Redis 3.0 Instance Specifications (Obsolete)

This section describes DCS Redis 3.0 instance specifications, including the total memory, available memory, maximum number of connections allowed, maximum/assured bandwidth, and reference performance.

The following metrics are related to the instance specifications:

Used memory: You can check the memory usage of an instance by viewing the Memory Usage and Used Memory metrics.
Maximum connections: The maximum number of connections allowed is the maximum number of clients that can be connected to an instance. To check the number of connections to an instance, view the Connected Clients metric.
QPS represents queries per second, which is the number of commands processed per second.

Single-node, master/standby, and Proxy Cluster types are available.
DCS Redis 3.0 instances have been taken offline at new sites, but can still be used at existing sites. DCS Redis 4.0 or 5.0 instances are recommended.

Both x86 and Arm architectures are supported.

Single-Node Instances

For each single-node DCS Redis instance, the available memory is less than the total memory because some memory is reserved for system overheads, as shown in the following table.

**Table 1** Specifications of single-node DCS Redis 3.0 instances
CPU	Total Memory (GB)	Available Memory (GB)	Max. Connections (Default/Limit) (Count)	Assured/Maximum Bandwidth (Mbit/s)	Reference Performance (QPS)	Specification Code (spec_code in the API)
Arm	2	1.2	5000/5000	42/512	50,000	dcs.arm.single_node
	4	2.4	5000/5000	64/1536	50,000
	8	4.8	5000/5000	64/1536	50,000
	16	9.6	5000/5000	85/3072	50,000
	32	19.2	5000/5000	85/3072	50,000
	64	38.4	5000/6000	128/5120	50,000
x86	2	1.5	5000/50,000	42/512	50,000	dcs.single_node
	4	3.2	5000/50,000	64/1536	50,000
	8	6.8	5000/50,000	64/1536	50,000
	16	13.6	5000/50,000	85/3072	50,000
	32	27.2	5000/50,000	85/3072	50,000
	64	58.2	5000/60,000	128/5120	50,000

Master/Standby Instances

For each master/standby DCS Redis instance, the available memory is less than that of a single-node DCS Redis instance because some memory is reserved for data persistence, as shown in the following table. The available memory of a master/standby instance can be adjusted to support background tasks such as data persistence and master/standby synchronization.

**Table 2** Specifications of master/standby DCS Redis 3.0 instances
CPU	Total Memory (GB)	Available Memory (GB)	Maximum Connections Allowed (Count)	Assured/Maximum Bandwidth (Mbit/s)	Reference Performance (QPS)	Specification Code (spec_code in the API)
Arm	2	1.2	5000/5000	42/512	50,000	dcs.arm.master_standby
	4	2.4	5000/5000	64/1536	50,000
	8	4.8	5000/5000	64/1536	50,000
	16	9.6	5000/5000	85/3072	50,000
	32	19.2	5000/5000	85/3072	50,000
	64	38.4	5000/6000	128/5120	50,000
x86	2	1.5	5000/50,000	42/512	50,000	dcs.master_standby
	4	3.2	5000/50,000	64/1536	50,000
	8	6.4	5000/50,000	64/1536	50,000
	16	12.8	5000/50,000	85/3072	50,000
	32	25.6	5000/50,000	85/3072	50,000
	64	51.2	5000/60,000	128/5120	50,000

Proxy Cluster Instances

In addition to larger memory, cluster instances feature more connections allowed, higher bandwidth allowed, and more QPS than single-node and master/standby instances.

**Table 3** Specifications of Proxy Cluster DCS Redis 3.0 instances
CPU	Specification (GB)	Available Memory (GB)	Maximum Connections Allowed (Count)	Assured/Maximum Bandwidth (Mbit/s)	Reference Performance (QPS)	Specification Code (spec_code in the API)
Arm	64	64	30,000/30,000	600/5120	100,000	dcs.arm.cluster
	128	128	60,000/60,000	600/5120	100,000
	256	256	60,000/60,000	600/5120	100,000
x86	64	64	90,000/90,000	600/5120	100,000	dcs.cluster
	128	128	180,000/180,000	600/5120	100,000
	256	256	240,000/240,000	600/5120	100,000