In plain words, each distributed plan pulls the necessary intermediate
results to the worker nodes that the plan hits. This is primarily useful
in three ways.
(i) If the distributed plan that uses intermediate
result(s) is a router query, then the intermediate results are only
broadcasted to a single node.
(ii) If a distributed plan consists of only intermediate results, which
is not uncommon, the intermediate results are broadcasted to a single
node only.
(iii) If a distributed query hits a sub-set of the shards in multiple
workers, the intermediate results will be broadcasted to the relevant
node(s).
The final item (iii) becomes crucial for append/range distributed
tables where typically the distributed queries hit a small subset of
shards/workers.
To do this, for each query that Citus creates a distributed plan, we keep
track of the subPlans used in the queryTree, and save it in the distributed
plan. Just before Citus executes each subPlan, Citus first keeps track of
every worker node that the distributed plan hits, and marks every subPlan
should be broadcasted to these nodes. Later, for each subPlan which is a
distributed plan, Citus does this operation recursively since these
distributed plans may access to different subPlans, and those have to be
recorded as well.
Phase 1 seeks to implement minimal infrastructure, so does not include:
- dynamic generation of support aggregates to handle multiple arguments
- configuration methods to direct aggregation strategy,
or mark an aggregate's serialize/deserialize as safe to operate across nodes
Aggregates can be distributed when:
- they have a single argument
- they have a combinefunc
- their transition type is not a pseudotype
Postgres doesn't require you to add all columns that are in the target list to
the GROUP BY when you group by a unique column (or columns). It even actively
removes these group by clauses when you do.
This is normally fine, but for repartition joins it is not. The reason for this
is that the temporary tables don't have these primary key columns. So when the
worker executes the query it will complain that it is missing columns in the
group by.
This PR fixes that by adding an ANY_VALUE aggregate around each variable in
the target list that does is not contained in the group by or in an aggregate.
This is done only for repartition joins.
The ANY_VALUE aggregate chooses the value from an undefined row in the
group.
It looks like the logic to prevent RETURNING in reference tables to
have duplicate entries that comes from local and remote executions
leads to missing some tuples for distributed tables.
With this PR, we're ensuring to kick in the logic for reference tables
only.
* Remove unused executor codes
All of the codes of real-time executor. Some functions
in router executor still remains there because there
are common functions. We'll move them to accurate places
in the follow-up commits.
* Move GUCs to transaction mngnt and remove unused struct
* Update test output
* Get rid of references of real-time executor from code
* Warn if real-time executor is picked
* Remove lots of unused connection codes
* Removed unused code for connection restrictions
Real-time and router executors cannot handle re-using of the existing
connections within a transaction block.
Adaptive executor and COPY can re-use the connections. So, there is no
reason to keep the code around for applying the restrictions in the
placement connection logic.
We've changed the logic for pulling RTE_RELATIONs in #3109 and
non-colocated subquery joins and partitioned tables.
@onurctirtir found this steps where I traced back and found the issues.
While looking into it in more detail, we decided to expand the list in a
way that the callers get all the relevant RTE_RELATIONs RELKIND_RELATION,
RELKIND_PARTITIONED_TABLE, RELKIND_FOREIGN_TABLE and RELKIND_MATVIEW.
These are all relation kinds that Citus planner is aware of.
This completely hides `ListCell` to the user of the loop
Example usage:
```c
WorkerNode *workerNode = NULL;
foreach_ptr(workerNode, workerNodeList) {
// Do stuff with workerNode
}
```
Instead of:
```c
ListCell *workerNodeCell = NULL;
foreach(cell, workerNodeList) {
WorkerNode *workerNode = lfirst(workerNodeCell);
// Do stuff with workerNode
}
```
This is an improvement over #2512.
This adds the boolean shouldhaveshards column to pg_dist_node. When it's false, create_distributed_table for new collocation groups will not create shards on that node. Reference tables will still be created on nodes where it is false.
When a function is marked as colocated with a distributed table,
we try delegating queries of kind "SELECT func(...)" to workers.
We currently only support this simple form, and don't delegate
forms like "SELECT f1(...), f2(...)", "SELECT f1(...) FROM ...",
or function calls inside transactions.
As a side effect, we also fix the transactional semantics of DO blocks.
Previously we didn't consider a DO block a multi-statement transaction.
Now we do.
Co-authored-by: Marco Slot <marco@citusdata.com>
Co-authored-by: serprex <serprex@users.noreply.github.com>
Co-authored-by: pykello <hadi.moshayedi@microsoft.com>
Since the distributed functions are useful when the workers have
metadata, we automatically sync it.
Also, after master_add_node(). We do it lazily and let the deamon
sync it. That's mainly because the metadata syncing cannot be done
in transaction blocks, and we don't want to add lots of transactional
limitations to master_add_node() and create_distributed_function().
DESCRIPTION: Distribute Types to worker nodes
When to propagate
==============
There are two logical moments that types could be distributed to the worker nodes
- When they get used ( just in time distribution )
- When they get created ( proactive distribution )
The just in time distribution follows the model used by how schema's get created right before we are going to create a table in that schema, for types this would be when the table uses a type as its column.
The proactive distribution is suitable for situations where it is benificial to have the type on the worker nodes directly. They can later on be used in queries where an intermediate result gets created with a cast to this type.
Just in time creation is always the last resort, you cannot create a distributed table before the type gets created. A good example use case is; you have an existing postgres server that needs to scale out. By adding the citus extension, add some nodes to the cluster, and distribute the table. The type got created before citus existed. There was no moment where citus could have propagated the creation of a type.
Proactive is almost always a good option. Types are not resource intensive objects, there is no performance overhead of having 100's of types. If you want to use them in a query to represent an intermediate result (which happens in our test suite) they just work.
There is however a moment when proactive type distribution is not beneficial; in transactions where the type is used in a distributed table.
Lets assume the following transaction:
```sql
BEGIN;
CREATE TYPE tt1 AS (a int, b int);
CREATE TABLE t1 AS (a int PRIMARY KEY, b tt1);
SELECT create_distributed_table('t1', 'a');
\copy t1 FROM bigdata.csv
```
Types are node scoped objects; meaning the type exists once per worker. Shards however have best performance when they are created over their own connection. For the type to be visible on all connections it needs to be created and committed before we try to create the shards. Here the just in time situation is most beneficial and follows how we create schema's on the workers. Outside of a transaction block we will just use 1 connection to propagate the creation.
How propagation works
=================
Just in time
-----------
Just in time propagation hooks into the infrastructure introduced in #2882. It adds types as a supported object in `SupportedDependencyByCitus`. This will make sure that any object being distributed by citus that depends on types will now cascade into types. When types are depending them self on other objects they will get created first.
Creation later works by getting the ddl commands to create the object by its `ObjectAddress` in `GetDependencyCreateDDLCommands` which will dispatch types to `CreateTypeDDLCommandsIdempotent`.
For the correct walking of the graph we follow array types, when later asked for the ddl commands for array types we return `NIL` (empty list) which makes that the object will not be recorded as distributed, (its an internal type, dependant on the user type).
Proactive distribution
---------------------
When the user creates a type (composite or enum) we will have a hook running in `multi_ProcessUtility` after the command has been applied locally. Running after running locally makes that we already have an `ObjectAddress` for the type. This is required to mark the type as being distributed.
Keeping the type up to date
====================
For types that are recorded in `pg_dist_object` (eg. `IsObjectDistributed` returns true for the `ObjectAddress`) we will intercept the utility commands that alter the type.
- `AlterTableStmt` with `relkind` set to `OBJECT_TYPE` encapsulate changes to the fields of a composite type.
- `DropStmt` with removeType set to `OBJECT_TYPE` encapsulate `DROP TYPE`.
- `AlterEnumStmt` encapsulates changes to enum values.
Enum types can not be changed transactionally. When the execution on a worker fails a warning will be shown to the user the propagation was incomplete due to worker communication failure. An idempotent command is shown for the user to re-execute when the worker communication is fixed.
Keeping types up to date is done via the executor. Before the statement is executed locally we create a plan on how to apply it on the workers. This plan is executed after we have applied the statement locally.
All changes to types need to be done in the same transaction for types that have already been distributed and will fail with an error if parallel queries have already been executed in the same transaction. Much like foreign keys to reference tables.
For another PR I needed to add another column which would require to add
another argument to an already 9 argument function signature. In this
case it would be a boolean flag and there were already two boolean flags
in there. In my experience it becomes really easy to mess up the order
of these flags at that point. Especially because the type system doesn't
distinguish between the 3 different booleans with completely different
meanings.
So I refactored these signatures to receive a struct containing most of
these arguments. Like that you don't mess up orderening, because the
meaning of the boolean is not order dependent but fieldname dependent.
It also makes it possible to set good shared defaults for this struct.
DESCRIPTION: Refactor ensure schema exists to dependency exists
Historically we only supported schema's as table dependencies to be created on the workers before a table gets distributed. This PR puts infrastructure in place to walk pg_depend to figure out which dependencies to create on the workers. Currently only schema's are supported as objects to create before creating a table.
We also keep track of dependencies that have been created in the cluster. When we add a new node to the cluster we use this catalog to know which objects need to be created on the worker.
Side effect of knowing which objects are already distributed is that we don't have debug messages anymore when creating schema's that are already created on the workers.
* Add tuplestore helpers
* More detailed error messages in tuplestore
* Add CreateTupleDescCopy to SetupTuplestore
* Use new SetupTuplestore helper function
* Remove unnecessary copy
* Remove comment about undefined behaviour
See a9c35cf85c
clang raises a warning due to FunctionCall2InfoData technically being variable sized
This is fine, as the struct is the size we want it to be. So silence the warning
master_deactivate_node is updated to decrement the replication factor
Otherwise deactivation could have create_reference_table produce a second record
UpdateColocationGroupReplicationFactor is renamed UpdateColocationGroupReplicationFactorForReferenceTables
& the implementation looks up the record based on distributioncolumntype == InvalidOid, rather than by id
Otherwise the record's replication factor fails to be maintained when there are no reference tables
This causes no behaviorial changes, only organizes better to implement modifying CTEs
Also rename ExtactInsertRangeTableEntry to ExtractResultRelationRTE,
as the source of this function didn't match the documentation
Remove Task's upsertQuery in favor of ROW_MODIFY_NONCOMMUTATIVE
Split up AcquireExecutorShardLock into more internal functions
Tests: Normalize multi_reference_table multi_create_table_constraints
Also automated all manual tests around multi user isolation for internal citus udf's
automate upgrade_to_reference_table tests
add negative tests for lock_relation_if_exists
add tests for permissions on worker_cleanup_job_schema_cache
add tests for worker_fetch_partition_file
add tests for worker_merge_files_into_table
fix problem with worker_merge_files_and_run_query when run as non-super user and add tests for behaviour
With this commit, we're introducing the Adaptive Executor.
The commit message consists of two distinct sections. The first part explains
how the executor works. The second part consists of the commit messages of
the individual smaller commits that resulted in this commit. The readers
can search for the each of the smaller commit messages on
https://github.com/citusdata/citus and can learn more about the history
of the change.
/*-------------------------------------------------------------------------
*
* adaptive_executor.c
*
* The adaptive executor executes a list of tasks (queries on shards) over
* a connection pool per worker node. The results of the queries, if any,
* are written to a tuple store.
*
* The concepts in the executor are modelled in a set of structs:
*
* - DistributedExecution:
* Execution of a Task list over a set of WorkerPools.
* - WorkerPool
* Pool of WorkerSessions for the same worker which opportunistically
* executes "unassigned" tasks from a queue.
* - WorkerSession:
* Connection to a worker that is used to execute "assigned" tasks
* from a queue and may execute unasssigned tasks from the WorkerPool.
* - ShardCommandExecution:
* Execution of a Task across a list of placements.
* - TaskPlacementExecution:
* Execution of a Task on a specific placement.
* Used in the WorkerPool and WorkerSession queues.
*
* Every connection pool (WorkerPool) and every connection (WorkerSession)
* have a queue of tasks that are ready to execute (readyTaskQueue) and a
* queue/set of pending tasks that may become ready later in the execution
* (pendingTaskQueue). The tasks are wrapped in a ShardCommandExecution,
* which keeps track of the state of execution and is referenced from a
* TaskPlacementExecution, which is the data structure that is actually
* added to the queues and describes the state of the execution of a task
* on a particular worker node.
*
* When the task list is part of a bigger distributed transaction, the
* shards that are accessed or modified by the task may have already been
* accessed earlier in the transaction. We need to make sure we use the
* same connection since it may hold relevant locks or have uncommitted
* writes. In that case we "assign" the task to a connection by adding
* it to the task queue of specific connection (in
* AssignTasksToConnections). Otherwise we consider the task unassigned
* and add it to the task queue of a worker pool, which means that it
* can be executed over any connection in the pool.
*
* A task may be executed on multiple placements in case of a reference
* table or a replicated distributed table. Depending on the type of
* task, it may not be ready to be executed on a worker node immediately.
* For instance, INSERTs on a reference table are executed serially across
* placements to avoid deadlocks when concurrent INSERTs take conflicting
* locks. At the beginning, only the "first" placement is ready to execute
* and therefore added to the readyTaskQueue in the pool or connection.
* The remaining placements are added to the pendingTaskQueue. Once
* execution on the first placement is done the second placement moves
* from pendingTaskQueue to readyTaskQueue. The same approach is used to
* fail over read-only tasks to another placement.
*
* Once all the tasks are added to a queue, the main loop in
* RunDistributedExecution repeatedly does the following:
*
* For each pool:
* - ManageWorkPool evaluates whether to open additional connections
* based on the number unassigned tasks that are ready to execute
* and the targetPoolSize of the execution.
*
* Poll all connections:
* - We use a WaitEventSet that contains all (non-failed) connections
* and is rebuilt whenever the set of active connections or any of
* their wait flags change.
*
* We almost always check for WL_SOCKET_READABLE because a session
* can emit notices at any time during execution, but it will only
* wake up WaitEventSetWait when there are actual bytes to read.
*
* We check for WL_SOCKET_WRITEABLE just after sending bytes in case
* there is not enough space in the TCP buffer. Since a socket is
* almost always writable we also use WL_SOCKET_WRITEABLE as a
* mechanism to wake up WaitEventSetWait for non-I/O events, e.g.
* when a task moves from pending to ready.
*
* For each connection that is ready:
* - ConnectionStateMachine handles connection establishment and failure
* as well as command execution via TransactionStateMachine.
*
* When a connection is ready to execute a new task, it first checks its
* own readyTaskQueue and otherwise takes a task from the worker pool's
* readyTaskQueue (on a first-come-first-serve basis).
*
* In cases where the tasks finish quickly (e.g. <1ms), a single
* connection will often be sufficient to finish all tasks. It is
* therefore not necessary that all connections are established
* successfully or open a transaction (which may be blocked by an
* intermediate pgbouncer in transaction pooling mode). It is therefore
* essential that we take a task from the queue only after opening a
* transaction block.
*
* When a command on a worker finishes or the connection is lost, we call
* PlacementExecutionDone, which then updates the state of the task
* based on whether we need to run it on other placements. When a
* connection fails or all connections to a worker fail, we also call
* PlacementExecutionDone for all queued tasks to try the next placement
* and, if necessary, mark shard placements as inactive. If a task fails
* to execute on all placements, the execution fails and the distributed
* transaction rolls back.
*
* For multi-row INSERTs, tasks are executed sequentially by
* SequentialRunDistributedExecution instead of in parallel, which allows
* a high degree of concurrency without high risk of deadlocks.
* Conversely, multi-row UPDATE/DELETE/DDL commands take aggressive locks
* which forbids concurrency, but allows parallelism without high risk
* of deadlocks. Note that this is unrelated to SEQUENTIAL_CONNECTION,
* which indicates that we should use at most one connection per node, but
* can run tasks in parallel across nodes. This is used when there are
* writes to a reference table that has foreign keys from a distributed
* table.
*
* Execution finishes when all tasks are done, the query errors out, or
* the user cancels the query.
*
*-------------------------------------------------------------------------
*/
All the commits involved here:
* Initial unified executor prototype
* Latest changes
* Fix rebase conflicts to master branch
* Add missing variable for assertion
* Ensure that master_modify_multiple_shards() returns the affectedTupleCount
* Adjust intermediate result sizes
The real-time executor uses COPY command to get the results
from the worker nodes. Unified executor avoids that which
results in less data transfer. Simply adjust the tests to lower
sizes.
* Force one connection per placement (or co-located placements) when requested
The existing executors (real-time and router) always open 1 connection per
placement when parallel execution is requested.
That might be useful under certain circumstances:
(a) User wants to utilize as much as CPUs on the workers per
distributed query
(b) User has a transaction block which involves COPY command
Also, lots of regression tests rely on this execution semantics.
So, we'd enable few of the tests with this change as well.
* For parameters to be resolved before using them
For the details, see PostgreSQL's copyParamList()
* Unified executor sorts the returning output
* Ensure that unified executor doesn't ignore sequential execution of DDLJob's
Certain DDL commands, mainly creating foreign keys to reference tables,
should be executed sequentially. Otherwise, we'd end up with a self
distributed deadlock.
To overcome this situaiton, we set a flag `DDLJob->executeSequentially`
and execute it sequentially. Note that we have to do this because
the command might not be called within a transaction block, and
we cannot call `SetLocalMultiShardModifyModeToSequential()`.
This fixes at least two test: multi_insert_select_on_conflit.sql and
multi_foreign_key.sql
Also, I wouldn't mind scattering local `targetPoolSize` variables within
the code. The reason is that we'll soon have a GUC (or a global
variable based on a GUC) that'd set the pool size. In that case, we'd
simply replace `targetPoolSize` with the global variables.
* Fix 2PC conditions for DDL tasks
* Improve closing connections that are not fully established in unified execution
* Support foreign keys to reference tables in unified executor
The idea for supporting foreign keys to reference tables is simple:
Keep track of the relation accesses within a transaction block.
- If a parallel access happens on a distributed table which
has a foreign key to a reference table, one cannot modify
the reference table in the same transaction. Otherwise,
we're very likely to end-up with a self-distributed deadlock.
- If an access to a reference table happens, and then a parallel
access to a distributed table (which has a fkey to the reference
table) happens, we switch to sequential mode.
Unified executor misses the function calls that marks the relation
accesses during the execution. Thus, simply add the necessary calls
and let the logic kick in.
* Make sure to close the failed connections after the execution
* Improve comments
* Fix savepoints in unified executor.
* Rebuild the WaitEventSet only when necessary
* Unclaim connections on all errors.
* Improve failure handling for unified executor
- Implement the notion of errorOnAnyFailure. This is similar to
Critical Connections that the connection managament APIs provide
- If the nodes inside a modifying transaction expand, activate 2PC
- Fix few bugs related to wait event sets
- Mark placement INACTIVE during the execution as much as possible
as opposed to we do in the COMMIT handler
- Fix few bugs related to scheduling next placement executions
- Improve decision on when to use 2PC
Improve the logic to start a transaction block for distributed transactions
- Make sure that only reference table modifications are always
executed with distributed transactions
- Make sure that stored procedures and functions are executed
with distributed transactions
* Move waitEventSet to DistributedExecution
This could also be local to RunDistributedExecution(), but in that case
we had to mark it as "volatile" to avoid PG_TRY()/PG_CATCH() issues, and
cast it to non-volatile when doing WaitEventSetFree(). We thought that
would make code a bit harder to read than making this non-local, so we
move it here. See comments for PG_TRY() in postgres/src/include/elog.h
and "man 3 siglongjmp" for more context.
* Fix multi_insert_select test outputs
Two things:
1) One complex transaction block is now supported. Simply update
the test output
2) Due to dynamic nature of the unified executor, the orders of
the errors coming from the shards might change (e.g., all of
the queries on the shards would fail, but which one appears
on the error message?). To fix that, we simply added it to
our shardId normalization tool which happens just before diff.
* Fix subeury_and_cte test
The error message is updated from:
failed to execute task
To:
more than one row returned by a subquery or an expression
which is a lot clearer to the user.
* Fix intermediate_results test outputs
Simply update the error message from:
could not receive query results
to
result "squares" does not exist
which makes a lot more sense.
* Fix multi_function_in_join test
The error messages update from:
Failed to execute task XXX
To:
function f(..) does not exist
* Fix multi_query_directory_cleanup test
The unified executor does not create any intermediate files.
* Fix with_transactions test
A test case that just started to work fine
* Fix multi_router_planner test outputs
The error message is update from:
Could not receive query results
To:
Relation does not exists
which is a lot more clearer for the users
* Fix multi_router_planner_fast_path test
The error message is update from:
Could not receive query results
To:
Relation does not exists
which is a lot more clearer for the users
* Fix isolation_copy_placement_vs_modification by disabling select_opens_transaction_block
* Fix ordering in isolation_multi_shard_modify_vs_all
* Add executor locks to unified executor
* Make sure to allocate enought WaitEvents
The previous code was missing the waitEvents for the latch and
postmaster death.
* Fix rebase conflicts for master rebase
* Make sure that TRUNCATE relies on unified executor
* Implement true sequential execution for multi-row INSERTS
Execute the individual tasks executed one by one. Note that this is different than
MultiShardConnectionType == SEQUENTIAL_CONNECTION case (e.g., sequential execution
mode). In that case, running the tasks across the nodes in parallel is acceptable
and implemented in that way.
However, the executions that are qualified here would perform poorly if the
tasks across the workers are executed in parallel. We currently qualify only
one class of distributed queries here, multi-row INSERTs. If we do not enforce
true sequential execution, concurrent multi-row upserts could easily form
a distributed deadlock when the upserts touch the same rows.
* Remove SESSION_LIFESPAN flag in unified_executor
* Apply failure test updates
We've changed the failure behaviour a bit, and also the error messages
that show up to the user. This PR covers majority of the updates.
* Unified executor honors citus.node_connection_timeout
With this commit, unified executor errors out if even
a single connection cannot be established within
citus.node_connection_timeout.
And, as a side effect this fixes failure_connection_establishment
test.
* Properly increment/decrement pool size variables
Before this commit, the idle and active connection
counts were not properly calculated.
* insert_select_executor goes through unified executor.
* Add missing file for task tracker
* Modify ExecuteTaskListExtended()'s signature
* Sort output of INSERT ... SELECT ... RETURNING
* Take partition locks correctly in unified executor
* Alternative implementation for force_max_query_parallelization
* Fix compile warnings in unified executor
* Fix style issues
* Decrement idleConnectionCount when idle connection is lost
* Always rebuild the wait event sets
In the previous implementation, on waitFlag changes, we were only
modifying the wait events. However, we've realized that it might
be an over optimization since (a) we couldn't see any performance
benefits (b) we see some errors on failures and because of (a)
we prefer to disable it now.
* Make sure to allocate enough sized waitEventSet
With multi-row INSERTs, we might have more sessions than
task*workerCount after few calls of RunDistributedExecution()
because the previous sessions would also be alive.
Instead, re-allocate events when the connectino set changes.
* Implement SELECT FOR UPDATE on reference tables
On master branch, we do two extra things on SELECT FOR UPDATE
queries on reference tables:
- Acquire executor locks
- Execute the query on all replicas
With this commit, we're implementing the same logic on the
new executor.
* SELECT FOR UPDATE opens transaction block even if SelectOpensTransactionBlock disabled
Otherwise, users would be very confused and their logic is very likely
to break.
* Fix build error
* Fix the newConnectionCount calculation in ManageWorkerPool
* Fix rebase conflicts
* Fix minor test output differences
* Fix citus indent
* Remove duplicate sorts that is added with rebase
* Create distributed table via executor
* Fix wait flags in CheckConnectionReady
* failure_savepoints output for unified executor.
* failure_vacuum output (pg 10) for unified executor.
* Fix WaitEventSetWait timeout in unified executor
* Stabilize failure_truncate test output
* Add an ORDER BY to multi_upsert
* Fix regression test outputs after rebase to master
* Add executor.c comment
* Rename executor.c to adaptive_executor.c
* Do not schedule tasks if the failed placement is not ready to execute
Before the commit, we were blindly scheduling the next placement executions
even if the failed placement is not on the ready queue. Now, we're ensuring
that if failed placement execution is on a failed pool or session where the
execution is on the pendingQueue, we do not schedule the next task. Because
the other placement execution should be already running.
* Implement a proper custom scan node for adaptive executor
- Switch between the executors, add GUC to set the pool size
- Add non-adaptive regression test suites
- Enable CIRCLE CI for non-adaptive tests
- Adjust test output files
* Add slow start interval to the executor
* Expose max_cached_connection_per_worker to user
* Do not start slow when there are cached connections
* Consider ExecutorSlowStartInterval in NextEventTimeout
* Fix memory issues with ReceiveResults().
* Disable executor via TaskExecutorType
* Make sure to execute the tests with the other executor
* Use task_executor_type to enable-disable adaptive executor
* Remove useless code
* Adjust the regression tests
* Add slow start regression test
* Rebase to master
* Fix test failures in adaptive executor.
* Rebase to master - 2
* Improve comments & debug messages
* Set force_max_query_parallelization in isolation_citus_dist_activity
* Force max parallelization for creating shards when asked to use exclusive connection.
* Adjust the default pool size
* Expand description of max_adaptive_executor_pool_size GUC
* Update warnings in FinishRemoteTransactionCommit()
* Improve session clean up at the end of execution
Explicitly list all the states that the execution might end,
otherwise warn.
* Remove MULTI_CONNECTION_WAIT_RETRY which is not used at all
* Add more ORDER BYs to multi_mx_partitioning
- All the schema creations on the workers will now be via superuser connections
- If a shard is being repaired or a shard is replicated, we will create the
schema only in the relevant worker; and in all the other cases where a schema
creation is needed, we will block operations until we ensure the schema exists
in all the workers
When `master_update_node` is called to update a node's location it waits for appropriate locks to become available. This is useful during normal operation as new operations will be blocked till after the metadata update while running operations have time to finish.
When `master_update_node` is called after a node failure it is less useful to wait for running operations to finish as they can't. The lock being held indicates an operation that once attempted to commit will fail as the machine already failed. Now the downside is the failover is postponed till the termination point of the operation. This has been observed by users to take a significant amount of time causing the rest of the system to be observed unavailable.
With this patch it is possible in such situations to invoke `master_update_node` with 2 optional arguments:
- `force` (bool defaults to `false`): When called with true the update of the metadata will be forced to proceed by terminating conflicting backends. A cancel is not enough as the backend might be in idle time (eg. an interactive session, or going back and forth between an appliaction), therefore a more intrusive solution of termination is used here.
- `lock_cooldown` (int defaults to `10000`): This is the time in milliseconds before conflicting backends are terminated. This is to allow the backends to finish cleanly before terminating them. This allows the user to set an upperbound to the expected time to complete the metadata update, eg. performing the failover.
The functionality is implemented by spawning a background worker that has the task of helping a certain backend in acquiring its locks. The backend is either terminated on successful execution of the metadata update, or once the memory context of the expression gets reset, eg. on a cancel of the statement.
InitializeCaches() method may prematurely set
performedInitialization without actually creating
DistShardCacheHash.
Fix makes sure flag is set only if DistShardCacheHash is created successfully.
Also introduced a new memory context to allocate aforementioned hash tables.
If allocation/initialization fails for any reason we make sure
memory is reclaimed by deleting the memory context.
Before this commit, shardPlacements were identified with shardId, nodeName
and nodeport. Instead of using nodeName and nodePort, we now use nodeId
since it apparently has performance benefits in several places in the
code.
We'd been ignoring updating uncrustify for some time now because I'd
thought these were misclassifications that would require an update in
our rules to address. Turns out they're legit, so I'm checking them in.
Before this commit, Citus supported INSERT...SELECT queries with
ON CONFLICT or RETURNING clauses only for pushdownable ones, since
queries supported via coordinator were utilizing COPY infrastructure
of PG to send selected tuples to the target worker nodes.
After this PR, INSERT...SELECT queries with ON CONFLICT or RETURNING
clauses will be performed in two phases via coordinator. In the first
phase selected tuples will be saved to the intermediate table which
is colocated with target table of the INSERT...SELECT query. Note that,
a utility function to save results to the colocated intermediate result
also implemented as a part of this commit. In the second phase, INSERT..
SELECT query is directly run on the worker node using the intermediate
table as the source table.
When initializing a Citus formation automatically from an external piece of
software such as Citus-HA, the following process process may be used:
- decide on the groupId in the external software
- SELECT * FROM master_add_inactive_node('localhost', 9701, groupid => X)
When Citus checks for maxGroupId, it forbids other software to pick their
own group Ids to ues with the master_add_inactive_node() API.
This patch removes the extra testing around maxGroupId.
The file handling the utility functions (DDL) for citus organically grew over time and became unreasonably large. This refactor takes that file and refactored the functionality into separate files per command. Initially modeled after the directory and file layout that can be found in postgres.
Although the size of the change is quite big there are barely any code changes. Only one two functions have been added for readability purposes:
- PostProcessIndexStmt which is extracted from PostProcessUtility
- PostProcessAlterTableStmt which is extracted from multi_ProcessUtility
A README.md has been added to `src/backend/distributed/commands` describing the contents of the module and every file in the module.
We need more documentation around the overloading of the COPY command, for now the boilerplate has been added for people with better knowledge to fill out.
After Fast ALTER TABLE ADD COLUMN with a non-NULL default in PG11, physical heaps might not contain all attributes after a ALTER TABLE ADD COLUMN happens. heap_getattr() returns NULL when the physical tuple doesn't contain an attribute. So we should use heap_deform_tuple() in these cases, which fills in the missing attributes.
Our catalog tables evolve over time, and an upgrade might involve some ALTER TABLE ADD COLUMN commands.
Note that we don't need to worry about postgres catalog tables and we can use heap_getattr() for them, because they only change between major versions.
This also fixes#2453.
* Keep track of cached entries in case of interruption.
Previously we set DistTableCacheEntry->sortedShardIntervalArray
and DistTableCacheEntry->shardIntervalArrayLength after we entered
all related shard entries into DistShardCacheHash. The drawback was
that if populating DistShardCacheHash was interrupted,
ResetDistTableCacheEntry() didn't see the shard hash entries created,
so was unable to clean them up.
This patch fixes that by setting sortedShardIntervalArray earlier,
and incrementing shardIntervalArrayLength as we enter shards into
the cache.
With this commit, we all partitioned distributed tables with
replication factor > 1. However, we also have many restrictions.
In summary, we disallow all kinds of modifications (including DDLs)
on the partition tables. Instead, the user is allowed to run the
modifications over the parent table.
The necessity for such a restriction have two aspects:
- We need to acquire shard resource locks appropriately
- We need to handle marking partitions INVALID in case
of any failures. Note that, in theory, the parent table
should also become INVALID, which is too aggressive.
We acquire distributed lock on all mx nodes for truncated
tables before actually doing truncate operation.
This is needed for distributed serialization of the truncate
command without causing a deadlock.
This commit by default enables hiding shard names on MX workers
by simple replacing `pg_table_is_visible()` calls with
`citus_table_is_visible()` calls on the MX worker nodes. The latter
function filters out tables that are known to be shards.
The main motivation of this change is a better UX. The functionality
can be opted out via a GUC.
We also added two views, namely citus_shards_on_worker and
citus_shard_indexes_on_worker such that users can query
them to see the shards and their corresponding indexes.
We also added debug messages such that the filtered tables can
be interactively seen by setting the level to DEBUG1.
When a hash distributed table have a foreign key to a reference
table, there are few restrictions we have to apply in order to
prevent distributed deadlocks or reading wrong results.
The necessity to apply the restrictions arise from cascading
nature of foreign keys. When a foreign key on a reference table
cascades to a distributed table, a single operation over a single
connection can acquire locks on multiple shards of the distributed
table. Thus, any parallel operation on that distributed table, in the
same transaction should not open parallel connections to the shards.
Otherwise, we'd either end-up with a self-distributed deadlock or
read wrong results.
As briefly described above, the restrictions that we apply is done
by tracking the distributed/reference relation accesses inside
transaction blocks, and act accordingly when necessary.
The two main rules are as follows:
- Whenever a parallel distributed relation access conflicts
with a consecutive reference relation access, Citus errors
out
- Whenever a reference relation access is followed by a
conflicting parallel relation access, the execution mode
is switched to sequential mode.
There are also some other notes to mention:
- If the user does SET LOCAL citus.multi_shard_modify_mode
TO 'sequential';, all the queries should simply work with
using one connection per worker and sequentially executing
the commands. That's obviously a slower approach than Citus'
usual parallel execution. However, we've at least have a way
to run all commands successfully.
- If an unrelated parallel query executed on any distributed
table, we cannot switch to sequential mode. Because, the essense
of sequential mode is using one connection per worker. However,
in the presence of a parallel connection, the connection manager
picks those connections to execute the commands. That contradicts
with our purpose, thus we error out.
- COPY to a distributed table cannot be executed in sequential mode.
Thus, if we switch to sequential mode and COPY is executed, the
operation fails and there is currently no way of implementing that.
Note that, when the local table is not empty and create_distributed_table
is used, citus uses COPY internally. Thus, in those cases,
create_distributed_table() will also fail.
- There is a GUC called citus.enforce_foreign_key_restrictions
to disable all the checks. We added that GUC since the restrictions
we apply is sometimes a bit more restrictive than its necessary.
The user might want to relax those. Similarly, if you don't have
CASCADEing reference tables, you might consider disabling all the
checks.
This table will be used by Citus Enterprise to populate authentication-
related fields in outbound connections; Citus Community lacks support
for this functionality.
To support more flexible (i.e. not at compile-time) specification of
libpq connection parameters, this change adds a new GUC, node_conninfo,
which must be a space-separated string of key-value pairs suitable for
parsing by libpq's connection establishment methods.
To avoid rebuilding and parsing these values at connection time, this
change also adds a cache in front of the configuration params to permit
immediate use of any previously-calculated parameters.
After this commit DDL commands honour `citus.multi_shard_modify_mode`.
We preferred using the code-path that executes single task router
queries (e.g., ExecuteSingleModifyTask()) in order not to invent
a new executor that is only applicable for DDL commands that require
sequential execution.
Previously we checked if an operator is in pg_catalog, and if it wasn't we prefixed it with namespace in worker queries. This can have a huge impact on performance of physical planner when using custom data types.
This happened regardless of current search_path config, because Citus overrides the search path in get_query_def_extended(). When we do so, the check for existence of the operator in current search path in generate_operator_name() fails for any operators outside pg_catalog. This means that nothing gets cached, and in the following calls we will again recheck the system tables for existence of the operators, which took an additional 40-50ms for some of the usecases we were seeing.
In this change we skip the pg_catalog check, and always prefix the operator with its namespace.
* Change worker_hash_partition_table() such that the
divergence between Citus planner's hashing and
worker_hash_partition_table() becomes the same.
* Rename single partitioning to single range partitioning.
* Add single hash repartitioning. Basically, logical planner
treats single hash and range partitioning almost equally.
Physical planner, on the other hand, treats single hash and
dual hash repartitioning almost equally (except for JoinPruning).
* Add a new GUC to enable this feature
- changes in ruleutils_11.c is reflected
- vacuum statement api change is handled. We now allow
multi-table vacuum commands.
- some other function header changes are reflected
- api conflicts between PG11 and earlier versions
are handled by adding shims in version_compat.h
- various regression tests are fixed due output and
functionality in PG1
- no change is made to support new features in PG11
they need to be handled by new commit
Previously, we prevented creation of partitioned tables on Citus MX.
We decided to not focus on this feature until there is a need. Since
now there are requests for this feature, we are implementing support
for partitioned tables on Citus MX.
After this change all the logic related to shard data fetch logic
will be removed. Planner won't plan any ShardFetchTask anymore.
Shard fetch related steps in real time executor and task-tracker
executor have been removed.
VLAs aren't supported by Visual Studio.
- Remove all existing instances of VLAs.
- Add a flag, -Werror=vla, which makes gcc refuse to compile if we add
VLAs in the future.
* Don't use expressions inside compound statements
* Don't depend on __builtin_constant_p
* Remove reliance on S_ISLNK
* Replace use of __func__: older mcvs doesn't support this builtin
By sharing the implementation of the function AppendOptionListToString on
three call sites, we would expand an extra OPTIONS keyword in a create index
statement, and omit other bits of the specific syntax here.
This patch introduces an AppendStorageParametersToString() function that is
very similar to AppendOptionListToString() but handles WITH(a="foo",...)
syntax that is used in reloptions (aka Storage Parameters).
Fixes#1747.
PostgreSQL implements support for several relation kinds in a single
statement, such as in the AlterTableStmt case, which supports both tables
and indexes and more (see ATExecSetRelOptions in PostgreSQL source code file
src/backend/commands/tablecmds.c for an example of that).
As a consequence, this patch implements support for setting and resetting
storage parameters on both relation kinds.
The macro we were using to detect strtoull isn't set on Windows, and
just in case there are differences use a portable function from PG
instead of calling strtoull directly.
This commit introduces a new GUC to limit the intermediate
result size which we handle when we use read_intermediate_result
function for CTEs and complex subqueries.
Postgres provides OS agnosting formatting macros for
formatting 64 bit numbers. Replaced %ld %lu with
INT64_FORMAT and UINT64_FORMAT respectively.
Also found some incorrect usages of formatting
flags and fixed them.
Store pointers to shared hashes in process-local variables. Previously
pointers to shared hashes were put into shared memory. This causes
problems on EXEC_BACKEND because everybody calls execve and receives a
brand new address space; the shared hash will be in a different place
for every backend. (normally we call fork, which gives you a copy of the
address space, so these pointers remain constant)
In DistributedTablesSize() we didn't close the relations that had
replication factor > 2. This caused relcache reference leaks, and
warning messages like following in logs:
WARNING: relcache reference leak: relation "researchers" not closed
ShardPlacementList's implementation can return NIL. In previous implementation
we got a segmentation fault in this case. The relation can be dropped after
getting distributed table list but before calling SingleReplicatedTable().
If we don't propagate the errors we are catching in PG_CATCH(), database's
internal state might not be clean. So we do PG_TRY() inside a subtransaction
so we can rollback to it after catching errors.
This patch adds --with-reports-host configure option, which sets the
REPORTS_BASE_URL constant. The default is reports.citusdata.com.
It also enables stats collection in tests.
Curl writes the received response to stdout if we don't specify a response
callback or an output file. This can pollute the PostgreSQL log. In this change
we add a callback function so the response messages aren't added to the log file.
Sends a request to /v1/releases/latest?flavor=$CITUS_EDITION once a day,
which returns a response similar to {"version": "7.1.0", "major": 7,
"minor": 1, "patch": 0}. Then compares it with current Citus version,
and if the latest release is newer, logs a LOG message.
This includes:
(1) Wrap everything inside a StartTransactionCommand()/CommitTransactionCommand().
This is so we can access the database. This also switches to a new memory context
and releases it, so we don't have to do our own memory management.
(2) LockCitusExtension() so the extension cannot be dropped or created concurrently.
(3) Check CitusHasBeenLoaded() && CheckCitusVersion() before doing any work.
(4) Do not PG_TRY() inside a loop.
By this commit, citus minds the replica identity of the table when
we distribute the table. So the shards of the distributed table
have the same replica identity with the local table.
This change introduces the `pg_dist_node_metadata` which has a single jsonb value. When creating
the extension, a random server id is generated and stored in there. Everything in the metadata table
is added as a nested objected to the json payload that is sent to the reports server.
The following scenario can cause an Assert() crash if we don't do this:
- Install Citus v7.0-15
- Restart server & run a query to start maintenanced.
- Install Citus v7.1
- Restart server & run a query. This will tell user to upgrade.
- Type "UPDATE EXTENSION c" & press tab. maintenanced will start and crash
with Assert(CitusHasBeenLoaded() && CheckCitusVersion(WARNING));
This change checks Citus version before calling metadata functions so the
crash doesn't happen.
This will provide the full project name (i.e. Citus/Citus Enterprise),
and the host system, compiler, and architecture word size.
I wanted to limit the number of copied files in 'config', so I added
only config.guess and call it manually, rather than using the macro
AC_CANONICAL_HOST, which requires several other files.
Eclipse apparently doesn't scan build output looking for -D flags, so
having the value actually appear in a header is nicer for those of us
using IDEs.
Previously <curl/curl.h> was included even if compiled --without-libcurl.
This can fail when libcurl headers are not there. This commit guards this
include by checks for HAVE_LIBCURL.
Adds ```citus.enable_statistics_collection``` GUC variable, which ```true``` by default, unless built without libcurl. If statistics collection is enabled, sends basic usage data to Citus servers every 24 hours.
The data that is collected consists of:
- Citus version
- OS name & release
- Hardware Id
- Number of tables, rounded to next power of 2
- Size of data, rounded to next power of 2
- Number of workers
When a table and it's shards are dropped, and afterwards the same
shard identifiers are reused, e.g. due to a DROP & CREATE EXTENSION,
the old entry in the shard cache and the required entry in the shard
cache might be for different tables.
Force invalidation for both old and new table to fix.
We should prevent running the deadlock detection if
there is a major version change. Otherwise, the daemon
may access to obsolete metadata catalog tables.
This change fixes a use-after-free bug while renaming obsolete
`pg_worker_list.conf` file, which causes Citus to crash during upgrade
(or even extension creation) if `pg_worker_list.conf` exists.
With this commit, the maintenance deamon starts to check for
distributed deadlocks.
We also introduced a GUC variable (distributed_deadlock_detection_factor)
whose value is multiplied with Postgres' deadlock_timeout. Setting
it to -1 disables the distributed deadlock detection.
This GUC has two settings, 'always' and 'never'. When it's set to
'never' all behavior stays exactly as it was prior to this commit. When
it's set to 'always' only SELECT queries are allowed to run, and only
secondary nodes are used when processing those queries.
Add some helper functions:
- WorkerNodeIsSecondary(), checks the noderole of the worker node
- WorkerNodeIsReadable(), returns whether we're currently allowed to
read from this node
- ActiveReadableNodeList(), some functions (namely, the ones on the
SELECT path) don't require working with Primary Nodes. They should call
this function instead of ActivePrimaryNodeList(), because the latter
will error out in contexts where we're not allowed to write to nodes.
- ActiveReadableNodeCount(), like the above, replaces
ActivePrimaryNodeCount().
- EnsureModificationsCanRun(), error out if we're not currently allowed
to run queries which modify data. (Either we're in read-only mode or
use_secondary_nodes is set)
Some parts of the code were switched over to use readable nodes instead
of primary nodes:
- Deadlock detection
- DistributedTableSize,
- the router, real-time, and task tracker executors
- ShardPlacement resolution
This change declares two new functions:
`master_update_table_statistics` updates the statistics of shards belong
to the given table as well as its colocated tables.
`get_colocated_shard_array` returns the ids of colocated shards of a
given shard.
This is a pretty substantial refactoring of the existing modify path
within the router executor and planner. In particular, we now hunt for
all VALUES range table entries in INSERT statements and group the rows
contained therein by shard identifier. These rows are stashed away for
later in "ModifyRoute" elements. During deparse, the appropriate RTE
is extracted from the Query and its values list is replaced by these
rows before any SQL is generated.
In this way, we can create multiple Tasks, but only one per shard, to
piecemeal execute a multi-row INSERT. The execution of jobs containing
such tasks now exclusively go through the "multi-router executor" which
was previously used for e.g. INSERT INTO ... SELECT.
By piggybacking onto that executor, we participate in ongoing trans-
actions, get rollback-ability, etc. In short order, the only remaining
use of the "single modify" router executor will be for bare single-
row INSERT statements (i.e. those not in a transaction).
This change appropriately handles deferred pruning as well as master-
evaluated functions.
With this PR, Citus starts to support all possible ways to create
distributed partitioned tables. These are;
- Distributing already created partitioning hierarchy
- CREATE TABLE ... PARTITION OF a distributed_table
- ALTER TABLE distributed_table ATTACH PARTITION non_distributed_table
- ALTER TABLE distributed_table ATTACH PARTITION distributed_table
We also support DETACHing partitions from partitioned tables and propogating
TRUNCATE and DDL commands to distributed partitioned tables.
This PR also refactors some parts of distributed table creation logic.
- master_activate_node and master_disable_node correctly toggle
isActive, without crashing
- master_add_node rejects duplicate nodes, even if they're in different
clusters
- master_remove_node allows removing nodes in different clusters
This commit is preperation for introducing distributed partitioned
table support. We want to clean and refactor some code in distributed
table creation logic so that we can handle partitioned tables in more
robust way.
- Never release locks
- AddNodeMetadata takes ShareRowExclusiveLock so it'll conflict with the
trigger which prevents multiple primary nodes.
- ActivateNode and SetNodeState used to take AccessShareLock, but they
modify the table so they should take RowExclusiveLock.
- DeleteNodeRow and InsertNodeRow used to take AccessExclusiveLock but
only need RowExclusiveLock.
- master_add_node enforces that there is only one primary per group
- there's also a trigger on pg_dist_node to prevent multiple primaries
per group
- functions in metadata cache only return primary nodes
- Rename ActiveWorkerNodeList -> ActivePrimaryNodeList
- Rename WorkerGetLive{Node->Group}Count()
- Refactor WorkerGetRandomCandidateNode
- master_remove_node only complains about active shard placements if the
node being removed is a primary.
- master_remove_node only deletes all reference table placements in the
group if the node being removed is the primary.
- Rename {Node->NodeGroup}HasShardPlacements, this reflects the behavior it
already had.
- Rename DeleteAllReferenceTablePlacementsFrom{Node->NodeGroup}. This also
reflects the behavior it already had, but the new signature forces the
caller to pass in a groupId
- Rename {WorkerGetLiveGroup->ActivePrimaryNode}Count
GCC 7 added `-Wimplicit-fallthrough` to warn for not explicitly specified switch/case fall-throughs.
According to https://gcc.gnu.org/gcc-7/changes.html, to suppress that warning we could either use `__attribute__(fallthrough)`, which didn't seem to work for earlier GCC versions, or a `/* fallthrough */` comment just before the following `case`.
Previously Citus code had the fall-through comments inside the brackets, which didn't seem to suppress the warning. Putting a `/* fallthrough */` comment outside the brackets and right before the `case` fixes the problem.
Comes with a few changes:
- Change the signature of some functions to accept groupid
- InsertShardPlacementRow
- DeleteShardPlacementRow
- UpdateShardPlacementState
- NodeHasActiveShardPlacements returns true if the group the node is a
part of has any active shard placements
- TupleToShardPlacement now returns ShardPlacements which have NULL
nodeName and nodePort.
- Populate (nodeName, nodePort) when creating ShardPlacements
- Disallow removing a node if it contains any shard placements
- DeleteAllReferenceTablePlacementsFromNode matches based on group. This
doesn't change behavior for now (while there is only one node per
group), but means in the future callers should be careful about
calling it on a secondary node, it'll delete placements on the primary.
- Create concept of a GroupShardPlacement, which represents an actual
tuple in pg_dist_placement and is distinct from a ShardPlacement,
which has been resolved to a specific node. In the future
ShardPlacement should be renamed to NodeShardPlacement.
- Create some triggers which allow existing code to continue to insert
into and update pg_dist_shard_placement as if it still existed.
This commit is intended to be a base for supporting declarative partitioning
on distributed tables. Here we add the following utility functions and their
unit tests:
* Very basic functions including differnentiating partitioned tables and
partitions, listing the partitions
* Generating the PARTITION BY (expr) and adding this to the DDL events
of partitioned tables
* Ability to generate text representations of the ranges for partitions
* Ability to generate the `ALTER TABLE parent_table ATTACH PARTITION
partition_table FOR VALUES value_range`
* Ability to apply add shard ids to the above command using
`worker_apply_inter_shard_ddl_command()`
* Ability to generate `ALTER TABLE parent_table DETACH PARTITION`
Hadi Moshayedi
Jelte Fennema
Marco Slot
Hanefi Onaldi
Philip Dubé
Halil Ozan Akgul
Hadi Moshayedi
SaitTalhaNisanci
Önder Kalacı
Onur TIRTIR
Marco Slot
Nils Dijk
exialin
Murat Tuncer
Jason Petersen
Nils Dijk
Jason Petersen
Jason Petersen
velioglu
Dimitri Fontaine
Hadi Moshayedi
mehmet furkan şahin
Burak Yucesoy
Brian Cloutier
Metin Doslu
Brian Cloutier
Murat Tuncer
Andres Freund
Eren Başak