Update documentation/sphinx/source/data-modeling.rst

Co-Authored-By: Alex Miller <35046903+alexmiller-apple@users.noreply.github.com>
This commit is contained in:
dyoungworth 2020-02-03 17:29:25 -08:00 committed by GitHub
parent 9325072e7e
commit ab9b62ac65
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions

View File

@ -275,7 +275,7 @@ Versionstamps
A common data model is to index your data with a sequencing prefix to allow log scans or tails of recent data. This index requires a unique, monotonically increasing value. This could be implemented at the client level by reading the value for conflict checks before every increment. A better solution is the versionstamp, which can be generated at commit-time with no read conflict ranges, providing a unique sequence ID in a single conflict-free write.
The version is used by FoundationDB to provide MVCC guarantees and transactional integrity. Versionstamps write the transaction's commit version as a value to an arbitrary key as part of the same transaction, allowing the client to leverage the version's unique and serial properties. Because the versionstamp is generated at commit-time, the versionstamped key cannot be read in the same transaction that it is written, and the versionstamp's value will be unknown until the transaction is committed. After the transaction is committed, the versionstamp can be obtained.
Versioning commits provides FoundationDB with MVCC guarantees and transactional integrity. Versionstamps write the transaction's commit version as a value to an arbitrary key as part of the same transaction, allowing the client to leverage the version's unique and serial properties. Because the versionstamp is generated at commit-time, the versionstamped key cannot be read in the same transaction that it is written, and the versionstamp's value will be unknown until the transaction is committed. After the transaction is committed, the versionstamp can be obtained.
The versionstamp guarantees uniqueness and monotonically increasing values for the entire lifetime of a single FDB cluster. This is even true if the cluster is restored from a backup, as a restored cluster will begin at a higher version than when the backup was taken.