Re: Issues Scaling Postgres Concurrency

2023-03-14 Thread Tom Lane
"Peter J. Holzer" writes: > On 2023-03-14 22:47:43 +0100, Laurenz Albe wrote: >> A query that counts the number of rows in a table of half a million >> rows is quite expensive and keeps a CPU core busy for a while >> (provided everything is cached). At some degree of parallelism, your >> CPU is

Re: Issues Scaling Postgres Concurrency

2023-03-14 Thread Peter J. Holzer
On 2023-03-14 22:47:43 +0100, Laurenz Albe wrote: > On Mon, 2023-03-13 at 12:24 -0400, Harrison Borges wrote: > > I’m running into severe performance problems with Postgres as I > > increase the number of concurrent requests against my backend. I’ve > > identified that the bottleneck is Postgres,

Re: Issues Scaling Postgres Concurrency

2023-03-14 Thread Laurenz Albe
On Mon, 2023-03-13 at 12:24 -0400, Harrison Borges wrote: > I’m running into severe performance problems with Postgres as I increase the > number > of concurrent requests against my backend. I’ve identified that the > bottleneck is > Postgres, and to simplify the test case, I created an endpoint

Re: Issues Scaling Postgres Concurrency

2023-03-14 Thread Alan Hodgson
On Mon, 2023-03-13 at 12:24 -0400, Harrison Borges wrote: > Hello everyone. > > I’m running into severe performance problems with Postgres as I > increase the number of concurrent requests against my backend. I’ve > identified that the bottleneck is Postgres, and to simplify the > test case, I

Re: Issues Scaling Postgres Concurrency

2023-03-14 Thread Adrian Klaver
On 3/13/23 9:24 AM, Harrison Borges wrote: Hello everyone. I’m running into severe performance problems with Postgres as I increase the number of concurrent requests against my backend. I’ve identified that the bottleneck is Postgres, and to simplify the test case, I created an endpoint that

Issues Scaling Postgres Concurrency

2023-03-14 Thread Harrison Borges
Hello everyone. I’m running into severe performance problems with Postgres as I increase the number of concurrent requests against my backend. I’ve identified that the bottleneck is Postgres, and to simplify the test case, I created an endpoint that only does a count query on a table with ~500k