[performance] processing media and scheduled jobs improvements (#1482)

* replace media workers with just runners.WorkerPool, move to state structure, use go-sched for global task scheduling

* improved code comment

* fix worker tryUntil function, update go-runners/go-sched

* make preprocess functions package public, use these where possible to stop doubled up processing

* remove separate emoji worker pool

* limit calls to time.Now() during media preprocessing

* use Processor{} to manage singular runtime of processing media

* ensure workers get started when media manager is used

* improved error setting in processing media, fix media test

* port changes from processingmedia to processing emoji

* finish code commenting

* finish code commenting and comment-out client API + federator worker pools until concurrency worker pools replaced

* linterrrrrrrrrrrrrrrr

---------

Signed-off-by: kim <grufwub@gmail.com>

1 files changed, 90 insertions, 0 deletions

diff --git a/internal/workers/workers.go b/internal/workers/workers.go
new file mode 100644
index 000000000..77b3065ce
--- /dev/null
+++ b/internal/workers/workers.go
@@ -0,0 +1,90 @@
+/*
+GoToSocial
+Copyright (C) 2021-2023 GoToSocial Authors admin@gotosocial.org
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU Affero General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+package workers
+
+import (
+	"log"
+	"runtime"
+
+	"codeberg.org/gruf/go-runners"
+	"codeberg.org/gruf/go-sched"
+)
+
+type Workers struct {
+	// Main task scheduler instance.
+	Scheduler sched.Scheduler
+
+	// Processor / federator worker pools.
+	// ClientAPI runners.WorkerPool
+	// Federator runners.WorkerPool
+
+	// Media manager worker pools.
+	Media runners.WorkerPool
+
+	// prevent pass-by-value.
+	_ nocopy
+}
+
+// Start will start all of the contained worker pools (and global scheduler).
+func (w *Workers) Start() {
+	// Get currently set GOMAXPROCS.
+	maxprocs := runtime.GOMAXPROCS(0)
+
+	tryUntil("starting scheduler", 5, func() bool {
+		return w.Scheduler.Start(nil)
+	})
+
+	// tryUntil("starting client API workerpool", 5, func() bool {
+	// 	return w.ClientAPI.Start(4*maxprocs, 400*maxprocs)
+	// })
+
+	// tryUntil("starting federator workerpool", 5, func() bool {
+	// 	return w.Federator.Start(4*maxprocs, 400*maxprocs)
+	// })
+
+	tryUntil("starting media workerpool", 5, func() bool {
+		return w.Media.Start(8*maxprocs, 80*maxprocs)
+	})
+}
+
+// Stop will stop all of the contained worker pools (and global scheduler).
+func (w *Workers) Stop() {
+	tryUntil("stopping scheduler", 5, w.Scheduler.Stop)
+	// tryUntil("stopping client API workerpool", 5, w.ClientAPI.Stop)
+	// tryUntil("stopping federator workerpool", 5, w.Federator.Stop)
+	tryUntil("stopping media workerpool", 5, w.Media.Stop)
+}
+
+// nocopy when embedded will signal linter to
+// error on pass-by-value of parent struct.
+type nocopy struct{}
+
+func (*nocopy) Lock() {}
+
+func (*nocopy) Unlock() {}
+
+// tryUntil will attempt to call 'do' for 'count' attempts, before panicking with 'msg'.
+func tryUntil(msg string, count int, do func() bool) {
+	for i := 0; i < count; i++ {
+		if do() {
+			return
+		}
+	}
+	log.Panicf("failed %s after %d tries", msg, count)
+}