We're about to use this to enable (ick) a timestamp-based update
decision tree, to help in resolving disastrous double-active conflicts.
Signed-off-by: Greg Farnum <greg@inktank.com>
The logic was a bit broken. Basically, we want to make sure
that region names are the same. However, if region name is not
set then we need to check whether it's the master region. This
can happen in upgrade cases where originally we didn't have
a region name set.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Multiple fixes:
- sync master, secondary entry point ver on creation
- use correct entry point version when removing entry point
- check correct version on bucket removal
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
was never initialized correctly anyway. It was only supposed to
be used for buckets, but it was never initialized in that case.
Using s->bucket_info.objv_tracker instead.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
We can only forward the bucket removal to the master if it was
successfully removed locally.
The master region has no knowledge about whether the
bucket can be removed or not, e.g., there are still objects in the
bucket. If we send it to the master first, then it'll happily remove it
even though it might fail in the end.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
We had a problem with bucket recreation, where we identified
that bucket has already existed, but missed the fact that it's
the same bucket, so removal of the bucket index was wrong.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
We have the con handy; use it. This avoids generate a spurious RESET
event, which we do not need or do anything useful with. Note that in this
case we are not attaching anything to the Connection priv field.
Signed-off-by: Sage Weil <sage@inktank.com>
If we get a reset during shutdown, we should still break the cycle to avoid
tripping the valgrind leak detection. Note that we are touching no
internal Monitor state here and the locking has not changed.
Signed-off-by: Sage Weil <sage@inktank.com>
Document these in the interface, not the implementation; having two copies
clutters the header and invites them to get out of sync.
Signed-off-by: Sage Weil <sage@inktank.com>
If the caller is marking down an addr, they presumably don't have the
Connection* handy, so we should generate a reset event to help them
clean up con <-> session ref cycles.
Signed-off-by: Sage Weil <sage@inktank.com>
This is a delta, not a timestamp.
This triggered when a cluster is idle for 2* the mon_delta_reset_interval,
and required a mon restart to fix.
Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
We periodically see strange values come out of the estimated cluster
throughput and recovery rates. Pretty sure this is cause by feeding
negative values into the rate arithmetic and then giving the si_t
helpers mangled (sign-extended + bit shifted) values.
Signed-off-by: Sage Weil <sage@inktank.com>
si_t (and friends) does not handle signed values, but at least we can
give the Formatters unmangled values. This shouldn't happen (tm), but
if it does this will make things a bit less confusing and makes the code
a bit less fragile.
Signed-off-by: Sage Weil <sage@inktank.com>
We also assert in on_flushed() that the temp collection is actually
empty.
Fixes: #5670
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
We often want to maintain a nonnegative value. We generalize
this to floors other than zero only because it makes the function
call make intuitive sense; I don't think it is at all useful.
Signed-off-by: Sage Weil <sage@inktank.com>
If we see a peer reporting features ~0ull, we know they are deluded in a
particular way and should infer what features they *actually* have. Do
this right when the features come over the wire to catch all users.
Fixes: #5655
Signed-off-by: Samuel Just <sam.just@inktank.com>
Signed-off-by: Sage Weil <sage@inktank.com>
We have the con handy; use it. This avoids generate a spurious RESET
event, which we do not need or do anything useful with. Note that in this
case we are not attaching anything to the Connection priv field.
Signed-off-by: Sage Weil <sage@inktank.com>
