I changed shared_buffers from 10G to 4G ,
swap usage has almost become nil.
# free
total used free shared buffers cached
Mem: 32871276 24575824 8295452 0 11064 22167324
-/+ buffers/cache: 2397436 30473840
Swap: 4192912 352 4192560
I also observed that there was a huge IO wait and load spike initially
which gradually reduced to normal levels. Now things seems to be
fine. but real test shall be during business hours.
vmstat output:
http://pastebin.com/ygu8gUhS
the iowait now is very respectable < 10% and CPU is idling most of
the time.
# vmstat 10
procs -----------memory---------- ---swap-- -----io---- --system--
-----cpu------
r b swpd free buff cache si so bi bo in cs us sy id wa st
2 1 352 8482444 11336 22299100 1 0 450 208 0 0
50 6 39 5 0
4 0 352 8393840 11352 22304484 0 0 480 163 9260 12717
32 4 62 3 0
5 1 352 8474788 11360 22308980 0 0 304 445 8295 12358
28 4 67 2 0
3 0 352 8370672 11376 22316676 0 0 648 158 8760 13214
38 4 55 3 0
11 0 352 8193824 11392 22323572 0 0 621 577 8800 13163
37 4 56 3 0
2 0 352 8229012 11408 22326664 0 0 169 405 9588 13696
34 4 61 1 0
6 1 352 8319176 11424 22333144 0 0 559 170 8830 12929
32 4 61 3 0
I shall also try pgtune in a while.
--
Sent via pgsql-performance mailing list (pgsql-performance@xxxxxxxxxxxxxx)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-performance
