mirror of https://github.com/postgres/postgres
Instead of building a separate memory context that's used just for running hash functions, make the hash functions run in the per-tuple context of the node's innerecontext. This saves a little space at runtime, and it avoids needing to reset two contexts instead of one inside buildSubPlanHash's main loop. This largely reverts commitmaster133924e13
. That's safe to do now becausebf6c614a2
decoupled the evaluation context used by TupleHashTableMatch from that used for hash function evaluation, so that there's no longer a risk of resetting the innerecontext too soon. Per discussion of bug #19040, although this is not directly a fix for that. Author: Tom Lane <tgl@sss.pgh.pa.us> Reviewed-by: Haiyang Li <mohen.lhy@alibaba-inc.com> Reviewed-by: Fei Changhong <feichanghong@qq.com> Discussion: https://postgr.es/m/19040-c9b6073ef814f48c@postgresql.org
parent
abdeacdb09
commit
bdc6cfcd12
Loading…
Reference in new issue