When receiving the lease release message, it's possible that the lease
has already expired and the corresponding dentry has been trimmed from
the cache.
Fixes#5871
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
We saw this assert because active is not correctly computed.
Remove assert and incorrectly computed active count.
We already use acting.size() to determine whether to set PG_STATE_DEGRADED.
Fixes: #6896
Signed-off-by: David Zafman <david.zafman@inktank.com>
Mark RADOS class libraries as module so that they will be automatically
ignored when stripping binaries.
Signed-off-by: James Page <james.page@ubuntu.com>
Track buffer::ptr::c_str() to catch internal calls that use it, like
buffer::ptr::cmp(). buffer::list::c_str() will be captured by this as
well, since it will do a final buffer::ptr::c_str() and possibly
several more if it needs to rebuild into a single raw buffer.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Make sure the requested length is below the maximum pipe size for now,
since we're only using one pipe and splicing once into and out of
it. The default max is 1MB on recent kernels, so this isn't such a
terrible limitation.
To get around this we could use multiple pipes, or keep both source and
destination fds open at the same time and call splice many times. This
is more usual usage for splice, but would require a lot more work to
restructure the filestore and messenger to handle it.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Create explicit methods for testing. Make buffer::list::write_fd() use
zero-copy if all the buffers support it. Don't automatically handle
reads yet, since we need better detection of read length first.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
This uses a pipe to reference kernel memory so we can use splice(2) to
avoid extra data copies. Take an fd in the factory to create it, since
that's the only way to use it efficiently, which is its whole purpose.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
This allows e.g. raw buffer constructors to provide more specific
information about what failed, as well as a useful error string
automatically.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Create a virtual function that returns the raw data instead of
accessing it directly, so raw buffers backed by pipes can be used as
buffer::ptrs. Make raw::is_page_aligned() virtual so it will not need
to look at the raw data for a pipe-based buffer.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
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.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
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>
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>
We don't ever use any value as a float, so just drop obtaining it. This
makes it easier to partially revert 2fe0d0d9 in an upcoming patch.
Backport: emperor
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Basic testing by forcing each monitor out of quorum at a time and making
sure they still reply to ping requests.
Fixes: #6705
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
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>
Create actingbackfill in choose_acting()
Use first backfill target as previously
Add asserts to catch inappropriate use of actingbackfill
Use is_acting() in proc_replica_info() because this is before actingbackfill set
Remove backfill_targets from stray_set to prevent purge_strays from removing collection
Can't check is_replica() anymore for backfill operations since a backfill isn't
a replica due to acting set change.
fixes: #5855
Signed-off-by: David Zafman <david.zafman@inktank.com>
