From 6606a7f86e97b9e5bcf19375fd0b7776cff84438 Mon Sep 17 00:00:00 2001
From: Pierre Bourdon <delroth@gmail.com>
Date: Sat, 20 Apr 2024 22:18:13 +0200
Subject: [PATCH] queue runner: introduce some parallelism for remote paths
 lookup

Each output for a given step being ingested is looked up in parallel,
which should basically multiply the speed of builds ingestion by the
average number of outputs per derivation.
---
 src/hydra-queue-runner/queue-monitor.cc | 40 +++++++++++++++++++++----
 src/hydra-queue-runner/state.hh         |  6 ++++
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/src/hydra-queue-runner/queue-monitor.cc b/src/hydra-queue-runner/queue-monitor.cc
index 5ab15230..4b98cbc6 100644
--- a/src/hydra-queue-runner/queue-monitor.cc
+++ b/src/hydra-queue-runner/queue-monitor.cc
@@ -1,6 +1,7 @@
 #include "state.hh"
 #include "hydra-build-result.hh"
 #include "globals.hh"
+#include "thread-pool.hh"
 
 #include <cstring>
 
@@ -403,6 +404,34 @@ void State::processQueueChange(Connection & conn)
 }
 
 
+std::map<DrvOutput, std::optional<StorePath>> State::getMissingRemotePaths(
+    ref<Store> destStore,
+    const std::map<DrvOutput, std::optional<StorePath>> & paths)
+{
+    Sync<std::map<DrvOutput, std::optional<StorePath>>> missing_;
+    ThreadPool tp;
+
+    for (auto & [output, maybeOutputPath] : paths) {
+        if (!maybeOutputPath) {
+            auto missing(missing_.lock());
+            missing->insert({output, maybeOutputPath});
+        } else {
+            tp.enqueue([&] {
+                if (!destStore->isValidPath(*maybeOutputPath)) {
+                    auto missing(missing_.lock());
+                    missing->insert({output, maybeOutputPath});
+                }
+            });
+        }
+    }
+
+    tp.process();
+
+    auto missing(missing_.lock());
+    return *missing;
+}
+
+
 Step::ptr State::createStep(ref<Store> destStore,
     Connection & conn, Build::ptr build, const StorePath & drvPath,
     Build::ptr referringBuild, Step::ptr referringStep, std::set<StorePath> & finishedDrvs,
@@ -483,16 +512,15 @@ Step::ptr State::createStep(ref<Store> destStore,
 
     /* Are all outputs valid? */
     auto outputHashes = staticOutputHashes(*localStore, *(step->drv));
-    bool valid = true;
-    std::map<DrvOutput, std::optional<StorePath>> missing;
+    std::map<DrvOutput, std::optional<StorePath>> paths;
     for (auto & [outputName, maybeOutputPath] : destStore->queryPartialDerivationOutputMap(drvPath, &*localStore)) {
         auto outputHash = outputHashes.at(outputName);
-        if (maybeOutputPath && destStore->isValidPath(*maybeOutputPath))
-            continue;
-        valid = false;
-        missing.insert({{outputHash, outputName}, maybeOutputPath});
+        paths.insert({{outputHash, outputName}, maybeOutputPath});
     }
 
+    auto missing = getMissingRemotePaths(destStore, paths);
+    bool valid = missing.empty();
+
     /* Try to copy the missing paths from the local store or from
        substitutes. */
     if (!missing.empty()) {
diff --git a/src/hydra-queue-runner/state.hh b/src/hydra-queue-runner/state.hh
index 922e61d5..dd1c8931 100644
--- a/src/hydra-queue-runner/state.hh
+++ b/src/hydra-queue-runner/state.hh
@@ -553,6 +553,12 @@ private:
     BuildOutput getBuildOutputCached(Connection & conn, nix::ref<nix::Store> destStore,
         const nix::StorePath & drvPath);
 
+    /* Returns paths missing from the remote store. Paths are processed in
+     * parallel to work around the possible latency of remote stores. */
+    std::map<nix::DrvOutput, std::optional<nix::StorePath>> getMissingRemotePaths(
+        nix::ref<nix::Store> destStore,
+        const std::map<nix::DrvOutput, std::optional<nix::StorePath>> & paths);
+
     Step::ptr createStep(nix::ref<nix::Store> store,
         Connection & conn, Build::ptr build, const nix::StorePath & drvPath,
         Build::ptr referringBuild, Step::ptr referringStep, std::set<nix::StorePath> & finishedDrvs,