mirror of
https://git.proxmox.com/git/ceph.git
synced 2025-04-28 15:01:36 +00:00
import 14.2.11 upstream release
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
This commit is contained in:
Fabian Grünbichler
parent
aae9ebf445
commit
141ee55dc7
@ -1,7 +1,7 @@
|
||||
cmake_minimum_required(VERSION 3.5.1)
|
||||
|
||||
project(ceph CXX C ASM)
|
||||
set(VERSION 14.2.10)
|
||||
set(VERSION 14.2.11)
|
||||
|
||||
if(POLICY CMP0028)
|
||||
cmake_policy(SET CMP0028 NEW)
|
||||
|
||||
@ -1,38 +1,14 @@
|
||||
14.2.9
|
||||
------
|
||||
>= 14.2.11
|
||||
----------
|
||||
|
||||
* Bucket notifications now support Kafka endpoints. This requires librdkafka of
|
||||
version 0.9.2 and up. Note that Ubuntu 16.04.6 LTS (Xenial Xerus) has an older
|
||||
version of librdkafka, and would require an update to the library.
|
||||
* RGW: The ``radosgw-admin`` sub-commands dealing with orphans --
|
||||
``radosgw-admin orphans find``, ``radosgw-admin orphans finish``,
|
||||
``radosgw-admin orphans list-jobs`` -- have been deprecated. They
|
||||
have not been actively maintained and they store intermediate
|
||||
results on the cluster, which could fill a nearly-full cluster.
|
||||
They have been replaced by a tool, currently considered
|
||||
experimental, ``rgw-orphan-list``.
|
||||
|
||||
* The pool parameter ``target_size_ratio``, used by the pg autoscaler,
|
||||
has changed meaning. It is now normalized across pools, rather than
|
||||
specifying an absolute ratio. For details, see :ref:`pg-autoscaler`.
|
||||
If you have set target size ratios on any pools, you may want to set
|
||||
these pools to autoscale ``warn`` mode to avoid data movement during
|
||||
the upgrade::
|
||||
|
||||
ceph osd pool set <pool-name> pg_autoscale_mode warn
|
||||
|
||||
* The behaviour of the ``-o`` argument to the rados tool has been reverted to
|
||||
its orignal behaviour of indicating an output file. This reverts it to a more
|
||||
consistent behaviour when compared to other tools. Specifying object size is now
|
||||
accomplished by using an upper case O ``-O``.
|
||||
|
||||
* The format of MDSs in `ceph fs dump` has changed.
|
||||
|
||||
* Ceph will issue a health warning if a RADOS pool's ``size`` is set to 1
|
||||
or in other words the pool is configured with no redundancy. This can
|
||||
be fixed by setting the pool size to the minimum recommended value
|
||||
with::
|
||||
|
||||
ceph osd pool set <pool-name> size <num-replicas>
|
||||
|
||||
The warning can be silenced with::
|
||||
|
||||
ceph config set global mon_warn_on_pool_no_redundancy false
|
||||
|
||||
* RGW: bucket listing performance on sharded bucket indexes has been
|
||||
notably improved by heuristically -- and significantly, in many
|
||||
cases -- reducing the number of entries requested from each bucket
|
||||
index shard.
|
||||
* Now when noscrub and/or nodeep-scrub flags are set globally or per pool,
|
||||
scheduled scrubs of the type disabled will be aborted. All user initiated
|
||||
scrubs are NOT interrupted.
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
# Contributor: John Coyle <dx9err@gmail.com>
|
||||
# Maintainer: John Coyle <dx9err@gmail.com>
|
||||
pkgname=ceph
|
||||
pkgver=14.2.10
|
||||
pkgver=14.2.11
|
||||
pkgrel=0
|
||||
pkgdesc="Ceph is a distributed object store and file system"
|
||||
pkgusers="ceph"
|
||||
@ -64,7 +64,7 @@ makedepends="
|
||||
xmlstarlet
|
||||
yasm
|
||||
"
|
||||
source="ceph-14.2.10.tar.bz2"
|
||||
source="ceph-14.2.11.tar.bz2"
|
||||
subpackages="
|
||||
$pkgname-base
|
||||
$pkgname-common
|
||||
@ -117,7 +117,7 @@ _sysconfdir=/etc
|
||||
_udevrulesdir=/etc/udev/rules.d
|
||||
_python_sitelib=/usr/lib/python2.7/site-packages
|
||||
|
||||
builddir=$srcdir/ceph-14.2.10
|
||||
builddir=$srcdir/ceph-14.2.11
|
||||
|
||||
build() {
|
||||
export CEPH_BUILD_VIRTUALENV=$builddir
|
||||
|
||||
@ -109,7 +109,7 @@
|
||||
# main package definition
|
||||
#################################################################################
|
||||
Name: ceph
|
||||
Version: 14.2.10
|
||||
Version: 14.2.11
|
||||
Release: 0%{?dist}
|
||||
%if 0%{?fedora} || 0%{?rhel}
|
||||
Epoch: 2
|
||||
@ -125,7 +125,7 @@ License: LGPL-2.1 and CC-BY-SA-3.0 and GPL-2.0 and BSL-1.0 and BSD-3-Clause and
|
||||
Group: System/Filesystems
|
||||
%endif
|
||||
URL: http://ceph.com/
|
||||
Source0: %{?_remote_tarball_prefix}ceph-14.2.10.tar.bz2
|
||||
Source0: %{?_remote_tarball_prefix}ceph-14.2.11.tar.bz2
|
||||
%if 0%{?suse_version}
|
||||
# _insert_obs_source_lines_here
|
||||
ExclusiveArch: x86_64 aarch64 ppc64le s390x
|
||||
@ -1126,7 +1126,7 @@ This package provides Ceph’s default alerts for Prometheus.
|
||||
# common
|
||||
#################################################################################
|
||||
%prep
|
||||
%autosetup -p1 -n ceph-14.2.10
|
||||
%autosetup -p1 -n ceph-14.2.11
|
||||
|
||||
%build
|
||||
# LTO can be enabled as soon as the following GCC bug is fixed:
|
||||
@ -1470,6 +1470,7 @@ fi
|
||||
%{_mandir}/man8/ceph-authtool.8*
|
||||
%{_mandir}/man8/ceph-conf.8*
|
||||
%{_mandir}/man8/ceph-dencoder.8*
|
||||
%{_mandir}/man8/ceph-diff-sorted.8*
|
||||
%{_mandir}/man8/ceph-rbdnamer.8*
|
||||
%{_mandir}/man8/ceph-syn.8*
|
||||
%{_mandir}/man8/ceph-post-file.8*
|
||||
@ -1482,6 +1483,7 @@ fi
|
||||
%{_mandir}/man8/rbd-replay.8*
|
||||
%{_mandir}/man8/rbd-replay-many.8*
|
||||
%{_mandir}/man8/rbd-replay-prep.8*
|
||||
%{_mandir}/man8/rgw-orphan-list.8*
|
||||
%dir %{_datadir}/ceph/
|
||||
%{_datadir}/ceph/known_hosts_drop.ceph.com
|
||||
%{_datadir}/ceph/id_rsa_drop.ceph.com
|
||||
@ -1847,10 +1849,12 @@ fi
|
||||
%{_mandir}/man8/rbd-nbd.8*
|
||||
|
||||
%files radosgw
|
||||
%{_bindir}/ceph-diff-sorted
|
||||
%{_bindir}/radosgw
|
||||
%{_bindir}/radosgw-token
|
||||
%{_bindir}/radosgw-es
|
||||
%{_bindir}/radosgw-object-expirer
|
||||
%{_bindir}/rgw-orphan-list
|
||||
%{_mandir}/man8/radosgw.8*
|
||||
%dir %{_localstatedir}/lib/ceph/radosgw
|
||||
%{_unitdir}/ceph-radosgw@.service
|
||||
|
||||
@ -1470,6 +1470,7 @@ fi
|
||||
%{_mandir}/man8/ceph-authtool.8*
|
||||
%{_mandir}/man8/ceph-conf.8*
|
||||
%{_mandir}/man8/ceph-dencoder.8*
|
||||
%{_mandir}/man8/ceph-diff-sorted.8*
|
||||
%{_mandir}/man8/ceph-rbdnamer.8*
|
||||
%{_mandir}/man8/ceph-syn.8*
|
||||
%{_mandir}/man8/ceph-post-file.8*
|
||||
@ -1482,6 +1483,7 @@ fi
|
||||
%{_mandir}/man8/rbd-replay.8*
|
||||
%{_mandir}/man8/rbd-replay-many.8*
|
||||
%{_mandir}/man8/rbd-replay-prep.8*
|
||||
%{_mandir}/man8/rgw-orphan-list.8*
|
||||
%dir %{_datadir}/ceph/
|
||||
%{_datadir}/ceph/known_hosts_drop.ceph.com
|
||||
%{_datadir}/ceph/id_rsa_drop.ceph.com
|
||||
@ -1847,10 +1849,12 @@ fi
|
||||
%{_mandir}/man8/rbd-nbd.8*
|
||||
|
||||
%files radosgw
|
||||
%{_bindir}/ceph-diff-sorted
|
||||
%{_bindir}/radosgw
|
||||
%{_bindir}/radosgw-token
|
||||
%{_bindir}/radosgw-es
|
||||
%{_bindir}/radosgw-object-expirer
|
||||
%{_bindir}/rgw-orphan-list
|
||||
%{_mandir}/man8/radosgw.8*
|
||||
%dir %{_localstatedir}/lib/ceph/radosgw
|
||||
%{_unitdir}/ceph-radosgw@.service
|
||||
|
||||
@ -1,7 +1,13 @@
|
||||
ceph (14.2.10-1xenial) xenial; urgency=medium
|
||||
ceph (14.2.11-1xenial) xenial; urgency=medium
|
||||
|
||||
|
||||
-- Jenkins Build Slave User <jenkins-build@braggi11.front.sepia.ceph.com> Thu, 25 Jun 2020 18:20:02 +0000
|
||||
-- Jenkins Build Slave User <jenkins-build@braggi11.front.sepia.ceph.com> Mon, 10 Aug 2020 20:49:33 +0000
|
||||
|
||||
ceph (14.2.11-1) stable; urgency=medium
|
||||
|
||||
* New upstream release
|
||||
|
||||
-- Ceph Release Team <ceph-maintainers@ceph.com> Mon, 10 Aug 2020 20:15:20 +0000
|
||||
|
||||
ceph (14.2.10-1) stable; urgency=medium
|
||||
|
||||
|
||||
@ -1,6 +1,10 @@
|
||||
lib/systemd/system/ceph-radosgw*
|
||||
usr/bin/ceph-diff-sorted
|
||||
usr/bin/radosgw
|
||||
usr/bin/radosgw-es
|
||||
usr/bin/radosgw-object-expirer
|
||||
usr/bin/radosgw-token
|
||||
usr/bin/rgw-orphan-list
|
||||
usr/share/man/man8/ceph-diff-sorted.8
|
||||
usr/share/man/man8/radosgw.8
|
||||
usr/share/man/man8/rgw-orphan-list.8
|
||||
|
||||
@ -174,6 +174,13 @@ The output format is json and contains fields as follows.
|
||||
* path: absolute path of a subvolume
|
||||
* type: subvolume type indicating whether it's clone or subvolume
|
||||
* pool_namespace: RADOS namespace of the subvolume
|
||||
* features: features supported by 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
|
||||
|
||||
List subvolumes using::
|
||||
|
||||
@ -195,6 +202,17 @@ List snapshots of a subvolume using::
|
||||
|
||||
$ ceph fs subvolume snapshot ls <vol_name> <subvol_name> [--group_name <subvol_group_name>]
|
||||
|
||||
Fetch the metadata of a snapshot using::
|
||||
|
||||
$ ceph fs subvolume snapshot info <vol_name> <subvol_name> <snap_name> [--group_name <subvol_group_name>]
|
||||
|
||||
The output format is json and contains fields as follows.
|
||||
|
||||
* created_at: time of creation of snapshot in the format "YYYY-MM-DD HH:MM:SS:ffffff"
|
||||
* data_pool: data pool the snapshot belongs to
|
||||
* has_pending_clones: "yes" if snapshot clone is in progress otherwise "no"
|
||||
* size: snapshot size in bytes
|
||||
|
||||
Cloning Snapshots
|
||||
-----------------
|
||||
|
||||
@ -202,10 +220,20 @@ Subvolumes can be created by cloning subvolume snapshots. Cloning is an asynchro
|
||||
data from a snapshot to a subvolume. Due to this bulk copy nature, cloning is currently inefficient for very huge
|
||||
data sets.
|
||||
|
||||
Before starting a clone operation, the snapshot should be protected. Protecting a snapshot ensures that the snapshot
|
||||
cannot be deleted when a clone operation is in progress. Snapshots can be protected using::
|
||||
.. note:: Removing a snapshot (source subvolume) would fail if there are pending or in progress clone operations.
|
||||
|
||||
Protecting snapshots prior to cloning was a pre-requisite in the Nautilus release, and the commands to protect/unprotect
|
||||
snapshots were introduced for this purpose. This pre-requisite, and hence the commands to protect/unprotect, is being
|
||||
deprecated in mainline CephFS, and may be removed from a future release.
|
||||
|
||||
The commands being deprecated are::
|
||||
|
||||
$ ceph fs subvolume snapshot protect <vol_name> <subvol_name> <snap_name> [--group_name <subvol_group_name>]
|
||||
$ ceph fs subvolume snapshot unprotect <vol_name> <subvol_name> <snap_name> [--group_name <subvol_group_name>]
|
||||
|
||||
.. note:: Using the above commands would not result in an error, but they serve no useful function.
|
||||
|
||||
.. note:: Use subvolume info command to fetch subvolume metadata regarding supported "features" to help decide if protect/unprotect of snapshots is required, based on the "snapshot-autoprotect" feature availability.
|
||||
|
||||
To initiate a clone operation use::
|
||||
|
||||
@ -231,12 +259,11 @@ A clone can be in one of the following states:
|
||||
|
||||
#. `pending` : Clone operation has not started
|
||||
#. `in-progress` : Clone operation is in progress
|
||||
#. `complete` : Clone operation has sucessfully finished
|
||||
#. `complete` : Clone operation has successfully finished
|
||||
#. `failed` : Clone operation has failed
|
||||
|
||||
Sample output from an `in-progress` clone operation::
|
||||
|
||||
$ ceph fs subvolume snapshot protect cephfs subvol1 snap1
|
||||
$ ceph fs subvolume snapshot clone cephfs subvol1 snap1 clone1
|
||||
$ ceph fs clone status cephfs clone1
|
||||
{
|
||||
@ -254,7 +281,7 @@ Sample output from an `in-progress` clone operation::
|
||||
|
||||
.. note:: Cloned subvolumes are accessible only after the clone operation has successfully completed.
|
||||
|
||||
For a successsful clone operation, `clone status` would look like so::
|
||||
For a successful clone operation, `clone status` would look like so::
|
||||
|
||||
$ ceph fs clone status cephfs clone1
|
||||
{
|
||||
@ -270,14 +297,6 @@ To delete a partial clone use::
|
||||
|
||||
$ ceph fs subvolume rm <vol_name> <clone_name> [--group_name <group_name>] --force
|
||||
|
||||
When no clone operations are in progress or scheduled, the snaphot can be unprotected. To unprotect a snapshot use::
|
||||
|
||||
$ ceph fs subvolume snapshot unprotect <vol_name> <subvol_name> <snap_name> [--group_name <subvol_group_name>]
|
||||
|
||||
Note that unprotecting a snapshot would fail if there are pending or in progress clone operations. Also note that,
|
||||
only unprotected snapshots can be removed. This guarantees that a snapshot cannot be deleted when clones are pending
|
||||
(or in progress).
|
||||
|
||||
.. note:: Cloning only synchronizes directories, regular files and symbolic links. Also, inode timestamps (access and
|
||||
modification times) are synchronized upto seconds granularity.
|
||||
|
||||
@ -287,7 +306,6 @@ An `in-progress` or a `pending` clone operation can be canceled. To cancel a clo
|
||||
|
||||
On successful cancelation, the cloned subvolume is moved to `canceled` state::
|
||||
|
||||
$ ceph fs subvolume snapshot protect cephfs subvol1 snap1
|
||||
$ ceph fs subvolume snapshot clone cephfs subvol1 snap1 clone1
|
||||
$ ceph fs clone cancel cephfs clone1
|
||||
$ ceph fs clone status cephfs clone1
|
||||
|
||||
@ -59,8 +59,8 @@ by the setting ``mds_log_max_segments``, and when the number of segments
|
||||
exceeds that setting the MDS starts writing back metadata so that it
|
||||
can remove (trim) the oldest segments. If this writeback is happening
|
||||
too slowly, or a software bug is preventing trimming, then this health
|
||||
message may appear. The threshold for this message to appear is for the
|
||||
number of segments to be double ``mds_log_max_segments``.
|
||||
message may appear. The threshold for this message to appear is controlled by
|
||||
the config option ``mds_log_warn_factor``, the default is 2.0.
|
||||
|
||||
Message: "Client *name* failing to respond to capability release"
|
||||
Code: MDS_HEALTH_CLIENT_LATE_RELEASE, MDS_HEALTH_CLIENT_LATE_RELEASE_MANY
|
||||
|
||||
@ -2,14 +2,6 @@
|
||||
MDS Config Reference
|
||||
======================
|
||||
|
||||
``mon force standby active``
|
||||
|
||||
:Description: If ``true`` monitors force standby-replay to be active. Set
|
||||
under ``[mon]`` or ``[global]``.
|
||||
|
||||
:Type: Boolean
|
||||
:Default: ``true``
|
||||
|
||||
``mds cache memory limit``
|
||||
|
||||
:Description: The memory limit the MDS should enforce for its cache.
|
||||
@ -540,31 +532,6 @@
|
||||
:Default: ``0``
|
||||
|
||||
|
||||
``mds standby for name``
|
||||
|
||||
:Description: An MDS daemon will standby for another MDS daemon of the name
|
||||
specified in this setting.
|
||||
|
||||
:Type: String
|
||||
:Default: N/A
|
||||
|
||||
|
||||
``mds standby for rank``
|
||||
|
||||
:Description: An MDS daemon will standby for an MDS daemon of this rank.
|
||||
:Type: 32-bit Integer
|
||||
:Default: ``-1``
|
||||
|
||||
|
||||
``mds standby replay``
|
||||
|
||||
:Description: Determines whether a ``ceph-mds`` daemon should poll and replay
|
||||
the log of an active MDS (hot standby).
|
||||
|
||||
:Type: Boolean
|
||||
:Default: ``false``
|
||||
|
||||
|
||||
``mds min caps per client``
|
||||
|
||||
:Description: Set the minimum number of capabilities a client may hold.
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
.. _msgr2-protocol:
|
||||
|
||||
msgr2 protocol
|
||||
==============
|
||||
msgr2 protocol (msgr2.0 and msgr2.1)
|
||||
====================================
|
||||
|
||||
This is a revision of the legacy Ceph on-wire protocol that was
|
||||
implemented by the SimpleMessenger. It addresses performance and
|
||||
@ -20,7 +20,7 @@ This protocol revision has several goals relative to the original protocol:
|
||||
(e.g., padding) that keep computation and memory copies out of the
|
||||
fast path where possible.
|
||||
* *Signing*. We will allow for traffic to be signed (but not
|
||||
necessarily encrypted). This may not be implemented in the initial version.
|
||||
necessarily encrypted). This is not implemented.
|
||||
|
||||
Definitions
|
||||
-----------
|
||||
@ -56,10 +56,19 @@ Banner
|
||||
|
||||
Both the client and server, upon connecting, send a banner::
|
||||
|
||||
"ceph %x %x\n", protocol_features_suppored, protocol_features_required
|
||||
"ceph v2\n"
|
||||
__le16 banner payload length
|
||||
banner payload
|
||||
|
||||
The protocol features are a new, distinct namespace. Initially no
|
||||
features are defined or required, so this will be "ceph 0 0\n".
|
||||
A banner payload has the form::
|
||||
|
||||
__le64 peer_supported_features
|
||||
__le64 peer_required_features
|
||||
|
||||
This is a new, distinct feature bit namespace (CEPH_MSGR2_*).
|
||||
Currently, only CEPH_MSGR2_FEATURE_REVISION_1 is defined. It is
|
||||
supported but not required, so that msgr2.0 and msgr2.1 peers
|
||||
can talk to each other.
|
||||
|
||||
If the remote party advertises required features we don't support, we
|
||||
can disconnect.
|
||||
@ -79,27 +88,150 @@ can disconnect.
|
||||
Frame format
|
||||
------------
|
||||
|
||||
All further data sent or received is contained by a frame. Each frame has
|
||||
the form::
|
||||
After the banners are exchanged, all further communication happens
|
||||
in frames. The exact format of the frame depends on the connection
|
||||
mode (msgr2.0-crc, msgr2.0-secure, msgr2.1-crc or msgr2.1-secure).
|
||||
All connections start in crc mode (either msgr2.0-crc or msgr2.1-crc,
|
||||
depending on peer_supported_features from the banner).
|
||||
|
||||
frame_len (le32)
|
||||
tag (TAG_* le32)
|
||||
frame_header_checksum (le32)
|
||||
payload
|
||||
[payload padding -- only present after stream auth phase]
|
||||
[signature -- only present after stream auth phase]
|
||||
Each frame has a 32-byte preamble::
|
||||
|
||||
__u8 tag
|
||||
__u8 number of segments
|
||||
{
|
||||
__le32 segment length
|
||||
__le16 segment alignment
|
||||
} * 4
|
||||
reserved (2 bytes)
|
||||
__le32 preamble crc
|
||||
|
||||
* The frame_header_checksum is over just the frame_len and tag values (8 bytes).
|
||||
An empty frame has one empty segment. A non-empty frame can have
|
||||
between one and four segments, all segments except the last may be
|
||||
empty.
|
||||
|
||||
* frame_len includes everything after the frame_len le32 up to the end of the
|
||||
frame (all payloads, signatures, and padding).
|
||||
If there are less than four segments, unused (trailing) segment
|
||||
length and segment alignment fields are zeroed.
|
||||
|
||||
* The payload format and length is determined by the tag.
|
||||
The reserved bytes are zeroed.
|
||||
|
||||
* The signature portion is only present if the authentication phase
|
||||
has completed (TAG_AUTH_DONE has been sent) and signatures are
|
||||
enabled.
|
||||
The preamble checksum is CRC32-C. It covers everything up to
|
||||
itself (28 bytes) and is calculated and verified irrespective of
|
||||
the connection mode (i.e. even if the frame is encrypted).
|
||||
|
||||
### msgr2.0-crc mode
|
||||
|
||||
A msgr2.0-crc frame has the form::
|
||||
|
||||
preamble (32 bytes)
|
||||
{
|
||||
segment payload
|
||||
} * number of segments
|
||||
epilogue (17 bytes)
|
||||
|
||||
where epilogue is::
|
||||
|
||||
__u8 late_flags
|
||||
{
|
||||
__le32 segment crc
|
||||
} * 4
|
||||
|
||||
late_flags is used for frame abortion. After transmitting the
|
||||
preamble and the first segment, the sender can fill the remaining
|
||||
segments with zeros and set a flag to indicate that the receiver must
|
||||
drop the frame. This allows the sender to avoid extra buffering
|
||||
when a frame that is being put on the wire is revoked (i.e. yanked
|
||||
out of the messenger): payload buffers can be unpinned and handed
|
||||
back to the user immediately, without making a copy or blocking
|
||||
until the whole frame is transmitted. Currently this is used only
|
||||
by the kernel client, see ceph_msg_revoke().
|
||||
|
||||
The segment checksum is CRC32-C. For "used" empty segments, it is
|
||||
set to (__le32)-1. For unused (trailing) segments, it is zeroed.
|
||||
|
||||
The crcs are calculated just to protect against bit errors.
|
||||
No authenticity guarantees are provided, unlike in msgr1 which
|
||||
attempted to provide some authenticity guarantee by optionally
|
||||
signing segment lengths and crcs with the session key.
|
||||
|
||||
Issues:
|
||||
|
||||
1. As part of introducing a structure for a generic frame with
|
||||
variable number of segments suitable for both control and
|
||||
message frames, msgr2.0 moved the crc of the first segment of
|
||||
the message frame (ceph_msg_header2) into the epilogue.
|
||||
|
||||
As a result, ceph_msg_header2 can no longer be safely
|
||||
interpreted before the whole frame is read off the wire.
|
||||
This is a regression from msgr1, because in order to scatter
|
||||
the payload directly into user-provided buffers and thus avoid
|
||||
extra buffering and copying when receiving message frames,
|
||||
ceph_msg_header2 must be available in advance -- it stores
|
||||
the transaction id which the user buffers are keyed on.
|
||||
The implementation has to choose between forgoing this
|
||||
optimization or acting on an unverified segment.
|
||||
|
||||
2. late_flags is not covered by any crc. Since it stores the
|
||||
abort flag, a single bit flip can result in a completed frame
|
||||
being dropped (causing the sender to hang waiting for a reply)
|
||||
or, worse, in an aborted frame with garbage segment payloads
|
||||
being dispatched.
|
||||
|
||||
This was the case with msgr1 and got carried over to msgr2.0.
|
||||
|
||||
### msgr2.1-crc mode
|
||||
|
||||
Differences from msgr2.0-crc:
|
||||
|
||||
1. The crc of the first segment is stored at the end of the
|
||||
first segment, not in the epilogue. The epilogue stores up to
|
||||
three crcs, not up to four.
|
||||
|
||||
If the first segment is empty, (__le32)-1 crc is not generated.
|
||||
|
||||
2. The epilogue is generated only if the frame has more than one
|
||||
segment (i.e. at least one of second to fourth segments is not
|
||||
empty). Rationale: If the frame has only one segment, it cannot
|
||||
be aborted and there are no crcs to store in the epilogue.
|
||||
|
||||
3. Unchecksummed late_flags is replaced with late_status which
|
||||
builds in bit error detection by using a 4-bit nibble per flag
|
||||
and two code words that are Hamming Distance = 4 apart (and not
|
||||
all zeros or ones). This comes at the expense of having only
|
||||
one reserved flag, of course.
|
||||
|
||||
Some example frames:
|
||||
|
||||
* A 0+0+0+0 frame (empty, no epilogue)::
|
||||
|
||||
preamble (32 bytes)
|
||||
|
||||
* A 20+0+0+0 frame (no epilogue)::
|
||||
|
||||
preamble (32 bytes)
|
||||
segment1 payload (20 bytes)
|
||||
__le32 segment1 crc
|
||||
|
||||
* A 0+70+0+0 frame::
|
||||
|
||||
preamble (32 bytes)
|
||||
segment2 payload (70 bytes)
|
||||
epilogue (13 bytes)
|
||||
|
||||
* A 20+70+0+350 frame::
|
||||
|
||||
preamble (32 bytes)
|
||||
segment1 payload (20 bytes)
|
||||
__le32 segment1 crc
|
||||
segment2 payload (70 bytes)
|
||||
segment4 payload (350 bytes)
|
||||
epilogue (13 bytes)
|
||||
|
||||
where epilogue is::
|
||||
|
||||
__u8 late_status
|
||||
{
|
||||
__le32 segment crc
|
||||
} * 3
|
||||
|
||||
Hello
|
||||
-----
|
||||
@ -198,47 +330,197 @@ authentication method as the first attempt:
|
||||
Post-auth frame format
|
||||
----------------------
|
||||
|
||||
The frame format is fixed (see above), but can take three different
|
||||
forms, depending on the AUTH_DONE flags:
|
||||
Depending on the negotiated connection mode from TAG_AUTH_DONE, the
|
||||
connection either stays in crc mode or switches to the corresponding
|
||||
secure mode (msgr2.0-secure or msgr2.1-secure).
|
||||
|
||||
* If neither FLAG_SIGNED or FLAG_ENCRYPTED is specified, things are simple::
|
||||
### msgr2.0-secure mode
|
||||
|
||||
frame_len
|
||||
tag
|
||||
payload
|
||||
payload_padding (out to auth block_size)
|
||||
A msgr2.0-secure frame has the form::
|
||||
|
||||
- The padding is some number of bytes < the auth block_size that
|
||||
brings the total length of the payload + payload_padding to a
|
||||
multiple of block_size. It does not include the frame_len or tag. Padding
|
||||
content can be zeros or (better) random bytes.
|
||||
|
||||
* If FLAG_SIGNED has been specified::
|
||||
|
||||
frame_len
|
||||
tag
|
||||
payload
|
||||
payload_padding (out to auth block_size)
|
||||
signature (sig_size bytes)
|
||||
|
||||
Here the padding just makes life easier for the signature. It can be
|
||||
random data to add additional confounder. Note also that the
|
||||
signature input must include some state from the session key and the
|
||||
previous message.
|
||||
|
||||
* If FLAG_ENCRYPTED has been specified::
|
||||
|
||||
frame_len
|
||||
tag
|
||||
{
|
||||
preamble (32 bytes)
|
||||
{
|
||||
payload
|
||||
payload_padding (out to auth block_size)
|
||||
} ^ stream cipher
|
||||
segment payload
|
||||
zero padding (out to 16 bytes)
|
||||
} * number of segments
|
||||
epilogue (16 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
|
||||
Note that the padding ensures that the total frame is a multiple of
|
||||
the auth method's block_size so that the message can be sent out over
|
||||
the wire without waiting for the next frame in the stream.
|
||||
where epilogue is::
|
||||
|
||||
__u8 late_flags
|
||||
zero padding (15 bytes)
|
||||
|
||||
late_flags has the same meaning as in msgr2.0-crc mode.
|
||||
|
||||
Each segment and the epilogue are zero padded out to 16 bytes.
|
||||
Technically, GCM doesn't require any padding because Counter mode
|
||||
(the C in GCM) essentially turns a block cipher into a stream cipher.
|
||||
But, if the overall input length is not a multiple of 16 bytes, some
|
||||
implicit zero padding would occur internally because GHASH function
|
||||
used by GCM for generating auth tags only works on 16-byte blocks.
|
||||
|
||||
Issues:
|
||||
|
||||
1. The sender encrypts the whole frame using a single nonce
|
||||
and generating a single auth tag. Because segment lengths are
|
||||
stored in the preamble, the receiver has no choice but to decrypt
|
||||
and interpret the preamble without verifying the auth tag -- it
|
||||
can't even tell how much to read off the wire to get the auth tag
|
||||
otherwise! This creates a decryption oracle, which, in conjunction
|
||||
with Counter mode malleability, could lead to recovery of sensitive
|
||||
information.
|
||||
|
||||
This issue extends to the first segment of the message frame as
|
||||
well. As in msgr2.0-crc mode, ceph_msg_header2 cannot be safely
|
||||
interpreted before the whole frame is read off the wire.
|
||||
|
||||
2. Deterministic nonce construction with a 4-byte counter field
|
||||
followed by an 8-byte fixed field is used. The initial values are
|
||||
taken from the connection secret -- a random byte string generated
|
||||
during the authentication phase. Because the counter field is
|
||||
only four bytes long, it can wrap and then repeat in under a day,
|
||||
leading to GCM nonce reuse and therefore a potential complete
|
||||
loss of both authenticity and confidentiality for the connection.
|
||||
This was addressed by disconnecting before the counter repeats
|
||||
(CVE-2020-1759).
|
||||
|
||||
### msgr2.1-secure mode
|
||||
|
||||
Differences from msgr2.0-secure:
|
||||
|
||||
1. The preamble, the first segment and the rest of the frame are
|
||||
encrypted separately, using separate nonces and generating
|
||||
separate auth tags. This gets rid of unverified plaintext use
|
||||
and keeps msgr2.1-secure mode close to msgr2.1-crc mode, allowing
|
||||
the implementation to receive message frames in a similar fashion
|
||||
(little to no buffering, same scatter/gather logic, etc).
|
||||
|
||||
In order to reduce the number of en/decryption operations per
|
||||
frame, the preamble is grown by a fixed size inline buffer (48
|
||||
bytes) that the first segment is inlined into, either fully or
|
||||
partially. The preamble auth tag covers both the preamble and the
|
||||
inline buffer, so if the first segment is small enough to be fully
|
||||
inlined, it becomes available after a single decryption operation.
|
||||
|
||||
2. As in msgr2.1-crc mode, the epilogue is generated only if the
|
||||
frame has more than one segment. The rationale is even stronger,
|
||||
as it would require an extra en/decryption operation.
|
||||
|
||||
3. For consistency with msgr2.1-crc mode, late_flags is replaced
|
||||
with late_status (the built-in bit error detection isn't really
|
||||
needed in secure mode).
|
||||
|
||||
4. In accordance with `NIST Recommendation for GCM`_, deterministic
|
||||
nonce construction with a 4-byte fixed field followed by an 8-byte
|
||||
counter field is used. An 8-byte counter field should never repeat
|
||||
but the nonce reuse protection put in place for msgr2.0-secure mode
|
||||
is still there.
|
||||
|
||||
The initial values are the same as in msgr2.0-secure mode.
|
||||
|
||||
.. _`NIST Recommendation for GCM`: https://nvlpubs.nist.gov/nistpubs/Legacy/SP/nistspecialpublication800-38d.pdf
|
||||
|
||||
As in msgr2.0-secure mode, each segment is zero padded out to
|
||||
16 bytes. If the first segment is fully inlined, its padding goes
|
||||
to the inline buffer. Otherwise, the padding is on the remainder.
|
||||
The corollary to this is that the inline buffer is consumed in
|
||||
16-byte chunks.
|
||||
|
||||
The unused portion of the inline buffer is zeroed.
|
||||
|
||||
Some example frames:
|
||||
|
||||
* A 0+0+0+0 frame (empty, nothing to inline, no epilogue)::
|
||||
|
||||
{
|
||||
preamble (32 bytes)
|
||||
zero padding (48 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
|
||||
* A 20+0+0+0 frame (first segment fully inlined, no epilogue)::
|
||||
|
||||
{
|
||||
preamble (32 bytes)
|
||||
segment1 payload (20 bytes)
|
||||
zero padding (28 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
|
||||
* A 0+70+0+0 frame (nothing to inline)::
|
||||
|
||||
{
|
||||
preamble (32 bytes)
|
||||
zero padding (48 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
{
|
||||
segment2 payload (70 bytes)
|
||||
zero padding (10 bytes)
|
||||
epilogue (16 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
|
||||
* A 20+70+0+350 frame (first segment fully inlined)::
|
||||
|
||||
{
|
||||
preamble (32 bytes)
|
||||
segment1 payload (20 bytes)
|
||||
zero padding (28 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
{
|
||||
segment2 payload (70 bytes)
|
||||
zero padding (10 bytes)
|
||||
segment4 payload (350 bytes)
|
||||
zero padding (2 bytes)
|
||||
epilogue (16 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
|
||||
* A 105+0+0+0 frame (first segment partially inlined, no epilogue)::
|
||||
|
||||
{
|
||||
preamble (32 bytes)
|
||||
segment1 payload (48 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
{
|
||||
segment1 payload remainder (57 bytes)
|
||||
zero padding (7 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
|
||||
* A 105+70+0+350 frame (first segment partially inlined)::
|
||||
|
||||
{
|
||||
preamble (32 bytes)
|
||||
segment1 payload (48 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
{
|
||||
segment1 payload remainder (57 bytes)
|
||||
zero padding (7 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
{
|
||||
segment2 payload (70 bytes)
|
||||
zero padding (10 bytes)
|
||||
segment4 payload (350 bytes)
|
||||
zero padding (2 bytes)
|
||||
epilogue (16 bytes)
|
||||
} ^ AES-128-GCM cipher
|
||||
auth tag (16 bytes)
|
||||
|
||||
where epilogue is::
|
||||
|
||||
__u8 late_status
|
||||
zero padding (15 bytes)
|
||||
|
||||
late_status has the same meaning as in msgr2.1-crc mode.
|
||||
|
||||
Message flow handshake
|
||||
----------------------
|
||||
|
||||
@ -48,7 +48,9 @@ endif()
|
||||
if(WITH_RADOSGW)
|
||||
list(APPEND man_srcs
|
||||
radosgw.rst
|
||||
radosgw-admin.rst)
|
||||
radosgw-admin.rst
|
||||
rgw-orphan-list.rst
|
||||
ceph-diff-sorted.rst)
|
||||
endif()
|
||||
|
||||
if(WITH_RBD)
|
||||
|
||||
71
ceph/doc/man/8/ceph-diff-sorted.rst
Normal file
71
ceph/doc/man/8/ceph-diff-sorted.rst
Normal file
@ -0,0 +1,71 @@
|
||||
:orphan:
|
||||
|
||||
==========================================================
|
||||
ceph-diff-sorted -- compare two sorted files line by line
|
||||
==========================================================
|
||||
|
||||
.. program:: ceph-diff-sorted
|
||||
|
||||
Synopsis
|
||||
========
|
||||
|
||||
| **ceph-diff-sorted** *file1* *file2*
|
||||
|
||||
Description
|
||||
===========
|
||||
|
||||
:program:`ceph-diff-sorted` is a simplifed *diff* utility optimized
|
||||
for comparing two files with lines that are lexically sorted.
|
||||
|
||||
The output is simplified in comparison to that of the standard `diff`
|
||||
tool available in POSIX systems. Angle brackets ('<' and '>') are used
|
||||
to show lines that appear in one file but not the other. The output is
|
||||
not compatible with the `patch` tool.
|
||||
|
||||
This tool was created in order to perform diffs of large files (e.g.,
|
||||
containing billions of lines) that the standard `diff` tool cannot
|
||||
handle efficiently. Knowing that the lines are sorted allows this to
|
||||
be done efficiently with minimal memory overhead.
|
||||
|
||||
The sorting of each file needs to be done lexcially. Most POSIX
|
||||
systems use the *LANG* environment variable to determine the `sort`
|
||||
tool's sorting order. To sort lexically we would need something such
|
||||
as:
|
||||
|
||||
$ LANG=C sort some-file.txt >some-file-sorted.txt
|
||||
|
||||
Examples
|
||||
========
|
||||
|
||||
Compare two files::
|
||||
|
||||
$ ceph-diff-sorted fileA.txt fileB.txt
|
||||
|
||||
Exit Status
|
||||
===========
|
||||
|
||||
When complete, the exit status will be set to one of the following:
|
||||
|
||||
0
|
||||
files same
|
||||
1
|
||||
files different
|
||||
2
|
||||
usage problem (e.g., wrong number of command-line arguments)
|
||||
3
|
||||
problem opening input file
|
||||
4
|
||||
bad file content (e.g., unsorted order or empty lines)
|
||||
|
||||
|
||||
Availability
|
||||
============
|
||||
|
||||
:program:`ceph-diff-sorted` is part of Ceph, a massively scalable,
|
||||
open-source, distributed storage system. Please refer to the Ceph
|
||||
documentation at http://ceph.com/docs for more information.
|
||||
|
||||
See also
|
||||
========
|
||||
|
||||
:doc:`rgw-orphan-list <rgw-orphan-list>`\(8)
|
||||
69
ceph/doc/man/8/rgw-orphan-list.rst
Normal file
69
ceph/doc/man/8/rgw-orphan-list.rst
Normal file
@ -0,0 +1,69 @@
|
||||
:orphan:
|
||||
|
||||
==================================================================
|
||||
rgw-orphan-list -- list rados objects that are not indexed by rgw
|
||||
==================================================================
|
||||
|
||||
.. program:: rgw-orphan-list
|
||||
|
||||
Synopsis
|
||||
========
|
||||
|
||||
| **rgw-orphan-list**
|
||||
|
||||
Description
|
||||
===========
|
||||
|
||||
:program:`rgw-orphan-list` is an *EXPERIMENTAL* RADOS gateway user
|
||||
administration utility. It produces a listing of rados objects that
|
||||
are not directly or indirectly referenced through the bucket indexes
|
||||
on a pool. It places the results and intermediate files on the local
|
||||
filesystem rather than on the ceph cluster itself, and therefore will
|
||||
not itself consume additional cluster storage.
|
||||
|
||||
In theory orphans should not exist. However because ceph evolves
|
||||
rapidly, bugs do crop up, and they may result in orphans that are left
|
||||
behind.
|
||||
|
||||
In its current form this utility does not take any command-line
|
||||
arguments or options. It will list the available pools and prompt the
|
||||
user to enter the pool they would like to list orphans for.
|
||||
|
||||
Behind the scenes it runs `rados ls` and `radosgw-admin bucket
|
||||
radoslist ...` and produces a list of those entries that appear in the
|
||||
former but not the latter. Those entries are presumed to be the
|
||||
orphans.
|
||||
|
||||
Warnings
|
||||
========
|
||||
|
||||
This utility is currently considered *EXPERIMENTAL*.
|
||||
|
||||
This utility will produce false orphan entries for unindexed buckets
|
||||
since such buckets have no bucket indices that can provide the
|
||||
starting point for tracing.
|
||||
|
||||
Options
|
||||
=======
|
||||
|
||||
At present there are no options.
|
||||
|
||||
Examples
|
||||
========
|
||||
|
||||
Launch the tool::
|
||||
|
||||
$ rgw-orphan-list
|
||||
|
||||
Availability
|
||||
============
|
||||
|
||||
:program:`radosgw-admin` is part of Ceph, a massively scalable, open-source,
|
||||
distributed storage system. Please refer to the Ceph documentation at
|
||||
http://ceph.com/docs for more information.
|
||||
|
||||
See also
|
||||
========
|
||||
|
||||
:doc:`radosgw-admin <radosgw-admin>`\(8)
|
||||
:doc:`ceph-diff-sorted <ceph-diff-sorted>`\(8)
|
||||
@ -40,3 +40,5 @@
|
||||
man/8/rbd-replay
|
||||
man/8/rbd
|
||||
man/8/rbdmap
|
||||
man/8/rgw-orphan-list
|
||||
man/8/ceph-diff-sorted
|
||||
|
||||
@ -25,11 +25,65 @@ The *prometheus* module is enabled with::
|
||||
Configuration
|
||||
-------------
|
||||
|
||||
By default the module will accept HTTP requests on port ``9283`` on all
|
||||
IPv4 and IPv6 addresses on the host. The port and listen address are both
|
||||
.. note::
|
||||
|
||||
The Prometheus manager module needs to be restarted for configuration changes to be applied.
|
||||
|
||||
By default the module will accept HTTP requests on port ``9283`` on all IPv4
|
||||
and IPv6 addresses on the host. The port and listen address are both
|
||||
configurable with ``ceph config-key set``, with keys
|
||||
``mgr/prometheus/server_addr`` and ``mgr/prometheus/server_port``.
|
||||
This port is registered with Prometheus's `registry <https://github.com/prometheus/prometheus/wiki/Default-port-allocations>`_.
|
||||
``mgr/prometheus/server_addr`` and ``mgr/prometheus/server_port``. This port
|
||||
is registered with Prometheus's `registry
|
||||
<https://github.com/prometheus/prometheus/wiki/Default-port-allocations>`_.
|
||||
|
||||
::
|
||||
|
||||
ceph config set mgr mgr/prometheus/server_addr 0.0.0.0
|
||||
ceph config set mgr mgr/prometheus/server_port 9283
|
||||
|
||||
.. warning::
|
||||
|
||||
The ``scrape_interval`` of this module should always be set to match
|
||||
Prometheus' scrape interval to work properly and not cause any issues.
|
||||
|
||||
The Prometheus manager module is, by default, configured with a scrape interval
|
||||
of 15 seconds. The scrape interval in the module is used for caching purposes
|
||||
and to determine when a cache is stale.
|
||||
|
||||
It is not recommended to use a scrape interval below 10 seconds. It is
|
||||
recommended to use 15 seconds as scrape interval, though, in some cases it
|
||||
might be useful to increase the scrape interval.
|
||||
|
||||
To set a different scrape interval in the Prometheus module, set
|
||||
``scrape_interval`` to the desired value::
|
||||
|
||||
ceph config set mgr mgr/prometheus/scrape_interval 20
|
||||
|
||||
On large clusters (>1000 OSDs), the time to fetch the metrics may become
|
||||
significant. Without the cache, the Prometheus manager module could,
|
||||
especially in conjunction with multiple Prometheus instances, overload the
|
||||
manager and lead to unresponsive or crashing Ceph manager instances. Hence,
|
||||
the cache is enabled by default and cannot be disabled. This means that there
|
||||
is a possibility that the cache becomes stale. The cache is considered stale
|
||||
when the time to fetch the metrics from Ceph exceeds the configured
|
||||
``scrape_interval``.
|
||||
|
||||
If that is the case, **a warning will be logged** and the module will either
|
||||
|
||||
* respond with a 503 HTTP status code (service unavailable) or,
|
||||
* it will return the content of the cache, even though it might be stale.
|
||||
|
||||
This behavior can be configured. By default, it will return a 503 HTTP status
|
||||
code (service unavailable). You can set other options using the ``ceph config
|
||||
set`` commands.
|
||||
|
||||
To tell the module to respond with possibly stale data, set it to ``return``::
|
||||
|
||||
ceph config set mgr mgr/prometheus/stale_cache_strategy return
|
||||
|
||||
To tell the module to respond with "service unavailable", set it to ``fail``::
|
||||
|
||||
ceph config set mgr mgr/prometheus/stale_cache_strategy fail
|
||||
|
||||
.. _prometheus-rbd-io-statistics:
|
||||
|
||||
@ -62,7 +116,7 @@ Statistic names and labels
|
||||
==========================
|
||||
|
||||
The names of the stats are exactly as Ceph names them, with
|
||||
illegal characters ``.``, ``-`` and ``::`` translated to ``_``,
|
||||
illegal characters ``.``, ``-`` and ``::`` translated to ``_``,
|
||||
and ``ceph_`` prefixed to all names.
|
||||
|
||||
|
||||
@ -75,7 +129,7 @@ rocksdb stats.
|
||||
|
||||
|
||||
The *cluster* statistics (i.e. those global to the Ceph cluster)
|
||||
have labels appropriate to what they report on. For example,
|
||||
have labels appropriate to what they report on. For example,
|
||||
metrics relating to pools have a ``pool_id`` label.
|
||||
|
||||
|
||||
@ -109,7 +163,7 @@ Correlating drive statistics with node_exporter
|
||||
The prometheus output from Ceph is designed to be used in conjunction
|
||||
with the generic host monitoring from the Prometheus node_exporter.
|
||||
|
||||
To enable correlation of Ceph OSD statistics with node_exporter's
|
||||
To enable correlation of Ceph OSD statistics with node_exporter's
|
||||
drive statistics, special series are output like this:
|
||||
|
||||
::
|
||||
|
||||
@ -123,6 +123,16 @@ The see the current configuration::
|
||||
|
||||
ceph telemetry status
|
||||
|
||||
Manually sending telemetry
|
||||
--------------------------
|
||||
|
||||
To ad hoc send telemetry data::
|
||||
|
||||
ceph telemetry send
|
||||
|
||||
In case telemetry is not enabled (with 'ceph telemetry on'), you need to add
|
||||
'--license sharing-1-0' to 'ceph telemetry send' command.
|
||||
|
||||
Sending telemetry through a proxy
|
||||
---------------------------------
|
||||
|
||||
|
||||
@ -218,6 +218,14 @@ instances or all radosgw-admin commands can be put into the ``[global]`` or the
|
||||
:Default: ``3600``
|
||||
|
||||
|
||||
``rgw gc max concurrent io``
|
||||
|
||||
:Description: The maximum number of concurrent IO operations that the RGW garbage
|
||||
collection thread will use when purging old data.
|
||||
:Type: Integer
|
||||
:Default: ``10``
|
||||
|
||||
|
||||
``rgw s3 success create obj status``
|
||||
|
||||
:Description: The alternate success status response for ``create-obj``.
|
||||
|
||||
@ -65,6 +65,7 @@ you may write data with one API and retrieve it with the other.
|
||||
Data Layout in RADOS <layout>
|
||||
STS Lite <STSLite>
|
||||
Role <role>
|
||||
Orphan List and Associated Tooliing <orphans>
|
||||
troubleshooting
|
||||
Manpage radosgw <../../man/8/radosgw>
|
||||
Manpage radosgw-admin <../../man/8/radosgw-admin>
|
||||
|
||||
@ -46,6 +46,7 @@ Example request::
|
||||
{
|
||||
"input": {
|
||||
"method": "GET",
|
||||
"subuser": "subuser",
|
||||
"user_info": {
|
||||
"used_id": "john",
|
||||
"display_name": "John"
|
||||
|
||||
115
ceph/doc/radosgw/orphans.rst
Normal file
115
ceph/doc/radosgw/orphans.rst
Normal file
@ -0,0 +1,115 @@
|
||||
==================================
|
||||
Orphan List and Associated Tooling
|
||||
==================================
|
||||
|
||||
.. version added:: Luminous
|
||||
|
||||
.. contents::
|
||||
|
||||
Orphans are RADOS objects that are left behind after their associated
|
||||
RGW objects are removed. Normally these RADOS objects are removed
|
||||
automatically, either immediately or through a process known as
|
||||
"garbage collection". Over the history of RGW, however, there may have
|
||||
been bugs that prevented these RADOS objects from being deleted, and
|
||||
these RADOS objects may be consuming space on the Ceph cluster without
|
||||
being of any use. From the perspective of RGW, we call such RADOS
|
||||
objects "orphans".
|
||||
|
||||
Orphans Find -- DEPRECATED
|
||||
--------------------------
|
||||
|
||||
The `radosgw-admin` tool has/had three subcommands to help manage
|
||||
orphans, however these subcommands are (or will soon be)
|
||||
deprecated. These subcommands are:
|
||||
|
||||
::
|
||||
# radosgw-admin orphans find ...
|
||||
# radosgw-admin orphans finish ...
|
||||
# radosgw-admin orphans list-jobs ...
|
||||
|
||||
There are two key problems with these subcommands, however. First,
|
||||
these subcommands have not been actively maintained and therefore have
|
||||
not tracked RGW as it has evolved in terms of features and updates. As
|
||||
a result the confidence that these subcommands can accurately identify
|
||||
true orphans is presently low.
|
||||
|
||||
Second, these subcommands store intermediate results on the cluster
|
||||
itself. This can be problematic when cluster administrators are
|
||||
confronting insufficient storage space and want to remove orphans as a
|
||||
means of addressing the issue. The intermediate results could strain
|
||||
the existing cluster storage capacity even further.
|
||||
|
||||
For these reasons "orphans find" has been deprecated.
|
||||
|
||||
Orphan List
|
||||
-----------
|
||||
|
||||
Because "orphans find" has been deprecated, RGW now includes an
|
||||
additional tool -- 'rgw-orphan-list'. When run it will list the
|
||||
available pools and prompt the user to enter the name of the data
|
||||
pool. At that point the tool will, perhaps after an extended period of
|
||||
time, produce a local file containing the RADOS objects from the
|
||||
designated pool that appear to be orphans. The administrator is free
|
||||
to examine this file and the decide on a course of action, perhaps
|
||||
removing those RADOS objects from the designated pool.
|
||||
|
||||
All intermediate results are stored on the local file system rather
|
||||
than the Ceph cluster. So running the 'rgw-orphan-list' tool should
|
||||
have no appreciable impact on the amount of cluster storage consumed.
|
||||
|
||||
WARNING: Experimental Status
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
The 'rgw-orphan-list' tool is new and therefore currently considered
|
||||
experimental. The list of orphans produced should be "sanity checked"
|
||||
before being used for a large delete operation.
|
||||
|
||||
WARNING: Specifying a Data Pool
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
If a pool other than an RGW data pool is specified, the results of the
|
||||
tool will be erroneous. All RADOS objects found on such a pool will
|
||||
falsely be designated as orphans.
|
||||
|
||||
WARNING: Unindexed Buckets
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
RGW allows for unindexed buckets, that is buckets that do not maintain
|
||||
an index of their contents. This is not a typical configuration, but
|
||||
it is supported. Because the 'rgw-orphan-list' tool uses the bucket
|
||||
indices to determine what RADOS objects should exist, objects in the
|
||||
unindexed buckets will falsely be listed as orphans.
|
||||
|
||||
|
||||
RADOS List
|
||||
----------
|
||||
|
||||
One of the sub-steps in computing a list of orphans is to map each RGW
|
||||
object into its corresponding set of RADOS objects. This is done using
|
||||
a subcommand of 'radosgw-admin'.
|
||||
|
||||
::
|
||||
# radosgw-admin bucket radoslist [--bucket={bucket-name}]
|
||||
|
||||
The subcommand will produce a list of RADOS objects that support all
|
||||
of the RGW objects. If a bucket is specified then the subcommand will
|
||||
only produce a list of RADOS objects that correspond back the RGW
|
||||
objects in the specified bucket.
|
||||
|
||||
Note: Shared Bucket Markers
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
Some administrators will be aware of the coding schemes used to name
|
||||
the RADOS objects that correspond to RGW objects, which include a
|
||||
"marker" unique to a given bucket.
|
||||
|
||||
RADOS objects that correspond with the contents of one RGW bucket,
|
||||
however, may contain a marker that specifies a different bucket. This
|
||||
behavior is a consequence of the "shallow copy" optimization used by
|
||||
RGW. When larger objects are copied from bucket to bucket, only the
|
||||
"head" objects are actually copied, and the tail objects are
|
||||
shared. Those shared objects will contain the marker of the original
|
||||
bucket.
|
||||
|
||||
.. _Data Layout in RADOS : ../layout
|
||||
.. _Pool Placement and Storage Classes : ../placement
|
||||
@ -431,7 +431,7 @@
|
||||
"strokeWidth": 1,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "count by(device_class) (ceph_osd_metadata)",
|
||||
"expr": "count by (device_class) (ceph_osd_metadata)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "{{device_class}}",
|
||||
|
||||
@ -27,7 +27,7 @@
|
||||
}
|
||||
]
|
||||
},
|
||||
"description": "Detailed Performance of RBD Images (IOPS/Latency)",
|
||||
"description": "Detailed Performance of RBD Images (IOPS/Throughput/Latency)",
|
||||
"editable": false,
|
||||
"gnetId": null,
|
||||
"graphTooltip": 0,
|
||||
@ -77,21 +77,21 @@
|
||||
"expr": "irate(ceph_rbd_write_ops{pool=\"$Pool\", image=\"$Image\"}[30s])",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Write {{instance}}",
|
||||
"legendFormat": "Write",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "irate(ceph_rbd_read_ops{pool=\"$Pool\", image=\"$Image\"}[30s])",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Read {{instance}}",
|
||||
"legendFormat": "Read",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"thresholds": [],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "IOPS Count",
|
||||
"title": "IOPS",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
@ -168,21 +168,21 @@
|
||||
"expr": "irate(ceph_rbd_write_bytes{pool=\"$Pool\", image=\"$Image\"}[30s])",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Read {{instance}}",
|
||||
"legendFormat": "Write",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "irate(ceph_rbd_read_bytes{pool=\"$Pool\", image=\"$Image\"}[30s])",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Write {{instance}}",
|
||||
"legendFormat": "Read",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"thresholds": [],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "IO Bytes per Second",
|
||||
"title": "Throughput",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
@ -259,21 +259,21 @@
|
||||
"expr": "irate(ceph_rbd_write_latency_sum{pool=\"$Pool\", image=\"$Image\"}[30s]) / irate(ceph_rbd_write_latency_count{pool=\"$Pool\", image=\"$Image\"}[30s])",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Write Latency Sum",
|
||||
"legendFormat": "Write",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "irate(ceph_rbd_read_latency_sum{pool=\"$Pool\", image=\"$Image\"}[30s]) / irate(ceph_rbd_read_latency_count{pool=\"$Pool\", image=\"$Image\"}[30s])",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 1,
|
||||
"legendFormat": "Read Latency Sum",
|
||||
"legendFormat": "Read",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"thresholds": [],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Averange Latency",
|
||||
"title": "Average Latency",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
|
||||
@ -416,7 +416,7 @@
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "topk(10, (sort((irate(ceph_rbd_write_ops[30s]) + on(image, pool, namespace) irate(ceph_rbd_read_ops[30s])))))",
|
||||
"expr": "topk(10, (sort((irate(ceph_rbd_write_ops[30s]) + on (image, pool, namespace) irate(ceph_rbd_read_ops[30s])))))",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 1,
|
||||
|
||||
7
ceph/qa/cephfs/clusters/1-mds-1-client-micro.yaml
Normal file
7
ceph/qa/cephfs/clusters/1-mds-1-client-micro.yaml
Normal file
@ -0,0 +1,7 @@
|
||||
roles:
|
||||
- [mon.a, mon.b, mon.c, mgr.x, mds.a, osd.0, osd.1, osd.2, osd.3]
|
||||
- [client.0]
|
||||
openstack:
|
||||
- volumes: # attached to each instance
|
||||
count: 4
|
||||
size: 10 # GB
|
||||
40
ceph/qa/objectstore/bluestore-hybrid.yaml
Normal file
40
ceph/qa/objectstore/bluestore-hybrid.yaml
Normal file
@ -0,0 +1,40 @@
|
||||
overrides:
|
||||
thrashosds:
|
||||
bdev_inject_crash: 2
|
||||
bdev_inject_crash_probability: .5
|
||||
ceph:
|
||||
fs: xfs
|
||||
conf:
|
||||
osd:
|
||||
osd objectstore: bluestore
|
||||
bluestore block size: 96636764160
|
||||
debug bluestore: 20
|
||||
debug bluefs: 20
|
||||
debug rocksdb: 10
|
||||
bluestore fsck on mount: true
|
||||
bluestore allocator: hybrid
|
||||
bluefs allocator: hybrid
|
||||
# lower the full ratios since we can fill up a 100gb osd so quickly
|
||||
mon osd full ratio: .9
|
||||
mon osd backfillfull_ratio: .85
|
||||
mon osd nearfull ratio: .8
|
||||
osd failsafe full ratio: .95
|
||||
# this doesn't work with failures bc the log writes are not atomic across the two backends
|
||||
# bluestore bluefs env mirror: true
|
||||
ceph-deploy:
|
||||
fs: xfs
|
||||
bluestore: yes
|
||||
conf:
|
||||
osd:
|
||||
osd objectstore: bluestore
|
||||
bluestore block size: 96636764160
|
||||
debug bluestore: 20
|
||||
debug bluefs: 20
|
||||
debug rocksdb: 10
|
||||
bluestore fsck on mount: true
|
||||
# lower the full ratios since we can fill up a 100gb osd so quickly
|
||||
mon osd full ratio: .9
|
||||
mon osd backfillfull_ratio: .85
|
||||
mon osd nearfull ratio: .8
|
||||
osd failsafe full ratio: .95
|
||||
|
||||
@ -181,8 +181,8 @@ function TEST_mon_last_clean_epoch() {
|
||||
|
||||
sleep 5
|
||||
|
||||
ceph tell osd.* injectargs '--osd-beacon-report-interval 10' || exit 1
|
||||
ceph tell mon.* injectargs \
|
||||
ceph tell 'osd.*' injectargs '--osd-beacon-report-interval 10' || exit 1
|
||||
ceph tell 'mon.*' injectargs \
|
||||
'--mon-min-osdmap-epochs 2 --paxos-service-trim-min 1' || exit 1
|
||||
|
||||
create_pool foo 32
|
||||
|
||||
62
ceph/qa/standalone/osd/bad-inc-map.sh
Executable file
62
ceph/qa/standalone/osd/bad-inc-map.sh
Executable file
@ -0,0 +1,62 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
source $CEPH_ROOT/qa/standalone/ceph-helpers.sh
|
||||
|
||||
mon_port=$(get_unused_port)
|
||||
|
||||
function run() {
|
||||
local dir=$1
|
||||
shift
|
||||
|
||||
export CEPH_MON="127.0.0.1:$mon_port"
|
||||
export CEPH_ARGS
|
||||
CEPH_ARGS+="--fsid=$(uuidgen) --auth-supported=none "
|
||||
CEPH_ARGS+="--mon-host=$CEPH_MON "
|
||||
set -e
|
||||
|
||||
local funcs=${@:-$(set | sed -n -e 's/^\(TEST_[0-9a-z_]*\) .*/\1/p')}
|
||||
for func in $funcs ; do
|
||||
setup $dir || return 1
|
||||
$func $dir || return 1
|
||||
teardown $dir || return 1
|
||||
done
|
||||
}
|
||||
|
||||
function TEST_bad_inc_map() {
|
||||
local dir=$1
|
||||
|
||||
run_mon $dir a
|
||||
run_mgr $dir x
|
||||
run_osd $dir 0
|
||||
run_osd $dir 1
|
||||
run_osd $dir 2
|
||||
|
||||
ceph config set osd.2 osd_inject_bad_map_crc_probability 1
|
||||
|
||||
# osd map churn
|
||||
create_pool foo 8
|
||||
ceph osd pool set foo min_size 1
|
||||
ceph osd pool set foo min_size 2
|
||||
|
||||
sleep 5
|
||||
|
||||
# make sure all the OSDs are still up
|
||||
TIMEOUT=10 wait_for_osd up 0
|
||||
TIMEOUT=10 wait_for_osd up 1
|
||||
TIMEOUT=10 wait_for_osd up 2
|
||||
|
||||
# check for the signature in the log
|
||||
grep "injecting map crc failure" $dir/osd.2.log || return 1
|
||||
grep "bailing because last" $dir/osd.2.log || return 1
|
||||
|
||||
echo success
|
||||
|
||||
delete_pool foo
|
||||
kill_daemons $dir || return 1
|
||||
}
|
||||
|
||||
main bad-inc-map "$@"
|
||||
|
||||
# Local Variables:
|
||||
# compile-command: "make -j4 && ../qa/run-standalone.sh bad-inc-map.sh"
|
||||
# End:
|
||||
@ -45,7 +45,7 @@ walk(if type == "object" then del(.mtime) else . end)
|
||||
| walk(if type == "object" then del(.version) else . end)
|
||||
| walk(if type == "object" then del(.prior_version) else . end)'
|
||||
|
||||
sortkeys='import json; import sys ; JSON=sys.stdin.read() ; ud = json.loads(JSON) ; print json.dumps(ud, sort_keys=True, indent=2)'
|
||||
sortkeys='import json; import sys ; JSON=sys.stdin.read() ; ud = json.loads(JSON) ; print(json.dumps(ud, sort_keys=True, indent=2))'
|
||||
|
||||
function run() {
|
||||
local dir=$1
|
||||
|
||||
@ -187,6 +187,120 @@ function TEST_interval_changes() {
|
||||
teardown $dir || return 1
|
||||
}
|
||||
|
||||
function _scrub_abort() {
|
||||
local dir=$1
|
||||
local poolname=test
|
||||
local OSDS=3
|
||||
local objects=1000
|
||||
local type=$2
|
||||
|
||||
TESTDATA="testdata.$$"
|
||||
if test $type = "scrub";
|
||||
then
|
||||
stopscrub="noscrub"
|
||||
check="noscrub"
|
||||
else
|
||||
stopscrub="nodeep-scrub"
|
||||
check="nodeep_scrub"
|
||||
fi
|
||||
|
||||
|
||||
setup $dir || return 1
|
||||
run_mon $dir a --osd_pool_default_size=3 || return 1
|
||||
run_mgr $dir x || return 1
|
||||
for osd in $(seq 0 $(expr $OSDS - 1))
|
||||
do
|
||||
run_osd $dir $osd --osd_pool_default_pg_autoscale_mode=off \
|
||||
--osd_deep_scrub_randomize_ratio=0.0 \
|
||||
--osd_scrub_sleep=5.0 \
|
||||
--osd_scrub_interval_randomize_ratio=0 || return 1
|
||||
done
|
||||
|
||||
# Create a pool with a single pg
|
||||
create_pool $poolname 1 1
|
||||
wait_for_clean || return 1
|
||||
poolid=$(ceph osd dump | grep "^pool.*[']${poolname}[']" | awk '{ print $2 }')
|
||||
|
||||
dd if=/dev/urandom of=$TESTDATA bs=1032 count=1
|
||||
for i in `seq 1 $objects`
|
||||
do
|
||||
rados -p $poolname put obj${i} $TESTDATA
|
||||
done
|
||||
rm -f $TESTDATA
|
||||
|
||||
local primary=$(get_primary $poolname obj1)
|
||||
local pgid="${poolid}.0"
|
||||
|
||||
CEPH_ARGS='' ceph daemon $(get_asok_path osd.$primary) trigger_$type $pgid
|
||||
# deep-scrub won't start without scrub noticing
|
||||
if [ "$type" = "deep_scrub" ];
|
||||
then
|
||||
CEPH_ARGS='' ceph daemon $(get_asok_path osd.$primary) trigger_scrub $pgid
|
||||
fi
|
||||
|
||||
# Wait for scrubbing to start
|
||||
set -o pipefail
|
||||
found="no"
|
||||
for i in $(seq 0 200)
|
||||
do
|
||||
flush_pg_stats
|
||||
if ceph pg dump pgs | grep ^$pgid| grep -q "scrubbing"
|
||||
then
|
||||
found="yes"
|
||||
#ceph pg dump pgs
|
||||
break
|
||||
fi
|
||||
done
|
||||
set +o pipefail
|
||||
|
||||
if test $found = "no";
|
||||
then
|
||||
echo "Scrubbing never started"
|
||||
return 1
|
||||
fi
|
||||
|
||||
ceph osd set $stopscrub
|
||||
|
||||
# Wait for scrubbing to end
|
||||
set -o pipefail
|
||||
for i in $(seq 0 200)
|
||||
do
|
||||
flush_pg_stats
|
||||
if ceph pg dump pgs | grep ^$pgid | grep -q "scrubbing"
|
||||
then
|
||||
continue
|
||||
fi
|
||||
#ceph pg dump pgs
|
||||
break
|
||||
done
|
||||
set +o pipefail
|
||||
|
||||
sleep 5
|
||||
|
||||
if ! grep "$check set, aborting" $dir/osd.${primary}.log
|
||||
then
|
||||
echo "Abort not seen in log"
|
||||
return 1
|
||||
fi
|
||||
|
||||
local last_scrub=$(get_last_scrub_stamp $pgid)
|
||||
ceph osd unset noscrub
|
||||
TIMEOUT=$(($objects / 2))
|
||||
wait_for_scrub $pgid "$last_scrub" || return 1
|
||||
|
||||
teardown $dir || return 1
|
||||
}
|
||||
|
||||
function TEST_scrub_abort() {
|
||||
local dir=$1
|
||||
_scrub_abort $dir scrub
|
||||
}
|
||||
|
||||
function TEST_deep_scrub_abort() {
|
||||
local dir=$1
|
||||
_scrub_abort $dir deep_scrub
|
||||
}
|
||||
|
||||
main osd-scrub-test "$@"
|
||||
|
||||
# Local Variables:
|
||||
|
||||
@ -1034,7 +1034,7 @@ def main(argv):
|
||||
|
||||
# Specify a bad --op command
|
||||
cmd = (CFSD_PREFIX + "--op oops").format(osd=ONEOSD)
|
||||
ERRORS += test_failure(cmd, "Must provide --op (info, log, remove, mkfs, fsck, repair, export, export-remove, import, list, fix-lost, list-pgs, dump-journal, dump-super, meta-list, get-osdmap, set-osdmap, get-inc-osdmap, set-inc-osdmap, mark-complete, reset-last-complete, dump-export, trim-pg-log)")
|
||||
ERRORS += test_failure(cmd, "Must provide --op (info, log, remove, mkfs, fsck, repair, export, export-remove, import, list, fix-lost, list-pgs, dump-journal, dump-super, meta-list, get-osdmap, set-osdmap, get-inc-osdmap, set-inc-osdmap, mark-complete, reset-last-complete, dump-export, trim-pg-log, statfs)")
|
||||
|
||||
# Provide just the object param not a command
|
||||
cmd = (CFSD_PREFIX + "object").format(osd=ONEOSD)
|
||||
|
||||
@ -1,5 +1,8 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
mgr:
|
||||
debug client: 10
|
||||
log-whitelist:
|
||||
- OSD full dropping all updates
|
||||
- OSD near full
|
||||
|
||||
1
ceph/qa/suites/fs/upgrade/volumes/.qa
Symbolic link
1
ceph/qa/suites/fs/upgrade/volumes/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
0
ceph/qa/suites/fs/upgrade/volumes/import-legacy/%
Normal file
0
ceph/qa/suites/fs/upgrade/volumes/import-legacy/%
Normal file
1
ceph/qa/suites/fs/upgrade/volumes/import-legacy/.qa
Symbolic link
1
ceph/qa/suites/fs/upgrade/volumes/import-legacy/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
@ -0,0 +1 @@
|
||||
../../../../../cephfs/objectstore-ec/bluestore-bitmap.yaml
|
||||
1
ceph/qa/suites/fs/upgrade/volumes/import-legacy/clusters/.qa
Symbolic link
1
ceph/qa/suites/fs/upgrade/volumes/import-legacy/clusters/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
@ -0,0 +1,7 @@
|
||||
roles:
|
||||
- [mon.a, mon.b, mon.c, mgr.x, mgr.y, mds.a, mds.b, mds.c, osd.0, osd.1, osd.2, osd.3]
|
||||
- [client.0, client.1]
|
||||
openstack:
|
||||
- volumes: # attached to each instance
|
||||
count: 4
|
||||
size: 10 # GB
|
||||
1
ceph/qa/suites/fs/upgrade/volumes/import-legacy/conf
Symbolic link
1
ceph/qa/suites/fs/upgrade/volumes/import-legacy/conf
Symbolic link
@ -0,0 +1 @@
|
||||
.qa/cephfs/conf/
|
||||
1
ceph/qa/suites/fs/upgrade/volumes/import-legacy/overrides/.qa
Symbolic link
1
ceph/qa/suites/fs/upgrade/volumes/import-legacy/overrides/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
@ -0,0 +1 @@
|
||||
.qa/cephfs/overrides/frag_enable.yaml
|
||||
@ -0,0 +1,5 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
global:
|
||||
mon pg warn min per osd: 0
|
||||
@ -0,0 +1 @@
|
||||
.qa/cephfs/overrides/whitelist_health.yaml
|
||||
@ -0,0 +1 @@
|
||||
.qa/cephfs/overrides/whitelist_wrongly_marked_down.yaml
|
||||
1
ceph/qa/suites/fs/upgrade/volumes/import-legacy/tasks/.qa
Symbolic link
1
ceph/qa/suites/fs/upgrade/volumes/import-legacy/tasks/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
@ -0,0 +1,42 @@
|
||||
meta:
|
||||
- desc: |
|
||||
install ceph/mimic latest
|
||||
tasks:
|
||||
- install:
|
||||
branch: mimic #tag: v13.2.8
|
||||
exclude_packages:
|
||||
- librados3
|
||||
- ceph-mgr-dashboard
|
||||
- ceph-mgr-diskprediction-local
|
||||
- ceph-mgr-diskprediction-cloud
|
||||
- ceph-mgr-rook
|
||||
- ceph-mgr-cephadm
|
||||
- cephadm
|
||||
extra_packages: ['librados2']
|
||||
- print: "**** done installing mimic"
|
||||
- ceph:
|
||||
mon_bind_addrvec: false
|
||||
mon_bind_msgr2: false
|
||||
log-whitelist:
|
||||
- overall HEALTH_
|
||||
- \(FS_
|
||||
- \(MDS_
|
||||
- \(OSD_
|
||||
- \(MON_DOWN\)
|
||||
- \(CACHE_POOL_
|
||||
- \(POOL_
|
||||
- \(MGR_DOWN\)
|
||||
- \(PG_
|
||||
- \(SMALLER_PGP_NUM\)
|
||||
- Monitor daemon marked osd
|
||||
- Behind on trimming
|
||||
- Manager daemon
|
||||
conf:
|
||||
global:
|
||||
mon warn on pool no app: false
|
||||
ms bind msgr2: false
|
||||
- exec:
|
||||
osd.0:
|
||||
- ceph osd require-osd-release mimic
|
||||
- ceph osd set-require-min-compat-client mimic
|
||||
- print: "**** done ceph"
|
||||
@ -0,0 +1,33 @@
|
||||
tasks:
|
||||
- workunit:
|
||||
clients:
|
||||
client.0:
|
||||
- fs/upgrade/volume_client
|
||||
env:
|
||||
ACTION: create
|
||||
- print: "**** fs/volume_client create"
|
||||
- ceph-fuse:
|
||||
client.0:
|
||||
mount_path: /volumes/_nogroup/vol_isolated
|
||||
mountpoint: mnt.0
|
||||
auth_id: vol_data_isolated
|
||||
client.1:
|
||||
mount_path: /volumes/_nogroup/vol_default
|
||||
mountpoint: mnt.1
|
||||
auth_id: vol_default
|
||||
- print: "**** ceph-fuse vol_isolated"
|
||||
- workunit:
|
||||
clients:
|
||||
client.0:
|
||||
- fs/upgrade/volume_client
|
||||
env:
|
||||
ACTION: populate
|
||||
cleanup: false
|
||||
- workunit:
|
||||
clients:
|
||||
client.1:
|
||||
- fs/upgrade/volume_client
|
||||
env:
|
||||
ACTION: populate
|
||||
cleanup: false
|
||||
- print: "**** fs/volume_client populate"
|
||||
@ -0,0 +1,54 @@
|
||||
overrides:
|
||||
ceph:
|
||||
mon_bind_msgr2: false
|
||||
mon_bind_addrvec: false
|
||||
log-whitelist:
|
||||
- scrub mismatch
|
||||
- ScrubResult
|
||||
- wrongly marked
|
||||
- \(POOL_APP_NOT_ENABLED\)
|
||||
- \(SLOW_OPS\)
|
||||
- overall HEALTH_
|
||||
- \(MON_MSGR2_NOT_ENABLED\)
|
||||
- slow request
|
||||
conf:
|
||||
global:
|
||||
bluestore warn on legacy statfs: false
|
||||
bluestore warn on no per pool omap: false
|
||||
mon:
|
||||
mon warn on osd down out interval zero: false
|
||||
|
||||
tasks:
|
||||
- mds_pre_upgrade:
|
||||
- print: "**** done mds pre-upgrade sequence"
|
||||
- install.upgrade:
|
||||
mon.a:
|
||||
- print: "**** done install.upgrade both hosts"
|
||||
- ceph.restart:
|
||||
daemons: [mon.*, mgr.*]
|
||||
mon-health-to-clog: false
|
||||
wait-for-healthy: false
|
||||
- exec:
|
||||
mon.a:
|
||||
- ceph config set global mon_warn_on_msgr2_not_enabled false
|
||||
- ceph.healthy:
|
||||
- ceph.restart:
|
||||
daemons: [osd.*]
|
||||
wait-for-healthy: false
|
||||
wait-for-osds-up: true
|
||||
- ceph.stop: [mds.*]
|
||||
- ceph.restart:
|
||||
daemons: [mds.*]
|
||||
wait-for-healthy: false
|
||||
wait-for-osds-up: true
|
||||
- exec:
|
||||
mon.a:
|
||||
- ceph mon enable-msgr2
|
||||
- ceph versions
|
||||
- ceph osd dump -f json-pretty
|
||||
- ceph config rm global mon_warn_on_msgr2_not_enabled
|
||||
- ceph osd require-osd-release nautilus
|
||||
- for f in `ceph osd pool ls` ; do ceph osd pool set $f pg_autoscale_mode off ; done
|
||||
#- ceph osd set-require-min-compat-client nautilus
|
||||
- ceph.healthy:
|
||||
- print: "**** done ceph.restart"
|
||||
@ -0,0 +1,25 @@
|
||||
overrides:
|
||||
ceph:
|
||||
log-whitelist:
|
||||
- missing required features
|
||||
tasks:
|
||||
- exec:
|
||||
mon.a:
|
||||
- ceph fs dump --format=json-pretty
|
||||
- ceph fs volume ls
|
||||
- ceph fs subvolume ls cephfs
|
||||
- workunit:
|
||||
clients:
|
||||
client.0:
|
||||
- fs/upgrade/volume_client
|
||||
env:
|
||||
ACTION: verify
|
||||
cleanup: false
|
||||
- workunit:
|
||||
clients:
|
||||
client.1:
|
||||
- fs/upgrade/volume_client
|
||||
env:
|
||||
ACTION: verify
|
||||
cleanup: false
|
||||
- print: "**** fs/volume_client verify"
|
||||
@ -0,0 +1 @@
|
||||
.qa/distros/all/ubuntu_18.04.yaml
|
||||
@ -19,6 +19,7 @@ tasks:
|
||||
- \(MGR_ZABBIX_
|
||||
- foo bar
|
||||
- Failed to open Telegraf
|
||||
- evicting unresponsive client
|
||||
- cephfs_test_runner:
|
||||
modules:
|
||||
- tasks.mgr.test_module_selftest
|
||||
|
||||
1
ceph/qa/suites/rados/perf/distros/ubuntu_16.04.yaml
Symbolic link
1
ceph/qa/suites/rados/perf/distros/ubuntu_16.04.yaml
Symbolic link
@ -0,0 +1 @@
|
||||
../../../../distros/supported-all-distro/ubuntu_16.04.yaml
|
||||
1
ceph/qa/suites/rados/perf/distros/ubuntu_latest.yaml
Symbolic link
1
ceph/qa/suites/rados/perf/distros/ubuntu_latest.yaml
Symbolic link
@ -0,0 +1 @@
|
||||
../../../../distros/supported-all-distro/ubuntu_latest.yaml
|
||||
@ -1 +0,0 @@
|
||||
../basic/supported-random-distro$
|
||||
@ -1,5 +1,6 @@
|
||||
# see http://tracker.ceph.com/issues/20360 and http://tracker.ceph.com/issues/18126
|
||||
os_type: centos
|
||||
os_version: '7.8'
|
||||
|
||||
openstack:
|
||||
- volumes: # attached to each instance
|
||||
|
||||
@ -0,0 +1,7 @@
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
osd:
|
||||
osd inject bad map crc probability: 0.1
|
||||
log-whitelist:
|
||||
- failed to encode map
|
||||
@ -1,5 +1,6 @@
|
||||
# see http://tracker.ceph.com/issues/20360 and http://tracker.ceph.com/issues/18126
|
||||
os_type: centos
|
||||
os_version: '7.8'
|
||||
|
||||
overrides:
|
||||
install:
|
||||
|
||||
1
ceph/qa/suites/rgw/hadoop-s3a/hadoop/default.yaml
Normal file
1
ceph/qa/suites/rgw/hadoop-s3a/hadoop/default.yaml
Normal file
@ -0,0 +1 @@
|
||||
|
||||
@ -1,3 +0,0 @@
|
||||
overrides:
|
||||
s3a-hadoop:
|
||||
hadoop-version: '2.7.3'
|
||||
@ -1,3 +0,0 @@
|
||||
overrides:
|
||||
s3a-hadoop:
|
||||
hadoop-version: '2.8.0'
|
||||
3
ceph/qa/suites/rgw/hadoop-s3a/hadoop/v32.yaml
Normal file
3
ceph/qa/suites/rgw/hadoop-s3a/hadoop/v32.yaml
Normal file
@ -0,0 +1,3 @@
|
||||
overrides:
|
||||
s3a-hadoop:
|
||||
hadoop-version: '3.2.0'
|
||||
0
ceph/qa/suites/rgw/tools/+
Normal file
0
ceph/qa/suites/rgw/tools/+
Normal file
1
ceph/qa/suites/rgw/tools/.qa
Symbolic link
1
ceph/qa/suites/rgw/tools/.qa
Symbolic link
@ -0,0 +1 @@
|
||||
../.qa
|
||||
1
ceph/qa/suites/rgw/tools/centos_latest.yaml
Symbolic link
1
ceph/qa/suites/rgw/tools/centos_latest.yaml
Symbolic link
@ -0,0 +1 @@
|
||||
.qa/distros/supported/centos_latest.yaml
|
||||
9
ceph/qa/suites/rgw/tools/cluster.yaml
Normal file
9
ceph/qa/suites/rgw/tools/cluster.yaml
Normal file
@ -0,0 +1,9 @@
|
||||
roles:
|
||||
- [mon.a, osd.0, osd.1, osd.2, mgr.0, client.0]
|
||||
openstack:
|
||||
- volumes: # attached to each instance
|
||||
count: 1
|
||||
size: 10 # GB
|
||||
overrides:
|
||||
rgw:
|
||||
frontend: beast
|
||||
19
ceph/qa/suites/rgw/tools/tasks.yaml
Normal file
19
ceph/qa/suites/rgw/tools/tasks.yaml
Normal file
@ -0,0 +1,19 @@
|
||||
tasks:
|
||||
- install:
|
||||
- ceph:
|
||||
- rgw:
|
||||
client.0:
|
||||
# force rgw_dns_name to be set with the fully qualified host name;
|
||||
# it will be appended to the empty string
|
||||
dns-name: ''
|
||||
- workunit:
|
||||
clients:
|
||||
client.0:
|
||||
- rgw/test_rgw_orphan_list.sh
|
||||
overrides:
|
||||
ceph:
|
||||
conf:
|
||||
client:
|
||||
debug rgw: 20
|
||||
debug ms: 1
|
||||
rgw enable static website: false
|
||||
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
@ -3,7 +3,7 @@ meta:
|
||||
librbd python api tests
|
||||
tasks:
|
||||
- workunit:
|
||||
tag: v14.2.2
|
||||
tag: v14.2.10
|
||||
clients:
|
||||
client.0:
|
||||
- rbd/test_librbd_python.sh
|
||||
|
||||
@ -1 +0,0 @@
|
||||
../../../../objectstore
|
||||
@ -0,0 +1 @@
|
||||
../.qa/
|
||||
@ -0,0 +1 @@
|
||||
.qa/objectstore/bluestore-bitmap.yaml
|
||||
@ -0,0 +1 @@
|
||||
.qa/objectstore/filestore-xfs.yaml
|
||||
@ -112,30 +112,35 @@ def task(ctx, config):
|
||||
if client_config is None:
|
||||
client_config = {}
|
||||
|
||||
auth_id = client_config.get("auth_id", id_)
|
||||
|
||||
skip = client_config.get("skip", False)
|
||||
if skip:
|
||||
skipped[id_] = skip
|
||||
continue
|
||||
|
||||
if id_ not in all_mounts:
|
||||
fuse_mount = FuseMount(ctx, client_config, testdir, id_, remote)
|
||||
fuse_mount = FuseMount(ctx, client_config, testdir, auth_id, remote)
|
||||
all_mounts[id_] = fuse_mount
|
||||
else:
|
||||
# Catch bad configs where someone has e.g. tried to use ceph-fuse and kcephfs for the same client
|
||||
assert isinstance(all_mounts[id_], FuseMount)
|
||||
|
||||
if not config.get("disabled", False) and client_config.get('mounted', True):
|
||||
mounted_by_me[id_] = all_mounts[id_]
|
||||
mounted_by_me[id_] = {"config": client_config, "mount": all_mounts[id_]}
|
||||
|
||||
ctx.mounts = all_mounts
|
||||
|
||||
# Mount any clients we have been asked to (default to mount all)
|
||||
log.info('Mounting ceph-fuse clients...')
|
||||
for mount in mounted_by_me.values():
|
||||
mount.mount()
|
||||
for info in mounted_by_me.values():
|
||||
config = info["config"]
|
||||
mount_path = config.get("mount_path")
|
||||
mountpoint = config.get("mountpoint")
|
||||
info["mount"].mount(mountpoint=mountpoint, mount_path=mount_path)
|
||||
|
||||
for mount in mounted_by_me.values():
|
||||
mount.wait_until_mounted()
|
||||
for info in mounted_by_me.values():
|
||||
info["mount"].wait_until_mounted()
|
||||
|
||||
# Umount any pre-existing clients that we have not been asked to mount
|
||||
for client_id in set(all_mounts.keys()) - set(mounted_by_me.keys()) - set(skipped.keys()):
|
||||
@ -148,7 +153,8 @@ def task(ctx, config):
|
||||
finally:
|
||||
log.info('Unmounting ceph-fuse clients...')
|
||||
|
||||
for mount in mounted_by_me.values():
|
||||
for info in mounted_by_me.values():
|
||||
# Conditional because an inner context might have umounted it
|
||||
mount = info["mount"]
|
||||
if mount.is_mounted():
|
||||
mount.umount_wait()
|
||||
|
||||
@ -1,4 +1,3 @@
|
||||
|
||||
import unittest
|
||||
from unittest import case
|
||||
import time
|
||||
@ -8,6 +7,8 @@ from teuthology.orchestra.run import CommandFailedError
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
class TestTimeoutError(RuntimeError):
|
||||
pass
|
||||
|
||||
class CephTestCase(unittest.TestCase):
|
||||
"""
|
||||
@ -32,6 +33,8 @@ class CephTestCase(unittest.TestCase):
|
||||
REQUIRE_MEMSTORE = False
|
||||
|
||||
def setUp(self):
|
||||
self._mon_configs_set = set()
|
||||
|
||||
self.ceph_cluster.mon_manager.raw_cluster_cmd("log",
|
||||
"Starting test {0}".format(self.id()))
|
||||
|
||||
@ -43,12 +46,42 @@ class CephTestCase(unittest.TestCase):
|
||||
raise case.SkipTest("Require `memstore` OSD backend (test " \
|
||||
"would take too long on full sized OSDs")
|
||||
|
||||
|
||||
|
||||
def tearDown(self):
|
||||
self.config_clear()
|
||||
|
||||
self.ceph_cluster.mon_manager.raw_cluster_cmd("log",
|
||||
"Ended test {0}".format(self.id()))
|
||||
|
||||
def config_clear(self):
|
||||
for section, key in self._mon_configs_set:
|
||||
self.config_rm(section, key)
|
||||
self._mon_configs_set.clear()
|
||||
|
||||
def _fix_key(self, key):
|
||||
return str(key).replace(' ', '_')
|
||||
|
||||
def config_get(self, section, key):
|
||||
key = self._fix_key(key)
|
||||
return self.ceph_cluster.mon_manager.raw_cluster_cmd("config", "get", section, key).strip()
|
||||
|
||||
def config_show(self, entity, key):
|
||||
key = self._fix_key(key)
|
||||
return self.ceph_cluster.mon_manager.raw_cluster_cmd("config", "show", entity, key).strip()
|
||||
|
||||
def config_minimal(self):
|
||||
return self.ceph_cluster.mon_manager.raw_cluster_cmd("config", "generate-minimal-conf").strip()
|
||||
|
||||
def config_rm(self, section, key):
|
||||
key = self._fix_key(key)
|
||||
self.ceph_cluster.mon_manager.raw_cluster_cmd("config", "rm", section, key)
|
||||
# simplification: skip removing from _mon_configs_set;
|
||||
# let tearDown clear everything again
|
||||
|
||||
def config_set(self, section, key, value):
|
||||
key = self._fix_key(key)
|
||||
self._mon_configs_set.add((section, key))
|
||||
self.ceph_cluster.mon_manager.raw_cluster_cmd("config", "set", section, key, str(value))
|
||||
|
||||
def assert_cluster_log(self, expected_pattern, invert_match=False,
|
||||
timeout=10, watch_channel=None):
|
||||
"""
|
||||
@ -142,7 +175,7 @@ class CephTestCase(unittest.TestCase):
|
||||
raise RuntimeError("wait_until_equal: forbidden value {0} seen".format(val))
|
||||
else:
|
||||
if elapsed >= timeout:
|
||||
raise RuntimeError("Timed out after {0} seconds waiting for {1} (currently {2})".format(
|
||||
raise TestTimeoutError("Timed out after {0} seconds waiting for {1} (currently {2})".format(
|
||||
elapsed, expect_val, val
|
||||
))
|
||||
else:
|
||||
@ -161,7 +194,7 @@ class CephTestCase(unittest.TestCase):
|
||||
return
|
||||
else:
|
||||
if elapsed >= timeout:
|
||||
raise RuntimeError("Timed out after {0}s".format(elapsed))
|
||||
raise TestTimeoutError("Timed out after {0}s".format(elapsed))
|
||||
else:
|
||||
log.debug("wait_until_true: waiting...")
|
||||
time.sleep(period)
|
||||
|
||||
@ -10,6 +10,7 @@ from tasks.cephfs.fuse_mount import FuseMount
|
||||
|
||||
from teuthology.orchestra import run
|
||||
from teuthology.orchestra.run import CommandFailedError
|
||||
from teuthology.contextutil import safe_while
|
||||
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
@ -169,8 +170,6 @@ class CephFSTestCase(CephTestCase):
|
||||
self.configs_set = set()
|
||||
|
||||
def tearDown(self):
|
||||
super(CephFSTestCase, self).tearDown()
|
||||
|
||||
self.mds_cluster.clear_firewall()
|
||||
for m in self.mounts:
|
||||
m.teardown()
|
||||
@ -181,6 +180,8 @@ class CephFSTestCase(CephTestCase):
|
||||
for subsys, key in self.configs_set:
|
||||
self.mds_cluster.clear_ceph_conf(subsys, key)
|
||||
|
||||
return super(CephFSTestCase, self).tearDown()
|
||||
|
||||
def set_conf(self, subsys, key, value):
|
||||
self.configs_set.add((subsys, key))
|
||||
self.mds_cluster.set_ceph_conf(subsys, key, value)
|
||||
@ -266,6 +267,10 @@ class CephFSTestCase(CephTestCase):
|
||||
if core_dir: # Non-default core_pattern with a directory in it
|
||||
# We have seen a core_pattern that looks like it's from teuthology's coredump
|
||||
# task, so proceed to clear out the core file
|
||||
if core_dir[0] == '|':
|
||||
log.info("Piped core dumps to program {0}, skip cleaning".format(core_dir[1:]))
|
||||
return;
|
||||
|
||||
log.info("Clearing core from directory: {0}".format(core_dir))
|
||||
|
||||
# Verify that we see the expected single coredump
|
||||
@ -304,3 +309,11 @@ class CephFSTestCase(CephTestCase):
|
||||
return subtrees
|
||||
time.sleep(pause)
|
||||
raise RuntimeError("rank {0} failed to reach desired subtree state", rank)
|
||||
|
||||
def _wait_until_scrub_complete(self, path="/", recursive=True):
|
||||
out_json = self.fs.rank_tell(["scrub", "start", path] + ["recursive"] if recursive else [])
|
||||
with safe_while(sleep=10, tries=10) as proceed:
|
||||
while proceed():
|
||||
out_json = self.fs.rank_tell(["scrub", "status"])
|
||||
if out_json['status'] == "no active scrubs running":
|
||||
break;
|
||||
|
||||
@ -27,7 +27,9 @@ class FuseMount(CephFSMount):
|
||||
self.inst = None
|
||||
self.addr = None
|
||||
|
||||
def mount(self, mount_path=None, mount_fs_name=None):
|
||||
def mount(self, mount_path=None, mount_fs_name=None, mountpoint=None):
|
||||
if mountpoint is not None:
|
||||
self.mountpoint = mountpoint
|
||||
self.setupfs(name=mount_fs_name)
|
||||
|
||||
try:
|
||||
@ -51,14 +53,8 @@ class FuseMount(CephFSMount):
|
||||
log.info('Mounting ceph-fuse client.{id} at {remote} {mnt}...'.format(
|
||||
id=self.client_id, remote=self.client_remote, mnt=self.mountpoint))
|
||||
|
||||
self.client_remote.run(
|
||||
args=[
|
||||
'mkdir',
|
||||
'--',
|
||||
self.mountpoint,
|
||||
],
|
||||
timeout=(15*60)
|
||||
)
|
||||
self.client_remote.run(args=['mkdir', '-p', self.mountpoint],
|
||||
timeout=(15*60), cwd=self.test_dir)
|
||||
|
||||
run_cmd = [
|
||||
'sudo',
|
||||
@ -83,6 +79,7 @@ class FuseMount(CephFSMount):
|
||||
self.mountpoint,
|
||||
]
|
||||
|
||||
cwd = self.test_dir
|
||||
if self.client_config.get('valgrind') is not None:
|
||||
run_cmd = misc.get_valgrind_args(
|
||||
self.test_dir,
|
||||
@ -90,17 +87,23 @@ class FuseMount(CephFSMount):
|
||||
run_cmd,
|
||||
self.client_config.get('valgrind'),
|
||||
)
|
||||
cwd = None # misc.get_valgrind_args chdir for us
|
||||
|
||||
run_cmd.extend(fuse_cmd)
|
||||
|
||||
def list_connections():
|
||||
from teuthology.misc import get_system_type
|
||||
|
||||
conn_dir = "/sys/fs/fuse/connections"
|
||||
|
||||
self.client_remote.run(args=['sudo', 'modprobe', 'fuse'],
|
||||
check_status=False)
|
||||
self.client_remote.run(
|
||||
args=["sudo", "mount", "-t", "fusectl", "/sys/fs/fuse/connections", "/sys/fs/fuse/connections"],
|
||||
check_status=False,
|
||||
timeout=(15*60)
|
||||
)
|
||||
args=["sudo", "mount", "-t", "fusectl", conn_dir, conn_dir],
|
||||
check_status=False, timeout=(30))
|
||||
|
||||
try:
|
||||
ls_str = self.client_remote.sh("ls /sys/fs/fuse/connections",
|
||||
ls_str = self.client_remote.sh("ls " + conn_dir,
|
||||
stdout=StringIO(),
|
||||
timeout=(15*60)).strip()
|
||||
except CommandFailedError:
|
||||
@ -118,6 +121,7 @@ class FuseMount(CephFSMount):
|
||||
|
||||
proc = self.client_remote.run(
|
||||
args=run_cmd,
|
||||
cwd=cwd,
|
||||
logger=log.getChild('ceph-fuse.{id}'.format(id=self.client_id)),
|
||||
stdin=run.PIPE,
|
||||
wait=False,
|
||||
@ -186,6 +190,7 @@ class FuseMount(CephFSMount):
|
||||
'--',
|
||||
self.mountpoint,
|
||||
],
|
||||
cwd=self.test_dir,
|
||||
stdout=StringIO(),
|
||||
stderr=StringIO(),
|
||||
wait=False,
|
||||
@ -231,7 +236,7 @@ class FuseMount(CephFSMount):
|
||||
# unrestricted access to the filesystem mount.
|
||||
try:
|
||||
stderr = StringIO()
|
||||
self.client_remote.run(args=['sudo', 'chmod', '1777', self.mountpoint], timeout=(15*60), stderr=stderr)
|
||||
self.client_remote.run(args=['sudo', 'chmod', '1777', self.mountpoint], timeout=(15*60), cwd=self.test_dir, stderr=stderr)
|
||||
except run.CommandFailedError:
|
||||
stderr = stderr.getvalue()
|
||||
if "Read-only file system".lower() in stderr.lower():
|
||||
@ -240,7 +245,7 @@ class FuseMount(CephFSMount):
|
||||
raise
|
||||
|
||||
def _mountpoint_exists(self):
|
||||
return self.client_remote.run(args=["ls", "-d", self.mountpoint], check_status=False, timeout=(15*60)).exitstatus == 0
|
||||
return self.client_remote.run(args=["ls", "-d", self.mountpoint], check_status=False, cwd=self.test_dir, timeout=(15*60)).exitstatus == 0
|
||||
|
||||
def umount(self):
|
||||
try:
|
||||
@ -252,6 +257,7 @@ class FuseMount(CephFSMount):
|
||||
'-u',
|
||||
self.mountpoint,
|
||||
],
|
||||
cwd=self.test_dir,
|
||||
timeout=(30*60),
|
||||
)
|
||||
except run.CommandFailedError:
|
||||
@ -346,8 +352,10 @@ class FuseMount(CephFSMount):
|
||||
'--',
|
||||
self.mountpoint,
|
||||
],
|
||||
cwd=self.test_dir,
|
||||
stderr=stderr,
|
||||
timeout=(60*5)
|
||||
timeout=(60*5),
|
||||
check_status=False,
|
||||
)
|
||||
except CommandFailedError:
|
||||
if "No such file or directory" in stderr.getvalue():
|
||||
@ -396,6 +404,7 @@ class FuseMount(CephFSMount):
|
||||
'-rf',
|
||||
self.mountpoint,
|
||||
],
|
||||
cwd=self.test_dir,
|
||||
timeout=(60*5)
|
||||
)
|
||||
|
||||
|
||||
@ -26,20 +26,16 @@ class KernelMount(CephFSMount):
|
||||
self.ipmi_password = ipmi_password
|
||||
self.ipmi_domain = ipmi_domain
|
||||
|
||||
def mount(self, mount_path=None, mount_fs_name=None):
|
||||
def mount(self, mount_path=None, mount_fs_name=None, mountpoint=None):
|
||||
if mountpoint is not None:
|
||||
self.mountpoint = mountpoint
|
||||
self.setupfs(name=mount_fs_name)
|
||||
|
||||
log.info('Mounting kclient client.{id} at {remote} {mnt}...'.format(
|
||||
id=self.client_id, remote=self.client_remote, mnt=self.mountpoint))
|
||||
|
||||
self.client_remote.run(
|
||||
args=[
|
||||
'mkdir',
|
||||
'--',
|
||||
self.mountpoint,
|
||||
],
|
||||
timeout=(5*60),
|
||||
)
|
||||
self.client_remote.run(args=['mkdir', '-p', self.mountpoint],
|
||||
timeout=(5*60))
|
||||
|
||||
if mount_path is None:
|
||||
mount_path = "/"
|
||||
@ -187,6 +183,7 @@ class KernelMount(CephFSMount):
|
||||
self.mountpoint,
|
||||
],
|
||||
timeout=(5*60),
|
||||
check_status=False,
|
||||
)
|
||||
|
||||
def _find_debug_dir(self):
|
||||
|
||||
@ -28,6 +28,7 @@ class CephFSMount(object):
|
||||
self.client_id = client_id
|
||||
self.client_remote = client_remote
|
||||
self.mountpoint_dir_name = 'mnt.{id}'.format(id=self.client_id)
|
||||
self._mountpoint = None
|
||||
self.fs = None
|
||||
|
||||
self.test_files = ['a', 'b', 'c']
|
||||
@ -36,8 +37,16 @@ class CephFSMount(object):
|
||||
|
||||
@property
|
||||
def mountpoint(self):
|
||||
return os.path.join(
|
||||
self.test_dir, '{dir_name}'.format(dir_name=self.mountpoint_dir_name))
|
||||
if self._mountpoint == None:
|
||||
self._mountpoint= os.path.join(
|
||||
self.test_dir, '{dir_name}'.format(dir_name=self.mountpoint_dir_name))
|
||||
return self._mountpoint
|
||||
|
||||
@mountpoint.setter
|
||||
def mountpoint(self, path):
|
||||
if not isinstance(path, str):
|
||||
raise RuntimeError('path should be of str type.')
|
||||
self._mountpoint = path
|
||||
|
||||
def is_mounted(self):
|
||||
raise NotImplementedError()
|
||||
@ -51,7 +60,7 @@ class CephFSMount(object):
|
||||
self.fs.wait_for_daemons()
|
||||
log.info('Ready to start {}...'.format(type(self).__name__))
|
||||
|
||||
def mount(self, mount_path=None, mount_fs_name=None):
|
||||
def mount(self, mount_path=None, mount_fs_name=None, mountpoint=None):
|
||||
raise NotImplementedError()
|
||||
|
||||
def umount(self):
|
||||
@ -440,13 +449,14 @@ class CephFSMount(object):
|
||||
n = {count}
|
||||
abs_path = "{abs_path}"
|
||||
|
||||
if not os.path.exists(os.path.dirname(abs_path)):
|
||||
os.makedirs(os.path.dirname(abs_path))
|
||||
if not os.path.exists(abs_path):
|
||||
os.makedirs(abs_path)
|
||||
|
||||
handles = []
|
||||
for i in range(0, n):
|
||||
fname = "{{0}}_{{1}}".format(abs_path, i)
|
||||
handles.append(open(fname, 'w'))
|
||||
fname = "file_"+str(i)
|
||||
path = os.path.join(abs_path, fname)
|
||||
handles.append(open(path, 'w'))
|
||||
|
||||
while True:
|
||||
time.sleep(1)
|
||||
|
||||
@ -8,6 +8,7 @@ import logging
|
||||
from textwrap import dedent
|
||||
from unittest import SkipTest
|
||||
from teuthology.orchestra.run import CommandFailedError
|
||||
from tasks.ceph_test_case import TestTimeoutError
|
||||
from tasks.cephfs.cephfs_test_case import CephFSTestCase, needs_trimming
|
||||
from tasks.cephfs.fuse_mount import FuseMount
|
||||
import os
|
||||
@ -39,20 +40,17 @@ class TestClientLimits(CephFSTestCase):
|
||||
:param use_subdir: whether to put test files in a subdir or use root
|
||||
"""
|
||||
|
||||
cache_size = open_files // 2
|
||||
self.config_set('mds', 'mds_cache_memory_limit', "1K")
|
||||
self.config_set('mds', 'mds_recall_max_caps', int(open_files/2))
|
||||
self.config_set('mds', 'mds_recall_warning_threshold', open_files)
|
||||
|
||||
self.set_conf('mds', 'mds cache size', cache_size)
|
||||
self.set_conf('mds', 'mds_recall_max_caps', open_files // 2)
|
||||
self.set_conf('mds', 'mds_recall_warning_threshold', open_files)
|
||||
self.fs.mds_fail_restart()
|
||||
self.fs.wait_for_daemons()
|
||||
|
||||
mds_min_caps_per_client = int(self.fs.get_config("mds_min_caps_per_client"))
|
||||
mds_recall_warning_decay_rate = float(self.fs.get_config("mds_recall_warning_decay_rate"))
|
||||
self.assertTrue(open_files >= mds_min_caps_per_client)
|
||||
mds_min_caps_per_client = int(self.config_get('mds.a', "mds_min_caps_per_client"))
|
||||
self.config_set('mds', 'mds_min_caps_working_set', mds_min_caps_per_client)
|
||||
mds_recall_warning_decay_rate = float(self.config_get('mds.a', "mds_recall_warning_decay_rate"))
|
||||
self.assertGreaterEqual(open_files, mds_min_caps_per_client)
|
||||
|
||||
mount_a_client_id = self.mount_a.get_global_id()
|
||||
path = "subdir/mount_a" if use_subdir else "mount_a"
|
||||
path = "subdir" if use_subdir else "."
|
||||
open_proc = self.mount_a.open_n_background(path, open_files)
|
||||
|
||||
# Client should now hold:
|
||||
@ -88,8 +86,6 @@ class TestClientLimits(CephFSTestCase):
|
||||
num_caps = self.get_session(mount_a_client_id)['num_caps']
|
||||
if num_caps <= mds_min_caps_per_client:
|
||||
return True
|
||||
elif num_caps < cache_size:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
@ -107,6 +103,53 @@ class TestClientLimits(CephFSTestCase):
|
||||
def test_client_pin_mincaps(self):
|
||||
self._test_client_pin(True, 200)
|
||||
|
||||
def test_client_min_caps_working_set(self):
|
||||
"""
|
||||
When a client has inodes pinned in its cache (open files), that the MDS
|
||||
will not warn about the client not responding to cache pressure when
|
||||
the number of caps is below mds_min_caps_working_set.
|
||||
"""
|
||||
|
||||
# Set MDS cache memory limit to a low value that will make the MDS to
|
||||
# ask the client to trim the caps.
|
||||
cache_memory_limit = "1K"
|
||||
open_files = 400
|
||||
|
||||
self.config_set('mds', 'mds_cache_memory_limit', cache_memory_limit)
|
||||
self.config_set('mds', 'mds_recall_max_caps', int(open_files/2))
|
||||
self.config_set('mds', 'mds_recall_warning_threshold', open_files)
|
||||
self.config_set('mds', 'mds_min_caps_working_set', open_files*2)
|
||||
|
||||
mds_min_caps_per_client = int(self.config_get('mds.a', "mds_min_caps_per_client"))
|
||||
mds_recall_warning_decay_rate = float(self.config_get('mds.a', "mds_recall_warning_decay_rate"))
|
||||
self.assertGreaterEqual(open_files, mds_min_caps_per_client)
|
||||
|
||||
mount_a_client_id = self.mount_a.get_global_id()
|
||||
self.mount_a.open_n_background("subdir", open_files)
|
||||
|
||||
# Client should now hold:
|
||||
# `open_files` caps for the open files
|
||||
# 1 cap for root
|
||||
# 1 cap for subdir
|
||||
self.wait_until_equal(lambda: self.get_session(mount_a_client_id)['num_caps'],
|
||||
open_files + 2,
|
||||
timeout=600,
|
||||
reject_fn=lambda x: x > open_files + 2)
|
||||
|
||||
# We can also test that the MDS health warning for oversized
|
||||
# cache is functioning as intended.
|
||||
self.wait_for_health("MDS_CACHE_OVERSIZED", mds_recall_warning_decay_rate*2)
|
||||
|
||||
try:
|
||||
# MDS should not be happy about that but it's not sending
|
||||
# MDS_CLIENT_RECALL warnings because the client's caps are below
|
||||
# mds_min_caps_working_set.
|
||||
self.wait_for_health("MDS_CLIENT_RECALL", mds_recall_warning_decay_rate*2)
|
||||
except TestTimeoutError:
|
||||
pass
|
||||
else:
|
||||
raise RuntimeError("expected no client recall warning")
|
||||
|
||||
def test_client_release_bug(self):
|
||||
"""
|
||||
When a client has a bug (which we will simulate) preventing it from releasing caps,
|
||||
@ -240,11 +283,9 @@ class TestClientLimits(CephFSTestCase):
|
||||
That the MDS will not let a client sit above mds_max_caps_per_client caps.
|
||||
"""
|
||||
|
||||
mds_min_caps_per_client = int(self.fs.get_config("mds_min_caps_per_client"))
|
||||
mds_min_caps_per_client = int(self.config_get('mds.a', "mds_min_caps_per_client"))
|
||||
mds_max_caps_per_client = 2*mds_min_caps_per_client
|
||||
self.set_conf('mds', 'mds_max_caps_per_client', mds_max_caps_per_client)
|
||||
self.fs.mds_fail_restart()
|
||||
self.fs.wait_for_daemons()
|
||||
self.config_set('mds', 'mds_max_caps_per_client', mds_max_caps_per_client)
|
||||
|
||||
self.mount_a.create_n_files("foo/", 3*mds_max_caps_per_client, sync=True)
|
||||
|
||||
|
||||
@ -75,6 +75,9 @@ class BacktraceWorkload(Workload):
|
||||
self._filesystem.mds_asok(["flush", "journal"])
|
||||
self._filesystem._write_data_xattr(st['st_ino'], "parent", "")
|
||||
|
||||
def create_files(self, nfiles=1000):
|
||||
self._mount.create_n_files("scrub-new-files/file", nfiles)
|
||||
|
||||
|
||||
class DupInodeWorkload(Workload):
|
||||
"""
|
||||
@ -89,7 +92,7 @@ class DupInodeWorkload(Workload):
|
||||
|
||||
def damage(self):
|
||||
temp_bin_path = "/tmp/10000000000.00000000_omap.bin"
|
||||
self._mount.umount()
|
||||
self._mount.umount_wait()
|
||||
self._filesystem.mds_asok(["flush", "journal"])
|
||||
self._filesystem.mds_stop()
|
||||
self._filesystem.rados(["getomapval", "10000000000.00000000",
|
||||
@ -144,6 +147,27 @@ class TestScrub(CephFSTestCase):
|
||||
errors[0].exception, errors[0].backtrace
|
||||
))
|
||||
|
||||
def _get_damage_count(self, damage_type='backtrace'):
|
||||
out_json = self.fs.rank_tell(["damage", "ls"])
|
||||
self.assertNotEqual(out_json, None)
|
||||
|
||||
damage_count = 0
|
||||
for it in out_json:
|
||||
if it['damage_type'] == damage_type:
|
||||
damage_count += 1
|
||||
return damage_count
|
||||
|
||||
def _scrub_new_files(self, workload):
|
||||
"""
|
||||
That scrubbing new files does not lead to errors
|
||||
"""
|
||||
workload.create_files(1000)
|
||||
self._wait_until_scrub_complete()
|
||||
self.assertEqual(self._get_damage_count(), 0)
|
||||
|
||||
def test_scrub_backtrace_for_new_files(self):
|
||||
self._scrub_new_files(BacktraceWorkload(self.fs, self.mount_a))
|
||||
|
||||
def test_scrub_backtrace(self):
|
||||
self._scrub(BacktraceWorkload(self.fs, self.mount_a))
|
||||
|
||||
|
||||
@ -29,6 +29,9 @@ class TestVolumes(CephFSTestCase):
|
||||
def _fs_cmd(self, *args):
|
||||
return self.mgr_cluster.mon_manager.raw_cluster_cmd("fs", *args)
|
||||
|
||||
def _raw_cmd(self, *args):
|
||||
return self.mgr_cluster.mon_manager.raw_cluster_cmd(*args)
|
||||
|
||||
def __check_clone_state(self, state, clone, clone_group=None, timo=120):
|
||||
check = 0
|
||||
args = ["clone", "status", self.volname, clone]
|
||||
@ -105,28 +108,33 @@ class TestVolumes(CephFSTestCase):
|
||||
self._verify_clone_attrs(subvolume, clone, source_group=source_group, clone_group=clone_group)
|
||||
|
||||
def _generate_random_volume_name(self, count=1):
|
||||
r = random.sample(range(10000), count)
|
||||
volumes = ["{0}_{1}".format(TestVolumes.TEST_VOLUME_PREFIX, c) for c in r]
|
||||
n = self.volume_start
|
||||
volumes = [f"{TestVolumes.TEST_VOLUME_PREFIX}_{i:016}" for i in range(n, n+count)]
|
||||
self.volume_start += count
|
||||
return volumes[0] if count == 1 else volumes
|
||||
|
||||
def _generate_random_subvolume_name(self, count=1):
|
||||
r = random.sample(range(10000), count)
|
||||
subvolumes = ["{0}_{1}".format(TestVolumes.TEST_SUBVOLUME_PREFIX, c) for c in r]
|
||||
n = self.subvolume_start
|
||||
subvolumes = [f"{TestVolumes.TEST_SUBVOLUME_PREFIX}_{i:016}" for i in range(n, n+count)]
|
||||
self.subvolume_start += count
|
||||
return subvolumes[0] if count == 1 else subvolumes
|
||||
|
||||
def _generate_random_group_name(self, count=1):
|
||||
r = random.sample(range(100), count)
|
||||
groups = ["{0}_{1}".format(TestVolumes.TEST_GROUP_PREFIX, c) for c in r]
|
||||
n = self.group_start
|
||||
groups = [f"{TestVolumes.TEST_GROUP_PREFIX}_{i:016}" for i in range(n, n+count)]
|
||||
self.group_start += count
|
||||
return groups[0] if count == 1 else groups
|
||||
|
||||
def _generate_random_snapshot_name(self, count=1):
|
||||
r = random.sample(range(100), count)
|
||||
snaps = ["{0}_{1}".format(TestVolumes.TEST_SNAPSHOT_PREFIX, c) for c in r]
|
||||
n = self.snapshot_start
|
||||
snaps = [f"{TestVolumes.TEST_SNAPSHOT_PREFIX}_{i:016}" for i in range(n, n+count)]
|
||||
self.snapshot_start += count
|
||||
return snaps[0] if count == 1 else snaps
|
||||
|
||||
def _generate_random_clone_name(self, count=1):
|
||||
r = random.sample(range(1000), count)
|
||||
clones = ["{0}_{1}".format(TestVolumes.TEST_CLONE_PREFIX, c) for c in r]
|
||||
n = self.clone_start
|
||||
clones = [f"{TestVolumes.TEST_CLONE_PREFIX}_{i:016}" for i in range(n, n+count)]
|
||||
self.clone_start += count
|
||||
return clones[0] if count == 1 else clones
|
||||
|
||||
def _enable_multi_fs(self):
|
||||
@ -164,6 +172,14 @@ class TestVolumes(CephFSTestCase):
|
||||
subvol_md = self._fs_cmd(*args)
|
||||
return subvol_md
|
||||
|
||||
def _get_subvolume_snapshot_info(self, vol_name, subvol_name, snapname, group_name=None):
|
||||
args = ["subvolume", "snapshot", "info", vol_name, subvol_name, snapname]
|
||||
if group_name:
|
||||
args.append(group_name)
|
||||
args = tuple(args)
|
||||
snap_md = self._fs_cmd(*args)
|
||||
return snap_md
|
||||
|
||||
def _delete_test_volume(self):
|
||||
self._fs_cmd("volume", "rm", self.volname, "--yes-i-really-mean-it")
|
||||
|
||||
@ -217,6 +233,12 @@ class TestVolumes(CephFSTestCase):
|
||||
self.vol_created = False
|
||||
self._enable_multi_fs()
|
||||
self._create_or_reuse_test_volume()
|
||||
self.config_set('mon', 'mon_allow_pool_delete', True)
|
||||
self.volume_start = random.randint(1, (1<<20))
|
||||
self.subvolume_start = random.randint(1, (1<<20))
|
||||
self.group_start = random.randint(1, (1<<20))
|
||||
self.snapshot_start = random.randint(1, (1<<20))
|
||||
self.clone_start = random.randint(1, (1<<20))
|
||||
|
||||
def tearDown(self):
|
||||
if self.vol_created:
|
||||
@ -302,6 +324,52 @@ class TestVolumes(CephFSTestCase):
|
||||
else:
|
||||
raise RuntimeError("expected the 'fs volume rm' command to fail.")
|
||||
|
||||
def test_volume_rm_arbitrary_pool_removal(self):
|
||||
"""
|
||||
That the arbitrary pool added to the volume out of band is removed
|
||||
successfully on volume removal.
|
||||
"""
|
||||
new_pool = "new_pool"
|
||||
# add arbitrary data pool
|
||||
self.fs.add_data_pool(new_pool)
|
||||
self._fs_cmd("volume", "rm", self.volname, "--yes-i-really-mean-it")
|
||||
|
||||
#check if fs is gone
|
||||
volumes = json.loads(self._fs_cmd("volume", "ls", "--format=json-pretty"))
|
||||
volnames = [volume['name'] for volume in volumes]
|
||||
self.assertNotIn(self.volname, volnames)
|
||||
|
||||
#check if osd pools are gone
|
||||
pools = json.loads(self._raw_cmd("osd", "pool", "ls", "detail", "--format=json-pretty"))
|
||||
for pool in pools:
|
||||
self.assertNotIn(self.volname, pool["application_metadata"].keys())
|
||||
|
||||
def test_volume_rm_when_mon_delete_pool_false(self):
|
||||
"""
|
||||
That the volume can only be removed when mon_allowd_pool_delete is set
|
||||
to true and verify that the pools are removed after volume deletion.
|
||||
"""
|
||||
self.config_set('mon', 'mon_allow_pool_delete', False)
|
||||
try:
|
||||
self._fs_cmd("volume", "rm", self.volname, "--yes-i-really-mean-it")
|
||||
except CommandFailedError as ce:
|
||||
self.assertEqual(ce.exitstatus, errno.EPERM,
|
||||
"expected the 'fs volume rm' command to fail with EPERM, "
|
||||
"but it failed with {0}".format(ce.exitstatus))
|
||||
self.config_set('mon', 'mon_allow_pool_delete', True)
|
||||
self._fs_cmd("volume", "rm", self.volname, "--yes-i-really-mean-it")
|
||||
|
||||
#check if fs is gone
|
||||
volumes = json.loads(self._fs_cmd("volume", "ls", "--format=json-pretty"))
|
||||
volnames = [volume['name'] for volume in volumes]
|
||||
self.assertNotIn(self.volname, volnames,
|
||||
"volume {0} exists after removal".format(self.volname))
|
||||
#check if pools are gone
|
||||
pools = json.loads(self._raw_cmd("osd", "pool", "ls", "detail", "--format=json-pretty"))
|
||||
for pool in pools:
|
||||
self.assertNotIn(self.volname, pool["application_metadata"].keys(),
|
||||
"pool {0} exists after volume removal".format(pool["pool_name"]))
|
||||
|
||||
### basic subvolume operations
|
||||
|
||||
def test_subvolume_create_and_rm(self):
|
||||
@ -784,7 +852,7 @@ class TestVolumes(CephFSTestCase):
|
||||
|
||||
subvol_md = ["atime", "bytes_pcent", "bytes_quota", "bytes_used", "created_at", "ctime",
|
||||
"data_pool", "gid", "mode", "mon_addrs", "mtime", "path", "pool_namespace",
|
||||
"type", "uid"]
|
||||
"type", "uid", "features"]
|
||||
|
||||
# create subvolume
|
||||
subvolume = self._generate_random_subvolume_name()
|
||||
@ -792,37 +860,34 @@ class TestVolumes(CephFSTestCase):
|
||||
|
||||
# get subvolume metadata
|
||||
subvol_info = json.loads(self._get_subvolume_info(self.volname, subvolume))
|
||||
if len(subvol_info) == 0:
|
||||
raise RuntimeError("Expected the 'fs subvolume info' command to list metadata of subvolume")
|
||||
self.assertNotEqual(len(subvol_info), 0, "expected the 'fs subvolume info' command to list metadata of subvolume")
|
||||
for md in subvol_md:
|
||||
if md not in subvol_info.keys():
|
||||
raise RuntimeError("%s not present in the metadata of subvolume" % md)
|
||||
self.assertIn(md, subvol_info.keys(), "'{0}' key not present in metadata of subvolume".format(md))
|
||||
|
||||
if subvol_info["bytes_pcent"] != "undefined":
|
||||
raise RuntimeError("bytes_pcent should be set to undefined if quota is not set")
|
||||
self.assertEqual(subvol_info["bytes_pcent"], "undefined", "bytes_pcent should be set to undefined if quota is not set")
|
||||
self.assertEqual(subvol_info["bytes_quota"], "infinite", "bytes_quota should be set to infinite if quota is not set")
|
||||
self.assertEqual(subvol_info["pool_namespace"], "", "expected pool namespace to be empty")
|
||||
|
||||
if subvol_info["bytes_quota"] != "infinite":
|
||||
raise RuntimeError("bytes_quota should be set to infinite if quota is not set")
|
||||
self.assertEqual(subvol_info["pool_namespace"], "")
|
||||
self.assertEqual(len(subvol_info["features"]), 2,
|
||||
msg="expected 2 features, found '{0}' ({1})".format(len(subvol_info["features"]), subvol_info["features"]))
|
||||
for feature in ['snapshot-clone', 'snapshot-autoprotect']:
|
||||
self.assertIn(feature, subvol_info["features"], msg="expected feature '{0}' in subvolume".format(feature))
|
||||
|
||||
nsize = self.DEFAULT_FILE_SIZE*1024*1024
|
||||
try:
|
||||
self._fs_cmd("subvolume", "resize", self.volname, subvolume, str(nsize))
|
||||
except CommandFailedError:
|
||||
raise RuntimeError("expected the 'fs subvolume resize' command to succeed")
|
||||
self._fs_cmd("subvolume", "resize", self.volname, subvolume, str(nsize))
|
||||
|
||||
# get subvolume metadata after quota set
|
||||
subvol_info = json.loads(self._get_subvolume_info(self.volname, subvolume))
|
||||
if len(subvol_info) == 0:
|
||||
raise RuntimeError("Expected the 'fs subvolume info' command to list metadata of subvolume")
|
||||
if subvol_info["bytes_pcent"] == "undefined":
|
||||
raise RuntimeError("bytes_pcent should not be set to undefined if quota is set")
|
||||
self.assertNotEqual(len(subvol_info), 0, "expected the 'fs subvolume info' command to list metadata of subvolume")
|
||||
|
||||
if subvol_info["bytes_quota"] == "infinite":
|
||||
raise RuntimeError("bytes_quota should not be set to infinite if quota is set")
|
||||
self.assertNotEqual(subvol_info["bytes_pcent"], "undefined", "bytes_pcent should not be set to undefined if quota is not set")
|
||||
self.assertNotEqual(subvol_info["bytes_quota"], "infinite", "bytes_quota should not be set to infinite if quota is not set")
|
||||
self.assertEqual(subvol_info["type"], "subvolume", "type should be set to subvolume")
|
||||
|
||||
if subvol_info["type"] != "subvolume":
|
||||
raise RuntimeError("type should be set to subvolume")
|
||||
self.assertEqual(len(subvol_info["features"]), 2,
|
||||
msg="expected 2 features, found '{0}' ({1})".format(len(subvol_info["features"]), subvol_info["features"]))
|
||||
for feature in ['snapshot-clone', 'snapshot-autoprotect']:
|
||||
self.assertIn(feature, subvol_info["features"], msg="expected feature '{0}' in subvolume".format(feature))
|
||||
|
||||
# remove subvolumes
|
||||
self._fs_cmd("subvolume", "rm", self.volname, subvolume)
|
||||
@ -850,18 +915,12 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
@ -904,8 +963,7 @@ class TestVolumes(CephFSTestCase):
|
||||
self._fs_cmd("subvolumegroup", "rm", self.volname, group)
|
||||
|
||||
def test_subvolume_group_create_with_desired_data_pool_layout(self):
|
||||
group1 = self._generate_random_group_name()
|
||||
group2 = self._generate_random_group_name()
|
||||
group1, group2 = self._generate_random_group_name(2)
|
||||
|
||||
# create group
|
||||
self._fs_cmd("subvolumegroup", "create", self.volname, group1)
|
||||
@ -966,8 +1024,7 @@ class TestVolumes(CephFSTestCase):
|
||||
raise RuntimeError("expected the 'fs subvolumegroup getpath' command to fail")
|
||||
|
||||
def test_subvolume_create_with_desired_data_pool_layout_in_group(self):
|
||||
subvol1 = self._generate_random_subvolume_name()
|
||||
subvol2 = self._generate_random_subvolume_name()
|
||||
subvol1, subvol2 = self._generate_random_subvolume_name(2)
|
||||
group = self._generate_random_group_name()
|
||||
|
||||
# create group. this also helps set default pool layout for subvolumes
|
||||
@ -998,8 +1055,7 @@ class TestVolumes(CephFSTestCase):
|
||||
self._fs_cmd("subvolumegroup", "rm", self.volname, group)
|
||||
|
||||
def test_subvolume_group_create_with_desired_mode(self):
|
||||
group1 = self._generate_random_group_name()
|
||||
group2 = self._generate_random_group_name()
|
||||
group1, group2 = self._generate_random_group_name(2)
|
||||
# default mode
|
||||
expected_mode1 = "755"
|
||||
# desired mode
|
||||
@ -1047,9 +1103,8 @@ class TestVolumes(CephFSTestCase):
|
||||
self._fs_cmd("subvolumegroup", "rm", self.volname, subvolgroupname)
|
||||
|
||||
def test_subvolume_create_with_desired_mode_in_group(self):
|
||||
subvol1 = self._generate_random_subvolume_name()
|
||||
subvol2 = self._generate_random_subvolume_name()
|
||||
subvol3 = self._generate_random_subvolume_name()
|
||||
subvol1, subvol2, subvol3 = self._generate_random_subvolume_name(3)
|
||||
|
||||
group = self._generate_random_group_name()
|
||||
# default mode
|
||||
expected_mode1 = "755"
|
||||
@ -1184,6 +1239,42 @@ class TestVolumes(CephFSTestCase):
|
||||
# verify trash dir is clean
|
||||
self._wait_for_trash_empty()
|
||||
|
||||
def test_subvolume_snapshot_info(self):
|
||||
|
||||
"""
|
||||
tests the 'fs subvolume snapshot info' command
|
||||
"""
|
||||
|
||||
snap_metadata = ["created_at", "data_pool", "has_pending_clones", "size"]
|
||||
|
||||
subvolume = self._generate_random_subvolume_name()
|
||||
snapshot = self._generate_random_snapshot_name()
|
||||
|
||||
# create subvolume
|
||||
self._fs_cmd("subvolume", "create", self.volname, subvolume)
|
||||
|
||||
# do some IO
|
||||
self._do_subvolume_io(subvolume, number_of_files=1)
|
||||
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
snap_info = json.loads(self._get_subvolume_snapshot_info(self.volname, subvolume, snapshot))
|
||||
self.assertNotEqual(len(snap_info), 0)
|
||||
for md in snap_metadata:
|
||||
if md not in snap_info:
|
||||
raise RuntimeError("%s not present in the metadata of subvolume snapshot" % md)
|
||||
self.assertEqual(snap_info["has_pending_clones"], "no")
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove subvolume
|
||||
self._fs_cmd("subvolume", "rm", self.volname, subvolume)
|
||||
|
||||
# verify trash dir is clean
|
||||
self._wait_for_trash_empty()
|
||||
|
||||
def test_subvolume_snapshot_create_idempotence(self):
|
||||
subvolume = self._generate_random_subvolume_name()
|
||||
snapshot = self._generate_random_snapshot_name()
|
||||
@ -1503,88 +1594,11 @@ class TestVolumes(CephFSTestCase):
|
||||
# verify trash dir is clean
|
||||
self._wait_for_trash_empty()
|
||||
|
||||
def test_subvolume_snapshot_protect_unprotect(self):
|
||||
subvolume = self._generate_random_subvolume_name()
|
||||
snapshot = self._generate_random_snapshot_name()
|
||||
|
||||
# create subvolume
|
||||
self._fs_cmd("subvolume", "create", self.volname, subvolume)
|
||||
|
||||
# protect a nonexistent snapshot
|
||||
try:
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
except CommandFailedError as ce:
|
||||
if ce.exitstatus != errno.ENOENT:
|
||||
raise RuntimeError("invalid error code when protecting a non-existing snapshot")
|
||||
else:
|
||||
raise RuntimeError("expected protection of non existent snapshot to fail")
|
||||
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# protecting snapshot again, should return EEXIST
|
||||
try:
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
except CommandFailedError as ce:
|
||||
if ce.exitstatus != errno.EEXIST:
|
||||
raise RuntimeError("invalid error code when protecting a protected snapshot")
|
||||
else:
|
||||
raise RuntimeError("expected protection of already protected snapshot to fail")
|
||||
|
||||
# remove snapshot should fail since the snapshot is protected
|
||||
try:
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
except CommandFailedError as ce:
|
||||
if ce.exitstatus != errno.EINVAL:
|
||||
raise RuntimeError("invalid error code when removing a protected snapshot")
|
||||
else:
|
||||
raise RuntimeError("expected removal of protected snapshot to fail")
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove subvolume
|
||||
self._fs_cmd("subvolume", "rm", self.volname, subvolume)
|
||||
|
||||
# verify trash dir is clean
|
||||
self._wait_for_trash_empty()
|
||||
|
||||
def test_subvolume_snapshot_clone_unprotected_snapshot(self):
|
||||
subvolume = self._generate_random_subvolume_name()
|
||||
snapshot = self._generate_random_snapshot_name()
|
||||
clone = self._generate_random_clone_name()
|
||||
|
||||
# create subvolume
|
||||
self._fs_cmd("subvolume", "create", self.volname, subvolume)
|
||||
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# clone a non protected snapshot
|
||||
try:
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
except CommandFailedError as ce:
|
||||
if ce.exitstatus != errno.EINVAL:
|
||||
raise RuntimeError("invalid error code when cloning a non protected snapshot")
|
||||
else:
|
||||
raise RuntimeError("expected cloning of unprotected snapshot to fail")
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove subvolumes
|
||||
self._fs_cmd("subvolume", "rm", self.volname, subvolume)
|
||||
|
||||
# verify trash dir is clean
|
||||
self._wait_for_trash_empty()
|
||||
|
||||
def test_subvolume_snapshot_clone(self):
|
||||
def test_subvolume_snapshot_protect_unprotect_sanity(self):
|
||||
"""
|
||||
Snapshot protect/unprotect commands are deprecated. This test exists to ensure that
|
||||
invoking the command does not cause errors, till they are removed from a subsequent release.
|
||||
"""
|
||||
subvolume = self._generate_random_subvolume_name()
|
||||
snapshot = self._generate_random_snapshot_name()
|
||||
clone = self._generate_random_clone_name()
|
||||
@ -1604,15 +1618,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
|
||||
# unprotecting when a clone is in progress should fail
|
||||
try:
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
except CommandFailedError as ce:
|
||||
if ce.exitstatus != errno.EEXIST:
|
||||
raise RuntimeError("invalid error code when unprotecting snapshot during clone")
|
||||
else:
|
||||
raise RuntimeError("expected unprotecting a snapshot to fail since it has pending clones")
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone)
|
||||
|
||||
@ -1632,6 +1637,39 @@ class TestVolumes(CephFSTestCase):
|
||||
# verify trash dir is clean
|
||||
self._wait_for_trash_empty()
|
||||
|
||||
def test_subvolume_snapshot_clone(self):
|
||||
subvolume = self._generate_random_subvolume_name()
|
||||
snapshot = self._generate_random_snapshot_name()
|
||||
clone = self._generate_random_clone_name()
|
||||
|
||||
# create subvolume
|
||||
self._fs_cmd("subvolume", "create", self.volname, subvolume)
|
||||
|
||||
# do some IO
|
||||
self._do_subvolume_io(subvolume, number_of_files=64)
|
||||
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
# verify clone
|
||||
self._verify_clone(subvolume, clone)
|
||||
|
||||
# remove subvolumes
|
||||
self._fs_cmd("subvolume", "rm", self.volname, subvolume)
|
||||
self._fs_cmd("subvolume", "rm", self.volname, clone)
|
||||
|
||||
# verify trash dir is clean
|
||||
self._wait_for_trash_empty()
|
||||
|
||||
def test_subvolume_snapshot_clone_pool_layout(self):
|
||||
subvolume = self._generate_random_subvolume_name()
|
||||
snapshot = self._generate_random_snapshot_name()
|
||||
@ -1650,18 +1688,12 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone, "--pool_layout", new_pool)
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
@ -1697,18 +1729,12 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
@ -1736,18 +1762,12 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone1)
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone1)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
@ -1761,18 +1781,12 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot clone -- use same snap name
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, clone1, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, clone1, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, clone1, snapshot, clone2)
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone2)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, clone1, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, clone1, snapshot)
|
||||
|
||||
@ -1802,9 +1816,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# create group
|
||||
self._fs_cmd("subvolumegroup", "create", self.volname, group)
|
||||
|
||||
@ -1814,9 +1825,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone, clone_group=group)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
@ -1851,18 +1859,12 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot, group)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot, group)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone, '--group_name', group)
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot, group)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot, group)
|
||||
|
||||
@ -1898,9 +1900,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot, s_group)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot, s_group)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone,
|
||||
'--group_name', s_group, '--target_group_name', c_group)
|
||||
@ -1908,9 +1907,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone, clone_group=c_group)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot, s_group)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot, s_group)
|
||||
|
||||
@ -1943,23 +1939,25 @@ class TestVolumes(CephFSTestCase):
|
||||
self.mount_a.run_shell(['mkdir', '-p', createpath])
|
||||
|
||||
# do some IO
|
||||
self._do_subvolume_io(subvolume, number_of_files=32)
|
||||
self._do_subvolume_io(subvolume, number_of_files=64)
|
||||
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
|
||||
# snapshot should not be deletable now
|
||||
try:
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
except CommandFailedError as ce:
|
||||
self.assertEqual(ce.exitstatus, errno.EAGAIN, msg="invalid error code when removing source snapshot of a clone")
|
||||
else:
|
||||
self.fail("expected removing source snapshot of a clone to fail")
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
@ -1987,9 +1985,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
|
||||
@ -1998,7 +1993,7 @@ class TestVolumes(CephFSTestCase):
|
||||
self._get_subvolume_path(self.volname, clone)
|
||||
except CommandFailedError as ce:
|
||||
if ce.exitstatus != errno.EAGAIN:
|
||||
raise RuntimeError("invalid error code when cloning a non protected snapshot")
|
||||
raise RuntimeError("invalid error code when fetching path of an pending clone")
|
||||
else:
|
||||
raise RuntimeError("expected fetching path of an pending clone to fail")
|
||||
|
||||
@ -2009,8 +2004,50 @@ class TestVolumes(CephFSTestCase):
|
||||
subvolpath = self._get_subvolume_path(self.volname, clone)
|
||||
self.assertNotEqual(subvolpath, None)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
# verify clone
|
||||
self._verify_clone(subvolume, clone)
|
||||
|
||||
# remove subvolumes
|
||||
self._fs_cmd("subvolume", "rm", self.volname, subvolume)
|
||||
self._fs_cmd("subvolume", "rm", self.volname, clone)
|
||||
|
||||
# verify trash dir is clean
|
||||
self._wait_for_trash_empty()
|
||||
|
||||
def test_subvolume_clone_in_progress_snapshot_rm(self):
|
||||
subvolume = self._generate_random_subvolume_name()
|
||||
snapshot = self._generate_random_snapshot_name()
|
||||
clone = self._generate_random_clone_name()
|
||||
|
||||
# create subvolume
|
||||
self._fs_cmd("subvolume", "create", self.volname, subvolume)
|
||||
|
||||
# do some IO
|
||||
self._do_subvolume_io(subvolume, number_of_files=64)
|
||||
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
|
||||
# snapshot should not be deletable now
|
||||
try:
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
except CommandFailedError as ce:
|
||||
self.assertEqual(ce.exitstatus, errno.EAGAIN, msg="invalid error code when removing source snapshot of a clone")
|
||||
else:
|
||||
self.fail("expected removing source snapshot of a clone to fail")
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone)
|
||||
|
||||
# clone should be accessible now
|
||||
subvolpath = self._get_subvolume_path(self.volname, clone)
|
||||
self.assertNotEqual(subvolpath, None)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
@ -2039,9 +2076,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
|
||||
@ -2060,9 +2094,6 @@ class TestVolumes(CephFSTestCase):
|
||||
subvolpath = self._get_subvolume_path(self.volname, clone)
|
||||
self.assertNotEqual(subvolpath, None)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
@ -2111,9 +2142,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume1, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume1, snapshot)
|
||||
|
||||
# schedule a clone with target as subvolume2
|
||||
try:
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume1, snapshot, subvolume2)
|
||||
@ -2137,9 +2165,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume1, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume1, snapshot)
|
||||
|
||||
@ -2172,9 +2197,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# add data pool
|
||||
new_pool = "new_pool"
|
||||
self.fs.add_data_pool(new_pool)
|
||||
@ -2200,9 +2222,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# check clone status
|
||||
self._wait_for_clone_to_fail(clone2)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
@ -2237,18 +2256,12 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
|
||||
# check clone status
|
||||
self._wait_for_clone_to_complete(clone)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
@ -2276,9 +2289,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule a clone
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
|
||||
@ -2288,9 +2298,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# verify canceled state
|
||||
self._check_clone_canceled(clone)
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
@ -2330,9 +2337,6 @@ class TestVolumes(CephFSTestCase):
|
||||
# snapshot subvolume
|
||||
self._fs_cmd("subvolume", "snapshot", "create", self.volname, subvolume, snapshot)
|
||||
|
||||
# now, protect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "protect", self.volname, subvolume, snapshot)
|
||||
|
||||
# schedule clones
|
||||
for clone in clones:
|
||||
self._fs_cmd("subvolume", "snapshot", "clone", self.volname, subvolume, snapshot, clone)
|
||||
@ -2358,9 +2362,6 @@ class TestVolumes(CephFSTestCase):
|
||||
if ce.exitstatus != errno.EINVAL:
|
||||
raise RuntimeError("invalid error code when cancelling on-going clone")
|
||||
|
||||
# now, unprotect snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "unprotect", self.volname, subvolume, snapshot)
|
||||
|
||||
# remove snapshot
|
||||
self._fs_cmd("subvolume", "snapshot", "rm", self.volname, subvolume, snapshot)
|
||||
|
||||
|
||||
@ -149,6 +149,7 @@ class DashboardTestCase(MgrTestCase):
|
||||
cls.login('admin', 'admin')
|
||||
|
||||
def setUp(self):
|
||||
super(DashboardTestCase, self).setUp()
|
||||
if not self._loggedin and self.AUTO_AUTHENTICATE:
|
||||
self.login('admin', 'admin')
|
||||
self.wait_for_health_clear(20)
|
||||
|
||||
@ -14,6 +14,7 @@ class AuthTest(DashboardTestCase):
|
||||
AUTO_AUTHENTICATE = False
|
||||
|
||||
def setUp(self):
|
||||
super(AuthTest, self).setUp()
|
||||
self.reset_session()
|
||||
|
||||
def _validate_jwt_token(self, token, username, permissions):
|
||||
|
||||
@ -19,6 +19,41 @@ class HealthTest(DashboardTestCase):
|
||||
'statuses': JObj({}, allow_unknown=True, unknown_schema=int)
|
||||
})
|
||||
|
||||
__mdsmap_schema = JObj({
|
||||
'session_autoclose': int,
|
||||
'balancer': str,
|
||||
'up': JObj({}, allow_unknown=True),
|
||||
'last_failure_osd_epoch': int,
|
||||
'in': JList(int),
|
||||
'last_failure': int,
|
||||
'max_file_size': int,
|
||||
'explicitly_allowed_features': int,
|
||||
'damaged': JList(int),
|
||||
'tableserver': int,
|
||||
'failed': JList(int),
|
||||
'metadata_pool': int,
|
||||
'epoch': int,
|
||||
'stopped': JList(int),
|
||||
'max_mds': int,
|
||||
'compat': JObj({
|
||||
'compat': JObj({}, allow_unknown=True),
|
||||
'ro_compat': JObj({}, allow_unknown=True),
|
||||
'incompat': JObj({}, allow_unknown=True)
|
||||
}),
|
||||
'min_compat_client': str,
|
||||
'data_pools': JList(int),
|
||||
'info': JObj({}, allow_unknown=True),
|
||||
'fs_name': str,
|
||||
'created': str,
|
||||
'standby_count_wanted': int,
|
||||
'enabled': bool,
|
||||
'modified': str,
|
||||
'session_timeout': int,
|
||||
'flags': int,
|
||||
'ever_allowed_features': int,
|
||||
'root': int
|
||||
})
|
||||
|
||||
def test_minimal_health(self):
|
||||
data = self._get('/api/health/minimal')
|
||||
self.assertStatus(200)
|
||||
@ -40,18 +75,10 @@ class HealthTest(DashboardTestCase):
|
||||
'fs_map': JObj({
|
||||
'filesystems': JList(
|
||||
JObj({
|
||||
'mdsmap': JObj({
|
||||
'info': JObj(
|
||||
{},
|
||||
allow_unknown=True,
|
||||
unknown_schema=JObj({
|
||||
'state': str
|
||||
})
|
||||
)
|
||||
})
|
||||
'mdsmap': self.__mdsmap_schema
|
||||
}),
|
||||
),
|
||||
'standbys': JList(JObj({})),
|
||||
'standbys': JList(JObj({}, allow_unknown=True)),
|
||||
}),
|
||||
'health': JObj({
|
||||
'checks': JList(str),
|
||||
@ -164,16 +191,7 @@ class HealthTest(DashboardTestCase):
|
||||
'filesystems': JList(
|
||||
JObj({
|
||||
'id': int,
|
||||
'mdsmap': JObj({
|
||||
# TODO: Expand mdsmap schema
|
||||
'info': JObj(
|
||||
{},
|
||||
allow_unknown=True,
|
||||
unknown_schema=JObj({
|
||||
'state': str
|
||||
}, allow_unknown=True)
|
||||
)
|
||||
}, allow_unknown=True)
|
||||
'mdsmap': self.__mdsmap_schema
|
||||
}),
|
||||
),
|
||||
'standbys': JList(JObj({}, allow_unknown=True)),
|
||||
|
||||
@ -2,9 +2,9 @@
|
||||
from __future__ import absolute_import
|
||||
|
||||
import logging
|
||||
|
||||
import six
|
||||
import time
|
||||
from contextlib import contextmanager
|
||||
|
||||
from .helper import DashboardTestCase, JAny, JList, JObj
|
||||
|
||||
@ -37,30 +37,68 @@ class PoolTest(DashboardTestCase):
|
||||
'wr': pool_list_stat_schema,
|
||||
}, allow_unknown=True)
|
||||
|
||||
def _pool_create(self, data):
|
||||
try:
|
||||
self._task_post('/api/pool/', data)
|
||||
self.assertStatus(201)
|
||||
pool_rbd_conf_schema = JList(JObj(sub_elems={
|
||||
'name': str,
|
||||
'value': str,
|
||||
'source': int
|
||||
}))
|
||||
|
||||
self._check_pool_properties(data)
|
||||
@contextmanager
|
||||
def __create_pool(self, name, data=None):
|
||||
pool_data = data or {
|
||||
'pool': name,
|
||||
'pg_num': '4',
|
||||
'pool_type': 'replicated',
|
||||
'compression_algorithm': 'snappy',
|
||||
'compression_mode': 'passive',
|
||||
'compression_max_blob_size': '131072',
|
||||
'compression_required_ratio': '0.875',
|
||||
'application_metadata': ['rbd'],
|
||||
'configuration': {
|
||||
'rbd_qos_bps_limit': 1024000,
|
||||
'rbd_qos_iops_limit': 5000,
|
||||
}
|
||||
}
|
||||
self._task_post('/api/pool/', pool_data)
|
||||
self.assertStatus(201)
|
||||
time.sleep(5)
|
||||
self._validate_pool_properties(pool_data, self._get_pool(name))
|
||||
yield pool_data
|
||||
self._task_delete('/api/pool/' + name)
|
||||
self.assertStatus(204)
|
||||
|
||||
self._task_delete("/api/pool/" + data['pool'])
|
||||
self.assertStatus(204)
|
||||
except Exception:
|
||||
log.exception("test_pool_create: data=%s", data)
|
||||
raise
|
||||
|
||||
def _check_pool_properties(self, data, pool_name=None):
|
||||
if not pool_name:
|
||||
pool_name = data['pool']
|
||||
pool = self._get_pool(pool_name)
|
||||
try:
|
||||
for k, v in data.items():
|
||||
self._check_pool_property(k, v, pool)
|
||||
|
||||
except Exception:
|
||||
log.exception("test_pool_create: pool=%s", pool)
|
||||
raise
|
||||
def _validate_pool_properties(self, data, pool):
|
||||
for prop, value in data.items():
|
||||
if prop == 'pool_type':
|
||||
self.assertEqual(pool['type'], value)
|
||||
elif prop == 'size':
|
||||
self.assertEqual(pool[prop], int(value),
|
||||
'{}: {} != {}'.format(prop, pool[prop], value))
|
||||
elif prop == 'pg_num':
|
||||
self._check_pg_num(value, pool)
|
||||
elif prop == 'application_metadata':
|
||||
self.assertIsInstance(pool[prop], list)
|
||||
self.assertEqual(value, pool[prop])
|
||||
elif prop == 'pool':
|
||||
self.assertEqual(pool['pool_name'], value)
|
||||
elif prop.startswith('compression'):
|
||||
if value is not None:
|
||||
if prop.endswith('size'):
|
||||
value = int(value)
|
||||
elif prop.endswith('ratio'):
|
||||
value = float(value)
|
||||
self.assertEqual(pool['options'][prop], value)
|
||||
else:
|
||||
self.assertEqual(pool['options'], {})
|
||||
elif prop == 'configuration':
|
||||
# configuration cannot really be checked here for two reasons:
|
||||
# 1. The default value cannot be given to this method, which becomes relevant
|
||||
# when resetting a value, because it's not always zero.
|
||||
# 2. The expected `source` cannot be given to this method, and it cannot
|
||||
# relibably be determined (see 1)
|
||||
pass
|
||||
else:
|
||||
self.assertEqual(pool[prop], value, '{}: {} != {}'.format(prop, pool[prop], value))
|
||||
|
||||
health = self._get('/api/health/minimal')['health']
|
||||
self.assertEqual(health['status'], 'HEALTH_OK', msg='health={}'.format(health))
|
||||
@ -71,49 +109,27 @@ class PoolTest(DashboardTestCase):
|
||||
self.assertSchemaBody(self.pool_schema)
|
||||
return pool
|
||||
|
||||
def _check_pool_property(self, prop, value, pool):
|
||||
if prop == 'pool_type':
|
||||
self.assertEqual(pool['type'], value)
|
||||
elif prop == 'size':
|
||||
self.assertEqual(pool[prop], int(value), '{}: {} != {}'.format(prop, pool[prop], value))
|
||||
elif prop == 'pg_num':
|
||||
self._check_pg_num(value, pool)
|
||||
elif prop == 'application_metadata':
|
||||
self.assertIsInstance(pool[prop], list)
|
||||
self.assertEqual(pool[prop], value)
|
||||
elif prop == 'pool':
|
||||
self.assertEqual(pool['pool_name'], value)
|
||||
elif prop.startswith('compression'):
|
||||
if value is not None:
|
||||
if prop.endswith('size'):
|
||||
value = int(value)
|
||||
elif prop.endswith('ratio'):
|
||||
value = float(value)
|
||||
self.assertEqual(pool['options'].get(prop), value)
|
||||
else:
|
||||
self.assertEqual(pool[prop], value, '{}: {} != {}'.format(prop, pool[prop], value))
|
||||
|
||||
def _check_pg_num(self, value, pool):
|
||||
# If both properties have not the same value, the cluster goes into a warning state,
|
||||
# which will only happen during a pg update on a existing pool.
|
||||
# The test that does that is currently commented out because
|
||||
# our QA systems can't deal with the change.
|
||||
# Feel free to test it locally.
|
||||
prop = 'pg_num'
|
||||
"""
|
||||
If both properties have not the same value, the cluster goes into a warning state, which
|
||||
will only happen during a pg update on an existing pool. The test that does that is
|
||||
currently commented out because our QA systems can't deal with the change. Feel free to test
|
||||
it locally.
|
||||
"""
|
||||
pgp_prop = 'pg_placement_num'
|
||||
health = lambda: self._get('/api/health/minimal')['health']['status'] == 'HEALTH_OK'
|
||||
t = 0;
|
||||
while (int(value) != pool[pgp_prop] or not health()) and t < 180:
|
||||
t = 0
|
||||
while (int(value) != pool[pgp_prop] or self._get('/api/health/minimal')['health']['status']
|
||||
!= 'HEALTH_OK') and t < 180:
|
||||
time.sleep(2)
|
||||
t += 2
|
||||
pool = self._get_pool(pool['pool_name'])
|
||||
for p in [prop, pgp_prop]: # Should have the same values
|
||||
for p in ['pg_num', pgp_prop]: # Should have the same values
|
||||
self.assertEqual(pool[p], int(value), '{}: {} != {}'.format(p, pool[p], value))
|
||||
|
||||
@classmethod
|
||||
def tearDownClass(cls):
|
||||
super(PoolTest, cls).tearDownClass()
|
||||
for name in ['dashboard_pool1', 'dashboard_pool2', 'dashboard_pool3', 'dashboard_pool_update1']:
|
||||
for name in ['dashboard_pool1', 'dashboard_pool2', 'dashboard_pool3']:
|
||||
cls._ceph_cmd(['osd', 'pool', 'delete', name, name, '--yes-i-really-really-mean-it'])
|
||||
cls._ceph_cmd(['osd', 'erasure-code-profile', 'rm', 'ecprofile'])
|
||||
|
||||
@ -188,23 +204,40 @@ class PoolTest(DashboardTestCase):
|
||||
self.assertNotIn('pg_status', pool)
|
||||
self.assertSchema(pool['stats'], self.pool_list_stats_schema)
|
||||
self.assertNotIn('flags_names', pool)
|
||||
self.assertSchema(pool['configuration'], self.pool_rbd_conf_schema)
|
||||
|
||||
def test_pool_create(self):
|
||||
self._ceph_cmd(['osd', 'crush', 'rule', 'create-erasure', 'ecrule'])
|
||||
self._ceph_cmd(
|
||||
['osd', 'erasure-code-profile', 'set', 'ecprofile', 'crush-failure-domain=osd'])
|
||||
pools = [{
|
||||
|
||||
pool = {
|
||||
'pool': 'dashboard_pool1',
|
||||
'pg_num': '32',
|
||||
'pool_type': 'replicated',
|
||||
'application_metadata': ['rbd', 'sth'],
|
||||
}, {
|
||||
}
|
||||
self._task_post('/api/pool/', pool)
|
||||
self.assertStatus(201)
|
||||
self._validate_pool_properties(pool, self._get_pool(pool['pool']))
|
||||
self._task_delete("/api/pool/" + pool['pool'])
|
||||
self.assertStatus(204)
|
||||
|
||||
pool = {
|
||||
'pool': 'dashboard_pool2',
|
||||
'pg_num': '32',
|
||||
'pool_type': 'erasure',
|
||||
'application_metadata': ['rbd'],
|
||||
'erasure_code_profile': 'ecprofile',
|
||||
'crush_rule': 'ecrule',
|
||||
}, {
|
||||
}
|
||||
self._task_post('/api/pool/', pool)
|
||||
self.assertStatus(201)
|
||||
self._validate_pool_properties(pool, self._get_pool(pool['pool']))
|
||||
self._task_delete("/api/pool/" + pool['pool'])
|
||||
self.assertStatus(204)
|
||||
|
||||
pool = {
|
||||
'pool': 'dashboard_pool3',
|
||||
'pg_num': '32',
|
||||
'pool_type': 'replicated',
|
||||
@ -212,64 +245,99 @@ class PoolTest(DashboardTestCase):
|
||||
'compression_mode': 'aggressive',
|
||||
'compression_max_blob_size': '10000000',
|
||||
'compression_required_ratio': '0.8',
|
||||
}]
|
||||
for data in pools:
|
||||
self._pool_create(data)
|
||||
|
||||
def test_update(self):
|
||||
pool = {
|
||||
'pool': 'dashboard_pool_update1',
|
||||
'pg_num': '32',
|
||||
'pool_type': 'replicated',
|
||||
'compression_mode': 'passive',
|
||||
'compression_algorithm': 'snappy',
|
||||
'compression_max_blob_size': '131072',
|
||||
'compression_required_ratio': '0.875',
|
||||
'configuration': {
|
||||
'rbd_qos_bps_limit': 2048,
|
||||
'rbd_qos_iops_limit': None,
|
||||
},
|
||||
}
|
||||
updates = [
|
||||
{
|
||||
'application_metadata': ['rbd', 'sth'],
|
||||
},
|
||||
# The following test case is currently commented out because
|
||||
# our QA systems can't deal with the change and will fail because
|
||||
# they can't recover from the resulting warning state.
|
||||
# Feel free to test it locally.
|
||||
# {
|
||||
# 'pg_num': '2', # Decrease PGs
|
||||
# },
|
||||
# {
|
||||
# 'pg_num': '8', # Increase PGs
|
||||
# },
|
||||
{
|
||||
'application_metadata': ['rgw'],
|
||||
},
|
||||
{
|
||||
expected_configuration = [{
|
||||
'name': 'rbd_qos_bps_limit',
|
||||
'source': 1,
|
||||
'value': '2048',
|
||||
}, {
|
||||
'name': 'rbd_qos_iops_limit',
|
||||
'source': 0,
|
||||
'value': '0',
|
||||
}]
|
||||
self._task_post('/api/pool/', pool)
|
||||
self.assertStatus(201)
|
||||
new_pool = self._get_pool(pool['pool'])
|
||||
self._validate_pool_properties(pool, new_pool)
|
||||
for conf in expected_configuration:
|
||||
self.assertIn(conf, new_pool['configuration'])
|
||||
|
||||
self._task_delete("/api/pool/" + pool['pool'])
|
||||
self.assertStatus(204)
|
||||
|
||||
def test_pool_update_metadata(self):
|
||||
pool_name = 'pool_update_metadata'
|
||||
with self.__create_pool(pool_name):
|
||||
props = {'application_metadata': ['rbd', 'sth']}
|
||||
self._task_put('/api/pool/{}'.format(pool_name), props)
|
||||
time.sleep(5)
|
||||
self._validate_pool_properties(props, self._get_pool(pool_name))
|
||||
|
||||
properties = {'application_metadata': ['rgw']}
|
||||
self._task_put('/api/pool/' + pool_name, properties)
|
||||
time.sleep(5)
|
||||
self._validate_pool_properties(properties, self._get_pool(pool_name))
|
||||
|
||||
properties = {'application_metadata': ['rbd', 'sth']}
|
||||
self._task_put('/api/pool/' + pool_name, properties)
|
||||
time.sleep(5)
|
||||
self._validate_pool_properties(properties, self._get_pool(pool_name))
|
||||
|
||||
properties = {'application_metadata': ['rgw']}
|
||||
self._task_put('/api/pool/' + pool_name, properties)
|
||||
time.sleep(5)
|
||||
self._validate_pool_properties(properties, self._get_pool(pool_name))
|
||||
|
||||
def test_pool_update_configuration(self):
|
||||
pool_name = 'pool_update_configuration'
|
||||
with self.__create_pool(pool_name):
|
||||
configuration = {
|
||||
'rbd_qos_bps_limit': 1024,
|
||||
'rbd_qos_iops_limit': None,
|
||||
}
|
||||
expected_configuration = [{
|
||||
'name': 'rbd_qos_bps_limit',
|
||||
'source': 1,
|
||||
'value': '1024',
|
||||
}, {
|
||||
'name': 'rbd_qos_iops_limit',
|
||||
'source': 0,
|
||||
'value': '0',
|
||||
}]
|
||||
self._task_put('/api/pool/' + pool_name, {'configuration': configuration})
|
||||
time.sleep(5)
|
||||
pool_config = self._get_pool(pool_name)['configuration']
|
||||
for conf in expected_configuration:
|
||||
self.assertIn(conf, pool_config)
|
||||
|
||||
def test_pool_update_compression(self):
|
||||
pool_name = 'pool_update_compression'
|
||||
with self.__create_pool(pool_name):
|
||||
properties = {
|
||||
'compression_algorithm': 'zstd',
|
||||
'compression_mode': 'aggressive',
|
||||
'compression_max_blob_size': '10000000',
|
||||
'compression_required_ratio': '0.8',
|
||||
},
|
||||
{
|
||||
'compression_mode': 'unset'
|
||||
}
|
||||
]
|
||||
self._task_post('/api/pool/', pool)
|
||||
self.assertStatus(201)
|
||||
self._check_pool_properties(pool)
|
||||
self._task_put('/api/pool/' + pool_name, properties)
|
||||
time.sleep(5)
|
||||
self._validate_pool_properties(properties, self._get_pool(pool_name))
|
||||
|
||||
for update in updates:
|
||||
self._task_put('/api/pool/' + pool['pool'], update)
|
||||
if update.get('compression_mode') == 'unset':
|
||||
update = {
|
||||
'compression_mode': None,
|
||||
'compression_algorithm': None,
|
||||
'compression_mode': None,
|
||||
'compression_max_blob_size': None,
|
||||
'compression_required_ratio': None,
|
||||
}
|
||||
self._check_pool_properties(update, pool_name=pool['pool'])
|
||||
self._task_delete("/api/pool/" + pool['pool'])
|
||||
self.assertStatus(204)
|
||||
def test_pool_update_unset_compression(self):
|
||||
pool_name = 'pool_update_unset_compression'
|
||||
with self.__create_pool(pool_name):
|
||||
self._task_put('/api/pool/' + pool_name, {'compression_mode': 'unset'})
|
||||
time.sleep(5)
|
||||
self._validate_pool_properties({
|
||||
'compression_algorithm': None,
|
||||
'compression_mode': None,
|
||||
'compression_max_blob_size': None,
|
||||
'compression_required_ratio': None,
|
||||
}, self._get_pool(pool_name))
|
||||
|
||||
def test_pool_create_fail(self):
|
||||
data = {'pool_type': u'replicated', 'rule_name': u'dnf', 'pg_num': u'8', 'pool': u'sadfs'}
|
||||
|
||||
@ -188,6 +188,8 @@ class RbdTest(DashboardTestCase):
|
||||
'block_name_prefix': JLeaf(str),
|
||||
'name': JLeaf(str),
|
||||
'id': JLeaf(str),
|
||||
'unique_id': JLeaf(str),
|
||||
'image_format': JLeaf(int),
|
||||
'pool_name': JLeaf(str),
|
||||
'features': JLeaf(int),
|
||||
'features_name': JList(JLeaf(str)),
|
||||
|
||||
@ -67,6 +67,7 @@ class RgwApiCredentialsTest(RgwTestCase):
|
||||
AUTH_ROLES = ['rgw-manager']
|
||||
|
||||
def setUp(self):
|
||||
super(RgwApiCredentialsTest, self).setUp()
|
||||
# Restart the Dashboard module to ensure that the connection to the
|
||||
# RGW Admin Ops API is re-established with the new credentials.
|
||||
self.logout()
|
||||
|
||||
@ -7,6 +7,7 @@ from .helper import DashboardTestCase, JList, JObj, JAny
|
||||
|
||||
class SettingsTest(DashboardTestCase):
|
||||
def setUp(self):
|
||||
super(SettingsTest, self).setUp()
|
||||
self.settings = self._get('/api/settings')
|
||||
|
||||
def tearDown(self):
|
||||
|
||||
@ -13,6 +13,7 @@ DATEFMT = '%Y-%m-%d %H:%M:%S.%f'
|
||||
class TestCrash(MgrTestCase):
|
||||
|
||||
def setUp(self):
|
||||
super(TestCrash, self).setUp()
|
||||
self.setup_mgrs()
|
||||
self._load_module('crash')
|
||||
|
||||
|
||||
@ -12,6 +12,7 @@ class TestFailover(MgrTestCase):
|
||||
MGRS_REQUIRED = 2
|
||||
|
||||
def setUp(self):
|
||||
super(TestFailover, self).setUp()
|
||||
self.setup_mgrs()
|
||||
|
||||
def test_timeout(self):
|
||||
|
||||
@ -12,6 +12,7 @@ DATEFMT = '%Y-%m-%d %H:%M:%S.%f'
|
||||
|
||||
class TestInsights(MgrTestCase):
|
||||
def setUp(self):
|
||||
super(TestInsights, self).setUp()
|
||||
self.setup_mgrs()
|
||||
self._load_module("insights")
|
||||
self._load_module("selftest")
|
||||
|
||||
@ -24,6 +24,7 @@ class TestModuleSelftest(MgrTestCase):
|
||||
MGRS_REQUIRED = 1
|
||||
|
||||
def setUp(self):
|
||||
super(TestModuleSelftest, self).setUp()
|
||||
self.setup_mgrs()
|
||||
|
||||
def _selftest_plugin(self, module_name):
|
||||
|
||||
@ -61,6 +61,7 @@ class TestProgress(MgrTestCase):
|
||||
return len(osd_map['osds'])
|
||||
|
||||
def setUp(self):
|
||||
super(TestProgress, self).setUp()
|
||||
# Ensure we have at least four OSDs
|
||||
if self._osd_count() < 4:
|
||||
raise SkipTest("Not enough OSDS!")
|
||||
|
||||
@ -11,6 +11,7 @@ class TestPrometheus(MgrTestCase):
|
||||
MGRS_REQUIRED = 3
|
||||
|
||||
def setUp(self):
|
||||
super(TestPrometheus, self).setUp()
|
||||
self.setup_mgrs()
|
||||
|
||||
def test_file_sd_command(self):
|
||||
|
||||
@ -103,9 +103,10 @@ def start_rgw(ctx, config, clients):
|
||||
kport=keystone_port),
|
||||
])
|
||||
|
||||
if client_config.get('dns-name'):
|
||||
|
||||
if client_config.get('dns-name') is not None:
|
||||
rgw_cmd.extend(['--rgw-dns-name', endpoint.dns_name])
|
||||
if client_config.get('dns-s3website-name'):
|
||||
if client_config.get('dns-s3website-name') is not None:
|
||||
rgw_cmd.extend(['--rgw-dns-s3website-name', endpoint.website_dns_name])
|
||||
|
||||
rgw_cmd.extend([
|
||||
@ -188,9 +189,8 @@ def assign_endpoints(ctx, config, default_cert):
|
||||
dns_name += remote.hostname
|
||||
|
||||
website_dns_name = client_config.get('dns-s3website-name')
|
||||
if website_dns_name:
|
||||
if len(website_dns_name) == 0 or website_dns_name.endswith('.'):
|
||||
website_dns_name += remote.hostname
|
||||
if website_dns_name is not None and (len(website_dns_name) == 0 or website_dns_name.endswith('.')):
|
||||
website_dns_name += remote.hostname
|
||||
|
||||
role_endpoints[role] = RGWEndpoint(remote.hostname, port, ssl_certificate, dns_name, website_dns_name)
|
||||
|
||||
|
||||
@ -308,10 +308,22 @@ class LocalRemote(object):
|
||||
|
||||
return proc
|
||||
|
||||
def sh(self, command, log_limit=1024, cwd=None, env=None):
|
||||
# XXX: for compatibility keep this method same teuthology.orchestra.remote.sh
|
||||
def sh(self, script, **kwargs):
|
||||
"""
|
||||
Shortcut for run method.
|
||||
|
||||
Usage:
|
||||
my_name = remote.sh('whoami')
|
||||
remote_date = remote.sh('date')
|
||||
"""
|
||||
if 'stdout' not in kwargs:
|
||||
kwargs['stdout'] = StringIO()
|
||||
if 'args' not in kwargs:
|
||||
kwargs['args'] = script
|
||||
proc = self.run(**kwargs)
|
||||
return proc.stdout.getvalue()
|
||||
|
||||
return misc.sh(command=command, log_limit=log_limit, cwd=cwd,
|
||||
env=env)
|
||||
|
||||
class LocalDaemon(object):
|
||||
def __init__(self, daemon_type, daemon_id):
|
||||
@ -474,16 +486,12 @@ class LocalFuseMount(FuseMount):
|
||||
if self.is_mounted():
|
||||
super(LocalFuseMount, self).umount()
|
||||
|
||||
def mount(self, mount_path=None, mount_fs_name=None):
|
||||
def mount(self, mount_path=None, mount_fs_name=None, mountpoint=None):
|
||||
if mountpoint is not None:
|
||||
self.mountpoint = mountpoint
|
||||
self.setupfs(name=mount_fs_name)
|
||||
|
||||
self.client_remote.run(
|
||||
args=[
|
||||
'mkdir',
|
||||
'--',
|
||||
self.mountpoint,
|
||||
],
|
||||
)
|
||||
self.client_remote.run(args=['mkdir', '-p', self.mountpoint])
|
||||
|
||||
def list_connections():
|
||||
self.client_remote.run(
|
||||
@ -559,6 +567,8 @@ class LocalFuseMount(FuseMount):
|
||||
|
||||
self.gather_mount_info()
|
||||
|
||||
self.mounted = True
|
||||
|
||||
def _run_python(self, pyscript, py_version='python'):
|
||||
"""
|
||||
Override this to remove the daemon-helper prefix that is used otherwise
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user