1
0
Fork 0
mirror of https://we.phorge.it/source/phorge.git synced 2024-11-25 08:12:40 +01:00
phorge-phorge/src/applications/drydock/worker/DrydockResourceUpdateWorker.php
epriestley 7168d8edd9 Make Drydock reclaim unused resources when it reaches a resource limit
Summary:
Fixes T9994. Currently, when Drydock can't allocate a new resource because some limit has been reached, it waits patiently for a resource to become available.

It is possible that no resource will ever become available. Particularly with "Working Copy" resources, the new lease may want a copy of `rB`, but the resource may already be maxed out on `rA`.

Right now, no process exists to automatically reclaim the unused `rA`.

When we encounter this situation, try to reclaim one of the other resources if it is just sitting there unused.

Specifically:

  - Add a "reclaim" command which means "release this resource //if// it is completely unused".
  - Add a `bin/drydock reclaim` to send this command to every active resource.
  - When we try to acquire a resource and can't, but only because of some kind of limit / utilization problem, try to release an unused resource to free up some room.

Test Plan:
  - Set "Working Copy" resource limit to 1.
  - Ran "Test Configuration" in `rA`, which worked.
  - Ran "Test Configuration" in `rB`, which hung forever.
  - Applied patch.
  - Ran "Test Configuration" in `rB`, saw it reclaim the `rA` resource, use the slot, then succeed.
  - Ran "Test Configuration" in `rA` again, saw it grab the slot back.
  - Ran `bin/drydock reclaim` and saw it reclaim a bunch of old orphaned resources.

Reviewers: chad

Reviewed By: chad

Maniphest Tasks: T9994

Differential Revision: https://secure.phabricator.com/D14819
2015-12-18 11:55:51 -08:00

301 lines
7.4 KiB
PHP

<?php
/**
* @task update Updating Resources
* @task command Processing Commands
* @task activate Activating Resources
* @task release Releasing Resources
* @task break Breaking Resources
* @task destroy Destroying Resources
*/
final class DrydockResourceUpdateWorker extends DrydockWorker {
protected function doWork() {
$resource_phid = $this->getTaskDataValue('resourcePHID');
$hash = PhabricatorHash::digestForIndex($resource_phid);
$lock_key = 'drydock.resource:'.$hash;
$lock = PhabricatorGlobalLock::newLock($lock_key)
->lock(1);
try {
$resource = $this->loadResource($resource_phid);
$this->handleUpdate($resource);
} catch (Exception $ex) {
$lock->unlock();
$this->flushDrydockTaskQueue();
throw $ex;
}
$lock->unlock();
}
/* -( Updating Resources )------------------------------------------------- */
/**
* Update a resource, handling exceptions thrown during the update.
*
* @param DrydockReosource Resource to update.
* @return void
* @task update
*/
private function handleUpdate(DrydockResource $resource) {
try {
$this->updateResource($resource);
} catch (Exception $ex) {
if ($this->isTemporaryException($ex)) {
$this->yieldResource($resource, $ex);
} else {
$this->breakResource($resource, $ex);
}
}
}
/**
* Update a resource.
*
* @param DrydockResource Resource to update.
* @return void
* @task update
*/
private function updateResource(DrydockResource $resource) {
$this->processResourceCommands($resource);
$resource_status = $resource->getStatus();
switch ($resource_status) {
case DrydockResourceStatus::STATUS_PENDING:
$this->activateResource($resource);
break;
case DrydockResourceStatus::STATUS_ACTIVE:
// Nothing to do.
break;
case DrydockResourceStatus::STATUS_RELEASED:
case DrydockResourceStatus::STATUS_BROKEN:
$this->destroyResource($resource);
break;
case DrydockResourceStatus::STATUS_DESTROYED:
// Nothing to do.
break;
}
$this->yieldIfExpiringResource($resource);
}
/**
* Convert a temporary exception into a yield.
*
* @param DrydockResource Resource to yield.
* @param Exception Temporary exception worker encountered.
* @task update
*/
private function yieldResource(DrydockResource $resource, Exception $ex) {
$duration = $this->getYieldDurationFromException($ex);
$resource->logEvent(
DrydockResourceActivationYieldLogType::LOGCONST,
array(
'duration' => $duration,
));
throw new PhabricatorWorkerYieldException($duration);
}
/* -( Processing Commands )------------------------------------------------ */
/**
* @task command
*/
private function processResourceCommands(DrydockResource $resource) {
if (!$resource->canReceiveCommands()) {
return;
}
$this->checkResourceExpiration($resource);
$commands = $this->loadCommands($resource->getPHID());
foreach ($commands as $command) {
if (!$resource->canReceiveCommands()) {
break;
}
$this->processResourceCommand($resource, $command);
$command
->setIsConsumed(true)
->save();
}
}
/**
* @task command
*/
private function processResourceCommand(
DrydockResource $resource,
DrydockCommand $command) {
switch ($command->getCommand()) {
case DrydockCommand::COMMAND_RELEASE:
$this->releaseResource($resource, null);
break;
case DrydockCommand::COMMAND_RECLAIM:
$reclaimer_phid = $command->getAuthorPHID();
$this->releaseResource($resource, $reclaimer_phid);
break;
}
}
/* -( Activating Resources )----------------------------------------------- */
/**
* @task activate
*/
private function activateResource(DrydockResource $resource) {
$blueprint = $resource->getBlueprint();
$blueprint->activateResource($resource);
$this->validateActivatedResource($blueprint, $resource);
}
/**
* @task activate
*/
private function validateActivatedResource(
DrydockBlueprint $blueprint,
DrydockResource $resource) {
if (!$resource->isActivatedResource()) {
throw new Exception(
pht(
'Blueprint "%s" (of type "%s") is not properly implemented: %s '.
'must actually allocate the resource it returns.',
$blueprint->getBlueprintName(),
$blueprint->getClassName(),
'allocateResource()'));
}
}
/* -( Releasing Resources )------------------------------------------------ */
/**
* @task release
*/
private function releaseResource(
DrydockResource $resource,
$reclaimer_phid) {
if ($reclaimer_phid) {
if (!$this->canReclaimResource($resource)) {
return;
}
$resource->logEvent(
DrydockResourceReclaimLogType::LOGCONST,
array(
'reclaimerPHID' => $reclaimer_phid,
));
}
$viewer = $this->getViewer();
$drydock_phid = id(new PhabricatorDrydockApplication())->getPHID();
$resource
->setStatus(DrydockResourceStatus::STATUS_RELEASED)
->save();
$statuses = array(
DrydockLeaseStatus::STATUS_PENDING,
DrydockLeaseStatus::STATUS_ACQUIRED,
DrydockLeaseStatus::STATUS_ACTIVE,
);
$leases = id(new DrydockLeaseQuery())
->setViewer($viewer)
->withResourcePHIDs(array($resource->getPHID()))
->withStatuses($statuses)
->execute();
foreach ($leases as $lease) {
$command = DrydockCommand::initializeNewCommand($viewer)
->setTargetPHID($lease->getPHID())
->setAuthorPHID($drydock_phid)
->setCommand(DrydockCommand::COMMAND_RELEASE)
->save();
$lease->scheduleUpdate();
}
$this->destroyResource($resource);
}
/* -( Breaking Resources )------------------------------------------------- */
/**
* @task break
*/
private function breakResource(DrydockResource $resource, Exception $ex) {
switch ($resource->getStatus()) {
case DrydockResourceStatus::STATUS_BROKEN:
case DrydockResourceStatus::STATUS_RELEASED:
case DrydockResourceStatus::STATUS_DESTROYED:
// If the resource was already broken, just throw a normal exception.
// This will retry the task eventually.
throw new PhutilProxyException(
pht(
'Unexpected failure while destroying resource ("%s").',
$resource->getPHID()),
$ex);
}
$resource
->setStatus(DrydockResourceStatus::STATUS_BROKEN)
->save();
$resource->scheduleUpdate();
$resource->logEvent(
DrydockResourceActivationFailureLogType::LOGCONST,
array(
'class' => get_class($ex),
'message' => $ex->getMessage(),
));
throw new PhabricatorWorkerPermanentFailureException(
pht(
'Permanent failure while activating resource ("%s"): %s',
$resource->getPHID(),
$ex->getMessage()));
}
/* -( Destroying Resources )----------------------------------------------- */
/**
* @task destroy
*/
private function destroyResource(DrydockResource $resource) {
$blueprint = $resource->getBlueprint();
$blueprint->destroyResource($resource);
DrydockSlotLock::releaseLocks($resource->getPHID());
$resource
->setStatus(DrydockResourceStatus::STATUS_DESTROYED)
->save();
}
}