| commit | eb3cc2962239cd86f1ac3344e897d617ef837caf | [log] [tgz] |
|---|---|---|
| author | Willy Tarreau <w@1wt.eu> | Thu Apr 15 18:13:13 2021 +0200 |
| committer | Willy Tarreau <w@1wt.eu> | Mon Apr 19 15:24:33 2021 +0200 |
| tree | 83aa79837464d30c63ffd70fb401893a528ee890 | |
| parent | 64383b81818c7f6228c45b80f126abeb90ba5712 [diff] |
MEDIUM: pools: unify pool_refill_alloc() across all models Now we don't loop anymore trying to refill multiple items at once, and an allocated object is directly returned to the requester instead of being stored into the shared pool. This has multiple benefits. The first one is that no locking is needed anymore on the allocation path and the second one is that the loop will no longer cause latency spikes.