wbtiger
/
foundationdb
mirror of https://github.com/apple/foundationdb.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix an error in configuration.rst

This commit is contained in:
lingbin 2019-08-14 15:14:05 +08:00
parent 4b404503fd
commit 745e569723
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
documentation/sphinx/source/configuration.rst
View File

@ -536,7 +536,7 @@ While everything is healthy, writes need to be made durable in both west coast d
If either west coast datacenter fails, the last few mutations will be propagated from the remaining west coast datacenter to the east coast. At this point, FoundationDB will start accepting commits on the east coast. Once the west coast comes back online, the system will automatically start copying all the data that was committed to the east coast back to the west coast replica. Once the west coast has caught up, the system will automatically switch back to accepting writes from the west coast again. If either west coast datacenter fails, the last few mutations will be propagated from the remaining west coast datacenter to the east coast. At this point, FoundationDB will start accepting commits on the east coast. Once the west coast comes back online, the system will automatically start copying all the data that was committed to the east coast back to the west coast replica. Once the west coast has caught up, the system will automatically switch back to accepting writes from the west coast again.
The west coast mutation logs will maintain their copies of all committed mutations until they have been applied by the east coast datacenter. In the event that the east coast has failed for long enough that the west coast mutation logs no longer have enough disk space to continue storing the mutations, FoundationDB can be requested to drop the east coast replica completely. This decision is not automatic, and requires a manual change to the configuration. The west coast database will then act as a single datacenter database until the east coast comes back online. Because the east coast datacenter was completely dropped from the configuration, to bring the west coast back online FoundationDB will have to copy all the data between the regions. The west coast mutation logs will maintain their copies of all committed mutations until they have been applied by the east coast datacenter. In the event that the east coast has failed for long enough that the west coast mutation logs no longer have enough disk space to continue storing the mutations, FoundationDB can be requested to drop the east coast replica completely. This decision is not automatic, and requires a manual change to the configuration. The west coast database will then act as a single datacenter database until the east coast comes back online. Because the east coast datacenter was completely dropped from the configuration, FoundationDB will have to copy all the data between the regions in order to bring it back online.
If a region failover occurs, clients will generally only see a latency spike of a few seconds. If a region failover occurs, clients will generally only see a latency spike of a few seconds.