mirror of
https://github.com/hanzoai/tasks.git
synced 2026-10-04 02:04:03 +00:00
Tim Deeb-SwihartandGitHub
be7b5514a5
## What changed? Both our PostgreSQL and MySQL database backends will now automatically reconnect to the database when certain errors occur: all errors chosen have been experienced when testing this behavior through an AWS Aurora RDS failover of either MySQL or PostgreSQL. For both backends we will reconnect when we see: - `ECONNRESET` - `ECONNABORTED` - `ECONNREFUSED` - `io.EOF` - `io.ErrUnexpectedEOF` - `database/sql/driver.ErrBadConn` for postgres we will also reconnect on the following SQLStates: - `25006` read-only transaction - `57P03` cannot connect now - `0A000` feature not supported, but ONLY when the message is `cannot set transaction read-write mode during recovery` for mysql we will also reconnect when we see the following error codes: - `1040` too many connections - `1792` read-only transaction (SQLstate `25006`) - `1836` running in read-only mode This logic is easily extensible should we discover more failure modes over time ## Why? We've had multiple community reports of Temporal problems during RDS failover. One part of this is the fact that we wouldn't necessarily reconnect; we were at the whims of our chosen SQL abstraction's connection pooling logic. ## How did you test it? I manually tested this functionality in the presence of repeated RDS failovers: - [x] postgres12 plugin with pq driver - [x] postgres12 plugin with pgx driver - [x] mysql plugin Automated testing will be added to our regular testing pipelines once our infrastructure friends have added the support I need (it's in progress) ## Potential risks We're concerned there's a correctness issue in our PostgreSQL backend that's related to our behavior during an RDS failover. If we merge this before I figure out what's going on, we could hide the issue and make it harder to reproduce. ## Documentation N/A ## Is hotfix candidate? Yes?
242 lines
6.4 KiB
Go
242 lines
6.4 KiB
Go
// The MIT License
|
|
//
|
|
// Copyright (c) 2020 Temporal Technologies Inc. All rights reserved.
|
|
//
|
|
// Copyright (c) 2020 Uber Technologies, Inc.
|
|
//
|
|
// Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
// of this software and associated documentation files (the "Software"), to deal
|
|
// in the Software without restriction, including without limitation the rights
|
|
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
// copies of the Software, and to permit persons to whom the Software is
|
|
// furnished to do so, subject to the following conditions:
|
|
//
|
|
// The above copyright notice and this permission notice shall be included in
|
|
// all copies or substantial portions of the Software.
|
|
//
|
|
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
|
// THE SOFTWARE.
|
|
|
|
package tests
|
|
|
|
import (
|
|
"math/rand"
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/require"
|
|
"github.com/stretchr/testify/suite"
|
|
|
|
"go.temporal.io/server/common/persistence/sql/sqlplugin"
|
|
"go.temporal.io/server/common/shuffle"
|
|
)
|
|
|
|
type (
|
|
historyShardSuite struct {
|
|
suite.Suite
|
|
*require.Assertions
|
|
|
|
store sqlplugin.DB
|
|
}
|
|
)
|
|
|
|
const (
|
|
testHistoryShardEncoding = "random encoding"
|
|
)
|
|
|
|
var (
|
|
testHistoryShardData = []byte("random history shard data")
|
|
)
|
|
|
|
func NewHistoryShardSuite(
|
|
t *testing.T,
|
|
store sqlplugin.DB,
|
|
) *historyShardSuite {
|
|
return &historyShardSuite{
|
|
Assertions: require.New(t),
|
|
store: store,
|
|
}
|
|
}
|
|
|
|
func (s *historyShardSuite) SetupSuite() {
|
|
|
|
}
|
|
|
|
func (s *historyShardSuite) TearDownSuite() {
|
|
|
|
}
|
|
|
|
func (s *historyShardSuite) SetupTest() {
|
|
s.Assertions = require.New(s.T())
|
|
}
|
|
|
|
func (s *historyShardSuite) TearDownTest() {
|
|
|
|
}
|
|
|
|
func (s *historyShardSuite) TestInsert_Success() {
|
|
shardID := rand.Int31()
|
|
rangeID := int64(1)
|
|
|
|
shard := s.newRandomShardRow(shardID, rangeID)
|
|
result, err := s.store.InsertIntoShards(newExecutionContext(), &shard)
|
|
s.NoError(err)
|
|
rowsAffected, err := result.RowsAffected()
|
|
s.NoError(err)
|
|
s.Equal(1, int(rowsAffected))
|
|
}
|
|
|
|
func (s *historyShardSuite) TestInsert_Fail_Duplicate() {
|
|
shardID := rand.Int31()
|
|
rangeID := int64(1)
|
|
|
|
shard := s.newRandomShardRow(shardID, rangeID)
|
|
result, err := s.store.InsertIntoShards(newExecutionContext(), &shard)
|
|
s.NoError(err)
|
|
rowsAffected, err := result.RowsAffected()
|
|
s.NoError(err)
|
|
s.Equal(1, int(rowsAffected))
|
|
|
|
shard = s.newRandomShardRow(shardID, rangeID)
|
|
_, err = s.store.InsertIntoShards(newExecutionContext(), &shard)
|
|
s.Error(err) // TODO persistence layer should do proper error translation
|
|
}
|
|
|
|
func (s *historyShardSuite) TestInsertSelect() {
|
|
shardID := rand.Int31()
|
|
rangeID := int64(1)
|
|
|
|
shard := s.newRandomShardRow(shardID, rangeID)
|
|
result, err := s.store.InsertIntoShards(newExecutionContext(), &shard)
|
|
s.NoError(err)
|
|
rowsAffected, err := result.RowsAffected()
|
|
s.NoError(err)
|
|
s.Equal(1, int(rowsAffected))
|
|
|
|
filter := sqlplugin.ShardsFilter{
|
|
ShardID: shardID,
|
|
}
|
|
row, err := s.store.SelectFromShards(newExecutionContext(), filter)
|
|
s.NoError(err)
|
|
s.Equal(&shard, row)
|
|
}
|
|
|
|
func (s *historyShardSuite) TestInsertUpdate_Success() {
|
|
shardID := rand.Int31()
|
|
rangeID := int64(1)
|
|
|
|
shard := s.newRandomShardRow(shardID, rangeID)
|
|
rangeID += 100
|
|
result, err := s.store.InsertIntoShards(newExecutionContext(), &shard)
|
|
s.NoError(err)
|
|
rowsAffected, err := result.RowsAffected()
|
|
s.NoError(err)
|
|
s.Equal(1, int(rowsAffected))
|
|
|
|
shard = s.newRandomShardRow(shardID, rangeID)
|
|
result, err = s.store.UpdateShards(newExecutionContext(), &shard)
|
|
s.NoError(err)
|
|
rowsAffected, err = result.RowsAffected()
|
|
s.NoError(err)
|
|
s.Equal(1, int(rowsAffected))
|
|
}
|
|
|
|
func (s *historyShardSuite) TestUpdate_Fail() {
|
|
shardID := rand.Int31()
|
|
rangeID := int64(1)
|
|
|
|
shard := s.newRandomShardRow(shardID, rangeID)
|
|
result, err := s.store.UpdateShards(newExecutionContext(), &shard)
|
|
s.NoError(err)
|
|
rowsAffected, err := result.RowsAffected()
|
|
s.NoError(err)
|
|
s.Equal(0, int(rowsAffected))
|
|
}
|
|
|
|
func (s *historyShardSuite) TestInsertUpdateSelect() {
|
|
shardID := rand.Int31()
|
|
rangeID := int64(1)
|
|
|
|
shard := s.newRandomShardRow(shardID, rangeID)
|
|
rangeID += 100
|
|
result, err := s.store.InsertIntoShards(newExecutionContext(), &shard)
|
|
s.NoError(err)
|
|
rowsAffected, err := result.RowsAffected()
|
|
s.NoError(err)
|
|
s.Equal(1, int(rowsAffected))
|
|
|
|
shard = s.newRandomShardRow(shardID, rangeID)
|
|
result, err = s.store.UpdateShards(newExecutionContext(), &shard)
|
|
s.NoError(err)
|
|
rowsAffected, err = result.RowsAffected()
|
|
s.NoError(err)
|
|
s.Equal(1, int(rowsAffected))
|
|
|
|
filter := sqlplugin.ShardsFilter{
|
|
ShardID: shardID,
|
|
}
|
|
row, err := s.store.SelectFromShards(newExecutionContext(), filter)
|
|
s.NoError(err)
|
|
s.Equal(&shard, row)
|
|
}
|
|
|
|
func (s *historyShardSuite) TestInsertReadLock() {
|
|
shardID := rand.Int31()
|
|
rangeID := int64(rand.Int31())
|
|
|
|
shard := s.newRandomShardRow(shardID, rangeID)
|
|
result, err := s.store.InsertIntoShards(newExecutionContext(), &shard)
|
|
s.NoError(err)
|
|
rowsAffected, err := result.RowsAffected()
|
|
s.NoError(err)
|
|
s.Equal(1, int(rowsAffected))
|
|
|
|
tx, err := s.store.BeginTx(newExecutionContext())
|
|
s.NoError(err)
|
|
filter := sqlplugin.ShardsFilter{
|
|
ShardID: shardID,
|
|
}
|
|
shardRange, err := tx.ReadLockShards(newExecutionContext(), filter)
|
|
s.NoError(err)
|
|
s.Equal(rangeID, shardRange)
|
|
s.NoError(tx.Commit())
|
|
}
|
|
|
|
func (s *historyShardSuite) TestInsertWriteLock() {
|
|
shardID := rand.Int31()
|
|
rangeID := int64(rand.Int31())
|
|
|
|
shard := s.newRandomShardRow(shardID, rangeID)
|
|
result, err := s.store.InsertIntoShards(newExecutionContext(), &shard)
|
|
s.NoError(err)
|
|
rowsAffected, err := result.RowsAffected()
|
|
s.NoError(err)
|
|
s.Equal(1, int(rowsAffected))
|
|
|
|
tx, err := s.store.BeginTx(newExecutionContext())
|
|
s.NoError(err)
|
|
filter := sqlplugin.ShardsFilter{
|
|
ShardID: shardID,
|
|
}
|
|
shardRange, err := tx.WriteLockShards(newExecutionContext(), filter)
|
|
s.NoError(err)
|
|
s.Equal(rangeID, shardRange)
|
|
s.NoError(tx.Commit())
|
|
}
|
|
|
|
func (s *historyShardSuite) newRandomShardRow(
|
|
shardID int32,
|
|
rangeID int64,
|
|
) sqlplugin.ShardsRow {
|
|
return sqlplugin.ShardsRow{
|
|
ShardID: shardID,
|
|
RangeID: rangeID,
|
|
Data: shuffle.Bytes(testHistoryShardData),
|
|
DataEncoding: testHistoryShardEncoding,
|
|
}
|
|
}
|