[glib/wip/carlosg/shared-hidden-cache-timeout] glocalfileinfo: Use a single timeout source at a time for hidden file cache

[Carlos Garnacho <carlosg src gnome org>]

commit 9abe31b95212bc807c7a5eaebb5961f727821dbf
Author: Carlos Garnacho <carlosg gnome org>
Date:   Sun Nov 1 20:55:27 2020 +0100

    glocalfileinfo: Use a single timeout source at a time for hidden file cache
    
    As hidden file caches currently work, every look up on a directory caches
    its .hidden file contents, and sets a 5s timeout to prune the directory
    from the cache.
    
    This creates a problem for usecases like Tracker Miners, which is in the
    business of inspecting as many files as possible from as many directories
    as possible in the shortest time possible. One timeout is created for each
    directory, which possibly means gobbling thousands of entries in the hidden
    file cache. This adds as many GSources to the glib worker thread, with the
    involved CPU overhead in iterating those in its main context.
    
    To fix this, use a unique timeout that will keep running until the cache
    is empty. This will keep the overhead constant with many files/folders
    being queried.

 gio/glocalfileinfo.c | 76 +++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 58 insertions(+), 18 deletions(-)
---
diff --git a/gio/glocalfileinfo.c b/gio/glocalfileinfo.c
index 90fcb3336..f1ee94682 100644
--- a/gio/glocalfileinfo.c
+++ b/gio/glocalfileinfo.c
@@ -1547,15 +1547,44 @@ win32_get_file_user_info (const gchar  *filename,
 /* support for '.hidden' files */
 G_LOCK_DEFINE_STATIC (hidden_cache);
 static GHashTable *hidden_cache;
+static GSource *hidden_cache_source = NULL; /* Under the hidden_cache lock */
+static guint hidden_cache_ttl = 5; /* In seconds */
+
+typedef struct
+{
+  GHashTable *hidden_files;
+  gint64 timestamp;
+} HiddenCacheData;
 
 static gboolean
 remove_from_hidden_cache (gpointer user_data)
 {
+  HiddenCacheData *data;
+  GHashTableIter iter;
+  gboolean retval;
+  gint64 timestamp;
+
   G_LOCK (hidden_cache);
-  g_hash_table_remove (hidden_cache, user_data);
+  timestamp = g_source_get_time (hidden_cache_source) / G_USEC_PER_SEC;
+
+  g_hash_table_iter_init (&iter, hidden_cache);
+  while (g_hash_table_iter_next (&iter, NULL, (gpointer *) &data))
+    {
+      if (timestamp > (data->timestamp / G_USEC_PER_SEC) + hidden_cache_ttl)
+        g_hash_table_iter_remove (&iter);
+    }
+
+  if (g_hash_table_size (hidden_cache) == 0)
+    {
+      g_clear_pointer (&hidden_cache_source, g_source_unref);
+      retval = G_SOURCE_REMOVE;
+    }
+  else
+    retval = G_SOURCE_CONTINUE;
+
   G_UNLOCK (hidden_cache);
 
-  return FALSE;
+  return retval;
 }
 
 static GHashTable *
@@ -1593,16 +1622,19 @@ read_hidden_file (const gchar *dirname)
 }
 
 static void
-maybe_unref_hash_table (gpointer data)
+free_hidden_file_data (gpointer user_data)
 {
-  if (data != NULL)
-    g_hash_table_unref (data);
+  HiddenCacheData *data = user_data;
+
+  g_clear_pointer (&data->hidden_files, g_hash_table_unref);
+  g_free (data);
 }
 
 static gboolean
 file_is_hidden (const gchar *path,
                 const gchar *basename)
 {
+  HiddenCacheData *data;
   gboolean result;
   gchar *dirname;
   gpointer table;
@@ -1613,28 +1645,36 @@ file_is_hidden (const gchar *path,
 
   if G_UNLIKELY (hidden_cache == NULL)
     hidden_cache = g_hash_table_new_full (g_str_hash, g_str_equal,
-                                          g_free, maybe_unref_hash_table);
+                                          g_free, free_hidden_file_data);
 
   if (!g_hash_table_lookup_extended (hidden_cache, dirname,
-                                     NULL, &table))
+                                     NULL, (gpointer *) &data))
     {
       gchar *mydirname;
-      GSource *remove_from_cache_source;
+
+      data = g_new0 (HiddenCacheData, 1);
+      data->hidden_files = table = read_hidden_file (dirname);
+      data->timestamp = g_get_monotonic_time ();
 
       g_hash_table_insert (hidden_cache,
                            mydirname = g_strdup (dirname),
-                           table = read_hidden_file (dirname));
+                           data);
 
-      remove_from_cache_source = g_timeout_source_new_seconds (5);
-      g_source_set_priority (remove_from_cache_source, G_PRIORITY_DEFAULT);
-      g_source_set_callback (remove_from_cache_source, 
-                             remove_from_hidden_cache, 
-                             mydirname, 
-                             NULL);
-      g_source_attach (remove_from_cache_source, 
-                       GLIB_PRIVATE_CALL (g_get_worker_context) ());
-      g_source_unref (remove_from_cache_source);
+      if (!hidden_cache_source)
+        {
+          hidden_cache_source = g_timeout_source_new_seconds (7);
+          g_source_set_priority (hidden_cache_source, G_PRIORITY_DEFAULT);
+          g_source_set_name (hidden_cache_source,
+                             "[gio] remove_from_hidden_cache");
+          g_source_set_callback (hidden_cache_source,
+                                 remove_from_hidden_cache,
+                                 NULL, NULL);
+          g_source_attach (hidden_cache_source,
+                           GLIB_PRIVATE_CALL (g_get_worker_context) ());
+        }
     }
+  else
+    table = data->hidden_files;
 
   result = table != NULL && g_hash_table_contains (table, basename);