object-storage: turn off stat() for container list

Turn of stat() system calls used to fetch the file size during a
container listing operation since these system calls can swamp Gluster
and the result is most often not used.

When a GET or HEAD request is made on a container, stat() system calls
are made during the Python standard library method, os.walk, to
determine if a given directory entry is another directory to recurse
into, and then utils._update_list() will stat() each file to get it
size, and finally utils.get_container_details_from_fs() will stat()
each directory encountered.

For most installations we have seen so far, we don't need the
container listing to accurately return the size of all the objects in
the container, so we can reduce the number of stat() system calls by
not fetching the size of the object.

For now, turn it off by default, and provide an /etc/swift/fs.conf
configuration parameter to turn it back on:

  accurate_size_in_listing = yes

The default for the above is "no".

Change-Id: I7dde11e14bb32ecafa3eabb08852f1ffc4366b35
BUG: 903396
Signed-off-by: Mohammed Junaid <junaid@redhat.com>
Reviewed-on: http://review.gluster.org/4787
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
Reviewed-by: Anand Avati <avati@redhat.com>

4 files changed, 56 insertions, 4 deletions

diff --git a/ufo/etc/fs.conf-gluster b/ufo/etc/fs.conf-gluster
index 54822a4..71a9b03 100644
--- a/ufo/etc/fs.conf-gluster
+++ b/ufo/etc/fs.conf-gluster
@@ -7,3 +7,11 @@ mount_ip = localhost
 # methods besides UFO (not object only), which disables a caching
 # optimizations in order to keep in sync with file system changes.
 object_only = no
+
+# Performance optimization parameter. When turned off, the filesystem will
+# see a reduced number of stat calls, resulting in substantially faster
+# response time for GET and HEAD container requests on containers with large
+# numbers of objects, at the expense of an accurate count of combined bytes
+# used by all objects in the container. For most installations "off" works
+# fine.
+accurate_size_in_listing = off
\ No newline at end of file
diff --git a/ufo/gluster/swift/common/Glusterfs.py b/ufo/gluster/swift/common/Glusterfs.py
index 6cbdf6c..1053610 100644
--- a/ufo/gluster/swift/common/Glusterfs.py
+++ b/ufo/gluster/swift/common/Glusterfs.py
@@ -27,6 +27,7 @@ MOUNT_IP = 'localhost'
 OBJECT_ONLY = False
 RUN_DIR='/var/run/swift'
 SWIFT_DIR = '/etc/swift'
+_do_getsize = False
 if _fs_conf.read(os.path.join('/etc/swift', 'fs.conf')):
     try:
         MOUNT_IP = _fs_conf.get('DEFAULT', 'mount_ip', 'localhost')
@@ -41,6 +42,12 @@ if _fs_conf.read(os.path.join('/etc/swift', 'fs.conf')):
     except (NoSectionError, NoOptionError):
         pass
 
+    try:
+        _do_getsize = _fs_conf.get('DEFAULT', 'accurate_size_in_listing', \
+                                       "no") in TRUE_VALUES
+    except (NoSectionError, NoOptionError):
+        pass
+
 NAME = 'glusterfs'
 
 
diff --git a/ufo/gluster/swift/common/utils.py b/ufo/gluster/swift/common/utils.py
index 7e9f8a6..f2cd8de 100644
--- a/ufo/gluster/swift/common/utils.py
+++ b/ufo/gluster/swift/common/utils.py
@@ -241,7 +241,7 @@ def _update_list(path, cont_path, src_list, reg_file=True, object_count=0,
 
         object_count += 1
 
-        if reg_file:
+        if Glusterfs._do_getsize and reg_file:
             bytes_used += os_path.getsize(os.path.join(path, obj_name))
             sleep()
 
diff --git a/ufo/test/unit/common/test_utils.py b/ufo/test/unit/common/test_utils.py
index 92ce9ae..c645509 100644
--- a/ufo/test/unit/common/test_utils.py
+++ b/ufo/test/unit/common/test_utils.py
@@ -26,7 +26,7 @@ import tarfile
 import shutil
 from collections import defaultdict
 from swift.common.utils import normalize_timestamp
-from gluster.swift.common import utils
+from gluster.swift.common import utils, Glusterfs
 
 #
 # Somewhat hacky way of emulating the operation of xattr calls. They are made
@@ -755,7 +755,7 @@ class TestUtils(unittest.TestCase):
             utils._get_account_details_from_fs = orig_gcdff
             utils.do_stat = orig_ds
 
-    def test_get_container_details_from_fs(self):
+    def test_get_account_details_from_fs(self):
         orig_cwd = os.getcwd()
         td = tempfile.mkdtemp()
         try:
@@ -779,7 +779,39 @@ class TestUtils(unittest.TestCase):
         assert cd.obj_list == []
         assert cd.dir_list == []
 
-    def test_get_account_details_from_fs(self):
+    def test_get_container_details_from_fs(self):
+        orig_cwd = os.getcwd()
+        td = tempfile.mkdtemp()
+        try:
+            tf = tarfile.open("common/data/container_tree.tar.bz2", "r:bz2")
+            os.chdir(td)
+            tf.extractall()
+
+            cd = utils._get_container_details_from_fs(td)
+            assert cd.bytes_used == 0, repr(cd.bytes_used)
+            assert cd.object_count == 8, repr(cd.object_count)
+            assert set(cd.obj_list) == set(['file1', 'file3', 'file2',
+                                   'dir3', 'dir1', 'dir2',
+                                   'dir1/file1', 'dir1/file2'
+                                   ]), repr(cd.obj_list)
+
+            full_dir1 = os.path.join(td, 'dir1')
+            full_dir2 = os.path.join(td, 'dir2')
+            full_dir3 = os.path.join(td, 'dir3')
+            exp_dir_dict = { td:        os.path.getmtime(td),
+                             full_dir1: os.path.getmtime(full_dir1),
+                             full_dir2: os.path.getmtime(full_dir2),
+                             full_dir3: os.path.getmtime(full_dir3),
+                             }
+            for d,m in cd.dir_list:
+                assert d in exp_dir_dict
+                assert exp_dir_dict[d] == m
+        finally:
+            os.chdir(orig_cwd)
+            shutil.rmtree(td)
+
+
+    def test_get_container_details_from_fs_do_getsize_true(self):
         orig_cwd = os.getcwd()
         td = tempfile.mkdtemp()
         try:
@@ -787,6 +819,9 @@ class TestUtils(unittest.TestCase):
             os.chdir(td)
             tf.extractall()
 
+            __do_getsize = Glusterfs._do_getsize
+            Glusterfs._do_getsize = True
+
             cd = utils._get_container_details_from_fs(td)
             assert cd.bytes_used == 30, repr(cd.bytes_used)
             assert cd.object_count == 8, repr(cd.object_count)
@@ -794,6 +829,7 @@ class TestUtils(unittest.TestCase):
                                    'dir3', 'dir1', 'dir2',
                                    'dir1/file1', 'dir1/file2'
                                    ]), repr(cd.obj_list)
+
             full_dir1 = os.path.join(td, 'dir1')
             full_dir2 = os.path.join(td, 'dir2')
             full_dir3 = os.path.join(td, 'dir3')
@@ -806,6 +842,7 @@ class TestUtils(unittest.TestCase):
                 assert d in exp_dir_dict
                 assert exp_dir_dict[d] == m
         finally:
+            Glusterfs._do_getsize = __do_getsize
             os.chdir(orig_cwd)
             shutil.rmtree(td)