mirror of
https://git.proxmox.com/git/ceph.git
synced 2025-04-28 16:34:15 +00:00
import 15.2.9
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
This commit is contained in:
Thomas Lamprecht
parent
8b89984e92
commit
adb31ebba1
@ -13,7 +13,8 @@ foreach(policy
|
||||
CMP0054
|
||||
CMP0056
|
||||
CMP0065
|
||||
CMP0075)
|
||||
CMP0075
|
||||
CMP0093)
|
||||
if(POLICY ${policy})
|
||||
cmake_policy(SET ${policy} NEW)
|
||||
endif()
|
||||
@ -667,4 +668,4 @@ add_custom_target(tags DEPENDS ctags)
|
||||
|
||||
find_package(CppCheck)
|
||||
find_package(IWYU)
|
||||
set(VERSION 15.2.8)
|
||||
set(VERSION 15.2.9)
|
||||
|
||||
@ -1,5 +1,13 @@
|
||||
15.2.9
|
||||
------
|
||||
* MGR: progress module can now be turned on/off, using the commands:
|
||||
``ceph progress on`` and ``ceph progress off``.
|
||||
|
||||
15.2.8
|
||||
------
|
||||
* $pid expansion in config paths like `admin_socket` will now properly expand
|
||||
to the daemon pid for commands like `ceph-mds` or `ceph-osd`. Previously only
|
||||
`ceph-fuse`/`rbd-nbd` expanded `$pid` with the actual daemon pid.
|
||||
|
||||
* ceph-volume: The ``lvm batch` subcommand received a major rewrite. This closed
|
||||
a number of bugs and improves usability in terms of size specification and
|
||||
|
||||
@ -59,7 +59,7 @@ cd build-doc
|
||||
if [ ! -e $vdir ]; then
|
||||
virtualenv --python=python3 $vdir
|
||||
fi
|
||||
$vdir/bin/pip install --quiet -r $TOPDIR/admin/doc-requirements.txt
|
||||
$vdir/bin/pip install --use-feature=2020-resolver --quiet -r $TOPDIR/admin/doc-requirements.txt -r $TOPDIR/admin/doc-python-common-requirements.txt
|
||||
|
||||
install -d -m0755 \
|
||||
$TOPDIR/build-doc/output/html \
|
||||
|
||||
3
ceph/admin/doc-python-common-requirements.txt
Normal file
3
ceph/admin/doc-python-common-requirements.txt
Normal file
@ -0,0 +1,3 @@
|
||||
pcpp
|
||||
Jinja2
|
||||
-e../src/python-common
|
||||
@ -1,7 +1,7 @@
|
||||
# Contributor: John Coyle <dx9err@gmail.com>
|
||||
# Maintainer: John Coyle <dx9err@gmail.com>
|
||||
pkgname=ceph
|
||||
pkgver=15.2.8
|
||||
pkgver=15.2.9
|
||||
pkgrel=0
|
||||
pkgdesc="Ceph is a distributed object store and file system"
|
||||
pkgusers="ceph"
|
||||
@ -63,7 +63,7 @@ makedepends="
|
||||
xmlstarlet
|
||||
yasm
|
||||
"
|
||||
source="ceph-15.2.8.tar.bz2"
|
||||
source="ceph-15.2.9.tar.bz2"
|
||||
subpackages="
|
||||
$pkgname-base
|
||||
$pkgname-common
|
||||
@ -116,7 +116,7 @@ _sysconfdir=/etc
|
||||
_udevrulesdir=/etc/udev/rules.d
|
||||
_python_sitelib=/usr/lib/python2.7/site-packages
|
||||
|
||||
builddir=$srcdir/ceph-15.2.8
|
||||
builddir=$srcdir/ceph-15.2.9
|
||||
|
||||
build() {
|
||||
export CEPH_BUILD_VIRTUALENV=$builddir
|
||||
|
||||
@ -98,7 +98,7 @@
|
||||
# main package definition
|
||||
#################################################################################
|
||||
Name: ceph
|
||||
Version: 15.2.8
|
||||
Version: 15.2.9
|
||||
Release: 0%{?dist}
|
||||
%if 0%{?fedora} || 0%{?rhel}
|
||||
Epoch: 2
|
||||
@ -114,7 +114,7 @@ License: LGPL-2.1 and LGPL-3.0 and CC-BY-SA-3.0 and GPL-2.0 and BSL-1.0 and BSD-
|
||||
Group: System/Filesystems
|
||||
%endif
|
||||
URL: http://ceph.com/
|
||||
Source0: %{?_remote_tarball_prefix}ceph-15.2.8.tar.bz2
|
||||
Source0: %{?_remote_tarball_prefix}ceph-15.2.9.tar.bz2
|
||||
%if 0%{?suse_version}
|
||||
# _insert_obs_source_lines_here
|
||||
ExclusiveArch: x86_64 aarch64 ppc64le s390x
|
||||
@ -414,10 +414,8 @@ Base is the package that includes all the files shared amongst ceph servers
|
||||
|
||||
%package -n cephadm
|
||||
Summary: Utility to bootstrap Ceph clusters
|
||||
BuildArch: noarch
|
||||
Requires: lvm2
|
||||
%if 0%{?suse_version}
|
||||
Requires: apparmor-abstractions
|
||||
%endif
|
||||
Requires: python%{python3_pkgversion}
|
||||
%if 0%{?weak_deps}
|
||||
Recommends: podman
|
||||
@ -477,8 +475,12 @@ Provides: ceph-test:/usr/bin/ceph-monstore-tool
|
||||
Requires: ceph-base = %{_epoch_prefix}%{version}-%{release}
|
||||
%if 0%{?weak_deps}
|
||||
Recommends: nvme-cli
|
||||
%if 0%{?suse_version}
|
||||
Requires: smartmontools
|
||||
%else
|
||||
Recommends: smartmontools
|
||||
%endif
|
||||
%endif
|
||||
%description mon
|
||||
ceph-mon is the cluster monitor daemon for the Ceph distributed file
|
||||
system. One or more instances of ceph-mon form a Paxos part-time
|
||||
@ -757,8 +759,12 @@ Requires: libstoragemgmt
|
||||
Requires: python%{python3_pkgversion}-ceph-common = %{_epoch_prefix}%{version}-%{release}
|
||||
%if 0%{?weak_deps}
|
||||
Recommends: nvme-cli
|
||||
%if 0%{?suse_version}
|
||||
Requires: smartmontools
|
||||
%else
|
||||
Recommends: smartmontools
|
||||
%endif
|
||||
%endif
|
||||
%description osd
|
||||
ceph-osd is the object storage daemon for the Ceph distributed file
|
||||
system. It is responsible for storing objects on a local file system
|
||||
@ -1134,7 +1140,7 @@ This package provides Ceph’s default alerts for Prometheus.
|
||||
# common
|
||||
#################################################################################
|
||||
%prep
|
||||
%autosetup -p1 -n ceph-15.2.8
|
||||
%autosetup -p1 -n ceph-15.2.9
|
||||
|
||||
%build
|
||||
# LTO can be enabled as soon as the following GCC bug is fixed:
|
||||
@ -1309,7 +1315,7 @@ ln -sf %{_sbindir}/mount.ceph %{buildroot}/sbin/mount.ceph
|
||||
install -m 0644 -D udev/50-rbd.rules %{buildroot}%{_udevrulesdir}/50-rbd.rules
|
||||
|
||||
# sudoers.d
|
||||
install -m 0600 -D sudoers.d/ceph-osd-smartctl %{buildroot}%{_sysconfdir}/sudoers.d/ceph-osd-smartctl
|
||||
install -m 0440 -D sudoers.d/ceph-osd-smartctl %{buildroot}%{_sysconfdir}/sudoers.d/ceph-osd-smartctl
|
||||
|
||||
%if 0%{?rhel} >= 8
|
||||
pathfix.py -pni "%{__python3} %{py3_shbang_opts}" %{buildroot}%{_bindir}/*
|
||||
|
||||
@ -414,10 +414,8 @@ Base is the package that includes all the files shared amongst ceph servers
|
||||
|
||||
%package -n cephadm
|
||||
Summary: Utility to bootstrap Ceph clusters
|
||||
BuildArch: noarch
|
||||
Requires: lvm2
|
||||
%if 0%{?suse_version}
|
||||
Requires: apparmor-abstractions
|
||||
%endif
|
||||
Requires: python%{python3_pkgversion}
|
||||
%if 0%{?weak_deps}
|
||||
Recommends: podman
|
||||
@ -477,8 +475,12 @@ Provides: ceph-test:/usr/bin/ceph-monstore-tool
|
||||
Requires: ceph-base = %{_epoch_prefix}%{version}-%{release}
|
||||
%if 0%{?weak_deps}
|
||||
Recommends: nvme-cli
|
||||
%if 0%{?suse_version}
|
||||
Requires: smartmontools
|
||||
%else
|
||||
Recommends: smartmontools
|
||||
%endif
|
||||
%endif
|
||||
%description mon
|
||||
ceph-mon is the cluster monitor daemon for the Ceph distributed file
|
||||
system. One or more instances of ceph-mon form a Paxos part-time
|
||||
@ -757,8 +759,12 @@ Requires: libstoragemgmt
|
||||
Requires: python%{python3_pkgversion}-ceph-common = %{_epoch_prefix}%{version}-%{release}
|
||||
%if 0%{?weak_deps}
|
||||
Recommends: nvme-cli
|
||||
%if 0%{?suse_version}
|
||||
Requires: smartmontools
|
||||
%else
|
||||
Recommends: smartmontools
|
||||
%endif
|
||||
%endif
|
||||
%description osd
|
||||
ceph-osd is the object storage daemon for the Ceph distributed file
|
||||
system. It is responsible for storing objects on a local file system
|
||||
@ -1309,7 +1315,7 @@ ln -sf %{_sbindir}/mount.ceph %{buildroot}/sbin/mount.ceph
|
||||
install -m 0644 -D udev/50-rbd.rules %{buildroot}%{_udevrulesdir}/50-rbd.rules
|
||||
|
||||
# sudoers.d
|
||||
install -m 0600 -D sudoers.d/ceph-osd-smartctl %{buildroot}%{_sysconfdir}/sudoers.d/ceph-osd-smartctl
|
||||
install -m 0440 -D sudoers.d/ceph-osd-smartctl %{buildroot}%{_sysconfdir}/sudoers.d/ceph-osd-smartctl
|
||||
|
||||
%if 0%{?rhel} >= 8
|
||||
pathfix.py -pni "%{__python3} %{py3_shbang_opts}" %{buildroot}%{_bindir}/*
|
||||
|
||||
@ -1,7 +1,13 @@
|
||||
ceph (15.2.8-1bionic) bionic; urgency=medium
|
||||
ceph (15.2.9-1bionic) bionic; urgency=medium
|
||||
|
||||
|
||||
-- Jenkins Build Slave User <jenkins-build@braggi12.front.sepia.ceph.com> Wed, 16 Dec 2020 18:29:12 +0000
|
||||
-- Jenkins Build Slave User <jenkins-build@braggi11.front.sepia.ceph.com> Tue, 23 Feb 2021 14:23:03 +0000
|
||||
|
||||
ceph (15.2.9-1) stable; urgency=medium
|
||||
|
||||
* New upstream release
|
||||
|
||||
-- Ceph Release Team <ceph-maintainers@ceph.com> Tue, 23 Feb 2021 14:10:13 +0000
|
||||
|
||||
ceph (15.2.8-1) stable; urgency=medium
|
||||
|
||||
|
||||
@ -24,6 +24,7 @@ check_function_exists(strerror_r HAVE_Strerror_R)
|
||||
check_function_exists(name_to_handle_at HAVE_NAME_TO_HANDLE_AT)
|
||||
check_function_exists(pipe2 HAVE_PIPE2)
|
||||
check_function_exists(accept4 HAVE_ACCEPT4)
|
||||
check_function_exists(sigdescr_np HAVE_SIGDESCR_NP)
|
||||
|
||||
include(CMakePushCheckState)
|
||||
cmake_push_check_state(RESET)
|
||||
|
||||
@ -61,7 +61,7 @@ override_dh_auto_install:
|
||||
install -D -m 644 udev/50-rbd.rules $(DESTDIR)/lib/udev/rules.d/50-rbd.rules
|
||||
install -D -m 644 src/etc-rbdmap $(DESTDIR)/etc/ceph/rbdmap
|
||||
install -D -m 644 etc/sysctl/90-ceph-osd.conf $(DESTDIR)/etc/sysctl.d/30-ceph-osd.conf
|
||||
install -D -m 600 sudoers.d/ceph-osd-smartctl $(DESTDIR)/etc/sudoers.d/ceph-osd-smartctl
|
||||
install -D -m 440 sudoers.d/ceph-osd-smartctl $(DESTDIR)/etc/sudoers.d/ceph-osd-smartctl
|
||||
|
||||
install -m 755 src/cephadm/cephadm $(DESTDIR)/usr/sbin/cephadm
|
||||
|
||||
|
||||
@ -17,8 +17,10 @@ if [ -r /etc/os-release ]; then
|
||||
case "$ID" in
|
||||
fedora)
|
||||
PYBUILD="3.7"
|
||||
if [ "$VERSION_ID" -ge "32" ] ; then
|
||||
if [ "$VERSION_ID" -eq "32" ] ; then
|
||||
PYBUILD="3.8"
|
||||
elif [ "$VERSION_ID" -ge "33" ] ; then
|
||||
PYBUILD="3.9"
|
||||
fi
|
||||
;;
|
||||
rhel|centos)
|
||||
|
||||
@ -319,7 +319,7 @@ This can be described with two layouts.
|
||||
db_devices:
|
||||
model: MC-55-44-XZ
|
||||
limit: 2 (db_slots is actually to be favoured here, but it's not implemented yet)
|
||||
|
||||
---
|
||||
service_type: osd
|
||||
service_id: osd_spec_ssd
|
||||
placement:
|
||||
@ -376,8 +376,7 @@ You can use the 'host_pattern' key in the layout to target certain nodes. Salt t
|
||||
rotational: 1
|
||||
db_devices:
|
||||
rotational: 0
|
||||
|
||||
|
||||
---
|
||||
service_type: osd
|
||||
service_id: osd_spec_six_to_ten
|
||||
placement:
|
||||
|
||||
@ -37,4 +37,5 @@ versions of Ceph.
|
||||
Client Setup <client-setup>
|
||||
DriveGroups <drivegroups>
|
||||
troubleshooting
|
||||
concepts
|
||||
concepts
|
||||
Cephadm Feature Planning <../dev/cephadm/index>
|
||||
@ -72,8 +72,20 @@ monitoring by following the steps below.
|
||||
|
||||
ceph orch apply grafana 1
|
||||
|
||||
Cephadm handles the prometheus, grafana, and alertmanager
|
||||
configurations automatically.
|
||||
Cephadm takes care of the configuration of Prometheus, Grafana, and Alertmanager
|
||||
automatically.
|
||||
|
||||
However, there is one exception to this rule. In a some setups, the Dashboard
|
||||
user's browser might not be able to access the Grafana URL configured in Ceph
|
||||
Dashboard. One such scenario is when the cluster and the accessing user are each
|
||||
in a different DNS zone.
|
||||
|
||||
For this case, there is an extra configuration option for Ceph Dashboard, which
|
||||
can be used to configure the URL for accessing Grafana by the user's browser.
|
||||
This value will never be altered by cephadm. To set this configuration option,
|
||||
issue the following command::
|
||||
|
||||
$ ceph dashboard set-grafana-frontend-api-url <grafana-server-api>
|
||||
|
||||
It may take a minute or two for services to be deployed. Once
|
||||
completed, you should see something like this from ``ceph orch ls``
|
||||
@ -88,6 +100,37 @@ completed, you should see something like this from ``ceph orch ls``
|
||||
node-exporter 2/2 6s ago docker.io/prom/node-exporter:latest e5a616e4b9cf present
|
||||
prometheus 1/1 6s ago docker.io/prom/prometheus:latest e935122ab143 present
|
||||
|
||||
Configuring SSL/TLS for Grafana
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
``cephadm`` will deploy Grafana using the certificate defined in the ceph
|
||||
key/value store. If a certificate is not specified, ``cephadm`` will generate a
|
||||
self-signed certificate during deployment of the Grafana service.
|
||||
|
||||
A custom certificate can be configured using the following commands.
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
ceph config-key set mgr/cephadm/grafana_key -i $PWD/key.pem
|
||||
ceph config-key set mgr/cephadm/grafana_crt -i $PWD/certificate.pem
|
||||
|
||||
The ``cephadm`` manager module needs to be restarted to be able to read updates
|
||||
to these keys.
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
ceph orch restart mgr
|
||||
|
||||
If you already deployed Grafana, you need to redeploy the service for the
|
||||
configuration to be updated.
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
ceph orch redeploy grafana
|
||||
|
||||
The ``redeploy`` command also takes care of setting the right URL for Ceph
|
||||
Dashboard.
|
||||
|
||||
Using custom images
|
||||
~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
@ -120,7 +163,7 @@ For example
|
||||
you have set the custom image for automatically. You will need to
|
||||
manually update the configuration (image name and tag) to be able to
|
||||
install updates.
|
||||
|
||||
|
||||
If you choose to go with the recommendations instead, you can reset the
|
||||
custom image you have set before. After that, the default value will be
|
||||
used again. Use ``ceph config rm`` to reset the configuration option
|
||||
@ -135,6 +178,86 @@ For example
|
||||
|
||||
ceph config rm mgr mgr/cephadm/container_image_prometheus
|
||||
|
||||
Using custom configuration files
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
By overriding cephadm templates, it is possible to completely customize the
|
||||
configuration files for monitoring services.
|
||||
|
||||
Internally, cephadm already uses `Jinja2
|
||||
<https://jinja.palletsprojects.com/en/2.11.x/>`_ templates to generate the
|
||||
configuration files for all monitoring components. To be able to customize the
|
||||
configuration of Prometheus, Grafana or the Alertmanager it is possible to store
|
||||
a Jinja2 template for each service that will be used for configuration
|
||||
generation instead. This template will be evaluated every time a service of that
|
||||
kind is deployed or reconfigured. That way, the custom configuration is
|
||||
preserved and automatically applied on future deployments of these services.
|
||||
|
||||
.. note::
|
||||
|
||||
The configuration of the custom template is also preserved when the default
|
||||
configuration of cephadm changes. If the updated configuration is to be used,
|
||||
the custom template needs to be migrated *manually*.
|
||||
|
||||
Option names
|
||||
""""""""""""
|
||||
|
||||
The following templates for files that will be generated by cephadm can be
|
||||
overridden. These are the names to be used when storing with ``ceph config-key
|
||||
set``:
|
||||
|
||||
- ``alertmanager_alertmanager.yml``
|
||||
- ``grafana_ceph-dashboard.yml``
|
||||
- ``grafana_grafana.ini``
|
||||
- ``prometheus_prometheus.yml``
|
||||
|
||||
You can look up the file templates that are currently used by cephadm in
|
||||
``src/pybind/mgr/cephadm/templates``:
|
||||
|
||||
- ``services/alertmanager/alertmanager.yml.j2``
|
||||
- ``services/grafana/ceph-dashboard.yml.j2``
|
||||
- ``services/grafana/grafana.ini.j2``
|
||||
- ``services/prometheus/prometheus.yml.j2``
|
||||
|
||||
Usage
|
||||
"""""
|
||||
|
||||
The following command applies a single line value:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
ceph config-key set mgr/cephadm/<option_name> <value>
|
||||
|
||||
To set contents of files as template use the ``-i`` argument:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
ceph config-key set mgr/cephadm/<option_name> -i $PWD/<filename>
|
||||
|
||||
.. note::
|
||||
|
||||
When using files as input to ``config-key`` an absolute path to the file must
|
||||
be used.
|
||||
|
||||
It is required to restart the cephadm mgr module after a configuration option
|
||||
has been set. Then the configuration file for the service needs to be recreated.
|
||||
This is done using `redeploy`. For more details see the following example.
|
||||
|
||||
Example
|
||||
"""""""
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
# set the contents of ./prometheus.yml.j2 as template
|
||||
ceph config-key set mgr/cephadm/services_prometheus_prometheus.yml \
|
||||
-i $PWD/prometheus.yml.j2
|
||||
|
||||
# restart cephadm mgr module
|
||||
ceph orch restart mgr
|
||||
|
||||
# redeploy the prometheus service
|
||||
ceph orch redeploy prometheus
|
||||
|
||||
Disabling monitoring
|
||||
--------------------
|
||||
|
||||
|
||||
@ -305,3 +305,53 @@ the cluster, create an initial ``ceph.conf`` file. For example::
|
||||
Then, run bootstrap referencing this file::
|
||||
|
||||
cephadm bootstrap -c /root/ceph.conf ...
|
||||
|
||||
|
||||
.. _cephadm-removing-hosts:
|
||||
|
||||
Removing Hosts
|
||||
==============
|
||||
|
||||
If the node that want you to remove is running OSDs, make sure you remove the OSDs from the node.
|
||||
|
||||
To remove a host from a cluster, do the following:
|
||||
|
||||
For all Ceph service types, except for ``node-exporter`` and ``crash``, remove
|
||||
the host from the placement specification file (for example, cluster.yml).
|
||||
For example, if you are removing the host named host2, remove all occurrences of
|
||||
``- host2`` from all ``placement:`` sections.
|
||||
|
||||
Update:
|
||||
|
||||
.. code-block:: yaml
|
||||
|
||||
service_type: rgw
|
||||
placement:
|
||||
hosts:
|
||||
- host1
|
||||
- host2
|
||||
|
||||
To:
|
||||
|
||||
.. code-block:: yaml
|
||||
|
||||
|
||||
service_type: rgw
|
||||
placement:
|
||||
hosts:
|
||||
- host1
|
||||
|
||||
Remove the host from cephadm's environment:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
ceph orch host rm host2
|
||||
|
||||
See also :ref:`orchestrator-cli-host-management`.
|
||||
|
||||
If the host is running ``node-exporter`` and crash services, remove them by running
|
||||
the following command on the host:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
cephadm rm-daemon --fsid CLUSTER_ID --name SERVICE_NAME
|
||||
|
||||
@ -28,7 +28,7 @@ The other dimension to MDS performance is the available RAM for caching. The
|
||||
MDS necessarily manages a distributed and cooperative metadata cache among all
|
||||
clients and other active MDSs. Therefore it is essential to provide the MDS
|
||||
with sufficient RAM to enable faster metadata access and mutation. The default
|
||||
MDS cache size (see also :doc:`/cephfs/cache-size-limits`) is 4GB. It is
|
||||
MDS cache size (see also :doc:`/cephfs/cache-configuration`) is 4GB. It is
|
||||
recommended to provision at least 8GB of RAM for the MDS to support this cache
|
||||
size.
|
||||
|
||||
|
||||
181
ceph/doc/cephfs/cache-configuration.rst
Normal file
181
ceph/doc/cephfs/cache-configuration.rst
Normal file
@ -0,0 +1,181 @@
|
||||
=======================
|
||||
MDS Cache Configuration
|
||||
=======================
|
||||
|
||||
The Metadata Server coordinates a distributed cache among all MDS and CephFS
|
||||
clients. The cache serves to improve metadata access latency and allow clients
|
||||
to safely (coherently) mutate metadata state (e.g. via `chmod`). The MDS issues
|
||||
**capabilities** and **directory entry leases** to indicate what state clients
|
||||
may cache and what manipulations clients may perform (e.g. writing to a file).
|
||||
|
||||
The MDS and clients both try to enforce a cache size. The mechanism for
|
||||
specifying the MDS cache size is described below. Note that the MDS cache size
|
||||
is a not a hard limit. The MDS always allows clients to lookup new metadata
|
||||
which is loaded into the cache. This is an essential policy as its avoids
|
||||
deadlock in client requests (some requests may rely on held capabilities before
|
||||
capabilities are released).
|
||||
|
||||
When the MDS cache is too large, the MDS will **recall** client state so cache
|
||||
items become unpinned and eligble to be dropped. The MDS can only drop cache
|
||||
state when no clients refer to the metadata to be dropped. Also described below
|
||||
is how to configure the MDS recall settings for your workload's needs. This is
|
||||
necessary if the internal throttles on the MDS recall can not keep up with the
|
||||
client workload.
|
||||
|
||||
|
||||
MDS Cache Size
|
||||
--------------
|
||||
|
||||
You can limit the size of the Metadata Server (MDS) cache by a byte count. This
|
||||
is done through the `mds_cache_memory_limit` configuration. For example::
|
||||
|
||||
ceph config set mds mds_cache_memory_limit 8GB
|
||||
|
||||
In addition, you can specify a cache reservation by using the
|
||||
`mds_cache_reservation` parameter for MDS operations. The cache reservation is
|
||||
limited as a percentage of the memory and is set to 5% by default. The intent
|
||||
of this parameter is to have the MDS maintain an extra reserve of memory for
|
||||
its cache for new metadata operations to use. As a consequence, the MDS should
|
||||
in general operate below its memory limit because it will recall old state from
|
||||
clients in order to drop unused metadata in its cache.
|
||||
|
||||
If the MDS cannot keep its cache under the target size, the MDS will send a
|
||||
health alert to the Monitors indicating the cache is too large. This is
|
||||
controlled by the `mds_health_cache_threshold` configuration which is by
|
||||
default 150% of the maximum cache size.
|
||||
|
||||
Because the cache limit is not a hard limit, potential bugs in the CephFS
|
||||
client, MDS, or misbehaving applications might cause the MDS to exceed its
|
||||
cache size. The health warnings are intended to help the operator detect this
|
||||
situation and make necessary adjustments or investigate buggy clients.
|
||||
|
||||
MDS Cache Trimming
|
||||
------------------
|
||||
|
||||
There are two configurations for throttling the rate of cache trimming in the MDS:
|
||||
|
||||
::
|
||||
|
||||
mds_cache_trim_threshold (default 64k)
|
||||
|
||||
|
||||
and
|
||||
|
||||
::
|
||||
|
||||
mds_cache_trim_decay_rate (default 1)
|
||||
|
||||
|
||||
The intent of the throttle is to prevent the MDS from spending too much time
|
||||
trimming its cache. This may limit its ability to handle client requests or
|
||||
perform other upkeep.
|
||||
|
||||
The trim configurations control an internal **decay counter**. Anytime metadata
|
||||
is trimmed from the cache, the counter is incremented. The threshold sets the
|
||||
maximum size of the counter while the decay rate indicates the exponential half
|
||||
life for the counter. If the MDS is continually removing items from its cache,
|
||||
it will reach a steady state of ``-ln(0.5)/rate*threshold`` items removed per
|
||||
second.
|
||||
|
||||
The defaults are conservative and may need changed for production MDS with
|
||||
large cache sizes.
|
||||
|
||||
|
||||
MDS Recall
|
||||
----------
|
||||
|
||||
MDS limits its recall of client state (capabilities/leases) to prevent creating
|
||||
too much work for itself handling release messages from clients. This is controlled
|
||||
via the following configurations:
|
||||
|
||||
|
||||
The maximum number of capabilities to recall from a single client in a given recall
|
||||
event::
|
||||
|
||||
mds_recall_max_caps (default: 5000)
|
||||
|
||||
The threshold and decay rate for the decay counter on a session::
|
||||
|
||||
mds_recall_max_decay_threshold (default: 16k)
|
||||
|
||||
and::
|
||||
|
||||
mds_recall_max_decay_rate (default: 2.5 seconds)
|
||||
|
||||
The session decay counter controls the rate of recall for an individual
|
||||
session. The behavior of the counter works the same as for cache trimming
|
||||
above. Each capability that is recalled increments the counter.
|
||||
|
||||
There is also a global decay counter that throttles for all session recall::
|
||||
|
||||
mds_recall_global_max_decay_threshold (default: 64k)
|
||||
|
||||
its decay rate is the same as ``mds_recall_max_decay_rate``. Any recalled
|
||||
capability for any session also increments this counter.
|
||||
|
||||
If clients are slow to release state, the warning "failing to respond to cache
|
||||
pressure" or ``MDS_HEALTH_CLIENT_RECALL`` will be reported. Each session's rate
|
||||
of release is monitored by another decay counter configured by::
|
||||
|
||||
mds_recall_warning_threshold (default: 32k)
|
||||
|
||||
and::
|
||||
|
||||
mds_recall_warning_decay_rate (default: 60.0 seconds)
|
||||
|
||||
Each time a capability is released, the counter is incremented. If clients do
|
||||
not release capabilities quickly enough and there is cache pressure, the
|
||||
counter will indicate if the client is slow to release state.
|
||||
|
||||
Some workloads and client behaviors may require faster recall of client state
|
||||
to keep up with capability acquisition. It is recommended to increase the above
|
||||
counters as needed to resolve any slow recall warnings in the cluster health
|
||||
state.
|
||||
|
||||
|
||||
Session Liveness
|
||||
----------------
|
||||
|
||||
The MDS also keeps track of whether sessions are quiescent. If a client session
|
||||
is not utilizing its capabilities or is otherwise quiet, the MDS will begin
|
||||
recalling state from the session even if its not under cache pressure. This
|
||||
helps the MDS avoid future work when the cluster workload is hot and cache
|
||||
pressure is forcing the MDS to recall state. The expectation is that a client
|
||||
not utilizing its capabilities is unlikely to use those capabilities anytime
|
||||
in the near future.
|
||||
|
||||
Determining whether a given session is quiescent is controlled by the following
|
||||
configuration variables::
|
||||
|
||||
mds_session_cache_liveness_magnitude (default: 10)
|
||||
|
||||
and::
|
||||
|
||||
mds_session_cache_liveness_decay_rate (default: 5min)
|
||||
|
||||
The configuration ``mds_session_cache_liveness_decay_rate`` indicates the
|
||||
half-life for the decay counter tracking the use of capabilities by the client.
|
||||
Each time a client manipulates or acquires a capability, the MDS will increment
|
||||
the counter. This is a rough but effective way to monitor utilization of the
|
||||
client cache.
|
||||
|
||||
The ``mds_session_cache_liveness_magnitude`` is a base-2 magnitude difference
|
||||
of the liveness decay counter and the number of capabilities outstanding for
|
||||
the session. So if the client has ``1*2^20`` (1M) capabilities outstanding and
|
||||
only uses **less** than ``1*2^(20-mds_session_cache_liveness_magnitude)`` (1K
|
||||
using defaults), the MDS will consider the client to be quiescent and begin
|
||||
recall.
|
||||
|
||||
|
||||
Capability Limit
|
||||
----------------
|
||||
|
||||
The MDS also tries to prevent a single client from acquiring too many
|
||||
capabilities. This helps prevent recovery from taking a long time in some
|
||||
situations. It is not generally necessary for a client to have such a large
|
||||
cache. The limit is configured via::
|
||||
|
||||
mds_max_caps_per_client (default: 1M)
|
||||
|
||||
It is not recommended to set this value above 5M but it may be helpful with
|
||||
some workloads.
|
||||
@ -1,14 +0,0 @@
|
||||
Understanding MDS Cache Size Limits
|
||||
===================================
|
||||
|
||||
This section describes ways to limit MDS cache size.
|
||||
|
||||
You can limit the size of the Metadata Server (MDS) cache by:
|
||||
|
||||
* *A memory limit*: A new behavior introduced in the Luminous release. Use the `mds_cache_memory_limit` parameters.
|
||||
|
||||
In addition, you can specify a cache reservation by using the `mds_cache_reservation` parameter for MDS operations. The cache reservation is limited as a percentage of the memory and is set to 5% by default. The intent of this parameter is to have the MDS maintain an extra reserve of memory for its cache for new metadata operations to use. As a consequence, the MDS should in general operate below its memory limit because it will recall old state from clients in order to drop unused metadata in its cache.
|
||||
|
||||
The `mds_cache_reservation` parameter replaces the `mds_health_cache_threshold` in all situations except when MDS nodes sends a health alert to the Monitors indicating the cache is too large. By default, `mds_health_cache_threshold` is 150% of the maximum cache size.
|
||||
|
||||
Be aware that the cache limit is not a hard limit. Potential bugs in the CephFS client or MDS or misbehaving applications might cause the MDS to exceed its cache size. The `mds_health_cache_threshold` configures the cluster health warning message so that operators can investigate why the MDS cannot shrink its cache.
|
||||
@ -85,7 +85,7 @@ FS Subvolume groups
|
||||
|
||||
Create a subvolume group using::
|
||||
|
||||
$ ceph fs subvolumegroup create <vol_name> <group_name> [--pool_layout <data_pool_name> --uid <uid> --gid <gid> --mode <octal_mode>]
|
||||
$ ceph fs subvolumegroup create <vol_name> <group_name> [--pool_layout <data_pool_name>] [--uid <uid>] [--gid <gid>] [--mode <octal_mode>]
|
||||
|
||||
The command succeeds even if the subvolume group already exists.
|
||||
|
||||
@ -111,12 +111,8 @@ List subvolume groups using::
|
||||
|
||||
$ ceph fs subvolumegroup ls <vol_name>
|
||||
|
||||
Create a snapshot (see :doc:`/cephfs/experimental-features`) of a
|
||||
subvolume group using::
|
||||
|
||||
$ ceph fs subvolumegroup snapshot create <vol_name> <group_name> <snap_name>
|
||||
|
||||
This implicitly snapshots all the subvolumes under the subvolume group.
|
||||
.. note:: Subvolume group snapshot feature is no longer supported in mainline CephFS (existing group
|
||||
snapshots can still be listed and deleted)
|
||||
|
||||
Remove a snapshot of a subvolume group using::
|
||||
|
||||
@ -135,7 +131,7 @@ FS Subvolumes
|
||||
|
||||
Create a subvolume using::
|
||||
|
||||
$ ceph fs subvolume create <vol_name> <subvol_name> [--size <size_in_bytes> --group_name <subvol_group_name> --pool_layout <data_pool_name> --uid <uid> --gid <gid> --mode <octal_mode> --namespace-isolated]
|
||||
$ ceph fs subvolume create <vol_name> <subvol_name> [--size <size_in_bytes>] [--group_name <subvol_group_name>] [--pool_layout <data_pool_name>] [--uid <uid>] [--gid <gid>] [--mode <octal_mode>] [--namespace-isolated]
|
||||
|
||||
|
||||
The command succeeds even if the subvolume already exists.
|
||||
@ -150,16 +146,24 @@ its parent directory and no size limit.
|
||||
|
||||
Remove a subvolume using::
|
||||
|
||||
$ ceph fs subvolume rm <vol_name> <subvol_name> [--group_name <subvol_group_name> --force]
|
||||
$ ceph fs subvolume rm <vol_name> <subvol_name> [--group_name <subvol_group_name>] [--force] [--retain-snapshots]
|
||||
|
||||
|
||||
The command removes the subvolume and its contents. It does this in two steps.
|
||||
First, it move the subvolume to a trash folder, and then asynchronously purges
|
||||
First, it moves the subvolume to a trash folder, and then asynchronously purges
|
||||
its contents.
|
||||
|
||||
The removal of a subvolume fails if it has snapshots, or is non-existent.
|
||||
'--force' flag allows the non-existent subvolume remove command to succeed.
|
||||
|
||||
A subvolume can be removed retaining existing snapshots of the subvolume using the
|
||||
'--retain-snapshots' option. If snapshots are retained, the subvolume is considered
|
||||
empty for all operations not involving the retained snapshots.
|
||||
|
||||
.. note:: Snapshot retained subvolumes can be recreated using 'ceph fs subvolume create'
|
||||
|
||||
.. note:: Retained snapshots can be used as a clone source to recreate the subvolume, or clone to a newer subvolume.
|
||||
|
||||
Resize a subvolume using::
|
||||
|
||||
$ ceph fs subvolume resize <vol_name> <subvol_name> <new_size> [--group_name <subvol_group_name>] [--no_shrink]
|
||||
@ -195,17 +199,32 @@ The output format is json and contains fields as follows.
|
||||
* type: subvolume type indicating whether it's clone or subvolume
|
||||
* pool_namespace: RADOS namespace of the subvolume
|
||||
* features: features supported by the subvolume
|
||||
* state: current state of the subvolume
|
||||
|
||||
If a subvolume has been removed retaining its snapshots, the output only contains fields as follows.
|
||||
|
||||
* type: subvolume type indicating whether it's clone or subvolume
|
||||
* features: features supported by the subvolume
|
||||
* state: current state of the subvolume
|
||||
|
||||
The subvolume "features" are based on the internal version of the subvolume and is a list containing
|
||||
a subset of the following features,
|
||||
|
||||
* "snapshot-clone": supports cloning using a subvolumes snapshot as the source
|
||||
* "snapshot-autoprotect": supports automatically protecting snapshots, that are active clone sources, from deletion
|
||||
* "snapshot-retention": supports removing subvolume contents, retaining any existing snapshots
|
||||
|
||||
The subvolume "state" is based on the current state of the subvolume and contains one of the following values.
|
||||
|
||||
* "complete": subvolume is ready for all operations
|
||||
* "snapshot-retained": subvolume is removed but its snapshots are retained
|
||||
|
||||
List subvolumes using::
|
||||
|
||||
$ ceph fs subvolume ls <vol_name> [--group_name <subvol_group_name>]
|
||||
|
||||
.. note:: subvolumes that are removed but have snapshots retained, are also listed.
|
||||
|
||||
Create a snapshot of a subvolume using::
|
||||
|
||||
$ ceph fs subvolume snapshot create <vol_name> <subvol_name> <snap_name> [--group_name <subvol_group_name>]
|
||||
@ -213,11 +232,13 @@ Create a snapshot of a subvolume using::
|
||||
|
||||
Remove a snapshot of a subvolume using::
|
||||
|
||||
$ ceph fs subvolume snapshot rm <vol_name> <subvol_name> <snap_name> [--group_name <subvol_group_name> --force]
|
||||
$ ceph fs subvolume snapshot rm <vol_name> <subvol_name> <snap_name> [--group_name <subvol_group_name>] [--force]
|
||||
|
||||
Using the '--force' flag allows the command to succeed that would otherwise
|
||||
fail if the snapshot did not exist.
|
||||
|
||||
.. note:: if the last snapshot within a snapshot retained subvolume is removed, the subvolume is also removed
|
||||
|
||||
List snapshots of a subvolume using::
|
||||
|
||||
$ ceph fs subvolume snapshot ls <vol_name> <subvol_name> [--group_name <subvol_group_name>]
|
||||
|
||||
@ -79,7 +79,7 @@ Administration
|
||||
Administrative commands <administration>
|
||||
Provision/Add/Remove MDS(s) <add-remove-mds>
|
||||
MDS failover and standby configuration <standby>
|
||||
MDS Cache Size Limits <cache-size-limits>
|
||||
MDS Cache Configuration <cache-configuration>
|
||||
MDS Configuration Settings <mds-config-ref>
|
||||
Manual: ceph-mds <../../man/8/ceph-mds>
|
||||
Export over NFS <nfs>
|
||||
|
||||
121
ceph/doc/dev/cephadm/compliance-check.rst
Normal file
121
ceph/doc/dev/cephadm/compliance-check.rst
Normal file
@ -0,0 +1,121 @@
|
||||
================
|
||||
Compliance Check
|
||||
================
|
||||
|
||||
The stability and reliability of a Ceph cluster is dependent not just upon the Ceph daemons, but
|
||||
also the OS and hardware that Ceph is installed on. This document is intended to promote a design
|
||||
discussion for providing a "compliance" feature within mgr/cephadm, which would be responsible for
|
||||
identifying common platform-related issues that could impact Ceph stability and operation.
|
||||
|
||||
The ultimate goal of these checks is to identify issues early and raise a healthcheck WARN
|
||||
event, to alert the Administrator to the issue.
|
||||
|
||||
Prerequisites
|
||||
=============
|
||||
In order to effectively analyse the hosts that Ceph is deployed to, this feature requires a cache
|
||||
of host-related metadata. The metadata is already available from cephadm's HostFacts class and the
|
||||
``gather-facts`` cephadm command. For the purposes of this document, we will assume that this
|
||||
data is available within the mgr/cephadm "cache" structure.
|
||||
|
||||
Some checks will require that the host status is also populated e.g. ONLINE, OFFLINE, MAINTENANCE
|
||||
|
||||
Administrator Interaction
|
||||
=========================
|
||||
Not all users will require this feature, and must be able to 'opt out'. For this reason,
|
||||
mgr/cephadm must provide controls, such as the following;
|
||||
|
||||
.. code-block::
|
||||
|
||||
ceph cephadm compliance enable | disable | status [--format json]
|
||||
ceph cephadm compliance ls [--format json]
|
||||
ceph cephadm compliance enable-check <name>
|
||||
ceph cephadm compliance disable-check <name>
|
||||
ceph cephadm compliance set-check-interval <int>
|
||||
ceph cephadm compliance get-check-interval
|
||||
|
||||
The status option would show the enabled/disabled state of the feature, along with the
|
||||
check-interval.
|
||||
|
||||
The ``ls`` subcommand would show all checks in the following format;
|
||||
|
||||
``check-name status description``
|
||||
|
||||
Proposed Integration
|
||||
====================
|
||||
The compliance checks are not required to run all the time, but instead should run at discrete
|
||||
intervals. The interval would be configurable under via the :code:`set-check-interval`
|
||||
subcommand (default would be every 12 hours)
|
||||
|
||||
|
||||
mgr/cephadm currently executes an event driven (time based) serve loop to act on deploy/remove and
|
||||
reconcile activity. In order to execute the compliance checks, the compliance check code would be
|
||||
called from this main serve loop - when the :code:`set-check-interval` is met.
|
||||
|
||||
|
||||
Proposed Checks
|
||||
===============
|
||||
All checks would push any errors to a list, so multiple issues can be escalated to the Admin at
|
||||
the same time. The list below provides a description of each check, with the text following the
|
||||
name indicating a shortname version *(the shortname is the reference for command Interaction
|
||||
when enabling or disabling a check)*
|
||||
|
||||
|
||||
OS Consistency (OS)
|
||||
___________________
|
||||
* all hosts must use same vendor
|
||||
* all hosts must be on the same major release (this check would only be applicable to distributions that
|
||||
offer a long-term-support strategy (RHEL, CentOS, SLES, Ubuntu etc)
|
||||
|
||||
|
||||
*src: gather-facts output*
|
||||
|
||||
Linux Kernel Security Mode (LSM)
|
||||
________________________________
|
||||
* All hosts should have a consistent SELINUX/AppArmor configuration
|
||||
|
||||
*src: gather-facts output*
|
||||
|
||||
Services Check (SERVICES)
|
||||
_________________________
|
||||
Hosts that are in an ONLINE state should adhere to the following;
|
||||
|
||||
* all daemons (systemd units) should be enabled
|
||||
* all daemons should be running (not dead)
|
||||
|
||||
*src: list_daemons output*
|
||||
|
||||
Support Status (SUPPORT)
|
||||
________________________
|
||||
If support status has been detected, it should be consistent across all hosts. At this point
|
||||
support status is available only for Red Hat machines.
|
||||
|
||||
*src: gather-facts output*
|
||||
|
||||
Network : MTU (MTU)
|
||||
________________________________
|
||||
All network interfaces on the same Ceph network (public/cluster) should have the same MTU
|
||||
|
||||
*src: gather-facts output*
|
||||
|
||||
Network : LinkSpeed (LINKSPEED)
|
||||
____________________________________________
|
||||
All network interfaces on the same Ceph network (public/cluster) should have the same Linkspeed
|
||||
|
||||
*src: gather-facts output*
|
||||
|
||||
Network : Consistency (INTERFACE)
|
||||
______________________________________________
|
||||
All hosts with OSDs should have consistent network configuration - eg. if some hosts do
|
||||
not separate cluster/public traffic but others do, that is an anomaly that would generate a
|
||||
compliance check warning.
|
||||
|
||||
*src: gather-facts output*
|
||||
|
||||
Notification Strategy
|
||||
=====================
|
||||
If any of the checks fail, mgr/cephadm would raise a WARN level alert
|
||||
|
||||
Futures
|
||||
=======
|
||||
The checks highlighted here serve only as a starting point, and we should expect to expand
|
||||
on the checks over time.
|
||||
104
ceph/doc/dev/cephadm/host-maintenance.rst
Normal file
104
ceph/doc/dev/cephadm/host-maintenance.rst
Normal file
@ -0,0 +1,104 @@
|
||||
================
|
||||
Host Maintenance
|
||||
================
|
||||
|
||||
All hosts that support Ceph daemons need to support maintenance activity, whether the host
|
||||
is physical or virtual. This means that management workflows should provide
|
||||
a simple and consistent way to support this operational requirement. This document defines
|
||||
the maintenance strategy that could be implemented in cephadm and mgr/cephadm.
|
||||
|
||||
|
||||
High Level Design
|
||||
=================
|
||||
Placing a host into maintenance, adopts the following workflow;
|
||||
|
||||
#. confirm that the removal of the host does not impact data availability (the following
|
||||
steps will assume it is safe to proceed)
|
||||
|
||||
* orch host ok-to-stop <host> would be used here
|
||||
|
||||
#. if the host has osd daemons, apply noout to the host subtree to prevent data migration
|
||||
from triggering during the planned maintenance slot.
|
||||
#. Stop the ceph target (all daemons stop)
|
||||
#. Disable the ceph target on that host, to prevent a reboot from automatically starting
|
||||
ceph services again)
|
||||
|
||||
|
||||
Exiting Maintenance, is basically the reverse of the above sequence
|
||||
|
||||
Admin Interaction
|
||||
=================
|
||||
The ceph orch command will be extended to support maintenance.
|
||||
|
||||
.. code-block::
|
||||
|
||||
ceph orch host enter-maintenance <host> [ --check ]
|
||||
ceph orch host exit-maintenance <host>
|
||||
|
||||
.. note:: In addition, the host's status should be updated to reflect whether it
|
||||
is in maintenance or not.
|
||||
|
||||
The 'check' Option
|
||||
__________________
|
||||
The orch host ok-to-stop command focuses on ceph daemons (mon, osd, mds), which
|
||||
provides the first check. However, a ceph cluster also uses other types of daemons
|
||||
for monitoring, management and non-native protocol support which means the
|
||||
logic will need to consider service impact too. The 'check' option provides
|
||||
this additional layer to alert the user of service impact to *secondary*
|
||||
daemons.
|
||||
|
||||
The list below shows some of these additional daemons.
|
||||
|
||||
* mgr (not included in ok-to-stop checks)
|
||||
* prometheus, grafana, alertmanager
|
||||
* rgw
|
||||
* haproxy
|
||||
* iscsi gateways
|
||||
* ganesha gateways
|
||||
|
||||
By using the --check option first, the Admin can choose whether to proceed. This
|
||||
workflow is obviously optional for the CLI user, but could be integrated into the
|
||||
UI workflow to help less experienced Administators manage the cluster.
|
||||
|
||||
By adopting this two-phase approach, a UI based workflow would look something
|
||||
like this.
|
||||
|
||||
#. User selects a host to place into maintenance
|
||||
|
||||
* orchestrator checks for data **and** service impact
|
||||
#. If potential impact is shown, the next steps depend on the impact type
|
||||
|
||||
* **data availability** : maintenance is denied, informing the user of the issue
|
||||
* **service availability** : user is provided a list of affected services and
|
||||
asked to confirm
|
||||
|
||||
|
||||
Components Impacted
|
||||
===================
|
||||
Implementing this capability will require changes to the following;
|
||||
|
||||
* cephadm
|
||||
|
||||
* Add maintenance subcommand with the following 'verbs'; enter, exit, check
|
||||
|
||||
* mgr/cephadm
|
||||
|
||||
* add methods to CephadmOrchestrator for enter/exit and check
|
||||
* data gathering would be skipped for hosts in a maintenance state
|
||||
|
||||
* mgr/orchestrator
|
||||
|
||||
* add CLI commands to OrchestratorCli which expose the enter/exit and check interaction
|
||||
|
||||
|
||||
Ideas for Future Work
|
||||
=====================
|
||||
#. When a host is placed into maintenance, the time of the event could be persisted. This
|
||||
would allow the orchestrator layer to establish a maintenance window for the task and
|
||||
alert if the maintenance window has been exceeded.
|
||||
#. The maintenance process could support plugins to allow other integration tasks to be
|
||||
initiated as part of the transition to and from maintenance. This plugin capability could
|
||||
support actions like;
|
||||
|
||||
* alert suppression to 3rd party monitoring framework(s)
|
||||
* service level reporting, to record outage windows
|
||||
13
ceph/doc/dev/cephadm/index.rst
Normal file
13
ceph/doc/dev/cephadm/index.rst
Normal file
@ -0,0 +1,13 @@
|
||||
===================================
|
||||
CEPHADM Developer Documentation
|
||||
===================================
|
||||
|
||||
.. rubric:: Contents
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
|
||||
|
||||
host-maintenance
|
||||
compliance-check
|
||||
|
||||
@ -732,24 +732,32 @@ Per client instance `rbd device map` options:
|
||||
|
||||
* noshare - Disable sharing of client instances with other mappings.
|
||||
|
||||
* crc - Enable CRC32C checksumming for data writes (default).
|
||||
* crc - Enable CRC32C checksumming for msgr1 on-the-wire protocol (default).
|
||||
For msgr2.1 protocol this option is ignored: full checksumming is always on
|
||||
in 'crc' mode and always off in 'secure' mode.
|
||||
|
||||
* nocrc - Disable CRC32C checksumming for data writes.
|
||||
* nocrc - Disable CRC32C checksumming for msgr1 on-the-wire protocol. Note
|
||||
that only payload checksumming is disabled, header checksumming is always on.
|
||||
For msgr2.1 protocol this option is ignored.
|
||||
|
||||
* cephx_require_signatures - Require cephx message signing (since 3.19,
|
||||
default).
|
||||
* cephx_require_signatures - Require msgr1 message signing feature (since 3.19,
|
||||
default). This option is deprecated and will be removed in the future as the
|
||||
feature has been supported since the Bobtail release.
|
||||
|
||||
* nocephx_require_signatures - Don't require cephx message signing (since
|
||||
3.19).
|
||||
* nocephx_require_signatures - Don't require msgr1 message signing feature
|
||||
(since 3.19). This option is deprecated and will be removed in the future.
|
||||
|
||||
* tcp_nodelay - Disable Nagle's algorithm on client sockets (since 4.0,
|
||||
default).
|
||||
|
||||
* notcp_nodelay - Enable Nagle's algorithm on client sockets (since 4.0).
|
||||
|
||||
* cephx_sign_messages - Enable message signing (since 4.4, default).
|
||||
* cephx_sign_messages - Enable message signing for msgr1 on-the-wire protocol
|
||||
(since 4.4, default). For msgr2.1 protocol this option is ignored: message
|
||||
signing is built into 'secure' mode and not offered in 'crc' mode.
|
||||
|
||||
* nocephx_sign_messages - Disable message signing (since 4.4).
|
||||
* nocephx_sign_messages - Disable message signing for msgr1 on-the-wire protocol
|
||||
(since 4.4). For msgr2.1 protocol this option is ignored.
|
||||
|
||||
* mount_timeout=x - A timeout on various steps in `rbd device map` and
|
||||
`rbd device unmap` sequences (default is 60 seconds). In particular,
|
||||
@ -844,6 +852,25 @@ Per mapping (block device) `rbd device map` options:
|
||||
backend that the data is incompressible, disabling compression in aggressive
|
||||
mode (since 5.8).
|
||||
|
||||
* ms_mode=legacy - Use msgr1 on-the-wire protocol (since 5.11, default).
|
||||
|
||||
* ms_mode=crc - Use msgr2.1 on-the-wire protocol, select 'crc' mode, also
|
||||
referred to as plain mode (since 5.11). If the daemon denies 'crc' mode,
|
||||
fail the connection.
|
||||
|
||||
* ms_mode=secure - Use msgr2.1 on-the-wire protocol, select 'secure' mode
|
||||
(since 5.11). 'secure' mode provides full in-transit encryption ensuring
|
||||
both confidentiality and authenticity. If the daemon denies 'secure' mode,
|
||||
fail the connection.
|
||||
|
||||
* ms_mode=prefer-crc - Use msgr2.1 on-the-wire protocol, select 'crc'
|
||||
mode (since 5.11). If the daemon denies 'crc' mode in favor of 'secure'
|
||||
mode, agree to 'secure' mode.
|
||||
|
||||
* ms_mode=prefer-secure - Use msgr2.1 on-the-wire protocol, select 'secure'
|
||||
mode (since 5.11). If the daemon denies 'secure' mode in favor of 'crc'
|
||||
mode, agree to 'crc' mode.
|
||||
|
||||
* udev - Wait for udev device manager to finish executing all matching
|
||||
"add" rules and release the device before exiting (default). This option
|
||||
is not passed to the kernel.
|
||||
|
||||
@ -270,6 +270,34 @@ commands::
|
||||
|
||||
$ ceph dashboard ac-user-create <username> <password> administrator
|
||||
|
||||
Account Lock-out
|
||||
^^^^^^^^^^^^^^^^
|
||||
|
||||
It disables a user account if a user repeatedly enters the wrong credentials
|
||||
for multiple times. It is enabled by default to prevent brute-force or dictionary
|
||||
attacks. The user can get or set the default number of lock-out attempts using
|
||||
these commands respectively::
|
||||
|
||||
$ ceph dashboard get-account-lockout-attempts
|
||||
$ ceph dashboard set-account-lockout-attempts <value:int>
|
||||
|
||||
.. warning::
|
||||
|
||||
This feature can be disabled by setting the default number of lock-out attempts to 0.
|
||||
However, by disabling this feature, the account is more vulnerable to brute-force or
|
||||
dictionary based attacks. This can be disabled by::
|
||||
|
||||
$ ceph dashboard set-account-lockout-attempts 0
|
||||
|
||||
Enable a Locked User
|
||||
^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
If a user account is disabled as a result of multiple invalid login attempts, then
|
||||
it needs to be manually enabled by the administrator. This can be done by the following
|
||||
command::
|
||||
|
||||
$ ceph dashboard ac-user-enable <username>
|
||||
|
||||
Accessing the Dashboard
|
||||
^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
@ -479,7 +507,8 @@ will not be visible in Prometheus.
|
||||
After you have set up Grafana and Prometheus, you will need to configure the
|
||||
connection information that the Ceph Dashboard will use to access Grafana.
|
||||
|
||||
You need to tell the dashboard on which url Grafana instance is running/deployed::
|
||||
You need to tell the dashboard on which URL the Grafana instance is
|
||||
running/deployed::
|
||||
|
||||
$ ceph dashboard set-grafana-api-url <grafana-server-url> # default: ''
|
||||
|
||||
@ -503,6 +532,38 @@ e.g. caused by certificates signed by unknown CA or not matching the host name::
|
||||
|
||||
You can directly access Grafana Instance as well to monitor your cluster.
|
||||
|
||||
Alternative URL for Browsers
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
The Ceph Dashboard backend requires the Grafana URL to be able to verify the
|
||||
existence of Grafana Dashboards before the frontend even loads them. Due to the
|
||||
nature of how Grafana is implemented in Ceph Dashboard, this means that two
|
||||
working connections are required in order to be able to see Grafana graphs in
|
||||
Ceph Dashboard:
|
||||
|
||||
- The backend (Ceph Mgr module) needs to verify the existence of the requested
|
||||
graph. If this request succeeds, it lets the frontend know that it can safely
|
||||
access Grafana.
|
||||
- The frontend then requests the Grafana graphs directly from the user's
|
||||
browser using an iframe. The Grafana instance is accessed directly without any
|
||||
detour through Ceph Dashboard.
|
||||
|
||||
Now, it might be the case that your environment makes it difficult for the
|
||||
user's browser to directly access the URL configured in Ceph Dashboard. To solve
|
||||
this issue, a separate URL can be configured which will solely be used to tell
|
||||
the frontend (the user's browser) which URL it should use to access Grafana.
|
||||
This setting won't ever be changed automatically, unlike the GRAFANA_API_URL
|
||||
which is set by :ref:`cephadm` (only if cephadm is used to deploy monitoring
|
||||
services).
|
||||
|
||||
To change the URL that is returned to the frontend issue the following command::
|
||||
|
||||
$ ceph dashboard set-grafana-frontend-api-url <grafana-server-url>
|
||||
|
||||
If no value is set for that option, it will simply fall back to the value of the
|
||||
GRAFANA_API_URL option. If set, it will instruct the browser to use this URL to
|
||||
access Grafana.
|
||||
|
||||
.. _dashboard-sso-support:
|
||||
|
||||
Enabling Single Sign-On (SSO)
|
||||
|
||||
@ -58,6 +58,8 @@ Status
|
||||
Show current orchestrator mode and high-level status (whether the orchestrator
|
||||
plugin is available and operational)
|
||||
|
||||
.. _orchestrator-cli-host-management:
|
||||
|
||||
Host Management
|
||||
===============
|
||||
|
||||
@ -70,7 +72,7 @@ Add and remove hosts::
|
||||
ceph orch host add <hostname> [<addr>] [<labels>...]
|
||||
ceph orch host rm <hostname>
|
||||
|
||||
For cephadm, see also :ref:`cephadm-fqdn`.
|
||||
For cephadm, see also :ref:`cephadm-fqdn` and :ref:`cephadm-removing-hosts`.
|
||||
|
||||
Host Specification
|
||||
------------------
|
||||
|
||||
@ -1127,7 +1127,7 @@ Miscellaneous
|
||||
when osd data is on HDD and osd journal is on SSD.
|
||||
|
||||
:Type: Float
|
||||
:Default: ``2``
|
||||
:Default: ``1``
|
||||
|
||||
|
||||
``osd command max records``
|
||||
|
||||
@ -88,7 +88,7 @@ Where:
|
||||
|
||||
:Description: Number of OSDs requested to send data during recovery of
|
||||
a single chunk. *d* needs to be chosen such that
|
||||
k+1 <= d <= k+m-1. Larger the *d*, the better the savings.
|
||||
k+1 <= d <= k+m-1. The larger the *d*, the better the savings.
|
||||
|
||||
:Type: Integer
|
||||
:Required: No.
|
||||
|
||||
@ -1175,3 +1175,16 @@ This warning can silenced by setting the
|
||||
``mon_warn_on_osd_down_out_interval_zero`` to false::
|
||||
|
||||
ceph config global mon mon_warn_on_osd_down_out_interval_zero false
|
||||
|
||||
DASHBOARD_DEBUG
|
||||
_______________
|
||||
|
||||
The Dashboard debug mode is enabled. This means, if there is an error
|
||||
while processing a REST API request, the HTTP error response contains
|
||||
a Python traceback. This behaviour should be disabled in production
|
||||
environments because such a traceback might contain and expose sensible
|
||||
information.
|
||||
|
||||
The debug mode can be disabled with::
|
||||
|
||||
ceph dashboard debug disable
|
||||
|
||||
@ -365,7 +365,8 @@ else
|
||||
--enable rhel-7-server-devtools-rpms
|
||||
dts_ver=8
|
||||
elif test $ID = centos -a $MAJOR_VERSION = 8 ; then
|
||||
$SUDO dnf config-manager --set-enabled PowerTools
|
||||
# Enable 'powertools' or 'PowerTools' repo
|
||||
$SUDO dnf config-manager --set-enabled $(dnf repolist --all 2>/dev/null|gawk 'tolower($0) ~ /^powertools\s/{print $1}')
|
||||
# before EPEL8 and PowerTools provide all dependencies, we use sepia for the dependencies
|
||||
$SUDO dnf config-manager --add-repo http://apt-mirror.front.sepia.ceph.com/lab-extras/8/
|
||||
$SUDO dnf config-manager --setopt=apt-mirror.front.sepia.ceph.com_lab-extras_8_.gpgcheck=0 --save
|
||||
|
||||
@ -126,7 +126,7 @@
|
||||
"label": "Read (-) / Write (+)",
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": "0",
|
||||
"min": null,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
|
||||
@ -230,8 +230,8 @@ groups:
|
||||
- alert: pool filling up
|
||||
expr: |
|
||||
(
|
||||
predict_linear(ceph_pool_stored[2d], 3600 * 24 * 5) >=
|
||||
ceph_pool_max_avail
|
||||
predict_linear(ceph_pool_stored[2d], 3600 * 24 * 5)
|
||||
>= ceph_pool_stored + ceph_pool_max_avail
|
||||
) * on(pool_id) group_left(name) ceph_pool_metadata
|
||||
labels:
|
||||
severity: warning
|
||||
@ -241,3 +241,15 @@ groups:
|
||||
description: >
|
||||
Pool {{ $labels.name }} will be full in less than 5 days
|
||||
assuming the average fill-up rate of the past 48 hours.
|
||||
|
||||
- name: healthchecks
|
||||
rules:
|
||||
- alert: Slow OSD Ops
|
||||
expr: ceph_healthcheck_slow_ops > 0
|
||||
for: 30s
|
||||
labels:
|
||||
severity: warning
|
||||
type: ceph_default
|
||||
annotations:
|
||||
description: >
|
||||
{{ $value }} OSD requests are taking too long to process (osd_op_complaint_time exceeded)
|
||||
|
||||
@ -9,4 +9,4 @@ tasks:
|
||||
- echo "deb https://download.opensuse.org/repositories/devel:/kubic:/libcontainers:/stable/xUbuntu_18.04/ /" | sudo tee /etc/apt/sources.list.d/devel:kubic:libcontainers:stable.list
|
||||
- sudo apt update
|
||||
- sudo apt -y install podman
|
||||
- echo -e "[registries.search]\nregistries = ['docker.io']" | sudo tee /etc/containers/registries.conf
|
||||
- echo -e "[[registry]]\nlocation = 'docker.io'\n\n[[registry.mirror]]\nlocation='docker-mirror.front.sepia.ceph.com:5000'\n" | sudo tee /etc/containers/registries.conf
|
||||
|
||||
@ -222,6 +222,17 @@ function TEST_profile_k_sanity() {
|
||||
m=1 || return 1
|
||||
}
|
||||
|
||||
function TEST_invalid_crush_failure_domain() {
|
||||
local dir=$1
|
||||
|
||||
run_mon $dir a || return 1
|
||||
|
||||
local profile=ec_profile
|
||||
local crush_failure_domain=invalid_failure_domain
|
||||
|
||||
! ceph osd erasure-code-profile set $profile k=4 m=2 crush-failure-domain=$crush_failure_domain 2>&1 || return 1
|
||||
}
|
||||
|
||||
main osd-erasure-code-profile "$@"
|
||||
|
||||
# Local Variables:
|
||||
|
||||
@ -15,5 +15,6 @@ overrides:
|
||||
|
||||
tasks:
|
||||
- cephfs_test_runner:
|
||||
fail_on_skip: false
|
||||
modules:
|
||||
- tasks.cephfs.test_volumes
|
||||
|
||||
1
ceph/qa/suites/krbd/basic/ms_mode/.qa
Symbolic link
1
ceph/qa/suites/krbd/basic/ms_mode/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
5
ceph/qa/suites/krbd/basic/ms_mode/crc.yaml
Normal file
5
ceph/qa/suites/krbd/basic/ms_mode/crc.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=crc
|
||||
5
ceph/qa/suites/krbd/basic/ms_mode/legacy.yaml
Normal file
5
ceph/qa/suites/krbd/basic/ms_mode/legacy.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=legacy
|
||||
5
ceph/qa/suites/krbd/basic/ms_mode/secure.yaml
Normal file
5
ceph/qa/suites/krbd/basic/ms_mode/secure.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=secure
|
||||
@ -3,5 +3,3 @@ overrides:
|
||||
conf:
|
||||
global:
|
||||
ms die on skipped message: false
|
||||
client:
|
||||
rbd default map options: read_from_replica=balance
|
||||
|
||||
1
ceph/qa/suites/krbd/fsx/ms_mode$/.qa
Symbolic link
1
ceph/qa/suites/krbd/fsx/ms_mode$/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
5
ceph/qa/suites/krbd/fsx/ms_mode$/crc.yaml
Normal file
5
ceph/qa/suites/krbd/fsx/ms_mode$/crc.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=crc,read_from_replica=balance
|
||||
5
ceph/qa/suites/krbd/fsx/ms_mode$/legacy.yaml
Normal file
5
ceph/qa/suites/krbd/fsx/ms_mode$/legacy.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=legacy,read_from_replica=balance
|
||||
5
ceph/qa/suites/krbd/fsx/ms_mode$/prefer-crc.yaml
Normal file
5
ceph/qa/suites/krbd/fsx/ms_mode$/prefer-crc.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=prefer-crc,read_from_replica=balance
|
||||
5
ceph/qa/suites/krbd/fsx/ms_mode$/secure.yaml
Normal file
5
ceph/qa/suites/krbd/fsx/ms_mode$/secure.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=secure,read_from_replica=balance
|
||||
1
ceph/qa/suites/krbd/rbd-nomount/ms_mode/.qa
Symbolic link
1
ceph/qa/suites/krbd/rbd-nomount/ms_mode/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
5
ceph/qa/suites/krbd/rbd-nomount/ms_mode/crc.yaml
Normal file
5
ceph/qa/suites/krbd/rbd-nomount/ms_mode/crc.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=crc
|
||||
5
ceph/qa/suites/krbd/rbd-nomount/ms_mode/legacy.yaml
Normal file
5
ceph/qa/suites/krbd/rbd-nomount/ms_mode/legacy.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=legacy
|
||||
5
ceph/qa/suites/krbd/rbd-nomount/ms_mode/secure.yaml
Normal file
5
ceph/qa/suites/krbd/rbd-nomount/ms_mode/secure.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=secure
|
||||
1
ceph/qa/suites/krbd/rbd/ms_mode/.qa
Symbolic link
1
ceph/qa/suites/krbd/rbd/ms_mode/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
5
ceph/qa/suites/krbd/rbd/ms_mode/crc.yaml
Normal file
5
ceph/qa/suites/krbd/rbd/ms_mode/crc.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=crc
|
||||
5
ceph/qa/suites/krbd/rbd/ms_mode/legacy.yaml
Normal file
5
ceph/qa/suites/krbd/rbd/ms_mode/legacy.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=legacy
|
||||
5
ceph/qa/suites/krbd/rbd/ms_mode/secure.yaml
Normal file
5
ceph/qa/suites/krbd/rbd/ms_mode/secure.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=secure
|
||||
1
ceph/qa/suites/krbd/singleton/ms_mode$/.qa
Symbolic link
1
ceph/qa/suites/krbd/singleton/ms_mode$/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
5
ceph/qa/suites/krbd/singleton/ms_mode$/crc.yaml
Normal file
5
ceph/qa/suites/krbd/singleton/ms_mode$/crc.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=crc
|
||||
5
ceph/qa/suites/krbd/singleton/ms_mode$/legacy.yaml
Normal file
5
ceph/qa/suites/krbd/singleton/ms_mode$/legacy.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=legacy
|
||||
5
ceph/qa/suites/krbd/singleton/ms_mode$/prefer-crc.yaml
Normal file
5
ceph/qa/suites/krbd/singleton/ms_mode$/prefer-crc.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=prefer-crc
|
||||
5
ceph/qa/suites/krbd/singleton/ms_mode$/secure.yaml
Normal file
5
ceph/qa/suites/krbd/singleton/ms_mode$/secure.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=secure
|
||||
1
ceph/qa/suites/krbd/thrash/ms_mode$/.qa
Symbolic link
1
ceph/qa/suites/krbd/thrash/ms_mode$/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
5
ceph/qa/suites/krbd/thrash/ms_mode$/crc.yaml
Normal file
5
ceph/qa/suites/krbd/thrash/ms_mode$/crc.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=crc
|
||||
5
ceph/qa/suites/krbd/thrash/ms_mode$/legacy.yaml
Normal file
5
ceph/qa/suites/krbd/thrash/ms_mode$/legacy.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=legacy
|
||||
5
ceph/qa/suites/krbd/thrash/ms_mode$/prefer-crc.yaml
Normal file
5
ceph/qa/suites/krbd/thrash/ms_mode$/prefer-crc.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=prefer-crc
|
||||
5
ceph/qa/suites/krbd/thrash/ms_mode$/secure.yaml
Normal file
5
ceph/qa/suites/krbd/thrash/ms_mode$/secure.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
rbd default map options: ms_mode=secure
|
||||
@ -1,5 +0,0 @@
|
||||
tasks:
|
||||
- workunit:
|
||||
clients:
|
||||
all:
|
||||
- rbd/krbd_stable_pages_required.sh
|
||||
5
ceph/qa/suites/krbd/wac/sysfs/tasks/stable_writes.yaml
Normal file
5
ceph/qa/suites/krbd/wac/sysfs/tasks/stable_writes.yaml
Normal file
@ -0,0 +1,5 @@
|
||||
tasks:
|
||||
- workunit:
|
||||
clients:
|
||||
all:
|
||||
- rbd/krbd_stable_writes.sh
|
||||
@ -11,3 +11,4 @@ tasks:
|
||||
- ceph orch ls
|
||||
- ceph orch host ls
|
||||
- ceph orch device ls
|
||||
- ceph orch ls --format yaml
|
||||
|
||||
@ -22,6 +22,7 @@ tasks:
|
||||
- \(OSD_HOST_DOWN\)
|
||||
- \(POOL_APP_NOT_ENABLED\)
|
||||
- \(OSDMAP_FLAGS\)
|
||||
- \(OSD_FLAGS\)
|
||||
- pauserd,pausewr flag\(s\) set
|
||||
- Monitor daemon marked osd\.[[:digit:]]+ down, but it is still running
|
||||
- evicting unresponsive client .+
|
||||
|
||||
@ -0,0 +1,44 @@
|
||||
roles:
|
||||
- - mon.a
|
||||
- mgr.x
|
||||
- osd.0
|
||||
- osd.1
|
||||
- osd.2
|
||||
- osd.3
|
||||
- client.0
|
||||
- - mon.b
|
||||
- mon.c
|
||||
- osd.4
|
||||
- osd.5
|
||||
- osd.6
|
||||
- osd.7
|
||||
openstack:
|
||||
- volumes: # attached to each instance
|
||||
count: 4
|
||||
size: 10 # GB
|
||||
tasks:
|
||||
- install:
|
||||
- ceph:
|
||||
create_rbd_pool: false
|
||||
pre-mgr-commands:
|
||||
- sudo ceph config set mgr mgr/devicehealth/enable_monitoring false --force
|
||||
log-ignorelist:
|
||||
- overall HEALTH_
|
||||
- \(OSDMAP_FLAGS\)
|
||||
- \(OSD_
|
||||
- \(PG_
|
||||
- \(POOL_
|
||||
- \(CACHE_POOL_
|
||||
- \(OBJECT_
|
||||
- \(SLOW_OPS\)
|
||||
- \(REQUEST_SLOW\)
|
||||
- \(TOO_FEW_PGS\)
|
||||
- slow request
|
||||
- exec:
|
||||
client.0:
|
||||
- ceph progress off
|
||||
|
||||
- workunit:
|
||||
clients:
|
||||
all:
|
||||
- mon/pg_autoscaler.sh
|
||||
@ -13,5 +13,6 @@ overrides:
|
||||
rgw curl low speed time: 300
|
||||
rgw md log max shards: 4
|
||||
rgw data log num shards: 4
|
||||
rgw sync obj etag verify: true
|
||||
rgw:
|
||||
compression type: random
|
||||
|
||||
@ -4,6 +4,7 @@ overrides:
|
||||
- \(MON_DOWN\)
|
||||
- \(MGR_DOWN\)
|
||||
- slow request
|
||||
- evicting unresponsive client
|
||||
meta:
|
||||
- desc: install ceph/nautilus latest
|
||||
tasks:
|
||||
|
||||
@ -26,6 +26,7 @@ tasks:
|
||||
- Monitor daemon marked osd
|
||||
- Behind on trimming
|
||||
- Manager daemon
|
||||
- evicting unresponsive client
|
||||
conf:
|
||||
global:
|
||||
mon warn on pool no app: false
|
||||
|
||||
@ -14,6 +14,8 @@ tasks:
|
||||
bluestore_warn_on_legacy_statfs: false
|
||||
bluestore warn on no per pool omap: false
|
||||
mon pg warn min per osd: 0
|
||||
log-whitelist:
|
||||
- evicting unresponsive client
|
||||
- exec:
|
||||
osd.0:
|
||||
- ceph osd require-osd-release nautilus
|
||||
|
||||
@ -155,13 +155,12 @@ def ceph_log(ctx, config):
|
||||
while not self.stop_event.is_set():
|
||||
self.stop_event.wait(timeout=30)
|
||||
try:
|
||||
run.wait(
|
||||
ctx.cluster.run(
|
||||
args=['sudo', 'logrotate', '/etc/logrotate.d/ceph-test.conf'
|
||||
],
|
||||
wait=False,
|
||||
)
|
||||
procs = ctx.cluster.run(
|
||||
args=['sudo', 'logrotate', '/etc/logrotate.d/ceph-test.conf'],
|
||||
wait=False,
|
||||
stderr=StringIO()
|
||||
)
|
||||
run.wait(procs)
|
||||
except exceptions.ConnectionLostError as e:
|
||||
# Some tests may power off nodes during test, in which
|
||||
# case we will see connection errors that we should ignore.
|
||||
@ -175,6 +174,14 @@ def ceph_log(ctx, config):
|
||||
log.debug("Missed logrotate, EOFError")
|
||||
except SSHException:
|
||||
log.debug("Missed logrotate, SSHException")
|
||||
except run.CommandFailedError as e:
|
||||
for p in procs:
|
||||
if p.finished and p.exitstatus != 0:
|
||||
err = p.stderr.getvalue()
|
||||
if 'error: error renaming temp state file' in err:
|
||||
log.info('ignoring transient state error: %s', e)
|
||||
else:
|
||||
raise
|
||||
except socket.error as e:
|
||||
if e.errno in (errno.EHOSTUNREACH, errno.ECONNRESET):
|
||||
log.debug("Missed logrotate, host unreachable")
|
||||
|
||||
@ -1317,13 +1317,17 @@ def registries_add_mirror_to_docker_io(conf, mirror):
|
||||
}
|
||||
else:
|
||||
v2 = config # type: ignore
|
||||
dockers = [r for r in v2['registry'] if r['prefix'] == 'docker.io']
|
||||
dockers = [
|
||||
r for r in v2['registry'] if
|
||||
r.get('prefix') == 'docker.io' or r.get('location') == 'docker.io'
|
||||
]
|
||||
if dockers:
|
||||
docker = dockers[0]
|
||||
docker['mirror'] = [{
|
||||
"location": mirror,
|
||||
"insecure": True,
|
||||
}]
|
||||
if 'mirror' not in docker:
|
||||
docker['mirror'] = [{
|
||||
"location": mirror,
|
||||
"insecure": True,
|
||||
}]
|
||||
return v2
|
||||
|
||||
|
||||
|
||||
@ -227,6 +227,9 @@ class CephFSTestCase(CephTestCase):
|
||||
def _session_by_id(self, session_ls):
|
||||
return dict([(s['id'], s) for s in session_ls])
|
||||
|
||||
def perf_dump(self, rank=None, status=None):
|
||||
return self.fs.rank_asok(['perf', 'dump'], rank=rank, status=status)
|
||||
|
||||
def wait_until_evicted(self, client_id, timeout=30):
|
||||
def is_client_evicted():
|
||||
ls = self._session_list()
|
||||
|
||||
@ -201,7 +201,7 @@ class CephFSMount(object):
|
||||
return self.run_shell(["bash", "-c", Raw(f"'{payload}'")], **kwargs)
|
||||
|
||||
def run_shell(self, args, wait=True, stdin=None, check_status=True,
|
||||
omit_sudo=True):
|
||||
omit_sudo=True, timeout=10800):
|
||||
if isinstance(args, str):
|
||||
args = args.split()
|
||||
|
||||
@ -209,7 +209,8 @@ class CephFSMount(object):
|
||||
return self.client_remote.run(args=args, stdout=StringIO(),
|
||||
stderr=StringIO(), wait=wait,
|
||||
stdin=stdin, check_status=check_status,
|
||||
omit_sudo=omit_sudo)
|
||||
omit_sudo=omit_sudo,
|
||||
timeout=timeout)
|
||||
|
||||
def open_no_data(self, basename):
|
||||
"""
|
||||
|
||||
@ -156,6 +156,36 @@ class TestClientLimits(CephFSTestCase):
|
||||
else:
|
||||
raise RuntimeError("expected no client recall warning")
|
||||
|
||||
def test_cap_acquisition_throttle_readdir(self):
|
||||
"""
|
||||
Mostly readdir acquires caps faster than the mds recalls, so the cap
|
||||
acquisition via readdir is throttled by retrying the readdir after
|
||||
a fraction of second (0.5) by default when throttling condition is met.
|
||||
"""
|
||||
|
||||
max_caps_per_client = 500
|
||||
cap_acquisition_throttle = 250
|
||||
|
||||
self.config_set('mds', 'mds_max_caps_per_client', max_caps_per_client)
|
||||
self.config_set('mds', 'mds_session_cap_acquisition_throttle', cap_acquisition_throttle)
|
||||
|
||||
# Create 1500 files split across 6 directories, 250 each.
|
||||
for i in range(1, 7):
|
||||
self.mount_a.create_n_files("dir{0}/file".format(i), cap_acquisition_throttle, sync=True)
|
||||
|
||||
mount_a_client_id = self.mount_a.get_global_id()
|
||||
|
||||
# recursive readdir
|
||||
self.mount_a.run_shell_payload("find | wc")
|
||||
|
||||
# validate cap_acquisition decay counter after readdir to exceed throttle count i.e 250
|
||||
cap_acquisition_value = self.get_session(mount_a_client_id)['cap_acquisition']['value']
|
||||
self.assertGreaterEqual(cap_acquisition_value, cap_acquisition_throttle)
|
||||
|
||||
# validate the throttle condition to be hit atleast once
|
||||
cap_acquisition_throttle_hit_count = self.perf_dump()['mds_server']['cap_acquisition_throttle']
|
||||
self.assertGreaterEqual(cap_acquisition_throttle_hit_count, 1)
|
||||
|
||||
def test_client_release_bug(self):
|
||||
"""
|
||||
When a client has a bug (which we will simulate) preventing it from releasing caps,
|
||||
|
||||
@ -425,12 +425,14 @@ class TestNFS(MgrTestCase):
|
||||
'''
|
||||
self._test_create_cluster()
|
||||
info_output = json.loads(self._nfs_cmd('cluster', 'info', self.cluster_id))
|
||||
info_ip = info_output[self.cluster_id][0].pop("ip")
|
||||
host_details = {self.cluster_id: [{
|
||||
"hostname": self._sys_cmd(['hostname']).decode("utf-8").strip(),
|
||||
"ip": list(set(self._sys_cmd(['hostname', '-I']).decode("utf-8").split())),
|
||||
"port": 2049
|
||||
}]}
|
||||
host_ip = self._sys_cmd(['hostname', '-I']).decode("utf-8").split()
|
||||
self.assertDictEqual(info_output, host_details)
|
||||
self.assertTrue(any([ip in info_ip for ip in host_ip]))
|
||||
self._test_delete_cluster()
|
||||
|
||||
def test_cluster_set_reset_user_config(self):
|
||||
|
||||
@ -856,7 +856,7 @@ vc.disconnect()
|
||||
volume_id = "volumeid"
|
||||
|
||||
# Create auth_id
|
||||
out = self.fs.mon_manager.raw_cluster_cmd(
|
||||
self.fs.mon_manager.raw_cluster_cmd(
|
||||
"auth", "get-or-create", "client.guest1",
|
||||
"mds", "allow *",
|
||||
"osd", "allow rw",
|
||||
@ -918,7 +918,7 @@ vc.disconnect()
|
||||
volume_id = "volumeid"
|
||||
|
||||
# Create auth_id
|
||||
out = self.fs.mon_manager.raw_cluster_cmd(
|
||||
self.fs.mon_manager.raw_cluster_cmd(
|
||||
"auth", "get-or-create", "client.guest1",
|
||||
"mds", "allow *",
|
||||
"osd", "allow rw",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -96,18 +96,19 @@ class DashboardTestCase(MgrTestCase):
|
||||
cls._ceph_cmd(set_roles_args)
|
||||
|
||||
@classmethod
|
||||
def login(cls, username, password):
|
||||
def login(cls, username, password, set_cookies=False):
|
||||
if cls._loggedin:
|
||||
cls.logout()
|
||||
cls._post('/api/auth', {'username': username, 'password': password})
|
||||
cls._post('/api/auth', {'username': username,
|
||||
'password': password}, set_cookies=set_cookies)
|
||||
cls._assertEq(cls._resp.status_code, 201)
|
||||
cls._token = cls.jsonBody()['token']
|
||||
cls._loggedin = True
|
||||
|
||||
@classmethod
|
||||
def logout(cls):
|
||||
def logout(cls, set_cookies=False):
|
||||
if cls._loggedin:
|
||||
cls._post('/api/auth/logout')
|
||||
cls._post('/api/auth/logout', set_cookies=set_cookies)
|
||||
cls._assertEq(cls._resp.status_code, 200)
|
||||
cls._token = None
|
||||
cls._loggedin = False
|
||||
@ -195,29 +196,49 @@ class DashboardTestCase(MgrTestCase):
|
||||
def tearDownClass(cls):
|
||||
super(DashboardTestCase, cls).tearDownClass()
|
||||
|
||||
# pylint: disable=inconsistent-return-statements
|
||||
# pylint: disable=inconsistent-return-statements, too-many-branches
|
||||
@classmethod
|
||||
def _request(cls, url, method, data=None, params=None):
|
||||
def _request(cls, url, method, data=None, params=None, set_cookies=False):
|
||||
url = "{}{}".format(cls._base_uri, url)
|
||||
log.info("Request %s to %s", method, url)
|
||||
headers = {}
|
||||
cookies = {}
|
||||
if cls._token:
|
||||
headers['Authorization'] = "Bearer {}".format(cls._token)
|
||||
if set_cookies:
|
||||
cookies['token'] = cls._token
|
||||
else:
|
||||
headers['Authorization'] = "Bearer {}".format(cls._token)
|
||||
|
||||
if method == 'GET':
|
||||
cls._resp = cls._session.get(url, params=params, verify=False,
|
||||
headers=headers)
|
||||
elif method == 'POST':
|
||||
cls._resp = cls._session.post(url, json=data, params=params,
|
||||
verify=False, headers=headers)
|
||||
elif method == 'DELETE':
|
||||
cls._resp = cls._session.delete(url, json=data, params=params,
|
||||
verify=False, headers=headers)
|
||||
elif method == 'PUT':
|
||||
cls._resp = cls._session.put(url, json=data, params=params,
|
||||
verify=False, headers=headers)
|
||||
if set_cookies:
|
||||
if method == 'GET':
|
||||
cls._resp = cls._session.get(url, params=params, verify=False,
|
||||
headers=headers, cookies=cookies)
|
||||
elif method == 'POST':
|
||||
cls._resp = cls._session.post(url, json=data, params=params,
|
||||
verify=False, headers=headers, cookies=cookies)
|
||||
elif method == 'DELETE':
|
||||
cls._resp = cls._session.delete(url, json=data, params=params,
|
||||
verify=False, headers=headers, cookies=cookies)
|
||||
elif method == 'PUT':
|
||||
cls._resp = cls._session.put(url, json=data, params=params,
|
||||
verify=False, headers=headers, cookies=cookies)
|
||||
else:
|
||||
assert False
|
||||
else:
|
||||
assert False
|
||||
if method == 'GET':
|
||||
cls._resp = cls._session.get(url, params=params, verify=False,
|
||||
headers=headers)
|
||||
elif method == 'POST':
|
||||
cls._resp = cls._session.post(url, json=data, params=params,
|
||||
verify=False, headers=headers)
|
||||
elif method == 'DELETE':
|
||||
cls._resp = cls._session.delete(url, json=data, params=params,
|
||||
verify=False, headers=headers)
|
||||
elif method == 'PUT':
|
||||
cls._resp = cls._session.put(url, json=data, params=params,
|
||||
verify=False, headers=headers)
|
||||
else:
|
||||
assert False
|
||||
try:
|
||||
if not cls._resp.ok:
|
||||
# Output response for easier debugging.
|
||||
@ -231,8 +252,8 @@ class DashboardTestCase(MgrTestCase):
|
||||
raise ex
|
||||
|
||||
@classmethod
|
||||
def _get(cls, url, params=None):
|
||||
return cls._request(url, 'GET', params=params)
|
||||
def _get(cls, url, params=None, set_cookies=False):
|
||||
return cls._request(url, 'GET', params=params, set_cookies=set_cookies)
|
||||
|
||||
@classmethod
|
||||
def _view_cache_get(cls, url, retries=5):
|
||||
@ -253,16 +274,16 @@ class DashboardTestCase(MgrTestCase):
|
||||
return res
|
||||
|
||||
@classmethod
|
||||
def _post(cls, url, data=None, params=None):
|
||||
cls._request(url, 'POST', data, params)
|
||||
def _post(cls, url, data=None, params=None, set_cookies=False):
|
||||
cls._request(url, 'POST', data, params, set_cookies=set_cookies)
|
||||
|
||||
@classmethod
|
||||
def _delete(cls, url, data=None, params=None):
|
||||
cls._request(url, 'DELETE', data, params)
|
||||
def _delete(cls, url, data=None, params=None, set_cookies=False):
|
||||
cls._request(url, 'DELETE', data, params, set_cookies=set_cookies)
|
||||
|
||||
@classmethod
|
||||
def _put(cls, url, data=None, params=None):
|
||||
cls._request(url, 'PUT', data, params)
|
||||
def _put(cls, url, data=None, params=None, set_cookies=False):
|
||||
cls._request(url, 'PUT', data, params, set_cookies=set_cookies)
|
||||
|
||||
@classmethod
|
||||
def _assertEq(cls, v1, v2):
|
||||
@ -281,8 +302,8 @@ class DashboardTestCase(MgrTestCase):
|
||||
|
||||
# pylint: disable=too-many-arguments
|
||||
@classmethod
|
||||
def _task_request(cls, method, url, data, timeout):
|
||||
res = cls._request(url, method, data)
|
||||
def _task_request(cls, method, url, data, timeout, set_cookies=False):
|
||||
res = cls._request(url, method, data, set_cookies=set_cookies)
|
||||
cls._assertIn(cls._resp.status_code, [200, 201, 202, 204, 400, 403, 404])
|
||||
|
||||
if cls._resp.status_code == 403:
|
||||
@ -334,16 +355,16 @@ class DashboardTestCase(MgrTestCase):
|
||||
return res_task['exception']
|
||||
|
||||
@classmethod
|
||||
def _task_post(cls, url, data=None, timeout=60):
|
||||
return cls._task_request('POST', url, data, timeout)
|
||||
def _task_post(cls, url, data=None, timeout=60, set_cookies=False):
|
||||
return cls._task_request('POST', url, data, timeout, set_cookies=set_cookies)
|
||||
|
||||
@classmethod
|
||||
def _task_delete(cls, url, timeout=60):
|
||||
return cls._task_request('DELETE', url, None, timeout)
|
||||
def _task_delete(cls, url, timeout=60, set_cookies=False):
|
||||
return cls._task_request('DELETE', url, None, timeout, set_cookies=set_cookies)
|
||||
|
||||
@classmethod
|
||||
def _task_put(cls, url, data=None, timeout=60):
|
||||
return cls._task_request('PUT', url, data, timeout)
|
||||
def _task_put(cls, url, data=None, timeout=60, set_cookies=False):
|
||||
return cls._task_request('PUT', url, data, timeout, set_cookies=set_cookies)
|
||||
|
||||
@classmethod
|
||||
def cookies(cls):
|
||||
|
||||
@ -30,6 +30,7 @@ class AuthTest(DashboardTestCase):
|
||||
self.assertIn('delete', perms)
|
||||
|
||||
def test_a_set_login_credentials(self):
|
||||
# test with Authorization header
|
||||
self.create_user('admin2', 'admin2', ['administrator'])
|
||||
self._post("/api/auth", {'username': 'admin2', 'password': 'admin2'})
|
||||
self.assertStatus(201)
|
||||
@ -37,7 +38,16 @@ class AuthTest(DashboardTestCase):
|
||||
self._validate_jwt_token(data['token'], "admin2", data['permissions'])
|
||||
self.delete_user('admin2')
|
||||
|
||||
# test with Cookies set
|
||||
self.create_user('admin2', 'admin2', ['administrator'])
|
||||
self._post("/api/auth", {'username': 'admin2', 'password': 'admin2'}, set_cookies=True)
|
||||
self.assertStatus(201)
|
||||
data = self.jsonBody()
|
||||
self._validate_jwt_token(data['token'], "admin2", data['permissions'])
|
||||
self.delete_user('admin2')
|
||||
|
||||
def test_login_valid(self):
|
||||
# test with Authorization header
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'})
|
||||
self.assertStatus(201)
|
||||
data = self.jsonBody()
|
||||
@ -51,7 +61,22 @@ class AuthTest(DashboardTestCase):
|
||||
}, allow_unknown=False))
|
||||
self._validate_jwt_token(data['token'], "admin", data['permissions'])
|
||||
|
||||
# test with Cookies set
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'}, set_cookies=True)
|
||||
self.assertStatus(201)
|
||||
data = self.jsonBody()
|
||||
self.assertSchema(data, JObj(sub_elems={
|
||||
'token': JLeaf(str),
|
||||
'username': JLeaf(str),
|
||||
'permissions': JObj(sub_elems={}, allow_unknown=True),
|
||||
'sso': JLeaf(bool),
|
||||
'pwdExpirationDate': JLeaf(int, none=True),
|
||||
'pwdUpdateRequired': JLeaf(bool)
|
||||
}, allow_unknown=False))
|
||||
self._validate_jwt_token(data['token'], "admin", data['permissions'])
|
||||
|
||||
def test_login_invalid(self):
|
||||
# test with Authorization header
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'inval'})
|
||||
self.assertStatus(400)
|
||||
self.assertJsonBody({
|
||||
@ -60,7 +85,17 @@ class AuthTest(DashboardTestCase):
|
||||
"detail": "Invalid credentials"
|
||||
})
|
||||
|
||||
# test with Cookies set
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'inval'}, set_cookies=True)
|
||||
self.assertStatus(400)
|
||||
self.assertJsonBody({
|
||||
"component": "auth",
|
||||
"code": "invalid_credentials",
|
||||
"detail": "Invalid credentials"
|
||||
})
|
||||
|
||||
def test_login_without_password(self):
|
||||
# test with Authorization header
|
||||
self.create_user('admin2', '', ['administrator'])
|
||||
self._post("/api/auth", {'username': 'admin2', 'password': ''})
|
||||
self.assertStatus(400)
|
||||
@ -71,7 +106,70 @@ class AuthTest(DashboardTestCase):
|
||||
})
|
||||
self.delete_user('admin2')
|
||||
|
||||
# test with Cookies set
|
||||
self.create_user('admin2', '', ['administrator'])
|
||||
self._post("/api/auth", {'username': 'admin2', 'password': ''}, set_cookies=True)
|
||||
self.assertStatus(400)
|
||||
self.assertJsonBody({
|
||||
"component": "auth",
|
||||
"code": "invalid_credentials",
|
||||
"detail": "Invalid credentials"
|
||||
})
|
||||
self.delete_user('admin2')
|
||||
|
||||
def test_lockout_user(self):
|
||||
# test with Authorization header
|
||||
self._ceph_cmd(['dashboard', 'set-account-lockout-attempts', '3'])
|
||||
for _ in range(3):
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'inval'})
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'})
|
||||
self.assertStatus(400)
|
||||
self.assertJsonBody({
|
||||
"component": "auth",
|
||||
"code": "invalid_credentials",
|
||||
"detail": "Invalid credentials"
|
||||
})
|
||||
self._ceph_cmd(['dashboard', 'ac-user-enable', 'admin'])
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'})
|
||||
self.assertStatus(201)
|
||||
data = self.jsonBody()
|
||||
self.assertSchema(data, JObj(sub_elems={
|
||||
'token': JLeaf(str),
|
||||
'username': JLeaf(str),
|
||||
'permissions': JObj(sub_elems={}, allow_unknown=True),
|
||||
'sso': JLeaf(bool),
|
||||
'pwdExpirationDate': JLeaf(int, none=True),
|
||||
'pwdUpdateRequired': JLeaf(bool)
|
||||
}, allow_unknown=False))
|
||||
self._validate_jwt_token(data['token'], "admin", data['permissions'])
|
||||
|
||||
# test with Cookies set
|
||||
self._ceph_cmd(['dashboard', 'set-account-lockout-attempts', '3'])
|
||||
for _ in range(3):
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'inval'}, set_cookies=True)
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'}, set_cookies=True)
|
||||
self.assertStatus(400)
|
||||
self.assertJsonBody({
|
||||
"component": "auth",
|
||||
"code": "invalid_credentials",
|
||||
"detail": "Invalid credentials"
|
||||
})
|
||||
self._ceph_cmd(['dashboard', 'ac-user-enable', 'admin'])
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'}, set_cookies=True)
|
||||
self.assertStatus(201)
|
||||
data = self.jsonBody()
|
||||
self.assertSchema(data, JObj(sub_elems={
|
||||
'token': JLeaf(str),
|
||||
'username': JLeaf(str),
|
||||
'permissions': JObj(sub_elems={}, allow_unknown=True),
|
||||
'sso': JLeaf(bool),
|
||||
'pwdExpirationDate': JLeaf(int, none=True),
|
||||
'pwdUpdateRequired': JLeaf(bool)
|
||||
}, allow_unknown=False))
|
||||
self._validate_jwt_token(data['token'], "admin", data['permissions'])
|
||||
|
||||
def test_logout(self):
|
||||
# test with Authorization header
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'})
|
||||
self.assertStatus(201)
|
||||
data = self.jsonBody()
|
||||
@ -86,7 +184,23 @@ class AuthTest(DashboardTestCase):
|
||||
self.assertStatus(401)
|
||||
self.set_jwt_token(None)
|
||||
|
||||
# test with Cookies set
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'}, set_cookies=True)
|
||||
self.assertStatus(201)
|
||||
data = self.jsonBody()
|
||||
self._validate_jwt_token(data['token'], "admin", data['permissions'])
|
||||
self.set_jwt_token(data['token'])
|
||||
self._post("/api/auth/logout", set_cookies=True)
|
||||
self.assertStatus(200)
|
||||
self.assertJsonBody({
|
||||
"redirect_url": "#/login"
|
||||
})
|
||||
self._get("/api/host", set_cookies=True)
|
||||
self.assertStatus(401)
|
||||
self.set_jwt_token(None)
|
||||
|
||||
def test_token_ttl(self):
|
||||
# test with Authorization header
|
||||
self._ceph_cmd(['dashboard', 'set-jwt-token-ttl', '5'])
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'})
|
||||
self.assertStatus(201)
|
||||
@ -99,7 +213,21 @@ class AuthTest(DashboardTestCase):
|
||||
self._ceph_cmd(['dashboard', 'set-jwt-token-ttl', '28800'])
|
||||
self.set_jwt_token(None)
|
||||
|
||||
# test with Cookies set
|
||||
self._ceph_cmd(['dashboard', 'set-jwt-token-ttl', '5'])
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'}, set_cookies=True)
|
||||
self.assertStatus(201)
|
||||
self.set_jwt_token(self.jsonBody()['token'])
|
||||
self._get("/api/host", set_cookies=True)
|
||||
self.assertStatus(200)
|
||||
time.sleep(6)
|
||||
self._get("/api/host", set_cookies=True)
|
||||
self.assertStatus(401)
|
||||
self._ceph_cmd(['dashboard', 'set-jwt-token-ttl', '28800'])
|
||||
self.set_jwt_token(None)
|
||||
|
||||
def test_remove_from_blacklist(self):
|
||||
# test with Authorization header
|
||||
self._ceph_cmd(['dashboard', 'set-jwt-token-ttl', '5'])
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'})
|
||||
self.assertStatus(201)
|
||||
@ -119,11 +247,37 @@ class AuthTest(DashboardTestCase):
|
||||
self._post("/api/auth/logout")
|
||||
self.assertStatus(200)
|
||||
|
||||
# test with Cookies set
|
||||
self._ceph_cmd(['dashboard', 'set-jwt-token-ttl', '5'])
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'}, set_cookies=True)
|
||||
self.assertStatus(201)
|
||||
self.set_jwt_token(self.jsonBody()['token'])
|
||||
# the following call adds the token to the blocklist
|
||||
self._post("/api/auth/logout", set_cookies=True)
|
||||
self.assertStatus(200)
|
||||
self._get("/api/host", set_cookies=True)
|
||||
self.assertStatus(401)
|
||||
time.sleep(6)
|
||||
self._ceph_cmd(['dashboard', 'set-jwt-token-ttl', '28800'])
|
||||
self.set_jwt_token(None)
|
||||
self._post("/api/auth", {'username': 'admin', 'password': 'admin'}, set_cookies=True)
|
||||
self.assertStatus(201)
|
||||
self.set_jwt_token(self.jsonBody()['token'])
|
||||
# the following call removes expired tokens from the blocklist
|
||||
self._post("/api/auth/logout", set_cookies=True)
|
||||
self.assertStatus(200)
|
||||
|
||||
def test_unauthorized(self):
|
||||
# test with Authorization header
|
||||
self._get("/api/host")
|
||||
self.assertStatus(401)
|
||||
|
||||
# test with Cookies set
|
||||
self._get("/api/host", set_cookies=True)
|
||||
self.assertStatus(401)
|
||||
|
||||
def test_invalidate_token_by_admin(self):
|
||||
# test with Authorization header
|
||||
self._get("/api/host")
|
||||
self.assertStatus(401)
|
||||
self.create_user('user', 'user', ['read-only'])
|
||||
@ -147,7 +301,32 @@ class AuthTest(DashboardTestCase):
|
||||
self.assertStatus(200)
|
||||
self.delete_user("user")
|
||||
|
||||
# test with Cookies set
|
||||
self._get("/api/host", set_cookies=True)
|
||||
self.assertStatus(401)
|
||||
self.create_user('user', 'user', ['read-only'])
|
||||
time.sleep(1)
|
||||
self._post("/api/auth", {'username': 'user', 'password': 'user'}, set_cookies=True)
|
||||
self.assertStatus(201)
|
||||
self.set_jwt_token(self.jsonBody()['token'])
|
||||
self._get("/api/host", set_cookies=True)
|
||||
self.assertStatus(200)
|
||||
time.sleep(1)
|
||||
self._ceph_cmd(['dashboard', 'ac-user-set-password', '--force-password',
|
||||
'user', 'user2'])
|
||||
time.sleep(1)
|
||||
self._get("/api/host", set_cookies=True)
|
||||
self.assertStatus(401)
|
||||
self.set_jwt_token(None)
|
||||
self._post("/api/auth", {'username': 'user', 'password': 'user2'}, set_cookies=True)
|
||||
self.assertStatus(201)
|
||||
self.set_jwt_token(self.jsonBody()['token'])
|
||||
self._get("/api/host", set_cookies=True)
|
||||
self.assertStatus(200)
|
||||
self.delete_user("user")
|
||||
|
||||
def test_check_token(self):
|
||||
# test with Authorization header
|
||||
self.login("admin", "admin")
|
||||
self._post("/api/auth/check", {"token": self.jsonBody()["token"]})
|
||||
self.assertStatus(200)
|
||||
@ -160,7 +339,21 @@ class AuthTest(DashboardTestCase):
|
||||
}, allow_unknown=False))
|
||||
self.logout()
|
||||
|
||||
# test with Cookies set
|
||||
self.login("admin", "admin", set_cookies=True)
|
||||
self._post("/api/auth/check", {"token": self.jsonBody()["token"]}, set_cookies=True)
|
||||
self.assertStatus(200)
|
||||
data = self.jsonBody()
|
||||
self.assertSchema(data, JObj(sub_elems={
|
||||
"username": JLeaf(str),
|
||||
"permissions": JObj(sub_elems={}, allow_unknown=True),
|
||||
"sso": JLeaf(bool),
|
||||
"pwdUpdateRequired": JLeaf(bool)
|
||||
}, allow_unknown=False))
|
||||
self.logout(set_cookies=True)
|
||||
|
||||
def test_check_wo_token(self):
|
||||
# test with Authorization header
|
||||
self.login("admin", "admin")
|
||||
self._post("/api/auth/check", {"token": ""})
|
||||
self.assertStatus(200)
|
||||
@ -169,3 +362,13 @@ class AuthTest(DashboardTestCase):
|
||||
"login_url": JLeaf(str)
|
||||
}, allow_unknown=False))
|
||||
self.logout()
|
||||
|
||||
# test with Cookies set
|
||||
self.login("admin", "admin", set_cookies=True)
|
||||
self._post("/api/auth/check", {"token": ""}, set_cookies=True)
|
||||
self.assertStatus(200)
|
||||
data = self.jsonBody()
|
||||
self.assertSchema(data, JObj(sub_elems={
|
||||
"login_url": JLeaf(str)
|
||||
}, allow_unknown=False))
|
||||
self.logout(set_cookies=True)
|
||||
|
||||
@ -237,36 +237,139 @@ class OsdTest(DashboardTestCase):
|
||||
class OsdFlagsTest(DashboardTestCase):
|
||||
def __init__(self, *args, **kwargs):
|
||||
super(OsdFlagsTest, self).__init__(*args, **kwargs)
|
||||
self._initial_flags = sorted( # These flags cannot be unset
|
||||
['sortbitwise', 'recovery_deletes', 'purged_snapdirs',
|
||||
'pglog_hardlimit'])
|
||||
self._initial_flags = ['sortbitwise', 'recovery_deletes', 'purged_snapdirs',
|
||||
'pglog_hardlimit'] # These flags cannot be unset
|
||||
|
||||
@classmethod
|
||||
def _get_cluster_osd_flags(cls):
|
||||
return sorted(
|
||||
json.loads(cls._ceph_cmd(['osd', 'dump',
|
||||
'--format=json']))['flags_set'])
|
||||
def _put_flags(cls, flags, ids=None):
|
||||
url = '/api/osd/flags'
|
||||
data = {'flags': flags}
|
||||
|
||||
@classmethod
|
||||
def _put_flags(cls, flags):
|
||||
cls._put('/api/osd/flags', data={'flags': flags})
|
||||
return sorted(cls._resp.json())
|
||||
if ids:
|
||||
url = url + '/individual'
|
||||
data['ids'] = ids
|
||||
|
||||
cls._put(url, data=data)
|
||||
return cls._resp.json()
|
||||
|
||||
def test_list_osd_flags(self):
|
||||
flags = self._get('/api/osd/flags')
|
||||
self.assertStatus(200)
|
||||
self.assertEqual(len(flags), 4)
|
||||
self.assertEqual(sorted(flags), self._initial_flags)
|
||||
self.assertCountEqual(flags, self._initial_flags)
|
||||
|
||||
def test_add_osd_flag(self):
|
||||
flags = self._put_flags([
|
||||
'sortbitwise', 'recovery_deletes', 'purged_snapdirs', 'noout',
|
||||
'pause', 'pglog_hardlimit'
|
||||
])
|
||||
self.assertEqual(flags, sorted([
|
||||
self.assertCountEqual(flags, [
|
||||
'sortbitwise', 'recovery_deletes', 'purged_snapdirs', 'noout',
|
||||
'pause', 'pglog_hardlimit'
|
||||
]))
|
||||
])
|
||||
|
||||
# Restore flags
|
||||
self._put_flags(self._initial_flags)
|
||||
|
||||
def test_get_indiv_flag(self):
|
||||
initial = self._get('/api/osd/flags/individual')
|
||||
self.assertStatus(200)
|
||||
self.assertSchema(initial, JList(JObj({
|
||||
'osd': int,
|
||||
'flags': JList(str)
|
||||
})))
|
||||
|
||||
self._ceph_cmd(['osd', 'set-group', 'noout,noin', 'osd.0', 'osd.1', 'osd.2'])
|
||||
flags_added = self._get('/api/osd/flags/individual')
|
||||
self.assertStatus(200)
|
||||
for osd in flags_added:
|
||||
if osd['osd'] in [0, 1, 2]:
|
||||
self.assertIn('noout', osd['flags'])
|
||||
self.assertIn('noin', osd['flags'])
|
||||
for osd_initial in initial:
|
||||
if osd['osd'] == osd_initial['osd']:
|
||||
self.assertGreater(len(osd['flags']), len(osd_initial['flags']))
|
||||
|
||||
self._ceph_cmd(['osd', 'unset-group', 'noout,noin', 'osd.0', 'osd.1', 'osd.2'])
|
||||
flags_removed = self._get('/api/osd/flags/individual')
|
||||
self.assertStatus(200)
|
||||
for osd in flags_removed:
|
||||
if osd['osd'] in [0, 1, 2]:
|
||||
self.assertNotIn('noout', osd['flags'])
|
||||
self.assertNotIn('noin', osd['flags'])
|
||||
|
||||
def test_add_indiv_flag(self):
|
||||
flags_update = {'noup': None, 'nodown': None, 'noin': None, 'noout': True}
|
||||
svc_id = 0
|
||||
|
||||
resp = self._put_flags(flags_update, [svc_id])
|
||||
self._check_indiv_flags_resp(resp, [svc_id], ['noout'], [], ['noup', 'nodown', 'noin'])
|
||||
self._check_indiv_flags_osd([svc_id], ['noout'], ['noup', 'nodown', 'noin'])
|
||||
|
||||
self._ceph_cmd(['osd', 'unset-group', 'noout', 'osd.{}'.format(svc_id)])
|
||||
|
||||
def test_add_multiple_indiv_flags(self):
|
||||
flags_update = {'noup': None, 'nodown': None, 'noin': True, 'noout': True}
|
||||
svc_id = 0
|
||||
|
||||
resp = self._put_flags(flags_update, [svc_id])
|
||||
self._check_indiv_flags_resp(resp, [svc_id], ['noout', 'noin'], [], ['noup', 'nodown'])
|
||||
self._check_indiv_flags_osd([svc_id], ['noout', 'noin'], ['noup', 'nodown'])
|
||||
|
||||
self._ceph_cmd(['osd', 'unset-group', 'noout,noin', 'osd.{}'.format(svc_id)])
|
||||
|
||||
def test_add_multiple_indiv_flags_multiple_osds(self):
|
||||
flags_update = {'noup': None, 'nodown': None, 'noin': True, 'noout': True}
|
||||
svc_id = [0, 1, 2]
|
||||
|
||||
resp = self._put_flags(flags_update, svc_id)
|
||||
self._check_indiv_flags_resp(resp, svc_id, ['noout', 'noin'], [], ['noup', 'nodown'])
|
||||
self._check_indiv_flags_osd([svc_id], ['noout', 'noin'], ['noup', 'nodown'])
|
||||
|
||||
self._ceph_cmd(['osd', 'unset-group', 'noout,noin', 'osd.0', 'osd.1', 'osd.2'])
|
||||
|
||||
def test_remove_indiv_flag(self):
|
||||
flags_update = {'noup': None, 'nodown': None, 'noin': None, 'noout': False}
|
||||
svc_id = 0
|
||||
self._ceph_cmd(['osd', 'set-group', 'noout', 'osd.{}'.format(svc_id)])
|
||||
|
||||
resp = self._put_flags(flags_update, [svc_id])
|
||||
self._check_indiv_flags_resp(resp, [svc_id], [], ['noout'], ['noup', 'nodown', 'noin'])
|
||||
self._check_indiv_flags_osd([svc_id], [], ['noup', 'nodown', 'noin', 'noout'])
|
||||
|
||||
def test_remove_multiple_indiv_flags(self):
|
||||
flags_update = {'noup': None, 'nodown': None, 'noin': False, 'noout': False}
|
||||
svc_id = 0
|
||||
self._ceph_cmd(['osd', 'set-group', 'noout,noin', 'osd.{}'.format(svc_id)])
|
||||
|
||||
resp = self._put_flags(flags_update, [svc_id])
|
||||
self._check_indiv_flags_resp(resp, [svc_id], [], ['noout', 'noin'], ['noup', 'nodown'])
|
||||
self._check_indiv_flags_osd([svc_id], [], ['noout', 'noin', 'noup', 'nodown'])
|
||||
|
||||
def test_remove_multiple_indiv_flags_multiple_osds(self):
|
||||
flags_update = {'noup': None, 'nodown': None, 'noin': False, 'noout': False}
|
||||
svc_id = [0, 1, 2]
|
||||
self._ceph_cmd(['osd', 'unset-group', 'noout,noin', 'osd.0', 'osd.1', 'osd.2'])
|
||||
|
||||
resp = self._put_flags(flags_update, svc_id)
|
||||
self._check_indiv_flags_resp(resp, svc_id, [], ['noout', 'noin'], ['noup', 'nodown'])
|
||||
self._check_indiv_flags_osd([svc_id], [], ['noout', 'noin', 'noup', 'nodown'])
|
||||
|
||||
def _check_indiv_flags_resp(self, resp, ids, added, removed, ignored):
|
||||
self.assertStatus(200)
|
||||
self.assertCountEqual(resp['ids'], ids)
|
||||
self.assertCountEqual(resp['added'], added)
|
||||
self.assertCountEqual(resp['removed'], removed)
|
||||
|
||||
for flag in ignored:
|
||||
self.assertNotIn(flag, resp['added'])
|
||||
self.assertNotIn(flag, resp['removed'])
|
||||
|
||||
def _check_indiv_flags_osd(self, ids, activated_flags, deactivated_flags):
|
||||
osds = json.loads(self._ceph_cmd(['osd', 'dump', '--format=json']))['osds']
|
||||
for osd in osds:
|
||||
if osd['osd'] in ids:
|
||||
for flag in activated_flags:
|
||||
self.assertIn(flag, osd['state'])
|
||||
for flag in deactivated_flags:
|
||||
self.assertNotIn(flag, osd['state'])
|
||||
|
||||
@ -1,6 +1,8 @@
|
||||
import json
|
||||
import logging
|
||||
|
||||
from unittest import SkipTest
|
||||
|
||||
from teuthology import misc
|
||||
from tasks.ceph_test_case import CephTestCase
|
||||
|
||||
@ -99,7 +101,7 @@ class MgrTestCase(CephTestCase):
|
||||
assert cls.mgr_cluster is not None
|
||||
|
||||
if len(cls.mgr_cluster.mgr_ids) < cls.MGRS_REQUIRED:
|
||||
cls.skipTest(
|
||||
raise SkipTest(
|
||||
"Only have {0} manager daemons, {1} are required".format(
|
||||
len(cls.mgr_cluster.mgr_ids), cls.MGRS_REQUIRED))
|
||||
|
||||
|
||||
@ -28,6 +28,16 @@ class TestDashboard(MgrTestCase):
|
||||
"mgr/dashboard/standby_error_status_code",
|
||||
"500")
|
||||
|
||||
def wait_until_webserver_available(self, url):
|
||||
def _check_connection():
|
||||
try:
|
||||
requests.get(url, allow_redirects=False, verify=False)
|
||||
return True
|
||||
except requests.ConnectionError:
|
||||
pass
|
||||
return False
|
||||
self.wait_until_true(_check_connection, timeout=30)
|
||||
|
||||
def test_standby(self):
|
||||
original_active_id = self.mgr_cluster.get_active_id()
|
||||
original_uri = self._get_uri("dashboard")
|
||||
@ -48,6 +58,9 @@ class TestDashboard(MgrTestCase):
|
||||
|
||||
self.assertNotEqual(original_uri, failed_over_uri)
|
||||
|
||||
# Wait until web server of the standby node is settled.
|
||||
self.wait_until_webserver_available(original_uri)
|
||||
|
||||
# The original active daemon should have come back up as a standby
|
||||
# and be doing redirects to the new active daemon.
|
||||
r = requests.get(original_uri, allow_redirects=False, verify=False)
|
||||
@ -55,7 +68,7 @@ class TestDashboard(MgrTestCase):
|
||||
self.assertEqual(r.headers['Location'], failed_over_uri)
|
||||
|
||||
# Ensure that every URL redirects to the active daemon.
|
||||
r = requests.get("{}/runtime.js".format(original_uri),
|
||||
r = requests.get("{}/runtime.js".format(original_uri.strip('/')),
|
||||
allow_redirects=False,
|
||||
verify=False)
|
||||
self.assertEqual(r.status_code, 303)
|
||||
@ -85,6 +98,9 @@ class TestDashboard(MgrTestCase):
|
||||
|
||||
self.assertNotEqual(original_uri, failed_over_uri)
|
||||
|
||||
# Wait until web server of the standby node is settled.
|
||||
self.wait_until_webserver_available(original_uri)
|
||||
|
||||
# Redirection should be disabled now, instead a 500 must be returned.
|
||||
r = requests.get(original_uri, allow_redirects=False, verify=False)
|
||||
self.assertEqual(r.status_code, 500)
|
||||
|
||||
@ -44,6 +44,88 @@ class TestProgress(MgrTestCase):
|
||||
log.info(json.dumps(p, indent=2))
|
||||
return p['events']
|
||||
|
||||
def _completed_events(self):
|
||||
"""
|
||||
This function returns all events that are completed
|
||||
"""
|
||||
p = self._get_progress()
|
||||
log.info(json.dumps(p, indent=2))
|
||||
return p['completed']
|
||||
|
||||
def is_osd_marked_out(self, ev):
|
||||
return ev['message'].endswith('marked out')
|
||||
|
||||
def is_osd_marked_in(self, ev):
|
||||
return ev['message'].endswith('marked in')
|
||||
|
||||
def _get_osd_in_out_events(self, marked='both'):
|
||||
"""
|
||||
Return the event that deals with OSDs being
|
||||
marked in, out or both
|
||||
"""
|
||||
|
||||
marked_in_events = []
|
||||
marked_out_events = []
|
||||
|
||||
events_in_progress = self._events_in_progress()
|
||||
for ev in events_in_progress:
|
||||
if self.is_osd_marked_out(ev):
|
||||
marked_out_events.append(ev)
|
||||
elif self.is_osd_marked_in(ev):
|
||||
marked_in_events.append(ev)
|
||||
|
||||
if marked == 'both':
|
||||
return [marked_in_events] + [marked_out_events]
|
||||
elif marked == 'in':
|
||||
return marked_in_events
|
||||
else:
|
||||
return marked_out_events
|
||||
|
||||
def _osd_in_out_events_count(self, marked='both'):
|
||||
"""
|
||||
Return the event that deals with OSDs being
|
||||
marked in, out or both
|
||||
"""
|
||||
|
||||
marked_in_events = []
|
||||
marked_out_events = []
|
||||
|
||||
events_in_progress = self._events_in_progress()
|
||||
for ev in events_in_progress:
|
||||
if self.is_osd_marked_out(ev):
|
||||
marked_out_events.append(ev)
|
||||
elif self.is_osd_marked_in(ev):
|
||||
marked_in_events.append(ev)
|
||||
|
||||
if marked == 'both':
|
||||
return [marked_in_events] + [marked_out_events]
|
||||
elif marked == 'in':
|
||||
return marked_in_events
|
||||
else:
|
||||
return marked_out_events
|
||||
|
||||
def _osd_in_out_events_count(self, marked='both'):
|
||||
"""
|
||||
Count the number of on going recovery events that deals with
|
||||
OSDs being marked in, out or both.
|
||||
"""
|
||||
events_in_progress = self._events_in_progress()
|
||||
marked_in_count = 0
|
||||
marked_out_count = 0
|
||||
|
||||
for ev in events_in_progress:
|
||||
if self.is_osd_marked_out(ev):
|
||||
marked_out_count += 1
|
||||
elif self.is_osd_marked_in(ev):
|
||||
marked_in_count += 1
|
||||
|
||||
if marked == 'both':
|
||||
return marked_in_count + marked_out_count
|
||||
elif marked == 'in':
|
||||
return marked_in_count
|
||||
else:
|
||||
return marked_out_count
|
||||
|
||||
def _setup_pool(self, size=None):
|
||||
self.mgr_cluster.mon_manager.create_pool(self.POOL)
|
||||
if size is not None:
|
||||
@ -105,9 +187,10 @@ class TestProgress(MgrTestCase):
|
||||
'osd', 'out', str(osd_id))
|
||||
|
||||
# Wait for a progress event to pop up
|
||||
self.wait_until_equal(lambda: len(self._all_events()), 1,
|
||||
timeout=self.EVENT_CREATION_PERIOD)
|
||||
ev = self._all_events()[0]
|
||||
self.wait_until_equal(lambda: self._osd_in_out_events_count('out'), 1,
|
||||
timeout=self.EVENT_CREATION_PERIOD*2,
|
||||
period=1)
|
||||
ev = self._get_osd_in_out_events('out')[0]
|
||||
log.info(json.dumps(ev, indent=1))
|
||||
self.assertIn("Rebalancing after osd.0 marked out", ev['message'])
|
||||
|
||||
@ -125,8 +208,9 @@ class TestProgress(MgrTestCase):
|
||||
|
||||
try:
|
||||
# Wait for progress event marked in to pop up
|
||||
self.wait_until_equal(lambda: len(self._events_in_progress()), 1,
|
||||
timeout=self.EVENT_CREATION_PERIOD)
|
||||
self.wait_until_equal(lambda: self._osd_in_out_events_count('in'), 1,
|
||||
timeout=self.EVENT_CREATION_PERIOD*2,
|
||||
period=1)
|
||||
except RuntimeError as ex:
|
||||
if not "Timed out after" in str(ex):
|
||||
raise ex
|
||||
@ -134,12 +218,17 @@ class TestProgress(MgrTestCase):
|
||||
log.info("There was no PGs affected by osd being marked in")
|
||||
return None
|
||||
|
||||
new_event = self._events_in_progress()[0]
|
||||
log.info(json.dumps(new_event, indent=1))
|
||||
self.assertIn("Rebalancing after osd.0 marked in", new_event['message'])
|
||||
|
||||
new_event = self._get_osd_in_out_events('in')[0]
|
||||
return new_event
|
||||
|
||||
def _no_events_anywhere(self):
|
||||
"""
|
||||
Whether there are any live or completed events
|
||||
"""
|
||||
p = self._get_progress()
|
||||
total_events = len(p['events']) + len(p['completed'])
|
||||
return total_events == 0
|
||||
|
||||
def _is_quiet(self):
|
||||
"""
|
||||
Whether any progress events are live.
|
||||
@ -261,4 +350,53 @@ class TestProgress(MgrTestCase):
|
||||
# Check that no event is created
|
||||
time.sleep(self.EVENT_CREATION_PERIOD)
|
||||
|
||||
self.assertEqual(len(self._all_events()), osd_count - pool_size)
|
||||
self.assertEqual(
|
||||
self._osd_in_out_completed_events_count('out'),
|
||||
osd_count - pool_size)
|
||||
|
||||
def test_turn_off_module(self):
|
||||
"""
|
||||
When the the module is turned off, there should not
|
||||
be any on going events or completed events.
|
||||
Also module should not accept any kind of Remote Event
|
||||
coming in from other module, however, once it is turned
|
||||
back, on creating an event should be working as it is.
|
||||
"""
|
||||
|
||||
pool_size = 3
|
||||
self._setup_pool(size=pool_size)
|
||||
self._write_some_data(self.WRITE_PERIOD)
|
||||
|
||||
self.mgr_cluster.mon_manager.raw_cluster_cmd("progress", "off")
|
||||
|
||||
self.mgr_cluster.mon_manager.raw_cluster_cmd(
|
||||
'osd', 'out', '0')
|
||||
|
||||
time.sleep(self.EVENT_CREATION_PERIOD)
|
||||
|
||||
self.mgr_cluster.mon_manager.raw_cluster_cmd(
|
||||
'osd', 'in', '0')
|
||||
|
||||
time.sleep(self.EVENT_CREATION_PERIOD)
|
||||
|
||||
self.assertTrue(self._no_events_anywhere())
|
||||
|
||||
self.mgr_cluster.mon_manager.raw_cluster_cmd("progress", "on")
|
||||
|
||||
self._write_some_data(self.WRITE_PERIOD)
|
||||
|
||||
self.mgr_cluster.mon_manager.raw_cluster_cmd(
|
||||
'osd', 'out', '0')
|
||||
|
||||
# Wait for a progress event to pop up
|
||||
self.wait_until_equal(lambda: self._osd_in_out_events_count('out'), 1,
|
||||
timeout=self.EVENT_CREATION_PERIOD*2,
|
||||
period=1)
|
||||
|
||||
ev1 = self._get_osd_in_out_events('out')[0]
|
||||
|
||||
log.info(json.dumps(ev1, indent=1))
|
||||
|
||||
self.wait_until_true(lambda: self._is_complete(ev1['id']),
|
||||
timeout=self.RECOVERY_PERIOD)
|
||||
self.assertTrue(self._is_quiet())
|
||||
|
||||
@ -464,6 +464,11 @@ def task(ctx, config):
|
||||
assert out['usage']['rgw.main']['num_objects'] == 1
|
||||
assert out['usage']['rgw.main']['size_kb'] > 0
|
||||
|
||||
# TESTCASE 'bucket-stats6', 'bucket', 'stats', 'non-existent bucket', 'fails, 'bucket not found error'
|
||||
(ret, out) = rgwadmin_rest(admin_conn, ['bucket', 'info'], {'bucket' : 'doesnotexist'})
|
||||
assert ret == 404
|
||||
assert out['Code'] == 'NoSuchBucket'
|
||||
|
||||
# reclaim it
|
||||
key.delete()
|
||||
|
||||
|
||||
@ -1268,7 +1268,10 @@ class LocalContext(object):
|
||||
self.daemons.daemons[prefixed_type][svc_id] = LocalDaemon(svc_type, svc_id)
|
||||
|
||||
def __del__(self):
|
||||
shutil.rmtree(self.teuthology_config['test_path'])
|
||||
test_path = self.teuthology_config['test_path']
|
||||
# opt_create_cluster_only does not create the test path
|
||||
if test_path:
|
||||
shutil.rmtree(test_path)
|
||||
|
||||
def teardown_cluster():
|
||||
log.info('\ntearing down the cluster...')
|
||||
|
||||
63
ceph/qa/workunits/fs/misc/subvolume.sh
Executable file
63
ceph/qa/workunits/fs/misc/subvolume.sh
Executable file
@ -0,0 +1,63 @@
|
||||
#!/bin/sh -x
|
||||
|
||||
expect_failure() {
|
||||
if "$@"; then return 1; else return 0; fi
|
||||
}
|
||||
|
||||
set -e
|
||||
|
||||
mkdir group
|
||||
mkdir group/subvol1
|
||||
|
||||
setfattr -n ceph.dir.subvolume -v 1 group/subvol1
|
||||
|
||||
# rename subvolume
|
||||
mv group/subvol1 group/subvol2
|
||||
|
||||
# move file out of the subvolume
|
||||
touch group/subvol2/file1
|
||||
expect_failure python3 -c "import os; os.rename('group/subvol2/file1', 'group/file1')"
|
||||
# move file into the subvolume
|
||||
touch group/file2
|
||||
expect_failure python3 -c "import os; os.rename('group/file2', 'group/subvol2/file2')"
|
||||
|
||||
# create hardlink within subvolume
|
||||
ln group/subvol2/file1 group/subvol2/file1_
|
||||
|
||||
# create hardlink out of subvolume
|
||||
expect_failure ln group/subvol2/file1 group/file1_
|
||||
expect_failure ln group/file2 group/subvol1/file2_
|
||||
|
||||
# create snapshot at subvolume root
|
||||
mkdir group/subvol2/.snap/s1
|
||||
|
||||
# create snapshot at descendent dir of subvolume
|
||||
mkdir group/subvol2/dir
|
||||
expect_failure mkdir group/subvol2/dir/.snap/s2
|
||||
|
||||
mkdir group/subvol3
|
||||
setfattr -n ceph.dir.subvolume -v 1 group/subvol3
|
||||
|
||||
# move file across subvolumes
|
||||
expect_failure python3 -c "import os; os.rename('group/subvol2/file1', 'group/subvol3/file1')"
|
||||
|
||||
# create hardlink across subvolumes
|
||||
expect_failure ln group/subvol2/file1 group/subvol3/file1
|
||||
|
||||
# create subvolume inside existing subvolume
|
||||
expect_failure setfattr -n ceph.dir.subvolume -v 1 group/subvol2/dir
|
||||
|
||||
# clear subvolume flag
|
||||
setfattr -n ceph.dir.subvolume -v 0 group/subvol2
|
||||
mkdir group/subvol2/dir/.snap/s2
|
||||
|
||||
# parent subvolume override child subvolume
|
||||
setfattr -n ceph.dir.subvolume -v 1 group/subvol2/dir
|
||||
setfattr -n ceph.dir.subvolume -v 1 group/subvol2
|
||||
expect_failure mkdir group/subvol2/dir/.snap/s3
|
||||
|
||||
rmdir group/subvol2/.snap/s1
|
||||
rmdir group/subvol2/dir/.snap/s2
|
||||
rm -rf group
|
||||
|
||||
echo OK
|
||||
@ -8,7 +8,7 @@ function assert_dm() {
|
||||
|
||||
local devno
|
||||
devno=$(sudo dmsetup info -c --noheadings -o Major,Minor $name)
|
||||
grep -q $val /sys/dev/block/$devno/bdi/stable_pages_required
|
||||
grep -q $val /sys/dev/block/$devno/queue/stable_writes
|
||||
}
|
||||
|
||||
function dmsetup_reload() {
|
||||
@ -22,7 +22,7 @@ function dmsetup_reload() {
|
||||
sudo dmsetup resume $name
|
||||
}
|
||||
|
||||
IMAGE_NAME="stable-pages-required-test"
|
||||
IMAGE_NAME="stable-writes-test"
|
||||
|
||||
rbd create --size 1 $IMAGE_NAME
|
||||
DEV=$(sudo rbd map $IMAGE_NAME)
|
||||
@ -31,11 +31,11 @@ fallocate -l 1M loopfile
|
||||
LOOP_DEV=$(sudo losetup -f --show loopfile)
|
||||
|
||||
[[ $(blockdev --getsize64 $DEV) -eq 1048576 ]]
|
||||
grep -q 1 /sys/block/${DEV#/dev/}/bdi/stable_pages_required
|
||||
grep -q 1 /sys/block/${DEV#/dev/}/queue/stable_writes
|
||||
|
||||
rbd resize --size 2 $IMAGE_NAME
|
||||
[[ $(blockdev --getsize64 $DEV) -eq 2097152 ]]
|
||||
grep -q 1 /sys/block/${DEV#/dev/}/bdi/stable_pages_required
|
||||
grep -q 1 /sys/block/${DEV#/dev/}/queue/stable_writes
|
||||
|
||||
cat <<EOF | sudo dmsetup create tbl
|
||||
0 1024 linear $LOOP_DEV 0
|
||||
@ -261,7 +261,7 @@ peer_add()
|
||||
peer_uuid=$(rbd mirror pool info --cluster ${cluster} --pool ${pool} --format xml | \
|
||||
xmlstarlet sel -t -v "//peers/peer[site_name='${remote_cluster}']/uuid")
|
||||
|
||||
rbd --cluster ${cluster} --pool ${pool} mirror pool peer remove ${peer_uuid}
|
||||
CEPH_ARGS='' rbd --cluster ${cluster} --pool ${pool} mirror pool peer remove ${peer_uuid}
|
||||
else
|
||||
test $error_code -eq 0
|
||||
if [ -n "$uuid_var_name" ]; then
|
||||
|
||||
@ -1,2 +1,2 @@
|
||||
bdf3eebcd22d7d0b3dd4d5501bee5bac354d5b55
|
||||
15.2.8
|
||||
357616cbf726abb779ca75a551e8d02568e15b17
|
||||
15.2.9
|
||||
|
||||
@ -42,7 +42,7 @@ class Create(object):
|
||||
Create an OSD by assigning an ID and FSID, registering them with the
|
||||
cluster with an ID and FSID, formatting and mounting the volume, adding
|
||||
all the metadata to the logical volumes using LVM tags, and starting
|
||||
the OSD daemon. This is a convinience command that combines the prepare
|
||||
the OSD daemon. This is a convenience command that combines the prepare
|
||||
and activate steps.
|
||||
|
||||
Encryption is supported via dmcrypt and the --dmcrypt flag.
|
||||
|
||||
@ -167,9 +167,8 @@ int main(int argc, const char **argv, const char *envp[]) {
|
||||
}
|
||||
|
||||
{
|
||||
g_ceph_context->_conf.finalize_reexpand_meta();
|
||||
common_init_finish(g_ceph_context);
|
||||
|
||||
|
||||
init_async_signal_handler();
|
||||
register_async_signal_handler(SIGHUP, sighup_handler);
|
||||
|
||||
|
||||
@ -48,7 +48,6 @@ import os
|
||||
import platform
|
||||
import pwd
|
||||
import random
|
||||
import re
|
||||
import select
|
||||
import shutil
|
||||
import socket
|
||||
@ -59,6 +58,7 @@ import tempfile
|
||||
import time
|
||||
import errno
|
||||
import struct
|
||||
from enum import Enum
|
||||
try:
|
||||
from typing import Dict, List, Tuple, Optional, Union, Any, NoReturn, Callable, IO
|
||||
except ImportError:
|
||||
@ -93,7 +93,7 @@ if sys.version_info > (3, 0):
|
||||
container_path = ''
|
||||
cached_stdin = None
|
||||
|
||||
DATEFMT = '%Y-%m-%dT%H:%M:%S.%f'
|
||||
DATEFMT = '%Y-%m-%dT%H:%M:%S.%fZ'
|
||||
|
||||
# Log and console output config
|
||||
logging_config = {
|
||||
@ -924,12 +924,22 @@ class FileLock(object):
|
||||
##################################
|
||||
# Popen wrappers, lifted from ceph-volume
|
||||
|
||||
def call(command, # type: List[str]
|
||||
desc=None, # type: Optional[str]
|
||||
verbose=False, # type: bool
|
||||
verbose_on_failure=True, # type: bool
|
||||
timeout=DEFAULT_TIMEOUT, # type: Optional[int]
|
||||
**kwargs):
|
||||
class CallVerbosity(Enum):
|
||||
SILENT = 0
|
||||
# log stdout/stderr to logger.debug
|
||||
DEBUG = 1
|
||||
# On a non-zero exit status, it will forcefully set
|
||||
# logging ON for the terminal
|
||||
VERBOSE_ON_FAILURE = 2
|
||||
# log at info (instead of debug) level.
|
||||
VERBOSE = 3
|
||||
|
||||
|
||||
def call(command: List[str],
|
||||
desc: Optional[str] = None,
|
||||
verbosity: CallVerbosity = CallVerbosity.VERBOSE_ON_FAILURE,
|
||||
timeout: Optional[int] = DEFAULT_TIMEOUT,
|
||||
**kwargs) -> Tuple[str, str, int]:
|
||||
"""
|
||||
Wrap subprocess.Popen to
|
||||
|
||||
@ -937,14 +947,12 @@ def call(command, # type: List[str]
|
||||
- decode utf-8
|
||||
- cleanly return out, err, returncode
|
||||
|
||||
If verbose=True, log at info (instead of debug) level.
|
||||
|
||||
:param verbose_on_failure: On a non-zero exit status, it will forcefully set
|
||||
logging ON for the terminal
|
||||
:param timeout: timeout in seconds
|
||||
"""
|
||||
if not desc:
|
||||
if desc is None:
|
||||
desc = command[0]
|
||||
if desc:
|
||||
desc += ': '
|
||||
timeout = timeout or args.timeout
|
||||
|
||||
logger.debug("Running command: %s" % ' '.join(command))
|
||||
@ -977,7 +985,7 @@ def call(command, # type: List[str]
|
||||
if end_time and (time.time() >= end_time):
|
||||
stop = True
|
||||
if process.poll() is None:
|
||||
logger.info(desc + ':timeout after %s seconds' % timeout)
|
||||
logger.info(desc + 'timeout after %s seconds' % timeout)
|
||||
process.kill()
|
||||
if reads and process.poll() is not None:
|
||||
# we want to stop, but first read off anything remaining
|
||||
@ -1007,55 +1015,58 @@ def call(command, # type: List[str]
|
||||
lines = message.split('\n')
|
||||
out_buffer = lines.pop()
|
||||
for line in lines:
|
||||
if verbose:
|
||||
logger.info(desc + ':stdout ' + line)
|
||||
else:
|
||||
logger.debug(desc + ':stdout ' + line)
|
||||
if verbosity == CallVerbosity.VERBOSE:
|
||||
logger.info(desc + 'stdout ' + line)
|
||||
elif verbosity != CallVerbosity.SILENT:
|
||||
logger.debug(desc + 'stdout ' + line)
|
||||
elif fd == process.stderr.fileno():
|
||||
err += message
|
||||
message = err_buffer + message
|
||||
lines = message.split('\n')
|
||||
err_buffer = lines.pop()
|
||||
for line in lines:
|
||||
if verbose:
|
||||
logger.info(desc + ':stderr ' + line)
|
||||
else:
|
||||
logger.debug(desc + ':stderr ' + line)
|
||||
if verbosity == CallVerbosity.VERBOSE:
|
||||
logger.info(desc + 'stderr ' + line)
|
||||
elif verbosity != CallVerbosity.SILENT:
|
||||
logger.debug(desc + 'stderr ' + line)
|
||||
else:
|
||||
assert False
|
||||
except (IOError, OSError):
|
||||
pass
|
||||
if verbose:
|
||||
logger.debug(desc + ':profile rt=%s, stop=%s, exit=%s, reads=%s'
|
||||
if verbosity == CallVerbosity.VERBOSE:
|
||||
logger.debug(desc + 'profile rt=%s, stop=%s, exit=%s, reads=%s'
|
||||
% (time.time()-start_time, stop, process.poll(), reads))
|
||||
|
||||
returncode = process.wait()
|
||||
|
||||
if out_buffer != '':
|
||||
if verbose:
|
||||
logger.info(desc + ':stdout ' + out_buffer)
|
||||
else:
|
||||
logger.debug(desc + ':stdout ' + out_buffer)
|
||||
if verbosity == CallVerbosity.VERBOSE:
|
||||
logger.info(desc + 'stdout ' + out_buffer)
|
||||
elif verbosity != CallVerbosity.SILENT:
|
||||
logger.debug(desc + 'stdout ' + out_buffer)
|
||||
if err_buffer != '':
|
||||
if verbose:
|
||||
logger.info(desc + ':stderr ' + err_buffer)
|
||||
else:
|
||||
logger.debug(desc + ':stderr ' + err_buffer)
|
||||
if verbosity == CallVerbosity.VERBOSE:
|
||||
logger.info(desc + 'stderr ' + err_buffer)
|
||||
elif verbosity != CallVerbosity.SILENT:
|
||||
logger.debug(desc + 'stderr ' + err_buffer)
|
||||
|
||||
if returncode != 0 and verbose_on_failure and not verbose:
|
||||
if returncode != 0 and verbosity == CallVerbosity.VERBOSE_ON_FAILURE:
|
||||
# dump stdout + stderr
|
||||
logger.info('Non-zero exit code %d from %s' % (returncode, ' '.join(command)))
|
||||
for line in out.splitlines():
|
||||
logger.info(desc + ':stdout ' + line)
|
||||
logger.info(desc + 'stdout ' + line)
|
||||
for line in err.splitlines():
|
||||
logger.info(desc + ':stderr ' + line)
|
||||
logger.info(desc + 'stderr ' + line)
|
||||
|
||||
return out, err, returncode
|
||||
|
||||
|
||||
def call_throws(command, **kwargs):
|
||||
# type: (List[str], Any) -> Tuple[str, str, int]
|
||||
out, err, ret = call(command, **kwargs)
|
||||
def call_throws(command: List[str],
|
||||
desc: Optional[str] = None,
|
||||
verbosity: CallVerbosity = CallVerbosity.VERBOSE_ON_FAILURE,
|
||||
timeout: Optional[int] = DEFAULT_TIMEOUT,
|
||||
**kwargs) -> Tuple[str, str, int]:
|
||||
out, err, ret = call(command, desc, verbosity, timeout, **kwargs)
|
||||
if ret:
|
||||
raise RuntimeError('Failed command: %s' % ' '.join(command))
|
||||
return out, err, ret
|
||||
@ -1166,7 +1177,7 @@ def get_file_timestamp(fn):
|
||||
return datetime.datetime.fromtimestamp(
|
||||
mt, tz=datetime.timezone.utc
|
||||
).strftime(DATEFMT)
|
||||
except Exception as e:
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
@ -1188,11 +1199,11 @@ def try_convert_datetime(s):
|
||||
p = re.compile(r'(\.[\d]{6})[\d]*')
|
||||
s = p.sub(r'\1', s)
|
||||
|
||||
# replace trailling Z with -0000, since (on python 3.6.8) it won't parse
|
||||
# replace trailing Z with -0000, since (on python 3.6.8) it won't parse
|
||||
if s and s[-1] == 'Z':
|
||||
s = s[:-1] + '-0000'
|
||||
|
||||
# cut off the redundnat 'CST' part that strptime can't parse, if
|
||||
# cut off the redundant 'CST' part that strptime can't parse, if
|
||||
# present.
|
||||
v = s.split(' ')
|
||||
s = ' '.join(v[0:3])
|
||||
@ -1409,13 +1420,16 @@ def get_last_local_ceph_image():
|
||||
[container_path, 'images',
|
||||
'--filter', 'label=ceph=True',
|
||||
'--filter', 'dangling=false',
|
||||
'--format', '{{.Repository}} {{.Tag}}'])
|
||||
for line in out.splitlines():
|
||||
if len(line.split()) == 2:
|
||||
repository, tag = line.split()
|
||||
r = '{}:{}'.format(repository, tag)
|
||||
logger.info('Using recent ceph image %s' % r)
|
||||
return r
|
||||
'--format', '{{.Repository}}@{{.Digest}}'])
|
||||
return _filter_last_local_ceph_image(out)
|
||||
|
||||
|
||||
def _filter_last_local_ceph_image(out):
|
||||
# str -> Optional[str]
|
||||
for image in out.splitlines():
|
||||
if image and not image.endswith('@'):
|
||||
logger.info('Using recent ceph image %s' % image)
|
||||
return image
|
||||
return None
|
||||
|
||||
|
||||
@ -1627,7 +1641,7 @@ def check_unit(unit_name):
|
||||
installed = False
|
||||
try:
|
||||
out, err, code = call(['systemctl', 'is-enabled', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
if code == 0:
|
||||
enabled = True
|
||||
installed = True
|
||||
@ -1641,7 +1655,7 @@ def check_unit(unit_name):
|
||||
state = 'unknown'
|
||||
try:
|
||||
out, err, code = call(['systemctl', 'is-active', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
out = out.strip()
|
||||
if out in ['active']:
|
||||
state = 'running'
|
||||
@ -2177,10 +2191,10 @@ def _write_container_cmd_to_bash(file_obj, container, comment=None, background=F
|
||||
# unit file, makes it easier to read and grok.
|
||||
file_obj.write('# ' + comment + '\n')
|
||||
# Sometimes, adding `--rm` to a run_cmd doesn't work. Let's remove the container manually
|
||||
file_obj.write('! '+ ' '.join(container.rm_cmd()) + '\n')
|
||||
file_obj.write('! '+ ' '.join(container.rm_cmd()) + ' 2> /dev/null\n')
|
||||
# Sometimes, `podman rm` doesn't find the container. Then you'll have to add `--storage`
|
||||
if 'podman' in container_path:
|
||||
file_obj.write('! '+ ' '.join(container.rm_cmd(storage=True)) + '\n')
|
||||
file_obj.write('! '+ ' '.join(container.rm_cmd(storage=True)) + ' 2> /dev/null\n')
|
||||
|
||||
# container run command
|
||||
file_obj.write(' '.join(container.run_cmd()) + (' &' if background else '') + '\n')
|
||||
@ -2292,9 +2306,9 @@ def deploy_daemon_units(fsid, uid, gid, daemon_type, daemon_id, c,
|
||||
|
||||
unit_name = get_unit_name(fsid, daemon_type, daemon_id)
|
||||
call(['systemctl', 'stop', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
call(['systemctl', 'reset-failed', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
if enable:
|
||||
call_throws(['systemctl', 'enable', unit_name])
|
||||
if start:
|
||||
@ -2339,7 +2353,7 @@ class Firewalld(object):
|
||||
else:
|
||||
return
|
||||
|
||||
out, err, ret = call([self.cmd, '--permanent', '--query-service', svc], verbose_on_failure=False)
|
||||
out, err, ret = call([self.cmd, '--permanent', '--query-service', svc], verbosity=CallVerbosity.DEBUG)
|
||||
if ret:
|
||||
logger.info('Enabling firewalld service %s in current zone...' % svc)
|
||||
out, err, ret = call([self.cmd, '--permanent', '--add-service', svc])
|
||||
@ -2357,7 +2371,7 @@ class Firewalld(object):
|
||||
|
||||
for port in fw_ports:
|
||||
tcp_port = str(port) + '/tcp'
|
||||
out, err, ret = call([self.cmd, '--permanent', '--query-port', tcp_port], verbose_on_failure=False)
|
||||
out, err, ret = call([self.cmd, '--permanent', '--query-port', tcp_port], verbosity=CallVerbosity.DEBUG)
|
||||
if ret:
|
||||
logger.info('Enabling firewalld port %s in current zone...' % tcp_port)
|
||||
out, err, ret = call([self.cmd, '--permanent', '--add-port', tcp_port])
|
||||
@ -2367,6 +2381,7 @@ class Firewalld(object):
|
||||
else:
|
||||
logger.debug('firewalld port %s is enabled in current zone' % tcp_port)
|
||||
|
||||
out, err, ret = call([self.cmd, '--permanent', '--query-port', tcp_port], verbose_on_failure=False)
|
||||
def apply_rules(self):
|
||||
# type: () -> None
|
||||
if not self.available:
|
||||
@ -2485,7 +2500,6 @@ Before=ceph-{fsid}.target
|
||||
LimitNOFILE=1048576
|
||||
LimitNPROC=1048576
|
||||
EnvironmentFile=-/etc/environment
|
||||
ExecStartPre=-{container_path} rm ceph-{fsid}-%i
|
||||
ExecStart=/bin/bash {data_dir}/{fsid}/%i/unit.run
|
||||
ExecStop=-{container_path} stop ceph-{fsid}-%i
|
||||
ExecStopPost=-/bin/bash {data_dir}/{fsid}/%i/unit.poststop
|
||||
@ -2792,7 +2806,14 @@ def command_bootstrap():
|
||||
'--allow-overwrite to overwrite' % f)
|
||||
dirname = os.path.dirname(f)
|
||||
if dirname and not os.path.exists(dirname):
|
||||
raise Error('%s directory %s does not exist' % (f, dirname))
|
||||
fname = os.path.basename(f)
|
||||
logger.info(f"Creating directory {dirname} for {fname}")
|
||||
try:
|
||||
# use makedirs to create intermediate missing dirs
|
||||
os.makedirs(dirname, 0o755)
|
||||
except PermissionError:
|
||||
raise Error(f"Unable to create {dirname} due to permissions failure. Retry with root, or sudo or preallocate the directory.")
|
||||
|
||||
|
||||
if not args.skip_prepare_host:
|
||||
command_prepare_host()
|
||||
@ -3608,7 +3629,7 @@ def command_ceph_volume():
|
||||
privileged=True,
|
||||
volume_mounts=mounts,
|
||||
)
|
||||
out, err, code = call_throws(c.run_cmd(), verbose=True)
|
||||
out, err, code = call_throws(c.run_cmd(), verbosity=CallVerbosity.VERBOSE)
|
||||
if not code:
|
||||
print(out)
|
||||
|
||||
@ -3626,7 +3647,10 @@ def command_unit():
|
||||
call_throws([
|
||||
'systemctl',
|
||||
args.command,
|
||||
unit_name])
|
||||
unit_name],
|
||||
verbosity=CallVerbosity.VERBOSE,
|
||||
desc=''
|
||||
)
|
||||
|
||||
##################################
|
||||
|
||||
@ -3813,7 +3837,7 @@ def list_daemons(detail=True, legacy_dir=None):
|
||||
'--format', '{{.Id}},{{.Config.Image}},{{%s}},{{.Created}},{{index .Config.Labels "io.ceph.version"}}' % image_field,
|
||||
'ceph-%s-%s' % (fsid, j)
|
||||
],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
if not code:
|
||||
(container_id, image_name, image_id, start,
|
||||
version) = out.strip().split(',')
|
||||
@ -3975,7 +3999,7 @@ class AdoptOsd(object):
|
||||
args=['lvm', 'list', '--format=json'],
|
||||
privileged=True
|
||||
)
|
||||
out, err, code = call_throws(c.run_cmd(), verbose=False)
|
||||
out, err, code = call_throws(c.run_cmd())
|
||||
if not code:
|
||||
try:
|
||||
js = json.loads(out)
|
||||
@ -4305,11 +4329,11 @@ def command_rm_daemon():
|
||||
'this command may destroy precious data!')
|
||||
|
||||
call(['systemctl', 'stop', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
call(['systemctl', 'reset-failed', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
call(['systemctl', 'disable', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
data_dir = get_data_dir(args.fsid, daemon_type, daemon_id)
|
||||
if daemon_type in ['mon', 'osd', 'prometheus'] and \
|
||||
not args.force_delete_data:
|
||||
@ -4344,25 +4368,25 @@ def command_rm_cluster():
|
||||
continue
|
||||
unit_name = get_unit_name(args.fsid, d['name'])
|
||||
call(['systemctl', 'stop', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
call(['systemctl', 'reset-failed', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
call(['systemctl', 'disable', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
|
||||
# cluster units
|
||||
for unit_name in ['ceph-%s.target' % args.fsid]:
|
||||
call(['systemctl', 'stop', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
call(['systemctl', 'reset-failed', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
call(['systemctl', 'disable', unit_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
|
||||
slice_name = 'system-%s.slice' % (('ceph-%s' % args.fsid).replace('-',
|
||||
'\\x2d'))
|
||||
call(['systemctl', 'stop', slice_name],
|
||||
verbose_on_failure=False)
|
||||
verbosity=CallVerbosity.DEBUG)
|
||||
|
||||
# rm units
|
||||
call_throws(['rm', '-f', args.unit_dir +
|
||||
@ -4655,13 +4679,13 @@ class Apt(Packager):
|
||||
|
||||
def install(self, ls):
|
||||
logger.info('Installing packages %s...' % ls)
|
||||
call_throws(['apt', 'install', '-y'] + ls)
|
||||
call_throws(['apt-get', 'install', '-y'] + ls)
|
||||
|
||||
def install_podman(self):
|
||||
if self.distro == 'ubuntu':
|
||||
logger.info('Setting up repo for podman...')
|
||||
self.add_kubic_repo()
|
||||
call_throws(['apt', 'update'])
|
||||
call_throws(['apt-get', 'update'])
|
||||
|
||||
logger.info('Attempting podman install...')
|
||||
try:
|
||||
@ -5436,7 +5460,6 @@ class HostFacts():
|
||||
up_secs, _ = raw_time.split()
|
||||
return float(up_secs)
|
||||
|
||||
@property
|
||||
def kernel_security(self):
|
||||
# type: () -> Dict[str, str]
|
||||
"""Determine the security features enabled in the kernel - SELinux, AppArmor"""
|
||||
@ -5501,6 +5524,23 @@ class HostFacts():
|
||||
"description": "Linux Security Module framework is not available"
|
||||
}
|
||||
|
||||
@property
|
||||
def kernel_parameters(self):
|
||||
# type: () -> Dict[str, str]
|
||||
"""Get kernel parameters required/used in Ceph clusters"""
|
||||
|
||||
k_param = {}
|
||||
out, _, _ = call_throws(['sysctl', '-a'], verbosity=CallVerbosity.SILENT)
|
||||
if out:
|
||||
param_list = out.split('\n')
|
||||
param_dict = { param.split(" = ")[0]:param.split(" = ")[-1] for param in param_list}
|
||||
|
||||
# return only desired parameters
|
||||
if 'net.ipv4.ip_nonlocal_bind' in param_dict:
|
||||
k_param['net.ipv4.ip_nonlocal_bind'] = param_dict['net.ipv4.ip_nonlocal_bind']
|
||||
|
||||
return k_param
|
||||
|
||||
def dump(self):
|
||||
# type: () -> str
|
||||
"""Return the attributes of this HostFacts object as json"""
|
||||
|
||||
@ -278,6 +278,15 @@ default via fe80::2480:28ec:5097:3fe2 dev wlp2s0 proto ra metric 20600 pref medi
|
||||
result = cd.dict_get_join({'a': 1}, 'a')
|
||||
assert result == 1
|
||||
|
||||
def test_last_local_images(self):
|
||||
out = '''
|
||||
docker.io/ceph/daemon-base@
|
||||
docker.io/ceph/ceph:v15.2.5
|
||||
docker.io/ceph/daemon-base:octopus
|
||||
'''
|
||||
image = cd._filter_last_local_ceph_image(out)
|
||||
assert image == 'docker.io/ceph/ceph:v15.2.5'
|
||||
|
||||
|
||||
class TestCustomContainer(unittest.TestCase):
|
||||
cc: cd.CustomContainer
|
||||
|
||||
@ -124,6 +124,8 @@
|
||||
|
||||
#define DEBUG_GETATTR_CAPS (CEPH_CAP_XATTR_SHARED)
|
||||
|
||||
using namespace TOPNSPC::common;
|
||||
|
||||
void client_flush_set_callback(void *p, ObjectCacher::ObjectSet *oset)
|
||||
{
|
||||
Client *client = static_cast<Client*>(p);
|
||||
@ -150,9 +152,11 @@ int Client::CommandHook::call(
|
||||
std::lock_guard l{m_client->client_lock};
|
||||
if (command == "mds_requests")
|
||||
m_client->dump_mds_requests(f);
|
||||
else if (command == "mds_sessions")
|
||||
m_client->dump_mds_sessions(f);
|
||||
else if (command == "dump_cache")
|
||||
else if (command == "mds_sessions") {
|
||||
bool cap_dump = false;
|
||||
cmd_getval(cmdmap, "cap_dump", cap_dump);
|
||||
m_client->dump_mds_sessions(f, cap_dump);
|
||||
} else if (command == "dump_cache")
|
||||
m_client->dump_cache(f);
|
||||
else if (command == "kick_stale_sessions")
|
||||
m_client->_kick_stale_sessions();
|
||||
@ -468,6 +472,7 @@ void Client::dump_status(Formatter *f)
|
||||
f->dump_int("osd_epoch", osd_epoch);
|
||||
f->dump_int("osd_epoch_barrier", cap_epoch_barrier);
|
||||
f->dump_bool("blacklisted", blacklisted);
|
||||
f->dump_string("fs_name", mdsmap->get_fs_name());
|
||||
}
|
||||
}
|
||||
|
||||
@ -519,7 +524,8 @@ void Client::_finish_init()
|
||||
lderr(cct) << "error registering admin socket command: "
|
||||
<< cpp_strerror(-ret) << dendl;
|
||||
}
|
||||
ret = admin_socket->register_command("mds_sessions",
|
||||
ret = admin_socket->register_command("mds_sessions "
|
||||
"name=cap_dump,type=CephBool,req=false",
|
||||
&m_command_hook,
|
||||
"show mds session state");
|
||||
if (ret < 0) {
|
||||
@ -1534,7 +1540,7 @@ void Client::connect_mds_targets(mds_rank_t mds)
|
||||
}
|
||||
}
|
||||
|
||||
void Client::dump_mds_sessions(Formatter *f)
|
||||
void Client::dump_mds_sessions(Formatter *f, bool cap_dump)
|
||||
{
|
||||
f->dump_int("id", get_nodeid().v);
|
||||
entity_inst_t inst(messenger->get_myname(), messenger->get_myaddr_legacy());
|
||||
@ -1544,7 +1550,7 @@ void Client::dump_mds_sessions(Formatter *f)
|
||||
f->open_array_section("sessions");
|
||||
for (const auto &p : mds_sessions) {
|
||||
f->open_object_section("session");
|
||||
p.second.dump(f);
|
||||
p.second.dump(f, cap_dump);
|
||||
f->close_section();
|
||||
}
|
||||
f->close_section();
|
||||
@ -1912,6 +1918,7 @@ void Client::encode_dentry_release(Dentry *dn, MetaRequest *req,
|
||||
rel.item.dname_len = dn->name.length();
|
||||
rel.item.dname_seq = dn->lease_seq;
|
||||
rel.dname = dn->name;
|
||||
dn->lease_mds = -1;
|
||||
}
|
||||
ldout(cct, 25) << __func__ << " exit(dn:"
|
||||
<< dn << ")" << dendl;
|
||||
@ -4211,7 +4218,7 @@ void Client::remove_session_caps(MetaSession *s, int err)
|
||||
|
||||
int Client::_do_remount(bool retry_on_error)
|
||||
{
|
||||
uint64_t max_retries = g_conf().get_val<uint64_t>("mds_max_retries_on_remount_failure");
|
||||
uint64_t max_retries = cct->_conf.get_val<uint64_t>("mds_max_retries_on_remount_failure");
|
||||
|
||||
errno = 0;
|
||||
int r = remount_cb(callback_handle);
|
||||
@ -7345,7 +7352,7 @@ unsigned Client::statx_to_mask(unsigned int flags, unsigned int want)
|
||||
mask |= CEPH_CAP_AUTH_SHARED;
|
||||
if (want & (CEPH_STATX_NLINK|CEPH_STATX_CTIME|CEPH_STATX_VERSION))
|
||||
mask |= CEPH_CAP_LINK_SHARED;
|
||||
if (want & (CEPH_STATX_ATIME|CEPH_STATX_MTIME|CEPH_STATX_CTIME|CEPH_STATX_SIZE|CEPH_STATX_BLOCKS|CEPH_STATX_VERSION))
|
||||
if (want & (CEPH_STATX_NLINK|CEPH_STATX_ATIME|CEPH_STATX_MTIME|CEPH_STATX_CTIME|CEPH_STATX_SIZE|CEPH_STATX_BLOCKS|CEPH_STATX_VERSION))
|
||||
mask |= CEPH_CAP_FILE_SHARED;
|
||||
if (want & (CEPH_STATX_VERSION|CEPH_STATX_CTIME))
|
||||
mask |= CEPH_CAP_XATTR_SHARED;
|
||||
@ -8130,6 +8137,7 @@ int Client::_readdir_cache_cb(dir_result_t *dirp, add_dirent_cb_t cb, void *p,
|
||||
|
||||
string dn_name;
|
||||
while (true) {
|
||||
int mask = caps;
|
||||
if (!dirp->inode->is_complete_and_ordered())
|
||||
return -EAGAIN;
|
||||
if (pd == dir->readdir_cache.end())
|
||||
@ -8147,7 +8155,10 @@ int Client::_readdir_cache_cb(dir_result_t *dirp, add_dirent_cb_t cb, void *p,
|
||||
}
|
||||
|
||||
int idx = pd - dir->readdir_cache.begin();
|
||||
int r = _getattr(dn->inode, caps, dirp->perms);
|
||||
if (dn->inode->is_dir()) {
|
||||
mask |= CEPH_STAT_RSTAT;
|
||||
}
|
||||
int r = _getattr(dn->inode, mask, dirp->perms);
|
||||
if (r < 0)
|
||||
return r;
|
||||
|
||||
@ -8231,7 +8242,7 @@ int Client::readdir_r_cb(dir_result_t *d, add_dirent_cb_t cb, void *p,
|
||||
uint64_t next_off = 1;
|
||||
|
||||
int r;
|
||||
r = _getattr(diri, caps, dirp->perms);
|
||||
r = _getattr(diri, caps | CEPH_STAT_RSTAT, dirp->perms);
|
||||
if (r < 0)
|
||||
return r;
|
||||
|
||||
@ -8264,7 +8275,7 @@ int Client::readdir_r_cb(dir_result_t *d, add_dirent_cb_t cb, void *p,
|
||||
in = diri->get_first_parent()->dir->parent_inode;
|
||||
|
||||
int r;
|
||||
r = _getattr(in, caps, dirp->perms);
|
||||
r = _getattr(in, caps | CEPH_STAT_RSTAT, dirp->perms);
|
||||
if (r < 0)
|
||||
return r;
|
||||
|
||||
@ -8330,7 +8341,11 @@ int Client::readdir_r_cb(dir_result_t *d, add_dirent_cb_t cb, void *p,
|
||||
|
||||
int r;
|
||||
if (check_caps) {
|
||||
r = _getattr(entry.inode, caps, dirp->perms);
|
||||
int mask = caps;
|
||||
if(entry.inode->is_dir()){
|
||||
mask |= CEPH_STAT_RSTAT;
|
||||
}
|
||||
r = _getattr(entry.inode, mask, dirp->perms);
|
||||
if (r < 0)
|
||||
return r;
|
||||
}
|
||||
@ -9224,7 +9239,7 @@ int64_t Client::_read(Fh *f, int64_t offset, uint64_t size, bufferlist *bl)
|
||||
int want, have = 0;
|
||||
bool movepos = false;
|
||||
std::unique_ptr<C_SaferCond> onuninline;
|
||||
int64_t r = 0;
|
||||
int64_t rc = 0;
|
||||
const auto& conf = cct->_conf;
|
||||
Inode *in = f->inode.get();
|
||||
utime_t lat;
|
||||
@ -9242,8 +9257,9 @@ int64_t Client::_read(Fh *f, int64_t offset, uint64_t size, bufferlist *bl)
|
||||
loff_t start_pos = offset;
|
||||
|
||||
if (in->inline_version == 0) {
|
||||
r = _getattr(in, CEPH_STAT_CAP_INLINE_DATA, f->actor_perms, true);
|
||||
auto r = _getattr(in, CEPH_STAT_CAP_INLINE_DATA, f->actor_perms, true);
|
||||
if (r < 0) {
|
||||
rc = r;
|
||||
goto done;
|
||||
}
|
||||
ceph_assert(in->inline_version > 0);
|
||||
@ -9254,9 +9270,12 @@ retry:
|
||||
want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
|
||||
else
|
||||
want = CEPH_CAP_FILE_CACHE;
|
||||
r = get_caps(f, CEPH_CAP_FILE_RD, want, &have, -1);
|
||||
if (r < 0) {
|
||||
goto done;
|
||||
{
|
||||
auto r = get_caps(f, CEPH_CAP_FILE_RD, want, &have, -1);
|
||||
if (r < 0) {
|
||||
rc = r;
|
||||
goto done;
|
||||
}
|
||||
}
|
||||
if (f->flags & O_DIRECT)
|
||||
have &= ~(CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO);
|
||||
@ -9278,12 +9297,12 @@ retry:
|
||||
bl->substr_of(in->inline_data, offset, len - offset);
|
||||
bl->append_zero(endoff - len);
|
||||
}
|
||||
r = endoff - offset;
|
||||
rc = endoff - offset;
|
||||
} else if ((uint64_t)offset < endoff) {
|
||||
bl->append_zero(endoff - offset);
|
||||
r = endoff - offset;
|
||||
rc = endoff - offset;
|
||||
} else {
|
||||
r = 0;
|
||||
rc = 0;
|
||||
}
|
||||
goto success;
|
||||
}
|
||||
@ -9296,27 +9315,31 @@ retry:
|
||||
if (f->flags & O_RSYNC) {
|
||||
_flush_range(in, offset, size);
|
||||
}
|
||||
r = _read_async(f, offset, size, bl);
|
||||
if (r < 0)
|
||||
rc = _read_async(f, offset, size, bl);
|
||||
if (rc < 0)
|
||||
goto done;
|
||||
} else {
|
||||
if (f->flags & O_DIRECT)
|
||||
_flush_range(in, offset, size);
|
||||
|
||||
bool checkeof = false;
|
||||
r = _read_sync(f, offset, size, bl, &checkeof);
|
||||
if (r < 0)
|
||||
rc = _read_sync(f, offset, size, bl, &checkeof);
|
||||
if (rc < 0)
|
||||
goto done;
|
||||
if (checkeof) {
|
||||
offset += r;
|
||||
size -= r;
|
||||
offset += rc;
|
||||
size -= rc;
|
||||
|
||||
put_cap_ref(in, CEPH_CAP_FILE_RD);
|
||||
have = 0;
|
||||
// reverify size
|
||||
r = _getattr(in, CEPH_STAT_CAP_SIZE, f->actor_perms);
|
||||
if (r < 0)
|
||||
goto done;
|
||||
{
|
||||
auto r = _getattr(in, CEPH_STAT_CAP_SIZE, f->actor_perms);
|
||||
if (r < 0) {
|
||||
rc = r;
|
||||
goto done;
|
||||
}
|
||||
}
|
||||
|
||||
// eof? short read.
|
||||
if ((uint64_t)offset < in->size)
|
||||
@ -9325,10 +9348,10 @@ retry:
|
||||
}
|
||||
|
||||
success:
|
||||
ceph_assert(r >= 0);
|
||||
ceph_assert(rc >= 0);
|
||||
if (movepos) {
|
||||
// adjust fd pos
|
||||
f->pos = start_pos + r;
|
||||
f->pos = start_pos + rc;
|
||||
}
|
||||
|
||||
lat = ceph_clock_now();
|
||||
@ -9348,7 +9371,7 @@ done:
|
||||
in->mark_caps_dirty(CEPH_CAP_FILE_WR);
|
||||
check_caps(in, 0);
|
||||
} else
|
||||
r = ret;
|
||||
rc = ret;
|
||||
}
|
||||
if (have) {
|
||||
put_cap_ref(in, CEPH_CAP_FILE_RD);
|
||||
@ -9356,7 +9379,7 @@ done:
|
||||
if (movepos) {
|
||||
unlock_fh_pos(f);
|
||||
}
|
||||
return r;
|
||||
return rc;
|
||||
}
|
||||
|
||||
Client::C_Readahead::C_Readahead(Client *c, Fh *f) :
|
||||
@ -9874,6 +9897,8 @@ int Client::ftruncate(int fd, loff_t length, const UserPerm& perms)
|
||||
if (f->flags & O_PATH)
|
||||
return -EBADF;
|
||||
#endif
|
||||
if ((f->mode & CEPH_FILE_MODE_WR) == 0)
|
||||
return -EBADF;
|
||||
struct stat attr;
|
||||
attr.st_size = length;
|
||||
return _setattr(f->inode, &attr, CEPH_SETATTR_SIZE, perms);
|
||||
@ -11463,6 +11488,9 @@ int Client::_getxattr(Inode *in, const char *name, void *value, size_t size,
|
||||
if (vxattr->flags & VXATTR_RSTAT) {
|
||||
flags |= CEPH_STAT_RSTAT;
|
||||
}
|
||||
if (vxattr->flags & VXATTR_DIRSTAT) {
|
||||
flags |= CEPH_CAP_FILE_SHARED;
|
||||
}
|
||||
r = _getattr(in, flags, perms, true);
|
||||
if (r != 0) {
|
||||
// Error from getattr!
|
||||
@ -11998,18 +12026,21 @@ size_t Client::_vxattrcb_snap_btime(Inode *in, char *val, size_t size)
|
||||
(long unsigned)in->snap_btime.nsec());
|
||||
}
|
||||
|
||||
size_t Client::_vxattrcb_cluster_fsid(Inode *in, char *val, size_t size)
|
||||
{
|
||||
return snprintf(val, size, "%s", monclient->get_fsid().to_string().c_str());
|
||||
}
|
||||
|
||||
size_t Client::_vxattrcb_client_id(Inode *in, char *val, size_t size)
|
||||
{
|
||||
auto name = messenger->get_myname();
|
||||
return snprintf(val, size, "%s%ld", name.type_str(), name.num());
|
||||
}
|
||||
|
||||
#define CEPH_XATTR_NAME(_type, _name) "ceph." #_type "." #_name
|
||||
#define CEPH_XATTR_NAME2(_type, _name, _name2) "ceph." #_type "." #_name "." #_name2
|
||||
|
||||
#define XATTR_NAME_CEPH(_type, _name) \
|
||||
{ \
|
||||
name: CEPH_XATTR_NAME(_type, _name), \
|
||||
getxattr_cb: &Client::_vxattrcb_ ## _type ## _ ## _name, \
|
||||
readonly: true, \
|
||||
exists_cb: NULL, \
|
||||
flags: 0, \
|
||||
}
|
||||
#define XATTR_NAME_CEPH2(_type, _name, _flags) \
|
||||
#define XATTR_NAME_CEPH(_type, _name, _flags) \
|
||||
{ \
|
||||
name: CEPH_XATTR_NAME(_type, _name), \
|
||||
getxattr_cb: &Client::_vxattrcb_ ## _type ## _ ## _name, \
|
||||
@ -12047,14 +12078,14 @@ const Client::VXattr Client::_dir_vxattrs[] = {
|
||||
XATTR_LAYOUT_FIELD(dir, layout, object_size),
|
||||
XATTR_LAYOUT_FIELD(dir, layout, pool),
|
||||
XATTR_LAYOUT_FIELD(dir, layout, pool_namespace),
|
||||
XATTR_NAME_CEPH(dir, entries),
|
||||
XATTR_NAME_CEPH(dir, files),
|
||||
XATTR_NAME_CEPH(dir, subdirs),
|
||||
XATTR_NAME_CEPH2(dir, rentries, VXATTR_RSTAT),
|
||||
XATTR_NAME_CEPH2(dir, rfiles, VXATTR_RSTAT),
|
||||
XATTR_NAME_CEPH2(dir, rsubdirs, VXATTR_RSTAT),
|
||||
XATTR_NAME_CEPH2(dir, rbytes, VXATTR_RSTAT),
|
||||
XATTR_NAME_CEPH2(dir, rctime, VXATTR_RSTAT),
|
||||
XATTR_NAME_CEPH(dir, entries, VXATTR_DIRSTAT),
|
||||
XATTR_NAME_CEPH(dir, files, VXATTR_DIRSTAT),
|
||||
XATTR_NAME_CEPH(dir, subdirs, VXATTR_DIRSTAT),
|
||||
XATTR_NAME_CEPH(dir, rentries, VXATTR_RSTAT),
|
||||
XATTR_NAME_CEPH(dir, rfiles, VXATTR_RSTAT),
|
||||
XATTR_NAME_CEPH(dir, rsubdirs, VXATTR_RSTAT),
|
||||
XATTR_NAME_CEPH(dir, rbytes, VXATTR_RSTAT),
|
||||
XATTR_NAME_CEPH(dir, rctime, VXATTR_RSTAT),
|
||||
{
|
||||
name: "ceph.quota",
|
||||
getxattr_cb: &Client::_vxattrcb_quota,
|
||||
@ -12104,6 +12135,24 @@ const Client::VXattr Client::_file_vxattrs[] = {
|
||||
{ name: "" } /* Required table terminator */
|
||||
};
|
||||
|
||||
const Client::VXattr Client::_common_vxattrs[] = {
|
||||
{
|
||||
name: "ceph.cluster_fsid",
|
||||
getxattr_cb: &Client::_vxattrcb_cluster_fsid,
|
||||
readonly: true,
|
||||
exists_cb: nullptr,
|
||||
flags: 0,
|
||||
},
|
||||
{
|
||||
name: "ceph.client_id",
|
||||
getxattr_cb: &Client::_vxattrcb_client_id,
|
||||
readonly: true,
|
||||
exists_cb: nullptr,
|
||||
flags: 0,
|
||||
},
|
||||
{ name: "" } /* Required table terminator */
|
||||
};
|
||||
|
||||
const Client::VXattr *Client::_get_vxattrs(Inode *in)
|
||||
{
|
||||
if (in->is_dir())
|
||||
@ -12124,7 +12173,16 @@ const Client::VXattr *Client::_match_vxattr(Inode *in, const char *name)
|
||||
vxattr++;
|
||||
}
|
||||
}
|
||||
|
||||
// for common vxattrs
|
||||
vxattr = _common_vxattrs;
|
||||
while (!vxattr->name.empty()) {
|
||||
if (vxattr->name == name)
|
||||
return vxattr;
|
||||
vxattr++;
|
||||
}
|
||||
}
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
|
||||
@ -778,7 +778,7 @@ protected:
|
||||
void _sync_write_commit(Inode *in);
|
||||
|
||||
void dump_mds_requests(Formatter *f);
|
||||
void dump_mds_sessions(Formatter *f);
|
||||
void dump_mds_sessions(Formatter *f, bool cap_dump=false);
|
||||
|
||||
int make_request(MetaRequest *req, const UserPerm& perms,
|
||||
InodeRef *ptarget = 0, bool *pcreated = 0,
|
||||
@ -1007,9 +1007,11 @@ private:
|
||||
|
||||
/* Flags for VXattr */
|
||||
static const unsigned VXATTR_RSTAT = 0x1;
|
||||
static const unsigned VXATTR_DIRSTAT = 0x2;
|
||||
|
||||
static const VXattr _dir_vxattrs[];
|
||||
static const VXattr _file_vxattrs[];
|
||||
static const VXattr _common_vxattrs[];
|
||||
|
||||
|
||||
|
||||
@ -1159,6 +1161,9 @@ private:
|
||||
bool _vxattrcb_snap_btime_exists(Inode *in);
|
||||
size_t _vxattrcb_snap_btime(Inode *in, char *val, size_t size);
|
||||
|
||||
size_t _vxattrcb_cluster_fsid(Inode *in, char *val, size_t size);
|
||||
size_t _vxattrcb_client_id(Inode *in, char *val, size_t size);
|
||||
|
||||
static const VXattr *_get_vxattrs(Inode *in);
|
||||
static const VXattr *_match_vxattr(Inode *in, const char *name);
|
||||
|
||||
|
||||
@ -5,6 +5,7 @@
|
||||
#include "messages/MClientCapRelease.h"
|
||||
|
||||
#include "MetaSession.h"
|
||||
#include "Inode.h"
|
||||
|
||||
#include "common/Formatter.h"
|
||||
|
||||
@ -21,7 +22,7 @@ const char *MetaSession::get_state_name() const
|
||||
}
|
||||
}
|
||||
|
||||
void MetaSession::dump(Formatter *f) const
|
||||
void MetaSession::dump(Formatter *f, bool cap_dump) const
|
||||
{
|
||||
f->dump_int("mds", mds_num);
|
||||
f->dump_object("addrs", addrs);
|
||||
@ -31,6 +32,13 @@ void MetaSession::dump(Formatter *f) const
|
||||
f->dump_stream("last_cap_renew_request") << last_cap_renew_request;
|
||||
f->dump_unsigned("cap_renew_seq", cap_renew_seq);
|
||||
f->dump_int("num_caps", caps.size());
|
||||
if (cap_dump) {
|
||||
f->open_array_section("caps");
|
||||
for (const auto& cap : caps) {
|
||||
f->dump_object("cap", *cap);
|
||||
}
|
||||
f->close_section();
|
||||
}
|
||||
f->dump_string("state", get_state_name());
|
||||
}
|
||||
|
||||
|
||||
@ -66,7 +66,7 @@ struct MetaSession {
|
||||
|
||||
const char *get_state_name() const;
|
||||
|
||||
void dump(Formatter *f) const;
|
||||
void dump(Formatter *f, bool cap_dump=false) const;
|
||||
|
||||
void enqueue_cap_release(inodeno_t ino, uint64_t cap_id, ceph_seq_t iseq,
|
||||
ceph_seq_t mseq, epoch_t osd_barrier);
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user