From e2eb4ae0c3bb5b8093f74dd3dacbbcb5b7d55747 Mon Sep 17 00:00:00 2001
From: Alexander Schepanovski <suor.web@gmail.com>
Date: Mon, 23 Sep 2019 19:58:56 +0700
Subject: [PATCH] perf: delay cache creation

The older code instantiates non-local cache remotes on Repo creation if
any of those are configured. And remote instantiation loads their API
libs.
---
 dvc/cache.py | 89 ++++++++++++++++++++++++++--------------------------
 1 file changed, 44 insertions(+), 45 deletions(-)

diff --git a/dvc/cache.py b/dvc/cache.py
index 24b9022a9..5c3e90c6c 100644
--- a/dvc/cache.py
+++ b/dvc/cache.py
@@ -3,7 +3,9 @@
 from __future__ import unicode_literals
 
 import os
+from funcy import cached_property
 
+from dvc.utils.compat import builtin_str
 from dvc.config import Config
 
 
@@ -21,6 +23,42 @@ class CacheConfig(object):
         )
 
 
+def _make_remote_property(name):
+    """
+    The config file is stored in a way that allows you to have a
+    cache for each remote.
+
+    This is needed when specifying external outputs
+    (as they require you to have an external cache location).
+
+    Imagine a config file like the following:
+
+            ['remote "dvc-storage"']
+            url = ssh://localhost/tmp
+            ask_password = true
+
+            [cache]
+            ssh = dvc-storage
+
+    This method creates a cached property, containing cache named `name`:
+
+        self.config == {'ssh': 'dvc-storage'}
+        self.ssh  # a RemoteSSH instance
+    """
+
+    def getter(self):
+        from dvc.remote import Remote
+
+        remote = self.config.get(name)
+        if not remote:
+            return None
+
+        return Remote(self.repo, name=remote)
+
+    getter.__name__ = builtin_str(name)
+    return cached_property(getter)
+
+
 class Cache(object):
     """Class that manages cache locations of a dvc repo.
 
@@ -35,7 +73,7 @@ class Cache(object):
 
         self.repo = repo
 
-        config = repo.config.config[Config.SECTION_CACHE]
+        self.config = config = repo.config.config[Config.SECTION_CACHE]
         local = config.get(Config.SECTION_CACHE_LOCAL)
 
         if local:
@@ -59,48 +97,9 @@ class Cache(object):
             }
 
         self.local = Remote(repo, **settings)
-        self.s3 = self._get_remote(config, Config.SECTION_CACHE_S3)
-        self.gs = self._get_remote(config, Config.SECTION_CACHE_GS)
-        self.ssh = self._get_remote(config, Config.SECTION_CACHE_SSH)
-        self.hdfs = self._get_remote(config, Config.SECTION_CACHE_HDFS)
-        self.azure = self._get_remote(config, Config.SECTION_CACHE_AZURE)
 
-    def _get_remote(self, config, name):
-        """
-        The config file is stored in a way that allows you to have a
-        cache for each remote.
-
-        This is needed when specifying external outputs
-        (as they require you to have an external cache location).
-
-        Imagine a config file like the following:
-
-                ['remote "dvc-storage"']
-                url = ssh://localhost/tmp
-                ask_password = true
-
-                [cache]
-                ssh = dvc-storage
-
-        This method resolves the name under the cache section into the
-        correct Remote instance.
-
-        Args:
-            config (dict): The cache section on the config file
-            name (str): Name of the section we are interested in to retrieve
-
-        Returns:
-            remote (dvc.Remote): Remote instance that the section is referring.
-                None when there's no remote with that name.
-
-        Example:
-            >>> _get_remote(config={'ssh': 'dvc-storage'}, name='ssh')
-        """
-        from dvc.remote import Remote
-
-        remote = config.get(name)
-
-        if not remote:
-            return None
-
-        return Remote(self.repo, name=remote)
+    s3 = _make_remote_property(Config.SECTION_CACHE_S3)
+    gs = _make_remote_property(Config.SECTION_CACHE_GS)
+    ssh = _make_remote_property(Config.SECTION_CACHE_SSH)
+    hdfs = _make_remote_property(Config.SECTION_CACHE_HDFS)
+    azure = _make_remote_property(Config.SECTION_CACHE_AZURE)