pgbench: could not connect to server: Resource temporarily unavailable
От | Kevin McKibbin |
---|---|
Тема | pgbench: could not connect to server: Resource temporarily unavailable |
Дата | |
Msg-id | CADc_NKg2d+oZY9mg4DdQdoUcGzN2kOYXBu-3--RW_hEe0tUV=g@mail.gmail.com обсуждение исходный текст |
Ответы |
Re: pgbench: could not connect to server: Resource temporarily unavailable
|
Список | pgsql-performance |
Hi Everyone,
I'm trying to run pgbench with various numbers of connections. However, my DB seems to be hitting some limit around 147-150 connections. I'd like to run with at least 500 and even up to 2000 if possible.
I've already increased the max_connections, shared_buffers and kernel.shmmax. All by 20 times.
What's limiting my DB from allowing more connections?
This is a sample of the output I'm getting, which repeats the error 52 times (one for each failed connection)
-bash-4.2$ pgbench -c 200 -j 200 -t 100 benchy
...
connection to database "benchy" failed:
could not connect to server: Resource temporarily unavailable
Is the server running locally and accepting
connections on Unix domain socket "/var/run/postgresql/.s.PGSQL.5432"?
transaction type: <builtin: TPC-B (sort of)>
scaling factor: 50
query mode: simple
number of clients: 200
number of threads: 200
number of transactions per client: 100
number of transactions actually processed: 14800/20000
latency average = 165.577 ms
tps = 1207.895829 (including connections establishing)
tps = 1255.496312 (excluding connections establishing)
could not connect to server: Resource temporarily unavailable
Is the server running locally and accepting
connections on Unix domain socket "/var/run/postgresql/.s.PGSQL.5432"?
transaction type: <builtin: TPC-B (sort of)>
scaling factor: 50
query mode: simple
number of clients: 200
number of threads: 200
number of transactions per client: 100
number of transactions actually processed: 14800/20000
latency average = 165.577 ms
tps = 1207.895829 (including connections establishing)
tps = 1255.496312 (excluding connections establishing)
Thanks,
Kevin
В списке pgsql-performance по дате отправления: