449c5205eb00e0fbc299084418f609904ed
---
 db/flush_job.cc | 17 ++++++++++-------
 db/memtable.h   |  4 ++++
 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/db/flush_job.cc b/db/flush_job.cc
index 8398bd8f8..17c9b0df6 100644
--- a/db/flush_job.cc
+++ b/db/flush_job.cc
@@ -311,6 +311,7 @@ Status FlushJob::WriteLevel0Table() {
     ro.total_order_seek = true;
     Arena arena;
     uint64_t total_num_entries = 0, total_num_deletes = 0;
+    uint64_t total_data_size = 0;
     size_t total_memory_usage = 0;
     for (MemTable* m : mems_) {
       ROCKS_LOG_INFO(
@@ -325,16 +326,18 @@ Status FlushJob::WriteLevel0Table() {
       }
       total_num_entries += m->num_entries();
       total_num_deletes += m->num_deletes();
+      total_data_size += m->get_data_size();
       total_memory_usage += m->ApproximateMemoryUsage();
     }
 
-    event_logger_->Log()
-        << "job" << job_context_->job_id << "event"
-        << "flush_started"
-        << "num_memtables" << mems_.size() << "num_entries" << total_num_entries
-        << "num_deletes" << total_num_deletes << "memory_usage"
-        << total_memory_usage << "flush_reason"
-        << GetFlushReasonString(cfd_->GetFlushReason());
+    event_logger_->Log() << "job" << job_context_->job_id << "event"
+                         << "flush_started"
+                         << "num_memtables" << mems_.size() << "num_entries"
+                         << total_num_entries << "num_deletes"
+                         << total_num_deletes << "total_data_size"
+                         << total_data_size << "memory_usage"
+                         << total_memory_usage << "flush_reason"
+                         << GetFlushReasonString(cfd_->GetFlushReason());
 
     {
       ScopedArenaIterator iter(
diff --git a/db/memtable.h b/db/memtable.h
index 46a746ad6..5724f2c31 100644
--- a/db/memtable.h
+++ b/db/memtable.h
@@ -265,6 +265,10 @@ class MemTable {
     return num_deletes_.load(std::memory_order_relaxed);
   }
 
+  uint64_t get_data_size() const {
+    return data_size_.load(std::memory_order_relaxed);
+  }
+
   // Dynamically change the memtable's capacity. If set below the current usage,
   // the next key added will trigger a flush. Can only increase size when
   // memtable prefix bloom is disabled, since we can't easily allocate more
-- 
GitLab