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>
Previously, it was guarranteed that prior to activation, flushed would
be false on a replica. Now, there may be a period where flushed is true
due to the flush in Stray completing prior to activation and flushed
being false again. This is necessary since shortly it won't be possible
to determine from the osdmap whether a stray will be activated in a
particular interval.
Signed-off-by: Samuel Just <sam.just@inktank.com>
- RBD Documentation, --image-format wrongly specified as --format in examples
- RBD Documentation, better describe image format, to differentiate from --format
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
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.
Fixes: #6795
Backport: emperor, dumpling
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
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>
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>
