On Wed, Jan 3, 2018 at 5:05 PM, Thuc Nguyen Canh <thucnguyenc...@gmail.com> wrote: > The dynamic_shared_memory_type is posix, the before and after values for > work_mem are ~41MB and ~64MB. > I'm using a Digital Ocean vps of 16RAM 8 Cores. > For more information, I managed to reproduce this issue on a fresh vps after > I changed the random_page_cost from 4.0 to 1.1. So that said, I did reduce > the random_page_cost to 1.1, in order to optimize postgresql performance on > SSD (DO uses SSD) and got this issue.
So you have 16GB of RAM and here we're failing to posix_fallocate() 50MB (actually we can't tell if it's the ftruncate() or posix_fallocate() call that failed, but the latter seems more likely since the former just creates a big hole in the underlying tmpfs file). Can you share the query plan (EXPLAIN SELECT ...)? -- Thomas Munro http://www.enterprisedb.com
