Yehuda Sadeh [Tue, 14 Jan 2014 22:48:16 +0000 (14:48 -0800)]
rgw: quota thread for full user stats sync
Get user stats up to date periodically. Add configurables for different
periods, whether we update idle users.
Make sure radosgw-admin does not start the quota threads.
Yehuda Sadeh [Mon, 13 Jan 2014 22:19:27 +0000 (14:19 -0800)]
rgw, cls_user: fix bucket creation
There's a single op to create and update the user bucket info, however,
the cases differ a bit, as we only need to guard against ENOENT if we're
updating the info.
Yehuda Sadeh [Thu, 9 Jan 2014 00:39:19 +0000 (16:39 -0800)]
rgw: pass bucket owner all around
User quota operations require that we know who the actual user we do the
operation on is. Pass that info when creating new object and when
removing objects.
Josh Durgin [Mon, 25 Nov 2013 21:43:43 +0000 (13:43 -0800)]
init, upstart: prevent daemons being started by both
There can be only one init system starting a daemon. If there is a
host entry in ceph.conf for a daemon, sysvinit would try to start it
even if the daemon's directory did not include a sysvinit file. This
preserves backwards compatibility with older installs using sysvinit,
but if an upstart file is present in the daemon's directory, upstart
will try to start them, regardless of host entries in ceph.conf.
If there's an upstart file in a daemon's directory and a host entry
for that daemon in ceph.conf, both sysvinit and upstart would attempt
to manage it.
Fix this by only starting daemons if the marker file for the other
init system is not present. This maintains backwards compatibility
with older installs using neither sysvinit or upstart marker files,
and does not break any valid configurations. The only configuration
that would break is one with both sysvinit and upstart files present
for the same daemon.
Yehuda Sadeh [Wed, 27 Nov 2013 21:34:00 +0000 (13:34 -0800)]
rgw: don't error out on empty owner when setting acls
Fixes: #6892
Backport: dumpling, emperor
s3cmd specifies empty owner field when trying to set acls on object
/ bucket. We errored out as it didn't match the current owner name, but
with this change we ignore it.
Fixes: #6829
Backport: dumpling, emperor
We didn't init this member variable, which might cause that when
modifying user info that has this flag set the 'system' flag might
inadvertently reset.
mon: OSDMonitor: don't crash if formatter is invalid during osd crush dump
Code would assume a formatter would always be defined. If a 'plain'
formatter or even an invalid formatter were to be supplied, the monitor
would crash and burn in poor style.
Fixes: 6820
Backport: emperor
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
mon: OSDMonitor: receive CephInt on 'osd pool set' instead on CephString
This partially reverts 2fe0d0d9 in order to allow Emperor monitors to
forward mon command messages to Dumpling monitors without breaking a
cluster.
The need for this patch became obvious after issue #6796 was triggered.
Basically, in a mixed cluster of Emperor/Dumpling monitors, if a client
happens to obtain the command descriptions from an Emperor monitor and
then issue an 'osd pool set' this can turn out in one of two ways:
1. client msg gets forwarded to an Emperor leader and everything's a-okay;
2. client msg gets forwarded to a Dumpling leader and the string fails to
be interpreted without the monitor noticing, thus leaving the monitor with
an uninitialized variable leading to trouble.
If 2 is triggered, a multitude of bad things can happen, such as thousands
of pg splits, due to a simple 'osd set pool foo pg_num 128' turning out
to be interpreted as 109120394 or some other random number.
This patch is such that we make sure the client sends an integer instead
of a string. We also make sure to interpret anything the client sends as
possibly being a string, or an integer.
Fixes: 6796
Backport: emperor
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Josh Durgin [Thu, 21 Nov 2013 02:35:34 +0000 (18:35 -0800)]
test: use older names for module setup/teardown
setUp and tearDown require nosetests 0.11, but 0.10.4 is the latest on
centos. Rename to use the older aliases, which still work with newer
versions of nosetests as well.
Fixes: #6368 Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: Dan Mick <dan.mick@inktank.com>
Josh Durgin [Mon, 18 Nov 2013 22:39:12 +0000 (14:39 -0800)]
osd: fix bench block size
The command was declared to take 'size' in dumpling, but was trying to
read 'bsize' instead, so it always used the default of 4MiB. Change
the bench command to read 'size', so it matches what existing clients
are sending.
Shipping an object_info_t to a replica with the dirty
flag set would cause the replica to interpret that
object as being lost. Instead, we always encode
lost into the slot where dumpling expects to find
it and add another field at the end of the encoding.
Backport: emperor Fixes: #6761 Signed-off-by: Samuel Just <sam.just@inktank.com> Reviewed-by: Greg Farnum <greg@inktank.com>
Samuel Just [Tue, 12 Nov 2013 23:15:26 +0000 (15:15 -0800)]
ReplicatedPG: test for missing head before find_object_context
find_object_context doesn't return EAGAIN for a missing head.
I chose not to change that behavior since it might hide bugs
in the future. All other callers check for missing on head
before calling into find_object_context because we potentially
need head or snapdir to map a snapid onto a clone.
Backport: emperor Fixes: 6758 Signed-off-by: Samuel Just <sam.just@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: David Zafman <david.zafman@inktank.com>
Samuel Just [Tue, 12 Nov 2013 21:39:04 +0000 (13:39 -0800)]
JounralingObjectStore: journal->committed_thru after replay
It's possible that the osd stopped between when the filestore
op_seq file was updated and when the journal was trimmed. In
that case, it's possible that on boot the journal might be
full, and yet not be trimmed because commit_start assumes
there is no work to do. Calling committed_thru on the journal
ensures that the journal matches committed_seq.
Backport: emperor dumpling Fixes: 6756 Signed-off-by: Samuel Just <sam.just@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: David Zafman <david.zafman@inktank.com>
mon: Monitor: make 'quorum enter/exit' available through the admin socket
If we don't have at least 'quorum enter' available through the admin
socket, then we can never tell a monitor to go back into quorum after
exiting, since it will not handle the command that forces it back in due
to not being in the quorum.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Samuel Just [Wed, 6 Nov 2013 22:33:03 +0000 (14:33 -0800)]
ReplicatedPG: don't skip missing if sentries is empty on pgls
Formerly, if sentries is empty, we skip missing. In general,
we need to continue adding items from missing until we get
to next (returned from collection_list_partial) to avoid
missing any objects.
Fixes: #6633 Signed-off-by: Samuel Just <sam.just@inktank.com> Reviewed-by: David Zafman <david.zafman@inktank.com>
Alan Somers [Fri, 11 Oct 2013 20:45:47 +0000 (13:45 -0700)]
test: Only build death tests on platforms that support them
googletest does not support death tests on FreeBSD. I've submitted a
patch upstream that trivially enables support, but in the meantime we
can't compile death tests for Ceph on FreeBSD.
Samuel Just [Tue, 5 Nov 2013 23:40:29 +0000 (15:40 -0800)]
RadosModel: use sharedptr_registry for snaps_in_use
There might be two concurrent rollback ops each of which
adds snap x to snaps_in_use. Between when the first
completes and the second completes, snap x may be removed
since the first would have removed snap x from snaps_in_use.
Using sharedptr_registry here avoids this by ensuring that
the snap won't be removed from snaps_in_use until all refs
are gone.
This patch also adds size() to sharedptr_registry.
Fixes: #6719 Signed-off-by: Samuel Just <sam.just@inktank.com> Reviewed-by: David Zafman <david.zafman@inktank.com>
projects / ceph.git / log