Compare commits

..

1 Commits

Author SHA1 Message Date
Sean McGivern
04e346df80 Track transaction time 2024-09-06 16:46:40 +01:00
29 changed files with 526 additions and 3054 deletions

View File

@@ -59,7 +59,6 @@ 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.
@@ -142,7 +141,6 @@ 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

@@ -106,7 +106,7 @@ cd ../..
# These tests will start and stop the pgcat server so it will need to be restarted after the tests
#
pip3 install -r tests/python/requirements.txt
pytest || exit 1
python3 tests/python/tests.py || exit 1
#

View File

@@ -23,17 +23,14 @@ jobs:
steps:
- name: Checkout Repository
uses: actions/checkout@v4
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
uses: actions/checkout@v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
uses: docker/setup-buildx-action@v2
- name: Determine tags
id: metadata
uses: docker/metadata-action@v5
uses: docker/metadata-action@v4
with:
images: ${{ env.registry }}/${{ env.image-name }}
tags: |
@@ -45,18 +42,15 @@ jobs:
type=raw,value=latest,enable={{ is_default_branch }}
- name: Log in to the Container registry
uses: docker/login-action@v3
uses: docker/login-action@v2.1.0
with:
registry: ${{ env.registry }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Build and push ${{ env.image-name }}
uses: docker/build-push-action@v6
uses: docker/build-push-action@v3
with:
context: .
platforms: linux/amd64,linux/arm64
provenance: false
push: true
tags: ${{ steps.metadata.outputs.tags }}
labels: ${{ steps.metadata.outputs.labels }}

3
.gitignore vendored
View File

@@ -10,5 +10,4 @@ lcov.info
dev/.bash_history
dev/cache
!dev/cache/.keepme
.venv
**/__pycache__
.venv

View File

@@ -6,32 +6,6 @@ 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/ && pytest`
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

94
Cargo.lock generated
View File

@@ -146,12 +146,6 @@ dependencies = [
"syn 2.0.26",
]
[[package]]
name = "atomic-waker"
version = "1.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
[[package]]
name = "atomic_enum"
version = "0.2.0"
@@ -548,23 +542,29 @@ checksum = "b6c80984affa11d98d1b88b66ac8853f143217b399d3c74116778ff8fdb4ed2e"
[[package]]
name = "h2"
version = "0.4.6"
version = "0.3.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "524e8ac6999421f49a846c2d4411f337e53497d8ec55d67753beffa43c5d9205"
checksum = "97ec8491ebaf99c8eaa73058b045fe58073cd6be7f596ac993ced0b0a0c01049"
dependencies = [
"atomic-waker",
"bytes",
"fnv",
"futures-core",
"futures-sink",
"futures-util",
"http",
"indexmap",
"indexmap 1.9.3",
"slab",
"tokio",
"tokio-util",
"tracing",
]
[[package]]
name = "hashbrown"
version = "0.12.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888"
[[package]]
name = "hashbrown"
version = "0.14.0"
@@ -609,9 +609,9 @@ dependencies = [
[[package]]
name = "http"
version = "1.1.0"
version = "0.2.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "21b9ddb458710bc376481b842f5da65cdf31522de232c1ca8146abce2a358258"
checksum = "bd6effc99afb63425aff9b05836f029929e345a6148a14b7ecd5ab67af944482"
dependencies = [
"bytes",
"fnv",
@@ -620,24 +620,12 @@ dependencies = [
[[package]]
name = "http-body"
version = "1.0.1"
version = "0.4.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1efedce1fb8e6913f23e0c92de8e62cd5b772a67e7b3946df930a62566c93184"
checksum = "d5f38f16d184e36f2408a55281cd658ecbd3ca05cce6d6510a176eca393e26d1"
dependencies = [
"bytes",
"http",
]
[[package]]
name = "http-body-util"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "793429d76616a256bcb62c2a2ec2bed781c8307e797e2598c50010f2bee2544f"
dependencies = [
"bytes",
"futures-util",
"http",
"http-body",
"pin-project-lite",
]
@@ -655,12 +643,13 @@ checksum = "c4a1e36c821dbe04574f602848a19f742f4fb3c98d40449f11bcad18d6b17421"
[[package]]
name = "hyper"
version = "1.4.1"
version = "0.14.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "50dfd22e0e76d0f662d429a5f80fcaf3855009297eab6a0a9f8543834744ba05"
checksum = "ffb1cfd654a8219eaef89881fdb3bb3b1cdc5fa75ded05d6933b2b382e395468"
dependencies = [
"bytes",
"futures-channel",
"futures-core",
"futures-util",
"h2",
"http",
@@ -669,26 +658,13 @@ dependencies = [
"httpdate",
"itoa",
"pin-project-lite",
"smallvec",
"socket2 0.4.9",
"tokio",
"tower-service",
"tracing",
"want",
]
[[package]]
name = "hyper-util"
version = "0.1.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cde7055719c54e36e95e8719f95883f22072a48ede39db7fc17a4e1d5281e9b9"
dependencies = [
"bytes",
"futures-util",
"http",
"http-body",
"hyper",
"pin-project-lite",
"tokio",
]
[[package]]
name = "iana-time-zone"
version = "0.1.57"
@@ -733,6 +709,16 @@ dependencies = [
"unicode-normalization",
]
[[package]]
name = "indexmap"
version = "1.9.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bd070e393353796e801d209ad339e89596eb4c8d430d18ede6a1cced8fafbd99"
dependencies = [
"autocfg",
"hashbrown 0.12.3",
]
[[package]]
name = "indexmap"
version = "2.0.0"
@@ -740,7 +726,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d5477fe2230a79769d8dc68e0eabf5437907c0457a5614a9e8dddb67f65eb65d"
dependencies = [
"equivalent",
"hashbrown",
"hashbrown 0.14.0",
]
[[package]]
@@ -862,7 +848,7 @@ version = "0.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1efa59af2ddfad1854ae27d75009d538d0998b4b2fd47083e743ac1a10e46c60"
dependencies = [
"hashbrown",
"hashbrown 0.14.0",
]
[[package]]
@@ -1034,7 +1020,7 @@ checksum = "9b2a4787296e9989611394c33f193f676704af1686e70b8f8033ab5ba9a35a94"
[[package]]
name = "pgcat"
version = "1.2.0"
version = "1.1.2-dev4"
dependencies = [
"arc-swap",
"async-trait",
@@ -1048,9 +1034,7 @@ dependencies = [
"fallible-iterator",
"futures",
"hmac",
"http-body-util",
"hyper",
"hyper-util",
"itertools",
"jemallocator",
"log",
@@ -1494,9 +1478,9 @@ dependencies = [
[[package]]
name = "smallvec"
version = "1.13.2"
version = "1.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3c5e1a9a646d36c3599cd173a41282daf47c44583ad367b8e6837255952e5c67"
checksum = "62bb4feee49fdd9f707ef802e22365a35de4b7b299de4763d44bfea899442ff9"
[[package]]
name = "socket2"
@@ -1757,13 +1741,19 @@ version = "0.19.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f8123f27e969974a3dfba720fdb560be359f57b44302d280ba72e76a74480e8a"
dependencies = [
"indexmap",
"indexmap 2.0.0",
"serde",
"serde_spanned",
"toml_datetime",
"winnow",
]
[[package]]
name = "tower-service"
version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6bc1c9ce2b5135ac7f93c72918fc37feb872bdc6a5533a8b85eb4b86bfdae52"
[[package]]
name = "tracing"
version = "0.1.37"

View File

@@ -1,6 +1,6 @@
[package]
name = "pgcat"
version = "1.2.0"
version = "1.1.2-dev4"
edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
@@ -29,9 +29,7 @@ base64 = "0.21"
stringprep = "0.1"
tokio-rustls = "0.24"
rustls-pemfile = "1"
http-body-util = "0.1.2"
hyper = { version = "1.4.1", features = ["full"] }
hyper-util = { version = "0.1.7", features = ["tokio"] }
hyper = { version = "0.14", features = ["full"] }
phf = { version = "0.11.1", features = ["macros"] }
exitcode = "1.1.2"
futures = "0.3"

View File

@@ -1,4 +1,4 @@
FROM cimg/rust:1.79.0
FROM cimg/rust:1.67.1
COPY --from=sclevine/yj /bin/yj /bin/yj
RUN /bin/yj -h
RUN sudo apt-get update && \

View File

@@ -268,8 +268,6 @@ 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.

View File

@@ -4,5 +4,5 @@ description: A Helm chart for PgCat a PostgreSQL pooler and proxy (like PgBounce
maintainers:
- name: Wildcard
email: support@w6d.io
appVersion: "1.2.0"
version: 0.2.0
appVersion: "1.1.1"
version: 0.1.0

View File

@@ -170,13 +170,13 @@ configuration:
connect_timeout: 5000
# How long an idle connection with a server is left open (ms).
idle_timeout: 30000 # milliseconds
idle_timeout: 30000 # milliseconds
# Max connection lifetime before it's closed, even if actively used.
server_lifetime: 86400000 # 24 hours
server_lifetime: 86400000 # 24 hours
# How long a client is allowed to be idle while in a transaction (ms).
idle_client_in_transaction_timeout: 0 # milliseconds
idle_client_in_transaction_timeout: 0 # milliseconds
# @param configuration.general.healthcheck_timeout How much time to give `SELECT 1` health check query to return with a result (ms).
healthcheck_timeout: 1000
@@ -240,15 +240,7 @@ configuration:
## the pool_name is what clients use as database name when connecting
## For the example below a client can connect using "postgres://sharding_user:sharding_user@pgcat_host:pgcat_port/sharded"
## @param [object]
pools:
[{
name: "simple", pool_mode: "transaction",
users: [{username: "user", password: "pass", pool_size: 5, statement_timeout: 0}],
shards: [{
servers: [{host: "postgres", port: 5432, role: "primary"}],
database: "postgres"
}]
}]
pools: []
# - ## default values
# ##
# ##

File diff suppressed because it is too large Load Diff

View File

@@ -55,12 +55,7 @@ where
let query_parts: Vec<&str> = query.trim_end_matches(';').split_whitespace().collect();
match query_parts
.first()
.unwrap_or(&"")
.to_ascii_uppercase()
.as_str()
{
match query_parts[0].to_ascii_uppercase().as_str() {
"BAN" => {
trace!("BAN");
ban(stream, query_parts).await
@@ -89,12 +84,7 @@ where
trace!("SHUTDOWN");
shutdown(stream).await
}
"SHOW" => match query_parts
.get(1)
.unwrap_or(&"")
.to_ascii_uppercase()
.as_str()
{
"SHOW" => match query_parts[1].to_ascii_uppercase().as_str() {
"HELP" => {
trace!("SHOW HELP");
show_help(stream).await

View File

@@ -1204,9 +1204,12 @@ where
if !server.in_transaction() {
// Report transaction executed statistics.
self.stats.transaction();
server
.stats()
.transaction(self.server_parameters.get_application_name());
server.stats().transaction(
Instant::now()
.duration_since(server.transaction_start().into())
.as_millis() as u64,
self.server_parameters.get_application_name(),
);
// Release server back to the pool if we are in transaction mode.
// If we are in session mode, we keep the server until the client disconnects.
@@ -1460,9 +1463,12 @@ where
if !server.in_transaction() {
self.stats.transaction();
server
.stats()
.transaction(self.server_parameters.get_application_name());
server.stats().transaction(
Instant::now()
.duration_since(server.transaction_start().into())
.as_millis() as u64,
self.server_parameters.get_application_name(),
);
// Release server back to the pool if we are in transaction mode.
// If we are in session mode, we keep the server until the client disconnects.
@@ -1511,9 +1517,12 @@ where
if !server.in_transaction() {
self.stats.transaction();
server
.stats()
.transaction(self.server_parameters.get_application_name());
server.stats().transaction(
Instant::now()
.duration_since(server.transaction_start().into())
.as_millis() as u64,
self.server_parameters.get_application_name(),
);
// Release server back to the pool if we are in transaction mode.
// If we are in session mode, we keep the server until the client disconnects.

View File

@@ -1,41 +1,23 @@
use http_body_util::Full;
use hyper::body;
use hyper::body::Bytes;
use hyper::server::conn::http1;
use hyper::service::service_fn;
use hyper::{Method, Request, Response, StatusCode};
use hyper_util::rt::TokioIo;
use hyper::service::{make_service_fn, service_fn};
use hyper::{Body, Method, Request, Response, Server, StatusCode};
use log::{debug, error, info};
use phf::phf_map;
use std::collections::HashMap;
use std::fmt;
use std::net::SocketAddr;
use std::sync::atomic::Ordering;
use tokio::net::TcpListener;
use std::sync::Arc;
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
@@ -138,46 +120,22 @@ 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: "counter",
ty: "gauge",
},
"servers_bytes_sent" => MetricHelpType {
help: "Volume in bytes of network traffic sent by server",
ty: "counter",
ty: "gauge",
},
"servers_transaction_count" => MetricHelpType {
help: "Number of transactions executed by server",
ty: "counter",
ty: "gauge",
},
"servers_query_count" => MetricHelpType {
help: "Number of queries executed by server",
ty: "counter",
ty: "gauge",
},
"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 {
@@ -245,9 +203,7 @@ 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)
}
@@ -262,9 +218,8 @@ 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)
}
@@ -274,9 +229,7 @@ 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)
}
@@ -290,9 +243,7 @@ impl<Value: fmt::Display> PrometheusMetric<Value> {
}
}
async fn prometheus_stats(
request: Request<body::Incoming>,
) -> Result<Response<Full<Bytes>>, hyper::http::Error> {
async fn prometheus_stats(request: Request<Body>) -> Result<Response<Body>, hyper::http::Error> {
match (request.method(), request.uri().path()) {
(&Method::GET, "/metrics") => {
let mut lines = Vec::new();
@@ -378,51 +329,34 @@ 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 prom_stats = HashMap::<String, ServerPrometheusStats>::new();
let mut server_stats_by_addresses = HashMap::<String, Arc<ServerStats>>::new();
for (_, stats) in server_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,
}
server_stats_by_addresses.insert(stats.address_name(), stats);
}
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) = prom_stats.get(&address.name()) {
if let Some(server_info) = server_stats_by_addresses.get(&address.name()) {
let metrics = [
("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 }),
(
"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),
),
];
for (key, value) in metrics {
if let Some(prometheus_metric) =
@@ -440,35 +374,14 @@ fn push_server_stats(lines: &mut Vec<String>) {
}
pub async fn start_metric_server(http_addr: SocketAddr) {
let listener = TcpListener::bind(http_addr);
let listener = match listener.await {
Ok(listener) => listener,
Err(e) => {
error!("Failed to bind prometheus server to HTTP address: {}.", e);
return;
}
};
let http_service_factory =
make_service_fn(|_conn| async { Ok::<_, hyper::Error>(service_fn(prometheus_stats)) });
let server = Server::bind(&http_addr).serve(http_service_factory);
info!(
"Exposing prometheus metrics on http://{}/metrics.",
http_addr
);
loop {
let stream = match listener.accept().await {
Ok((stream, _)) => stream,
Err(e) => {
error!("Error accepting connection: {}", e);
continue;
}
};
let io = TokioIo::new(stream);
tokio::task::spawn(async move {
if let Err(err) = http1::Builder::new()
.serve_connection(io, service_fn(prometheus_stats))
.await
{
eprintln!("Error serving HTTP connection for metrics: {:?}", err);
}
});
if let Err(e) = server.await {
error!("Failed to run HTTP server: {}.", e);
}
}

View File

@@ -427,12 +427,8 @@ impl QueryRouter {
None => (),
};
let has_locks = !query.locks.is_empty();
if has_locks {
self.active_role = Some(Role::Primary);
} else if !visited_write_statement {
// If we already visited a write statement, we should be going to the primary.
// If we already visited a write statement, we should be going to the primary.
if !visited_write_statement {
self.active_role = match self.primary_reads_enabled() {
false => Some(Role::Replica), // If primary should not be receiving reads, use a replica.
true => None, // Any server role is fine in this case.
@@ -1162,29 +1158,6 @@ mod test {
}
}
#[test]
fn test_select_for_update() {
QueryRouter::setup();
let mut qr = QueryRouter::new();
qr.pool_settings.query_parser_read_write_splitting = true;
let queries_in_primary_role = vec![
simple_query("BEGIN"), // Transaction start
simple_query("SELECT * FROM items WHERE id = 5 FOR UPDATE"),
simple_query("UPDATE items SET name = 'pumpkin' WHERE id = 5"),
];
for query in queries_in_primary_role {
assert!(qr.infer(&qr.parse(&query).unwrap()).is_ok());
assert_eq!(qr.role(), Some(Role::Primary));
}
// query without lock do not change role
let query = simple_query("SELECT * FROM items WHERE id = 5");
assert!(qr.infer(&qr.parse(&query).unwrap()).is_ok());
assert_eq!(qr.role(), None);
}
#[test]
fn test_infer_primary_reads_enabled() {
QueryRouter::setup();
@@ -1399,19 +1372,6 @@ 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();

View File

@@ -15,6 +15,7 @@ use std::sync::Arc;
use std::time::SystemTime;
use tokio::io::{AsyncRead, AsyncReadExt, AsyncWrite, BufStream};
use tokio::net::TcpStream;
use tokio::time::Instant;
use tokio_rustls::rustls::{OwnedTrustAnchor, RootCertStore};
use tokio_rustls::{client::TlsStream, TlsConnector};
@@ -285,6 +286,9 @@ pub struct Server {
/// Is the server inside a transaction or idle.
in_transaction: bool,
/// The time the most recent transaction started.
transaction_start: Instant,
/// Is there more data for the client to read.
data_available: bool,
@@ -804,6 +808,7 @@ impl Server {
process_id,
secret_key,
in_transaction: false,
transaction_start: Instant::now(),
in_copy_mode: false,
data_available: false,
bad: false,
@@ -936,6 +941,7 @@ impl Server {
// In transaction.
'T' => {
self.in_transaction = true;
self.transaction_start = Instant::now();
}
// Idle, transaction over.
@@ -1220,6 +1226,12 @@ impl Server {
self.in_transaction
}
/// The start time of the most recent transaction.
/// Will be stale if not in a transaction.
pub fn transaction_start(&self) -> Instant {
self.transaction_start
}
/// Currently copying data from client to server or vice-versa.
pub fn in_copy_mode(&self) -> bool {
self.in_copy_mode

View File

@@ -187,11 +187,12 @@ impl ServerStats {
/// we report each individual queries outside a transaction as a transaction
/// We only count the initial BEGIN as a transaction, all queries within do not
/// count as transactions
pub fn transaction(&self, application_name: &str) {
pub fn transaction(&self, milliseconds: u64, application_name: &str) {
self.set_application(application_name.to_string());
self.transaction_count.fetch_add(1, Ordering::Relaxed);
self.address.stats.xact_count_add();
self.address.stats.xact_time_add(milliseconds);
}
/// Report data sent to a server

View File

@@ -1,34 +0,0 @@
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/ && pytest ${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

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

View File

@@ -5,38 +5,6 @@ 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

View File

@@ -1,3 +1,2 @@
pytest
psycopg2==2.9.3
psutil==5.9.1
psutil==5.9.1

View File

@@ -1,29 +1,83 @@
from typing import Tuple
import psycopg2
import psutil
import os
import signal
import time
import psycopg2
import utils
SHUTDOWN_TIMEOUT = 5
PGCAT_HOST = "127.0.0.1"
PGCAT_PORT = "6432"
def pgcat_start():
pg_cat_send_signal(signal.SIGTERM)
os.system("./target/debug/pgcat .circleci/pgcat.toml &")
time.sleep(2)
def pg_cat_send_signal(signal: signal.Signals):
try:
for proc in psutil.process_iter(["pid", "name"]):
if "pgcat" == proc.name():
os.kill(proc.pid, signal)
except Exception as e:
# The process can be gone when we send this signal
print(e)
if signal == signal.SIGTERM:
# Returns 0 if pgcat process exists
time.sleep(2)
if not os.system('pgrep pgcat'):
raise Exception("pgcat not closed after SIGTERM")
def connect_db(
autocommit: bool = True,
admin: bool = False,
) -> Tuple[psycopg2.extensions.connection, psycopg2.extensions.cursor]:
if admin:
user = "admin_user"
password = "admin_pass"
db = "pgcat"
else:
user = "sharding_user"
password = "sharding_user"
db = "sharded_db"
conn = psycopg2.connect(
f"postgres://{user}:{password}@{PGCAT_HOST}:{PGCAT_PORT}/{db}?application_name=testing_pgcat",
connect_timeout=2,
)
conn.autocommit = autocommit
cur = conn.cursor()
return (conn, cur)
def cleanup_conn(conn: psycopg2.extensions.connection, cur: psycopg2.extensions.cursor):
cur.close()
conn.close()
def test_normal_db_access():
utils.pgcat_start()
conn, cur = utils.connect_db(autocommit=False)
pgcat_start()
conn, cur = connect_db(autocommit=False)
cur.execute("SELECT 1")
res = cur.fetchall()
print(res)
utils.cleanup_conn(conn, cur)
cleanup_conn(conn, cur)
def test_admin_db_access():
conn, cur = utils.connect_db(admin=True)
conn, cur = connect_db(admin=True)
cur.execute("SHOW POOLS")
res = cur.fetchall()
print(res)
utils.cleanup_conn(conn, cur)
cleanup_conn(conn, cur)
def test_shutdown_logic():
@@ -32,17 +86,17 @@ def test_shutdown_logic():
# NO ACTIVE QUERIES SIGINT HANDLING
# Start pgcat
utils.pgcat_start()
pgcat_start()
# Create client connection and send query (not in transaction)
conn, cur = utils.connect_db()
conn, cur = connect_db()
cur.execute("BEGIN;")
cur.execute("SELECT 1;")
cur.execute("COMMIT;")
# Send sigint to pgcat
utils.pg_cat_send_signal(signal.SIGINT)
pg_cat_send_signal(signal.SIGINT)
time.sleep(1)
# Check that any new queries fail after sigint since server should close with no active transactions
@@ -54,18 +108,18 @@ def test_shutdown_logic():
# Fail if query execution succeeded
raise Exception("Server not closed after sigint")
utils.cleanup_conn(conn, cur)
utils.pg_cat_send_signal(signal.SIGTERM)
cleanup_conn(conn, cur)
pg_cat_send_signal(signal.SIGTERM)
# - - - - - - - - - - - - - - - - - -
# NO ACTIVE QUERIES ADMIN SHUTDOWN COMMAND
# Start pgcat
utils.pgcat_start()
pgcat_start()
# Create client connection and begin transaction
conn, cur = utils.connect_db()
admin_conn, admin_cur = utils.connect_db(admin=True)
conn, cur = connect_db()
admin_conn, admin_cur = connect_db(admin=True)
cur.execute("BEGIN;")
cur.execute("SELECT 1;")
@@ -84,24 +138,24 @@ def test_shutdown_logic():
# Fail if query execution succeeded
raise Exception("Server not closed after sigint")
utils.cleanup_conn(conn, cur)
utils.cleanup_conn(admin_conn, admin_cur)
utils.pg_cat_send_signal(signal.SIGTERM)
cleanup_conn(conn, cur)
cleanup_conn(admin_conn, admin_cur)
pg_cat_send_signal(signal.SIGTERM)
# - - - - - - - - - - - - - - - - - -
# HANDLE TRANSACTION WITH SIGINT
# Start pgcat
utils.pgcat_start()
pgcat_start()
# Create client connection and begin transaction
conn, cur = utils.connect_db()
conn, cur = connect_db()
cur.execute("BEGIN;")
cur.execute("SELECT 1;")
# Send sigint to pgcat while still in transaction
utils.pg_cat_send_signal(signal.SIGINT)
pg_cat_send_signal(signal.SIGINT)
time.sleep(1)
# Check that any new queries succeed after sigint since server should still allow transaction to complete
@@ -111,18 +165,18 @@ def test_shutdown_logic():
# Fail if query fails since server closed
raise Exception("Server closed while in transaction", e.pgerror)
utils.cleanup_conn(conn, cur)
utils.pg_cat_send_signal(signal.SIGTERM)
cleanup_conn(conn, cur)
pg_cat_send_signal(signal.SIGTERM)
# - - - - - - - - - - - - - - - - - -
# HANDLE TRANSACTION WITH ADMIN SHUTDOWN COMMAND
# Start pgcat
utils.pgcat_start()
pgcat_start()
# Create client connection and begin transaction
conn, cur = utils.connect_db()
admin_conn, admin_cur = utils.connect_db(admin=True)
conn, cur = connect_db()
admin_conn, admin_cur = connect_db(admin=True)
cur.execute("BEGIN;")
cur.execute("SELECT 1;")
@@ -140,30 +194,30 @@ def test_shutdown_logic():
# Fail if query fails since server closed
raise Exception("Server closed while in transaction", e.pgerror)
utils.cleanup_conn(conn, cur)
utils.cleanup_conn(admin_conn, admin_cur)
utils.pg_cat_send_signal(signal.SIGTERM)
cleanup_conn(conn, cur)
cleanup_conn(admin_conn, admin_cur)
pg_cat_send_signal(signal.SIGTERM)
# - - - - - - - - - - - - - - - - - -
# NO NEW NON-ADMIN CONNECTIONS DURING SHUTDOWN
# Start pgcat
utils.pgcat_start()
pgcat_start()
# Create client connection and begin transaction
transaction_conn, transaction_cur = utils.connect_db()
transaction_conn, transaction_cur = connect_db()
transaction_cur.execute("BEGIN;")
transaction_cur.execute("SELECT 1;")
# Send sigint to pgcat while still in transaction
utils.pg_cat_send_signal(signal.SIGINT)
pg_cat_send_signal(signal.SIGINT)
time.sleep(1)
start = time.perf_counter()
try:
conn, cur = utils.connect_db()
conn, cur = connect_db()
cur.execute("SELECT 1;")
utils.cleanup_conn(conn, cur)
cleanup_conn(conn, cur)
except psycopg2.OperationalError as e:
time_taken = time.perf_counter() - start
if time_taken > 0.1:
@@ -173,49 +227,49 @@ def test_shutdown_logic():
else:
raise Exception("Able connect to database during shutdown")
utils.cleanup_conn(transaction_conn, transaction_cur)
utils.pg_cat_send_signal(signal.SIGTERM)
cleanup_conn(transaction_conn, transaction_cur)
pg_cat_send_signal(signal.SIGTERM)
# - - - - - - - - - - - - - - - - - -
# ALLOW NEW ADMIN CONNECTIONS DURING SHUTDOWN
# Start pgcat
utils.pgcat_start()
pgcat_start()
# Create client connection and begin transaction
transaction_conn, transaction_cur = utils.connect_db()
transaction_conn, transaction_cur = connect_db()
transaction_cur.execute("BEGIN;")
transaction_cur.execute("SELECT 1;")
# Send sigint to pgcat while still in transaction
utils.pg_cat_send_signal(signal.SIGINT)
pg_cat_send_signal(signal.SIGINT)
time.sleep(1)
try:
conn, cur = utils.connect_db(admin=True)
conn, cur = connect_db(admin=True)
cur.execute("SHOW DATABASES;")
utils.cleanup_conn(conn, cur)
cleanup_conn(conn, cur)
except psycopg2.OperationalError as e:
raise Exception(e)
utils.cleanup_conn(transaction_conn, transaction_cur)
utils.pg_cat_send_signal(signal.SIGTERM)
cleanup_conn(transaction_conn, transaction_cur)
pg_cat_send_signal(signal.SIGTERM)
# - - - - - - - - - - - - - - - - - -
# ADMIN CONNECTIONS CONTINUING TO WORK AFTER SHUTDOWN
# Start pgcat
utils.pgcat_start()
pgcat_start()
# Create client connection and begin transaction
transaction_conn, transaction_cur = utils.connect_db()
transaction_conn, transaction_cur = connect_db()
transaction_cur.execute("BEGIN;")
transaction_cur.execute("SELECT 1;")
admin_conn, admin_cur = utils.connect_db(admin=True)
admin_conn, admin_cur = connect_db(admin=True)
admin_cur.execute("SHOW DATABASES;")
# Send sigint to pgcat while still in transaction
utils.pg_cat_send_signal(signal.SIGINT)
pg_cat_send_signal(signal.SIGINT)
time.sleep(1)
try:
@@ -223,24 +277,24 @@ def test_shutdown_logic():
except psycopg2.OperationalError as e:
raise Exception("Could not execute admin command:", e)
utils.cleanup_conn(transaction_conn, transaction_cur)
utils.cleanup_conn(admin_conn, admin_cur)
utils.pg_cat_send_signal(signal.SIGTERM)
cleanup_conn(transaction_conn, transaction_cur)
cleanup_conn(admin_conn, admin_cur)
pg_cat_send_signal(signal.SIGTERM)
# - - - - - - - - - - - - - - - - - -
# HANDLE SHUTDOWN TIMEOUT WITH SIGINT
# Start pgcat
utils.pgcat_start()
pgcat_start()
# Create client connection and begin transaction, which should prevent server shutdown unless shutdown timeout is reached
conn, cur = utils.connect_db()
conn, cur = connect_db()
cur.execute("BEGIN;")
cur.execute("SELECT 1;")
# Send sigint to pgcat while still in transaction
utils.pg_cat_send_signal(signal.SIGINT)
pg_cat_send_signal(signal.SIGINT)
# pgcat shutdown timeout is set to SHUTDOWN_TIMEOUT seconds, so we sleep for SHUTDOWN_TIMEOUT + 1 seconds
time.sleep(SHUTDOWN_TIMEOUT + 1)
@@ -254,5 +308,12 @@ def test_shutdown_logic():
# Fail if query execution succeeded
raise Exception("Server not closed after sigint and expected timeout")
utils.cleanup_conn(conn, cur)
utils.pg_cat_send_signal(signal.SIGTERM)
cleanup_conn(conn, cur)
pg_cat_send_signal(signal.SIGTERM)
# - - - - - - - - - - - - - - - - - -
test_normal_db_access()
test_admin_db_access()
test_shutdown_logic()

View File

@@ -1,60 +0,0 @@
from typing import Tuple
import os
import psutil
import signal
import time
import psycopg2
PGCAT_HOST = "127.0.0.1"
PGCAT_PORT = "6432"
def pgcat_start():
pg_cat_send_signal(signal.SIGTERM)
os.system("./target/debug/pgcat .circleci/pgcat.toml &")
time.sleep(2)
def pg_cat_send_signal(signal: signal.Signals):
try:
for proc in psutil.process_iter(["pid", "name"]):
if "pgcat" == proc.name():
os.kill(proc.pid, signal)
except Exception as e:
# The process can be gone when we send this signal
print(e)
if signal == signal.SIGTERM:
# Returns 0 if pgcat process exists
time.sleep(2)
if not os.system('pgrep pgcat'):
raise Exception("pgcat not closed after SIGTERM")
def connect_db(
autocommit: bool = True,
admin: bool = False,
) -> Tuple[psycopg2.extensions.connection, psycopg2.extensions.cursor]:
if admin:
user = "admin_user"
password = "admin_pass"
db = "pgcat"
else:
user = "sharding_user"
password = "sharding_user"
db = "sharded_db"
conn = psycopg2.connect(
f"postgres://{user}:{password}@{PGCAT_HOST}:{PGCAT_PORT}/{db}?application_name=testing_pgcat",
connect_timeout=2,
)
conn.autocommit = autocommit
cur = conn.cursor()
return (conn, cur)
def cleanup_conn(conn: psycopg2.extensions.connection, cur: psycopg2.extensions.cursor):
cur.close()
conn.close()

View File

@@ -91,27 +91,6 @@ describe "Admin" do
end
end
[
"SHOW ME THE MONEY",
"SHOW ME THE WAY",
"SHOW UP",
"SHOWTIME",
"HAMMER TIME",
"SHOWN TO BE TRUE",
"SHOW ",
"SHOW ",
"SHOW 1",
";;;;;"
].each do |cmd|
describe "Bad command #{cmd}" do
it "does not panic and responds with PG::SystemError" do
admin_conn = PG::connect(processes.pgcat.admin_connection_string)
expect { admin_conn.async_exec(cmd) }.to raise_error(PG::SystemError).with_message(/Unsupported/)
admin_conn.close
end
end
end
describe "PAUSE" do
it "pauses all pools" do
admin_conn = PG::connect(processes.pgcat.admin_connection_string)

View File

@@ -16,7 +16,7 @@ describe "Stats" do
it "updates *_query_time and *_wait_time" do
connections = Array.new(3) { PG::connect("#{pgcat_conn_str}?application_name=one_query") }
connections.each do |c|
Thread.new { c.async_exec("SELECT pg_sleep(0.25)") }
Thread.new { c.async_exec("BEGIN; SELECT pg_sleep(0.25); COMMIT;") }
end
sleep(1)
connections.map(&:close)
@@ -25,10 +25,32 @@ describe "Stats" do
sleep(15.5)
admin_conn = PG::connect(processes.pgcat.admin_connection_string)
results = admin_conn.async_exec("SHOW STATS")[0]
admin_conn.close
expect(results["total_query_time"].to_i).to be_within(200).of(750)
expect(results["avg_query_time"].to_i).to be_within(50).of(250)
expect(results["total_xact_time"].to_i).to be_within(200).of(750)
expect(results["avg_xact_time"].to_i).to be_within(50).of(250)
expect(results["total_wait_time"].to_i).to_not eq(0)
expect(results["avg_wait_time"].to_i).to_not eq(0)
connections = Array.new(3) { PG::connect("#{pgcat_conn_str}?application_name=one_query") }
connections.each do |c|
Thread.new { c.async_exec("SELECT pg_sleep(0.25);") }
end
sleep(1)
connections.map(&:close)
results = admin_conn.async_exec("SHOW STATS")[0]
admin_conn.close
# This should increase with more queries
expect(results["total_query_time"].to_i).to be_within(400).of(1500)
expect(results["avg_query_time"].to_i).to be_within(50).of(250)
# This should not increase as we did not run any additional transactions
expect(results["total_xact_time"].to_i).to be_within(200).of(750)
expect(results["avg_xact_time"].to_i).to be_within(50).of(250)
expect(results["total_wait_time"].to_i).to_not eq(0)
expect(results["avg_wait_time"].to_i).to_not eq(0)
end

664
tests/rust/Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

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