These Tair (Redis OSS-compatible) specifications are no longer available for purchase. Existing instances continue to work normally. This page lists the connection limits, bandwidth, and queries per second (QPS) reference values for each retired specification.
Enterprise Edition (Memory-optimized) with read/write splitting (formerly Performance-enhanced)
Specification | InstanceClass (for API calls) | I/O threads | Read/write nodes | Read replicas | Bandwidth (MB/s) | Maximum connections | QPS reference |
1 GB performance-enhanced read/write splitting instance (1 node, 1 read replica) | redis.amber.logic.splitrw.small.1db.1rodb.6proxy.multithread | 4 | 1 | 1 | 192 | 60000 | 480000 |
2 GB performance-enhanced read/write splitting instance (1 node, 1 read replica) | redis.amber.logic.splitrw.mid.1db.1rodb.6proxy.multithread | 4 | 1 | 1 | 192 | 60000 | 480000 |
4 GB performance-enhanced read/write splitting instance (1 node, 1 read replica) | redis.amber.logic.splitrw.stand.1db.1rodb.6proxy.multithread | 4 | 1 | 1 | 192 | 60000 | 480000 |
8 GB performance-enhanced read/write splitting instance (1 node, 1 read replica) | redis.amber.logic.splitrw.large.1db.1rodb.6proxy.multithread | 4 | 1 | 1 | 192 | 60000 | 480000 |
16 GB performance-enhanced read/write splitting instance (1 node, 1 read replica) | redis.amber.logic.splitrw.2xlarge.1db.1rodb.6proxy.multithread | 4 | 1 | 1 | 192 | 60000 | 480000 |
32 GB performance-enhanced read/write splitting instance (1 node, 1 read replica) | redis.amber.logic.splitrw.4xlarge.1db.1rodb.6proxy.multithread | 4 | 1 | 1 | 192 | 60000 | 480000 |
64 GB performance-enhanced read/write splitting instance (1 node, 1 read replica) | redis.amber.logic.splitrw.8xlarge.1db.1rodb.6proxy.multithread | 4 | 1 | 1 | 192 | 60000 | 480000 |
1 GB performance-enhanced read/write splitting instance (1 node, 3 read replicas) | redis.amber.logic.splitrw.small.1db.3rodb.12proxy.multithread | 4 | 1 | 3 | 384 | 120000 | 960000 |
2 GB performance-enhanced read/write splitting instance (1 node, 3 read replicas) | redis.amber.logic.splitrw.mid.1db.3rodb.12proxy.multithread | 4 | 1 | 3 | 384 | 120000 | 960000 |
4 GB performance-enhanced read/write splitting instance (1 node, 3 read replicas) | redis.amber.logic.splitrw.stand.1db.3rodb.12proxy.multithread | 4 | 1 | 3 | 384 | 120000 | 960000 |
8 GB performance-enhanced read/write splitting instance (1 node, 3 read replicas) | redis.amber.logic.splitrw.large.1db.3rodb.12proxy.multithread | 4 | 1 | 3 | 384 | 120000 | 960000 |
16 GB performance-enhanced read/write splitting instance (1 node, 3 read replicas) | redis.amber.logic.splitrw.2xlarge.1db.3rodb.12proxy.multithread | 4 | 1 | 3 | 384 | 120000 | 960000 |
32 GB performance-enhanced read/write splitting instance (1 node, 3 read replicas) | redis.amber.logic.splitrw.4xlarge.1db.3rodb.12proxy.multithread | 4 | 1 | 3 | 384 | 120000 | 960000 |
64 GB performance-enhanced read/write splitting instance (1 node, 3 read replicas) | redis.amber.logic.splitrw.8xlarge.1db.3rodb.12proxy.multithread | 4 | 1 | 3 | 384 | 120000 | 960000 |
1 GB performance-enhanced read/write splitting instance (1 node, 5 read replicas) | redis.amber.logic.splitrw.small.1db.5rodb.18proxy.multithread | 4 | 1 | 5 | 576 | 180000 | 1440000 |
2 GB performance-enhanced read/write splitting instance (1 node, 5 read replicas) | redis.amber.logic.splitrw.mid.1db.5rodb.18proxy.multithread | 4 | 1 | 5 | 576 | 180000 | 1440000 |
4 GB performance-enhanced read/write splitting instance (1 node, 5 read replicas) | redis.amber.logic.splitrw.stand.1db.5rodb.18proxy.multithread | 4 | 1 | 5 | 576 | 180000 | 1440000 |
8 GB performance-enhanced read/write splitting instance (1 node, 5 read replicas) | redis.amber.logic.splitrw.large.1db.5rodb.18proxy.multithread | 4 | 1 | 5 | 576 | 180000 | 1440000 |
16 GB performance-enhanced read/write splitting instance (1 node, 5 read replicas) | redis.amber.logic.splitrw.2xlarge.1db.5rodb.18proxy.multithread | 4 | 1 | 5 | 576 | 180000 | 1440000 |
32 GB performance-enhanced read/write splitting instance (1 node, 5 read replicas) | redis.amber.logic.splitrw.4xlarge.1db.5rodb.18proxy.multithread | 4 | 1 | 5 | 576 | 180000 | 1440000 |
64 GB performance-enhanced read/write splitting instance (1 node, 5 read replicas) | redis.amber.logic.splitrw.8xlarge.1db.5rodb.18proxy.multithread | 4 | 1 | 5 | 576 | 180000 | 1440000 |
Standard Edition (dual-replica, custom package)
Specification | InstanceClass (for API calls) | Maximum connections | Bandwidth (MB/s) | QPS reference |
1 GB high-spec master-replica instance | redis.master.small.special2x | 20000 | 48 | 80000 |
2 GB high-spec master-replica instance | redis.master.mid.special2x | 20000 | 48 | 80000 |
4 GB high-spec master-replica instance | redis.master.stand.special2x | 20000 | 48 | 80000 |
8 GB high-spec master-replica instance | redis.master.large.special1x | 20000 | 48 | 80000 |
16 GB high-spec master-replica instance | redis.master.2xlarge.special1x | 20000 | 48 | 80000 |
32 GB high-spec master-replica instance | redis.master.4xlarge.special1x | 20000 | 48 | 80000 |
64 GB high-spec master-replica instance | redis.master.8xlarge.special1x | 20000 | 96 | 80000 |
Standard Edition (single-replica, custom package)
Specification | InstanceClass (for API calls) | Maximum connections | Bandwidth (MB/s) | QPS reference |
1 GB high-spec single-node instance | redis.basic.small.special2x | 20000 | 48 | 80000 |
2 GB high-spec single-node instance | redis.basic.mid.special2x | 20000 | 48 | 80000 |
4 GB high-spec single-node instance | redis.basic.stand.special2x | 20000 | 48 | 80000 |
8 GB high-spec single-node instance | redis.basic.large.special2x | 20000 | 48 | 80000 |
16 GB high-spec single-node instance | redis.basic.2xlarge.special2x | 20000 | 48 | 80000 |
32 GB high-spec single-node instance | redis.basic.4xlarge.special2x | 20000 | 48 | 80000 |
Standard Edition for zone-disaster recovery
| Specification | InstanceClass (for API calls) | Maximum connections | Bandwidth (MB/s) | QPS reference |
|---|---|---|---|---|
| 1 GB zone-disaster recovery instance | redis.logic.sharding.drredissdb1g.1db.0rodb.4proxy.default | 10,000 | 10 | 80,000 |
| 2 GB zone-disaster recovery instance | redis.logic.sharding.drredissdb2g.1db.0rodb.4proxy.default | 10,000 | 16 | 80,000 |
| 4 GB zone-disaster recovery instance | redis.logic.sharding.drredissdb4g.1db.0rodb.4proxy.default | 10,000 | 24 | 80,000 |
| 8 GB zone-disaster recovery instance | redis.logic.sharding.drredissdb8g.1db.0rodb.4proxy.default | 10,000 | 24 | 80,000 |
| 16 GB zone-disaster recovery instance | redis.logic.sharding.drredissdb16g.1db.0rodb.4proxy.default | 10,000 | 32 | 80,000 |
| 32 GB zone-disaster recovery instance | redis.logic.sharding.drredissdb32g.1db.0rodb.4proxy.default | 10,000 | 32 | 80,000 |
| 64 GB zone-disaster recovery instance | redis.logic.sharding.drredissdb64g.1db.0rodb.4proxy.default | 10,000 | 48 | 80,000 |
Cluster Edition (dual-replica)
| Specification | InstanceClass (for API calls) | Shards | Maximum connections | Bandwidth (MB/s) | QPS reference |
|---|---|---|---|---|---|
| 1 GB cluster instance (2 shards) | redis.logic.sharding.512m.2db.0rodb.4proxy.default | 2 | 20,000 | 48 | 200,000 |
| 1 GB cluster instance (4 shards) | redis.logic.sharding.256m.4db.0rodb.4proxy.default | 4 | 40,000 | 96 | 400,000 |
| 2 GB cluster instance (4 shards) | redis.logic.sharding.512m.4db.0rodb.4proxy.default | 4 | 40,000 | 96 | 400,000 |
| 2 GB cluster instance (8 shards) | redis.logic.sharding.256m.8db.0rodb.8proxy.default | 8 | 80,000 | 192 | 800,000 |
| 4 GB cluster instance (8 shards) | redis.logic.sharding.512m.8db.0rodb.8proxy.default | 8 | 80,000 | 192 | 800,000 |
| 4 GB cluster instance (16 shards) | redis.logic.sharding.256m.16db.0rodb.16proxy.default | 16 | 160,000 | 384 | 1,600,000 |
| 8 GB cluster instance (16 shards) | redis.logic.sharding.512m.16db.0rodb.16proxy.default | 16 | 160,000 | 384 | 1,600,000 |
| 8 GB cluster instance (32 shards) | redis.logic.sharding.256m.32db.0rodb.32proxy.default | 32 | 320,000 | 768 | 3,200,000 |
| 16 GB cluster instance (32 shards) | redis.logic.sharding.512m.32db.0rodb.32proxy.default | 32 | 320,000 | 768 | 3,200,000 |
| 16 GB cluster instance | redis.sharding.small.default | 8 | 80,000 | 768 | 640,000 |
| 32 GB cluster instance | redis.sharding.mid.default | 8 | 80,000 | 768 | 640,000 |
| 64 GB cluster instance | redis.sharding.large.default | 8 | 80,000 | 768 | 640,000 |
| 128 GB cluster instance | redis.sharding.2xlarge.default | 16 | 160,000 | 1,536 | 1,280,000 |
| 256 GB cluster instance | redis.sharding.4xlarge.default | 16 | 160,000 | 1,536 | 1,280,000 |
| 512 GB cluster instance | redis.sharding.8xlarge.default | 32 | 320,000 | 2,048 | 2,560,000 |
Cluster Edition for zone-disaster recovery
| Specification | InstanceClass (for API calls) | Shards | Maximum connections | Bandwidth (MB/s) | QPS reference |
|---|---|---|---|---|---|
| 16 GB cluster instance for zone-disaster recovery | redis.logic.sharding.drredismdb16g.8db.0rodb.8proxy.default | 8 | 80,000 | 768 | 640,000 |
| 32 GB cluster instance for zone-disaster recovery | redis.logic.sharding.drredismdb32g.8db.0rodb.8proxy.default | 8 | 80,000 | 768 | 640,000 |
| 64 GB cluster instance for zone-disaster recovery | redis.logic.sharding.drredismdb64g.8db.0rodb.8proxy.default | 8 | 80,000 | 768 | 640,000 |
| 128 GB cluster instance for zone-disaster recovery | redis.logic.sharding.drredismdb128g.16db.0rodb.16proxy.default | 16 | 160,000 | 1,536 | 1,280,000 |
| 256 GB cluster instance for zone-disaster recovery | redis.logic.sharding.drredismdb256g.16db.0rodb.16proxy.default | 16 | 160,000 | 1,536 | 1,280,000 |
| 512 GB cluster instance for zone-disaster recovery | redis.logic.sharding.drredismdb512g.32db.0rodb.32proxy.default | 32 | 320,000 | 2,048 | 2,560,000 |
Bandwidth calculation rules
Each bandwidth value in the tables above represents the total bandwidth for the entire instance — the combined bandwidth across all shards or nodes.
Bandwidth applies equally to upstream and downstream traffic. For example, a 10 MB/s (80 Mbps) instance has 10 MB/s upstream and 10 MB/s downstream.
The bandwidth limits of Tair and Redis Open-Source Edition refer to the data transfer capacity of individual shards within their respective distributed systems. The limits are generally independent of the network connection type used by clients.
To handle unexpected or scheduled traffic peaks, adjust the instance bandwidth. For details, see Manually increase the bandwidth of an instance.
For common bandwidth questions, see FAQ about bandwidth.
FAQ
The zone-disaster recovery specifications are retired. How do I create an instance with zone-disaster recovery?
The zone-disaster recovery architecture has been upgraded. When creating an instance, set Zone Type to Dual-zone and specify a Primary Zone and a Secondary Zone.