[pgpool-general: 4503] Re: Determining pgpool child memory footprint

Kennedy, Robert Robert.Kennedy at cirrus.com
Tue Mar 1 03:27:23 JST 2016


Wolfgang -

Thank you, I had looked at a number of those options previously but not implemented all of them. RedHat 7.2 has at least autosized fs.file-max to something reasonable, and we implemented higher per-user limits in limits.d. I'll re-run my test cases with the TCP tweaks in place to see if it alleviates my problem.

Cheers,
Robert K.




On 2/29/16, 11:59 AM, "Wolf Schwurack" <wolf at uen.org> wrote:

>What OS is your pgpool server?  We run on Ubuntu and was always out of memory until I made configuration changes on the OS.
>
>Before change using 100% of 16G
>After changes using 4% of 16G
>
>Here's a link of the changes I make
>
>https://urldefense.proofpoint.com/v2/url?u=http-3A__www.nateware.com_linux-2Dnetwork-2Dtuning-2Dfor-2D2013.html-23.Vs4GNpMrJE4&d=CwIFAg&c=O3LcjD-V2Iepl5V0N1424A&r=QX35-QcOL1vhnovn57T7m2SQyJK0sRmaolPGVaMbsys&m=zFV0J3guNLkzgT7jAGXwLi7X-Ad77cvX8LXq8F5UEbo&s=mKXL-Gdd6E5BCoAgGbuFbh1Iyf34Eub3hTHg6XOGsO4&e= 
>
>Wolfgang Schwurack
>Database/System Administrator
>
>
>
>-----Original Message-----
>From: pgpool-general-bounces at pgpool.net [mailto:pgpool-general-bounces at pgpool.net] On Behalf Of Kennedy, Robert
>Sent: Monday, February 29, 2016 10:47 AM
>To: pgpool-general at pgpool.net
>Subject: [pgpool-general: 4501] Determining pgpool child memory footprint
>
>
>We are attempting to size the memory for a pgpool-II 3.5.0 instance and would like to know what things a child will use private resident memory for above and beyond what is necessary for TCP connection and socket handling. We are not using memcache and are not using load balancing, failover, or replication. In this environment pgpool is strictly used to manage a flood of connections for a distributed application that cannot do its own pooling. There is only one <user,database> tuple used for all the connections and nearly all of the connections consist of a single row UPDATE.
>
>In our testing we've seen widely varying amounts of resident memory usage for pgpool children and wonder what is driving it. We believe our various test cases are not so different in their behavior as to generate as much difference as we are seeing between test runs.
>
>No memory appears to be leaking, and the children are being recycled without issue when the service is idle.
>
>Cheers,
>Robert Kennedy
>
>
>_______________________________________________
>pgpool-general mailing list
>pgpool-general at pgpool.net
>https://urldefense.proofpoint.com/v2/url?u=http-3A__www.pgpool.net_mailman_listinfo_pgpool-2Dgeneral&d=CwIFAg&c=O3LcjD-V2Iepl5V0N1424A&r=QX35-QcOL1vhnovn57T7m2SQyJK0sRmaolPGVaMbsys&m=zFV0J3guNLkzgT7jAGXwLi7X-Ad77cvX8LXq8F5UEbo&s=opjz1uoS7iLg76pfiLASv3X8TjC0B0F9bu8wiTRp3pE&e= 


More information about the pgpool-general mailing list