[SERVER-23731] Perform _storeCurrentLocs in parallel with the recipient shard's preparation stage Created: 14/Apr/16 Updated: 06/Dec/22 Resolved: 09/Mar/18 |
|
| Status: | Closed |
| Project: | Core Server |
| Component/s: | Sharding |
| Affects Version/s: | 3.3.4 |
| Fix Version/s: | None |
| Type: | Improvement | Priority: | Major - P3 |
| Reporter: | Kaloian Manassiev | Assignee: | [DO NOT USE] Backlog - Sharding Team |
| Resolution: | Won't Fix | Votes: | 0 |
| Labels: | None | ||
| Remaining Estimate: | Not Specified | ||
| Time Spent: | Not Specified | ||
| Original Estimate: | Not Specified | ||
| Issue Links: |
|
||||
| Assigned Teams: |
Sharding
|
||||
| Participants: | |||||
| Description |
|
Currently, the chunk cloning sequence is to first run _storeCurrentLocs to gather the recordIds of all documents in the chunk to be moved, so they can be sorted in the order on disk and then telling the recipient shard to start the initial clone. The recipient shard's preparation for initial clone consists of several steps, including cleaning up the range for the chunk. We should overlap these two stages. This only applies to 3.4 and later. |
| Comments |
| Comment by Gregory McKeon (Inactive) [ 08/Feb/18 ] |
|
This will be made irrelevant by the work in |