diff options
| author | Alistair Coles <alistairncoles@gmail.com> | 2021-11-15 18:38:12 +0000 |
|---|---|---|
| committer | Alistair Coles <alistairncoles@gmail.com> | 2021-12-03 12:43:23 +0000 |
| commit | 8ee631cceeac560cc272693b4a70567a271f2754 (patch) | |
| tree | cd5e5a339acdc425c3f402bf6ef87688b08661e3 /etc | |
| parent | ada9f0eeb08368e1956fc5d6197debf1a8a47f8a (diff) | |
| download | swift-8ee631cceeac560cc272693b4a70567a271f2754.tar.gz | |
reconstructor: restrict max objects per revert job
Previously the ssync Sender would attempt to revert all objects in a
partition within a single SSYNC request. With this change the
reconstructor daemon option max_objects_per_revert can be used to limit
the number of objects reverted inside a single SSYNC request for revert
type jobs i.e. when reverting handoff partitions.
If more than max_objects_per_revert are available, the remaining objects
will remain in the sender partition and will not be reverted until the
next call to ssync.Sender, which would currrently be the next time the
reconstructor visits that handoff partition.
Note that the option only applies to handoff revert jobs, not to sync
jobs.
Change-Id: If81760c80a4692212e3774e73af5ce37c02e8aff
Diffstat (limited to 'etc')
| -rw-r--r-- | etc/object-server.conf-sample | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/etc/object-server.conf-sample b/etc/object-server.conf-sample index db4d22636..e9557b6c2 100644 --- a/etc/object-server.conf-sample +++ b/etc/object-server.conf-sample @@ -358,6 +358,7 @@ use = egg:swift#recon # lockup_timeout = 1800 # ring_check_interval = 15.0 # recon_cache_path = /var/cache/swift +# # The handoffs_only mode option is for special case emergency situations during # rebalance such as disk full in the cluster. This option SHOULD NOT BE # CHANGED, except for extreme situations. When handoffs_only mode is enabled @@ -380,6 +381,19 @@ use = egg:swift#recon # Setting to -1 means "no limit". # rebuild_handoff_node_count = 2 # +# By default the reconstructor attempts to revert all objects from handoff +# partitions in a single batch using a single SSYNC request. In exceptional +# circumstances max_objects_per_revert can be used to temporarily limit the +# number of objects reverted by each reconstructor revert type job. If more +# than max_objects_per_revert are available in a sender's handoff partition, +# the remaining objects will remain in the handoff partition and will not be +# reverted until the next time the reconstructor visits that handoff partition +# i.e. with this option set, a single cycle of the reconstructor may not +# completely revert all handoff partitions. The option has no effect on +# reconstructor sync type jobs between primary partitions. A value of 0 (the +# default) means there is no limit. +# max_objects_per_revert = 0 +# # You can set scheduling priority of processes. Niceness values range from -20 # (most favorable to the process) to 19 (least favorable to the process). # nice_priority = |