revi-archive/phorge-phorge
1
0
Fork 0
mirror of https://we.phorge.it/source/phorge.git synced 2025-01-10 23:01:04 +01:00
Code Issues Releases Wiki Activity

Improve performance of repository discovery in repositories with >65K refs

Browse source 
Summary:
Ref T13593. The commit cache in this Engine has a maximum fixed size (currently 65,535 entries).

If we execute discovery in a repository with more refs than this (e.g., 180K), we get fast lookups for the first 65,535 refs and slow lookups for the remaining refs.

Instead, divide the refs into chunks no larger than the cache size, and perform an explicit cache fill before each chunk is processed.

Test Plan:
  - Created a repository with 1K refs. Set cache size to 256. Ran discovery.
    - Before patch: saw one large cache fill and then ~750 single-gets.
    - After patch: saw four large cache fills.
  - Compared `bin/repository discover ... --verbose` output before and after patch for overall effect; saw no differences.

Maniphest Tasks: T13593

Differential Revision: https://secure.phabricator.com/D21521
This commit is contained in:
epriestley 2021-01-26 08:38:05 -08:00
parent 888604c9dd
commit ed86c42b26
1 changed files with 69 additions and 44 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
src/applications/repository/engine/PhabricatorRepositoryDiscoveryEngine.php
View file

@ -142,18 +142,21 @@ final class PhabricatorRepositoryDiscoveryEngine
return array();
}
$heads = $this->sortRefs($heads);
$head_commits = mpull($heads, 'getCommitIdentifier');
$this->log(
pht(
'Discovering commits in repository "%s".',
$repository->getDisplayName()));
$this->fillCommitCache($head_commits);
$ref_lists = array();
$refs = array();
foreach ($heads as $ref) {
$head_groups = $this->getRefGroupsForDiscovery($heads);
foreach ($head_groups as $head_group) {
$group_identifiers = mpull($head_group, 'getCommitIdentifier');
$group_identifiers = array_fuse($group_identifiers);
$this->fillCommitCache($group_identifiers);
foreach ($head_group as $ref) {
$name = $ref->getShortName();
$commit = $ref->getCommitIdentifier();
@ -193,10 +196,32 @@ final class PhabricatorRepositoryDiscoveryEngine
$this->didDiscoverRefs($head_refs);
$refs[] = $head_refs;
$ref_lists[] = $head_refs;
}
}
return array_mergev($refs);
$refs = array_mergev($ref_lists);
return $refs;
}
/**
* @task git
*/
private function getRefGroupsForDiscovery(array $heads) {
$heads = $this->sortRefs($heads);
// See T13593. We hold a commit cache with a fixed maximum size. Split the
// refs into chunks no larger than the cache size, so we don't overflow the
// cache when testing them.
$array_iterator = new ArrayIterator($heads);
$chunk_iterator = new PhutilChunkedIterator(
$array_iterator,
self::MAX_COMMIT_CACHE_SIZE);
return $chunk_iterator;
}