Re: [GENERAL] Total ram size study

2017-04-22 Thread John R Pierce
On 4/22/2017 8:27 AM, Melvin Davidson wrote: *Has anyone ever done a study on performance increase via ram increase? I have a client on AWS with 8GB total ram (2GB shared_buffers), and I am curious if doubling the ram to 16GB (4GB shared_buffers) will result in minimizing query response time.*

Re: [GENERAL] Total ram size study

2017-04-22 Thread Marcin Giedz
@postgresql.org Subject: Re: [GENERAL] Total ram size study Thanks Vick, Those were my thoughts as well. Your response gives me something to help convince the client to kick up the hardware. On Sat, Apr 22, 2017 at 12:20 PM, Vick Khera <vi...@khera.org> wrote: > I've not done a for

Re: [GENERAL] Total ram size study

2017-04-22 Thread Melvin Davidson
Thanks Vick, Those were my thoughts as well. Your response gives me something to help convince the client to kick up the hardware. On Sat, Apr 22, 2017 at 12:20 PM, Vick Khera wrote: > I've not done a formal study, but I've always found that throwing hardware > at the problem

Re: [GENERAL] Total ram size study

2017-04-22 Thread Vick Khera
I've not done a formal study, but I've always found that throwing hardware at the problem does wonders. My current database I made faster by bumping RAM until the entire working set fits in memory. The server has 256GB of RAM, half of which is used by ZFS for its purposes, and the other half for

[GENERAL] Total ram size study

2017-04-22 Thread Melvin Davidson
*Has anyone ever done a study on performance increase via ram increase?I have a client on AWS with 8GB total ram (2GB shared_buffers), and I amcurious if doubling the ram to 16GB (4GB shared_buffers) will result in minimizing query response time.* -- *Melvin Davidson* I reserve the right to