aboutsummaryrefslogtreecommitdiffstats
path: root/storage/src/tests/storageserver/rpc/caching_rpc_target_resolver_test.cpp
Commit message (Collapse)AuthorAgeFilesLines
* Update Verizon Media copyright notices.gjoranv2021-10-071-1/+1
|
* Use a hash map for specs. If the request is a point lookup then just use a ↵Henning Baldersheim2021-06-021-1/+1
| | | | | | | | hash lookup. If it is a wildcard lookup iterate as earlier on. Also use vespalib::stringref in interface to avoid conversion. Use vespalib:string in the hash map to locate string in object aswe are still on old abi.
* As we have have now removed the expensive Route member we can further ↵Henning Baldersheim2020-11-261-2/+4
| | | | | | | | | | compact the message objects. - Compact StorageMessageAddress to 16 bytes by - using reference to cluster name. - Use small enums for protocol and node type. - Avoid having StorageMessage as separate allocation. - Avoid default values
* Add support for multiple RPC targets per node when using Storage API over RPC.Geir Storli2020-10-021-26/+44
| | | | | | | This should allow for better parallelization and higher feed throughput. The bucket id associated with a message is used to select the RPC target. This ensures the same RPC target is used for all messages to the same bucket to the same node, and the RPC target itself handles sequencing of these messages.
* Minor adjustments based on review feedback.Geir Storli2020-09-141-3/+3
|
* Decouple CachingRpcTargetResolver from slobrok and fnet implementations and ↵Geir Storli2020-09-141-0/+134
write unit tests.