-
Notifications
You must be signed in to change notification settings - Fork 5.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
osd: fixes to make rbd on ec work #12305
Commits on Nov 22, 2016
-
ECTransaction::get_write_plan: fix bug with substripe write with alig…
…ned offset Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 001c759 - Browse repository at this point
Copy the full SHA 001c759View commit details -
ExtentCache: fix bug in get_remaining_extents_for_rmw
Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 64e00a5 - Browse repository at this point
Copy the full SHA 64e00a5View commit details
Commits on Nov 24, 2016
-
ECTransaction: adjacent extents might have unaligned boundaries
Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 9e2645a - Browse repository at this point
Copy the full SHA 9e2645aView commit details
Commits on Dec 2, 2016
-
PGTransaction,ReplicatedPG: clarify handling of noop operations
The offending transaction was [call rbd.copyup,delete] on a non-existent object. PGTransaction incorrectly ended up with Create and delete_first causing a transaction beginning with trying to collection_move_rename a non-existent head object. In fact, if we delete an object which the transaction currently claims to be creating, the transaction should show as empty (for that object). Rather than going through the normal write pipeline for that case, let's just record a 0 error code in the log and call it a day. That way, the transaction generating code only needs to worry about about updates to actual objects. Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for d6417f4 - Browse repository at this point
Copy the full SHA d6417f4View commit details -
ECBackend::try_state_to_reads: fix debug spacing
Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 32bd456 - Browse repository at this point
Copy the full SHA 32bd456View commit details -
ECBackend: ops must consistently use or not use the cache
If the state is flipped, ops already in the pipeline need to continue to maintain it. Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 7750616 - Browse repository at this point
Copy the full SHA 7750616View commit details -
ReplicatedPG::do_op: wait_for_commit even for results < 0 entries
This way, the replies come back in order and we don't expose uncommitted results. Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 6f0dafc - Browse repository at this point
Copy the full SHA 6f0dafcView commit details
Commits on Dec 4, 2016
-
OSD::init_op_flags: don't consider PING to be a write
Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 89fd030 - Browse repository at this point
Copy the full SHA 89fd030View commit details -
ReplicatedPG::submit_log_entries: fill in repop->v
This way, we can deal with waiting_for_commit appropriately. Also, add more debugging to new_repop and already_*. Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for ef376c9 - Browse repository at this point
Copy the full SHA ef376c9View commit details -
ReplicatedPG: always send the ack with the commit
This was always a pretty silly concept and it has gotten in the way of something else. Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 6b89fac - Browse repository at this point
Copy the full SHA 6b89facView commit details -
ReplicatedPG: allow repops to apply with commit
Up to now, the repop machinery depended on all repops commiting and applying in order. For MOSDPGUpdateLogMissing operations, however, we don't really want to send two messages in the ECBackend case. Instead, just allow those repops to skip the applied stage and be completed in order once the repops ahead of them finish. Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 7c97cd2 - Browse repository at this point
Copy the full SHA 7c97cd2View commit details -
ReplicatedPG: add debugging to EINVAL returns
Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for c0c7f92 - Browse repository at this point
Copy the full SHA c0c7f92View commit details -
ReplicatedPG::record_write_error: send only the flags requested by th…
…e op This isn't really important, but it's nice to be consistent with OSD::reply_op_error. Yet another reason to do away with the ack flag. Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 5c5c117 - Browse repository at this point
Copy the full SHA 5c5c117View commit details -
ReplicatedPG: add return value to RepGather
Now that repops can represent an error, we need to remember the error code so that we can reply to waiting_for_* messages with the right value. Signed-off-by: Samuel Just <sjust@redhat.com>
Configuration menu - View commit details
-
Copy full SHA for 9bf51f9 - Browse repository at this point
Copy the full SHA 9bf51f9View commit details