- 14 3月, 2013 5 次提交
- 13 3月, 2013 2 次提交
- 07 3月, 2013 4 次提交
- 06 3月, 2013 1 次提交
-
-
由 antirez 提交于
-
- 05 3月, 2013 8 次提交
-
-
由 antirez 提交于
-
由 antirez 提交于
If we have a master in FAIL state that's reachable again, and apparently no one is going to serve its slots, clear the FAIL flag and let the cluster continue with its operations again.
-
由 antirez 提交于
This is the unix time at which we set the FAIL flag for the node. It is only valid if FAIL is set. The idea is to use it in order to make the cluster more robust, for instance in order to revert a FAIL state if it is long-standing but still slots are assigned to this node, that is, no one is going to fix these slots apparently.
-
由 antirez 提交于
-
由 antirez 提交于
Usually we try to send just 1 ping every second, however when we detect we are going to have unreliable failure detection because we can't ping some node in time, send an additional ping. This should only happen with very large clusters or when the the node timeout is set to a very low value.
-
由 antirez 提交于
-
由 antirez 提交于
If we are a cluster node the DB content will not match our configured slots. Don't do the check at all.
-
由 antirez 提交于
There are pathological cases where the line can be even longer a single node may contain all the slots in importing/migrating state.
-
- 04 3月, 2013 3 次提交
- 28 2月, 2013 9 次提交
-
-
由 antirez 提交于
As stated in the comment this is usually due to a resharding in progress so the client should be still redirected to the old node that will handle the redirection elsewhere.
-
由 antirez 提交于
The new code makes sure that the node slots bitmap is always consistent with the cluster->slots array.
-
由 antirez 提交于
-
由 antirez 提交于
-
由 antirez 提交于
Before a relatively slow popcount() operation was needed every time we needed to get the number of slots served by a given cluster node. Now we just need to check an integer that is taken in sync with the bitmap.
-
由 antirez 提交于
-
由 antirez 提交于
-
由 antirez 提交于
-
由 antirez 提交于
-
- 27 2月, 2013 2 次提交
- 26 2月, 2013 6 次提交
-
-
由 antirez 提交于
-
由 antirez 提交于
-
由 antirez 提交于
The new system detects a failure only when there is quorum from masters.
-
由 antirez 提交于
-
由 antirez 提交于
This is not very important as anyway when the function counting the number of reports is called the cleanup is performed. However with this change if only part of the nodes that reported the failure will report the node is back ok, we'll cleanup the older entries ASAP. In complex split net split scenarios, and when we are dealing with clusters having nodes in the order of ~ 1000, this can save some CPU.
-
由 antirez 提交于
This is the missing part of the API that will be used to reimplement failure detection of Cluster nodes.
-