From 7af6fa8a3a6796b70532c31b0c746e89d516d7d0 Mon Sep 17 00:00:00 2001
From: Nikhil Tanwar <2002nikhiltanwar@gmail.com>
Date: Sat, 27 Apr 2024 16:27:18 +0530
Subject: [PATCH] Cache stat values after first use.

When reading ZIMs with a lot of files (for example: mediawiki_en_all), getting their filesize took a lot of time. There were 2 choices:
1. Read filesize while creating the tree - this gave fast subsequent responses (on commands such as ls) but the fuse initialization took a good amount of time.
2. Find filesize when requested by a command (and save it for future requests) - This provides fast initialization but the first read takes time (though, not as much as getting all filesizes - only the requested ones). They are later saved for subsequent requests.
I went with option 2.
---
 src/zimfuse/main.cpp | 6 ++++++
 src/zimfuse/tree.h   | 3 +++
 2 files changed, 9 insertions(+)

diff --git a/src/zimfuse/main.cpp b/src/zimfuse/main.cpp
index d61146a7..bad05da0 100644
--- a/src/zimfuse/main.cpp
+++ b/src/zimfuse/main.cpp
@@ -18,6 +18,11 @@ static const Node* getNode(const std::string& nName)
 
 void setStat(struct stat* st, const Node* node)
 {
+  Tree* const tree = static_cast<Tree*>(fuse_get_context()->private_data);
+  if (tree->statCache.count(node->originalPath)) {
+    *st = tree->statCache[node->originalPath];
+    return;
+  }
   if (node->isDir) {
     st->st_mode = S_IFDIR | 0555;
     st->st_nlink = 1;
@@ -30,6 +35,7 @@ void setStat(struct stat* st, const Node* node)
                         .getItem(true)
                         .getSize();
   }
+  tree->statCache[node->originalPath] = *st;
 }
 
 static int zimGetAttr(const char* path, struct stat* st, fuse_file_info* fi)
diff --git a/src/zimfuse/tree.h b/src/zimfuse/tree.h
index 2c775db9..e45553bf 100644
--- a/src/zimfuse/tree.h
+++ b/src/zimfuse/tree.h
@@ -3,11 +3,14 @@
 
 #include <zim/archive.h>
 #include "node.h"
+#include <sys/stat.h>
 #include <unordered_map>
 
 class Tree
 {
 public:
+    using statStruct = struct stat;
+    std::unordered_map<std::string, statStruct> statCache;
     Tree(const std::string &path);
     std::pair<Node*, bool> attachNode(const std::string& path, Node* parent);
     std::pair<Node*, bool> attachFile(const std::string& path, Node* parent, int collisionCount);