Kafka Versions and Configurations
Versions
Kafka versions 3.5 and 4.1 are supported.
Node configurations
When creating a Kafka managed database cluster, you can select the node configuration — the number of vCPUs, RAM, and disk size.
The available node configurations are divided into lines. Depending on the line, configuration, and pool, different processors and disks.
When choosing a configuration, keep in mind that a portion of the disk space is reserved for service needs and is not available for database storage. For more information, see the Using disk space in a Kafka cluster instructions.
After creating a cluster, you can change the node configuration — scale the cluster.
Configuration lines
The resource ratio in configuration lines can be:
To see the availability of configuration lines in regions, see the Managed Databases availability matrix.
Standard
A line of fixed configurations with a local disk and a balanced vCPU:RAM ratio, suitable for most DBMS. We recommend using this line if you do not know the workload profile.
Intel® Xeon® Scalable or AMD EPYC™ processors are used. To see the processor frequency in different lines, see the Processors table.
To see disk performance and bandwidth in different lines, see the Performance and bandwidth table.
CPU
A line of fixed configurations with a local disk and a balanced vCPU:RAM ratio. Suitable for workload profiles that are computationally demanding. For example, if the database performs analytical queries, multiple nested queries, or data encryption. One way to determine such a load profile is to monitor the Load Average metric, which shows the average system load over one, five, or 15 minutes.
Intel® Xeon® Scalable or AMD EPYC™ processors are used. To see the processor frequency in different lines, see the Processors table.
To see disk performance and bandwidth in different lines, see the Performance and bandwidth table.
Memory
A line of fixed configurations with a local disk and a balanced vCPU:RAM ratio. Suitable for workload profiles that are demanding on caching. For example, if the database performs multiple, rarely repeating queries to different parts of tables. One way to determine such a load profile is to monitor the Cache hit ratio (Cash_hit_ratio) metric, which shows the percentage of data in a query read from the cache.
Intel® Xeon® Scalable or AMD EPYC™ processors are used. To see the processor frequency in different lines, see the Processors table.
To see disk performance and bandwidth in different lines, see the Performance and bandwidth table.
HighFreq
A line of fixed configurations with a balanced vCPU:RAM ratio.
High-performance Enterprise-grade equipment is used:
- Intel® Xeon® Gold 6354 (in pools ru-9, ru-2, ru-8, ke-1) or AMD EPYC 9474F (in pools ru-3, ru-7, uz-1) processors. To see the processor frequency in different lines, see the Processors table;
- RAM ECC Reg 3.2 GHz (in pools ru-9, ru-2, ru-8, ke-1) or RAM DDR5 ECC Reg 4.8 GHz (in pools ru-3, ru-7, uz-1);
- High-performance SSD NVMe disks. To see disk performance and bandwidth in different lines, see the Performance and bandwidth table.
Dedicated
A line of fixed configurations with cluster nodes on separate cloud servers. Each cloud server occupies an entire dedicated host (physical server). Suitable for users who need physical isolation of databases from other clients, maximum performance, and maximum available resource sizes.
High-performance Enterprise-grade equipment is used:
- one Intel® Xeon® Gold 6336Y, Intel® Xeon® Gold 6240, Intel® Xeon® W-2255 or Intel® Xeon® E-2488 processor depending on the configuration. To see the type and frequency of processors in different lines, see the Processors table;
- RAM 128 GB DDR4 ECC Reg, 64 GB DDR4 ECC Reg or 32 GB DDR5 ECC Reg depending on the configuration;
- SSD NVMe disks in RAID 1. The number of disks in the cluster depends on the configuration. To see disk performance and bandwidth in different lines, see the Performance and bandwidth table;
- two 2 × 25 GE network cards for the main network + MC-LAG with 25 Gbps connection speed for the service network (for backup, monitoring, and data replication in the cluster).
* The DBMS clusters use Hyper-Threading Technology. Each physical core can process multiple threads in parallel — as a result, the total number of virtual cores (vCPUs) exceeds the number of physical cores. This allows for more efficient load distribution during multithreaded or analytical tasks.
** Part of the RAM is reserved for the physical server services.
* ** The disks are combined into RAID 1 — a disk array with mirroring that provides additional fault tolerance. When using mirroring for databases, 50% of the total disk space is available. A portion of the disk space is also reserved for the physical server services.
Flex
A line of custom configurations with local or network volume, in which you can choose the resource ratio.
For more information about disks, see the Disks instructions.
Intel® Xeon® Scalable or AMD EPYC™ processors are used. To see the processor frequency in different lines, see the Processors table.
To see the availability of configurations in regions, see the Managed Databases availability matrix. Configuration limits depend on the pool.
Local disk
Network volume
* If the configuration has more than 8 vCPUs, the vCPU:RAM ratio must be at least 1:4. For example, for 10 vCPUs, at least 40 GB of RAM is required.
** If the configuration has more than 8 vCPUs, the vCPU:Local disk ratio must be at least 1:32. For example, for 10 vCPUs, a disk with a size of at least 320 GB is required.
If the configurations are not suitable, you can order a custom configuration. Create a ticket and specify the resource ratio:
- vCPU:RAM — at least 1:4;
- vCPU:RAM:Local disk — at least 1:4:16.
Processors
Available processors differ across configuration lines. The processor frequency affects the speed of processing user requests, executing complex algorithms, and performing operations with data. When a cloud server is under 100% load, the processor operates using the Turbo Boost technology. Since the processor is emulated, a lower frequency will be displayed during testing.
To see the availability of configuration lines in regions, see the Managed Databases availability matrix.