[SERVER-9394] optimize secondaries to not create excessive load on the primary under certain scenarios Created: 18/Apr/13 Updated: 11/Jul/16 Resolved: 07/Mar/14 |
|
| Status: | Closed |
| Project: | Core Server |
| Component/s: | Replication |
| Affects Version/s: | 2.4.2 |
| Fix Version/s: | 2.5.4 |
| Type: | Improvement | Priority: | Major - P3 |
| Reporter: | Dwight Merriman | Assignee: | Dwight Merriman |
| Resolution: | Done | Votes: | 0 |
| Labels: | None | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Backwards Compatibility: | Fully Compatible |
| Participants: |
| Description |
|
on a low latency connection a secondary can issue several thousand getmore requests per second to a primary if it is caught up. it then creates a lot of overhead for the primary and gets back microscopic batches when this case occurs. this won't happen if the network has some significant latency (e.g. 3ms ping times), only when it's very fast, especially when testing on a single machine. |
| Comments |
| Comment by auto [ 21/May/13 ] |
|
Author: {u'username': u'milkie', u'name': u'Eric Milkie', u'email': u'milkie@10gen.com'}Message: Revert " This reverts commit f2c59cd1fabc8c5e6a5311c16943b6d4ca4325c0. |
| Comment by auto [ 21/May/13 ] |
|
Author: {u'username': u'dwight', u'name': u'Dwight', u'email': u'dwight@10gen.com'}Message: |
| Comment by auto [ 18/Apr/13 ] |
|
Author: {u'date': u'2013-04-18T18:54:14Z', u'name': u'Dwight', u'email': u'dwight@10gen.com'}Message: |