Today we released a new release of the stable series of RonDB. This version RonDB 22.10.7 is mostly a bug fix release, but also contains a few new features that were required for the Kubernetes integration of RonDB.
The major development in RonDB is currently around RonDB 24.10 which is aimed for a first release in 1-2 months.
RonDB 22.10.7 contains the following new features:
RONDB-789: Find out memory availability in a container
RonDB uses Automatic Memory Configuration as default. In this setting RonDB will discover the amount of memory available and allocate most of the available memory to the RonDB data nodes. In Linux using VMs or bare metal servers this information is found in /proc/meminfo. However running in a container the information is instead stored in /sys/fs/cgroup/memory.max. The setting of the amount of memory to be available is set in the RonDB Helm charts and can thus now be automatically detected without extra configuration variables. Setting TotalMemoryConfig will still override the discovered memory size.
RONDB-785: Set LocationDomainId dynamically
With RonDB Kubernetes support it is very easy to setup the cluster in such a way that nodes in the RonDB cluster are spread in several Availability Zones (Availability Domains in Oracle Cloud). In order to avoid sending network messages over Availability Zone boundaries more than necessary we try to locate the transaction coordinator in our domain and read data from our domain if possible.
To avoid complex Kubernetes setups this required the ability to set the domain in the RonDB data node container using a RonDB management client command. In RonDB we use a Location Domain Id to figure out which Availability Zone we are in. How this is set is up to the management software (Kubernetes and containers in our case).
This features makes it possible to access RonDB through a network load balancer that chooses a MySQL Server (or RDRS server) in the same domain, this MySQL Server will contact a RonDB data node in the same domain and finally the RonDB data node will ensure that it reads data from the same domain. Thus we can completely avoid any network messages that passes over domain boundaries for key lookups that reads.
RONDB-784: Performance improvement for Complex Features in Go REST API Server
- Bump GO version to 1.22.9.
- Use hamba avro as a replacement for linkedin avro library to deserialize complex features
- Avoid json.Unmarshal when parsing complex feature field
- Use Sonic library to serialize JSON before sending to the client.
This feature cuts latency of complex feature processing to half of what it used to be. This significantly improves latency of Feature Store REST API lookups.
RONDB-776: Changed hopsworks.schema to use TEXT data type
Impacts the GO REST API Server and its Feature Store REST API.
No comments:
Post a Comment