Not sure what is going on but other than upgrading to 9.3.4 from 9.2.4, i'm seeing major slowness in basic queries and seeing a ton of the bind and parse in my logs. These are standard lookups and should take micro seconds. I'm logging all queries that take over a second and this seems to be getting worse, seems like it's snowballing.
2014-11-04 08:54:52 PST clsdb cls 216.0.0.50(33569) 14857 2014-11-04 08:54:52.476 PSTLOG: duration: 2206.070 ms parse dbdpg_p12768_2: SELECT contact_seq_id, status FROM cls.contacts
WHERE
cust_seq_id = $1
AND contact_id = $2
2014-11-04 08:54:52 PST clsdb cls 216.20.0.50(48450) 14882 2014-11-04 08:54:52.394 PSTLOG: duration: 1624.847 ms bind dbdpg_p21610_2: SELECT contact_seq_id, status FROM cls.contacts
WHERE
cust_seq_id = $1
AND contact_id = $2
CentOS 6.x
Postgres: 9.3.4
256GB Mem
32Core
I'm tearing up my system to see what is happening, the postgres is the only change, the processes or the data is not. I tried tuning postgresql.conf and modifed effective cache etc, but I've reverted it all, so again just looking for some assistance.
Again no I/O have plenty of memory etc. The server is running hotter than it used to as well.
Thanks
Tory
