Commit message (Collapse) | Author | Age | Files | Lines | ||
---|---|---|---|---|---|---|
... | ||||||
* | Use enum class for the flags. | Henning Baldersheim | 2022-01-06 | 1 | -4/+4 | |
| | ||||||
* | Simplify DocEntry to get a clean interface with multiple implementations, ↵ | Henning Baldersheim | 2022-01-06 | 1 | -0/+1 | |
| | | | | | | instead of an mutant. Also add tests for the different variations a DocEntry can have. | |||||
* | _executor -> _thread | Henning Baldersheim | 2021-12-09 | 1 | -2/+2 | |
| | ||||||
* | Add init_fun to vespalib::Thread too to figure out what the thread is used for. | Henning Baldersheim | 2021-12-09 | 1 | -1/+3 | |
| | ||||||
* | Decrement persistence thread merge counter when syncronous processing is ↵ | Tor Brede Vekterli | 2021-12-03 | 1 | -0/+4 | |
| | | | | | | | | | | | | | | | | | | complete Add a generic interface for letting an operation know that the synchronous parts of its processing in the persistence thread is complete. This allows a potentially longer-running async operation to free up any limits that were put in place when it was taking up synchronous thread resources. Currently only used by merge-related operations (that may dispatch many async ops). Since we have a max upper bound for how many threads in a stripe may be processing merge ops at the same time (to avoid blocking client ops), we previously could effectively stall the pipelining of merges caused by hitting the concurrency limit even if all persistence threads were otherwise idle (waiting for prior async merge ops to complete). We now explicitly decrease the merge concurrency counter once the synchronous processing is done, allowing us to take on further merges immediately. | |||||
* | Add metrics for active operations on service layer. | Tor Egge | 2021-12-01 | 2 | -0/+151 | |
| | ||||||
* | Update operation metrics for delayed or chained merge handler replies. | Tor Egge | 2021-11-24 | 1 | -2/+76 | |
| | ||||||
* | Actually test maintenance -> down node state transition | Tor Brede Vekterli | 2021-11-24 | 1 | -1/+1 | |
| | ||||||
* | Handle case where bucket spaces have differing maintenance state for a node | Tor Brede Vekterli | 2021-11-24 | 1 | -26/+83 | |
| | | | | | | | | | | | Only skip deactivating buckets if the entire _node_ is marked as maintenance state, i.e. the node has maintenance state across all bucket spaces provided in the bundle. Otherwise treat the state transition as if the node goes down, deactivating all buckets. Also ensure that the bucket deactivation logic above the SPI is identical to that within Proton. This avoids bucket DBs getting out of sync between the two. | |||||
* | Update merge latency metrics after async writes have completed. | Tor Egge | 2021-11-23 | 1 | -2/+37 | |
| | ||||||
* | Revert "Continue serving search queries when in Maintenance node state ↵ | Henning Baldersheim | 2021-11-23 | 1 | -83/+26 | |
| | | | | [run-systemtest]" | |||||
* | Handle case where bucket spaces have differing maintenance state for a node | Tor Brede Vekterli | 2021-11-23 | 1 | -26/+83 | |
| | | | | | | | | | | | Only skip deactivating buckets if the entire _node_ is marked as maintenance state, i.e. the node has maintenance state across all bucket spaces provided in the bundle. Otherwise treat the state transition as if the node goes down, deactivating all buckets. Also ensure that the bucket deactivation logic above the SPI is identical to that within Proton. This avoids bucket DBs getting out of sync between the two. | |||||
* | GC unused code | Henning Baldersheim | 2021-11-20 | 2 | -16/+0 | |
| | ||||||
* | Remove redundant sync_all | Henning Baldersheim | 2021-11-20 | 1 | -1/+0 | |
| | ||||||
* | Let removeAsync handle list of documents. | Henning Baldersheim | 2021-11-18 | 3 | -6/+14 | |
| | ||||||
* | Move BucketIdFactory to test fixture. | Henning Baldersheim | 2021-11-18 | 6 | -21/+13 | |
| | ||||||
* | Move removeLocation over to Asynchandler and issue all removes for one ↵ | Henning Baldersheim | 2021-11-17 | 1 | -4/+9 | |
| | | | | | | bucket before waiting for the replies. Prepare RemoveResult to contain more replies. | |||||
* | Rename ISequencedTaskExecutor::sync() to sync_all(). | Tor Egge | 2021-10-28 | 1 | -1/+1 | |
| | ||||||
* | Merge pull request #19735 from ↵ | Geir Storli | 2021-10-28 | 3 | -0/+80 | |
|\ | | | | | | | | | vespa-engine/toregge/handover-tracker-to-apply-bucket-diff-state-on-exceptions Handover tracker to ApplyBucketDiffState on exceptions. | |||||
| * | Handover tracker to ApplyBucketDiffState on exceptions. | Tor Egge | 2021-10-26 | 3 | -0/+80 | |
| | | ||||||
* | | Update 2019 Oath copyrights. | gjoranv | 2021-10-27 | 2 | -2/+2 | |
|/ | ||||||
* | Adjust dummy persistence spi semantics towards proton spi semantics when | Tor Egge | 2021-10-25 | 1 | -4/+4 | |
| | | | | | | | bucket doesn't exist: * getBucketInfo() returns success with empty bucket info * createIterator() returns success * iterate() returns empty complete result. | |||||
* | Merge pull request #19717 from ↵ | Geir Storli | 2021-10-25 | 2 | -4/+8 | |
|\ | | | | | | | | | vespa-engine/toregge/delay-apply-bucket-diff-state-deletion-try-2 Delay deletion of ApplyBucketState. | |||||
| * | Delay deletion of ApplyBucketState. | Tor Egge | 2021-10-25 | 2 | -4/+8 | |
| | | ||||||
* | | create/delete bucket will never throw. | Henning Baldersheim | 2021-10-25 | 4 | -9/+7 | |
| | | ||||||
* | | Async createBucket | Henning Baldersheim | 2021-10-25 | 3 | -7/+7 | |
|/ | ||||||
* | Add class comment for MergeHandlerTest. | Tor Egge | 2021-10-21 | 1 | -0/+4 | |
| | ||||||
* | Delay replies for async apply bucket diff. | Tor Egge | 2021-10-21 | 2 | -28/+92 | |
| | ||||||
* | Eliminate ApplyBucketDiffEntryResult. | Tor Egge | 2021-10-20 | 1 | -21/+39 | |
| | ||||||
* | Merge pull request #19643 from ↵ | Geir Storli | 2021-10-20 | 1 | -4/+3 | |
|\ | | | | | | | | | vespa-engine/toregge/update-merge-latency-metrics-from-operation-complete-callbacks Update merge handler put/remove latency metrics from operation complete callback. | |||||
| * | Update merge handler put/remove latency metrics from operation complete ↵ | Tor Egge | 2021-10-19 | 1 | -4/+3 | |
| | | | | | | | | callback. | |||||
* | | Change editMergeStatus to return a shared pointer to merge status | Tor Egge | 2021-10-19 | 1 | -19/+19 | |
| | | | | | | | | to ensure it remains live while being used in merge handler. | |||||
* | | Merge pull request #19625 from vespa-engine/balder/only-keep-async-variants | Henning Baldersheim | 2021-10-19 | 3 | -38/+64 | |
|\ \ | | | | | | | Only keep async variant to simplify what to implement and what fallba… | |||||
| * | | Only keep async variant to simplify what to implement and what fallback ↵ | Henning Baldersheim | 2021-10-18 | 3 | -38/+64 | |
| |/ | | | | | | | there are. | |||||
* / | Pass message tracker to MergeHandler::handleApplyBucketDiffReply. | Tor Egge | 2021-10-19 | 1 | -21/+21 | |
|/ | | | | | | This enables handover of bucket lock (part of message tracker) to be forwarded to ApplyBucketDiffState to keep bucket locked until async writes have been completed and service layer bucket db has been updated. | |||||
* | Implement async delete bucket. | Henning Baldersheim | 2021-10-18 | 3 | -8/+17 | |
| | ||||||
* | Add class representing async state for applying bucket diff to local node. | Tor Egge | 2021-10-15 | 3 | -71/+151 | |
| | ||||||
* | Update Verizon Media copyright notices. | gjoranv | 2021-10-07 | 3 | -3/+3 | |
| | ||||||
* | Update 2017 copyright notices. | gjoranv | 2021-10-07 | 27 | -27/+27 | |
| | ||||||
* | Report max address space used in attribute vector components from content ↵ | Geir Storli | 2021-08-20 | 1 | -29/+15 | |
| | | | | | | | nodes (proton) to the cluster controller. This is more generic than explicit address space values for enum store and multi value. This is used in the cluster controller to determine whether to block external feed. | |||||
* | - Change error handling so that both synchonous and asynchronous errors can ↵ | Henning Baldersheim | 2021-02-23 | 1 | -14/+14 | |
| | | | | | | | | be reported back from bucket executor. - Treat remapping as an error. - For lidspace compaction job iterator is reset and will be recreated on next invocation. - For bucketmove th ebucket is rechecked and either discarded or restarted. | |||||
* | - Reduce visibility of ClusterState and Distribution. | Henning Baldersheim | 2021-02-19 | 5 | -2/+9 | |
| | ||||||
* | use size literals in storage | Arne Juul | 2021-02-15 | 2 | -7/+9 | |
| | ||||||
* | Make the noise level used when deciding whether to report resource usage ↵ | Geir Storli | 2021-02-04 | 1 | -12/+34 | |
| | | | | configurable. | |||||
* | Revert "Properly track execution of BucketTasks and provide sync() and ↵ | Henning Baldersheim | 2021-02-02 | 1 | -34/+0 | |
| | | | | order… " | |||||
* | Properly track execution of BucketTasks and provide sync() and orderly shutdown. | Henning Baldersheim | 2021-02-02 | 1 | -0/+34 | |
| | ||||||
* | Revert "Implement BucketExecutor::sync." | Henning Baldersheim | 2021-02-02 | 1 | -34/+0 | |
| | ||||||
* | Use conditional notify instead of sleep. | Henning Baldersheim | 2021-02-01 | 1 | -0/+1 | |
| | ||||||
* | Implement BucketExecutor::sync. | Henning Baldersheim | 2021-02-01 | 1 | -0/+33 | |
| | ||||||
* | Wire reporting of attribute resource usage all the way to the cluster ↵ | Geir Storli | 2021-01-29 | 1 | -0/+22 | |
| | | | | controller via the host info API. |