1 Commits
Author SHA1 Message Date
jcoffey-dev 6a80aaea08 Cluster role changes apply to delivery and tasks without a restart
ci / fork-checks (pull_request) Successful in 49s
ci / build (pull_request) Successful in 5m3s
In cluster rehearsal 3, turning outboundMta off on node1's role was
reported applied (x:settingsReload applied: true), yet node1 kept
delivering mail, a report message included, until it was restarted.
The queue and report managers were started at boot only when the
node's role included outboundMta (crates/smtp/src/lib.rs), and the task
manager only when the role had some task type (spawn_task_manager).
After that nothing looked at the role again: a queue manager that was
running kept claiming and delivering, and one that wasn't never
started.

They now start on every node (outside recovery mode) and follow the
role live:

- Queue manager: before each scan it reads the role from the running
  settings. Without outboundMta it claims nothing new; deliveries
  already running finish and report back as usual, which releases
  their locks. When the role comes back (a reload wakes the manager
  with ReloadSettings, and it looks again every 30 s regardless) it
  logs queue.started and scans the whole queue at once.
- Report scheduler: DMARC and TLS report events are handled only while
  the role has outboundMta, as at boot; events arriving without it are
  dropped, as they were on a node started without the role.
- Task manager: task_enabled already read the current role on every
  scan. It now also runs on nodes whose role has no task type (the
  scan returns at once until one is added), a job claimed before a
  role change is handed back at once rather than run or held until
  its lease lapses, and a settings reload wakes the manager so a role
  that gained task types starts claiming them straight away.

Starting the queue manager on every node also drains the queue channel
on nodes without outboundMta. Upstream left that channel unread, so
each message queued there parked a refresh in it, and by the code,
queueing would block once 1024 had piled up (not reproduced here).

A role object edit reaches the nodes that name that role in
INBUXA_ROLE. Moving a node to another role still means changing its
environment, and so a restart. Listener changes in a role still need a
restart too (listeners bind at boot); this change is about tasks and
delivery.

cluster::live_roles::live_role_tests (new; PostgreSQL, two nodes over
one store):
1. A node started with outboundMta delivers and runs a TLS report
   task; after its role loses outboundMta and the settings reload, a
   new message isn't attempted and a new report task stays pending;
   with the role back, both are taken up.
2. A node started with no task type at all gains outboundMta: a
   waiting message is attempted and a report task runs.
On main the test fails at step 1 ("delivery attempted without
outboundMta"); with step 1 bypassed, step 2 fails (nothing picked the
message up in 20 s).
2026-09-24 16:15:13 -07:00
24 changed files with 794 additions and 1765 deletions
-2
View File
@@ -94,7 +94,6 @@ impl Data {
span_id_gen: id_generator, span_id_gen: id_generator,
queue_status: true.into(), queue_status: true.into(),
settings_reload: Default::default(), settings_reload: Default::default(),
store_health: Default::default(),
applications, applications,
logos: Default::default(), logos: Default::default(),
smtp_connectors: TlsConnectors::try_new().failed("Failed to build TLS connectors"), smtp_connectors: TlsConnectors::try_new().failed("Failed to build TLS connectors"),
@@ -238,7 +237,6 @@ impl Default for Data {
registry_id_gen: Default::default(), registry_id_gen: Default::default(),
queue_status: true.into(), queue_status: true.into(),
settings_reload: Default::default(), settings_reload: Default::default(),
store_health: Default::default(),
applications: WebApplications::new(), applications: WebApplications::new(),
logos: Default::default(), logos: Default::default(),
smtp_connectors: TlsConnectors::try_new().unwrap(), smtp_connectors: TlsConnectors::try_new().unwrap(),
-2
View File
@@ -163,8 +163,6 @@ pub struct Data {
pub queue_status: AtomicBool, pub queue_status: AtomicBool,
// inbuxa: coalesces the settings reloads registry writes trigger // inbuxa: coalesces the settings reloads registry writes trigger
pub settings_reload: cache::reload::SettingsReloadGate, pub settings_reload: cache::reload::SettingsReloadGate,
// inbuxa: the readiness probe's cached answer
pub store_health: storage::ready::StoreHealth,
pub applications: WebApplications, pub applications: WebApplications,
pub logos: Mutex<AHashMap<Box<str>, LogoCache>>, pub logos: Mutex<AHashMap<Box<str>, LogoCache>>,
-1
View File
@@ -26,7 +26,6 @@ pub mod document;
pub mod encryption; pub mod encryption;
pub mod index; pub mod index;
pub mod quota; pub mod quota;
pub mod ready; // inbuxa: readiness follows the data store
pub mod state; pub mod state;
pub mod transaction; pub mod transaction;
-83
View File
@@ -1,83 +0,0 @@
/*
* SPDX-FileCopyrightText: 2026 Coffey Labs
*
* SPDX-License-Identifier: AGPL-3.0-only
*/
//! Readiness that reflects the data store.
//!
//! /healthz/ready used to answer 200 whenever a data store was configured,
//! so a load balancer kept sending traffic to a node through a database
//! outage. It now reads one key from the data store, with a short time
//! limit, and caches the answer for a couple of seconds so probes can't load
//! the database. Liveness stays 200: restarting a node doesn't bring its
//! database back, and an orchestrator that restarts on failed liveness would
//! otherwise restart every node at once.
use crate::Server;
use parking_lot::Mutex;
use std::{
sync::atomic::{AtomicBool, Ordering},
time::{Duration, Instant},
};
use store::{ValueKey, write::ValueClass};
/// How long a probe's answer is reused.
pub const READY_CACHE: Duration = Duration::from_secs(2);
/// How long a probe waits for the data store.
pub const READY_PROBE_TIMEOUT: Duration = Duration::from_secs(2);
#[derive(Default)]
pub struct StoreHealth {
last: Mutex<Option<(Instant, bool)>>,
probing: AtomicBool,
}
/// Clears the probing flag even when the request is dropped mid-probe.
struct ProbeGuard<'x>(&'x AtomicBool);
impl Drop for ProbeGuard<'_> {
fn drop(&mut self) {
self.0.store(false, Ordering::Release);
}
}
impl Server {
/// Whether the data store answers: a cached result younger than
/// READY_CACHE, or a fresh read bounded by READY_PROBE_TIMEOUT. While
/// one probe is running, other callers get the last answer.
pub async fn is_data_store_ready(&self) -> bool {
let store = &self.core.storage.data;
if store.is_none() {
return false;
}
let health = &self.inner.data.store_health;
let last = *health.last.lock();
if let Some((at, ready)) = last
&& at.elapsed() < READY_CACHE
{
return ready;
}
if health.probing.swap(true, Ordering::AcqRel) {
return last.is_none_or(|(_, ready)| ready);
}
let _guard = ProbeGuard(&health.probing);
let ready = tokio::time::timeout(
READY_PROBE_TIMEOUT,
store.get_value::<u64>(ValueKey::from(ValueClass::Property(0))),
)
.await
.is_ok_and(|result| result.is_ok());
// Say so once per outage, not on every probe
if !ready && last.is_none_or(|(_, ready)| ready) {
trc::event!(
Store(trc::StoreEvent::UnexpectedError),
Details = "Readiness probe: the data store didn't answer",
Limit = READY_PROBE_TIMEOUT,
);
}
*health.last.lock() = Some((Instant::now(), ready));
ready
}
}
+1 -3
View File
@@ -553,10 +553,8 @@ impl ParseHttp for Server {
return Ok(JsonProblemResponse(StatusCode::OK).into_http_response()); return Ok(JsonProblemResponse(StatusCode::OK).into_http_response());
} }
"ready" => { "ready" => {
// inbuxa: ready only while the data store answers
// (a cached, time-limited read); liveness stays 200
return Ok(JsonProblemResponse({ return Ok(JsonProblemResponse({
if self.is_data_store_ready().await { if !self.core.storage.data.is_none() {
StatusCode::OK StatusCode::OK
} else { } else {
StatusCode::SERVICE_UNAVAILABLE StatusCode::SERVICE_UNAVAILABLE
-3
View File
@@ -30,9 +30,6 @@ pub mod s3;
pub mod sqlite; pub mod sqlite;
// inbuxa: scale-out storage (sharded stores) // inbuxa: scale-out storage (sharded stores)
pub mod scaleout; pub mod scaleout;
// inbuxa: client-side SQL query limits
#[cfg(any(feature = "postgres", feature = "mysql"))]
pub mod query_timeout;
pub const MAX_TOKEN_LENGTH: usize = (u8::MAX >> 1) as usize; pub const MAX_TOKEN_LENGTH: usize = (u8::MAX >> 1) as usize;
+35 -50
View File
@@ -10,7 +10,7 @@ use std::ops::Range;
use mysql_async::prelude::Queryable; use mysql_async::prelude::Queryable;
use super::{MysqlStore, bounded, into_error}; use super::{MysqlStore, into_error};
impl MysqlStore { impl MysqlStore {
pub(crate) async fn get_blob( pub(crate) async fn get_blob(
@@ -19,63 +19,48 @@ impl MysqlStore {
range: Range<usize>, range: Range<usize>,
) -> trc::Result<Option<Vec<u8>>> { ) -> trc::Result<Option<Vec<u8>>> {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prep("SELECT v FROM t WHERE k = ?")
let s = conn .await
.prep("SELECT v FROM t WHERE k = ?") .map_err(into_error)?;
.await conn.exec_first::<Vec<u8>, _, _>(&s, (key,))
.map_err(into_error)?; .await
conn.exec_first::<Vec<u8>, _, _>(&s, (key,)) .map(|bytes| {
.await if range.start == 0 && range.end == usize::MAX {
.map(|bytes| { bytes
if range.start == 0 && range.end == usize::MAX { } else {
bytes.map(|bytes| {
bytes bytes
} else { .get(range.start..std::cmp::min(bytes.len(), range.end))
bytes.map(|bytes| { .unwrap_or_default()
bytes .to_vec()
.get(range.start..std::cmp::min(bytes.len(), range.end)) })
.unwrap_or_default() }
.to_vec() })
}) .map_err(into_error)
}
})
.map_err(into_error)
})
.await;
bounded(conn, result, limit)
} }
pub(crate) async fn put_blob(&self, key: &[u8], data: &[u8]) -> trc::Result<()> { pub(crate) async fn put_blob(&self, key: &[u8], data: &[u8]) -> trc::Result<()> {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prep("INSERT INTO t (k, v) VALUES (?, ?) ON DUPLICATE KEY UPDATE v = VALUES(v)")
let s = conn .await
.prep("INSERT INTO t (k, v) VALUES (?, ?) ON DUPLICATE KEY UPDATE v = VALUES(v)") .map_err(into_error)?;
.await conn.exec_drop(&s, (key, data))
.map_err(into_error)?; .await
conn.exec_drop(&s, (key, data)) .map_err(into_error)
.await .map(|_| ())
.map_err(into_error)
.map(|_| ())
})
.await;
bounded(conn, result, limit)
} }
pub(crate) async fn delete_blob(&self, key: &[u8]) -> trc::Result<bool> { pub(crate) async fn delete_blob(&self, key: &[u8]) -> trc::Result<bool> {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prep("DELETE FROM t WHERE k = ?")
let s = conn .await
.prep("DELETE FROM t WHERE k = ?") .map_err(into_error)?;
.await conn.exec_iter(&s, (key,))
.map_err(into_error)?; .await
conn.exec_iter(&s, (key,)) .map_err(into_error)
.await .map(|hits| hits.affected_rows() > 0)
.map_err(into_error)
.map(|hits| hits.affected_rows() > 0)
})
.await;
bounded(conn, result, limit)
} }
} }
+21 -26
View File
@@ -10,7 +10,7 @@ use mysql_async::{Params, Row, prelude::Queryable};
use crate::{IntoRows, QueryResult, QueryType, Value}; use crate::{IntoRows, QueryResult, QueryType, Value};
use super::{MysqlStore, bounded, into_error}; use super::{MysqlStore, into_error};
impl MysqlStore { impl MysqlStore {
pub(crate) async fn sql_query<T: QueryResult>( pub(crate) async fn sql_query<T: QueryResult>(
@@ -19,32 +19,27 @@ impl MysqlStore {
params: &[Value<'_>], params: &[Value<'_>],
) -> trc::Result<T> { ) -> trc::Result<T> {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.query; let s = conn.prep(query).await.map_err(into_error)?;
let result = tokio::time::timeout(limit, async { let params = Params::Positional(params.iter().map(Into::into).collect());
let s = conn.prep(query).await.map_err(into_error)?;
let params = Params::Positional(params.iter().map(Into::into).collect());
match T::query_type() { match T::query_type() {
QueryType::Execute => conn.exec_drop(s, params).await.map_or_else( QueryType::Execute => conn.exec_drop(s, params).await.map_or_else(
|e| Err(into_error(e)), |e| Err(into_error(e)),
|_| Ok(T::from_exec(conn.affected_rows() as usize)), |_| Ok(T::from_exec(conn.affected_rows() as usize)),
), ),
QueryType::Exists => conn QueryType::Exists => conn
.exec_first::<Row, _, _>(s, params) .exec_first::<Row, _, _>(s, params)
.await .await
.map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_exists(r.is_some()))), .map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_exists(r.is_some()))),
QueryType::QueryOne => conn QueryType::QueryOne => conn
.exec_first::<Row, _, _>(s, params) .exec_first::<Row, _, _>(s, params)
.await .await
.map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_query_one(r))), .map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_query_one(r))),
QueryType::QueryAll => conn QueryType::QueryAll => conn
.exec::<Row, _, _>(s, params) .exec::<Row, _, _>(s, params)
.await .await
.map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_query_all(r))), .map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_query_all(r))),
} }
})
.await;
bounded(conn, result, limit)
} }
} }
+68 -78
View File
@@ -6,7 +6,7 @@
* Modified by Coffey Labs in 2026 for INBUXA. * Modified by Coffey Labs in 2026 for INBUXA.
*/ */
use super::{MysqlStore, bounded, into_error}; use super::{MysqlStore, into_error};
use crate::{ use crate::{
backend::mysql::MysqlSearchField, backend::mysql::MysqlSearchField,
search::{ search::{
@@ -72,7 +72,6 @@ impl MysqlStore {
.db_name(Some(replica.database.clone())) .db_name(Some(replica.database.clone()))
.tcp_port(replica.port as u16), .tcp_port(replica.port as u16),
), ),
timeouts: Default::default(),
})), })),
replica.host, replica.host,
replica.port as u16, replica.port as u16,
@@ -82,7 +81,6 @@ impl MysqlStore {
let primary = Store::MySQL(Arc::new(MysqlStore { let primary = Store::MySQL(Arc::new(MysqlStore {
conn_pool: Pool::new(opts), conn_pool: Pool::new(opts),
timeouts: Default::default(),
})); }));
// ST-1: no replicas, no change // ST-1: no replicas, no change
@@ -101,96 +99,88 @@ impl MysqlStore {
pub(crate) async fn create_storage_tables(&self) -> trc::Result<()> { pub(crate) async fn create_storage_tables(&self) -> trc::Result<()> {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
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_DIRECTORY,
SUBSPACE_QUEUE_MESSAGE,
SUBSPACE_QUEUE_EVENT,
SUBSPACE_REPORT_OUT,
SUBSPACE_REPORT_IN,
SUBSPACE_LOGS,
SUBSPACE_TELEMETRY_SPAN,
SUBSPACE_TELEMETRY_METRIC,
] {
let table = char::from(table);
conn.query_drop(format!(
"CREATE TABLE IF NOT EXISTS {table} (
k VARBINARY(255) NOT NULL,
v MEDIUMBLOB NOT NULL,
PRIMARY KEY (k)
) ENGINE=InnoDB"
))
.await
.map_err(into_error)?;
}
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_DIRECTORY,
SUBSPACE_QUEUE_MESSAGE,
SUBSPACE_QUEUE_EVENT,
SUBSPACE_REPORT_OUT,
SUBSPACE_REPORT_IN,
SUBSPACE_LOGS,
SUBSPACE_TELEMETRY_SPAN,
SUBSPACE_TELEMETRY_METRIC,
] {
let table = char::from(table);
conn.query_drop(format!( conn.query_drop(format!(
"CREATE TABLE IF NOT EXISTS {} ( "CREATE TABLE IF NOT EXISTS {table} (
k VARBINARY(255) NOT NULL, k VARBINARY(255) NOT NULL,
v LONGBLOB NOT NULL, v MEDIUMBLOB NOT NULL,
PRIMARY KEY (k) PRIMARY KEY (k)
) ENGINE=InnoDB", ) ENGINE=InnoDB"
char::from(SUBSPACE_BLOBS),
)) ))
.await .await
.map_err(into_error)?; .map_err(into_error)?;
}
for table in [SUBSPACE_INDEXES, SUBSPACE_REGISTRY_IDX] { conn.query_drop(format!(
let table = char::from(table); "CREATE TABLE IF NOT EXISTS {} (
conn.query_drop(format!( k VARBINARY(255) NOT NULL,
"CREATE TABLE IF NOT EXISTS {table} ( v LONGBLOB NOT NULL,
k BLOB, PRIMARY KEY (k)
PRIMARY KEY (k(400)) ) ENGINE=InnoDB",
) ENGINE=InnoDB" char::from(SUBSPACE_BLOBS),
)) ))
.await .await
.map_err(into_error)?; .map_err(into_error)?;
}
for table in [SUBSPACE_COUNTER, SUBSPACE_QUOTA, SUBSPACE_IN_MEMORY_COUNTER] { for table in [SUBSPACE_INDEXES, SUBSPACE_REGISTRY_IDX] {
conn.query_drop(format!( let table = char::from(table);
"CREATE TABLE IF NOT EXISTS {} ( conn.query_drop(format!(
k VARBINARY(255) NOT NULL, "CREATE TABLE IF NOT EXISTS {table} (
v BIGINT NOT NULL DEFAULT 0, k BLOB,
PRIMARY KEY (k) PRIMARY KEY (k(400))
) ENGINE=InnoDB", ) ENGINE=InnoDB"
char::from(table) ))
)) .await
.await .map_err(into_error)?;
.map_err(into_error)?; }
}
Ok(()) for table in [SUBSPACE_COUNTER, SUBSPACE_QUOTA, SUBSPACE_IN_MEMORY_COUNTER] {
}) conn.query_drop(format!(
.await; "CREATE TABLE IF NOT EXISTS {} (
bounded(conn, result, limit) k VARBINARY(255) NOT NULL,
v BIGINT NOT NULL DEFAULT 0,
PRIMARY KEY (k)
) ENGINE=InnoDB",
char::from(table)
))
.await
.map_err(into_error)?;
}
Ok(())
} }
pub(crate) async fn create_search_tables(&self) -> trc::Result<()> { pub(crate) async fn create_search_tables(&self) -> trc::Result<()> {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.maintenance;
let result = tokio::time::timeout(limit, async {
create_search_tables::<EmailSearchField>(&mut conn).await?;
create_search_tables::<CalendarSearchField>(&mut conn).await?;
create_search_tables::<ContactSearchField>(&mut conn).await?;
//create_search_tables::<FileSearchField>(&mut conn).await?;
create_search_tables::<TracingSearchField>(&mut conn).await?;
Ok(()) create_search_tables::<EmailSearchField>(&mut conn).await?;
}) create_search_tables::<CalendarSearchField>(&mut conn).await?;
.await; create_search_tables::<ContactSearchField>(&mut conn).await?;
bounded(conn, result, limit) //create_search_tables::<FileSearchField>(&mut conn).await?;
create_search_tables::<TracingSearchField>(&mut conn).await?;
Ok(())
} }
} }
+1 -41
View File
@@ -6,7 +6,6 @@
* Modified by Coffey Labs in 2026 for INBUXA. * Modified by Coffey Labs in 2026 for INBUXA.
*/ */
use crate::backend::query_timeout::QueryTimeouts;
use crate::{ use crate::{
search::{ search::{
CalendarSearchField, ContactSearchField, EmailSearchField, FileSearchField, SearchField, CalendarSearchField, ContactSearchField, EmailSearchField, FileSearchField, SearchField,
@@ -15,7 +14,7 @@ use crate::{
write::SearchIndex, write::SearchIndex,
}; };
use mysql_async::Pool; use mysql_async::Pool;
use std::{fmt::Display, time::Duration}; use std::fmt::Display;
pub mod blob; pub mod blob;
pub mod lookup; pub mod lookup;
@@ -26,8 +25,6 @@ pub mod write;
pub struct MysqlStore { pub struct MysqlStore {
pub(crate) conn_pool: Pool, pub(crate) conn_pool: Pool,
/// inbuxa: client-side query limits (see backend::query_timeout)
pub(crate) timeouts: QueryTimeouts,
} }
/// inbuxa: how long a request waits for a pooled connection (including /// inbuxa: how long a request waits for a pooled connection (including
@@ -57,43 +54,6 @@ pub(crate) async fn pool_conn(
} }
} }
/// inbuxa: the error for an operation that ran past its time limit.
pub(crate) fn query_timeout_error(limit: Duration) -> trc::Error {
trc::StoreEvent::MysqlError
.reason("Query timed out")
.details(format!(
"No answer from the database within {} s",
limit.as_secs()
))
}
/// inbuxa: ends an operation run on `conn` under `limit`. When it ran out,
/// the connection is closed rather than returned to the pool: a query may
/// still be in flight on it, or a transaction open. Conn::disconnect marks
/// the connection closed before it sends anything, so even when the server
/// doesn't answer and the attempt is dropped, the pool discards it instead
/// of waiting to clean it up.
pub(crate) fn bounded<T>(
conn: mysql_async::Conn,
result: Result<trc::Result<T>, tokio::time::error::Elapsed>,
limit: Duration,
) -> trc::Result<T> {
match result {
Ok(result) => result,
Err(_) => {
discard(conn);
Err(query_timeout_error(limit))
}
}
}
/// inbuxa: closes a connection whose state is unknown (see bounded).
pub(crate) fn discard(conn: mysql_async::Conn) {
tokio::spawn(async move {
let _ = tokio::time::timeout(Duration::from_secs(1), conn.disconnect()).await;
});
}
#[inline(always)] #[inline(always)]
pub(crate) fn into_error(err: impl Display) -> trc::Error { pub(crate) fn into_error(err: impl Display) -> trc::Error {
trc::StoreEvent::MysqlError.reason(err) trc::StoreEvent::MysqlError.reason(err)
+66 -109
View File
@@ -6,7 +6,7 @@
* Modified by Coffey Labs in 2026 for INBUXA. * Modified by Coffey Labs in 2026 for INBUXA.
*/ */
use super::{MysqlStore, bounded, discard, into_error, is_timeout_error, query_timeout_error}; use super::{MysqlStore, into_error, is_timeout_error};
use crate::{Deserialize, IterateParams, Key, ValueKey, write::ValueClass}; use crate::{Deserialize, IterateParams, Key, ValueKey, write::ValueClass};
use futures::TryStreamExt; use futures::TryStreamExt;
use mysql_async::{Row, prelude::Queryable}; use mysql_async::{Row, prelude::Queryable};
@@ -17,50 +17,40 @@ impl MysqlStore {
U: Deserialize + 'static, U: Deserialize + 'static,
{ {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prep(format!(
let s = conn "SELECT v FROM {} WHERE k = ?",
.prep(format!( char::from(key.subspace())
"SELECT v FROM {} WHERE k = ?", ))
char::from(key.subspace()) .await
)) .map_err(into_error)?;
.await let key = key.serialize(0);
.map_err(into_error)?; conn.exec_first::<Vec<u8>, _, _>(&s, (&key,))
let key = key.serialize(0); .await
conn.exec_first::<Vec<u8>, _, _>(&s, (&key,)) .map_err(into_error)
.await .and_then(|r| {
.map_err(into_error) if let Some(r) = r {
.and_then(|r| { Ok(Some(U::deserialize_owned_with_key(&key, r)?))
if let Some(r) = r { } else {
Ok(Some(U::deserialize_owned_with_key(&key, r)?)) Ok(None)
} else { }
Ok(None) })
}
})
})
.await;
bounded(conn, result, limit)
} }
pub(crate) async fn key_exists(&self, key: impl Key) -> trc::Result<bool> { pub(crate) async fn key_exists(&self, key: impl Key) -> trc::Result<bool> {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prep(format!(
let s = conn "SELECT 1 FROM {} WHERE k = ?",
.prep(format!( char::from(key.subspace())
"SELECT 1 FROM {} WHERE k = ?", ))
char::from(key.subspace()) .await
)) .map_err(into_error)?;
.await let key = key.serialize(0);
.map_err(into_error)?; conn.exec_first::<u8, _, _>(&s, (&key,))
let key = key.serialize(0); .await
conn.exec_first::<u8, _, _>(&s, (&key,)) .map_err(into_error)
.await .map(|r| r.is_some())
.map_err(into_error)
.map(|r| r.is_some())
})
.await;
bounded(conn, result, limit)
} }
pub(crate) async fn iterate<T: Key>( pub(crate) async fn iterate<T: Key>(
@@ -74,36 +64,28 @@ impl MysqlStore {
let end = params.end.serialize(0); let end = params.end.serialize(0);
let keys = if params.values { "k, v" } else { "k" }; let keys = if params.values { "k, v" } else { "k" };
// inbuxa: a scan may run for hours, so the query limit bounds each let s = conn
// wait for the database (preparing, the query starting, the next .prep(&match (params.first, params.ascending) {
// row) rather than the scan. A wait that runs out closes the (true, true) => {
// connection. format!(
let limit = self.timeouts.query; "SELECT {keys} FROM {table} WHERE k >= ? AND k <= ? ORDER BY k ASC LIMIT 1"
let query = match (params.first, params.ascending) { )
(true, true) => { }
format!("SELECT {keys} FROM {table} WHERE k >= ? AND k <= ? ORDER BY k ASC LIMIT 1") (true, false) => {
} format!(
(true, false) => { "SELECT {keys} FROM {table} WHERE k >= ? AND k <= ? ORDER BY k DESC LIMIT 1"
format!( )
"SELECT {keys} FROM {table} WHERE k >= ? AND k <= ? ORDER BY k DESC LIMIT 1" }
) (false, true) => {
} format!("SELECT {keys} FROM {table} WHERE k >= ? AND k <= ? ORDER BY k ASC")
(false, true) => { }
format!("SELECT {keys} FROM {table} WHERE k >= ? AND k <= ? ORDER BY k ASC") (false, false) => {
} format!("SELECT {keys} FROM {table} WHERE k >= ? AND k <= ? ORDER BY k DESC")
(false, false) => { }
format!("SELECT {keys} FROM {table} WHERE k >= ? AND k <= ? ORDER BY k DESC") })
} .await
}; .map_err(into_error)?;
let s = match tokio::time::timeout(limit, conn.prep(&query)).await {
Ok(s) => s.map_err(into_error)?,
Err(_) => {
discard(conn);
return Err(query_timeout_error(limit));
}
};
let mut from = begin; let mut from = begin;
let mut stalled = false;
let mut to = end; let mut to = end;
let mut resume_key = None; let mut resume_key = None;
@@ -112,26 +94,13 @@ impl MysqlStore {
let mut timed_out = false; let mut timed_out = false;
{ {
let mut rows = match tokio::time::timeout( let mut rows = conn
limit, .exec_stream::<Row, _, _>(&s, (from.clone(), to.clone()))
conn.exec_stream::<Row, _, _>(&s, (from.clone(), to.clone())), .await
) .map_err(into_error)?;
.await
{
Ok(rows) => rows.map_err(into_error)?,
// Leaves the scan loop for the timeout below
Err(_) => break,
};
loop { loop {
let next = match tokio::time::timeout(limit, rows.try_next()).await { match rows.try_next().await {
Ok(next) => next,
Err(_) => {
stalled = true;
break;
}
};
match next {
Ok(Some(mut row)) => { Ok(Some(mut row)) => {
let value = if params.values { let value = if params.values {
row.take_opt::<Vec<u8>, _>(1) row.take_opt::<Vec<u8>, _>(1)
@@ -167,10 +136,6 @@ impl MysqlStore {
} }
} }
if stalled {
break;
}
match last_key { match last_key {
Some(last_key) if timed_out => { Some(last_key) if timed_out => {
if params.ascending { if params.ascending {
@@ -183,9 +148,6 @@ impl MysqlStore {
_ => return Ok(()), _ => return Ok(()),
} }
} }
discard(conn);
Err(query_timeout_error(limit))
} }
pub(crate) async fn get_counter( pub(crate) async fn get_counter(
@@ -196,19 +158,14 @@ impl MysqlStore {
let table = char::from(key.subspace()); let table = char::from(key.subspace());
let key = key.serialize(0); let key = key.serialize(0);
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prep(format!("SELECT v FROM {table} WHERE k = ?"))
let s = conn .await
.prep(format!("SELECT v FROM {table} WHERE k = ?")) .map_err(into_error)?;
.await match conn.exec_first::<i64, _, _>(&s, (key,)).await {
.map_err(into_error)?; Ok(Some(num)) => Ok(num),
match conn.exec_first::<i64, _, _>(&s, (key,)).await { Ok(None) => Ok(0),
Ok(Some(num)) => Ok(num), Err(e) => Err(into_error(e)),
Ok(None) => Ok(0), }
Err(e) => Err(into_error(e)),
}
})
.await;
bounded(conn, result, limit)
} }
} }
+79 -96
View File
@@ -10,8 +10,8 @@ use crate::{
backend::{ backend::{
MAX_TOKEN_LENGTH, MAX_TOKEN_LENGTH,
mysql::{ mysql::{
DELETE_CHUNK_SIZE, MIN_DELETE_CHUNK_SIZE, MysqlSearchField, MysqlStore, bounded, DELETE_CHUNK_SIZE, MIN_DELETE_CHUNK_SIZE, MysqlSearchField, MysqlStore, into_error,
into_error, is_timeout_error, is_timeout_error,
}, },
}, },
search::{ search::{
@@ -27,62 +27,57 @@ use std::fmt::Write;
impl MysqlStore { impl MysqlStore {
pub async fn index(&self, documents: Vec<IndexDocument>) -> trc::Result<()> { pub async fn index(&self, documents: Vec<IndexDocument>) -> trc::Result<()> {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.query; let mut tx_opts = TxOpts::default();
let result = tokio::time::timeout(limit, async { tx_opts
let mut tx_opts = TxOpts::default(); .with_consistent_snapshot(false)
tx_opts .with_isolation_level(IsolationLevel::ReadCommitted);
.with_consistent_snapshot(false) let mut trx = conn.start_transaction(tx_opts).await.map_err(into_error)?;
.with_isolation_level(IsolationLevel::ReadCommitted);
let mut trx = conn.start_transaction(tx_opts).await.map_err(into_error)?;
for document in documents { for document in documents {
let index = document.index; let index = document.index;
let primary_keys = index.primary_keys(); let primary_keys = index.primary_keys();
let all_fields = index.all_fields(); let all_fields = index.all_fields();
let mut fields = document.fields; let mut fields = document.fields;
let mut values = Vec::with_capacity(fields.len() + 2); let mut values = Vec::with_capacity(fields.len() + 2);
let mut query = format!("INSERT INTO {} (", index.mysql_table()); let mut query = format!("INSERT INTO {} (", index.mysql_table());
for (i, field) in primary_keys.iter().chain(all_fields).enumerate() { for (i, field) in primary_keys.iter().chain(all_fields).enumerate() {
if i > 0 { if i > 0 {
query.push(','); query.push(',');
}
query.push_str(field.column());
} }
query.push_str(field.column());
query.push_str(") VALUES (");
for (i, field) in primary_keys.iter().chain(all_fields).enumerate() {
if i > 0 {
query.push(',');
}
if let Some(value) = fields.remove(field) {
query.push('?');
values.push(value);
} else {
query.push_str("NULL");
}
}
query.push_str(") ON DUPLICATE KEY UPDATE ");
for (i, field) in all_fields.iter().enumerate() {
if i > 0 {
query.push(',');
}
let column = field.column();
let _ = write!(&mut query, "{column} = VALUES({column})");
}
let s = trx.prep(&query).await.map_err(into_error)?;
trx.exec_drop(&s, values).await.map_err(into_error)?;
} }
trx.commit().await.map_err(into_error) query.push_str(") VALUES (");
})
.await; for (i, field) in primary_keys.iter().chain(all_fields).enumerate() {
bounded(conn, result, limit) if i > 0 {
query.push(',');
}
if let Some(value) = fields.remove(field) {
query.push('?');
values.push(value);
} else {
query.push_str("NULL");
}
}
query.push_str(") ON DUPLICATE KEY UPDATE ");
for (i, field) in all_fields.iter().enumerate() {
if i > 0 {
query.push(',');
}
let column = field.column();
let _ = write!(&mut query, "{column} = VALUES({column})");
}
let s = trx.prep(&query).await.map_err(into_error)?;
trx.exec_drop(&s, values).await.map_err(into_error)?;
}
trx.commit().await.map_err(into_error)
} }
pub async fn query<R: SearchDocumentId>( pub async fn query<R: SearchDocumentId>(
@@ -102,17 +97,12 @@ impl MysqlStore {
} }
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.query; let s = conn.prep(query).await.map_err(into_error)?;
let result = tokio::time::timeout(limit, async {
let s = conn.prep(query).await.map_err(into_error)?;
conn.exec::<i64, _, _>(s, params) conn.exec::<i64, _, _>(s, params)
.await .await
.map(|r| r.into_iter().map(|r| R::from_u64(r as u64)).collect()) .map(|r| r.into_iter().map(|r| R::from_u64(r as u64)).collect())
.map_err(into_error) .map_err(into_error)
})
.await;
bounded(conn, result, limit)
} }
pub async fn unindex(&self, filter: SearchQuery) -> trc::Result<u64> { pub async fn unindex(&self, filter: SearchQuery) -> trc::Result<u64> {
@@ -121,47 +111,40 @@ impl MysqlStore {
let params = build_filter(&mut query, &filter.filters); let params = build_filter(&mut query, &filter.filters);
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.maintenance; let s = conn.prep(&query).await.map_err(into_error)?;
let result = tokio::time::timeout(limit, async {
let s = conn.prep(&query).await.map_err(into_error)?;
match conn.exec_drop(s, params.clone()).await { match conn.exec_drop(s, params.clone()).await {
Ok(_) => return Ok(conn.affected_rows()), Ok(_) => return Ok(conn.affected_rows()),
Err(err) if is_timeout_error(&err) => (), Err(err) if is_timeout_error(&err) => (),
Err(err) => return Err(into_error(err)), Err(err) => return Err(into_error(err)),
} }
let mut chunk_size = DELETE_CHUNK_SIZE; let mut chunk_size = DELETE_CHUNK_SIZE;
let mut deleted = 0; let mut deleted = 0;
loop {
let s = conn
.prep(format!("{query} LIMIT {chunk_size}"))
.await
.map_err(into_error)?;
loop { loop {
let s = conn match conn.exec_drop(&s, params.clone()).await {
.prep(format!("{query} LIMIT {chunk_size}")) Ok(_) => {
.await let affected = conn.affected_rows();
.map_err(into_error)?; if affected == 0 {
return Ok(deleted);
loop {
match conn.exec_drop(&s, params.clone()).await {
Ok(_) => {
let affected = conn.affected_rows();
if affected == 0 {
return Ok(deleted);
}
deleted += affected;
} }
Err(err) deleted += affected;
if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE =>
{
chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
break;
}
Err(err) => return Err(into_error(err)),
} }
Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
break;
}
Err(err) => return Err(into_error(err)),
} }
} }
}) }
.await;
bounded(conn, result, limit)
} }
} }
+81 -97
View File
@@ -6,9 +6,7 @@
* Modified by Coffey Labs in 2026 for INBUXA. * Modified by Coffey Labs in 2026 for INBUXA.
*/ */
use super::{ use super::{DELETE_CHUNK_SIZE, MIN_DELETE_CHUNK_SIZE, MysqlStore, into_error, is_timeout_error};
DELETE_CHUNK_SIZE, MIN_DELETE_CHUNK_SIZE, MysqlStore, bounded, into_error, is_timeout_error,
};
use crate::{ use crate::{
IndexKey, Key, LogKey, SUBSPACE_COUNTER, SUBSPACE_IN_MEMORY_COUNTER, SUBSPACE_QUOTA, IndexKey, Key, LogKey, SUBSPACE_COUNTER, SUBSPACE_IN_MEMORY_COUNTER, SUBSPACE_QUOTA,
SUBSPACE_REGISTRY_IDX, SUBSPACE_REGISTRY_IDX,
@@ -34,45 +32,41 @@ impl MysqlStore {
let start = Instant::now(); let start = Instant::now();
let mut retry_count = 0; let mut retry_count = 0;
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.query;
let result = tokio::time::timeout(limit, async {
loop {
let err = match self.write_trx(&mut conn, &mut batch).await {
Ok(result) => {
return Ok(result);
}
Err(err) => err,
};
let _ = conn.query_drop("ROLLBACK;").await; loop {
let err = match self.write_trx(&mut conn, &mut batch).await {
match err { Ok(result) => {
CommitError::Mysql(Error::Server(err)) return Ok(result);
if [1062, 1213].contains(&err.code)
&& retry_count < MAX_COMMIT_ATTEMPTS
&& start.elapsed() < MAX_COMMIT_TIME => {}
/*CommitError::Retry => {
if retry_count > MAX_COMMIT_ATTEMPTS || start.elapsed() > MAX_COMMIT_TIME {
return Err(trc::StoreEvent::AssertValueFailed
.into_err()
.caused_by(trc::location!()));
}
}*/
CommitError::Mysql(err) => {
return Err(into_error(err));
}
CommitError::Internal(err) => {
return Err(err);
}
} }
Err(err) => err,
};
let backoff = rand::rng().random_range(50..=300); let _ = conn.query_drop("ROLLBACK;").await;
tokio::time::sleep(Duration::from_millis(backoff)).await;
retry_count += 1; match err {
CommitError::Mysql(Error::Server(err))
if [1062, 1213].contains(&err.code)
&& retry_count < MAX_COMMIT_ATTEMPTS
&& start.elapsed() < MAX_COMMIT_TIME => {}
/*CommitError::Retry => {
if retry_count > MAX_COMMIT_ATTEMPTS || start.elapsed() > MAX_COMMIT_TIME {
return Err(trc::StoreEvent::AssertValueFailed
.into_err()
.caused_by(trc::location!()));
}
}*/
CommitError::Mysql(err) => {
return Err(into_error(err));
}
CommitError::Internal(err) => {
return Err(err);
}
} }
})
.await; let backoff = rand::rng().random_range(50..=300);
bounded(conn, result, limit) tokio::time::sleep(Duration::from_millis(backoff)).await;
retry_count += 1;
}
} }
async fn write_trx( async fn write_trx(
@@ -391,81 +385,71 @@ impl MysqlStore {
pub(crate) async fn purge_store(&self) -> trc::Result<()> { pub(crate) async fn purge_store(&self) -> trc::Result<()> {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.maintenance; for subspace in [SUBSPACE_QUOTA, SUBSPACE_COUNTER, SUBSPACE_IN_MEMORY_COUNTER] {
let result = tokio::time::timeout(limit, async { purge_table(&mut conn, char::from(subspace)).await?;
for subspace in [SUBSPACE_QUOTA, SUBSPACE_COUNTER, SUBSPACE_IN_MEMORY_COUNTER] { }
purge_table(&mut conn, char::from(subspace)).await?;
}
Ok(()) Ok(())
})
.await;
bounded(conn, result, limit)
} }
pub(crate) async fn delete_range(&self, from: impl Key, to: impl Key) -> trc::Result<()> { pub(crate) async fn delete_range(&self, from: impl Key, to: impl Key) -> trc::Result<()> {
let mut conn = self.conn().await?; let mut conn = self.conn().await?;
let limit = self.timeouts.maintenance; let table = char::from(from.subspace());
let result = tokio::time::timeout(limit, async { let mut from = from.serialize(0);
let table = char::from(from.subspace()); let to = to.serialize(0);
let mut from = from.serialize(0);
let to = to.serialize(0);
let delete = conn let delete = conn
.prep(format!("DELETE FROM {table} WHERE k >= ? AND k < ?")) .prep(format!("DELETE FROM {table} WHERE k >= ? AND k < ?"))
.await
.map_err(into_error)?;
match conn.exec_drop(&delete, (&from, &to)).await {
Ok(_) => return Ok(()),
Err(err) if is_timeout_error(&err) => (),
Err(err) => return Err(into_error(err)),
}
let mut chunk_size = DELETE_CHUNK_SIZE;
loop {
let boundary = conn
.prep(format!(
"SELECT k FROM {table} WHERE k >= ? AND k < ? ORDER BY k ASC LIMIT 1 OFFSET {chunk_size}"
))
.await .await
.map_err(into_error)?; .map_err(into_error)?;
match conn.exec_drop(&delete, (&from, &to)).await {
Ok(_) => return Ok(()),
Err(err) if is_timeout_error(&err) => (),
Err(err) => return Err(into_error(err)),
}
let mut chunk_size = DELETE_CHUNK_SIZE;
loop { loop {
let boundary = conn let next = match conn
.prep(format!( .exec_first::<Vec<u8>, _, _>(&boundary, (&from, &to))
"SELECT k FROM {table} WHERE k >= ? AND k < ? ORDER BY k ASC LIMIT 1 OFFSET {chunk_size}"
))
.await .await
.map_err(into_error)?; {
Ok(next) => next,
loop { Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
let next = match conn chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
.exec_first::<Vec<u8>, _, _>(&boundary, (&from, &to)) break;
.await
{
Ok(next) => next,
Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
break;
}
Err(err) => return Err(into_error(err)),
};
match conn
.exec_drop(&delete, (&from, next.as_ref().unwrap_or(&to)))
.await
{
Ok(_) => (),
Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
break;
}
Err(err) => return Err(into_error(err)),
} }
Err(err) => return Err(into_error(err)),
};
match next { match conn
Some(next) => from = next, .exec_drop(&delete, (&from, next.as_ref().unwrap_or(&to)))
None => return Ok(()), .await
{
Ok(_) => (),
Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
break;
} }
Err(err) => return Err(into_error(err)),
}
match next {
Some(next) => from = next,
None => return Ok(()),
} }
} }
}) }
.await;
bounded(conn, result, limit)
} }
} }
+40 -57
View File
@@ -2,15 +2,13 @@
* SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]> * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
* *
* SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
*
* Modified by Coffey Labs in 2026 for INBUXA.
*/ */
use std::ops::Range; use std::ops::Range;
use crate::backend::postgres::into_pool_error; use crate::backend::postgres::into_pool_error;
use super::{PostgresStore, bounded, into_error}; use super::{PostgresStore, into_error};
impl PostgresStore { impl PostgresStore {
pub(crate) async fn get_blob( pub(crate) async fn get_blob(
@@ -19,68 +17,53 @@ impl PostgresStore {
range: Range<usize>, range: Range<usize>,
) -> trc::Result<Option<Vec<u8>>> { ) -> trc::Result<Option<Vec<u8>>> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prepare_cached("SELECT v FROM t WHERE k = $1")
let s = conn .await
.prepare_cached("SELECT v FROM t WHERE k = $1") .map_err(into_error)?;
.await conn.query_opt(&s, &[&key])
.map_err(into_error)?; .await
conn.query_opt(&s, &[&key]) .and_then(|row| {
.await if let Some(row) = row {
.and_then(|row| { Ok(Some(if range.start == 0 && range.end == usize::MAX {
if let Some(row) = row { row.try_get::<_, Vec<u8>>(0)?
Ok(Some(if range.start == 0 && range.end == usize::MAX {
row.try_get::<_, Vec<u8>>(0)?
} else {
let bytes = row.try_get::<_, &[u8]>(0)?;
bytes
.get(range.start..std::cmp::min(bytes.len(), range.end))
.unwrap_or_default()
.to_vec()
}))
} else { } else {
Ok(None) let bytes = row.try_get::<_, &[u8]>(0)?;
} bytes
}) .get(range.start..std::cmp::min(bytes.len(), range.end))
.map_err(into_error) .unwrap_or_default()
}) .to_vec()
.await; }))
bounded(conn, result, limit) } else {
Ok(None)
}
})
.map_err(into_error)
} }
pub(crate) async fn put_blob(&self, key: &[u8], data: &[u8]) -> trc::Result<()> { pub(crate) async fn put_blob(&self, key: &[u8], data: &[u8]) -> trc::Result<()> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prepare_cached(
let s = conn "INSERT INTO t (k, v) VALUES ($1, $2) ON CONFLICT (k) DO UPDATE SET v = EXCLUDED.v",
.prepare_cached( )
"INSERT INTO t (k, v) VALUES ($1, $2) ON CONFLICT (k) DO UPDATE SET v = EXCLUDED.v", .await
) .map_err(into_error)?;
.await conn.execute(&s, &[&key, &data])
.map_err(into_error)?; .await
conn.execute(&s, &[&key, &data]) .map_err(into_error)
.await .map(|_| ())
.map_err(into_error)
.map(|_| ())
})
.await;
bounded(conn, result, limit)
} }
pub(crate) async fn delete_blob(&self, key: &[u8]) -> trc::Result<bool> { pub(crate) async fn delete_blob(&self, key: &[u8]) -> trc::Result<bool> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prepare_cached("DELETE FROM t WHERE k = $1")
let s = conn .await
.prepare_cached("DELETE FROM t WHERE k = $1") .map_err(into_error)?;
.await conn.execute(&s, &[&key])
.map_err(into_error)?; .await
conn.execute(&s, &[&key]) .map_err(into_error)
.await .map(|hits| hits > 0)
.map_err(into_error)
.map(|hits| hits > 0)
})
.await;
bounded(conn, result, limit)
} }
} }
+25 -32
View File
@@ -2,8 +2,6 @@
* SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]> * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
* *
* SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
*
* Modified by Coffey Labs in 2026 for INBUXA.
*/ */
use crate::{QueryResult, QueryType, backend::postgres::into_pool_error}; use crate::{QueryResult, QueryType, backend::postgres::into_pool_error};
@@ -14,7 +12,7 @@ use tokio_postgres::types::{FromSql, ToSql, Type};
use crate::IntoRows; use crate::IntoRows;
use super::{PostgresStore, bounded, into_error}; use super::{PostgresStore, into_error};
impl PostgresStore { impl PostgresStore {
pub(crate) async fn sql_query<T: QueryResult>( pub(crate) async fn sql_query<T: QueryResult>(
@@ -23,38 +21,33 @@ impl PostgresStore {
params_: &[crate::Value<'_>], params_: &[crate::Value<'_>],
) -> trc::Result<T> { ) -> trc::Result<T> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.query; let s = conn.prepare_cached(query).await.map_err(into_error)?;
let result = tokio::time::timeout(limit, async { let params = params_
let s = conn.prepare_cached(query).await.map_err(into_error)?; .iter()
let params = params_ .map(|v| v as &(dyn tokio_postgres::types::ToSql + Sync))
.iter() .collect::<Vec<_>>();
.map(|v| v as &(dyn tokio_postgres::types::ToSql + Sync))
.collect::<Vec<_>>();
match T::query_type() { match T::query_type() {
QueryType::Execute => conn QueryType::Execute => conn
.execute(&s, params.as_slice()) .execute(&s, params.as_slice())
.await
.map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_exec(r as usize))),
QueryType::Exists => {
let rows = conn.query_raw(&s, params).await.map_err(into_error)?;
pin_mut!(rows);
rows.try_next()
.await .await
.map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_exec(r as usize))), .map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_exists(r.is_some())))
QueryType::Exists => {
let rows = conn.query_raw(&s, params).await.map_err(into_error)?;
pin_mut!(rows);
rows.try_next()
.await
.map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_exists(r.is_some())))
}
QueryType::QueryOne => conn
.query_opt(&s, params.as_slice())
.await
.map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_query_one(r))),
QueryType::QueryAll => conn
.query(&s, params.as_slice())
.await
.map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_query_all(r))),
} }
}) QueryType::QueryOne => conn
.await; .query_opt(&s, params.as_slice())
bounded(conn, result, limit) .await
.map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_query_one(r))),
QueryType::QueryAll => conn
.query(&s, params.as_slice())
.await
.map_or_else(|e| Err(into_error(e)), |r| Ok(T::from_query_all(r))),
}
} }
} }
+72 -154
View File
@@ -6,7 +6,7 @@
* Modified by Coffey Labs in 2026 for INBUXA. * Modified by Coffey Labs in 2026 for INBUXA.
*/ */
use super::{PostgresStore, bounded, into_error}; use super::{PostgresStore, into_error};
use crate::{ use crate::{
backend::postgres::{ backend::postgres::{
PsqlSearchField, into_pool_error, PsqlSearchField, into_pool_error,
@@ -119,7 +119,6 @@ impl PostgresStore {
Store::PostgreSQL(Arc::new(PostgresStore { Store::PostgreSQL(Arc::new(PostgresStore {
conn_pool: pool, conn_pool: pool,
ts_configs: ts_configs.clone(), ts_configs: ts_configs.clone(),
timeouts: Default::default(),
})), })),
replica.host, replica.host,
replica.port as u16, replica.port as u16,
@@ -130,7 +129,6 @@ impl PostgresStore {
let primary = Store::PostgreSQL(Arc::new(PostgresStore { let primary = Store::PostgreSQL(Arc::new(PostgresStore {
conn_pool: primary_pool, conn_pool: primary_pool,
ts_configs, ts_configs,
timeouts: Default::default(),
})); }));
// ST-1: no replicas, no change // ST-1: no replicas, no change
@@ -149,92 +147,84 @@ impl PostgresStore {
pub(crate) async fn create_storage_tables(&self) -> trc::Result<()> { pub(crate) async fn create_storage_tables(&self) -> trc::Result<()> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; 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] { for table in [
let table = char::from(table); SUBSPACE_ACL,
conn.execute( SUBSPACE_TASK_QUEUE,
&format!( SUBSPACE_DELETED_ITEMS,
"CREATE TABLE IF NOT EXISTS {table} ( SUBSPACE_SPAM_SAMPLES,
k BYTEA PRIMARY KEY crate::SUBSPACE_INBUXA, // inbuxa: masked email
)" SUBSPACE_BLOB_LINK,
), SUBSPACE_IN_MEMORY_VALUE,
&[], SUBSPACE_PROPERTY,
) SUBSPACE_REGISTRY,
.await SUBSPACE_REGISTRY_PK,
.map_err(into_error)?; SUBSPACE_QUEUE_MESSAGE,
} SUBSPACE_QUEUE_EVENT,
SUBSPACE_REPORT_OUT,
for table in [SUBSPACE_COUNTER, SUBSPACE_QUOTA, SUBSPACE_IN_MEMORY_COUNTER] { SUBSPACE_REPORT_IN,
conn.execute( SUBSPACE_LOGS,
&format!( SUBSPACE_BLOBS,
"CREATE TABLE IF NOT EXISTS {} ( 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, k BYTEA PRIMARY KEY,
v BIGINT NOT NULL DEFAULT 0 v BYTEA NOT NULL
)", )"
char::from(table) ),
), &[],
&[], )
) .await
.await .map_err(into_error)?;
.map_err(into_error)?; }
}
Ok(()) for table in [SUBSPACE_INDEXES, SUBSPACE_REGISTRY_IDX] {
}) let table = char::from(table);
.await; conn.execute(
bounded(conn, result, limit) &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(())
} }
pub(crate) async fn create_search_tables(&self) -> trc::Result<()> { pub(crate) async fn create_search_tables(&self) -> trc::Result<()> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; 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(()) create_search_tables::<EmailSearchField>(&conn).await?;
}) create_search_tables::<CalendarSearchField>(&conn).await?;
.await; create_search_tables::<ContactSearchField>(&conn).await?;
bounded(conn, result, limit) //create_search_tables::<FileSearchField>(&conn).await?;
create_search_tables::<TracingSearchField>(&conn).await?;
Ok(())
} }
} }
@@ -275,21 +265,12 @@ async fn create_search_tables<T: SearchableField + PsqlSearchField + 'static>(
for field in T::all_fields() { for field in T::all_fields() {
if field.is_text() || field.is_json() { if field.is_text() || field.is_json() {
let column_name = field.column(); 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!( let create_index_query = format!(
"CREATE INDEX IF NOT EXISTS {index_name} ON {table_name} USING GIN({column_name}) WITH (fastupdate = off)", "CREATE INDEX IF NOT EXISTS gin_{table_name}_{column_name} ON {table_name} USING GIN({column_name})",
); );
conn.execute(&create_index_query, &[]) conn.execute(&create_index_query, &[])
.await .await
.map_err(into_error)?; .map_err(into_error)?;
// Indexes made before this change keep fastupdate=on
disable_gin_fastupdate(conn, &index_name).await;
} }
if field.is_indexed() { if field.is_indexed() {
@@ -306,69 +287,6 @@ async fn create_search_tables<T: SearchableField + PsqlSearchField + 'static>(
Ok(()) 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> { async fn discover_ts_configs(pool: &Pool) -> AHashSet<&'static str> {
let mut ts_configs = AHashSet::from_iter([PG_FALLBACK_LANG, PG_UNSTEMMED_LANG]); let mut ts_configs = AHashSet::from_iter([PG_FALLBACK_LANG, PG_UNSTEMMED_LANG]);
+1 -33
View File
@@ -6,7 +6,6 @@
* Modified by Coffey Labs in 2026 for INBUXA. * Modified by Coffey Labs in 2026 for INBUXA.
*/ */
use crate::backend::query_timeout::QueryTimeouts;
use crate::{ use crate::{
search::{ search::{
CalendarSearchField, ContactSearchField, EmailSearchField, FileSearchField, SearchField, CalendarSearchField, ContactSearchField, EmailSearchField, FileSearchField, SearchField,
@@ -15,8 +14,7 @@ use crate::{
write::SearchIndex, write::SearchIndex,
}; };
use ahash::AHashSet; use ahash::AHashSet;
use deadpool_postgres::{Object, Pool}; use deadpool_postgres::Pool;
use std::time::Duration;
use tokio_postgres::error::SqlState; use tokio_postgres::error::SqlState;
pub mod blob; pub mod blob;
@@ -30,8 +28,6 @@ pub mod write;
pub struct PostgresStore { pub struct PostgresStore {
pub(crate) conn_pool: Pool, pub(crate) conn_pool: Pool,
pub(crate) ts_configs: AHashSet<&'static str>, pub(crate) ts_configs: AHashSet<&'static str>,
/// inbuxa: client-side query limits (see backend::query_timeout)
pub(crate) timeouts: QueryTimeouts,
} }
#[inline(always)] #[inline(always)]
@@ -76,34 +72,6 @@ pub(crate) fn is_timeout_error(err: &tokio_postgres::Error) -> bool {
}) })
} }
/// inbuxa: the error for an operation that ran past its time limit.
pub(crate) fn query_timeout_error(limit: Duration) -> trc::Error {
trc::StoreEvent::PostgresqlError
.reason("Query timed out")
.details(format!(
"No answer from the database within {} s",
limit.as_secs()
))
}
/// inbuxa: ends an operation run on `conn` under `limit`. When it ran out,
/// the connection is taken out of the pool and closed: a query may still be
/// in flight on it, or a transaction open, so it can't be handed to the
/// next caller.
pub(crate) fn bounded<T>(
conn: Object,
result: Result<trc::Result<T>, tokio::time::error::Elapsed>,
limit: Duration,
) -> trc::Result<T> {
match result {
Ok(result) => result,
Err(_) => {
drop(Object::take(conn));
Err(query_timeout_error(limit))
}
}
}
#[inline(always)] #[inline(always)]
pub(crate) fn into_pool_error(err: deadpool_postgres::PoolError) -> trc::Error { pub(crate) fn into_pool_error(err: deadpool_postgres::PoolError) -> trc::Error {
match err { match err {
+63 -108
View File
@@ -2,11 +2,9 @@
* SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]> * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
* *
* SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
*
* Modified by Coffey Labs in 2026 for INBUXA.
*/ */
use super::{PostgresStore, bounded, into_error, is_timeout_error, query_timeout_error}; use super::{PostgresStore, into_error, is_timeout_error};
use crate::{ use crate::{
Deserialize, IterateParams, Key, ValueKey, backend::postgres::into_pool_error, Deserialize, IterateParams, Key, ValueKey, backend::postgres::into_pool_error,
write::ValueClass, write::ValueClass,
@@ -19,50 +17,40 @@ impl PostgresStore {
U: Deserialize + 'static, U: Deserialize + 'static,
{ {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prepare_cached(&format!(
let s = conn "SELECT v FROM {} WHERE k = $1",
.prepare_cached(&format!( char::from(key.subspace())
"SELECT v FROM {} WHERE k = $1", ))
char::from(key.subspace()) .await
)) .map_err(into_error)?;
.await let key = key.serialize(0);
.map_err(into_error)?; conn.query_opt(&s, &[&key])
let key = key.serialize(0); .await
conn.query_opt(&s, &[&key]) .map_err(into_error)
.await .and_then(|r| {
.map_err(into_error) if let Some(r) = r {
.and_then(|r| { Ok(Some(U::deserialize_with_key(&key, r.get(0))?))
if let Some(r) = r { } else {
Ok(Some(U::deserialize_with_key(&key, r.get(0))?)) Ok(None)
} else { }
Ok(None) })
}
})
})
.await;
bounded(conn, result, limit)
} }
pub(crate) async fn key_exists(&self, key: impl Key) -> trc::Result<bool> { pub(crate) async fn key_exists(&self, key: impl Key) -> trc::Result<bool> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prepare_cached(&format!(
let s = conn "SELECT 1 FROM {} WHERE k = $1",
.prepare_cached(&format!( char::from(key.subspace())
"SELECT 1 FROM {} WHERE k = $1", ))
char::from(key.subspace()) .await
)) .map_err(into_error)?;
.await let key = key.serialize(0);
.map_err(into_error)?; conn.query_opt(&s, &[&key])
let key = key.serialize(0); .await
conn.query_opt(&s, &[&key]) .map_err(into_error)
.await .map(|r| r.is_some())
.map_err(into_error)
.map(|r| r.is_some())
})
.await;
bounded(conn, result, limit)
} }
pub(crate) async fn iterate<T: Key>( pub(crate) async fn iterate<T: Key>(
@@ -76,65 +64,44 @@ impl PostgresStore {
let end = params.end.serialize(0); let end = params.end.serialize(0);
let keys = if params.values { "k, v" } else { "k" }; let keys = if params.values { "k, v" } else { "k" };
// inbuxa: a scan may run for hours, so the query limit bounds each let s = conn
// wait for the database (preparing, the query starting, the next .prepare_cached(&match (params.first, params.ascending) {
// row) rather than the scan. A wait that runs out closes the (true, true) => {
// connection. format!(
let limit = self.timeouts.query; "SELECT {keys} FROM {table} WHERE k >= $1 AND k <= $2 ORDER BY k ASC LIMIT 1"
let query = match (params.first, params.ascending) { )
(true, true) => { }
format!( (true, false) => {
"SELECT {keys} FROM {table} WHERE k >= $1 AND k <= $2 ORDER BY k ASC LIMIT 1" format!(
)
}
(true, false) => {
format!(
"SELECT {keys} FROM {table} WHERE k >= $1 AND k <= $2 ORDER BY k DESC LIMIT 1" "SELECT {keys} FROM {table} WHERE k >= $1 AND k <= $2 ORDER BY k DESC LIMIT 1"
) )
} }
(false, true) => { (false, true) => {
format!("SELECT {keys} FROM {table} WHERE k >= $1 AND k <= $2 ORDER BY k ASC") format!("SELECT {keys} FROM {table} WHERE k >= $1 AND k <= $2 ORDER BY k ASC")
} }
(false, false) => { (false, false) => {
format!("SELECT {keys} FROM {table} WHERE k >= $1 AND k <= $2 ORDER BY k DESC") format!("SELECT {keys} FROM {table} WHERE k >= $1 AND k <= $2 ORDER BY k DESC")
} }
}; })
let s = match tokio::time::timeout(limit, conn.prepare_cached(&query)).await { .await.map_err(into_error)?;
Ok(s) => s.map_err(into_error)?,
Err(_) => {
drop(deadpool_postgres::Object::take(conn));
return Err(query_timeout_error(limit));
}
};
let mut from = begin; let mut from = begin;
let mut to = end; let mut to = end;
let mut resume_key: Option<Vec<u8>> = None; let mut resume_key: Option<Vec<u8>> = None;
let mut stalled = false;
loop { loop {
let mut last_key = None; let mut last_key = None;
let mut timed_out = false; let mut timed_out = false;
{ {
let rows = let rows = conn
match tokio::time::timeout(limit, conn.query_raw(&s, &[&from, &to])).await { .query_raw(&s, &[&from, &to])
Ok(rows) => rows.map_err(into_error)?, .await
// Leaves the scan loop for the timeout below .map_err(into_error)?;
Err(_) => break,
};
pin_mut!(rows); pin_mut!(rows);
loop { loop {
let next = match tokio::time::timeout(limit, rows.try_next()).await { match rows.try_next().await {
Ok(next) => next,
Err(_) => {
stalled = true;
break;
}
};
match next {
Ok(Some(row)) => { Ok(Some(row)) => {
let key = row.try_get::<_, &[u8]>(0).map_err(into_error)?; let key = row.try_get::<_, &[u8]>(0).map_err(into_error)?;
let value = if params.values { let value = if params.values {
@@ -165,10 +132,6 @@ impl PostgresStore {
} }
} }
if stalled {
break;
}
match last_key { match last_key {
Some(last_key) if timed_out => { Some(last_key) if timed_out => {
if params.ascending { if params.ascending {
@@ -181,9 +144,6 @@ impl PostgresStore {
_ => return Ok(()), _ => return Ok(()),
} }
} }
drop(deadpool_postgres::Object::take(conn));
Err(query_timeout_error(limit))
} }
pub(crate) async fn get_counter( pub(crate) async fn get_counter(
@@ -195,19 +155,14 @@ impl PostgresStore {
let key = key.serialize(0); let key = key.serialize(0);
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.query; let s = conn
let result = tokio::time::timeout(limit, async { .prepare_cached(&format!("SELECT v FROM {table} WHERE k = $1"))
let s = conn .await
.prepare_cached(&format!("SELECT v FROM {table} WHERE k = $1")) .map_err(into_error)?;
.await match conn.query_opt(&s, &[&key]).await {
.map_err(into_error)?; Ok(Some(row)) => row.try_get(0).map_err(into_error),
match conn.query_opt(&s, &[&key]).await { Ok(None) => Ok(0),
Ok(Some(row)) => row.try_get(0).map_err(into_error), Err(e) => Err(into_error(e)),
Ok(None) => Ok(0), }
Err(e) => Err(into_error(e)),
}
})
.await;
bounded(conn, result, limit)
} }
} }
+149 -164
View File
@@ -10,8 +10,8 @@ use crate::{
backend::{ backend::{
MAX_TOKEN_LENGTH, MAX_TOKEN_LENGTH,
postgres::{ postgres::{
DELETE_CHUNK_SIZE, MIN_DELETE_CHUNK_SIZE, PostgresStore, PsqlSearchField, bounded, DELETE_CHUNK_SIZE, MIN_DELETE_CHUNK_SIZE, PostgresStore, PsqlSearchField, into_error,
into_error, into_pool_error, is_timeout_error, into_pool_error, is_timeout_error,
}, },
}, },
search::{ search::{
@@ -36,130 +36,125 @@ impl PostgresStore {
pub async fn index(&self, documents: Vec<IndexDocument>) -> trc::Result<()> { pub async fn index(&self, documents: Vec<IndexDocument>) -> trc::Result<()> {
let mut conn = self.conn_pool.get().await.map_err(into_pool_error)?; let mut conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.query; let trx = conn
let result = tokio::time::timeout(limit, async { .build_transaction()
let trx = conn .isolation_level(IsolationLevel::ReadCommitted)
.build_transaction() .start()
.isolation_level(IsolationLevel::ReadCommitted) .await
.start() .map_err(into_error)?;
.await
.map_err(into_error)?;
for document in documents { for document in documents {
let index = document.index; let index = document.index;
let primary_keys = index.primary_keys(); let primary_keys = index.primary_keys();
let all_fields = index.all_fields(); let all_fields = index.all_fields();
let fields = document.fields; let fields = document.fields;
// inbuxa: keyword text (addresses, contact fields, ...) is split into // inbuxa: keyword text (addresses, contact fields, ...) is split into
// words before it reaches the text parser, see keyword_terms(). // words before it reaches the text parser, see keyword_terms().
let keywords = primary_keys let keywords = primary_keys
.iter() .iter()
.chain(all_fields) .chain(all_fields)
.map(|field| match fields.get(field) { .map(|field| match fields.get(field) {
Some(SearchValue::Text { Some(SearchValue::Text {
value, value,
language: Language::None, language: Language::None,
}) if field.is_text() => Some(keyword_terms(value)), }) if field.is_text() => Some(keyword_terms(value)),
_ => None, _ => None,
}) })
.collect::<Vec<_>>(); .collect::<Vec<_>>();
let mut values = Vec::with_capacity(fields.len() + 2); let mut values = Vec::with_capacity(fields.len() + 2);
let mut query = format!("INSERT INTO {} (", index.psql_table()); let mut query = format!("INSERT INTO {} (", index.psql_table());
for (i, field) in primary_keys.iter().chain(all_fields).enumerate() { for (i, field) in primary_keys.iter().chain(all_fields).enumerate() {
if i > 0 { if i > 0 {
query.push(','); query.push(',');
}
query.push_str(field.column());
if let Some(sort_column) = field.sort_column() {
query.push(',');
query.push_str(sort_column);
}
} }
query.push_str(field.column());
query.push_str(") VALUES ("); if let Some(sort_column) = field.sort_column() {
query.push(',');
for (i, field) in primary_keys.iter().chain(all_fields).enumerate() { query.push_str(sort_column);
if i > 0 {
query.push(',');
}
if let Some(value) = fields.get(field) {
let value_ref = format!("${}", values.len() + 1);
let (text_len, language) =
if let SearchValue::Text { value, language } = value {
(value.len(), self.ts_config(language))
} else {
(0, PG_UNSTEMMED_LANG)
};
if let Some(keywords) = &keywords[i] {
let _ = write!(&mut query, "to_tsvector('{language}',{value_ref})");
values.push(keywords as &(dyn ToSql + Sync));
if field.sort_column().is_some() {
let value_ref = format!("${}", values.len() + 1);
if text_len > 255 {
let _ = write!(&mut query, ",left({value_ref},255)");
} else {
let _ = write!(&mut query, ",{value_ref}");
}
values.push(value as &(dyn ToSql + Sync));
}
continue;
} else if field.is_text() {
let _ = write!(&mut query, "to_tsvector('{language}',{value_ref})");
} else if text_len > 512 {
query.push_str("left(");
query.push_str(&value_ref);
query.push_str(",512)");
} else {
query.push_str(&value_ref);
}
if field.sort_column().is_some() {
if text_len > 255 {
query.push_str(",left(");
query.push_str(&value_ref);
query.push_str(",255)");
} else {
query.push(',');
query.push_str(&value_ref);
}
}
values.push(value as &(dyn ToSql + Sync));
} else {
query.push_str("NULL");
if field.sort_column().is_some() {
query.push_str(",NULL");
}
}
} }
query.push_str(") ON CONFLICT (");
for (i, pkey) in primary_keys.iter().enumerate() {
if i > 0 {
query.push(',');
}
query.push_str(pkey.column());
}
query.push_str(") DO UPDATE SET ");
for (i, field) in all_fields.iter().enumerate() {
if i > 0 {
query.push(',');
}
let column = field.column();
let _ = write!(&mut query, "{column} = EXCLUDED.{column}");
}
trx.execute(&query, &values).await.map_err(into_error)?;
} }
trx.commit().await.map_err(into_error) query.push_str(") VALUES (");
})
.await; for (i, field) in primary_keys.iter().chain(all_fields).enumerate() {
bounded(conn, result, limit) if i > 0 {
query.push(',');
}
if let Some(value) = fields.get(field) {
let value_ref = format!("${}", values.len() + 1);
let (text_len, language) = if let SearchValue::Text { value, language } = value
{
(value.len(), self.ts_config(language))
} else {
(0, PG_UNSTEMMED_LANG)
};
if let Some(keywords) = &keywords[i] {
let _ = write!(&mut query, "to_tsvector('{language}',{value_ref})");
values.push(keywords as &(dyn ToSql + Sync));
if field.sort_column().is_some() {
let value_ref = format!("${}", values.len() + 1);
if text_len > 255 {
let _ = write!(&mut query, ",left({value_ref},255)");
} else {
let _ = write!(&mut query, ",{value_ref}");
}
values.push(value as &(dyn ToSql + Sync));
}
continue;
} else if field.is_text() {
let _ = write!(&mut query, "to_tsvector('{language}',{value_ref})");
} else if text_len > 512 {
query.push_str("left(");
query.push_str(&value_ref);
query.push_str(",512)");
} else {
query.push_str(&value_ref);
}
if field.sort_column().is_some() {
if text_len > 255 {
query.push_str(",left(");
query.push_str(&value_ref);
query.push_str(",255)");
} else {
query.push(',');
query.push_str(&value_ref);
}
}
values.push(value as &(dyn ToSql + Sync));
} else {
query.push_str("NULL");
if field.sort_column().is_some() {
query.push_str(",NULL");
}
}
}
query.push_str(") ON CONFLICT (");
for (i, pkey) in primary_keys.iter().enumerate() {
if i > 0 {
query.push(',');
}
query.push_str(pkey.column());
}
query.push_str(") DO UPDATE SET ");
for (i, field) in all_fields.iter().enumerate() {
if i > 0 {
query.push(',');
}
let column = field.column();
let _ = write!(&mut query, "{column} = EXCLUDED.{column}");
}
trx.execute(&query, &values).await.map_err(into_error)?;
}
trx.commit().await.map_err(into_error)
} }
pub async fn query<R: SearchDocumentId>( pub async fn query<R: SearchDocumentId>(
@@ -175,21 +170,16 @@ impl PostgresStore {
build_sort(&mut query, sort); build_sort(&mut query, sort);
} }
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.query; let s = conn.prepare_cached(&query).await.map_err(into_error)?;
let result = tokio::time::timeout(limit, async {
let s = conn.prepare_cached(&query).await.map_err(into_error)?;
conn.query(&s, params.as_slice()) conn.query(&s, params.as_slice())
.await .await
.and_then(|rows| { .and_then(|rows| {
rows.into_iter() rows.into_iter()
.map(|row| row.try_get::<_, DocId>(0).map(|v| R::from_u64(v.0))) .map(|row| row.try_get::<_, DocId>(0).map(|v| R::from_u64(v.0)))
.collect::<Result<Vec<R>, _>>() .collect::<Result<Vec<R>, _>>()
}) })
.map_err(into_error) .map_err(into_error)
})
.await;
bounded(conn, result, limit)
} }
pub async fn unindex(&self, filter: SearchQuery) -> trc::Result<u64> { pub async fn unindex(&self, filter: SearchQuery) -> trc::Result<u64> {
@@ -199,45 +189,40 @@ impl PostgresStore {
let params = self.build_filter(&mut where_clause, &filter.filters); let params = self.build_filter(&mut where_clause, &filter.filters);
let params = params.iter().map(SqlParam::as_sql).collect::<Vec<_>>(); let params = params.iter().map(SqlParam::as_sql).collect::<Vec<_>>();
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.maintenance; let s = conn
let result = tokio::time::timeout(limit, async { .prepare_cached(&format!("DELETE FROM {table}{where_clause}"))
.await
.map_err(into_error)?;
match conn.execute(&s, params.as_slice()).await {
Ok(deleted) => return Ok(deleted),
Err(err) if is_timeout_error(&err) => (),
Err(err) => return Err(into_error(err)),
}
let mut chunk_size = DELETE_CHUNK_SIZE;
let mut deleted = 0;
loop {
let s = conn let s = conn
.prepare_cached(&format!("DELETE FROM {table}{where_clause}")) .prepare_cached(&format!(
"DELETE FROM {table} WHERE ctid IN (SELECT ctid FROM {table}{where_clause} LIMIT {chunk_size})"
))
.await .await
.map_err(into_error)?; .map_err(into_error)?;
match conn.execute(&s, params.as_slice()).await {
Ok(deleted) => return Ok(deleted),
Err(err) if is_timeout_error(&err) => (),
Err(err) => return Err(into_error(err)),
}
let mut chunk_size = DELETE_CHUNK_SIZE;
let mut deleted = 0;
loop { loop {
let s = conn match conn.execute(&s, params.as_slice()).await {
.prepare_cached(&format!( Ok(0) => return Ok(deleted),
"DELETE FROM {table} WHERE ctid IN (SELECT ctid FROM {table}{where_clause} LIMIT {chunk_size})" Ok(affected) => deleted += affected,
)) Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
.await chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
.map_err(into_error)?; break;
loop {
match conn.execute(&s, params.as_slice()).await {
Ok(0) => return Ok(deleted),
Ok(affected) => deleted += affected,
Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
break;
}
Err(err) => return Err(into_error(err)),
} }
Err(err) => return Err(into_error(err)),
} }
} }
}) }
.await;
bounded(conn, result, limit)
} }
fn build_filter<'x>( fn build_filter<'x>(
+89 -105
View File
@@ -2,11 +2,9 @@
* SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]> * SPDX-FileCopyrightText: 2020 Stalwart Labs LLC <[email protected]>
* *
* SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL * SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-SEL
*
* Modified by Coffey Labs in 2026 for INBUXA.
*/ */
use super::{PostgresStore, bounded, into_error, is_timeout_error}; use super::{PostgresStore, into_error, is_timeout_error};
use crate::{ use crate::{
IndexKey, Key, LogKey, SUBSPACE_COUNTER, SUBSPACE_IN_MEMORY_COUNTER, SUBSPACE_QUOTA, IndexKey, Key, LogKey, SUBSPACE_COUNTER, SUBSPACE_IN_MEMORY_COUNTER, SUBSPACE_QUOTA,
SUBSPACE_REGISTRY_IDX, SUBSPACE_REGISTRY_IDX,
@@ -32,53 +30,48 @@ enum CommitError {
impl PostgresStore { impl PostgresStore {
pub(crate) async fn write(&self, mut batch: Batch<'_>) -> trc::Result<AssignedIds> { pub(crate) async fn write(&self, mut batch: Batch<'_>) -> trc::Result<AssignedIds> {
let mut conn = self.conn_pool.get().await.map_err(into_pool_error)?; let mut conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.query; let start = Instant::now();
let result = tokio::time::timeout(limit, async { let mut retry_count = 0;
let start = Instant::now();
let mut retry_count = 0;
loop { loop {
match self.write_trx(&mut conn, &mut batch).await { match self.write_trx(&mut conn, &mut batch).await {
Ok(result) => { Ok(result) => {
return Ok(result); return Ok(result);
}
Err(err) => {
match err {
CommitError::Postgres(err) => match err.code() {
Some(
&SqlState::T_R_SERIALIZATION_FAILURE
| &SqlState::T_R_DEADLOCK_DETECTED,
) if retry_count < MAX_COMMIT_ATTEMPTS
&& start.elapsed() < MAX_COMMIT_TIME => {}
Some(&SqlState::UNIQUE_VIOLATION) => {
return Err(trc::StoreEvent::AssertValueFailed
.into_err()
.reason("Unique violation")
.caused_by(trc::location!()));
}
_ => return Err(into_error(err)),
},
CommitError::Internal(err) => return Err(err),
/*CommitError::Retry => {
if retry_count > MAX_COMMIT_ATTEMPTS
|| start.elapsed() > MAX_COMMIT_TIME
{
return Err(trc::StoreEvent::AssertValueFailed
.into_err()
.caused_by(trc::location!()));
}
}*/
} }
Err(err) => {
match err {
CommitError::Postgres(err) => match err.code() {
Some(
&SqlState::T_R_SERIALIZATION_FAILURE
| &SqlState::T_R_DEADLOCK_DETECTED,
) if retry_count < MAX_COMMIT_ATTEMPTS
&& start.elapsed() < MAX_COMMIT_TIME => {}
Some(&SqlState::UNIQUE_VIOLATION) => {
return Err(trc::StoreEvent::AssertValueFailed
.into_err()
.reason("Unique violation")
.caused_by(trc::location!()));
}
_ => return Err(into_error(err)),
},
CommitError::Internal(err) => return Err(err),
/*CommitError::Retry => {
if retry_count > MAX_COMMIT_ATTEMPTS
|| start.elapsed() > MAX_COMMIT_TIME
{
return Err(trc::StoreEvent::AssertValueFailed
.into_err()
.caused_by(trc::location!()));
}
}*/
}
let backoff = rand::rng().random_range(50..=300); let backoff = rand::rng().random_range(50..=300);
tokio::time::sleep(Duration::from_millis(backoff)).await; tokio::time::sleep(Duration::from_millis(backoff)).await;
retry_count += 1; retry_count += 1;
}
} }
} }
}) }
.await;
bounded(conn, result, limit)
} }
async fn write_trx( async fn write_trx(
@@ -400,81 +393,72 @@ impl PostgresStore {
pub(crate) async fn purge_store(&self) -> trc::Result<()> { pub(crate) async fn purge_store(&self) -> trc::Result<()> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; 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 subspace in [SUBSPACE_QUOTA, SUBSPACE_COUNTER, SUBSPACE_IN_MEMORY_COUNTER] {
purge_table(&conn, char::from(subspace)).await?;
}
Ok(()) for subspace in [SUBSPACE_QUOTA, SUBSPACE_COUNTER, SUBSPACE_IN_MEMORY_COUNTER] {
}) purge_table(&conn, char::from(subspace)).await?;
.await; }
bounded(conn, result, limit)
Ok(())
} }
pub(crate) async fn delete_range(&self, from: impl Key, to: impl Key) -> trc::Result<()> { pub(crate) async fn delete_range(&self, from: impl Key, to: impl Key) -> trc::Result<()> {
let conn = self.conn_pool.get().await.map_err(into_pool_error)?; let conn = self.conn_pool.get().await.map_err(into_pool_error)?;
let limit = self.timeouts.maintenance; let table = char::from(from.subspace());
let result = tokio::time::timeout(limit, async { let mut from = from.serialize(0);
let table = char::from(from.subspace()); let to = to.serialize(0);
let mut from = from.serialize(0);
let to = to.serialize(0);
let delete = conn let delete = conn
.prepare_cached(&format!("DELETE FROM {table} WHERE k >= $1 AND k < $2")) .prepare_cached(&format!("DELETE FROM {table} WHERE k >= $1 AND k < $2"))
.await
.map_err(into_error)?;
match conn.execute(&delete, &[&from, &to]).await {
Ok(_) => return Ok(()),
Err(err) if is_timeout_error(&err) => (),
Err(err) => return Err(into_error(err)),
}
let mut chunk_size = DELETE_CHUNK_SIZE;
loop {
let boundary = conn
.prepare_cached(&format!(
"SELECT k FROM {table} WHERE k >= $1 AND k < $2 ORDER BY k ASC LIMIT 1 OFFSET {chunk_size}"
))
.await .await
.map_err(into_error)?; .map_err(into_error)?;
match conn.execute(&delete, &[&from, &to]).await {
Ok(_) => return Ok(()),
Err(err) if is_timeout_error(&err) => (),
Err(err) => return Err(into_error(err)),
}
let mut chunk_size = DELETE_CHUNK_SIZE;
loop { loop {
let boundary = conn let next = match conn.query_opt(&boundary, &[&from, &to]).await {
.prepare_cached(&format!( Ok(next) => match next {
"SELECT k FROM {table} WHERE k >= $1 AND k < $2 ORDER BY k ASC LIMIT 1 OFFSET {chunk_size}" Some(row) => Some(row.try_get::<_, Vec<u8>>(0).map_err(into_error)?),
)) None => None,
},
Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
break;
}
Err(err) => return Err(into_error(err)),
};
match conn
.execute(&delete, &[&from, next.as_ref().unwrap_or(&to)])
.await .await
.map_err(into_error)?; {
Ok(_) => (),
loop { Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
let next = match conn.query_opt(&boundary, &[&from, &to]).await { chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
Ok(next) => match next { break;
Some(row) => Some(row.try_get::<_, Vec<u8>>(0).map_err(into_error)?),
None => None,
},
Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
break;
}
Err(err) => return Err(into_error(err)),
};
match conn
.execute(&delete, &[&from, next.as_ref().unwrap_or(&to)])
.await
{
Ok(_) => (),
Err(err) if is_timeout_error(&err) && chunk_size > MIN_DELETE_CHUNK_SIZE => {
chunk_size = (chunk_size / 2).max(MIN_DELETE_CHUNK_SIZE);
break;
}
Err(err) => return Err(into_error(err)),
} }
Err(err) => return Err(into_error(err)),
}
match next { match next {
Some(next) => from = next, Some(next) => from = next,
None => return Ok(()), None => return Ok(()),
}
} }
} }
}) }
.await;
bounded(conn, result, limit)
} }
} }
-77
View File
@@ -1,77 +0,0 @@
/*
* SPDX-FileCopyrightText: 2026 Coffey Labs
*
* SPDX-License-Identifier: AGPL-3.0-only
*/
//! Client-side limits on SQL queries.
//!
//! The pool timeouts bound getting a connection, not using one. A database
//! that stops answering while the TCP connection stays up (a paused
//! container, a hung server whose kernel still acknowledges keepalives)
//! left a query on a checked-out connection waiting for as long as it took.
//! A server-side statement_timeout can't help there: the server that would
//! enforce it is the one not answering. So each operation on a PostgreSQL
//! or MySQL connection runs under a time limit here, and a connection whose
//! operation ran out is closed rather than put back in the pool, since its
//! protocol state is unknown.
//!
//! Two limits:
//! - `query`, two minutes, for request-path work: reads, writes, blob
//! transfers, search queries and document indexing. Those take
//! milliseconds; two minutes leaves room for a large blob over a slow
//! link and still ends a hang.
//! - `maintenance`, thirty minutes, for work that legitimately runs long in
//! one statement: range deletes (account removal, purges), unindexing,
//! and creating tables and indexes at startup.
//!
//! Iterating over a range (exports, reindexing, maintenance scans) can run
//! for hours, so there the `query` limit applies to each wait for the next
//! row instead of the whole scan.
use std::time::Duration;
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct QueryTimeouts {
pub query: Duration,
pub maintenance: Duration,
}
impl QueryTimeouts {
pub const QUERY: Duration = Duration::from_secs(120);
pub const MAINTENANCE: Duration = Duration::from_secs(30 * 60);
}
impl Default for QueryTimeouts {
fn default() -> Self {
Self {
query: Self::QUERY,
maintenance: Self::MAINTENANCE,
}
}
}
#[cfg(feature = "test_mode")]
impl crate::Store {
/// Sets the query limits of a SQL store that was just built (tests only:
/// the limits aren't configurable).
pub fn with_query_timeouts(self, timeouts: QueryTimeouts) -> Self {
match self {
#[cfg(feature = "postgres")]
crate::Store::PostgreSQL(mut store) => {
std::sync::Arc::get_mut(&mut store)
.expect("store already shared")
.timeouts = timeouts;
crate::Store::PostgreSQL(store)
}
#[cfg(feature = "mysql")]
crate::Store::MySQL(mut store) => {
std::sync::Arc::get_mut(&mut store)
.expect("store already shared")
.timeouts = timeouts;
crate::Store::MySQL(store)
}
store => store,
}
}
}
-2
View File
@@ -21,8 +21,6 @@ pub mod replica_mysql; // inbuxa: read replicas on MySQL
#[cfg(all(feature = "postgres", feature = "redis"))] #[cfg(all(feature = "postgres", feature = "redis"))]
pub mod replica_cluster; // inbuxa: read replicas across nodes pub mod replica_cluster; // inbuxa: read replicas across nodes
pub mod scaleout; // inbuxa: scale-out storage pub mod scaleout; // inbuxa: scale-out storage
#[cfg(feature = "postgres")]
pub mod search_gin; // inbuxa: GIN indexes without a pending list
#[cfg(any(feature = "postgres", feature = "mysql"))] #[cfg(any(feature = "postgres", feature = "mysql"))]
pub mod sql_timeout; pub mod sql_timeout;
pub mod task_locks; // inbuxa: task locks across nodes pub mod task_locks; // inbuxa: task locks across nodes
+3 -283
View File
@@ -9,31 +9,11 @@
//! the pool's timeouts. Upstream's pools had none, so the worker waited for //! the pool's timeouts. Upstream's pools had none, so the worker waited for
//! good. No database is needed: a local listener that never answers plays //! good. No database is needed: a local listener that never answers plays
//! the server. //! the server.
//!
//! inbuxa: the same for a database that stops answering while connections
//! are already open (a paused container): a query on a checked-out
//! connection ends within the query limit, the store works again once the
//! database is back, and /healthz/ready says 503 in between while
//! /healthz/live stays 200. These need the local test databases; a proxy
//! that can stop forwarding plays the pause.
use registry::schema::structs::DataStore; use registry::schema::structs::DataStore;
use std::{ use std::time::{Duration, Instant};
sync::{ use store::{Store, ValueKey, write::ValueClass};
Arc, use tokio::net::TcpListener;
atomic::{AtomicBool, Ordering},
},
time::{Duration, Instant},
};
use store::{
IterateParams, Store, ValueKey,
backend::query_timeout::QueryTimeouts,
write::{BatchBuilder, ValueClass},
};
use tokio::{
io::{AsyncReadExt, AsyncWriteExt},
net::{TcpListener, TcpStream},
};
/// Accepts connections on a local port and never sends a byte. /// Accepts connections on a local port and never sends a byte.
async fn silent_server() -> u16 { async fn silent_server() -> u16 {
@@ -114,263 +94,3 @@ pub async fn mysql_pool_timeout() {
) )
.await; .await;
} }
/// A TCP proxy to a local port that can stop forwarding, in both
/// directions, while keeping every connection open: a paused server whose
/// kernel still keeps the connections up.
struct PausableProxy {
port: u16,
paused: Arc<AtomicBool>,
}
impl PausableProxy {
async fn start(upstream: u16) -> Self {
let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
let port = listener.local_addr().unwrap().port();
let paused = Arc::new(AtomicBool::new(false));
let paused_ = paused.clone();
tokio::spawn(async move {
while let Ok((client, _)) = listener.accept().await {
let Ok(server) = TcpStream::connect(("127.0.0.1", upstream)).await else {
continue;
};
let (client_rx, client_tx) = client.into_split();
let (server_rx, server_tx) = server.into_split();
tokio::spawn(forward(client_rx, server_tx, paused_.clone()));
tokio::spawn(forward(server_rx, client_tx, paused_.clone()));
}
});
PausableProxy { port, paused }
}
fn pause(&self, paused: bool) {
self.paused.store(paused, Ordering::SeqCst);
}
}
async fn forward(
mut from: tokio::net::tcp::OwnedReadHalf,
mut to: tokio::net::tcp::OwnedWriteHalf,
paused: Arc<AtomicBool>,
) {
let mut buf = vec![0u8; 16384];
loop {
while paused.load(Ordering::SeqCst) {
tokio::time::sleep(Duration::from_millis(20)).await;
}
let n = match from.read(&mut buf).await {
Ok(0) | Err(_) => return,
Ok(n) => n,
};
// Hold what arrived while paused until the pause ends
while paused.load(Ordering::SeqCst) {
tokio::time::sleep(Duration::from_millis(20)).await;
}
if to.write_all(&buf[..n]).await.is_err() {
return;
}
}
}
const TEST_LIMITS: QueryTimeouts = QueryTimeouts {
query: Duration::from_secs(2),
maintenance: Duration::from_secs(3),
};
/// Opens `connections` pooled connections at once, so the operations that
/// follow find one idle and check it out.
async fn warm(store: &Store, connections: usize) {
let reads = (0..connections).map(|_| async {
store
.get_value::<u64>(ValueKey::from(ValueClass::Property(0)))
.await
.unwrap();
});
futures::future::join_all(reads).await;
}
/// With the database paused, reads, scans and writes on connections the
/// pool already holds end in an error within the query limit; once it is
/// back, the store works again.
async fn assert_queries_time_out(store: Store, proxy: &PausableProxy) {
store.create_tables().await.unwrap();
warm(&store, 4).await;
// mysql_async resets a connection on its way back to the pool; let
// those finish, or the connections are stuck in the reset when the
// pause starts and the pool's own wait timeout answers instead
tokio::time::sleep(Duration::from_secs(1)).await;
proxy.pause(true);
let key = || ValueKey::from(ValueClass::Property(0));
let limit = TEST_LIMITS.query;
for (what, op) in [("read", 0), ("scan", 1), ("write", 2)] {
let started = Instant::now();
let result = tokio::time::timeout(Duration::from_secs(20), async {
match op {
0 => store.get_value::<u64>(key()).await.map(|_| ()),
1 => {
store
.iterate(
IterateParams::new(
ValueKey::from(ValueClass::Property(0)),
ValueKey::from(ValueClass::Property(u8::MAX)),
),
|_, _| Ok(true),
)
.await
}
_ => {
let mut batch = BatchBuilder::new();
batch
.with_account_id(u32::MAX - 7)
.with_collection(types::collection::Collection::Email)
.with_document(0)
.set(ValueClass::Property(0), 1u64.to_be_bytes().to_vec());
store.write(batch.build_all()).await.map(|_| ())
}
}
})
.await;
let elapsed = started.elapsed();
match result {
Ok(Err(err)) => {
let err = format!("{err:?}");
println!("Paused database, {what}: {err} after {elapsed:?}");
assert!(err.contains("Query timed out"), "{what}: {err}");
assert!(
elapsed >= limit && elapsed < limit * 3,
"{what} ended after {elapsed:?}"
);
}
Ok(Ok(())) => panic!("{what} succeeded against a paused database"),
Err(_) => panic!("{what} still waiting after {elapsed:?}"),
}
}
proxy.pause(false);
tokio::time::timeout(Duration::from_secs(20), store.get_value::<u64>(key()))
.await
.expect("still waiting after the database came back")
.expect("the store didn't recover");
}
#[cfg(feature = "postgres")]
#[tokio::test(flavor = "multi_thread")]
pub async fn postgres_query_timeout() {
println!("Running PostgreSQL query timeout test...");
let DataStore::PostgreSql(mut config) =
crate::utils::storage::build_data_store("PostgreSql", "").await
else {
unreachable!()
};
let proxy = PausableProxy::start(config.port as u16).await;
config.host = "127.0.0.1".into();
config.port = proxy.port as u64;
// New connections through the paused proxy give up as quickly
config.timeout = Some(TEST_LIMITS.query.into());
let store = Store::build(DataStore::PostgreSql(config))
.await
.unwrap()
.with_query_timeouts(TEST_LIMITS);
assert_queries_time_out(store, &proxy).await;
}
#[cfg(feature = "mysql")]
#[tokio::test(flavor = "multi_thread")]
pub async fn mysql_query_timeout() {
println!("Running MySQL query timeout test...");
let DataStore::MySql(mut config) = crate::utils::storage::build_data_store("MySql", "").await
else {
unreachable!()
};
let proxy = PausableProxy::start(config.port as u16).await;
config.host = "127.0.0.1".into();
config.port = proxy.port as u64;
let store = Store::build(DataStore::MySql(config))
.await
.unwrap()
.with_query_timeouts(TEST_LIMITS);
assert_queries_time_out(store, &proxy).await;
}
/// /healthz/ready follows the data store; /healthz/live doesn't.
#[cfg(feature = "postgres")]
#[tokio::test(flavor = "multi_thread")]
pub async fn postgres_readiness() {
use crate::utils::server::TestServerBuilder;
use registry::schema::enums::NetworkListenerProtocol;
const HTTP_PORT: u16 = 11_320;
if std::env::var("STORE").as_deref() != Ok("PostgreSql") {
println!("Skipping the readiness test: it runs with STORE=PostgreSql.");
return;
}
println!("Running readiness test...");
let test = TestServerBuilder::new("postgres_readiness")
.await
.with_listener(NetworkListenerProtocol::Http, "http", HTTP_PORT, true)
.await
.build()
.await;
// Point the running node's data store at the database through the proxy
let DataStore::PostgreSql(mut config) =
crate::utils::storage::build_data_store("PostgreSql", "").await
else {
unreachable!()
};
let proxy = PausableProxy::start(config.port as u16).await;
config.host = "127.0.0.1".into();
config.port = proxy.port as u64;
config.timeout = Some(TEST_LIMITS.query.into());
let store = Store::build(DataStore::PostgreSql(config))
.await
.unwrap()
.with_query_timeouts(TEST_LIMITS);
let inner = &test.server.inner;
let mut core = inner.shared_core.load_full().as_ref().clone();
core.storage.data = store;
inner.shared_core.store(Arc::new(core));
let health = |path: &'static str| async move {
reqwest::Client::builder()
.danger_accept_invalid_certs(true)
.timeout(Duration::from_secs(10))
.build()
.unwrap()
.get(format!("https://127.0.0.1:{HTTP_PORT}/healthz/{path}"))
.send()
.await
.unwrap()
.status()
.as_u16()
};
let wait_for = |path: &'static str, status: u16| async move {
let started = Instant::now();
loop {
let got = health(path).await;
if got == status {
println!("/healthz/{path}: {got} after {:?}", started.elapsed());
return;
}
assert!(
started.elapsed() < Duration::from_secs(20),
"/healthz/{path} still {got}, expected {status}"
);
tokio::time::sleep(Duration::from_millis(250)).await;
}
};
wait_for("ready", 200).await;
proxy.pause(true);
wait_for("ready", 503).await;
assert_eq!(health("live").await, 200);
proxy.pause(false);
wait_for("ready", 200).await;
assert_eq!(health("live").await, 200);
if test.is_reset() {
test.temp_dir.delete();
}
}
-159
View File
@@ -1,159 +0,0 @@
/*
* SPDX-FileCopyrightText: 2026 Coffey Labs
*
* SPDX-License-Identifier: AGPL-3.0-only
*/
//! PostgreSQL full-text GIN indexes are built with fastupdate off, and an
//! index made earlier with the default is switched over at startup. With
//! fastupdate on, new entries wait in a pending list that every search scans
//! in full until VACUUM merges it.
use crate::utils::storage::build_data_store;
use registry::schema::structs::DataStore;
use store::{Rows, SearchStore, Store};
const SCHEMA: &str = "gin_fastupdate_test";
#[tokio::test(flavor = "multi_thread")]
pub async fn postgres_gin_fastupdate() {
println!("Running PostgreSQL GIN fastupdate test...");
// Work in a schema of our own so the shared search tables are untouched
let admin = Store::build(build_data_store("PostgreSql", "").await)
.await
.expect("Failed to connect to PostgreSQL");
for query in [
format!("DROP SCHEMA IF EXISTS {SCHEMA} CASCADE"),
format!("CREATE SCHEMA {SCHEMA}"),
] {
admin.sql_query::<usize>(&query, vec![]).await.unwrap();
}
let DataStore::PostgreSql(mut config) = build_data_store("PostgreSql", "").await else {
unreachable!()
};
config.options = Some(format!("-c search_path={SCHEMA}"));
let store = Store::build(DataStore::PostgreSql(config))
.await
.expect("Failed to connect to PostgreSQL");
let search = SearchStore::Store(store.clone());
// A fresh schema
search.create_indexes().await.unwrap();
let indexes = gin_indexes(&admin).await;
assert!(
indexes.len() >= 4,
"expected the search GIN indexes, found {indexes:?}"
);
for (name, options) in &indexes {
assert!(
options.contains("fastupdate=off"),
"fresh index {name} has options {options:?}"
);
}
// A schema from before the change: the same indexes, made with the
// default fastupdate=on, and a pending list with something in it
for (name, _) in &indexes {
admin
.sql_query::<usize>(
&format!("ALTER INDEX {SCHEMA}.{name} RESET (fastupdate)"),
vec![],
)
.await
.unwrap();
}
for (name, options) in gin_indexes(&admin).await {
assert!(
!options.contains("fastupdate"),
"index {name} still has options {options:?}"
);
}
admin
.sql_query::<usize>(
&format!(
"INSERT INTO {SCHEMA}.s_email (accid, docid, subj, body) \
SELECT 1, n, to_tsvector('simple', 'pending subject ' || n), \
to_tsvector('simple', 'pending body text ' || n) \
FROM generate_series(1, 500) n"
),
vec![],
)
.await
.unwrap();
assert!(
pending_tuples(&admin, "gin_s_email_body").await > 0,
"no pending list to merge"
);
// Startup on the existing schema switches every index over and merges
// what was pending
search.create_indexes().await.unwrap();
for (name, options) in gin_indexes(&admin).await {
assert!(
options.contains("fastupdate=off"),
"existing index {name} has options {options:?} after startup"
);
}
assert_eq!(pending_tuples(&admin, "gin_s_email_body").await, 0);
// And a second startup changes nothing
search.create_indexes().await.unwrap();
for (name, options) in gin_indexes(&admin).await {
assert!(options.contains("fastupdate=off"), "{name}: {options:?}");
}
admin
.sql_query::<usize>(&format!("DROP SCHEMA {SCHEMA} CASCADE"), vec![])
.await
.unwrap();
}
/// The GIN indexes in the test schema with their reloptions.
async fn gin_indexes(admin: &Store) -> Vec<(String, String)> {
admin
.sql_query::<Rows>(
&format!(
"SELECT c.relname::text, COALESCE(array_to_string(c.reloptions, ','), '') \
FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace \
JOIN pg_am a ON a.oid = c.relam \
WHERE n.nspname = '{SCHEMA}' AND c.relkind = 'i' AND a.amname = 'gin' \
ORDER BY 1"
),
vec![],
)
.await
.unwrap()
.rows
.into_iter()
.map(|row| {
let mut values = row.values.into_iter();
(
values.next().unwrap().to_str().into_owned(),
values.next().unwrap().to_str().into_owned(),
)
})
.collect()
}
/// Tuples waiting in a GIN index's pending list (pgstattuple is a contrib
/// extension the test database has).
async fn pending_tuples(admin: &Store, index: &str) -> i64 {
admin
.sql_query::<usize>("CREATE EXTENSION IF NOT EXISTS pgstattuple", vec![])
.await
.unwrap();
admin
.sql_query::<Rows>(
&format!("SELECT pending_tuples FROM pgstatginindex('{SCHEMA}.{index}'::regclass)"),
vec![],
)
.await
.unwrap()
.rows
.into_iter()
.next()
.and_then(|row| row.values.into_iter().next())
.map(|value| value.to_str().parse::<i64>().unwrap())
.unwrap()
}