On Thu, Mar 17, 2016 at 9:00 AM, Amit Kapila <amit.kapil...@gmail.com> wrote: >If you see, for the Base readings, there is a performance increase up till 64 clients and then there is a fall at 88 clients, which to me >indicates that it hits very high-contention around CLogControlLock at 88 clients which CLog patch is able to control to a great degree (if >required, I think the same can be verified by LWLock stats data). One reason for hitting contention at 88 clients is that this machine >seems to have 64-cores (it has 8 sockets and 8 Core(s) per socket) as per below information of lscpu command.
I am attaching LWLock stats data for above test setups(unlogged tables). *BASE* At 64 clients Block-time unit At 88 clients Block-time unit ProcArrayLock 182946 117827 ClogControlLock 107420 120266 *clog patch* ProcArrayLock 183663 121215 ClogControlLock 72806 65220 *clog patch + save snapshot* ProcArrayLock 128260 83356 ClogControlLock 78921 74011 This is for unlogged lables, I mainly see ProcArrayLock have higher contention at 64 clients and at 88 contention is slightly moved to other entities. -- Thanks and Regards Mithun C Y EnterpriseDB: http://www.enterprisedb.com
lwlock details.odt
Description: application/vnd.oasis.opendocument.text
-- Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-hackers