ceph-volume: Set max open files limit on container

The ceph-volume lvm list command takes ages to complete when having
a lot of LV devices on containerized deployment.
For instance, with 25 OSDs on a node it takes 3 mins 44s to list the
OSD.
Adding the max open files limit to the container engine cli when
executing the ceph-volume command seems to improve a lot thee
execution time ~30s.

This was impacting the OSDs creation with ceph-volume (both filestore
and bluestore) when using multiple LV devices.

Closes: https://bugzilla.redhat.com/show_bug.cgi?id=1702285
Signed-off-by: Dimitri Savineau <dsavinea@redhat.com>

diff --git a/library/ceph_volume.py b/library/ceph_volume.py
index c07e920ac5ffd41724ff6385a3a9bf081b73578b..9777c51bc7b6d15c33ed125f2627b58029e0e482 100644 (file)
--- a/library/ceph_volume.py
+++ b/library/ceph_volume.py
@@ -190,6 +190,7 @@ def container_exec(binary, container_image):
     container_binary = os.getenv('CEPH_CONTAINER_BINARY')
     command_exec = [container_binary, 'run',
                     '--rm', '--privileged', '--net=host', '--ipc=host',
+                    '--ulimit', 'nofile=1024:1024',
                     '-v', '/run/lock/lvm:/run/lock/lvm:z',
                     '-v', '/var/run/udev/:/var/run/udev/:z',
                     '-v', '/dev:/dev', '-v', '/etc/ceph:/etc/ceph:z',

diff --git a/library/test_ceph_volume.py b/library/test_ceph_volume.py
index e58b93bdbcd14940dfa03e05cc08e93c4b6b8272..adebd6577c4202e883140ca698d6464ceb3585cb 100644 (file)
--- a/library/test_ceph_volume.py
+++ b/library/test_ceph_volume.py
@@ -53,6 +53,7 @@ class TestCephVolumeModule(object):
         fake_binary = "ceph-volume"
         fake_container_image = "docker.io/ceph/daemon:latest-luminous"
         expected_command_list = ['docker', 'run', '--rm', '--privileged', '--net=host', '--ipc=host',  # noqa E501
+                                 '--ulimit', 'nofile=1024:1024',
                                  '-v', '/run/lock/lvm:/run/lock/lvm:z',
                                  '-v', '/var/run/udev/:/var/run/udev/:z',
                                  '-v', '/dev:/dev', '-v', '/etc/ceph:/etc/ceph:z',  # noqa E501
@@ -69,6 +70,7 @@ class TestCephVolumeModule(object):
         fake_module.params = {'data': '/dev/sda'}
         fake_container_image = "docker.io/ceph/daemon:latest-luminous"
         expected_command_list = ['docker', 'run', '--rm', '--privileged', '--net=host', '--ipc=host',  # noqa E501
+                                 '--ulimit', 'nofile=1024:1024',
                                  '-v', '/run/lock/lvm:/run/lock/lvm:z',
                                  '-v', '/var/run/udev/:/var/run/udev/:z',
                                  '-v', '/dev:/dev', '-v', '/etc/ceph:/etc/ceph:z',  # noqa E501
@@ -137,6 +139,7 @@ class TestCephVolumeModule(object):
         fake_module.params = {'cluster': 'ceph', 'data': '/dev/sda'}
         fake_container_image = "docker.io/ceph/daemon:latest-luminous"
         expected_command_list = ['docker', 'run', '--rm', '--privileged', '--net=host', '--ipc=host',  # noqa E501
+                                 '--ulimit', 'nofile=1024:1024',
                                  '-v', '/run/lock/lvm:/run/lock/lvm:z',
                                  '-v', '/var/run/udev/:/var/run/udev/:z',
                                  '-v', '/dev:/dev', '-v', '/etc/ceph:/etc/ceph:z',  # noqa E501
@@ -169,6 +172,7 @@ class TestCephVolumeModule(object):
         fake_module = MagicMock()
         fake_container_image = "docker.io/ceph/daemon:latest-luminous"
         expected_command_list = ['docker', 'run', '--rm', '--privileged', '--net=host', '--ipc=host',  # noqa E501
+                                 '--ulimit', 'nofile=1024:1024',
                                  '-v', '/run/lock/lvm:/run/lock/lvm:z',
                                  '-v', '/var/run/udev/:/var/run/udev/:z',
                                  '-v', '/dev:/dev', '-v', '/etc/ceph:/etc/ceph:z',  # noqa E501
@@ -192,6 +196,7 @@ class TestCephVolumeModule(object):
         fake_action = "create"
         fake_container_image = "docker.io/ceph/daemon:latest-luminous"
         expected_command_list = ['docker', 'run', '--rm', '--privileged', '--net=host', '--ipc=host',  # noqa E501
+                                 '--ulimit', 'nofile=1024:1024',
                                  '-v', '/run/lock/lvm:/run/lock/lvm:z',
                                  '-v', '/var/run/udev/:/var/run/udev/:z',
                                  '-v', '/dev:/dev', '-v', '/etc/ceph:/etc/ceph:z',  # noqa E501
@@ -240,6 +245,7 @@ class TestCephVolumeModule(object):
         fake_action = "prepare"
         fake_container_image = "docker.io/ceph/daemon:latest-luminous"
         expected_command_list = ['docker', 'run', '--rm', '--privileged', '--net=host', '--ipc=host',  # noqa E501
+                                 '--ulimit', 'nofile=1024:1024',
                                  '-v', '/run/lock/lvm:/run/lock/lvm:z',
                                  '-v', '/var/run/udev/:/var/run/udev/:z',
                                  '-v', '/dev:/dev', '-v', '/etc/ceph:/etc/ceph:z',  # noqa E501
@@ -289,6 +295,7 @@ class TestCephVolumeModule(object):
 
         fake_container_image = "docker.io/ceph/daemon:latest-luminous"
         expected_command_list = ['docker', 'run', '--rm', '--privileged', '--net=host', '--ipc=host',  # noqa E501
+                                 '--ulimit', 'nofile=1024:1024',
                                  '-v', '/run/lock/lvm:/run/lock/lvm:z',
                                  '-v', '/var/run/udev/:/var/run/udev/:z',
                                  '-v', '/dev:/dev', '-v', '/etc/ceph:/etc/ceph:z',  # noqa E501

diff --git a/roles/ceph-osd/tasks/start_osds.yml b/roles/ceph-osd/tasks/start_osds.yml
index e2486701dbd136d0187ee02d9b641091beac75f9..809e6c68c5e9c081bbe14a7c8ddf1dca4e09f875 100644 (file)
--- a/roles/ceph-osd/tasks/start_osds.yml
+++ b/roles/ceph-osd/tasks/start_osds.yml
@@ -29,7 +29,7 @@
 
 - name: set_fact docker_exec_start_osd
   set_fact:
-    docker_exec_start_osd: "{{ '{{ container_binary }} run --rm --net=host --privileged=true -v /var/run/udev/:/var/run/udev/:z -v /run/lvm/:/run/lvm/ -v /etc/ceph:/etc/ceph:z -v /dev:/dev --entrypoint=ceph-volume ' + ceph_docker_registry + '/' + ceph_docker_image + ':' + ceph_docker_image_tag if containerized_deployment else 'ceph-volume' }}"
+    docker_exec_start_osd: "{{ '{{ container_binary }} run --rm --ulimit nofile=1024:1024 --net=host --privileged=true -v /var/run/udev/:/var/run/udev/:z -v /run/lvm/:/run/lvm/ -v /etc/ceph:/etc/ceph:z -v /dev:/dev --entrypoint=ceph-volume ' + ceph_docker_registry + '/' + ceph_docker_image + ':' + ceph_docker_image_tag if containerized_deployment else 'ceph-volume' }}"
 
 - name: collect osd ids
   command: "{{ docker_exec_start_osd }} lvm list --format json"