Optimization: don't re-verify unchanged files

Let the user specify known-good file modtimes. If the files modtime is at least
that old, then the file hasn't changed and does not need to be re-verified.

This is only valid in node when using FS backing storage, not in the browser

1 files changed, 62 insertions, 7 deletions

diff --git a/lib/torrent.js b/lib/torrent.js
index 527ba55..475b41f 100644
--- a/lib/torrent.js
+++ b/lib/torrent.js
@@ -5,12 +5,12 @@ module.exports = Torrent
 var addrToIPPort = require('addr-to-ip-port')
 var BitField = require('bitfield')
 var ChunkStoreWriteStream = require('chunk-store-stream/write')
-var cpus = require('cpus')
 var debug = require('debug')('webtorrent:torrent')
 var Discovery = require('torrent-discovery')
 var EventEmitter = require('events').EventEmitter
 var extend = require('xtend')
 var extendMutable = require('xtend/mutable')
+var fs = require('fs')
 var FSChunkStore = require('fs-chunk-store') // browser: `memory-chunk-store`
 var ImmediateChunkStore = require('immediate-chunk-store')
 var inherits = require('inherits')
@@ -45,6 +45,8 @@ var PIPELINE_MAX_DURATION = 1
 var RECHOKE_INTERVAL = 10000 // 10 seconds
 var RECHOKE_OPTIMISTIC_DURATION = 2 // 30 seconds
 
+var FILESYSTEM_CONCURRENCY = 2
+
 var TMP = typeof pathExists.sync === 'function'
   ? path.join(pathExists.sync('/tmp') ? '/tmp' : os.tmpDir(), 'webtorrent')
   : '/tmp/webtorrent'
@@ -99,6 +101,9 @@ function Torrent (torrentId, client, opts) {
   // for cleanup
   this._servers = []
 
+  // optimization: don't recheck every file if it hasn't changed
+  this._fileModtimes = opts.fileModtimes
+
   if (torrentId !== null) this._onTorrentId(torrentId)
 }
 
@@ -403,7 +408,55 @@ Torrent.prototype._onMetadata = function (metadata) {
   })
 
   self._debug('verifying existing torrent data')
-  parallelLimit(self.pieces.map(function (piece, index) {
+  if (self._fileModtimes && self._store === FSChunkStore) {
+    // don't verify if the files haven't been modified since we last checked
+    self.getFileModtimes(function (err, fileModtimes) {
+      if (err) return self._onError(err)
+
+      var unchanged = self.files.map(function (_, index) {
+        return fileModtimes[index] === self._fileModtimes[index]
+      }).reduce(function (a, b) {
+        return a && b
+      })
+      if (unchanged) {
+        for (var index = 0; index < self.pieces.length; index++) {
+          self._markVerified(index)
+        }
+        self._onStore()
+      } else {
+        self._verifyPieces()
+      }
+    })
+  } else {
+    self._verifyPieces()
+  }
+
+  self.emit('metadata')
+}
+
+/*
+ * Gets the last modified time of every file on disk for this torrent.
+ * Only valid in Node, not in the browser.
+ */
+Torrent.prototype.getFileModtimes = function (cb) {
+  var self = this
+  var ret = []
+  parallelLimit(self.files.map(function (file, index) {
+    return function (cb) {
+      fs.stat(path.join(self.path, file.path), function (err, stat) {
+        ret[index] = stat && stat.mtime.getTime()
+        cb(err)
+      })
+    }
+  }), FILESYSTEM_CONCURRENCY, function (err) {
+    self._debug('done getting file modtimes')
+    cb(err, ret)
+  })
+}
+
+Torrent.prototype._verifyPieces = function () {
+  var self = this
+  parallelLimit(self.pieces.map(function (_, index) {
     return function (cb) {
       self.store.get(index, function (err, buf) {
         if (err) return cb(null) // ignore error
@@ -411,9 +464,7 @@ Torrent.prototype._onMetadata = function (metadata) {
           if (hash === self._hashes[index]) {
             if (!self.pieces[index]) return
             self._debug('piece verified %s', index)
-            self.pieces[index] = null
-            self._reservations[index] = null
-            self.bitfield.set(index, true)
+            self._markVerified(index)
           } else {
             self._debug('piece invalid %s', index)
           }
@@ -421,13 +472,17 @@ Torrent.prototype._onMetadata = function (metadata) {
         })
       })
     }
-  }), cpus().length, function (err) {
+  }), FILESYSTEM_CONCURRENCY, function (err) {
     if (err) return self._onError(err)
     self._debug('done verifying')
     self._onStore()
   })
+}
 
-  self.emit('metadata')
+Torrent.prototype._markVerified = function (index) {
+  this.pieces[index] = null
+  this._reservations[index] = null
+  this.bitfield.set(index, true)
 }
 
 /**