Compare commits

..

8 Commits

Author SHA1 Message Date
Mostafa
efe8fb3203 link gif 2024-09-03 11:13:58 -05:00
Mostafa
f3fcf2a76e Make running integration tests easier 2024-09-03 11:05:56 -05:00
Mostafa
cacfadcf87 Merge branch 'main' of github.com:postgresml/pgcat into mostafa_development-guide 2024-09-03 08:42:59 -05:00
Mostafa
7a8823df50 rebase on main 2024-09-03 08:37:00 -05:00
Mostafa Abdelraouf
ca34597002 Fix broken integration test #740 (#787) 2024-08-31 17:15:13 -05:00
Mostafa Abdelraouf
2def40ea6a Add test case for issue 776 (#786)
I am adding a tiny test that uses the SQL statement that was reported to break an older version of SQL parser library

#776
2024-08-31 10:52:33 -05:00
Mostafa Abdelraouf
c05129018d Improve Prometheus stats + Add Grafana dashboard (#785)
We were missing some labels on metrics generated by the Prometheus exporter so I fixed that. There are still some gaps that I want to address with respect to the metrics we track but this seems like a good start.

I also created a Grafana Dashboard and exported it to JSON. It is designed with the same metric names the Prometheus exporter uses.
2024-08-31 08:18:57 -05:00
Mostafa
ff2ff51125 wip 2024-08-30 03:59:23 -05:00
11 changed files with 2747 additions and 290 deletions

View File

@@ -59,6 +59,7 @@ admin_password = "admin_pass"
# session: one server connection per connected client
# transaction: one server connection per client transaction
pool_mode = "transaction"
prepared_statements_cache_size = 500
# If the client doesn't specify, route traffic to
# this role by default.
@@ -141,6 +142,7 @@ query_parser_enabled = true
query_parser_read_write_splitting = true
primary_reads_enabled = true
sharding_function = "pg_bigint_hash"
prepared_statements_cache_size = 500
[pools.simple_db.users.0]
username = "simple_user"

View File

@@ -6,6 +6,32 @@ Thank you for contributing! Just a few tips here:
2. Run the test suite (e.g. `pgbench`) to make sure everything still works. The tests are in `.circleci/run_tests.sh`.
3. Performance is important, make sure there are no regressions in your branch vs. `main`.
## How to run the integration tests locally and iterate on them
We have integration tests written in Ruby, Python, Go and Rust.
Below are the steps to run them in a developer-friendly way that allows iterating and quick turnaround.
Hear me out, this should be easy, it will involve opening a shell into a container with all the necessary dependancies available for you and you can modify the test code and immediately rerun your test in the interactive shell.
Quite simply, make sure you have docker installed and then run
`./start_test_env.sh`
That is it!
Within this test environment you can modify the file in your favorite IDE and rerun the tests without having to bootstrap the entire environment again.
Once the environment is ready, you can run the tests by running
Ruby: `cd /app/tests/ruby && bundle exec ruby <test_name>.rb --format documentation`
Python: `cd /app && python3 tests/python/tests.py`
Rust: `cd /app/tests/rust && cargo run`
Go: `cd /app/tests/go && /usr/local/go/bin/go test`
You can also rebuild PgCat directly within the environment and the tests will run against the newly built binary
To rebuild PgCat, just run `cargo build` within the container under `/app`
![Animated gif showing how to run tests](https://github.com/user-attachments/assets/2258fde3-2aed-4efb-bdc5-e4f12dcd4d33)
Happy hacking!
## TODOs

View File

@@ -268,6 +268,8 @@ psql -h 127.0.0.1 -p 6432 -d pgbouncer -c 'SHOW DATABASES'
Additionally, Prometheus statistics are available at `/metrics` via HTTP.
We also have a [basic Grafana dashboard](https://github.com/postgresml/pgcat/blob/main/grafana_dashboard.json) based on Prometheus metrics that you can import into Grafana and build on it or use it for monitoring.
### Live configuration reloading
The config can be reloaded by sending a `kill -s SIGHUP` to the process or by querying `RELOAD` to the admin database. All settings except the `host` and `port` can be reloaded without restarting the pooler, including sharding and replicas configurations.

2124
grafana_dashboard.json Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -12,19 +12,30 @@ use std::collections::HashMap;
use std::fmt;
use std::net::SocketAddr;
use std::sync::atomic::Ordering;
use std::sync::Arc;
use tokio::net::TcpListener;
use crate::config::Address;
use crate::pool::{get_all_pools, PoolIdentifier};
use crate::stats::get_server_stats;
use crate::stats::pool::PoolStats;
use crate::stats::{get_server_stats, ServerStats};
struct MetricHelpType {
help: &'static str,
ty: &'static str,
}
struct ServerPrometheusStats {
bytes_received: u64,
bytes_sent: u64,
transaction_count: u64,
query_count: u64,
error_count: u64,
active_count: u64,
idle_count: u64,
login_count: u64,
tested_count: u64,
}
// reference for metric types: https://prometheus.io/docs/concepts/metric_types/
// counters only increase
// gauges can arbitrarily increase or decrease
@@ -127,22 +138,46 @@ static METRIC_HELP_AND_TYPES_LOOKUP: phf::Map<&'static str, MetricHelpType> = ph
},
"servers_bytes_received" => MetricHelpType {
help: "Volume in bytes of network traffic received by server",
ty: "gauge",
ty: "counter",
},
"servers_bytes_sent" => MetricHelpType {
help: "Volume in bytes of network traffic sent by server",
ty: "gauge",
ty: "counter",
},
"servers_transaction_count" => MetricHelpType {
help: "Number of transactions executed by server",
ty: "gauge",
ty: "counter",
},
"servers_query_count" => MetricHelpType {
help: "Number of queries executed by server",
ty: "gauge",
ty: "counter",
},
"servers_error_count" => MetricHelpType {
help: "Number of errors",
ty: "counter",
},
"servers_idle_count" => MetricHelpType {
help: "Number of server connection in idle state",
ty: "gauge",
},
"servers_active_count" => MetricHelpType {
help: "Number of server connection in active state",
ty: "gauge",
},
"servers_tested_count" => MetricHelpType {
help: "Number of server connection in tested state",
ty: "gauge",
},
"servers_login_count" => MetricHelpType {
help: "Number of server connection in login state",
ty: "gauge",
},
"servers_is_banned" => MetricHelpType {
help: "0 if server is not banned, 1 if server is banned",
ty: "gauge",
},
"servers_is_paused" => MetricHelpType {
help: "0 if server is not paused, 1 if server is paused",
ty: "gauge",
},
"databases_pool_size" => MetricHelpType {
@@ -210,7 +245,9 @@ impl<Value: fmt::Display> PrometheusMetric<Value> {
labels.insert("shard", address.shard.to_string());
labels.insert("role", address.role.to_string());
labels.insert("pool", address.pool_name.clone());
labels.insert("index", address.address_index.to_string());
labels.insert("database", address.database.to_string());
labels.insert("user", address.username.clone());
Self::from_name(&format!("databases_{}", name), value, labels)
}
@@ -225,8 +262,9 @@ impl<Value: fmt::Display> PrometheusMetric<Value> {
labels.insert("shard", address.shard.to_string());
labels.insert("role", address.role.to_string());
labels.insert("pool", address.pool_name.clone());
labels.insert("index", address.address_index.to_string());
labels.insert("database", address.database.to_string());
labels.insert("user", address.username.clone());
Self::from_name(&format!("servers_{}", name), value, labels)
}
@@ -236,7 +274,9 @@ impl<Value: fmt::Display> PrometheusMetric<Value> {
labels.insert("shard", address.shard.to_string());
labels.insert("pool", address.pool_name.clone());
labels.insert("role", address.role.to_string());
labels.insert("index", address.address_index.to_string());
labels.insert("database", address.database.to_string());
labels.insert("user", address.username.clone());
Self::from_name(&format!("stats_{}", name), value, labels)
}
@@ -338,34 +378,51 @@ fn push_database_stats(lines: &mut Vec<String>) {
// Adds relevant metrics shown in a SHOW SERVERS admin command.
fn push_server_stats(lines: &mut Vec<String>) {
let server_stats = get_server_stats();
let mut server_stats_by_addresses = HashMap::<String, Arc<ServerStats>>::new();
let mut prom_stats = HashMap::<String, ServerPrometheusStats>::new();
for (_, stats) in server_stats {
server_stats_by_addresses.insert(stats.address_name(), stats);
let entry = prom_stats
.entry(stats.address_name())
.or_insert(ServerPrometheusStats {
bytes_received: 0,
bytes_sent: 0,
transaction_count: 0,
query_count: 0,
error_count: 0,
active_count: 0,
idle_count: 0,
login_count: 0,
tested_count: 0,
});
entry.bytes_received += stats.bytes_received.load(Ordering::Relaxed);
entry.bytes_sent += stats.bytes_sent.load(Ordering::Relaxed);
entry.transaction_count += stats.transaction_count.load(Ordering::Relaxed);
entry.query_count += stats.query_count.load(Ordering::Relaxed);
entry.error_count += stats.error_count.load(Ordering::Relaxed);
match stats.state.load(Ordering::Relaxed) {
crate::stats::ServerState::Login => entry.login_count += 1,
crate::stats::ServerState::Active => entry.active_count += 1,
crate::stats::ServerState::Tested => entry.tested_count += 1,
crate::stats::ServerState::Idle => entry.idle_count += 1,
}
}
for (_, pool) in get_all_pools() {
for shard in 0..pool.shards() {
for server in 0..pool.servers(shard) {
let address = pool.address(shard, server);
if let Some(server_info) = server_stats_by_addresses.get(&address.name()) {
if let Some(server_info) = prom_stats.get(&address.name()) {
let metrics = [
(
"bytes_received",
server_info.bytes_received.load(Ordering::Relaxed),
),
("bytes_sent", server_info.bytes_sent.load(Ordering::Relaxed)),
(
"transaction_count",
server_info.transaction_count.load(Ordering::Relaxed),
),
(
"query_count",
server_info.query_count.load(Ordering::Relaxed),
),
(
"error_count",
server_info.error_count.load(Ordering::Relaxed),
),
("bytes_received", server_info.bytes_received),
("bytes_sent", server_info.bytes_sent),
("transaction_count", server_info.transaction_count),
("query_count", server_info.query_count),
("error_count", server_info.error_count),
("idle_count", server_info.idle_count),
("active_count", server_info.active_count),
("login_count", server_info.login_count),
("tested_count", server_info.tested_count),
("is_banned", if pool.is_banned(address) { 1 } else { 0 }),
("is_paused", if pool.paused() { 1 } else { 0 }),
];
for (key, value) in metrics {
if let Some(prometheus_metric) =

View File

@@ -1399,6 +1399,19 @@ mod test {
assert!(!qr.query_parser_enabled());
}
#[test]
fn test_query_parser() {
QueryRouter::setup();
let mut qr = QueryRouter::new();
qr.pool_settings.query_parser_read_write_splitting = true;
let query = simple_query("SELECT req_tab_0.* FROM validation req_tab_0 WHERE array['http://www.w3.org/ns/shacl#ValidationResult'] && req_tab_0.type::text[] AND ( ( (req_tab_0.focusnode = 'DataSource_Credilogic_DataSourceAddress_144959227') ) )");
assert!(qr.infer(&qr.parse(&query).unwrap()).is_ok());
let query = simple_query("WITH EmployeeSalaries AS (SELECT Department, Salary FROM Employees) SELECT Department, AVG(Salary) AS AverageSalary FROM EmployeeSalaries GROUP BY Department;");
assert!(qr.infer(&qr.parse(&query).unwrap()).is_ok());
}
#[test]
fn test_update_from_pool_settings() {
QueryRouter::setup();

34
start_test_env.sh Executable file
View File

@@ -0,0 +1,34 @@
GREEN="\033[0;32m"
RED="\033[0;31m"
BLUE="\033[0;34m"
RESET="\033[0m"
cd tests/docker/
docker compose kill main || true
docker compose build main
docker compose down
docker compose up -d
# wait for the container to start
while ! docker compose exec main ls; do
echo "Waiting for test environment to start"
sleep 1
done
echo "==================================="
docker compose exec -e LOG_LEVEL=error -d main toxiproxy-server
docker compose exec --workdir /app main cargo build
docker compose exec -d --workdir /app main ./target/debug/pgcat ./.circleci/pgcat.toml
docker compose exec --workdir /app/tests/ruby main bundle install
docker compose exec --workdir /app/tests/python main pip3 install -r requirements.txt
echo "Interactive test environment ready"
echo "To run integration tests, you can use the following commands:"
echo -e " ${BLUE}Ruby: ${RED}cd /app/tests/ruby && bundle exec ruby tests.rb --format documentation${RESET}"
echo -e " ${BLUE}Python: ${RED}cd /app && python3 tests/python/tests.py${RESET}"
echo -e " ${BLUE}Rust: ${RED}cd /app/tests/rust && cargo run ${RESET}"
echo -e " ${BLUE}Go: ${RED}cd /app/tests/go && /usr/local/go/bin/go test${RESET}"
echo "the source code for tests are directly linked to the source code in the container so you can modify the code and run the tests again"
echo "You can rebuild PgCat from within the container by running"
echo -e " ${GREEN}cargo build${RESET}"
echo "and then run the tests again"
echo "==================================="
docker compose exec --workdir /app/tests main bash

View File

@@ -1,4 +1,3 @@
version: "3"
services:
pg1:
image: postgres:14
@@ -48,6 +47,8 @@ services:
main:
build: .
command: ["bash", "/app/tests/docker/run.sh"]
environment:
- INTERACTIVE_TEST_ENVIRONMENT=true
volumes:
- ../../:/app/
- /app/target/

View File

@@ -5,6 +5,38 @@ rm /app/*.profraw || true
rm /app/pgcat.profdata || true
rm -rf /app/cov || true
# Prepares the interactive test environment
#
if [ -n "$INTERACTIVE_TEST_ENVIRONMENT" ]; then
ports=(5432 7432 8432 9432 10432)
for port in "${ports[@]}"; do
is_it_up=0
attempts=0
while [ $is_it_up -eq 0 ]; do
PGPASSWORD=postgres psql -h 127.0.0.1 -p $port -U postgres -c '\q' > /dev/null 2>&1
if [ $? -eq 0 ]; then
echo "PostgreSQL on port $port is up."
is_it_up=1
else
attempts=$((attempts+1))
if [ $attempts -gt 10 ]; then
echo "PostgreSQL on port $port is down, giving up."
exit 1
fi
echo "PostgreSQL on port $port is down, waiting for it to start."
sleep 1
fi
done
done
PGPASSWORD=postgres psql -e -h 127.0.0.1 -p 5432 -U postgres -f /app/tests/sharding/query_routing_setup.sql
PGPASSWORD=postgres psql -e -h 127.0.0.1 -p 7432 -U postgres -f /app/tests/sharding/query_routing_setup.sql
PGPASSWORD=postgres psql -e -h 127.0.0.1 -p 8432 -U postgres -f /app/tests/sharding/query_routing_setup.sql
PGPASSWORD=postgres psql -e -h 127.0.0.1 -p 9432 -U postgres -f /app/tests/sharding/query_routing_setup.sql
PGPASSWORD=postgres psql -e -h 127.0.0.1 -p 10432 -U postgres -f /app/tests/sharding/query_routing_setup.sql
sleep 100000000000000000
exit 0
fi
export LLVM_PROFILE_FILE="/app/pgcat-%m-%p.profraw"
export RUSTC_BOOTSTRAP=1
export CARGO_INCREMENTAL=0

682
tests/rust/Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -15,13 +15,11 @@ async fn test_prepared_statements() {
for _ in 0..5 {
let pool = pool.clone();
let handle = tokio::task::spawn(async move {
for _ in 0..1000 {
match sqlx::query("SELECT one").fetch_all(&pool).await {
for i in 0..1000 {
match sqlx::query(&format!("SELECT {:?}", i % 5)).fetch_all(&pool).await {
Ok(_) => (),
Err(err) => {
if err.to_string().contains("prepared statement") {
panic!("prepared statement error: {}", err);
}
panic!("prepared statement error: {}", err);
}
}
}