mirror of https://github.com/postgres/postgres
This adds support for load balancing connections with libpq using a
connection parameter: load_balance_hosts=<string>. When setting the
param to random, hosts and addresses will be connected to in random
order. This then results in load balancing across these addresses and
hosts when multiple clients or frequent connection setups are used.
The randomization employed performs two levels of shuffling:
1. The given hosts are randomly shuffled, before resolving them
one-by-one.
2. Once a host its addresses get resolved, the returned addresses
are shuffled, before trying to connect to them one-by-one.
Author: Jelte Fennema <postgres@jeltef.nl>
Reviewed-by: Aleksander Alekseev <aleksander@timescale.com>
Reviewed-by: Michael Banck <mbanck@gmx.net>
Reviewed-by: Andrey Borodin <amborodin86@gmail.com>
Discussion: https://postgr.es/m/PR3PR83MB04768E2FF04818EEB2179949F7A69@PR3PR83MB0476.EURPRD83.prod.outlook.
pull/137/head
Daniel Gustafsson
2 years ago
parent
44d85ba5a3
commit
7f5b19817e
@ -0,0 +1,81 @@ |
||||
# Copyright (c) 2023, PostgreSQL Global Development Group |
||||
use strict; |
||||
use warnings; |
||||
use Config; |
||||
use PostgreSQL::Test::Utils; |
||||
use PostgreSQL::Test::Cluster; |
||||
use Test::More; |
||||
|
||||
# This tests load balancing across the list of different hosts in the host |
||||
# parameter of the connection string. |
||||
|
||||
# Cluster setup which is shared for testing both load balancing methods |
||||
my $node1 = PostgreSQL::Test::Cluster->new('node1'); |
||||
my $node2 = PostgreSQL::Test::Cluster->new('node2', own_host => 1); |
||||
my $node3 = PostgreSQL::Test::Cluster->new('node3', own_host => 1); |
||||
|
||||
# Create a data directory with initdb |
||||
$node1->init(); |
||||
$node2->init(); |
||||
$node3->init(); |
||||
|
||||
# Start the PostgreSQL server |
||||
$node1->start(); |
||||
$node2->start(); |
||||
$node3->start(); |
||||
|
||||
# Start the tests for load balancing method 1 |
||||
my $hostlist = $node1->host . ',' . $node2->host . ',' . $node3->host; |
||||
my $portlist = $node1->port . ',' . $node2->port . ',' . $node3->port; |
||||
|
||||
$node1->connect_fails( |
||||
"host=$hostlist port=$portlist load_balance_hosts=doesnotexist", |
||||
"load_balance_hosts doesn't accept unknown values", |
||||
expected_stderr => qr/invalid load_balance_hosts value: "doesnotexist"/); |
||||
|
||||
# load_balance_hosts=disable should always choose the first one. |
||||
$node1->connect_ok("host=$hostlist port=$portlist load_balance_hosts=disable", |
||||
"load_balance_hosts=disable connects to the first node", |
||||
sql => "SELECT 'connect2'", |
||||
log_like => [qr/statement: SELECT 'connect2'/]); |
||||
|
||||
# Statistically the following loop with load_balance_hosts=random will almost |
||||
# certainly connect at least once to each of the nodes. The chance of that not |
||||
# happening is so small that it's negligible: (2/3)^50 = 1.56832855e-9 |
||||
foreach my $i (1 .. 50) { |
||||
$node1->connect_ok("host=$hostlist port=$portlist load_balance_hosts=random", |
||||
"repeated connections with random load balancing", |
||||
sql => "SELECT 'connect1'"); |
||||
} |
||||
|
||||
my $node1_occurences = () = $node1->log_content() =~ /statement: SELECT 'connect1'/g; |
||||
my $node2_occurences = () = $node2->log_content() =~ /statement: SELECT 'connect1'/g; |
||||
my $node3_occurences = () = $node3->log_content() =~ /statement: SELECT 'connect1'/g; |
||||
|
||||
my $total_occurences = $node1_occurences + $node2_occurences + $node3_occurences; |
||||
|
||||
ok($node1_occurences > 1, "received at least one connection on node1"); |
||||
ok($node2_occurences > 1, "received at least one connection on node2"); |
||||
ok($node3_occurences > 1, "received at least one connection on node3"); |
||||
ok($total_occurences == 50, "received 50 connections across all nodes"); |
||||
|
||||
$node1->stop(); |
||||
$node2->stop(); |
||||
|
||||
# load_balance_hosts=disable should continue trying hosts until it finds a |
||||
# working one. |
||||
$node3->connect_ok("host=$hostlist port=$portlist load_balance_hosts=disable", |
||||
"load_balance_hosts=disable continues until it connects to the a working node", |
||||
sql => "SELECT 'connect3'", |
||||
log_like => [qr/statement: SELECT 'connect3'/]); |
||||
|
||||
# Also with load_balance_hosts=random we continue to the next nodes if previous |
||||
# ones are down. Connect a few times to make sure it's not just lucky. |
||||
foreach my $i (1 .. 5) { |
||||
$node3->connect_ok("host=$hostlist port=$portlist load_balance_hosts=random", |
||||
"load_balance_hosts=random continues until it connects to the a working node", |
||||
sql => "SELECT 'connect4'", |
||||
log_like => [qr/statement: SELECT 'connect4'/]); |
||||
} |
||||
|
||||
done_testing(); |
||||
@ -0,0 +1,124 @@ |
||||
# Copyright (c) 2023, PostgreSQL Global Development Group |
||||
use strict; |
||||
use warnings; |
||||
use Config; |
||||
use PostgreSQL::Test::Utils; |
||||
use PostgreSQL::Test::Cluster; |
||||
use Test::More; |
||||
|
||||
if ($ENV{PG_TEST_EXTRA} !~ /\bload_balance\b/) |
||||
{ |
||||
plan skip_all => |
||||
'Potentially unsafe test load_balance not enabled in PG_TEST_EXTRA'; |
||||
} |
||||
|
||||
# This tests loadbalancing based on a DNS entry that contains multiple records |
||||
# for different IPs. Since setting up a DNS server is more effort than we |
||||
# consider reasonable to run this test, this situation is instead immitated by |
||||
# using a hosts file where a single hostname maps to multiple different IP |
||||
# addresses. This test requires the adminstrator to add the following lines to |
||||
# the hosts file (if we detect that this hasn't happend we skip the test): |
||||
# |
||||
# 127.0.0.1 pg-loadbalancetest |
||||
# 127.0.0.2 pg-loadbalancetest |
||||
# 127.0.0.3 pg-loadbalancetest |
||||
# |
||||
# Windows or Linux are required to run this test because these OSes allow |
||||
# binding to 127.0.0.2 and 127.0.0.3 addresess by default, but other OSes |
||||
# don't. We need to bind to different IP addresses, so that we can use these |
||||
# different IP addresses in the hosts file. |
||||
# |
||||
# The hosts file needs to be prepared before running this test. We don't do it |
||||
# on the fly, because it requires root permissions to change the hosts file. In |
||||
# CI we set up the previously mentioned rules in the hosts file, so that this |
||||
# load balancing method is tested. |
||||
|
||||
# Cluster setup which is shared for testing both load balancing methods |
||||
my $can_bind_to_127_0_0_2 = $Config{osname} eq 'linux' || $PostgreSQL::Test::Utils::windows_os; |
||||
|
||||
# Checks for the requirements for testing load balancing method 2 |
||||
if (!$can_bind_to_127_0_0_2) { |
||||
plan skip_all => 'load_balance test only supported on Linux and Windows'; |
||||
} |
||||
|
||||
my $hosts_path; |
||||
if ($windows_os) { |
||||
$hosts_path = 'c:\Windows\System32\Drivers\etc\hosts'; |
||||
} |
||||
else |
||||
{ |
||||
$hosts_path = '/etc/hosts'; |
||||
} |
||||
|
||||
my $hosts_content = PostgreSQL::Test::Utils::slurp_file($hosts_path); |
||||
|
||||
my $hosts_count = () = $hosts_content =~ /127\.0\.0\.[1-3] pg-loadbalancetest/g; |
||||
if ($hosts_count != 3) { |
||||
# Host file is not prepared for this test |
||||
plan skip_all => "hosts file was not prepared for DNS load balance test" |
||||
} |
||||
|
||||
$PostgreSQL::Test::Cluster::use_tcp = 1; |
||||
$PostgreSQL::Test::Cluster::test_pghost = '127.0.0.1'; |
||||
my $port = PostgreSQL::Test::Cluster::get_free_port(); |
||||
my $node1 = PostgreSQL::Test::Cluster->new('node1', port => $port); |
||||
my $node2 = PostgreSQL::Test::Cluster->new('node2', port => $port, own_host => 1); |
||||
my $node3 = PostgreSQL::Test::Cluster->new('node3', port => $port, own_host => 1); |
||||
|
||||
# Create a data directory with initdb |
||||
$node1->init(); |
||||
$node2->init(); |
||||
$node3->init(); |
||||
|
||||
# Start the PostgreSQL server |
||||
$node1->start(); |
||||
$node2->start(); |
||||
$node3->start(); |
||||
|
||||
# load_balance_hosts=disable should always choose the first one. |
||||
$node1->connect_ok("host=pg-loadbalancetest port=$port load_balance_hosts=disable", |
||||
"load_balance_hosts=disable connects to the first node", |
||||
sql => "SELECT 'connect2'", |
||||
log_like => [qr/statement: SELECT 'connect2'/]); |
||||
|
||||
|
||||
# Statistically the following loop with load_balance_hosts=random will almost |
||||
# certainly connect at least once to each of the nodes. The chance of that not |
||||
# happening is so small that it's negligible: (2/3)^50 = 1.56832855e-9 |
||||
foreach my $i (1 .. 50) { |
||||
$node1->connect_ok("host=pg-loadbalancetest port=$port load_balance_hosts=random", |
||||
"repeated connections with random load balancing", |
||||
sql => "SELECT 'connect1'"); |
||||
} |
||||
|
||||
my $node1_occurences = () = $node1->log_content() =~ /statement: SELECT 'connect1'/g; |
||||
my $node2_occurences = () = $node2->log_content() =~ /statement: SELECT 'connect1'/g; |
||||
my $node3_occurences = () = $node3->log_content() =~ /statement: SELECT 'connect1'/g; |
||||
|
||||
my $total_occurences = $node1_occurences + $node2_occurences + $node3_occurences; |
||||
|
||||
ok($node1_occurences > 1, "received at least one connection on node1"); |
||||
ok($node2_occurences > 1, "received at least one connection on node2"); |
||||
ok($node3_occurences > 1, "received at least one connection on node3"); |
||||
ok($total_occurences == 50, "received 50 connections across all nodes"); |
||||
|
||||
$node1->stop(); |
||||
$node2->stop(); |
||||
|
||||
# load_balance_hosts=disable should continue trying hosts until it finds a |
||||
# working one. |
||||
$node3->connect_ok("host=pg-loadbalancetest port=$port load_balance_hosts=disable", |
||||
"load_balance_hosts=disable continues until it connects to the a working node", |
||||
sql => "SELECT 'connect3'", |
||||
log_like => [qr/statement: SELECT 'connect3'/]); |
||||
|
||||
# Also with load_balance_hosts=random we continue to the next nodes if previous |
||||
# ones are down. Connect a few times to make sure it's not just lucky. |
||||
foreach my $i (1 .. 5) { |
||||
$node3->connect_ok("host=pg-loadbalancetest port=$port load_balance_hosts=random", |
||||
"load_balance_hosts=random continues until it connects to the a working node", |
||||
sql => "SELECT 'connect4'", |
||||
log_like => [qr/statement: SELECT 'connect4'/]); |
||||
} |
||||
|
||||
done_testing(); |
||||
Loading…
Reference in new issue