This topic describes the specifications of performance-enhanced cluster instances of ApsaraDB for Redis Enhanced Edition (Tair). The specifications include the memory capacity, maximum number of connections, maximum bandwidth, and queries per second (QPS) reference value.
|Instance type||InstanceClass that is used in API operations||Number of CPU cores||Number of I/O threads||Number of shards||Maximum number of new connections per second||Maximum number of connections (in direct connect mode) )||Maximum number of connections (in proxy mode) )||Bandwidth (MB/s)||QPS reference value|
|2 GB performance-enhanced cluster instance||redis.amber.logic.sharding.1g.2db.0rodb.6proxy.multithread||12||4||2||50,000||60,000||480,000||192||480,000|
|4 GB performance-enhanced cluster instance||redis.amber.logic.sharding.2g.2db.0rodb.6proxy.multithread||12||4||2||50,000||60,000||480,000||192||480,000|
|8 GB performance-enhanced cluster instance||redis.amber.logic.sharding.2g.4db.0rodb.12proxy.multithread||24||4||4||50,000||120,000||500,000||384||960,000|
|16 GB performance-enhanced cluster instance||redis.amber.logic.sharding.2g.8db.0rodb.24proxy.multithread||48||4||8||50,000||240,000||500,000||768||1,920,000|
|32 GB performance-enhanced cluster instance||redis.amber.logic.sharding.4g.8db.0rodb.24proxy.multithread||48||4||8||50,000||240,000||500,000||768||1,920,000|
|64 GB performance-enhanced cluster instance||redis.amber.logic.sharding.8g.8db.0rodb.24proxy.multithread||48||4||8||50,000||240,000||500,000||768||1,920,000|
|96 GB performance-enhanced cluster instance||redis.amber.logic.sharding.6g.16db.0rodb.48proxy.multithread||96||4||16||50,000||480,000||500,000||1,536||3,840,000|
|128 GB performance-enhanced cluster instance||redis.amber.logic.sharding.8g.16db.0rodb.48proxy.multithread||96||4||16||50,000||480,000||500,000||1,536||3,840,000|
|256 GB performance-enhanced cluster instance||redis.amber.logic.sharding.16g.16db.0rodb.48proxy.multithread||96||4||16||50,000||480,000||500,000||1,536||3,840,000|
|512 GB performance-enhanced cluster instance||redis.amber.logic.sharding.16g.32db.0rodb.96proxy.multithread||96||4||32||50,000||960,000||500,000||2,048||7,680,000|
|1,024 GB performance-enhanced cluster instance||redis.amber.logic.sharding.16g.64db.0rodb.192proxy.multithread||384||4||64||50,000||1,920,000||500,000||2,048||15,360,000|
|2,048 GB performance-enhanced cluster instance||redis.amber.logic.sharding.16g.128db.0rodb.384proxy.multithread||768||4||128||50,000||3,840,000||500,000||2,048||30,720,000|
|4,096 GB performance-enhanced cluster instance||redis.amber.logic.sharding.16g.256db.0rodb.768proxy.multithread||1,536||4||256||50,000||7,680,000||500,000||2,048||61,440,000|
Notes about CPU cores
To ensure service stability, the system reserves a CPU core to process background tasks. In a cluster instance or a read/write splitting instance, the system reserves a CPU core for each data shard or each read replica to process background tasks.
Calculation rules for bandwidth values
- The bandwidth value in the preceding tables is the bandwidth of the instance. The
bandwidth value is the sum of the bandwidth of all shards or nodes in the instance.
Each shard has the following bandwidth limits:
- Community Edition: If the memory of each shard is less than or equal to 1 GB, the maximum bandwidth of each shard is 48 MB/s. If the memory of each shard is greater than 1 GB, the maximum bandwidth of each shard is 96 MB/s.
- Enhanced Edition (Tair): The maximum bandwidth of each shard is 96 MB/s.
- If the default proxy endpoint is used by a cluster instance, the upper limit of bandwidth
for the cluster instance is 2,048 MB/s. After the upper limit is reached, the bandwidth
cannot be increased even if you add more shards to the cluster instance.
Note To handle excessive network traffic, you can enable the direct connection mode. For more information, see Enable the direct connection mode. The direct connection mode is applicable only to cluster instances. In direct connection mode, the upper limit of the bandwidth is equal to the maximum bandwidth of a single shard multiplied by the number of shards. For example, if a cluster instance contains 128 shards and each shard is allocated with a memory of more than 1 GB, the bandwidth limit is 12,288 MB/s.
- The bandwidth value applies to the upstream and downstream bandwidths. For example,
if the bandwidth of an instance is 10 MB/s, the upstream and downstream bandwidths
of the instance are both 10 MB/s.
Note If your instance has unexpected or scheduled traffic peaks, you can adjust the bandwidth of the instance as needed. For more information, see Adjust the bandwidth of an ApsaraDB for Redis instance.
- The bandwidth value in the preceding table is the internal bandwidth of the ApsaraDB for Redis instance. The Internet bandwidth is determined by the internal bandwidth and is limited by the bandwidth of the connection between the ApsaraDB for Redis instance and the client. We recommend that you connect to the instance over an internal network to maximize performance.
Calculation rules for connections
|Maximum number of connections||In proxy mode, the maximum number of connections of an instance is 500,000. If the connections reach the upper limit, subsequent connections cannot be established even if you add more shards or nodes.|
|Maximum number of new connections per second||The following example shows how the maximum number of new connections per second affects
the maximum number of connections at a specific second: The maximum number of new
connections per second of an instance is 10,000. The maximum number of connections
of the instance is 50,000. The actual number of connections at the Nth second after
the instance starts to run is 12,000. Then, at the (N+1)th second, the maximum number
of connections is 22,000, which is calculated by using the following formula: 12,000
Note If the instance is connected in direct connection mode, connection performance degrades because the proxy server is bypassed. The maximum number of new connections per second for a single data shard is 2,000. For example, if an instance has four data shards, the maximum number of new connections per second is 8,000.
Q: Why is the maximum number of connections of my instance different from that described in this topic?
A: The maximum number of connections of specific instance types may be adjusted after the service is upgraded. If the maximum number of connections of your instance is different from that described in this topic, change your instance specifications to update the bandwidth. Make sure that you select the same instance type when you change the specifications. For more information, see Change the configurations of an instance.