Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Remove never used per storage node ops latencies in host info. | Geir Storli | 2018-03-13 | 3 | -69/+4 |
| | |||||
* | Merge pull request #5269 from ↵ | Geir Storli | 2018-03-09 | 5 | -70/+104 |
|\ | | | | | | | | | vespa-engine/geirst/fix-cluster-stats-change-tracker-in-clustercontroller Fix ClusterStatsChangeTracker to keep previous 'may have merges pendi… | ||||
| * | Fix ClusterStatsChangeTracker to keep previous 'may have merges pending' ↵ | Geir Storli | 2018-03-08 | 5 | -70/+104 |
| | | | | | | | | state per content node. | ||||
* | | More descriptive test names | Tor Brede Vekterli | 2018-03-08 | 1 | -5/+5 |
| | | |||||
* | | Update constraint mock variable naming | Tor Brede Vekterli | 2018-03-08 | 1 | -4/+4 |
| | | |||||
* | | Must use published state from default bucket space, not baseline | Tor Brede Vekterli | 2018-03-08 | 1 | -1/+7 |
| | | |||||
* | | Unify style | Tor Brede Vekterli | 2018-03-08 | 1 | -6/+9 |
| | | |||||
* | | Add a simple maintenance state transition constraint for nodes in default space | Tor Brede Vekterli | 2018-03-08 | 6 | -14/+133 |
|/ | | | | | | | | Avoids transitioning an already up/init/retired node to maintenance mode when global merges are pending, but allows transitions when the node is considered down/maintenance in the already published state. Not stateful, so triggers false positives on cluster controller restart edges. | ||||
* | Simplifications. | Geir Storli | 2018-03-07 | 2 | -7/+3 |
| | |||||
* | Fix AggregatedStatsMergePendingChecker to take state of aggregated cluster ↵ | Geir Storli | 2018-03-07 | 9 | -85/+134 |
| | | | | | | | | | | stats into account. We may have merges pending if: - we don't yet have updates from all distributors - we don't have stats for the content node in question Also move mayHaveMergesPendingInGlobalSpace() to AggregatedStatsMergePendingChecker. | ||||
* | Also list derived bucket space states in html state. | Geir Storli | 2018-03-07 | 2 | -3/+13 |
| | |||||
* | Add bucket space column to html state. | Geir Storli | 2018-03-07 | 1 | -6/+20 |
| | |||||
* | Use computeIfAbsent() instead of explicit get() and put(). | Geir Storli | 2018-03-06 | 1 | -6/+1 |
| | |||||
* | Add factory functions for NodeEvent and improve some function names. | Geir Storli | 2018-03-06 | 8 | -35/+42 |
| | |||||
* | Extend EventDiffCalculator to emit events for changes in derived bucket ↵ | Geir Storli | 2018-03-02 | 8 | -80/+324 |
| | | | | space cluster states. | ||||
* | Add node state reason for nodes that may have buckets pending. | Geir Storli | 2018-03-02 | 3 | -13/+65 |
| | |||||
* | Also use AnnotatedClusterState for derived bucket space states in ↵ | Geir Storli | 2018-03-02 | 9 | -53/+71 |
| | | | | ClusterStateBundle. | ||||
* | Merge pull request #5177 from ↵ | Tor Brede Vekterli | 2018-03-01 | 10 | -55/+187 |
|\ | | | | | | | | | vespa-engine/geirst/add-buckets-pending-stats-on-clustercontroller-status-page Geirst/add buckets pending stats on clustercontroller status page | ||||
| * | Simplifications. | Geir Storli | 2018-03-01 | 4 | -6/+10 |
| | | |||||
| * | Add per node buckets pending stats on html status page. | Geir Storli | 2018-02-28 | 6 | -34/+93 |
| | | |||||
| * | Add function to get aggregated node stats per distributor. | Geir Storli | 2018-02-28 | 4 | -21/+90 |
| | | |||||
* | | Merge pull request #5164 from ↵ | Geir Storli | 2018-02-28 | 21 | -92/+490 |
|\ \ | |/ |/| | | | | | vespa-engine/vekterli/add-v3-cluster-state-propagation-rpc Add v3 RPC for sending cluster states to content nodes | ||||
| * | Add class comments | Tor Brede Vekterli | 2018-02-28 | 5 | -0/+32 |
| | | |||||
| * | Factor out common RPC version downgrade code | Tor Brede Vekterli | 2018-02-27 | 1 | -12/+11 |
| | | |||||
| * | Add v3 RPC for sending cluster states to content nodes | Tor Brede Vekterli | 2018-02-27 | 21 | -84/+451 |
| | | | | | | | | | | | | | | | | | | Supports sending states for multiple bucket spaces at once, with possibilities for extending protocol later for sending distribution config etc. Payload is LZ4-compressed when possible. If a receiver node does not understand the v3 protocol, the protocol version is transparently downgraded to legacy v2 RPC. | ||||
* | | Add switch to enable multiple bucket spaces in cluster controller. | Geir Storli | 2018-02-27 | 4 | -2/+11 |
|/ | |||||
* | Rename ClusterStateChangeTracker -> ClusterStatsChangeTracker. | Geir Storli | 2018-02-27 | 3 | -22/+22 |
| | |||||
* | Rename hasMergesPending() -> mayHaveMergesPending() followup. | Geir Storli | 2018-02-27 | 1 | -6/+6 |
| | |||||
* | Rename hasMergesPending() -> mayHaveMergesPending(). | Geir Storli | 2018-02-27 | 6 | -10/+10 |
| | |||||
* | Rename ClusterStatsBucketsPendingState -> ClusterStateChangeTracker. | Geir Storli | 2018-02-27 | 3 | -13/+12 |
| | |||||
* | Wire buckets pending state into state version tracker. | Geir Storli | 2018-02-27 | 4 | -2/+65 |
| | |||||
* | Remove unused function parameter. | Geir Storli | 2018-02-27 | 4 | -11/+8 |
| | |||||
* | Add class tracking whether we have changes in buckets pending state in the ↵ | Geir Storli | 2018-02-27 | 4 | -3/+171 |
| | | | | 'global' bucket space. | ||||
* | Let BucketSpaceStats track invalid count to allow transition from invalid -> ↵ | Geir Storli | 2018-02-27 | 4 | -19/+52 |
| | | | | valid. | ||||
* | Add class checking whether a bucket space on a content node might have ↵ | Geir Storli | 2018-02-27 | 5 | -51/+161 |
| | | | | buckets pending. | ||||
* | Track whether BucketSpaceStats is valid or not. | Geir Storli | 2018-02-27 | 3 | -3/+64 |
| | |||||
* | Nonfunctional changes only | Jon Bratseth | 2018-02-26 | 3 | -165/+24 |
| | |||||
* | Remove never used distributor-put-latency metrics from restapiv2. | Geir Storli | 2018-02-22 | 13 | -327/+0 |
| | |||||
* | Initial support for per bucket space cluster states in cluster controller | Tor Brede Vekterli | 2018-02-22 | 21 | -102/+757 |
| | | | | | Multiple spaces are only enabled in tests, so the controller still only generates the legacy baseline cluster state, maintaining today's behavior. | ||||
* | Cleanup import statements. | Geir Storli | 2018-02-20 | 1 | -1/+0 |
| | |||||
* | Add factory functions for BucketSpaceStats. | Geir Storli | 2018-02-20 | 2 | -7/+14 |
| | |||||
* | License year bump. | Geir Storli | 2018-02-20 | 2 | -2/+2 |
| | |||||
* | Add handling of bucket spaces stats to HostInfo and ClusterStatsAggregator. | Geir Storli | 2018-02-19 | 12 | -417/+281 |
| | | | | Handling of outstanding merge ops has been removed as this information has never been provided by the distributors. | ||||
* | Rename NodeMergeStats -> ContentNodeStats. | Geir Storli | 2018-02-19 | 7 | -60/+60 |
| | |||||
* | Rename StorageMergeStats -> ContentClusterStats. | Geir Storli | 2018-02-19 | 6 | -39/+35 |
| | |||||
* | Log when a cluster state version is published | Tor Brede Vekterli | 2017-10-30 | 1 | -0/+1 |
| | | | | | | Makes it much easier to reason about which state transitions have been made visible in the cluster, and which ones have just been internal state transitions in the controller. | ||||
* | Update wanted state on description changes, and fix method names | Håkon Hallingstad | 2017-10-24 | 1 | -13/+17 |
| | |||||
* | Also set the distributor wanted state when safe-setting the storage node state | Håkon Hallingstad | 2017-10-21 | 4 | -12/+247 |
| | | | | | | | | | | This is done as part of the SAFE REST API call to set the node state of a storage node to ensure atomicity of the state change, reduce the number of state changes, and minimize the time to complete the state changes. The right way to think about the safe-set is then: In order to safely set a storage node to (e.g.) maintenance, the distributor will also have to be set to down. And so on for the various permutations of state transitions. | ||||
* | Ignore current wanted state when safely setting state to up | Håkon Hallingstad | 2017-10-20 | 2 | -10/+5 |
| | |||||
* | Merge pull request #3525 from ↵ | Tor Brede Vekterli | 2017-10-12 | 8 | -21/+165 |
|\ | | | | | | | | | vespa-engine/vekterli/re-enable-synchronous-set-node-state Re-enable synchronous set node state with additional safeguards |