summaryrefslogtreecommitdiffstats
path: root/container-search/src/main/java/com/yahoo/search/dispatch/searchcluster/SearchCluster.java
Commit message (Expand)AuthorAgeFilesLines
* Gc unused config options: min-group-coverage and max nodes per groupJon Bratseth2021-06-151-3/+2
* Revert "Revert "Don't consider number of working nodes in coverage""Jon Bratseth2021-05-111-21/+5
* Revert "Don't consider number of working nodes in coverage"Jon Bratseth2021-05-101-5/+21
* Don't consider number of working nodes in coverageJon Bratseth2021-05-101-21/+5
* Remove commentJon Bratseth2021-04-161-1/+1
* Improve coverage messageJon Bratseth2021-04-161-12/+11
* Use median not average document count to determine group coverageJon Bratseth2021-04-151-55/+35
* Allow retired nodes to be unreachableJon Bratseth2021-04-011-10/+11
* SimplifyJon Bratseth2021-03-311-9/+8
* Minor group logic improvementsJon Bratseth2021-03-311-16/+20
* - Call getAsInt.....Henning Baldersheim2021-01-081-1/+1
* Revert "Revert "Disable topk optimisation on dispatch when content distributi...Henning Baldersheim2021-01-081-0/+6
* Revert "Disable topk optimisation on dispatch when content distribution is se...Henning Baldersheim2021-01-081-6/+0
* Disable topk optimisation on dispatch when content distribution is severly sk...Henning Baldersheim2021-01-071-0/+6
* Allow from 5% skew in document distribution and still get good results when a...Henning Baldersheim2020-05-281-1/+2
* Merge pull request #12918 from vespa-engine/balder/top-k-probabilityHenning Baldersheim2020-04-161-0/+10
|\
| * Add query control of top-k-probability.Henning Baldersheim2020-04-151-0/+3
| * Make SearchCluster.TopKEstimator a top level class.Henning Baldersheim2020-04-151-25/+3
| * Introduce top-k-probability and use it to fetch correct proper amount of hits...Henning Baldersheim2020-04-151-0/+29
* | Avoid a single group rejecting feedJon Bratseth2020-04-151-18/+22
|/
* Revert "Revert "Revert "Revert "Don't take combined clusters of size 1 down""""Jon Bratseth2020-03-261-5/+8
* Revert "Revert "Revert "Don't take combined clusters of size 1 down"""Jon Bratseth2020-03-261-8/+5
* Revert "Revert "Don't take combined clusters of size 1 down""Jon Bratseth2020-03-251-5/+8
* Revert "Don't take combined clusters of size 1 down"Harald Musum2020-03-251-8/+5
* Don't take combined clusters of size 1 downJon Bratseth2020-03-251-5/+8
* Revert "Revert "Revert "Revert "Create a resourcepool so that we do not need ...Henning Baldersheim2020-02-191-0/+7
* Revert "Revert "Revert "Create a resourcepool so that we do not need to recon...Harald Musum2020-02-191-7/+0
* Revert "Revert "Create a resourcepool so that we do not need to reconnect to ...Henning Baldersheim2020-02-141-0/+7
* Revert "Create a resourcepool so that we do not need to reconnect to content ...Harald Musum2020-02-141-7/+0
* Create a resourcepool so that we do not need to reconnect to content cluster ...Henning Baldersheim2020-02-131-0/+7
* Keep silent until you know what you are talking about.Henning Baldersheim2020-02-111-0/+1
* Never nullHenning Baldersheim2020-02-111-2/+0
* Decouple so ClusterMonitor is on the outside of the searchcluster and can be ...Henning Baldersheim2020-02-041-21/+9
* Move pingfactory to constructor.Henning Baldersheim2020-02-041-9/+8
* Do not start cluster monitor thread in test as it will race with explicit pin...Henning Baldersheim2020-02-041-2/+5
* Merge pull request #12031 from vespa-engine/balder/wait-until-nodestate-is-knownHenning Baldersheim2020-02-031-1/+1
|\
| * A dispatcher should not be considered ready before it has information about a...Henning Baldersheim2020-01-311-1/+1
* | Provide pongHandler in constructor to avoid needing an AtomicReference.Henning Baldersheim2020-02-031-2/+2
* | Send ping every second truly async to all nodes who does not have any pending...Henning Baldersheim2020-01-311-34/+22
|/
* Add isBlockingWrites to pongJon Bratseth2020-01-201-1/+1
* Deprecate and ignore use-local-nodeJon Bratseth2020-01-091-12/+2
* This is the correct way of shutting down the the Dispatcher.Henning Baldersheim2019-12-181-2/+1
* Avoid too much logging during node up and down.Henning Baldersheim2019-10-041-1/+3
* Improve readability.Henning Baldersheim2019-10-041-1/+1
* - Shut down monitoring thread.Henning Baldersheim2019-10-041-5/+15
* false is false, and true is true, can not be bothHenning Baldersheim2019-09-201-4/+7
* Revert "Revert "Bratseth/vip logic take 2""Henning Baldersheim2019-09-201-61/+73
* Revert "Bratseth/vip logic take 2"Harald Musum2019-09-201-73/+61
* Drive the ping ourselves to avoid waiting for the monitor thread.Henning Baldersheim2019-09-191-0/+2
* No need to set up depending on coverageJon Bratseth2019-09-191-2/+1