user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
Search results ordered by [date|relevance]  view[summary|nested|Atom feed]
thread overview below | download mbox.gz: |
* [PATCH 35/82] git: async: automatic retry on alternates change
  2020-06-10  7:03  5% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
@ 2020-06-10  7:04  7% ` Eric Wong
  0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-06-10  7:04 UTC (permalink / raw)
  To: meta

This matches the behavior of the existing synchronous ->cat_file
method.  In fact, ->cat_file now becomes a small wrapper around
the ->cat_async method.
---
 lib/PublicInbox/Git.pm | 64 +++++++++++++++++++++++++-----------------
 t/git.t                | 37 ++++++++++++++++++++----
 2 files changed, 70 insertions(+), 31 deletions(-)

diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index 60236afe7bf..a55c48d5f52 100644
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -18,6 +18,7 @@ use base qw(Exporter);
 our @EXPORT_OK = qw(git_unquote git_quote);
 use Errno qw(EINTR);
 our $PIPE_BUFSIZ = 65536; # Linux default
+our $in_cleanup;
 
 use constant MAX_INFLIGHT =>
 	(($^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF()) * 3)
@@ -155,6 +156,26 @@ sub my_readline ($$) {
 	}
 }
 
+sub cat_async_retry ($$$$$) {
+	my ($self, $inflight, $req, $cb, $arg) = @_;
+
+	# {inflight} may be non-existent, but if it isn't we delete it
+	# here to prevent cleanup() from waiting:
+	delete $self->{inflight};
+	cleanup($self);
+
+	$self->{inflight} = $inflight;
+	batch_prepare($self);
+	my $buf = "$req\n";
+	for (my $i = 0; $i < @$inflight; $i += 3) {
+		$buf .= "$inflight->[$i]\n";
+	}
+	print { $self->{out} } $buf or fail($self, "write error: $!");
+	unshift(@$inflight, \$req, $cb, $arg); # \$ref to indicate retried
+
+	cat_async_step($self, $inflight); # take one step
+}
+
 sub cat_async_step ($$) {
 	my ($self, $inflight) = @_;
 	die 'BUG: inflight empty or odd' if scalar(@$inflight) < 3;
@@ -168,8 +189,13 @@ sub cat_async_step ($$) {
 			fail($self, defined($bref) ? 'read EOF' : "read: $!");
 		chop($$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 = $req;
+		$oid = ref($req) ? $$req : $req;
 	} else {
 		fail($self, "Unexpected result from async git cat-file: $head");
 	}
@@ -190,33 +216,18 @@ sub batch_prepare ($) {
 	_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, $sizeref) = @_;
-	my ($retried, $head, $rbuf);
+	my ($self, $oid, $sizeref) = @_;
+	my $result = [];
+	cat_async($self, $oid, \&_cat_file_cb, $result);
 	cat_async_wait($self);
-again:
-	batch_prepare($self);
-	$rbuf = delete($self->{cat_rbuf}) // \(my $new = '');
-	print { $self->{out} } $obj, "\n" or fail($self, "write error: $!");
-	$head = my_readline($self->{in}, $rbuf);
-	if ($head =~ / missing$/) {
-		if (!$retried && alternates_changed($self)) {
-			$retried = 1;
-			cleanup($self);
-			goto again;
-		}
-		return;
-	}
-	$head =~ /^[0-9a-f]{40} \S+ ([0-9]+)$/ or
-		fail($self, "Unexpected result from git cat-file: $head");
-
-	my $size = $1 + 0;
-	$$sizeref = $size if $sizeref;
-	my $ret = my_read($self->{in}, $rbuf, $size + 1);
-	$self->{cat_rbuf} = $rbuf if $$rbuf ne '';
-	fail($self, defined($ret) ? 'read EOF' : "read: $!") if !$ret;
-	chop($$ret) eq "\n" or fail($self, 'newline missing after blob');
-	$ret;
+	$$sizeref = $result->[1] if $sizeref;
+	$result->[0];
 }
 
 sub check {
@@ -283,6 +294,7 @@ sub qx {
 # returns true if there are pending "git cat-file" processes
 sub cleanup {
 	my ($self) = @_;
+	local $in_cleanup = 1;
 	if (my $ac = $self->{async_cat}) {
 		$ac->close; # PublicInbox::GitAsyncCat::close -> EPOLL_CTL_DEL
 	}
diff --git a/t/git.t b/t/git.t
index 98d16f289c3..228df90fa45 100644
--- a/t/git.t
+++ b/t/git.t
@@ -86,23 +86,50 @@ if (1) {
 
 if ('alternates reloaded') {
 	my ($alt, $alt_obj) = tmpdir();
-	my @cmd = ('git', "--git-dir=$alt", qw(hash-object -w --stdin));
+	my $hash_obj = [ 'git', "--git-dir=$alt", qw(hash-object -w --stdin) ];
 	PublicInbox::Import::init_bare($alt);
 	open my $fh, '<', "$alt/config" or die "open failed: $!\n";
-	my $rd = popen_rd(\@cmd, {}, { 0 => $fh } );
-	close $fh or die "close failed: $!";
-	chomp(my $remote = <$rd>);
+	chomp(my $remote = xqx($hash_obj, undef, { 0 => $fh }));
 	my $gcf = PublicInbox::Git->new($dir);
 	is($gcf->cat_file($remote), undef, "remote file not found");
 	open $fh, '>>', "$dir/objects/info/alternates" or
 			die "open failed: $!\n";
-	print $fh "$alt/objects" or die "print failed: $!\n";
+	print $fh "$alt/objects\n" or die "print failed: $!\n";
 	close $fh or die "close failed: $!";
 	my $found = $gcf->cat_file($remote);
 	open $fh, '<', "$alt/config" or die "open failed: $!\n";
 	my $config = eval { local $/; <$fh> };
 	is($$found, $config, 'alternates reloaded');
 
+	# with the async interface
+	my ($async_alt, $async_dir_obj) = tmpdir();
+	PublicInbox::Import::init_bare($async_alt);
+	my @exist = map { chomp; [ split / / ] } (xqx(['git', "--git-dir=$dir",
+			qw(cat-file --batch-all-objects --batch-check)]));
+	my $results = [];
+	my $cb = sub {
+		my ($bref, $oid, $type, $size) = @_;
+		push @$results, [ $oid, $type, $size ];
+	};
+	for my $i (0..5) {
+		$gcf->cat_async($exist[$i]->[0], $cb, $results);
+		next if $i != 3;
+
+		# stick a new alternate into a running async pipeline
+		$hash_obj->[1] = "--git-dir=$async_alt";
+		$remote = xqx($hash_obj, undef, { 0 => \'async' });
+		chomp $remote;
+		open $fh, '>>', "$dir/objects/info/alternates" or
+				die "open failed: $!\n";
+		print $fh "$async_alt/objects\n" or die "print failed: $!\n";
+		close $fh or die "close failed: $!";
+		# trigger cat_async_retry:
+		$gcf->cat_async($remote, $cb, $results);
+	}
+	$gcf->cat_async_wait;
+	my $expect = [ @exist[0..3], [ $remote, 'blob', 5 ], @exist[4..5] ];
+	is_deeply($results, $expect, 'got expected results');
+
 	ok(!$gcf->cleanup, 'cleanup can expire');
 	ok(!$gcf->cleanup, 'cleanup idempotent');
 

^ permalink raw reply related	[relevance 7%]

* [PATCH 00/82] public-inbox-imapd: read-only IMAP server
@ 2020-06-10  7:03  5% Eric Wong
  2020-06-10  7:04  7% ` [PATCH 35/82] git: async: automatic retry on alternates change Eric Wong
  0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-06-10  7:03 UTC (permalink / raw)
  To: meta

So I finally wrote my first IMAP server!  And I'm actually
fairly satisfied with how it's turning out to support a bunch
of other performance + scalability work I've wanted to do.

Some previous notes here:
  https://public-inbox.org/meta/20200609113442.GA16856@dcvr/

I finally seem to have gotten it to play nicely with mutt header
caching, so it's fit for public consumption :)

imaps://news.public-inbox.org/INBOX.comp.mail.public-inbox.meta.0

You can use any username+password, and AUTH=ANONYMOUS also
works if your client does that.

It doesn't support UTF-7 (mailbox names) or advertise UTF-8
in CAPABILITIES, yet; I still have RFCs to read :P

And there's a bunch of new things which could use some
testing from non-mutt/mbsync/offlineimap users.
Maybe you'll find some client-side bugs like I did :P

v1 reindexing also gets a little bit of parallelism :)

Anyways, I'll probably be porting some of the scalability
and slow-storage work to older parts of the code before
fiddling with more IMAP extensions.

Eric Wong (82):
  doc: add some IMAP standards
  nntpd: restrict allowed newsgroup names
  preliminary imap server implementation
  inboxidle: new class to detect inbox changes
  imap: support IDLE
  msgmap: split ->max into its own method
  imap: delay InboxIdle start, support refresh
  imap: implement STATUS command
  imap: use Text::ParseWords::parse_line to handle quoted words
  imap: support LIST command
  t/imapd: support FakeInotify and KQNotify
  imap: support fetch for BODYSTRUCTURE and BODY
  eml: each_part: single part $idx is 1
  imap: allow fetch of partial of BODY[...] and headers
  imap: always include `resp-text' in responses
  imap: split out unit tests and benchmarks
  imap: fix multi-message partial header fetches
  imap: simplify partial fetch structure
  imap: support sequence number FETCH
  imap: do not include ".PEEK" in responses
  imap: support the CLOSE command
  imap: speed up HEADER.FIELDS[.NOT] range fetches
  git: async: flatten the inflight array
  git: do our own read buffering for cat-file
  imap: use git-cat-file asynchronously
  git: idle rbuf for async
  imap: support LSUB command
  imap: FETCH: support comma-delimited ranges
  add imapd compression test
  testcommon: tcp_(server|connect): BAIL_OUT on failure
  *deflate: drop invalid comment about rbuf
  imap: fix pipelining with async git
  git: cat_async: provide requested OID + "missing" on missing blobs
  git: move async_cat reference to PublicInbox::Git
  git: async: automatic retry on alternates change
  imapclient: wrapper for Mail::IMAPClient
  xt: add imapd-validate and imapd-mbsync-oimap
  imap: support out-of-bounds ranges
  xt/perf-imap-list: time refresh_inboxlist
  imap: case-insensitive mailbox name comparisons
  imap: break giant inboxes into sub-inboxes of 50K messages
  imap: start introducing iterative config reloading
  imap: require ".$UID_MIN-$UID_END" suffix
  imapd: ensure LIST is sorted alphabetically, for now
  imap: omit $UID_END from mailbox name, use index
  t/config.t: always compare against git bool behavior
  xt/*: show some tunable parameters
  imap: STATUS and LIST are case-insensitive, too
  imap: EXAMINE/STATUS: return correct counts
  imap: avoid uninitialized warnings on incomplete commands
  imap: start parsing out queries for SQLite and Xapian
  imap: SEARCH: clamp results to the 50K UID range
  imap: allow UID range search on timestamps
  over: get_art: use dbh->prepare_cached
  search: index byte size of a message for IMAP search
  search: index UID for IMAP search, too
  imap: remove dummies from sequence number FETCH
  imap: compile UID FETCH to opcodes
  imap: UID FETCH: optimize for smsg-only case
  imap: UID FETCH: optimize (UID FLAGS) harder
  imap: IDLE: avoid extraneous wakeups, keep-alive
  imap: 30 minute auto-logout timer
  imap: split ->logged_in attribute into a separate class
  searchidx: v1 (re)-index uses git asynchronously
  index: account for CRLF conversion when storing bytes
  imap: rely on smsg->{bytes} for RFC822.SIZE
  imap: UID FETCH requires at least one data item
  imap: LIST shows "INBOX" in all caps
  imap: support 8000 octet lines
  imap: reinstate some message sequence number support
  imap: cleanup ->{uid_base} usage
  imap: FETCH: more granular CRLF conversion
  imap: further speed up HEADER.FIELDS FETCH requests
  imap: FETCH: try to make fake MSNs sequentially
  imap: STATUS/EXAMINE: rely on SQLite overview
  imap: UID SEARCH: support multiple ranges
  imap: wire up Xapian search, msn SEARCH and multiple ranges
  imap: misc cleanups and notes
  imapd: don't bother sorting LIST output
  imap: drop non-UID SEARCH for now
  over: uid_range: remove LIMIT
  imap: FETCH: proper MSN => UID mapping for requests

 Documentation/public-inbox-imapd.pod |   91 ++
 Documentation/standards.perl         |   10 +
 MANIFEST                             |   18 +
 lib/PublicInbox/Config.pm            |   18 +
 lib/PublicInbox/Daemon.pm            |   24 +-
 lib/PublicInbox/DummyInbox.pm        |   22 +
 lib/PublicInbox/Eml.pm               |    9 +-
 lib/PublicInbox/FakeInotify.pm       |   59 ++
 lib/PublicInbox/Git.pm               |  163 +--
 lib/PublicInbox/GitAsyncCat.pm       |   51 +
 lib/PublicInbox/IMAP.pm              | 1397 ++++++++++++++++++++++++++
 lib/PublicInbox/IMAPClient.pm        |  119 +++
 lib/PublicInbox/IMAPD.pm             |  114 +++
 lib/PublicInbox/IMAPdeflate.pm       |  126 +++
 lib/PublicInbox/Import.pm            |    2 +-
 lib/PublicInbox/In2Tie.pm            |   17 +
 lib/PublicInbox/Inbox.pm             |   33 +-
 lib/PublicInbox/InboxIdle.pm         |   79 ++
 lib/PublicInbox/KQNotify.pm          |   66 ++
 lib/PublicInbox/Lock.pm              |    7 +
 lib/PublicInbox/MsgIter.pm           |    2 +-
 lib/PublicInbox/Msgmap.pm            |   20 +-
 lib/PublicInbox/NNTPD.pm             |   12 +-
 lib/PublicInbox/NNTPdeflate.pm       |    1 -
 lib/PublicInbox/Over.pm              |   50 +-
 lib/PublicInbox/Search.pm            |   32 +-
 lib/PublicInbox/SearchIdx.pm         |   89 +-
 lib/PublicInbox/SearchIdxShard.pm    |   11 +-
 lib/PublicInbox/Smsg.pm              |    8 +-
 lib/PublicInbox/TestCommon.pm        |    7 +-
 lib/PublicInbox/V2Writable.pm        |   10 +-
 script/public-inbox-imapd            |   14 +
 t/config.t                           |   15 +-
 t/eml.t                              |    2 +-
 t/git.t                              |   40 +-
 t/imap.t                             |  133 +++
 t/imapd-tls.t                        |  204 ++++
 t/imapd.t                            |  398 ++++++++
 t/import.t                           |    5 +-
 t/inbox_idle.t                       |   72 ++
 t/nntpd.t                            |    5 +-
 t/over.t                             |    3 +
 t/search.t                           |   19 +
 xt/cmp-msgstr.t                      |    1 -
 xt/cmp-msgview.t                     |    1 -
 xt/eml_check_limits.t                |    6 +-
 xt/git_async_cmp.t                   |    2 +-
 xt/imapd-mbsync-oimap.t              |  132 +++
 xt/imapd-validate.t                  |  177 ++++
 xt/mem-msgview.t                     |    1 +
 xt/msgtime_cmp.t                     |    1 -
 xt/perf-msgview.t                    |    1 -
 52 files changed, 3718 insertions(+), 181 deletions(-)
 create mode 100644 Documentation/public-inbox-imapd.pod
 create mode 100644 lib/PublicInbox/DummyInbox.pm
 create mode 100644 lib/PublicInbox/FakeInotify.pm
 create mode 100644 lib/PublicInbox/GitAsyncCat.pm
 create mode 100644 lib/PublicInbox/IMAP.pm
 create mode 100644 lib/PublicInbox/IMAPClient.pm
 create mode 100644 lib/PublicInbox/IMAPD.pm
 create mode 100644 lib/PublicInbox/IMAPdeflate.pm
 create mode 100644 lib/PublicInbox/In2Tie.pm
 create mode 100644 lib/PublicInbox/InboxIdle.pm
 create mode 100644 lib/PublicInbox/KQNotify.pm
 create mode 100644 script/public-inbox-imapd
 create mode 100644 t/imap.t
 create mode 100644 t/imapd-tls.t
 create mode 100644 t/imapd.t
 create mode 100644 t/inbox_idle.t
 create mode 100644 xt/imapd-mbsync-oimap.t
 create mode 100644 xt/imapd-validate.t

^ permalink raw reply	[relevance 5%]

Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2020-06-10  7:03  5% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
2020-06-10  7:04  7% ` [PATCH 35/82] git: async: automatic retry on alternates change Eric Wong

Code repositories for project(s) associated with this public inbox

	https://80x24.org/public-inbox.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).