I am running hangfire in a single web application, my application is being run on 2 physical servers but hangfire is in 1 database.
At the moment, i am generating a server for each queue, because each queue i need to run 1 worker at a time and they must be in order. I set them up like this
// core
services.AddHangfire(options =>
{
options.SetDataCompatibilityLevel(CompatibilityLevel.Version_170);
options.UseSimpleAssemblyNameTypeSerializer();
options.UseRecommendedSerializerSettings();
options.UseSqlServerStorage(appSettings.Data.DefaultConnection.ConnectionString, storageOptions);
});
// add multiple servers, this way we get to control how many workers are in each queue
services.AddHangfireServer(options =>
{
options.ServerName = "workflow-queue";
options.WorkerCount = 1;
options.Queues = new string[] { "workflow-queue" };
options.SchedulePollingInterval = TimeSpan.FromSeconds(10);
});
services.AddHangfireServer(options =>
{
options.ServerName = "alert-schedule";
options.WorkerCount = 1;
options.Queues = new string[] { "alert-schedule" };
options.SchedulePollingInterval = TimeSpan.FromMinutes(1);
});
services.AddHangfireServer(options =>
{
options.ServerName = string.Format("trigger-schedule");
options.WorkerCount = 1;
options.Queues = new string[] { "trigger-schedule" };
options.SchedulePollingInterval = TimeSpan.FromMinutes(1);
});
services.AddHangfireServer(options =>
{
options.ServerName = "report-schedule";
options.WorkerCount = 1;
options.Queues = new string[] { "report-schedule" };
options.SchedulePollingInterval = TimeSpan.FromMinutes(1);
});
services.AddHangfireServer(options =>
{
options.ServerName = "maintenance";
options.WorkerCount = 5;
options.Queues = new string[] { "maintenance" };
options.SchedulePollingInterval = TimeSpan.FromMinutes(10);
});
My problem is that it is generating multiple queues on the servers, with different ports.

In my code i am then trying to stop jobs from running if they are queued/retrying, but if the job is being run on a different physical server, it is not found and queued again.
Here is the code to check if its running already
public async Task<bool> IsAlreadyQueuedAsync(PerformContext context)
{
var disableJob = false;
var monitoringApi = JobStorage.Current.GetMonitoringApi();
// get the jobId, method and queue using performContext
var jobId = context.BackgroundJob.Id;
var methodInfo = context.BackgroundJob.Job.Method;
var queueAttribute = (QueueAttribute)Attribute.GetCustomAttribute(context.BackgroundJob.Job.Method, typeof(QueueAttribute));
// enqueuedJobs
var enqueuedjobStatesToCheck = new[] { "Processing" };
var enqueuedJobs = monitoringApi.EnqueuedJobs(queueAttribute.Queue, 0, 1000);
var enqueuedJobsAlready = enqueuedJobs.Count(e => e.Key != jobId && e.Value != null && e.Value.Job != null && e.Value.Job.Method.Equals(methodInfo) && enqueuedjobStatesToCheck.Contains(e.Value.State));
if (enqueuedJobsAlready > 0)
disableJob = true;
// scheduledJobs
if (!disableJob)
{
// check if there are any scheduledJobs that are processing
var scheduledJobs = monitoringApi.ScheduledJobs(0, 1000);
var scheduledJobsAlready = scheduledJobs.Count(e => e.Key != jobId && e.Value != null && e.Value.Job != null && e.Value.Job.Method.Equals(methodInfo));
if (scheduledJobsAlready > 0)
disableJob = true;
}
// failedJobs
if (!disableJob)
{
var failedJobs = monitoringApi.FailedJobs(0, 1000);
var failedJobsAlready = failedJobs.Count(e => e.Key != jobId && e.Value != null && e.Value.Job != null && e.Value.Job.Method.Equals(methodInfo));
if (failedJobsAlready > 0)
disableJob = true;
}
// if runBefore is true, then lets remove the current job running, else it will write a "successful" message in the logs
if (disableJob)
{
// use hangfire delete, for cleanup
BackgroundJob.Delete(jobId);
// create our sqlBuilder to remove the entries altogether including the count
var sqlBuilder = new SqlBuilder()
.DELETE_FROM("Hangfire.[Job]")
.WHERE("[Id] = {0};", jobId);
sqlBuilder.Append("DELETE TOP(1) FROM Hangfire.[Counter] WHERE [Key] = 'stats:deleted' AND [Value] = 1;");
using (var cmd = _context.CreateCommand(sqlBuilder))
await cmd.ExecuteNonQueryAsync();
return true;
}
return false;
}
Each method has something like the following attributes as well
public interface IAlertScheduleService
{
[Hangfire.Queue("alert-schedule")]
[Hangfire.DisableConcurrentExecution(60 * 60 * 5)]
Task RunAllAsync(PerformContext context);
}
Simple implementation of the interface
public class AlertScheduleService : IAlertScheduleService
{
public Task RunAllAsync(PerformContext context)
{
if (IsAlreadyQueuedAsync(context))
return;
// guess it isnt queued, so run it here....
}
}
Here is how i am adding my scheduled jobs
//// our recurring jobs
//// set these to run hourly, so they can play "catch-up" if needed
RecurringJob.AddOrUpdate<IAlertScheduleService>(e => e.RunAllAsync(null), Cron.Hourly(0), queue: "alert-schedule");
Why does this happen? How can i stop it happening?
Somewhat of a blind shot, preventing a job to be queued if a job is already queued in the same queue. The try-catch logic is quite ugly but I have no better idea right now... Also, really not sure the lock logic always prevents from having two jobs in EnqueudState, but it should help anyway. Maybe mixing with an IApplyStateFilter.
public class DoNotQueueIfAlreadyQueued : IElectStateFilter
{
public void OnStateElection(ElectStateContext context)
{
if (context.CandidateState is EnqueuedState)
{
EnqueuedState es = context.CandidateState as EnqueuedState;
IDisposable distributedLock = null;
try
{
while (distributedLock == null)
{
try
{
distributedLock = context.Connection.AcquireDistributedLock($"{nameof(DoNotQueueIfAlreadyQueued)}-{es.Queue}", TimeSpan.FromSeconds(1));
}
catch { }
}
var m = context.Storage.GetMonitoringApi();
if (m.EnqueuedCount(es.Queue) > 0)
{
context.CandidateState = new DeletedState();
}
}
finally
{
distributedLock.Dispose();
}
}
}
}
The filter can be declared as in this answer