Kavita/API/Services/TaskScheduler.cs
Joseph Milazzo 56cf7be799
Scan Chunking (#604)
* Some performance refactoring around getting Library and avoid a byte[] copy for getting cover images for epubs.

* Initial commit. Rewrote the main series scan loop to use chunks of data at a time. Not fully shaken out.

* Hooked in the ability for the UI to react to series being added or removed from the DB.

* Cleaned up the messaging in the scan loop to be more clear.

* Metadata scan and scan work as expected and populate data to the UI. There is a slow down in speed for overall operation.

Scan series and refresh series metadata does not work fully.

* Fixed a bug where MangaFiles were not having LastModified Updated correctly, meaning they were opening archives every scan.

* Modified the code to be more realistic to the underlying file

* Updated ScanService to properly handle deleted files and not result in a higher-level scan.

* Shuffled around volume related repo apis to the volume repo rather than being in series.

* Rewrote scan series to be much cleaner and more concise on the flow. Fixed an issue in UpdateVolumes such that the debug code to log out removed volumes could throw an exception and actually break updating volumes.

* Refactored the code to set MangaFile last modified timestamp into the MangaFile entity.

* Added Series Name to ScanSeries event

* Added additional checks in ScanSeries to ensure we never go outside the library folder.

Added extra debug messages for when a metadata refresh doesn't actually make changes and for when we regen cover images.

* More logging statements saying where they originate from. Fixed a critical bug which caused only 1 chunk to ever be processed.

* Fixed a concurrency issue with natural sorter which could cause issues in ArchiveService.cs.

* Log cleanups

* Fixed an issue with logging out total time of a scan.

* Only show added toastrs for admins. When kicking off a refresh metadata for series, make sure we regenerate all cover images.

* Code smells on benchmark despite it being ignored
2021-09-30 06:08:05 -07:00

172 lines
6.7 KiB
C#

using System.IO;
using System.Threading;
using System.Threading.Tasks;
using API.Entities.Enums;
using API.Helpers.Converters;
using API.Interfaces;
using API.Interfaces.Services;
using Hangfire;
using Microsoft.Extensions.Logging;
namespace API.Services
{
public class TaskScheduler : ITaskScheduler
{
private readonly ICacheService _cacheService;
private readonly ILogger<TaskScheduler> _logger;
private readonly IScannerService _scannerService;
private readonly IUnitOfWork _unitOfWork;
private readonly IMetadataService _metadataService;
private readonly IBackupService _backupService;
private readonly ICleanupService _cleanupService;
private readonly IStatsService _statsService;
private readonly IVersionUpdaterService _versionUpdaterService;
private const string SendDataTask = "finalize-stats";
public static BackgroundJobServer Client => new BackgroundJobServer();
public TaskScheduler(ICacheService cacheService, ILogger<TaskScheduler> logger, IScannerService scannerService,
IUnitOfWork unitOfWork, IMetadataService metadataService, IBackupService backupService,
ICleanupService cleanupService, IStatsService statsService, IVersionUpdaterService versionUpdaterService)
{
_cacheService = cacheService;
_logger = logger;
_scannerService = scannerService;
_unitOfWork = unitOfWork;
_metadataService = metadataService;
_backupService = backupService;
_cleanupService = cleanupService;
_statsService = statsService;
_versionUpdaterService = versionUpdaterService;
}
public void ScheduleTasks()
{
_logger.LogInformation("Scheduling reoccurring tasks");
var setting = Task.Run(() => _unitOfWork.SettingsRepository.GetSettingAsync(ServerSettingKey.TaskScan)).GetAwaiter().GetResult().Value;
if (setting != null)
{
var scanLibrarySetting = setting;
_logger.LogDebug("Scheduling Scan Library Task for {Setting}", scanLibrarySetting);
RecurringJob.AddOrUpdate("scan-libraries", () => _scannerService.ScanLibraries(),
() => CronConverter.ConvertToCronNotation(scanLibrarySetting));
}
else
{
RecurringJob.AddOrUpdate("scan-libraries", () => _scannerService.ScanLibraries(), Cron.Daily);
}
setting = Task.Run(() => _unitOfWork.SettingsRepository.GetSettingAsync(ServerSettingKey.TaskBackup)).Result.Value;
if (setting != null)
{
_logger.LogDebug("Scheduling Backup Task for {Setting}", setting);
RecurringJob.AddOrUpdate("backup", () => _backupService.BackupDatabase(), () => CronConverter.ConvertToCronNotation(setting));
}
else
{
RecurringJob.AddOrUpdate("backup", () => _backupService.BackupDatabase(), Cron.Weekly);
}
RecurringJob.AddOrUpdate("cleanup", () => _cleanupService.Cleanup(), Cron.Daily);
RecurringJob.AddOrUpdate("check-for-updates", () => _scannerService.ScanLibraries(), Cron.Daily);
}
#region StatsTasks
public async Task ScheduleStatsTasks()
{
var allowStatCollection = (await _unitOfWork.SettingsRepository.GetSettingsDtoAsync()).AllowStatCollection;
if (!allowStatCollection)
{
_logger.LogDebug("User has opted out of stat collection, not registering tasks");
return;
}
_logger.LogDebug("Scheduling stat collection daily");
RecurringJob.AddOrUpdate(SendDataTask, () => _statsService.CollectAndSendStatsData(), Cron.Daily);
}
public void CancelStatsTasks()
{
_logger.LogDebug("Cancelling/Removing StatsTasks");
RecurringJob.RemoveIfExists(SendDataTask);
}
public void RunStatCollection()
{
_logger.LogInformation("Enqueuing stat collection");
BackgroundJob.Enqueue(() => _statsService.CollectAndSendStatsData());
}
#endregion
#region UpdateTasks
public void ScheduleUpdaterTasks()
{
_logger.LogInformation("Scheduling Auto-Update tasks");
RecurringJob.AddOrUpdate("check-updates", () => CheckForUpdate(), Cron.Weekly);
}
#endregion
public void ScanLibrary(int libraryId, bool forceUpdate = false)
{
_logger.LogInformation("Enqueuing library scan for: {LibraryId}", libraryId);
BackgroundJob.Enqueue(() => _scannerService.ScanLibrary(libraryId));
// When we do a scan, force cache to re-unpack in case page numbers change
BackgroundJob.Enqueue(() => _cleanupService.CleanupCacheDirectory());
}
public void CleanupChapters(int[] chapterIds)
{
BackgroundJob.Enqueue(() => _cacheService.CleanupChapters(chapterIds));
}
public void RefreshMetadata(int libraryId, bool forceUpdate = true)
{
_logger.LogInformation("Enqueuing library metadata refresh for: {LibraryId}", libraryId);
BackgroundJob.Enqueue(() => _metadataService.RefreshMetadata(libraryId, forceUpdate));
}
public void CleanupTemp()
{
var tempDirectory = Path.Join(Directory.GetCurrentDirectory(), "temp");
BackgroundJob.Enqueue(() => DirectoryService.ClearDirectory(tempDirectory));
}
public void RefreshSeriesMetadata(int libraryId, int seriesId, bool forceUpdate = true)
{
_logger.LogInformation("Enqueuing series metadata refresh for: {SeriesId}", seriesId);
BackgroundJob.Enqueue(() => _metadataService.RefreshMetadataForSeries(libraryId, seriesId, forceUpdate));
}
public void ScanSeries(int libraryId, int seriesId, bool forceUpdate = false)
{
_logger.LogInformation("Enqueuing series scan for: {SeriesId}", seriesId);
BackgroundJob.Enqueue(() => _scannerService.ScanSeries(libraryId, seriesId, CancellationToken.None));
}
public void BackupDatabase()
{
BackgroundJob.Enqueue(() => _backupService.BackupDatabase());
}
/// <summary>
/// Not an external call. Only public so that we can call this for a Task
/// </summary>
// ReSharper disable once MemberCanBePrivate.Global
public async Task CheckForUpdate()
{
var update = await _versionUpdaterService.CheckForUpdate();
await _versionUpdaterService.PushUpdate(update);
}
}
}