[SERVER-79044] Run 1TB clone with WT readahead Created: 18/Jul/23  Updated: 02/Nov/23  Resolved: 02/Nov/23

Status: Closed
Project: Core Server
Component/s: None
Affects Version/s: None
Fix Version/s: None

Type: Task Priority: Major - P3
Reporter: Matt Kneiser Assignee: Matt Kneiser
Resolution: Won't Do Votes: 0
Labels: None
Remaining Estimate: Not Specified
Time Spent: Not Specified
Original Estimate: Not Specified

Issue Links:
Depends
depends on SERVER-79043 Create testing environment for readahead Closed
Sprint: Execution NAMR Team 2023-07-24, Execution NAMR Team 2023-08-07
Participants:

 Description   

This ticket is to capture the effort required to use the testing environment developed in SERVER-79043 to run a clone command against a 1TB collection, copying half the dataset to a recipient mongod (and therefore not copying any data to the donor).

  • Collect FTDC data from both mongod's
  • Collect logs from both mongod's
  • Stretch goal: after doing all of the above, a validate command should pass on the recipient? This will take hours, and done for sanity that the new (half) collection is valid.


 Comments   
Comment by Matt Kneiser [ 02/Nov/23 ]

Proved too difficult to accomplish. Observed a recipient memory leak that OOM'd the machine. Instrumenting with ASAN and separately with the valgrind heap profiler didn't turn anything up.

Generated at Thu Feb 08 06:39:56 UTC 2024 using Jira 9.7.1#970001-sha1:2222b88b221c4928ef0de3161136cc90c8356a66.