Develop applications with Active-Active databases

Overview of how developing applications differs for Active-Active databases from standalone Redis databases.

Developing geo-distributed, multi-master applications can be difficult. Application developers may have to understand a large number of race conditions between updates to various sites, network, and cluster failures that could reorder the events and change the outcome of the updates performed across geo-distributed writes.

Active-Active databases (formerly known as CRDB) are geo-distributed databases that span multiple Redis Enterprise Software (RS) clusters. Active-Active databases depend on multi-master replication (MMR) and Conflict-free Replicated Data Types (CRDTs) to power a simple development experience for geo-distributed applications. Active-Active databases allow developers to use existing Redis data types and commands, but understand the developers intent and automatically handle conflicting concurrent writes to the same key across multiple geographies. For example, developers can simply use the INCR or INCRBY method in Redis in all instances of the geo-distributed application, and Active-Active databases handle the additive nature of INCR to reflect the correct final value. The following example displays a sequence of events over time : t1 to t9. This Active-Active database has two member Active-Active databases : member CRDB1 and member CRDB2. The local operations executing in each member Active-Active database is listed under the member Active-Active database name. The "Sync" even represent the moment where synchronization catches up to distribute all local member Active-Active database updates to other participating clusters and other member Active-Active databases.

Databases provide various approaches to address some of these concerns:

• Active-Passive Geo-distributed deployments: With active-passive distributions, all writes go to an active cluster. Redis Enterprise provides a "Replica Of" capability that provides a similar approach. This can be employed when the workload is heavily balanced towards read and few writes. However, WAN performance and availability is quite flaky and traveling large distances for writes take away from application performance and availability.
• Two-phase Commit (2PC): This approach is designed around a protocol that commits a transaction across multiple transaction managers. Two-phase commit provides a consistent transactional write across regions but fails transactions unless all participating transaction managers are "available" at the time of the transaction. The number of messages exchanged and its cross-regional availability requirement make two-phase commit unsuitable for even moderate throughputs and cross-geo writes that go over WANs.
• Sync update with Quorum-based writes: This approach synchronously coordinates a write across majority number of replicas across clusters spanning multiple regions. However, just like two-phase commit, number of messages exchanged and its cross-regional availability requirement make geo-distributed quorum writes unsuitable for moderate throughputs and cross geo writes that go over WANs.
• Last-Writer-Wins (LWW) Conflict Resolution: Some systems provide simplistic conflict resolution for all types of writes where the system clocks are used to determine the winner across conflicting writes. LWW is lightweight and can be suitable for simpler data. However, LWW can be destructive to updates that are not necessarily conflicting. For example adding a new element to a set across two geographies concurrently would result in only one of these new elements appearing in the final result with LWW.
• MVCC (multi-version concurrency control): MVCC systems maintain multiple versions of data and may expose ways for applications to resolve conflicts. Even though MVCC system can provide a flexible way to resolve conflicting writes, it comes at a cost of great complexity in the development of a solution.

Even though types and commands in Active-Active databases look identical to standard Redis types and commands, the underlying types in RS are enhanced to maintain more metadata to create the conflict-free data type experience. This section explains what you need to know about developing with Active-Active databases on Redis Enterprise Software.

Lua scripts

Active-Active databases support Lua scripts, but unlike standard Redis, Lua scripts always execute in effects replication mode. There is currently no way to execute them in script-replication mode.

Eviction

The default policy for Active-Active databases is noeviction mode. Redis Enterprise version 6.0.20 and later support all eviction policies for Active-Active databases, unless Redis Flex or Auto Tiering(previously known as Redis on Flash) is enabled. For details, see eviction for Active-Active databases (Redis Enterprise) or eviction for Active-Active databases (Redis Cloud).

Expiration

Expiration is supported with special multi-master semantics.

If a key's expiration time is changed at the same time on different members of the Active-Active database, the longer extended time set via TTL on a key is preserved. As an example:

If this command was performed on key1 on cluster #1

127.0.0.1:6379> EXPIRE key1 10

And if this command was performed on key1 on cluster #2

127.0.0.1:6379> EXPIRE key1 50

The EXPIRE command setting the key to 50 would win.

And if this command was performed on key1 on cluster #3:

127.0.0.1:6379> PERSIST key1

It would win out of the three clusters hosting the Active-Active database as it sets the TTL on key1 to an infinite time.

The replica responsible for the "winning" expire value is also responsible to expire the key and propagate a DEL effect when this happens. A "losing" replica is from this point on not responsible for expiring the key, unless another EXPIRE command resets the TTL. Furthermore, a replica that is NOT the "owner" of the expired value:

• Silently ignores the key if a user attempts to access it in READ mode, e.g. treating it as if it was expired but not propagating a DEL.

• Expires it (sending a DEL) before making any modifications if a user attempts to access it in WRITE mode.

  Note:

  Expiration values are in the range of [0, 2^49] for Active-Active databases and [0, 2^64] for non Active-Active databases.

Out-of-Memory (OOM)

If a member Active-Active database is in an out of memory situation, that member is marked "inconsistent" by RS, the member stops responding to user traffic, and the syncer initiates full reconciliation with other peers in the Active-Active database.

Active-Active Database Key Counts

Keys are counted differently for Active-Active databases:

• DBSIZE (in shard-cli dbsize) reports key header instances that represent multiple potential values of a key before a replication conflict is resolved.
• expired_keys (in bdb-cli info) can be more than the keys count in DBSIZE (in shard-cli dbsize) because expires are not always removed when a key becomes a tombstone. A tombstone is a key that is logically deleted but still takes memory until it is collected by the garbage collector.
• The Expires average TTL (in bdb-cli info) is computed for local expires only.

INFO

The INFO command has an additional crdt section which provides advanced troubleshooting information (applicable to support etc.):