Perf Benchmarking and regression.

Поиск
Список
Период
Сортировка
От Mithun Cy
Тема Perf Benchmarking and regression.
Дата
Msg-id CAD__OuhPmc6XH=wYRm_+Q657yQE88DakN4=Ybh2oveFasHkoeA@mail.gmail.com
обсуждение исходный текст
Ответы Re: Perf Benchmarking and regression.  (Andres Freund <andres@anarazel.de>)
Список pgsql-hackers
Дерево обсуждения
I tried to do some benchmarking on postgres master head
commit 72a98a639574d2e25ed94652848555900c81a799
Author: Andres Freund <andres@anarazel.de>
Date:   Tue Apr 26 20:32:51 2016 -0700

CASE : Read-Write Tests when data exceeds shared buffers.

Non Default settings and test
./postgres -c shared_buffers=8GB -N 200 -c min_wal_size=15GB -c max_wal_size=20GB -c checkpoint_timeout=900 -c maintenance_work_mem=1GB -c checkpoint_completion_target=0.9 &

./pgbench -i -s 1000 postgres

./pgbench -c $threads -j $threads -T 1800 -M prepared postgres


Machine : "cthulhu" 8 node numa machine with 128 hyper threads.
>numactl --hardware
available: 8 nodes (0-7)
node 0 cpus: 0 65 66 67 68 69 70 71 96 97 98 99 100 101 102 103
node 0 size: 65498 MB
node 0 free: 37885 MB
node 1 cpus: 72 73 74 75 76 77 78 79 104 105 106 107 108 109 110 111
node 1 size: 65536 MB
node 1 free: 31215 MB
node 2 cpus: 80 81 82 83 84 85 86 87 112 113 114 115 116 117 118 119
node 2 size: 65536 MB
node 2 free: 15331 MB
node 3 cpus: 88 89 90 91 92 93 94 95 120 121 122 123 124 125 126 127
node 3 size: 65536 MB
node 3 free: 36774 MB
node 4 cpus: 1 2 3 4 5 6 7 8 33 34 35 36 37 38 39 40
node 4 size: 65536 MB
node 4 free: 62 MB
node 5 cpus: 9 10 11 12 13 14 15 16 41 42 43 44 45 46 47 48
node 5 size: 65536 MB
node 5 free: 9653 MB
node 6 cpus: 17 18 19 20 21 22 23 24 49 50 51 52 53 54 55 56
node 6 size: 65536 MB
node 6 free: 50209 MB
node 7 cpus: 25 26 27 28 29 30 31 32 57 58 59 60 61 62 63 64
node 7 size: 65536 MB
node 7 free: 43966 MB
node distances:
node   0   1   2   3   4   5   6   7
  0:  10  21  21  21  21  21  21  21
  1:  21  10  21  21  21  21  21  21
  2:  21  21  10  21  21  21  21  21
  3:  21  21  21  10  21  21  21  21
  4:  21  21  21  21  10  21  21  21
  5:  21  21  21  21  21  10  21  21
  6:  21  21  21  21  21  21  10  21
  7:  21  21  21  21  21  21  21  10


I see some regression when compared to 9.5

SessionsPostgreSQL-9.5 scale 1000PostgreSQL-9.6 scale 1000%diff
1747.367249892.14989119.3723557185
85281.2827994941.905008-6.4260484416
169000.9154198695.396233-3.3943123758
2411852.83962710843.328776-8.5170379653
3214323.04833411977.505153-16.3760054864
4016098.92658312195.447024-24.2468312336
4816959.64696512639.951087-25.4704351271
5617157.73776212543.212929-26.894715941
6417201.91492212628.002422-26.5895542487
7216956.99483511280.870599-33.4736448954
8016775.95489611348.830603-32.3506132834
8816609.13755810823.465121-34.834273705
9616510.09940411091.757753-32.8183466278
10416275.72492710665.743275-34.4683980416
11216141.81512810977.84664-31.9912503461
12015904.08661410716.17755-32.6199749153
12815738.39150310962.333439-30.3465450271


When I run git bisect on master (And this is for 128 clients).

2 commitIds which affected the performance

1. # first bad commit: [ac1d7945f866b1928c2554c0f80fd52d7f977772] Make idle backends exit if the postmaster dies.
this made performance to drop from

15947.21546 (15K +) to 13409.758510 (arround 13K+).

2. # first bad commit: [428b1d6b29ca599c5700d4bc4f4ce4c5880369bf] Allow to trigger kernel writeback after a configurable number of writes.

this made performance to drop further to 10962.333439 (10K +)

I think It did not recover afterwards.

--
Thanks and Regards
Mithun C Y

В списке pgsql-hackers по дате отправления:

Предыдущее
От: Kohei KaiGai
Дата:
Сообщение: textlike under the LIKE operator for char(n)
Следующее
От: Kevin Grittner
Дата:
Сообщение: Re: textlike under the LIKE operator for char(n)