Move cas server from ref-based to object-based garbage collection.

2 files changed, 46 insertions, 3 deletions

diff --git a/buildstream/_artifactcache/cascache.py b/buildstream/_artifactcache/cascache.py
index 6b3bdb471..2ae36d22a 100644
--- a/buildstream/_artifactcache/cascache.py
+++ b/buildstream/_artifactcache/cascache.py
@@ -623,6 +623,41 @@ class CASCache():
         # first ref of this list will be the file modified earliest.
         return [ref for _, ref in sorted(zip(mtimes, refs))]
 
+    # list_objects():
+    #
+    # List cached objects in Least Recently Modified (LRM) order.
+    #
+    # Returns:
+    #     (list) - A list of objects and timestamps in LRM order
+    #
+    def list_objects(self):
+        objs = []
+        mtimes = []
+
+        for root, _, files in os.walk(os.path.join(self.casdir, 'objects')):
+            for filename in files:
+                obj_path = os.path.join(root, filename)
+                try:
+                    mtimes.append(os.path.getmtime(obj_path))
+                except FileNotFoundError:
+                    pass
+                else:
+                    objs.append(obj_path)
+
+        # NOTE: Sorted will sort from earliest to latest, thus the
+        # first element of this list will be the file modified earliest.
+        return sorted(zip(mtimes, objs))
+
+    def clean_up_refs_until(self, time):
+        ref_heads = os.path.join(self.casdir, 'refs', 'heads')
+
+        for root, _, files in os.walk(ref_heads):
+            for filename in files:
+                ref_path = os.path.join(root, filename)
+                # Obtain the mtime (the time a file was last modified)
+                if os.path.getmtime(ref_path) < time:
+                    os.unlink(ref_path)
+
     # remove():
     #
     # Removes the given symbolic ref from the repo.
diff --git a/buildstream/_artifactcache/casserver.py b/buildstream/_artifactcache/casserver.py
index e2344f0f7..3a6481fb2 100644
--- a/buildstream/_artifactcache/casserver.py
+++ b/buildstream/_artifactcache/casserver.py
@@ -462,12 +462,13 @@ def _clean_up_cache(cas, object_size):
         return 0
 
     # obtain a list of LRP artifacts
-    LRP_artifacts = cas.list_refs()
+    LRP_objects = cas.list_objects()
 
     removed_size = 0  # in bytes
+    last_mtime = 0
     while object_size - removed_size > free_disk_space:
         try:
-            to_remove = LRP_artifacts.pop(0)  # The first element in the list is the LRP artifact
+            last_mtime, to_remove = LRP_objects.pop(0)  # The first element in the list is the LRP objects
         except IndexError:
             # This exception is caught if there are no more artifacts in the list
             # LRP_artifacts. This means the the artifact is too large for the filesystem
@@ -476,7 +477,14 @@ def _clean_up_cache(cas, object_size):
                                             "the filesystem which mounts the remote "
                                             "cache".format(object_size))
 
-        removed_size += cas.remove(to_remove, defer_prune=False)
+        try:
+            size = os.stat(to_remove).st_size
+            os.unlink(to_remove)
+            removed_size += size
+        except FileNotFoundError:
+            pass
+
+    cas.clean_up_refs_until(last_mtime)
 
     if removed_size > 0:
         logging.info("Successfully removed {} bytes from the cache".format(removed_size))