Expiration

You may want Couchbase Server to automatically delete some documents after a period of time. For example, you often want documents that contain user session data to expire some time after the user’s last interaction. Or you may use documents to store cached data. You can have these documents automatically expire so your application knows to refresh the data from its source.

Couchbase Server Enterprise Edition lets you have documents expire after a period of time, called the document’s Time To Live (TTL). This feature only works in Couchbase and Ephemeral buckets. It does not work in Memcached buckets.

You can set an expiration value on an individual document either when you create it or when you mutate it. Set the expiration to the number of seconds the document should exist before Couchbase Server automatically removes it. You can change this value later in case you want extend the life of the document.

You can also configure buckets and collections to automatically apply a default expiration on the documents they contain. The maxTTL parameter on collections and buckets sets the number of seconds a new or mutated document lasts before expiring. By default, maxTTL is 0 for both buckets and collections, meaning that their documents do not automatically expire. The maxTTL setting also imposes an upper limit on the expiration time you can explicitly set on an individual document in the bucket or collection. If you try to set a document’s expiration to a period longer than the non-zero maxTTL setting, Couchbase Server sets the expiration to the maxTTL value.

Scopes do not support the maxTTL setting.

By default, when you set maxTTL on a collection or bucket, it’s applied every time you create or mutate a document. This behavior means that Couchbase Server extends the document’s life every time you mutate it. This works well for use cases such as maintaining user sessions where you want the document to exist for some time after its last change.

You can have Couchbase Server preserve the original expiration of the document when you mutate it. See Mutation’s Effect on Expiration for an explanation.

For details about setting expiration and maxTTL values, see Manage Expiration.

In general, non-zero expiration set at a lower level take precedence over settings at a higher level—​non-zero expiration times set at a document level override a collection’s non-zero maxTTL settings, which in turn override maxTTL settings at the bucket level. The three exceptions to this rule are:

The following table summarizes the interaction between a document’s expiration setting and the maxTTL settings of the collection and bucket that contain it.

When you change the maxTTL setting of a bucket or collection, the change does not have an immediate effect on the documents it contains. The maxTTL setting on a bucket or collection only has an effect when you create or mutate a document. Any existing expiration set on a document does not change, even if their duration is longer than the maxTTL setting. Also, documents that are not set to expire do not automatically start expiring after you set a non-zero maxTTL setting. To have the existing documents start expiring, you must mutate them.

The value you set a document’s expiration or a collection or bucket’s maxTTL is the number of seconds a document should exist. The actual expiration value in the document is saved as a timestamp. This timestamp is the time when you created or mutated the document plus the number of seconds it should exist. When the current time is later than the expiration timestamp, Couchbase Server deletes the document when one the following occurs:

As described in Storage, Couchbase Server maintains a tombstone for a period of time afterwards for each collection or item that it deletes. The tombstone acts as a marker to indicate the item no longer exists. To make sure that no trace of deleted items remain, Couchbase Server removes tombstones during a Metadata Purge. This purge is an automatic, non-disruptive background-process. You can change the schedule of metadata purges using Couchbase Server Web Console. See Auto-Compaction. The console lets you set the intervals between purges to be short so that Couchbase Server frequently removes tombstones.

Cross Datacenter Replication (XDCR) does not replicate the bucket or collection maxTTL setting from the source to the target. However, by default XDCR replicates the individual document’s expirations (including expirations set by the containing bucket or collection’s maxTTL setting) to the target. Buckets and collections on the target cluster can have their own maxTTL settings that can differ from those of the buckets and collections in the source. When the target collection or bucket has a non-zero maxTTL setting, the target database applies it as described earlier. Couchbase Server treats the replicated expiration time as being explicitly set on the document when applying maxTTL settings even if it resulted from a maxTTL setting in the source.

For example, suppose a document is in a bucket that has a maxTTL setting of 7200. When you mutate this document in a source database, Couchbase Server applies the maxTTL value to the document. Couchbase Server then replicates this document to the target database. Suppose the bucket in the target database has a maxTTL setting of 3600. In this case, the target database will apply its own bucket’s maxTTL setting to the document because the replicated document’s expiration is longer than allowed by the maxTTL setting.

You can use deletion filters to prevent XDCR from replicating expiration values.

When you enable auditing, Couchbase Server logs changes to each bucket’s maxTTL setting. See Auditing for more information.

Expiration is performed in a non-durable manner, even if a minimum level of durability is specified on the bucket. Using expirations in conjunction with durability settings may lead to data inconsistencies across nodes.

For more information, see the page on Durability.