You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Not a regression. The jump on query/predicate_pushdown/100k (≈195 ms → ≈710 ms, first seen on the 2026-10-06 run) comes from the #445 fix in v2.0.3 (6739a94).
The 100k fixture writes 200,000 uncheckpointed in-memory facts. Before #445, every pending fact past position 65,535 shared one index slot, and every row this query should return (?v > 90000, facts past position 180,000) was in that range. So the old benchmark timed an empty result:
1k and 10k sizes (under 65,535 facts) are unchanged. ~710 ms for 10k rows is in line with 10k at ~56 ms for 1k rows. v3 measures ~533 ms. The new number is the correct baseline; Bencher should settle once its history catches up.
Activity
adityamukho commentedon Oct 8, 2026
Not a regression. The jump on
query/predicate_pushdown/100k(≈195 ms → ≈710 ms, first seen on the 2026-10-06 run) comes from the #445 fix in v2.0.3 (6739a94).The 100k fixture writes 200,000 uncheckpointed in-memory facts. Before #445, every pending fact past position 65,535 shared one index slot, and every row this query should return (
?v > 90000, facts past position 180,000) was in that range. So the old benchmark timed an empty result:1k and 10k sizes (under 65,535 facts) are unchanged. ~710 ms for 10k rows is in line with 10k at ~56 ms for 1k rows. v3 measures ~533 ms. The new number is the correct baseline; Bencher should settle once its history catches up.
Closing as not a regression.