From 2a3363d52eab5d1f83fa45fbd6b295c9a66061a4 Mon Sep 17 00:00:00 2001
From: Siying Dong <siying.d@fb.com>
Date: Mon, 2 Oct 2017 09:40:00 -0700
Subject: [PATCH] ldb dump can print histogram of value size

Summary:
Make "ldb dump --count_only" print histogram of value size. Also, fix a bug that "ldb dump --path=<db_path>" doesn't work.
Closes https://github.com/facebook/rocksdb/pull/2944

Differential Revision: D5954527

Pulled By: siying

fbshipit-source-id: c620a444ec544258b8d113f5f663c375dd53d6be
---
 tools/ldb_cmd.cc | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/tools/ldb_cmd.cc b/tools/ldb_cmd.cc
index c8b6221a5..4c4b596c7 100644
--- a/tools/ldb_cmd.cc
+++ b/tools/ldb_cmd.cc
@@ -1353,6 +1353,9 @@ DBDumperCommand::DBDumperCommand(
   itr = options.find(ARG_PATH);
   if (itr != options.end()) {
     path_ = itr->second;
+    if (db_path_.empty()) {
+      db_path_ = path_;
+    }
   }
 }
 
@@ -1485,6 +1488,8 @@ void DBDumperCommand::DoDumpCommand() {
             ReadableTime(ttl_start).c_str(), ReadableTime(ttl_end).c_str());
   }
 
+  HistogramImpl vsize_hist;
+
   for (; iter->Valid(); iter->Next()) {
     int rawtime = 0;
     // If end marker was specified, we stop before it
@@ -1529,7 +1534,9 @@ void DBDumperCommand::DoDumpCommand() {
 
     }
 
-
+    if (count_only_) {
+      vsize_hist.Add(iter->value().size());
+    }
 
     if (!count_only_ && !count_delim_) {
       if (is_db_ttl_ && timestamp_) {
@@ -1551,6 +1558,11 @@ void DBDumperCommand::DoDumpCommand() {
   } else {
     fprintf(stdout, "Keys in range: %lld\n", (long long) count);
   }
+
+  if (count_only_) {
+    fprintf(stdout, "Value size distribution: \n");
+    fprintf(stdout, "%s\n", vsize_hist.ToString().c_str());
+  }
   // Clean up
   delete iter;
 }