Version clustered, observed repositories in a reasonable way (by largest discovered HEAD)

epriestley · epriestley · commit f5f784f4c1d0 · 2016-05-30T09:53:01.000-07:00
Summary: Ref T4292. For hosted, clustered repositories we have a good way to increment the internal version of the repository: every time a user pushes something, we increment the version by 1. We don't have a great way to do this for observed/remote repositories because when we `git fetch` we might get nothing, or we might get some changes, and we can't easily tell //what// changes we got. For example, if we see that another node is at "version 97", and we do a fetch and see some changes, we don't know if we're in sync with them (i.e., also at "version 97") or ahead of them (at "version 98"). This implements a simple way to version an observed repository: - Take the head of every branch/tag. - Look them up. - Pick the biggest internal ID number. This will work //except// when branches are deleted, which could cause the version to go backward if the "biggest commit" is the one that was deleted. This should be OK, since it's rare and the effects are minor and the repository will "self-heal" on the next actual push. Test Plan: - Created an observed repository. - Ran `bin/repository update` and observed a sensible version number appear in the version table. - Pushed to the remote, did another update, saw a sensible update. - Did an update with no push, saw no effect on version number. - Toggled repository to hosted, saw the version reset. - Simulated read traffic to out-of-sync node, saw it do a remote fetch. Reviewers: chad Reviewed By: chad Maniphest Tasks: T4292 Differential Revision: https://secure.phabricator.com/D15986
diff --git a/src/applications/diffusion/conduit/DiffusionBranchQueryConduitAPIMethod.php b/src/applications/diffusion/conduit/DiffusionBranchQueryConduitAPIMethod.php
@@ -56,7 +56,10 @@ protected function getGitResult(ConduitAPIRequest $request) {
     } else {
       $refs = id(new DiffusionLowLevelGitRefQuery())
         ->setRepository($repository)
-        ->withIsOriginBranch(true)
+        ->withRefTypes(
+          array(
+            PhabricatorRepositoryRefCursor::TYPE_BRANCH,
+          ))
         ->execute();
     }
 
diff --git a/src/applications/diffusion/conduit/DiffusionTagsQueryConduitAPIMethod.php b/src/applications/diffusion/conduit/DiffusionTagsQueryConduitAPIMethod.php
@@ -72,7 +72,10 @@ private function loadGitTagList() {
 
     $refs = id(new DiffusionLowLevelGitRefQuery())
       ->setRepository($repository)
-      ->withIsTag(true)
+      ->withRefTypes(
+        array(
+          PhabricatorRepositoryRefCursor::TYPE_TAG,
+        ))
       ->execute();
 
     $tags = array();
diff --git a/src/applications/diffusion/editor/DiffusionURIEditor.php b/src/applications/diffusion/editor/DiffusionURIEditor.php
@@ -463,6 +463,8 @@ protected function applyFinalEffects(
       break;
     }
 
+    $was_hosted = $repository->isHosted();
+
     if ($observe_uri) {
       $repository
         ->setHosted(false)
@@ -477,6 +479,17 @@ protected function applyFinalEffects(
 
     $repository->save();
 
+    $is_hosted = $repository->isHosted();
+
+    // If we've swapped the repository from hosted to observed or vice versa,
+    // reset all the cluster version clocks.
+    if ($was_hosted != $is_hosted) {
+      $cluster_engine = id(new DiffusionRepositoryClusterEngine())
+        ->setViewer($this->getActor())
+        ->setRepository($repository)
+        ->synchronizeWorkingCopyAfterHostingChange();
+    }
+
     return $xactions;
   }
 
diff --git a/src/applications/diffusion/management/DiffusionRepositoryStorageManagementPanel.php b/src/applications/diffusion/management/DiffusionRepositoryStorageManagementPanel.php
@@ -137,12 +137,28 @@ private function buildClusterStatusPanel() {
         $version = idx($versions, $device->getPHID());
         if ($version) {
           $version_number = $version->getRepositoryVersion();
-          $version_number = phutil_tag(
-            'a',
-            array(
-              'href' => "/diffusion/pushlog/view/{$version_number}/",
-            ),
-            $version_number);
+
+          $href = null;
+          if ($repository->isHosted()) {
+            $href = "/diffusion/pushlog/view/{$version_number}/";
+          } else {
+            $commit = id(new DiffusionCommitQuery())
+              ->setViewer($viewer)
+              ->withIDs(array($version_number))
+              ->executeOne();
+            if ($commit) {
+              $href = $commit->getURI();
+            }
+          }
+
+          if ($href) {
+            $version_number = phutil_tag(
+              'a',
+              array(
+                'href' => $href,
+              ),
+              $version_number);
+          }
         } else {
           $version_number = '-';
         }
diff --git a/src/applications/diffusion/protocol/DiffusionRepositoryClusterEngine.php b/src/applications/diffusion/protocol/DiffusionRepositoryClusterEngine.php
@@ -82,6 +82,53 @@ public function synchronizeWorkingCopyAfterCreation() {
   }
 
 
+  /**
+   * @task sync
+   */
+  public function synchronizeWorkingCopyAfterHostingChange() {
+    if (!$this->shouldEnableSynchronization()) {
+      return;
+    }
+
+    $repository = $this->getRepository();
+    $repository_phid = $repository->getPHID();
+
+    $versions = PhabricatorRepositoryWorkingCopyVersion::loadVersions(
+      $repository_phid);
+    $versions = mpull($versions, null, 'getDevicePHID');
+
+    // After converting a hosted repository to observed, or vice versa, we
+    // need to reset version numbers because the clocks for observed and hosted
+    // repositories run on different units.
+
+    // We identify all the cluster leaders and reset their version to 0.
+    // We identify all the cluster followers and demote them.
+
+    // This allows the cluter to start over again at version 0 but keep the
+    // same leaders.
+
+    if ($versions) {
+      $max_version = (int)max(mpull($versions, 'getRepositoryVersion'));
+      foreach ($versions as $version) {
+        $device_phid = $version->getDevicePHID();
+
+        if ($version->getRepositoryVersion() == $max_version) {
+          PhabricatorRepositoryWorkingCopyVersion::updateVersion(
+            $repository_phid,
+            $device_phid,
+            0);
+        } else {
+          PhabricatorRepositoryWorkingCopyVersion::demoteDevice(
+            $repository_phid,
+            $device_phid);
+        }
+      }
+    }
+
+    return $this;
+  }
+
+
   /**
    * @task sync
    */
@@ -149,14 +196,18 @@ public function synchronizeWorkingCopyBeforeRead() {
 
       $max_version = (int)max(mpull($versions, 'getRepositoryVersion'));
       if ($max_version > $this_version) {
-        $fetchable = array();
-        foreach ($versions as $version) {
-          if ($version->getRepositoryVersion() == $max_version) {
-            $fetchable[] = $version->getDevicePHID();
+        if ($repository->isHosted()) {
+          $fetchable = array();
+          foreach ($versions as $version) {
+            if ($version->getRepositoryVersion() == $max_version) {
+              $fetchable[] = $version->getDevicePHID();
+            }
           }
-        }
 
-        $this->synchronizeWorkingCopyFromDevices($fetchable);
+          $this->synchronizeWorkingCopyFromDevices($fetchable);
+        } else {
+          $this->synchornizeWorkingCopyFromRemote();
+        }
 
         PhabricatorRepositoryWorkingCopyVersion::updateVersion(
           $repository_phid,
@@ -329,6 +380,47 @@ public function synchronizeWorkingCopyBeforeWrite() {
   }
 
 
+  public function synchronizeWorkingCopyAfterDiscovery($new_version) {
+    if (!$this->shouldEnableSynchronization()) {
+      return;
+    }
+
+    $repository = $this->getRepository();
+    $repository_phid = $repository->getPHID();
+    if ($repository->isHosted()) {
+      return;
+    }
+
+    $viewer = $this->getViewer();
+
+    $device = AlmanacKeys::getLiveDevice();
+    $device_phid = $device->getPHID();
+
+    // NOTE: We are not holding a lock here because this method is only called
+    // from PhabricatorRepositoryDiscoveryEngine, which already holds a device
+    // lock. Even if we do race here and record an older version, the
+    // consequences are mild: we only do extra work to correct it later.
+
+    $versions = PhabricatorRepositoryWorkingCopyVersion::loadVersions(
+      $repository_phid);
+    $versions = mpull($versions, null, 'getDevicePHID');
+
+    $this_version = idx($versions, $device_phid);
+    if ($this_version) {
+      $this_version = (int)$this_version->getRepositoryVersion();
+    } else {
+      $this_version = -1;
+    }
+
+    if ($new_version > $this_version) {
+      PhabricatorRepositoryWorkingCopyVersion::updateVersion(
+        $repository_phid,
+        $device_phid,
+        $new_version);
+    }
+  }
+
+
   /**
    * @task sync
    */
@@ -471,13 +563,6 @@ private function shouldEnableSynchronization() {
       return false;
     }
 
-    // TODO: It may eventually make sense to try to version and synchronize
-    // observed repositories (so that daemons don't do reads against out-of
-    // date hosts), but don't bother for now.
-    if (!$repository->isHosted()) {
-      return false;
-    }
-
     $device = AlmanacKeys::getLiveDevice();
     if (!$device) {
       return false;
@@ -487,6 +572,50 @@ private function shouldEnableSynchronization() {
   }
 
 
+  /**
+   * @task internal
+   */
+  private function synchornizeWorkingCopyFromRemote() {
+    $repository = $this->getRepository();
+    $device = AlmanacKeys::getLiveDevice();
+
+    $local_path = $repository->getLocalPath();
+    $fetch_uri = $repository->getRemoteURIEnvelope();
+
+    if ($repository->isGit()) {
+      $this->requireWorkingCopy();
+
+      $argv = array(
+        'fetch --prune -- %P %s',
+        $fetch_uri,
+        '+refs/*:refs/*',
+      );
+    } else {
+      throw new Exception(pht('Remote sync only supported for git!'));
+    }
+
+    $future = DiffusionCommandEngine::newCommandEngine($repository)
+      ->setArgv($argv)
+      ->setSudoAsDaemon(true)
+      ->setCredentialPHID($repository->getCredentialPHID())
+      ->setProtocol($repository->getRemoteProtocol())
+      ->newFuture();
+
+    $future->setCWD($local_path);
+
+    try {
+      $future->resolvex();
+    } catch (Exception $ex) {
+      $this->logLine(
+        pht(
+          'Synchronization of "%s" from remote failed: %s',
+          $device->getName(),
+          $ex->getMessage()));
+      throw $ex;
+    }
+  }
+
+
   /**
    * @task internal
    */
@@ -560,17 +689,7 @@ private function synchronizeWorkingCopyFromBinding($binding) {
     $local_path = $repository->getLocalPath();
 
     if ($repository->isGit()) {
-      if (!Filesystem::pathExists($local_path)) {
-        throw new Exception(
-          pht(
-            'Repository "%s" does not have a working copy on this device '.
-            'yet, so it can not be synchronized. Wait for the daemons to '.
-            'construct one or run `bin/repository update %s` on this host '.
-            '("%s") to build it explicitly.',
-            $repository->getDisplayName(),
-            $repository->getMonogram(),
-            $device->getName()));
-      }
+      $this->requireWorkingCopy();
 
       $argv = array(
         'fetch --prune -- %s %s',
@@ -622,4 +741,24 @@ private function logText($message) {
     }
     return $this;
   }
+
+  private function requireWorkingCopy() {
+    $repository = $this->getRepository();
+    $local_path = $repository->getLocalPath();
+
+    if (!Filesystem::pathExists($local_path)) {
+      $device = AlmanacKeys::getLiveDevice();
+
+      throw new Exception(
+        pht(
+          'Repository "%s" does not have a working copy on this device '.
+          'yet, so it can not be synchronized. Wait for the daemons to '.
+          'construct one or run `bin/repository update %s` on this host '.
+          '("%s") to build it explicitly.',
+          $repository->getDisplayName(),
+          $repository->getMonogram(),
+          $device->getName()));
+    }
+  }
+
 }
diff --git a/src/applications/diffusion/query/lowlevel/DiffusionLowLevelGitRefQuery.php b/src/applications/diffusion/query/lowlevel/DiffusionLowLevelGitRefQuery.php
@@ -6,30 +6,33 @@
  */
 final class DiffusionLowLevelGitRefQuery extends DiffusionLowLevelQuery {
 
-  private $isTag;
-  private $isOriginBranch;
+  private $refTypes;
 
-  public function withIsTag($is_tag) {
-    $this->isTag = $is_tag;
-    return $this;
-  }
-
-  public function withIsOriginBranch($is_origin_branch) {
-    $this->isOriginBranch = $is_origin_branch;
+  public function withRefTypes(array $ref_types) {
+    $this->refTypes = $ref_types;
     return $this;
   }
 
   protected function executeQuery() {
+    $ref_types = $this->refTypes;
+    if ($ref_types) {
+      $type_branch = PhabricatorRepositoryRefCursor::TYPE_BRANCH;
+      $type_tag = PhabricatorRepositoryRefCursor::TYPE_TAG;
+
+      $ref_types = array_fuse($ref_types);
+
+      $with_branches = isset($ref_types[$type_branch]);
+      $with_tags = isset($ref_types[$type_tag]);
+    } else {
+      $with_branches = true;
+      $with_tags = true;
+    }
+
     $repository = $this->getRepository();
 
     $prefixes = array();
 
-    $any = ($this->isTag || $this->isOriginBranch);
-    if (!$any) {
-      throw new Exception(pht('Specify types of refs to query.'));
-    }
-
-    if ($this->isOriginBranch) {
+    if ($with_branches) {
       if ($repository->isWorkingCopyBare()) {
         $prefix = 'refs/heads/';
       } else {
@@ -39,7 +42,7 @@ protected function executeQuery() {
       $prefixes[] = $prefix;
     }
 
-    if ($this->isTag) {
+    if ($with_tags) {
       $prefixes[] = 'refs/tags/';
     }
 
diff --git a/src/applications/diffusion/query/lowlevel/DiffusionLowLevelResolveRefsQuery.php b/src/applications/diffusion/query/lowlevel/DiffusionLowLevelResolveRefsQuery.php
@@ -66,8 +66,11 @@ private function resolveGitRefs() {
     // First, resolve branches and tags.
     $ref_map = id(new DiffusionLowLevelGitRefQuery())
       ->setRepository($repository)
-      ->withIsTag(true)
-      ->withIsOriginBranch(true)
+      ->withRefTypes(
+        array(
+          PhabricatorRepositoryRefCursor::TYPE_BRANCH,
+          PhabricatorRepositoryRefCursor::TYPE_TAG,
+        ))
       ->execute();
     $ref_map = mgroup($ref_map, 'getShortName');
 
diff --git a/src/applications/repository/engine/PhabricatorRepositoryDiscoveryEngine.php b/src/applications/repository/engine/PhabricatorRepositoryDiscoveryEngine.php
diff --git a/src/applications/repository/engine/PhabricatorRepositoryPullEngine.php b/src/applications/repository/engine/PhabricatorRepositoryPullEngine.php
diff --git a/src/applications/repository/engine/PhabricatorRepositoryRefEngine.php b/src/applications/repository/engine/PhabricatorRepositoryRefEngine.php
