NOTICE: help.openstreetmap.org is no longer in use from 1st March 2024. Please use the OpenStreetMap Community Forum

Hello,

I'm not sure if this is a simple question with a straightforward answer, but I'll ask anyway.

I know for spinning HDDs splitting the tablespaces across multiple drives has been shown to increase performance when loading the planet file into postgres using osm2pgsql, but what about SSDs?

All things being equal, which of the following options is faster (or more efficient) when farming out the 4 osm2pgsql tablespaces (i.e. main_data, main_index, slim_data, and slim_index):

  1. a single large (1TB) SSD with 1 partition.
  2. a single large (1TB) SSD with 4 partitions (one for each tablespace).
  3. 2 medium sized (512GB) SSDs (one for data and one for indices).
  4. 4 smaller (<=512GB) SSDs (one for each tablespace).
  5. Maybe some other configuration?

I have a 1TB SSD I can test option 1 and 2 with, but if options 3 and/or 4 are not any faster, I'd rather not spend the money to find out.

Has anyone benchmarked this?

Thanks,

asked 08 May '16, 03:01

placebo10's gravatar image

placebo10
71336
accept rate: 0%

Follow this question

By Email:

Once you sign in you will be able to subscribe for any updates here

By RSS:

Answers

Answers and Comments

Markdown Basics

  • *italic* or _italic_
  • **bold** or __bold__
  • link:[text](http://url.com/ "title")
  • image?![alt text](/path/img.jpg "title")
  • numbered list: 1. Foo 2. Bar
  • to add a line break simply add two spaces to where you would like the new line to be.
  • basic HTML tags are also supported

Question tags:

×263
×196
×9
×2

question asked: 08 May '16, 03:01

question was seen: 1,729 times

last updated: 08 May '16, 03:01

NOTICE: help.openstreetmap.org is no longer in use from 1st March 2024. Please use the OpenStreetMap Community Forum