On Sat, Dec 8, 2018 at 6:35 PM Amit Kapila <amit.kapil...@gmail.com> wrote: > > On Fri, Dec 7, 2018 at 7:25 PM John Naylor <jcnay...@gmail.com> wrote: > > > > On 12/6/18, Amit Kapila <amit.kapil...@gmail.com> wrote: > > > On Thu, Dec 6, 2018 at 10:53 PM John Naylor <jcnay...@gmail.com> wrote: > > >> > > >> I've added an additional regression test for finding the right block
I did run some performance tests on the latest patch v11, I see small regression in execution time of COPY statement. Tests I have used is same as provided in [1] just that I ran it for fill factor 20 and 70. Here are my results! Machine : cthulhu (Intel based 8 numa machine) Server setting is default, configured with HEAP_FSM_CREATION_THRESHOLD = 4, Entire data directory was on HDD. Results are execution time(unit ms) taken by copy statement when number of records equal to exact number which fit HEAP_FSM_CREATION_THRESHOLD = 4 pages. For fill factor 20 it is till tid (3, 43) and for scale factor 70 till tid (3, 157). Result is taken as a median of 10 runs. Fill factor 20 Tables Base Patch % of increase in execution time 500 121.97 125.315 2.7424776584 1000 246.592 253.789 2.9185861666 Fill factor 70 500 211.502 217.128 2.6600221275 1000 420.309 432.606 2.9257046601 So 2-3% consistent regression, And on every run I can see for patch v11 execution time is slightly more than base. I also tried to insert more records till 8 pages and same regression is observed! So I guess even HEAP_FSM_CREATION_THRESHOLD = 4 is not perfect! [1] https://www.postgresql.org/message-id/CAJVSVGX%3D2Q52fwijD9cjeq1UdiYGXns2_9WAPFf%3DE8cwbFCDvQ%40mail.gmail.com -- Thanks and Regards Mithun Chicklore Yogendra EnterpriseDB: http://www.enterprisedb.com
