[SERVER-4014] Insert into sharded cluster without pre-splitting should be as close to performance with pre-splitting as possible Created: 04/Oct/11 Updated: 11/Jul/16 Resolved: 04/Oct/11 |
|
| Status: | Closed |
| Project: | Core Server |
| Component/s: | Sharding |
| Affects Version/s: | 2.0.0 |
| Fix Version/s: | 2.1.0 |
| Type: | Improvement | Priority: | Major - P3 |
| Reporter: | Max Schireson | Assignee: | Max Schireson |
| Resolution: | Done | Votes: | 0 |
| Labels: | mongos, performance, sharding | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Participants: |
| Description |
|
The number of chunks moved should be as small as possible while still maintaining balanced data. Overloading of any shard should be avoided. |
| Comments |
| Comment by auto [ 04/Oct/11 ] |
|
Author: {u'login': u'erh', u'name': u'Eliot', u'email': u'eliot@10gen.com'}Message: Merge pull request #95 from MSchireson/master Changed balancer_policy.cpp to move chunks more aggressively before the shards get big |