Listing objects isn't reliable with cache pools; skip that part of the
test if we see that rbd has tiering enabled.
Signed-off-by: Sage Weil <sage@inktank.com>
First, make_writeable treats whiteout heads like snapdir for
cloning purposes. Second, to ensure that we send the correct
deletes on flush to the backing pool, we instead use oi.snaps
on any clone we are flushing to infer the snaps during which
head did not exist and send a delete as appropriate prior to
the copy_from.
Normally, we'd have a problem if the delete and the copy_from
completed, but an interval change intervened before the dirty
flag was cleared since we'd end up re-deleting the object.
To avoid that, we use the CEPH_OSD_FLAG_ORDERSNAP flag.
Additionally, we will use the correct snap_seq on the delete
or flush as appropriate to ensure that the previous clone
gets created with the same clone id as in the cache pool.
Fixes: #7942
Signed-off-by: Samuel Just <sam.just@inktank.com>
We don't actually send the whole info on each repop, just the log
entries, updated stats, and a few other bits. For hit_set ops, we need
to also communicate the new hit_set history status atomically with the
log entries and the transaction. Thus, we add a channel for an optional
pg_hit_set_history_t field in PGBackend::submit_transaction interface
and associated messages and implementations to update the hit_set info
field along with the log entries.
This also means that hit_set_(persist|trim) update an
updated_hit_set_history field on the OpContext instead of directly
modifying the info field.
Fixes: #8124
Signed-off-by: Samuel Just <sam.just@inktank.com>
A 'status' or 'health' request will return a HEALTH_WARN whenever the
monitor handling the request has the option set to zero.
Fixes: 7784
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
We were waiting for the election to finish, but we need to *also* wait for
paxos to recover. Being a peon or leader is not sufficient and we may
return a map that is still old.
Fixes: #7997
Signed-off-by: Sage Weil <sage@inktank.com>
We check whether the head is degraded, and we check whether a clone is
unreadable, but in the case where we have a cache op on a degraded object,
we don't check. That leads to an assert when the repop hits the replica
and the object is in the peer's missing set.
Fix this by adding a check on the clone when write_ordered is true. Note
that checking write_ordered is better than whether it is a cache op because
we want to preserve write ordering even for reads that are flagged by the
client.
Fixes: #8048
Signed-off-by: Sage Weil <sage@inktank.com>
If we recalculate the mapping and find that there is no primary, we need
to set the 'osd' field to -1. Otherwise, the caller will try to resend
to a dead session with bad results.
This was introduced in the refactor 860d72770c.
Fixes: #8130
Signed-off-by: Sage Weil <sage@inktank.com>
If we have just started and receive a command, we currently will reply with
EINVAL because the leader commands are empty. Note that this race is very
difficult to reach because the (old) peon needs to forward a command to
the mon while it still thinks it has quorum, and the message needs to get
sent after the leader mon has restarted and reset its connection but before
it has declared a new election.
To fix this, we should assume at startup time that our commands are
valid. If it is an internal command that does not require quorum, that
is fine. If it does require quorum, we will retry the command after the
election completes and we will revalidate the command then.
Fixes: #8132
Signed-off-by: Sage Weil <sage@inktank.com>
In 69321bf, EAGAIN changed behaviour to block indefinitely
rather than returning to user. Change the return for
`osd pool set` operations that are blocked by creating PGs
to return EBUSY instead of EAGAIN, so that they are excepted
from this blocking behaviour.
Signed-off-by: John Spray <john.spray@inktank.com>
