# There are also API changes to simplify our usage and data set.
package PublicInbox::Git;
use strict;
-use warnings;
-use POSIX qw(dup2);
+use v5.10.1;
+use parent qw(Exporter);
+use POSIX ();
use IO::Handle; # ->autoflush
+use Errno qw(EINTR);
use File::Glob qw(bsd_glob GLOB_NOSORT);
+use Time::HiRes qw(stat);
use PublicInbox::Spawn qw(popen_rd);
use PublicInbox::Tmpfile;
-use base qw(Exporter);
+use Carp qw(croak);
our @EXPORT_OK = qw(git_unquote git_quote);
+our $PIPE_BUFSIZ = 65536; # Linux default
+our $in_cleanup;
use constant MAX_INFLIGHT =>
- ($^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF())
+ (($^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF()) * 3)
/
65; # SHA-256 hex size + "\n" in preparation for git using non-SHA1
sub new {
my ($class, $git_dir) = @_;
- my @st;
- $st[7] = $st[10] = 0;
# may contain {-tmp} field for File::Temp::Dir
- bless { git_dir => $git_dir, st => \@st, -git_path => {} }, $class
+ bless { git_dir => $git_dir, alt_st => '', -git_path => {} }, $class
}
sub git_path ($$) {
my ($self) = @_;
my $alt = git_path($self, 'objects/info/alternates');
my @st = stat($alt) or return 0;
- my $old_st = $self->{st};
- # 10 - ctime, 7 - size
- return 0 if ($st[10] == $old_st->[10] && $st[7] == $old_st->[7]);
- $self->{st} = \@st;
+
+ # can't rely on 'q' on some 32-bit builds, but `d' works
+ my $st = pack('dd', $st[10], $st[7]); # 10: ctime, 7: size
+ return 0 if $self->{alt_st} eq $st;
+ $self->{alt_st} = $st; # always a true value
}
sub last_check_err {
$self->{$in} = $in_r;
}
-sub read_cat_in_full ($$$) {
- my ($self, $in, $left) = @_;
- my $offset = 0;
- my $buf = '';
+sub my_read ($$$) {
+ my ($fh, $rbuf, $len) = @_;
+ my $left = $len - length($$rbuf);
+ my $r;
while ($left > 0) {
- my $r = read($in, $buf, $left, $offset);
- defined($r) or fail($self, "read failed: $!");
- $r == 0 and fail($self, 'exited unexpectedly');
- $left -= $r;
- $offset += $r;
+ $r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf));
+ if ($r) {
+ $left -= $r;
+ } else {
+ next if (!defined($r) && $! == EINTR);
+ return $r;
+ }
}
- my $r = read($in, my $lf, 1);
- defined($r) or fail($self, "read failed: $!");
- fail($self, 'newline missing after blob') if ($r != 1 || $lf ne "\n");
- \$buf;
+ \substr($$rbuf, 0, $len, '');
}
-sub _cat_async_step ($$$) {
- my ($self, $inflight, $in) = @_;
- my $pair = shift @$inflight or die 'BUG: inflight empty';
- my ($cb, $arg) = @$pair;
- local $/ = "\n";
- my $head = $in->getline;
- $head =~ / missing$/ and return
- eval { $cb->(undef, undef, undef, undef, $arg) };
+sub my_readline ($$) {
+ my ($fh, $rbuf) = @_;
+ while (1) {
+ if ((my $n = index($$rbuf, "\n")) >= 0) {
+ return substr($$rbuf, 0, $n + 1, '');
+ }
+ my $r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf));
+ next if $r || (!defined($r) && $! == EINTR);
+ return defined($r) ? '' : undef; # EOF or error
+ }
+}
+
+sub cat_async_retry ($$$$$) {
+ my ($self, $inflight, $req, $cb, $arg) = @_;
+
+ # {inflight} may be non-existent, but if it isn't we delete it
+ # here to prevent cleanup() from waiting:
+ delete $self->{inflight};
+ cleanup($self);
+
+ $self->{inflight} = $inflight;
+ batch_prepare($self);
+ my $buf = "$req\n";
+ for (my $i = 0; $i < @$inflight; $i += 3) {
+ $buf .= "$inflight->[$i]\n";
+ }
+ print { $self->{out} } $buf or fail($self, "write error: $!");
+ unshift(@$inflight, \$req, $cb, $arg); # \$ref to indicate retried
+
+ cat_async_step($self, $inflight); # take one step
+}
- $head =~ /^([0-9a-f]{40}) (\S+) ([0-9]+)$/ or
+sub cat_async_step ($$) {
+ my ($self, $inflight) = @_;
+ die 'BUG: inflight empty or odd' if scalar(@$inflight) < 3;
+ my ($req, $cb, $arg) = splice(@$inflight, 0, 3);
+ my $rbuf = delete($self->{cat_rbuf}) // \(my $new = '');
+ my ($bref, $oid, $type, $size);
+ my $head = my_readline($self->{in}, $rbuf);
+ if ($head =~ /^([0-9a-f]{40}) (\S+) ([0-9]+)$/) {
+ ($oid, $type, $size) = ($1, $2, $3 + 0);
+ $bref = my_read($self->{in}, $rbuf, $size + 1) or
+ fail($self, defined($bref) ? 'read EOF' : "read: $!");
+ chop($$bref) eq "\n" or fail($self, 'LF missing after blob');
+ } elsif ($head =~ / missing$/) {
+ # ref($req) indicates it's already been retried
+ if (!ref($req) && !$in_cleanup && alternates_changed($self)) {
+ return cat_async_retry($self, $inflight,
+ $req, $cb, $arg);
+ }
+ $type = 'missing';
+ $oid = ref($req) ? $$req : $req;
+ } else {
fail($self, "Unexpected result from async git cat-file: $head");
- my ($oid_hex, $type, $size) = ($1, $2, $3 + 0);
- my $bref = read_cat_in_full($self, $in, $size);
- eval { $cb->($bref, $oid_hex, $type, $size, $arg) };
+ }
+ eval { $cb->($bref, $oid, $type, $size, $arg) };
+ $self->{cat_rbuf} = $rbuf if $$rbuf ne '';
+ warn "E: $oid: $@\n" if $@;
}
sub cat_async_wait ($) {
my ($self) = @_;
my $inflight = delete $self->{inflight} or return;
- my $in = $self->{in};
while (scalar(@$inflight)) {
- _cat_async_step($self, $inflight, $in);
+ cat_async_step($self, $inflight);
}
}
+sub batch_prepare ($) {
+ _bidi_pipe($_[0], qw(--batch in out pid));
+}
+
+sub _cat_file_cb {
+ my ($bref, undef, undef, $size, $result) = @_;
+ @$result = ($bref, $size);
+}
+
sub cat_file {
- my ($self, $obj, $ref) = @_;
- my ($retried, $in, $head);
+ my ($self, $oid, $sizeref) = @_;
+ my $result = [];
+ cat_async($self, $oid, \&_cat_file_cb, $result);
cat_async_wait($self);
-again:
- batch_prepare($self);
- $self->{out}->print($obj, "\n") or fail($self, "write error: $!");
+ $$sizeref = $result->[1] if $sizeref;
+ $result->[0];
+}
- $in = $self->{in};
- local $/ = "\n";
- $head = $in->getline;
- if ($head =~ / missing$/) {
- if (!$retried && alternates_changed($self)) {
- $retried = 1;
- cleanup($self);
- goto again;
- }
- return;
+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 = '');
+ chomp(my $line = my_readline($self->{in_c}, $rbuf));
+ my ($hex, $type, $size) = split(/ /, $line);
+
+ # Future versions of git.git may have type=ambiguous, but for now,
+ # we must handle 'dangling' below (and maybe some other oddball
+ # stuff):
+ # https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/
+ if ($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;
}
- $head =~ /^[0-9a-f]{40} \S+ ([0-9]+)$/ or
- fail($self, "Unexpected result from git cat-file: $head");
+ eval { $cb->($hex, $type, $size, $arg, $self) };
+ warn "E: check($req) $@\n" if $@;
+ $self->{rbuf_c} = $rbuf if $$rbuf ne '';
+}
+
+sub check_async_wait ($) {
+ my ($self) = @_;
+ my $inflight_c = delete $self->{inflight_c} or return;
+ while (scalar(@$inflight_c)) {
+ check_async_step($self, $inflight_c);
+ }
+}
- my $size = $1;
- $$ref = $size if $ref;
- read_cat_in_full($self, $in, $size);
+sub check_async_begin ($) {
+ my ($self) = @_;
+ cleanup($self) if alternates_changed($self);
+ _bidi_pipe($self, qw(--batch-check in_c out_c pid_c err_c));
+ die 'BUG: already in async check' if $self->{inflight_c};
+ $self->{inflight_c} = [];
+}
+
+sub check_async ($$$$) {
+ my ($self, $oid, $cb, $arg) = @_;
+ my $inflight_c = $self->{inflight_c} // check_async_begin($self);
+ if (scalar(@$inflight_c) >= MAX_INFLIGHT) {
+ check_async_step($self, $inflight_c);
+ }
+ print { $self->{out_c} } $oid, "\n" or fail($self, "write error: $!");
+ push(@$inflight_c, $oid, $cb, $arg);
}
-sub batch_prepare ($) { _bidi_pipe($_[0], qw(--batch in out pid)) }
+sub _check_cb { # check_async callback
+ my ($hex, $type, $size, $result) = @_;
+ @$result = ($hex, $type, $size);
+}
sub check {
- my ($self, $obj) = @_;
- _bidi_pipe($self, qw(--batch-check in_c out_c pid_c err_c));
- $self->{out_c}->print($obj, "\n") or fail($self, "write error: $!");
- local $/ = "\n";
- chomp(my $line = $self->{in_c}->getline);
- my ($hex, $type, $size) = split(' ', $line);
+ my ($self, $oid) = @_;
+ my $result = [];
+ check_async($self, $oid, \&_check_cb, $result);
+ check_async_wait($self);
+ my ($hex, $type, $size) = @$result;
# Future versions of git.git may show 'ambiguous', but for now,
# we must handle 'dangling' below (and maybe some other oddball
# stuff):
# https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/
return if $type eq 'missing' || $type eq 'ambiguous';
-
- if ($hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop') {
- $size = $type + length("\n");
- my $r = read($self->{in_c}, my $buf, $size);
- defined($r) or fail($self, "read failed: $!");
- return;
- }
-
+ return if $hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop';
($hex, $type, $size);
}
sub _destroy {
- my ($self, $in, $out, $pid, $err) = @_;
+ my ($self, $rbuf, $in, $out, $pid, $err) = @_;
my $p = delete $self->{$pid} or return;
- delete @$self{($in, $out)};
+ delete @$self{($rbuf, $in, $out)};
delete $self->{$err} if $err; # `err_c'
# PublicInbox::DS may not be loaded
sub fail {
my ($self, $msg) = @_;
$self->{inflight} ? cat_async_abort($self) : cleanup($self);
- die $msg;
+ croak("git $self->{git_dir}: $msg");
}
sub popen {
# returns true if there are pending "git cat-file" processes
sub cleanup {
my ($self) = @_;
- _destroy($self, qw(in out pid));
- _destroy($self, qw(in_c out_c pid_c err_c));
+ local $in_cleanup = 1;
+ delete $self->{async_cat};
+ check_async_wait($self);
+ cat_async_wait($self);
+ _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});
}
sub cat_async ($$$;$) {
my ($self, $oid, $cb, $arg) = @_;
- my $inflight = $self->{inflight} or die 'BUG: not in async';
+ my $inflight = $self->{inflight} // cat_async_begin($self);
if (scalar(@$inflight) >= MAX_INFLIGHT) {
- _cat_async_step($self, $inflight, $self->{in});
+ cat_async_step($self, $inflight);
}
- $self->{out}->print($oid, "\n") or fail($self, "write error: $!");
- push(@$inflight, [ $cb, $arg ]);
+ print { $self->{out} } $oid, "\n" or fail($self, "write error: $!");
+ push(@$inflight, $oid, $cb, $arg);
+}
+
+# this is safe to call inside $cb, but not guaranteed to enqueue
+# returns true if successful, undef if not.
+sub async_prefetch {
+ my ($self, $oid, $cb, $arg) = @_;
+ if (defined($self->{async_cat}) && (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, $arg);
+ }
+ }
+ undef;
}
sub extract_cmt_time {
my ($self) = @_;
my $modified = 0;
my $fh = popen($self, qw(rev-parse --branches));
- cat_async_begin($self);
local $/ = "\n";
while (my $oid = <$fh>) {
chomp $oid;