With reference to the conversation ongoing in message ID : c562dc2a-6e36-46f3-a5ea-cd42eebd7118,As a follow-up to the skip scan regression discussion, I tested a small patch that introduces static allocation/caching of `IndexAmRoutine` objects in `amapi.c`, removing the malloc/free overhead.
Test setup : - Baseline: PG17 (commit before skip scan) - After: PG18 build with skip scan (patched) - pgbench scale=1, 100 partitions - Query: `select count(*) from pgbench_accounts where bid = 0` - Clients: 1, 4, 32 - Protocols: simple, prepared
Results (tps, 10s runs) :
Mode Clients Before (PG17) After (PG18 w/ static fix)
This shows the static fix eliminates the severe ~50% regression previously observed by Tomas, leaving only a small residual slowdown (~2-15%).
Patch summary : - Cache `IndexAmRoutine` instances per AM OID instead of malloc/free per call. - Avoid `pfree(amroutine)` in hot paths. - Keeps allocations stable across lookups, reducing malloc churn.
Proposal : I suggest adopting this static allocation approach for PG18 to prevent performance cliffs. Longer term, we can explore lighter-weight caching mechanisms or further executor tuning.
