Files
inbuxa-server/crates/store/src/backend/postgres/main.rs
T
2026-09-25 00:45:09 +00:00

405 lines
15 KiB
Rust

/*
* SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
*
* SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
*
* Modified by Coffey Labs in 2026 for INBUXA.
*/
use super::{PostgresStore, bounded, into_error};
use crate::{
backend::postgres::{
PsqlSearchField, into_pool_error,
search::{PG_FALLBACK_LANG, PG_LANGS, PG_UNSTEMMED_LANG},
tls::MakeRustlsConnect,
},
search::{
CalendarSearchField, ContactSearchField, EmailSearchField, SearchableField,
TracingSearchField,
},
*,
};
use ::registry::schema::{enums::PostgreSqlRecyclingMethod, structs};
use ahash::AHashSet;
use deadpool_postgres::{
Config, ManagerConfig, Object, Pool, PoolConfig, RecyclingMethod, Runtime, Timeouts,
};
use std::time::Duration;
use tokio_postgres::NoTls;
use utils::tls::rustls_client_config;
/// inbuxa: how long a request waits for a pooled connection.
pub(crate) const POOL_WAIT_TIMEOUT: Duration = Duration::from_secs(30);
/// inbuxa: how long opening a connection may take when the store sets no
/// timeout of its own.
pub(crate) const POOL_CREATE_TIMEOUT: Duration = Duration::from_secs(15);
/// inbuxa: how long checking a pooled connection before reuse may take.
pub(crate) const POOL_RECYCLE_TIMEOUT: Duration = Duration::from_secs(10);
/// inbuxa: idle time before TCP keepalive probes start.
pub(crate) const POOL_KEEPALIVE_IDLE: Duration = Duration::from_secs(60);
/// inbuxa: the pool's timeouts. Opening a connection is bounded by the
/// store's own timeout when it has one; waiting for one covers at least that
/// long, so a slow connect isn't cut short by the wait.
pub(crate) fn pool_timeouts(connect_timeout: Option<Duration>) -> Timeouts {
let create = connect_timeout.unwrap_or(POOL_CREATE_TIMEOUT);
Timeouts {
wait: POOL_WAIT_TIMEOUT.max(create).into(),
create: create.into(),
recycle: POOL_RECYCLE_TIMEOUT.into(),
}
}
impl PostgresStore {
pub async fn open(config: structs::PostgreSqlStore) -> Result<Store, String> {
// inbuxa: ST-15: where the primary is, to tell a replica from it
let primary_location = (config.host.clone(), config.port as u16, config.database.clone());
let mut cfg = Config::new();
cfg.dbname = config.database.into();
cfg.host = config.host.into();
cfg.user = config.auth_username;
cfg.password = config.auth_secret.secret().await?.map(|v| v.into_owned());
cfg.port = (config.port as u16).into();
cfg.connect_timeout = config.timeout.map(|t| t.into_inner());
cfg.options = config.options;
cfg.manager = Some(ManagerConfig {
recycling_method: match config.pool_recycling_method {
PostgreSqlRecyclingMethod::Fast => RecyclingMethod::Fast,
PostgreSqlRecyclingMethod::Verified => RecyclingMethod::Verified,
PostgreSqlRecyclingMethod::Clean => RecyclingMethod::Clean,
},
});
// inbuxa: upstream set no pool timeouts, so a request waited for a
// free connection, or for one to be made or recycled, for as long as
// it took: forever when the server stopped answering. A worker now
// gets an error instead and the task or request is retried.
let mut pool = config
.pool_max_connections
.map(|max_conn| PoolConfig::new(max_conn as usize))
.unwrap_or_default();
pool.timeouts = pool_timeouts(cfg.connect_timeout);
cfg.pool = pool.into();
// Notice a server that went away without closing the connection in
// minutes rather than the system default of two hours
cfg.keepalives = true.into();
cfg.keepalives_idle = POOL_KEEPALIVE_IDLE.into();
let primary_pool = if config.use_tls {
cfg.create_pool(
Some(Runtime::Tokio1),
MakeRustlsConnect::new(rustls_client_config(config.allow_invalid_certs)?),
)
} else {
cfg.create_pool(Some(Runtime::Tokio1), NoTls)
}
.map_err(|e| format!("Failed to create connection pool: {e}"))?;
let ts_configs = discover_ts_configs(&primary_pool).await;
// inbuxa: ST-5 to ST-15: each replica inherits the primary's settings
// except where it is and how to sign in
let mut replicas = vec![];
for replica in config.read_replicas {
let mut cfg = cfg.clone();
cfg.dbname = replica.database.clone().into();
cfg.host = replica.host.clone().into();
cfg.user = replica.auth_username;
cfg.password = replica.auth_secret.secret().await?.map(|v| v.into_owned());
cfg.port = (replica.port as u16).into();
cfg.options = replica.options;
let pool = if config.use_tls {
cfg.create_pool(
Some(Runtime::Tokio1),
MakeRustlsConnect::new(rustls_client_config(config.allow_invalid_certs)?),
)
} else {
cfg.create_pool(Some(Runtime::Tokio1), NoTls)
}
.map_err(|e| format!("Failed to create connection pool: {e}"))?;
replicas.push(crate::backend::scaleout::replica::Replica::new(
Store::PostgreSQL(Arc::new(PostgresStore {
conn_pool: pool,
ts_configs: ts_configs.clone(),
timeouts: Default::default(),
})),
replica.host,
replica.port as u16,
replica.database,
));
}
let primary = Store::PostgreSQL(Arc::new(PostgresStore {
conn_pool: primary_pool,
ts_configs,
timeouts: Default::default(),
}));
// ST-1: no replicas, no change
if replicas.is_empty() {
return Ok(primary);
}
Ok(Store::Replicated(
crate::backend::scaleout::replica::ReplicatedStore::new(
primary,
primary_location,
replicas,
crate::backend::scaleout::replica::ReplicaKind::PostgreSql,
),
))
}
pub(crate) async fn create_storage_tables(&self) -> trc::Result<()> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.maintenance;
let result = tokio::time::timeout(limit, async {
for table in [
SUBSPACE_ACL,
SUBSPACE_TASK_QUEUE,
SUBSPACE_DELETED_ITEMS,
SUBSPACE_SPAM_SAMPLES,
crate::SUBSPACE_INBUXA, // inbuxa: masked email
SUBSPACE_BLOB_LINK,
SUBSPACE_IN_MEMORY_VALUE,
SUBSPACE_PROPERTY,
SUBSPACE_REGISTRY,
SUBSPACE_REGISTRY_PK,
SUBSPACE_QUEUE_MESSAGE,
SUBSPACE_QUEUE_EVENT,
SUBSPACE_REPORT_OUT,
SUBSPACE_REPORT_IN,
SUBSPACE_LOGS,
SUBSPACE_BLOBS,
SUBSPACE_DIRECTORY,
SUBSPACE_TELEMETRY_SPAN,
SUBSPACE_TELEMETRY_METRIC,
] {
let table = char::from(table);
conn.execute(
&format!(
"CREATE TABLE IF NOT EXISTS {table} (
k BYTEA PRIMARY KEY,
v BYTEA NOT NULL
)"
),
&[],
)
.await
.map_err(into_error)?;
}
for table in [SUBSPACE_INDEXES, SUBSPACE_REGISTRY_IDX] {
let table = char::from(table);
conn.execute(
&format!(
"CREATE TABLE IF NOT EXISTS {table} (
k BYTEA PRIMARY KEY
)"
),
&[],
)
.await
.map_err(into_error)?;
}
for table in [SUBSPACE_COUNTER, SUBSPACE_QUOTA, SUBSPACE_IN_MEMORY_COUNTER] {
conn.execute(
&format!(
"CREATE TABLE IF NOT EXISTS {} (
k BYTEA PRIMARY KEY,
v BIGINT NOT NULL DEFAULT 0
)",
char::from(table)
),
&[],
)
.await
.map_err(into_error)?;
}
Ok(())
})
.await;
bounded(conn, result, limit)
}
pub(crate) async fn create_search_tables(&self) -> trc::Result<()> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.maintenance;
let result = tokio::time::timeout(limit, async {
create_search_tables::<EmailSearchField>(&conn).await?;
create_search_tables::<CalendarSearchField>(&conn).await?;
create_search_tables::<ContactSearchField>(&conn).await?;
//create_search_tables::<FileSearchField>(&conn).await?;
create_search_tables::<TracingSearchField>(&conn).await?;
Ok(())
})
.await;
bounded(conn, result, limit)
}
}
async fn create_search_tables<T: SearchableField + PsqlSearchField + 'static>(
conn: &Object,
) -> trc::Result<()> {
let table_name = T::index().psql_table();
let mut query = format!("CREATE TABLE IF NOT EXISTS {} (", table_name);
// Add primary key columns
let pkeys = T::primary_keys();
for pkey in pkeys {
query.push_str(&format!("{} {}, ", pkey.column(), pkey.column_type()));
}
// Add other columns
for field in T::all_fields() {
query.push_str(&format!("{} {}", field.column(), field.column_type()));
if let Some(sort_type) = field.sort_column_type() {
query.push_str(&format!(", {} {}", field.sort_column().unwrap(), sort_type));
}
query.push_str(", ");
}
// Add primary key constraint
query.push_str("PRIMARY KEY (");
for (i, pkey) in pkeys.iter().enumerate() {
if i > 0 {
query.push_str(", ");
}
query.push_str(pkey.column());
}
query.push_str("))");
conn.execute(&query, &[]).await.map_err(into_error)?;
// Create indexes
for field in T::all_fields() {
if field.is_text() || field.is_json() {
let column_name = field.column();
// inbuxa: with GIN's default fastupdate=on, new entries wait in
// an unindexed pending list that every search scans in full
// until a VACUUM (or 4 MB of backlog) merges it. On a mailbox
// taking steady mail that list never drains and searches slow
// from milliseconds to hundreds of them. Pay the index update
// at insert time instead.
let index_name = format!("gin_{table_name}_{column_name}");
let create_index_query = format!(
"CREATE INDEX IF NOT EXISTS {index_name} ON {table_name} USING GIN({column_name}) WITH (fastupdate = off)",
);
conn.execute(&create_index_query, &[])
.await
.map_err(into_error)?;
// Indexes made before this change keep fastupdate=on
disable_gin_fastupdate(conn, &index_name).await;
}
if field.is_indexed() {
let column_name = field.sort_column().unwrap_or(field.column());
let create_index_query = format!(
"CREATE INDEX IF NOT EXISTS idx_{table_name}_{column_name} ON {table_name}({column_name})",
);
conn.execute(&create_index_query, &[])
.await
.map_err(into_error)?;
}
}
Ok(())
}
/// inbuxa: turns fastupdate off on a GIN index made with the default and
/// merges the pending list it has built up. Idempotent: an index that already
/// has the option is left alone, so this costs one catalog read per index at
/// startup. A failure is logged and startup goes on, since search still works,
/// only slower.
async fn disable_gin_fastupdate(conn: &Object, index_name: &str) {
if let Err(err) = try_disable_gin_fastupdate(conn, index_name).await {
trc::event!(
Store(trc::StoreEvent::PostgresqlError),
Details = format!("Failed to turn off fastupdate on search index {index_name}"),
Reason = err.to_string(),
);
}
}
async fn try_disable_gin_fastupdate(conn: &Object, index_name: &str) -> trc::Result<()> {
let options = conn
.query_opt(
"SELECT COALESCE(reloptions, '{}')::text[] FROM pg_class WHERE oid = to_regclass($1)",
&[&index_name],
)
.await
.map_err(into_error)?
.map(|row| row.try_get::<_, Vec<String>>(0))
.transpose()
.map_err(into_error)?;
let Some(options) = options else {
return Ok(());
};
if gin_fastupdate_is_off(&options) {
return Ok(());
}
// SET (fastupdate) takes a SHARE UPDATE EXCLUSIVE lock, which doesn't
// block reads or writes. Turning it off stops new entries going to the
// pending list but doesn't flush the entries already there.
conn.execute(
&format!("ALTER INDEX {index_name} SET (fastupdate = off)"),
&[],
)
.await
.map_err(into_error)?;
conn.query_one(
"SELECT gin_clean_pending_list($1::text::regclass)",
&[&index_name],
)
.await
.map_err(into_error)?;
Ok(())
}
/// Whether a relation's reloptions turn GIN's fastupdate off.
fn gin_fastupdate_is_off(options: &[String]) -> bool {
options.iter().any(|option| {
option.split_once('=').is_some_and(|(name, value)| {
name.trim().eq_ignore_ascii_case("fastupdate")
&& matches!(
value.trim().to_ascii_lowercase().as_str(),
"off" | "false" | "no" | "0" | "f" | "n"
)
})
})
}
async fn discover_ts_configs(pool: &Pool) -> AHashSet<&'static str> {
let mut ts_configs = AHashSet::from_iter([PG_FALLBACK_LANG, PG_UNSTEMMED_LANG]);
match probe_ts_configs(pool).await {
Ok(available) => {
for name in available {
if let Some(config) = PG_LANGS.iter().copied().find(|config| *config == name) {
ts_configs.insert(config);
}
}
}
Err(err) => {
trc::event!(
Store(trc::StoreEvent::PostgresqlError),
Details = "Failed to query pg_ts_config, assuming english only",
Reason = err.to_string(),
);
}
}
ts_configs
}
async fn probe_ts_configs(pool: &Pool) -> trc::Result<Vec<String>> {
let conn = pool.get().await.map_err(into_pool_error)?;
conn.query("SELECT cfgname::text FROM pg_ts_config", &[])
.await
.map_err(into_error)?
.into_iter()
.map(|row| row.try_get::<_, String>(0).map_err(into_error))
.collect()
}