download-from-binary-cache: parallelise fetching of NAR info files

Getting substitute information using the binary cache substituter has
non-trivial latency overhead.  A package or NixOS system configuration
can have hundreds of dependencies, and in the worst case (when the
local info cache is empty) we have to do a separate HTTP request for
each of these.  If the ping time to the server is t, getting N info
files will take tN seconds; e.g., with a ping time of 0.1s to
nixos.org, sequentially downloading 1000 info files (a typical NixOS
config) will take at least 100 seconds.

To fix this problem, the binary cache substituter can now perform
requests in parallel.  This required changing the substituter
interface to support a function querySubstitutablePathInfos() that
queries multiple paths at the same time, and rewriting queryMissing()
to take advantage of parallelism.  (Due to local caching,
parallelising queryMissing() is sufficient for most use cases, since
it's almost always called before building a derivation and thus fills
the local info cache.)

For example, parallelism speeds up querying all 1056 paths in a
particular NixOS system configuration from 116s to 2.6s.  It works so
well because the eccentricity of the top-level derivation in the
dependency graph is only 9.  So we only need 10 round-trips (when
using an unlimited number of parallel connections) to get everything.

Currently we do a maximum of 150 parallel connections to the server.
Thus it's important that the binary cache server (e.g. nixos.org) has
a high connection limit.  Alternatively we could use HTTP pipelining,
but WWW::Curl doesn't support it and libcurl has a hard-coded limit of
5 requests per pipeline.

1 files changed, 128 insertions, 76 deletions

diff --git a/scripts/download-from-binary-cache.pl.in b/scripts/download-from-binary-cache.pl.in
index ea37c818d311..a67818e7f5b4 100644
--- a/scripts/download-from-binary-cache.pl.in
+++ b/scripts/download-from-binary-cache.pl.in
@@ -12,33 +12,40 @@ use strict;
 
 my @binaryCacheUrls = map { s/\/+$//; $_ } split(/ /, ($ENV{"NIX_BINARY_CACHES"} || ""));
 
+my $maxParallelRequests = 150;
+
 my ($dbh, $insertNAR, $queryNAR, $insertNegativeNAR, $queryNegativeNAR);
 my %cacheIds;
 
 my $curlm = WWW::Curl::Multi->new;
 my $activeRequests = 0;
 my $curlIdCount = 1;
-my %curlHandles;
+my %requests;
+my %scheduled;
 my $caBundle = $ENV{"CURL_CA_BUNDLE"} || $ENV{"OPENSSL_X509_CERT_FILE"};
 
 
 sub addRequest {
-    my ($url) = @_;
+    my ($storePath, $url) = @_;
     
     my $curl = WWW::Curl::Easy->new;
     my $curlId = $curlIdCount++;
-    $curlHandles{$curlId} = { handle => $curl, content => "" };
+    $requests{$curlId} = { storePath => $storePath, url => $url, handle => $curl, content => "" };
 
     $curl->setopt(CURLOPT_PRIVATE, $curlId);
     $curl->setopt(CURLOPT_URL, $url);
-    $curl->setopt(CURLOPT_WRITEDATA, \$curlHandles{$curlId}->{content});
+    $curl->setopt(CURLOPT_WRITEDATA, \$requests{$curlId}->{content});
     $curl->setopt(CURLOPT_FOLLOWLOCATION, 1);
     $curl->setopt(CURLOPT_CAINFO, $caBundle) if defined $caBundle;
 
-    $curlm->add_handle($curl);
-    $activeRequests++;
+    if ($activeRequests >= $maxParallelRequests) {
+        $scheduled{$curlId} = 1;
+    } else {
+        $curlm->add_handle($curl);
+        $activeRequests++;
+    }
 
-    return $curlHandles{$curlId};
+    return $requests{$curlId};
 }
 
 
@@ -55,12 +62,20 @@ sub processRequests {
         if ($curlm->perform() != $activeRequests) {
             while (my ($id, $result) = $curlm->info_read) {
                 if ($id) {
-                    my $handle = $curlHandles{$id}->{handle};
-                    $curlHandles{$id}->{result} = $result;
-                    $curlHandles{$id}->{httpStatus} = $handle->getinfo(CURLINFO_HTTP_CODE);
-                    #print STDERR "\nRequest completed ($id, $result, $curlHandles{$id}->{httpStatus})\n";
+                    my $handle = $requests{$id}->{handle};
+                    $requests{$id}->{result} = $result;
+                    $requests{$id}->{httpStatus} = $handle->getinfo(CURLINFO_HTTP_CODE);
+                    #print STDERR "\nRequest completed ($id, $result, $requests{$id}->{httpStatus})\n";
                     $activeRequests--;
-                    delete $curlHandles{$id}->{handle};
+                    delete $requests{$id}->{handle};
+
+                    if (scalar(keys %scheduled) > 0) {
+                        my $id2 = (keys %scheduled)[0];
+                        $curlm->add_handle($requests{$id2}->{handle});
+                        $activeRequests++;
+                        delete $scheduled{$id2};
+                    }
+                    
                 }
             }
         }
@@ -130,23 +145,21 @@ EOF
 }
 
 
-sub getInfoFrom {
-    my ($storePath, $pathHash, $binaryCacheUrl) = @_;
+sub negativeHit {
+    my ($storePath, $binaryCacheUrl) = @_;
+    $queryNegativeNAR->execute(getCacheId($binaryCacheUrl), basename($storePath));
+    return @{$queryNegativeNAR->fetchall_arrayref()} != 0;
+}
 
-    my $cacheId = getCacheId($binaryCacheUrl);
 
-    # Bail out if there is a negative cache entry.
-    $queryNegativeNAR->execute($cacheId, basename($storePath));
-    return undef if @{$queryNegativeNAR->fetchall_arrayref()} != 0;
+sub processNARInfo {
+    my ($storePath, $binaryCacheUrl, $request) = @_;
     
-    my $infoUrl = "$binaryCacheUrl/$pathHash.narinfo";
-    print STDERR "checking $infoUrl...\n";
-    my $request = addRequest($infoUrl);
-    processRequests;
+    my $cacheId = getCacheId($binaryCacheUrl);
 
     if ($request->{result} != 0 || $request->{httpStatus} != 200) {
         if ($request->{httpStatus} != 404) {
-            print STDERR "could not download ‘$infoUrl’ (" .
+            print STDERR "could not download ‘$request->{url}’ (" .
                 ($request->{result} != 0 ? "Curl error $request->{result}" : "HTTP status $request->{httpStatus}") . ")\n";
         } else {
             $insertNegativeNAR->execute($cacheId, basename($storePath), time());
@@ -172,7 +185,7 @@ sub getInfoFrom {
     }
     return undef if $storePath ne $storePath2;
     if ($storePath ne $storePath2 || !defined $url || !defined $narHash) {
-        print STDERR "bad NAR info file ‘$infoUrl’\n";
+        print STDERR "bad NAR info file ‘$request->{url}’\n";
         return undef;
     }
     
@@ -236,24 +249,65 @@ sub cachedGetInfoFrom {
 }
 
 
-sub getInfo {
-    my ($storePath) = @_;
+sub printInfo {
+    my ($storePath, $info) = @_;
+    print "$storePath\n";
+    print $info->{deriver} ? "$Nix::Config::storeDir/$info->{deriver}" : "", "\n";
+    print scalar @{$info->{refs}}, "\n";
+    print "$Nix::Config::storeDir/$_\n" foreach @{$info->{refs}};
+    print $info->{fileSize} || 0, "\n";
+    print $info->{narSize} || 0, "\n";
+}
 
-    my $pathHash = substr(basename($storePath), 0, 32);
 
-    # First look if we have cached info for one of the URLs.
-    foreach my $binaryCacheUrl (@binaryCacheUrls) {
-        my $info = cachedGetInfoFrom($storePath, $pathHash, $binaryCacheUrl);
-        return $info if defined $info;
+sub printInfoParallel {
+    my @paths = @_;
+
+    # First print all paths for which we have cached info.
+    my @left;
+    foreach my $storePath (@paths) {
+        my $pathHash = substr(basename($storePath), 0, 32);
+        my $found = 0;
+        foreach my $binaryCacheUrl (@binaryCacheUrls) {
+            my $info = cachedGetInfoFrom($storePath, $pathHash, $binaryCacheUrl);
+            if (defined $info) {
+                printInfo($storePath, $info);
+                $found = 1;
+                last;
+            }
+        }
+        push @left, $storePath if !$found;
     }
 
-    # No, so do an HTTP request until we get a hit.
+    return if scalar @left == 0;
+
     foreach my $binaryCacheUrl (@binaryCacheUrls) {
-        my $info = getInfoFrom($storePath, $pathHash, $binaryCacheUrl);
-        return $info if defined $info;
-    }
 
-    return undef;
+        my @left2;
+        %requests = ();
+        foreach my $storePath (@left) {
+            my $pathHash = substr(basename($storePath), 0, 32);
+            if (negativeHit($storePath, $binaryCacheUrl)) {
+                push @left2, $storePath;
+                next;
+            }
+            my $infoUrl = "$binaryCacheUrl/$pathHash.narinfo";
+            addRequest($storePath, $infoUrl);
+        }
+
+        processRequests;
+
+        foreach my $request (values %requests) {
+            my $info = processNARInfo($request->{storePath}, $binaryCacheUrl, $request);
+            if (defined $info) {
+                printInfo($request->{storePath}, $info);
+            } else {
+                push @left2, $request->{storePath};
+            }
+        }
+
+        @left = @left2;
+    }
 }
 
 
@@ -264,30 +318,37 @@ sub downloadBinary {
 
     cache: foreach my $binaryCacheUrl (@binaryCacheUrls) {
         my $info = cachedGetInfoFrom($storePath, $pathHash, $binaryCacheUrl);
-        $info = getInfoFrom($storePath, $pathHash, $binaryCacheUrl) unless defined $info;
-        if (defined $info) {
-            my $decompressor;
-            if ($info->{compression} eq "bzip2") { $decompressor = "$Nix::Config::bzip2 -d"; }
-            elsif ($info->{compression} eq "xz") { $decompressor = "$Nix::Config::xz -d"; }
-            else {
-                print STDERR "unknown compression method ‘$info->{compression}’\n";
-                next;
-            }
-            print STDERR "\n*** Downloading ‘$info->{url}’ into ‘$storePath’...\n";
-            if (system("$Nix::Config::curl --fail --location $binaryCacheUrl/$info->{url} | $decompressor | $Nix::Config::binDir/nix-store --restore $storePath") != 0) {
-                die "download of `$info->{url}' failed" . ($! ? ": $!" : "") . "\n" unless $? == 0;
-                next;
-            }
-            # The hash in the manifest can be either in base-16 or
-            # base-32.  Handle both.
-            $info->{narHash} =~ /^sha256:(.*)$/ or die "invalid hash";
-            my $hash = $1;
-            my $hash2 = hashPath("sha256", 1, $storePath);
-            die "hash mismatch in downloaded path ‘$storePath’; expected $hash, got $hash2\n"
-                if $hash ne $hash2;
-            print STDERR "\n";
-            return 1;
+
+        unless (defined $info) {
+            next if negativeHit($storePath, $binaryCacheUrl);
+            my $request = addRequest($storePath, "$binaryCacheUrl/$pathHash.narinfo");
+            processRequests;
+            $info = processNARInfo($storePath, $binaryCacheUrl, $request);
+        }
+
+        next unless defined $info;
+        
+        my $decompressor;
+        if ($info->{compression} eq "bzip2") { $decompressor = "$Nix::Config::bzip2 -d"; }
+        elsif ($info->{compression} eq "xz") { $decompressor = "$Nix::Config::xz -d"; }
+        else {
+            print STDERR "unknown compression method ‘$info->{compression}’\n";
+            next;
+        }
+        print STDERR "\n*** Downloading ‘$info->{url}’ into ‘$storePath’...\n";
+        if (system("$Nix::Config::curl --fail --location $binaryCacheUrl/$info->{url} | $decompressor | $Nix::Config::binDir/nix-store --restore $storePath") != 0) {
+            die "download of `$info->{url}' failed" . ($! ? ": $!" : "") . "\n" unless $? == 0;
+            next;
         }
+        # The hash in the manifest can be either in base-16 or
+        # base-32.  Handle both.
+        $info->{narHash} =~ /^sha256:(.*)$/ or die "invalid hash";
+        my $hash = $1;
+        my $hash2 = hashPath("sha256", 1, $storePath);
+        die "hash mismatch in downloaded path ‘$storePath’; expected $hash, got $hash2\n"
+            if $hash ne $hash2;
+        print STDERR "\n";
+        return 1;
     }
 
     return 0;
@@ -300,29 +361,20 @@ initCache();
 if ($ARGV[0] eq "--query") {
 
     while (<STDIN>) {
-        my $cmd = $_; chomp $cmd;
-
+        chomp;
+        my ($cmd, @args) = split " ", $_;
+        
         if ($cmd eq "have") {
             my $storePath = <STDIN>; chomp $storePath;
             # FIXME: want to give correct info here, but it's too slow.
-            #print "0\n";
-            my $info = getInfo($storePath);
-            if (defined $info) { print "1\n"; } else { print "0\n"; }
+            print "0\n";
+            #my $info = getInfo($storePath);
+            #if (defined $info) { print "1\n"; } else { print "0\n"; }
         }
 
         elsif ($cmd eq "info") {
-            my $storePath = <STDIN>; chomp $storePath;
-            my $info = getInfo($storePath);
-            if (defined $info) {
-                print "1\n";
-                print $info->{deriver} ? "$Nix::Config::storeDir/$info->{deriver}" : "", "\n";
-                print scalar @{$info->{refs}}, "\n";
-                print "$Nix::Config::storeDir/$_\n" foreach @{$info->{refs}};
-                print $info->{fileSize} || 0, "\n";
-                print $info->{narSize} || 0, "\n";
-            } else {
-                print "0\n";
-            }
+            printInfoParallel(@args);
+            print "\n";
         }
 
         else { die "unknown command `$cmd'"; }