X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGit.pm;h=2ae5eff9c01614a13f0781561c9aed64d1a52838;hb=081918279573b209c27a91e443c37df597bcd43f;hp=2323cecc49f1affe6571820e2653802aa1273a41;hpb=d78f50649a5545d66a61b5465ca7f5ce4be398ea;p=public-inbox.git diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm index 2323cecc..2ae5eff9 100644 --- a/lib/PublicInbox/Git.pm +++ b/lib/PublicInbox/Git.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2014-2020 all contributors +# Copyright (C) 2014-2021 all contributors # License: GPLv2 or later # # Used to read files from a git repository without excessive forking. @@ -12,15 +12,20 @@ use v5.10.1; use parent qw(Exporter); use POSIX (); use IO::Handle; # ->autoflush -use Errno qw(EINTR); +use Errno qw(EINTR EAGAIN); use File::Glob qw(bsd_glob GLOB_NOSORT); +use File::Spec (); use Time::HiRes qw(stat); use PublicInbox::Spawn qw(popen_rd); use PublicInbox::Tmpfile; +use IO::Poll qw(POLLIN); use Carp qw(croak); +use Digest::SHA (); +use PublicInbox::DS qw(dwaitpid); our @EXPORT_OK = qw(git_unquote git_quote); our $PIPE_BUFSIZ = 65536; # Linux default our $in_cleanup; +our $RDTIMEO = 60_000; # milliseconds use constant MAX_INFLIGHT => (($^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF()) * 3) @@ -92,9 +97,9 @@ sub alternates_changed { sub last_check_err { my ($self) = @_; my $fh = $self->{err_c} or return; - sysseek($fh, 0, 0) or fail($self, "sysseek failed: $!"); + sysseek($fh, 0, 0) or $self->fail("sysseek failed: $!"); defined(sysread($fh, my $buf, -s $fh)) or - fail($self, "sysread failed: $!"); + $self->fail("sysread failed: $!"); $buf; } @@ -103,24 +108,25 @@ sub _bidi_pipe { if ($self->{$pid}) { if (defined $err) { # "err_c" my $fh = $self->{$err}; - sysseek($fh, 0, 0) or fail($self, "sysseek failed: $!"); - truncate($fh, 0) or fail($self, "truncate failed: $!"); + sysseek($fh, 0, 0) or $self->fail("sysseek failed: $!"); + truncate($fh, 0) or $self->fail("truncate failed: $!"); } return; } my ($out_r, $out_w); - pipe($out_r, $out_w) or fail($self, "pipe failed: $!"); + pipe($out_r, $out_w) or $self->fail("pipe failed: $!"); my @cmd = (qw(git), "--git-dir=$self->{git_dir}", qw(-c core.abbrev=40 cat-file), $batch); my $redir = { 0 => $out_r }; if ($err) { my $id = "git.$self->{git_dir}$batch.err"; - my $fh = tmpfile($id) or fail($self, "tmpfile($id): $!"); + my $fh = tmpfile($id) or $self->fail("tmpfile($id): $!"); $self->{$err} = $fh; $redir->{2} = $fh; } my ($in_r, $p) = popen_rd(\@cmd, undef, $redir); $self->{$pid} = $p; + $self->{"$pid.owner"} = $$; $out_w->autoflush(1); if ($^O eq 'linux') { # 1031: F_SETPIPE_SZ fcntl($out_w, 1031, 4096); @@ -130,6 +136,8 @@ sub _bidi_pipe { $self->{$in} = $in_r; } +sub poll_in ($) { IO::Poll::_poll($RDTIMEO, fileno($_[0]), my $ev = POLLIN) } + sub my_read ($$$) { my ($fh, $rbuf, $len) = @_; my $left = $len - length($$rbuf); @@ -138,9 +146,12 @@ sub my_read ($$$) { $r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf)); if ($r) { $left -= $r; + } elsif (defined($r)) { # EOF + return 0; } else { - next if (!defined($r) && $! == EINTR); - return $r; + next if ($! == EAGAIN and poll_in($fh)); + next if $! == EINTR; # may be set by sysread or poll_in + return; # unrecoverable error } } \substr($$rbuf, 0, $len, ''); @@ -152,9 +163,15 @@ sub my_readline ($$) { if ((my $n = index($$rbuf, "\n")) >= 0) { return substr($$rbuf, 0, $n + 1, ''); } - my $r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf)); - next if $r || (!defined($r) && $! == EINTR); - return defined($r) ? '' : undef; # EOF or error + my $r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf)) + and next; + + # return whatever's left on EOF + return substr($$rbuf, 0, length($$rbuf)+1, '') if defined($r); + + next if ($! == EAGAIN and poll_in($fh)); + next if $! == EINTR; # may be set by sysread or poll_in + return; # unrecoverable error } } @@ -172,7 +189,7 @@ sub cat_async_retry ($$$$$) { for (my $i = 0; $i < @$inflight; $i += 3) { $buf .= "$inflight->[$i]\n"; } - print { $self->{out} } $buf or fail($self, "write error: $!"); + print { $self->{out} } $buf or $self->fail("write error: $!"); unshift(@$inflight, \$req, $cb, $arg); # \$ref to indicate retried cat_async_step($self, $inflight); # take one step @@ -202,16 +219,17 @@ sub cat_async_step ($$) { $type = 'missing'; $oid = ref($req) ? $$req : $req if $oid eq ''; } else { - $self->fail("Unexpected result from async git cat-file: $head"); + my $err = $! ? " ($!)" : ''; + $self->fail("bad result from async cat-file: $head$err"); } - eval { $cb->($bref, $oid, $type, $size, $arg) }; $self->{cat_rbuf} = $rbuf if $$rbuf ne ''; + eval { $cb->($bref, $oid, $type, $size, $arg) }; warn "E: $oid: $@\n" if $@; } sub cat_async_wait ($) { my ($self) = @_; - my $inflight = delete $self->{inflight} or return; + my $inflight = $self->{inflight} or return; while (scalar(@$inflight)) { cat_async_step($self, $inflight); } @@ -222,24 +240,23 @@ sub batch_prepare ($) { } sub _cat_file_cb { - my ($bref, undef, undef, $size, $result) = @_; - @$result = ($bref, $size); + my ($bref, $oid, $type, $size, $result) = @_; + @$result = ($bref, $oid, $type, $size); } sub cat_file { - my ($self, $oid, $sizeref) = @_; + my ($self, $oid) = @_; my $result = []; cat_async($self, $oid, \&_cat_file_cb, $result); cat_async_wait($self); - $$sizeref = $result->[1] if $sizeref; - $result->[0]; + wantarray ? @$result : $result->[0]; } sub check_async_step ($$) { my ($self, $inflight_c) = @_; die 'BUG: inflight empty or odd' if scalar(@$inflight_c) < 3; my ($req, $cb, $arg) = splice(@$inflight_c, 0, 3); - my $rbuf = delete($self->{rbuf_c}) // \(my $new = ''); + my $rbuf = delete($self->{chk_rbuf}) // \(my $new = ''); chomp(my $line = my_readline($self->{in_c}, $rbuf)); my ($hex, $type, $size) = split(/ /, $line); @@ -249,16 +266,16 @@ sub check_async_step ($$) { # https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/ if ($hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop') { my $ret = my_read($self->{in_c}, $rbuf, $type + 1); - fail($self, defined($ret) ? 'read EOF' : "read: $!") if !$ret; + $self->fail(defined($ret) ? 'read EOF' : "read: $!") if !$ret; } + $self->{chk_rbuf} = $rbuf if $$rbuf ne ''; eval { $cb->($hex, $type, $size, $arg, $self) }; warn "E: check($req) $@\n" if $@; - $self->{rbuf_c} = $rbuf if $$rbuf ne ''; } sub check_async_wait ($) { my ($self) = @_; - my $inflight_c = delete $self->{inflight_c} or return; + my $inflight_c = $self->{inflight_c} or return; while (scalar(@$inflight_c)) { check_async_step($self, $inflight_c); } @@ -275,10 +292,10 @@ sub check_async_begin ($) { sub check_async ($$$$) { my ($self, $oid, $cb, $arg) = @_; my $inflight_c = $self->{inflight_c} // check_async_begin($self); - if (scalar(@$inflight_c) >= MAX_INFLIGHT) { + while (scalar(@$inflight_c) >= MAX_INFLIGHT) { check_async_step($self, $inflight_c); } - print { $self->{out_c} } $oid, "\n" or fail($self, "write error: $!"); + print { $self->{out_c} } $oid, "\n" or $self->fail("write error: $!"); push(@$inflight_c, $oid, $cb, $arg); } @@ -310,44 +327,70 @@ sub _destroy { # GitAsyncCat::event_step may delete {pid} my $p = delete $self->{$pid} or return; - - # PublicInbox::DS may not be loaded - eval { PublicInbox::DS::dwaitpid($p, undef, undef) }; - waitpid($p, 0) if $@; # wait synchronously if not in event loop + dwaitpid($p) if $$ == $self->{"$pid.owner"}; } sub cat_async_abort ($) { my ($self) = @_; - if (my $inflight = delete $self->{inflight}) { + if (my $inflight = $self->{inflight}) { while (@$inflight) { my ($req, $cb, $arg) = splice(@$inflight, 0, 3); $req =~ s/ .*//; # drop git_dir for Gcf2Client eval { $cb->(undef, $req, undef, undef, $arg) }; warn "E: $req: $@ (in abort)\n" if $@; } + delete $self->{cat_rbuf}; + delete $self->{inflight}; } cleanup($self); } -sub fail { +sub fail { # may be augmented in subclasses my ($self, $msg) = @_; cat_async_abort($self); croak(ref($self) . ' ' . ($self->{git_dir} // '') . ": $msg"); } +# $git->popen(qw(show f00)); # or +# $git->popen(qw(show f00), { GIT_CONFIG => ... }, { 2 => ... }); sub popen { - my ($self, @cmd) = @_; - @cmd = ('git', "--git-dir=$self->{git_dir}", @cmd); - popen_rd(\@cmd); + my ($self, $cmd) = splice(@_, 0, 2); + $cmd = [ 'git', "--git-dir=$self->{git_dir}", + ref($cmd) ? @$cmd : ($cmd, grep { defined && !ref } @_) ]; + popen_rd($cmd, grep { !defined || ref } @_); # env and opt } +# same args as popen above sub qx { - my ($self, @cmd) = @_; - my $fh = $self->popen(@cmd); - local $/ = "\n"; - return <$fh> if wantarray; - local $/; - <$fh> + my $fh = popen(@_); + if (wantarray) { + my @ret = <$fh>; + close $fh; # caller should check $? + @ret; + } else { + local $/; + my $ret = <$fh>; + close $fh; # caller should check $? + $ret; + } +} + +sub date_parse { + my $self = shift; + map { + substr($_, length('--max-age='), -1) + } $self->qx('rev-parse', map { "--since=$_" } @_); +} + +# check_async and cat_async may trigger the other, so ensure they're +# both completely done by using this: +sub async_wait_all ($) { + my ($self) = @_; + while (scalar(@{$self->{inflight_c} // []}) || + scalar(@{$self->{inflight} // []})) { + $self->check_async_wait; + $self->cat_async_wait; + } } # returns true if there are pending "git cat-file" processes @@ -355,8 +398,9 @@ sub cleanup { my ($self) = @_; local $in_cleanup = 1; delete $self->{async_cat}; - check_async_wait($self); - cat_async_wait($self); + async_wait_all($self); + delete $self->{inflight}; + delete $self->{inflight_c}; _destroy($self, qw(cat_rbuf in out pid)); _destroy($self, qw(chk_rbuf in_c out_c pid_c err_c)); !!($self->{pid} || $self->{pid_c}); @@ -383,7 +427,7 @@ sub local_nick ($) { my $ret = '???'; # don't show full FS path, basename should be OK: if ($self->{git_dir} =~ m!/([^/]+)(?:/\.git)?\z!) { - $ret = "/path/to/$1"; + $ret = "$1.git"; } wantarray ? ($ret) : $ret; } @@ -416,28 +460,13 @@ sub cat_async_begin { sub cat_async ($$$;$) { my ($self, $oid, $cb, $arg) = @_; my $inflight = $self->{inflight} // cat_async_begin($self); - if (scalar(@$inflight) >= MAX_INFLIGHT) { + while (scalar(@$inflight) >= MAX_INFLIGHT) { cat_async_step($self, $inflight); } - - print { $self->{out} } $oid, "\n" or fail($self, "write error: $!"); + print { $self->{out} } $oid, "\n" or $self->fail("write error: $!"); push(@$inflight, $oid, $cb, $arg); } -sub async_prefetch { - my ($self, $oid, $cb, $arg) = @_; - if (my $inflight = $self->{inflight}) { - # we could use MAX_INFLIGHT here w/o the halving, - # but lets not allow one client to monopolize a git process - if (scalar(@$inflight) < int(MAX_INFLIGHT/2)) { - print { $self->{out} } $oid, "\n" or - fail($self, "write error: $!"); - return push(@$inflight, $oid, $cb, $arg); - } - } - undef; -} - sub extract_cmt_time { my ($bref, undef, undef, undef, $modified) = @_; @@ -462,6 +491,56 @@ sub modified ($) { $modified || time; } +# for grokmirror, which doesn't read gitweb.description +# templates/hooks--update.sample and git-multimail in git.git +# only match "Unnamed repository", not the full contents of +# templates/this--description in git.git +sub manifest_entry { + my ($self, $epoch, $default_desc) = @_; + my $fh = $self->popen('show-ref'); + my $dig = Digest::SHA->new(1); + while (read($fh, my $buf, 65536)) { + $dig->add($buf); + } + close $fh or return; # empty, uninitialized git repo + undef $fh; # for open, below + my $git_dir = $self->{git_dir}; + my $ent = { + fingerprint => $dig->hexdigest, + reference => undef, + modified => modified($self), + }; + chomp(my $owner = $self->qx('config', 'gitweb.owner')); + utf8::decode($owner); + $ent->{owner} = $owner eq '' ? undef : $owner; + my $desc = ''; + if (open($fh, '<', "$git_dir/description")) { + local $/ = "\n"; + chomp($desc = <$fh>); + utf8::decode($desc); + } + $desc = 'Unnamed repository' if $desc eq ''; + if (defined $epoch && $desc =~ /\AUnnamed repository/) { + $desc = "$default_desc [epoch $epoch]"; + } + $ent->{description} = $desc; + if (open($fh, '<', "$git_dir/objects/info/alternates")) { + # n.b.: GitPython doesn't seem to handle comments or C-quoted + # strings like native git does; and we don't for now, either. + local $/ = "\n"; + chomp(my @alt = <$fh>); + + # grokmirror only supports 1 alternate for "reference", + if (scalar(@alt) == 1) { + my $objdir = "$git_dir/objects"; + my $ref = File::Spec->rel2abs($alt[0], $objdir); + $ref =~ s!/[^/]+/?\z!!; # basename + $ent->{reference} = $ref; + } + } + $ent; +} + 1; __END__ =pod