Skip to content

perf: query platform wiki entity counts directly #1276

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
addshore wants to merge 1 commit into
base: main
Choose a base branch
from
Open

perf: query platform wiki entity counts directly #1276

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 16 additions & 31 deletions app/Jobs/PlatformStatsSummaryJob.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,7 @@

namespace App\Jobs;

use App\Constants\MediawikiNamespace;
use App\Helper\MWTimestampHelper;
use App\Services\MediaWikiHostResolver;
use App\Traits;
use App\User;
use App\Wiki;
use Carbon\CarbonImmutable;
Expand All @@ -31,8 +28,6 @@
* Example: php artisan job:dispatch PlatformStatsSummaryJob
*/
class PlatformStatsSummaryJob extends Job {
use Traits\PageFetcher;

public $timeout = 3600;

private $inactiveThreshold;
Expand All @@ -41,8 +36,6 @@ class PlatformStatsSummaryJob extends Job {

private $platformSummaryStatsVersion = 'v1';

private MediaWikiHostResolver $mwHostResolver;

public function __construct() {
$this->inactiveThreshold = Config::get('wbstack.platform_summary_inactive_threshold');
$this->creationRateRanges = Config::get('wbstack.platform_summary_creation_rate_ranges');
Expand Down Expand Up @@ -78,6 +71,7 @@ public function prepareStats(array $allStats, $wikis): array {
$propertiesCount = [];

$currentTime = CarbonImmutable::now();
$statsByWiki = array_column($allStats, null, 'wiki');

foreach ($wikis as $wiki) {
if (!is_null($wiki->deleted_at)) {
Expand All @@ -86,39 +80,24 @@ public function prepareStats(array $allStats, $wikis): array {
continue;
}

$this->apiUrl = $this->mwHostResolver->getBackendUrlForDomain($wiki->domain) . '/w/api.php'; // used in PageFetcher::fetchPagesInNamespace

// add items and properties counts of the wiki to the corresponded arrays
try {
$nextItemCount = count($this->fetchPagesInNamespace($wiki->domain, MediawikiNamespace::item));
array_push($itemsCount, $nextItemCount);
} catch (\Exception $ex) {
Log::warning('Failed to fetch item count for wiki ' . $wiki->domain . ', will use 0 instead.');
}
try {
$nextPropertyCount = count($this->fetchPagesInNamespace($wiki->domain, MediawikiNamespace::property));
array_push($propertiesCount, $nextPropertyCount);
} catch (\Exception $ex) {
Log::warning('Failed to fetch property count for wiki ' . $wiki->domain . ', will use 0 instead.');
}

$wikiDb = $wiki->wikiDb()->first();
$wikiDb = $wiki->wikiDb;

if (!$wikiDb) {
Log::error(__METHOD__ . ": Could not find WikiDB for {$wiki->domain}");

continue;
}

$found_key = array_search($wiki->domain, array_column($allStats, 'wiki'));
$stats = $statsByWiki[$wiki->domain] ?? null;

if ($found_key === false) {
if ($stats === null) {
Log::warning(__METHOD__ . ": Could not find stats for {$wiki->domain}");

continue;
}

$stats = $allStats[$found_key];
$itemsCount[] = $stats['items'];
$propertiesCount[] = $stats['properties'];

// is it empty?
if ($this->isNullOrEmpty($stats['edits']) && $this->isNullOrEmpty($stats['pages']) && $this->isNullOrEmpty($stats['lastEdit'])) {
Expand Down Expand Up @@ -170,9 +149,8 @@ public function prepareStats(array $allStats, $wikis): array {
];
}

public function handle(DatabaseManager $manager, MediaWikiHostResolver $mwHostResolver): void {
$this->mwHostResolver = $mwHostResolver;
$wikis = Wiki::withTrashed()->with('wikidb')->get();
public function handle(DatabaseManager $manager): void {
$wikis = Wiki::withTrashed()->with('wikiDb')->get();

$conn = $manager->connection('mysql');
$mwConn = $manager->connection('mw');
Expand Down Expand Up @@ -232,8 +210,15 @@ public function handle(DatabaseManager $manager, MediaWikiHostResolver $mwHostRe
WHERE ct_rev_id < 100
) t4,
(
SELECT
COUNT(CASE WHEN page_namespace = 120 THEN 1 END) AS items,
COUNT(CASE WHEN page_namespace = 122 THEN 1 END) AS properties
FROM ",wiki_dbs.name,".",wiki_dbs.prefix,"_page
WHERE page_namespace IN (120, 122)
) t5,
(
SELECT '",wikis.domain,"' as wiki
) t5
) t6
"

) SEPARATOR ' UNION ALL ')
Expand Down
Loading
Loading