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 75/82] imap: STATUS/EXAMINE: rely on SQLite overview
  2020-06-10  7:03  7% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
@ 2020-06-10  7:05  6% ` Eric Wong
  0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-06-10  7:05 UTC (permalink / raw)
  To: meta

We can get exact values for EXISTS, UIDNEXT using SQLite
rather than calculating off $ibx->mm->max ourselves.

Furthermore, $ibx->mm is less useful than $ibx->over for IMAP
(and for our read-only daemons in general) so do not depend on
$ibx->mm outside of startup/reload to save FDs and reduce kernel
page cache footprint.
---
 lib/PublicInbox/DummyInbox.pm | 11 ++++++-----
 lib/PublicInbox/IMAP.pm       | 30 ++++++++++++++++++------------
 lib/PublicInbox/IMAPD.pm      |  2 +-
 lib/PublicInbox/Over.pm       | 30 ++++++++++++++++++++++++++++++
 t/over.t                      |  3 +++
 5 files changed, 58 insertions(+), 18 deletions(-)

diff --git a/lib/PublicInbox/DummyInbox.pm b/lib/PublicInbox/DummyInbox.pm
index b6c48db1a0e..c3f4f5c6674 100644
--- a/lib/PublicInbox/DummyInbox.pm
+++ b/lib/PublicInbox/DummyInbox.pm
@@ -9,13 +9,14 @@ use strict;
 
 sub created_at { 0 } # Msgmap::created_at
 sub mm { shift }
-sub max { undef } # Msgmap::max
-sub msg_range { [] } # Msgmap::msg_range
+sub uid_range { [] } # Over::uid_range
+sub subscribe_unlock { undef };
 
 no warnings 'once';
-*uid_range = *query_xover = \&msg_range;
+*max = \&created_at;
+*query_xover = \&uid_range;
 *over = \&mm;
-*subscribe_unlock = *unsubscribe_unlock =
-	*get_art = *description = *base_url = \&max;
+*unsubscribe_unlock =
+	*get_art = *description = *base_url = \&subscribe_unlock;
 
 1;
diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index d0683530988..41c8066446c 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -183,7 +183,7 @@ sub cmd_noop ($$) { "$_[1] OK Noop done\r\n" }
 # called by PublicInbox::InboxIdle
 sub on_inbox_unlock {
 	my ($self, $ibx) = @_;
-	my $new = $ibx->mm->max;
+	my $new = $ibx->over->max;
 	my $uid_base = $self->{uid_base} // 0;
 	my $uid_end = $uid_base + UID_BLOCK;
 	defined(my $old = $self->{-idle_max}) or die 'BUG: -idle_max unset';
@@ -223,7 +223,7 @@ sub cmd_idle ($$) {
 	# IDLE seems allowed by dovecot w/o a mailbox selected *shrug*
 	my $ibx = $self->{ibx} or return "$tag BAD no mailbox selected\r\n";
 	$self->{-idle_tag} = $tag;
-	my $max = $ibx->mm->max // 0;
+	my $max = $ibx->over->max;
 	my $uid_end = $self->{uid_base} + UID_BLOCK;
 	my $sock = $self->{sock} or return;
 	my $fd = fileno($sock);
@@ -283,14 +283,20 @@ sub inbox_lookup ($$) {
 		my $mb_top = $1;
 		$uid_base = $2 * UID_BLOCK;
 		$ibx = $self->{imapd}->{mailboxes}->{lc $mailbox} or return;
-		$exists = $ibx->mm->max // 0;
-		ensure_ranges_exist($self->{imapd}, $ibx, $exists);
-		my $uid_end = $uid_base + UID_BLOCK;
-		$exists = $uid_end if $exists > $uid_end;
-		$uidnext = $exists + 1;
-		$exists -= $uid_base;
+		my $max;
+		($exists, $uidnext, $max) = $ibx->over->imap_status($uid_base,
+							$uid_base + UID_BLOCK);
+		ensure_ranges_exist($self->{imapd}, $ibx, $max);
 	} else { # check for dummy inboxes
-		$ibx = $self->{imapd}->{mailboxes}->{lc $mailbox} or return;
+		$mailbox = lc $mailbox;
+		$ibx = $self->{imapd}->{mailboxes}->{$mailbox} or return;
+
+		# if "INBOX.foo.bar" is selected and "INBOX.foo.bar.0",
+		# check for new UID ranges (e.g. "INBOX.foo.bar.1")
+		if (my $z = $self->{imapd}->{mailboxes}->{"$mailbox.0"}) {
+			ensure_ranges_exist($self->{imapd}, $z, $z->over->max);
+		}
+
 		$uid_base = $exists = 0;
 		$uidnext = 1;
 	}
@@ -590,7 +596,7 @@ sub range_step ($$) {
 		($beg, $end) = ($1 + 0, $2 + 0);
 	} elsif ($range =~ /\A([0-9]+):\*\z/) {
 		$beg = $1 + 0;
-		$end = $self->{ibx}->mm->max // 0;
+		$end = $self->{ibx}->over->max;
 		my $uid_end = $self->{uid_base} + UID_BLOCK;
 		$end = $uid_end if $end > $uid_end;
 		$beg = $end if $beg > $end;
@@ -1093,14 +1099,14 @@ sub cmd_uid_search ($$$;) {
 	if (!scalar(keys %$q)) {
 		$self->msg_more('* SEARCH');
 		my $beg = 1;
-		my $end = $ibx->mm->max // 0;
+		my $end = $ibx->over->max;
 		uid_clamp($self, \$beg, \$end);
 		long_response($self, \&uid_search_uid_range,
 				$tag, \$beg, $end, $sql);
 	} elsif (my $uid = $q->{uid}) {
 		if ($uid =~ /\A([0-9]+):([0-9]+|\*)\z/s) {
 			my ($beg, $end) = ($1, $2);
-			$end = $ibx->mm->max if $end eq '*';
+			$end = $ibx->over->max if $end eq '*';
 			uid_clamp($self, \$beg, \$end);
 			$self->msg_more('* SEARCH');
 			long_response($self, \&uid_search_uid_range,
diff --git a/lib/PublicInbox/IMAPD.pm b/lib/PublicInbox/IMAPD.pm
index 186ec7b0062..e4dc90e8d0e 100644
--- a/lib/PublicInbox/IMAPD.pm
+++ b/lib/PublicInbox/IMAPD.pm
@@ -44,7 +44,7 @@ sub imapd_refresh_ibx { # pi_config->each_inbox cb
 	# this case is a 32-bit representation of the creation
 	# date/time of the mailbox"
 	defined($ibx->{uidvalidity} = $mm->created_at) or return;
-	PublicInbox::IMAP::ensure_ranges_exist($imapd, $ibx, $mm->max // 1);
+	PublicInbox::IMAP::ensure_ranges_exist($imapd, $ibx, $mm->max // 0);
 
 	# preload to avoid fragmentation:
 	$ibx->description;
diff --git a/lib/PublicInbox/Over.pm b/lib/PublicInbox/Over.pm
index 1faeff418f4..e0f20ea6d3d 100644
--- a/lib/PublicInbox/Over.pm
+++ b/lib/PublicInbox/Over.pm
@@ -229,4 +229,34 @@ sub uid_range {
 	$dbh->selectcol_arrayref($q, undef, $beg, $end);
 }
 
+sub max {
+	my ($self) = @_;
+	my $sth = $self->connect->prepare_cached(<<'', undef, 1);
+SELECT MAX(num) FROM over WHERE num > 0
+
+	$sth->execute;
+	$sth->fetchrow_array // 0;
+}
+
+sub imap_status {
+	my ($self, $uid_base, $uid_end) = @_;
+	my $dbh = $self->connect;
+	my $sth = $dbh->prepare_cached(<<'', undef, 1);
+SELECT COUNT(num) FROM over WHERE num > ? AND num <= ?
+
+	$sth->execute($uid_base, $uid_end);
+	my $exists = $sth->fetchrow_array;
+
+	$sth = $dbh->prepare_cached(<<'', undef, 1);
+SELECT MAX(num) + 1 FROM over WHERE num <= ?
+
+	$sth->execute($uid_end);
+	my $uidnext = $sth->fetchrow_array;
+
+	$sth = $dbh->prepare_cached(<<'', undef, 1);
+SELECT MAX(num) FROM over WHERE num > 0
+
+	($exists, $uidnext, $sth->fetchrow_array // 0);
+}
+
 1;
diff --git a/t/over.t b/t/over.t
index 5586aa310e6..734fdaa3604 100644
--- a/t/over.t
+++ b/t/over.t
@@ -10,6 +10,8 @@ use_ok 'PublicInbox::OverIdx';
 my ($tmpdir, $for_destroy) = tmpdir();
 my $over = PublicInbox::OverIdx->new("$tmpdir/over.sqlite3");
 $over->connect;
+is($over->max, 0, 'max is zero on new DB (scalar context)');
+is_deeply([$over->max], [0], 'max is zero on new DB (list context)');
 my $x = $over->next_tid;
 is(int($x), $x, 'integer tid');
 my $y = $over->next_tid;
@@ -58,6 +60,7 @@ foreach my $mid (qw(a b)) {
 	my $msgs = [ map { $_->{num} } @{$over->get_thread($mid)} ];
 	is_deeply([98, 99], $msgs, "linked messages by Message-ID: <$mid>");
 }
+isnt($over->max, 0, 'max is non-zero');
 
 $over->rollback_lazy;
 

^ permalink raw reply related	[relevance 6%]

* [PATCH 00/82] public-inbox-imapd: read-only IMAP server
@ 2020-06-10  7:03  7% Eric Wong
  2020-06-10  7:05  6% ` [PATCH 75/82] imap: STATUS/EXAMINE: rely on SQLite overview 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 7%]

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  7% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
2020-06-10  7:05  6% ` [PATCH 75/82] imap: STATUS/EXAMINE: rely on SQLite overview 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).