Re: INSERT - UPDATE throughput oscillating and SSD activity after stopping the client - Mailing list pgsql-general

From Jeff Janes
Subject Re: INSERT - UPDATE throughput oscillating and SSD activity after stopping the client
Date
Msg-id CAMkU=1yHt5X7hnNdeBFswQRq-Swm=BSs-YS_maCpONdCEtf_RA@mail.gmail.com
Whole thread Raw
In response to Re: INSERT - UPDATE throughput oscillating and SSD activity after stopping the client  (Tom DalPozzo <t.dalpozzo@gmail.com>)
Responses Re: INSERT - UPDATE throughput oscillating and SSD activity after stopping the client
List pgsql-general
On Tue, Dec 6, 2016 at 2:44 AM, Tom DalPozzo <t.dalpozzo@gmail.com> wrote:
Hi,
about SSD light: 
 
I guessed it was WAL -> actual db files data traffic. It explains why the light stops blinking after shutting down the server (I did it via kill command) .

Do you kill with -15 (the default) or -9?  And which process, the postgres master itself or just some random child?
 
But if so, I expected the light to restart blinking after     restarting the server (in order to continue WAL->db activity).

The normal checkpoint is paced.  So trickling out data slowly will keep the light on, but not actually stress the system.

When you shutdown the system, it does a fast checkpoint.  This gets the data written out as quickly as possible (since you are shutting down, it doesn't worry about interfering with performance for other users, as there are none), so once it is done you don't see the light anymore.  If you do a clean shutdown (kill -15 of the postgres master) this fast checkpoint happens upon shutdown.  If you do an abort (kill -9) then the fast checkpoint happens upon start-up, once recovery is finished but before the database is opened of regular use.

 Cheers,

Jeff

pgsql-general by date:

Previous
From: Joseph Brenner
Date:
Subject: Re: Select works only when connected from login postgres
Next
From: Lee Hachadoorian
Date:
Subject: Re: Extensions and privileges in public schema