@torrent-tv/proxy 2.81.2 → 2.83.0

package/services/encode/run-costs.js

@@ -48,6 +48,40 @@ export class RunCosts {
   /** How long the first output took to appear, in milliseconds. @type {number[]} */
   #firstOutput = [];
 
+  /**
+   * What this host was measured to do at startup, before any viewer existed.
+   *
+   * WITHOUT IT BOTH FIGURES ARE ZERO AT A COLD OPEN, and zero does not read as
+   * "not measured" — it reads as "free". The whole comparison the plan makes is
+   * between leaving an encoder where it stands, which costs the remainder of its
+   * warm-up, and moving it, which costs the killing plus a warm-up from the
+   * beginning. Subtract one from the other and what is left is the killing plus
+   * the time the run has already lived — the warm-up a move throws away. Set the
+   * warm-up to zero and that difference collapses to zero as well: keeping and
+   * moving cost exactly the same, the tie falls to position, and any advantage
+   * however small wins. Field 2026-09-08: an encoder moved between two adjacent
+   * numbers every half second, produced nothing, and was killed each time.
+   *
+   * Readings from real runs replace it as they arrive; this is where the plan
+   * starts from, not where it stays.
+   *
+   * @type {{ firstByteWaitSec: number, killCostSec: number } | null}
+   */
+  #atStartup = null;
+
+  /**
+   * Take what the startup measurement found on this host.
+   *
+   * @param {{ firstByteWaitSec: number, killCostSec: number } | null} measured
+   * @returns {void}
+   */
+  noteStartup(measured) {
+    this.#atStartup =
+      Number.isFinite(measured?.firstByteWaitSec) && measured.firstByteWaitSec > 0
+        ? { firstByteWaitSec: measured.firstByteWaitSec, killCostSec: Math.max(0, measured.killCostSec ?? 0) }
+        : null;
+  }
+
   /**
    * Take the two readings a finished run carries. Either may be absent — a run
    * that was never told to stop did not die on command, and one that produced
@@ -112,8 +146,9 @@ export class RunCosts {
     // piece's encoding. Whoever uses it separates the two, because the piece
     // costs more when encoders share the machine and the spawn does not.
     return {
-      killCostSec: (middleOf(this.#dying) ?? 0) / 1000,
-      firstByteWaitSec: (middleOf(this.#firstOutput) ?? 0) / 1000,
+      killCostSec: (middleOf(this.#dying) ?? 0) / 1000 || (this.#atStartup?.killCostSec ?? 0),
+      firstByteWaitSec:
+        (middleOf(this.#firstOutput) ?? 0) / 1000 || (this.#atStartup?.firstByteWaitSec ?? 0),
       samples: Math.min(this.#dying.length, this.#firstOutput.length)
     };
   }

package/services/encode/start-stop-cost.js

@@ -0,0 +1,178 @@
+/**
+ * @file What starting and stopping an encoder costs on THIS host, measured
+ * before any viewer exists.
+ *
+ * WHY IT HAS TO BE MEASURED AT STARTUP. Both figures decide one thing: whether
+ * to leave an encoder where it stands or kill it and start another elsewhere.
+ * The plan compares when the wanted pieces appear under each arrangement, and
+ * for that it needs how long a fresh encoder takes to produce anything and how
+ * long killing one takes.
+ *
+ * Until now both were learned only from runs that had ENDED, so at a cold open
+ * they were zero — and zero does not read as "not measured", it reads as
+ * "free". A warming encoder then owed one piece and a moved one owed
+ * `0 + 0 + one piece`: the same figure to the millisecond. The tie fell to
+ * position, so any advantage however small won, and the plan moved the encoder
+ * on every pass. Field 2026-09-08, the first fifteen seconds of a session:
+ * start at #68, a second later kill and start at #69, half a second later kill
+ * and start at #68 again, each dying having produced nothing. Over two days,
+ * 153 runs stopped that way and 68 of them made no segment at all.
+ *
+ * ONE RUN GIVES BOTH READINGS. An encoder is started on a generated picture
+ * through the same pipeline a session uses, timed until it says it has closed
+ * its first piece, then killed and timed until it exits. Nothing about the
+ * measurement is chosen: it is the same encoder, the same muxer, the same
+ * channel the encoder announces finished pieces on.
+ */
+
+import { spawn } from "node:child_process";
+import { mkdtempSync, rmSync } from "node:fs";
+import os from "node:os";
+import path from "node:path";
+
+/**
+ * How long the measurement may take before it is abandoned.
+ *
+ * Not a property of the host and not a figure anything is derived from: it
+ * bounds a startup step so a machine that cannot produce a piece at all does not
+ * hold the proxy closed. A host that hits it has said something useful — that
+ * its first piece takes longer than this — and the plan is told the bound rather
+ * than a zero.
+ */
+const GIVE_UP_AFTER_MS = 30_000;
+
+/**
+ * Measure a start and a stop on this host.
+ *
+ * @param {object} params
+ * @param {string} params.ffmpegBin
+ * @param {import("./Encoder.js").Encoder} params.encoder - The encoder this
+ *   proxy has chosen, so the reading is of the thing that will actually run.
+ * @param {number} [params.segmentDurationSec]
+ * @param {{ info: Function, warn: Function }} [params.logger]
+ * @param {() => number} [params.now]
+ * @returns {Promise<{ firstByteWaitSec: number, killCostSec: number } | null>}
+ *   Null where nothing could be measured, which is said rather than passed off
+ *   as a zero.
+ */
+export async function measureStartAndStop({
+  ffmpegBin,
+  encoder,
+  segmentDurationSec = 4,
+  logger = null,
+  now = Date.now
+}) {
+  const log = logger ?? { info: () => {}, warn: () => {} };
+  const dir = mkdtempSync(path.join(os.tmpdir(), "tt-startstop-"));
+  try {
+    const args = [
+      "-hide_banner",
+      "-nostats",
+      "-loglevel",
+      "error",
+      // The device, where the kind takes one.
+      ...(typeof encoder?.benchmarkInputArgs === "function" ? encoder.benchmarkInputArgs() : []),
+      // A generated picture: the reading is of this host's encoder and muxer,
+      // and a file would add its own reading and its own download.
+      "-f",
+      "lavfi",
+      "-i",
+      `testsrc2=size=640x360:rate=25`,
+      "-t",
+      String(segmentDurationSec * 4),
+      // The encoder this proxy has chosen, asked for its own arguments: the
+      // reading must be of the thing that will actually run, since what a start
+      // costs is mostly the encoder opening.
+      // The same arguments the throughput benchmark uses, for the same reason:
+      // a start is timed on the encoder itself, not on a scaler in front of it.
+      ...(typeof encoder?.benchmarkArgs === "function"
+        ? encoder.benchmarkArgs(null)
+        : ["-c:v", "libx264", "-preset", "ultrafast"]),
+      "-an",
+      "-f",
+      "segment",
+      "-segment_time",
+      String(segmentDurationSec),
+      // The channel the encoder names its finished pieces on — the same one a
+      // session reads, so "the first piece exists" means here what it means
+      // there.
+      "-segment_list",
+      "pipe:3",
+      "-segment_list_flags",
+      "+live",
+      "-segment_format",
+      "mp4",
+      path.join(dir, "seg-%05d.mp4")
+    ];
+
+    const spawnedAt = now();
+    const child = spawn(ffmpegBin, args, {
+      stdio: ["ignore", "ignore", "pipe", "pipe"],
+      windowsHide: true
+    });
+
+    const firstPiece = await new Promise((resolve) => {
+      const timer = setTimeout(() => resolve(null), GIVE_UP_AFTER_MS);
+      timer.unref?.();
+      child.stdio?.[3]?.on("data", () => {
+        clearTimeout(timer);
+        resolve(now() - spawnedAt);
+      });
+      child.on("error", () => {
+        clearTimeout(timer);
+        resolve(null);
+      });
+      child.on("exit", () => {
+        clearTimeout(timer);
+        resolve(null);
+      });
+    });
+
+    if (firstPiece === null) {
+      try {
+        child.kill("SIGKILL");
+      } catch {
+        // Already gone.
+      }
+      log.warn("hwaccel: a start could not be measured; the plan is told so rather than told zero");
+      return null;
+    }
+
+    const killedAt = now();
+    const died = await new Promise((resolve) => {
+      const timer = setTimeout(() => resolve(null), GIVE_UP_AFTER_MS);
+      timer.unref?.();
+      child.on("exit", () => {
+        clearTimeout(timer);
+        resolve(now() - killedAt);
+      });
+      try {
+        child.kill("SIGTERM");
+      } catch {
+        clearTimeout(timer);
+        resolve(null);
+      }
+    });
+
+    const firstByteWaitSec = firstPiece / 1000;
+    const killCostSec = died === null ? 0 : died / 1000;
+    log.info(
+      `hwaccel: a start costs ${firstByteWaitSec.toFixed(2)}s to a first piece and ` +
+      `a stop ${killCostSec.toFixed(2)}s on this host — measured before any viewer, ` +
+      "because a plan told zero reads it as free and moves an encoder for nothing"
+    );
+    return { firstByteWaitSec, killCostSec };
+  } catch (error) {
+    log.warn(
+      `hwaccel: a start and a stop could not be measured: ` +
+      `${error instanceof Error ? error.message : String(error)}`
+    );
+    return null;
+  } finally {
+    try {
+      rmSync(dir, { recursive: true, force: true });
+    } catch {
+      // best effort
+    }
+  }
+}

package/services/hls-session-manager.js

@@ -94,6 +94,8 @@ import { LiveOutputs } from "./output/LiveOutputs.js";
 import { variantHeightsFor } from "./output/ladder.js";
 import { EncodeOrchestrator } from "./orchestrators/EncodeOrchestrator.js";
 import { wireDiskSpace } from "./disk/wire.js";
+import { IDLE_KEEP_MS } from "./disk/keep.js";
+import { Returns } from "./disk/returns.js";
 import { freeBytesFor } from "./disk/free.js";
 
 /**
@@ -474,7 +476,7 @@ const DEFAULT_SESSION_TTL_MS = 30 * 60 * 1000;
  * not this; this only stops something nobody has touched all day from sitting
  * there for the life of the process.
  */
-const SEGMENT_STORE_IDLE_MS = 6 * 60 * 60 * 1000;
+const SEGMENT_STORE_IDLE_MS = IDLE_KEEP_MS;
 const DEFAULT_STARTUP_WAIT_MS = 5_000;
 // Realtime budget — runtime downswitch (software encoder only). Periodically
 // check each active software-transcode session's ffmpeg `speed`; when it stays
@@ -1399,6 +1401,7 @@ export class HlsSessionManager {
     stateDir = "",
     segmentStore = null,
     getTorrentTotals,
+    startStopCost = null,
     spillDisk = null}) {
     this.enabled = Boolean(enabled);
     this.ffmpegBin = ffmpegBin;
@@ -1576,6 +1579,11 @@ export class HlsSessionManager {
       segmentStore: this.segmentStore,
       logger
     });
+    // What a start and a stop were measured to cost here, before any viewer
+    // existed. Without it both read zero at a cold open, and zero is not
+    // "unmeasured" — it is "free", which is what moved an encoder between two
+    // adjacent numbers every half second in the field.
+    this.encodeOrchestrator.noteStartupCosts(startStopCost);
     // Where each file is cut, held once per file and grid rather than once per
     // session. Two sessions of one film MUST agree about this to the
     // millisecond — a segment made by either has to be appendable where the
@@ -1599,6 +1607,10 @@ export class HlsSessionManager {
       void this.cleanupExpired();
     }, CLEANUP_INTERVAL_MS);
     this.cleanupTimer.unref();
+    // How long after material stops being read somebody asks for it again — the
+    // one term of the keeping period that is guessed rather than measured, and
+    // the only place it can be measured from.
+    this.returns = new Returns();
     // One owner of the disk, and the list of what takes it lives with the owner.
     this.diskSpace = wireDiskSpace({
       segmentStore: this.segmentStore,
@@ -2251,6 +2263,10 @@ export class HlsSessionManager {
     // session was never registered, and no sweep looks for one. Proxy
     // 2.9.101-2.9.102 failed here on every single request and the leftovers
     // were the only trace of it on disk.
+    // A RETURN, if this output was held before — and its age, which is the one
+    // term of the keeping period that nothing measures. Read BEFORE the
+    // directory is claimed, since claiming it is what marks it read.
+    this.returns.note({ lastReadAt: this.segmentStore.lastReadAt(spec.toKey()), now: Date.now() });
     this.segmentStore.directoryFor(spec.toKey());
     this.segmentStore.useFormat(spec.toKey(), segmentFormat);
 
@@ -9672,6 +9688,12 @@ export class HlsSessionManager {
     // last read, and how much room the disk has for the lot.
     // The room is the disk owner's to divide; this asks what the share is now.
     await this.diskSpace.revise();
+    // What viewers actually do, beside the period that stands in for it. Said
+    // where it can be read against the disk figures rather than on its own.
+    const returns = this.returns.describe(IDLE_KEEP_MS);
+    if (returns !== null) {
+      logger.info(returns);
+    }
     this.segmentStore.enforce({
       idleMs: SEGMENT_STORE_IDLE_MS,
       maxBytes: this.diskSpace.segmentBytes(),