* [PATCH 41/82] imap: break giant inboxes into sub-inboxes of 50K messages
2020-06-10 7:03 6% [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 limit on mailbox size should keep users of tools like
mbsync (isync) and offlineimap happy, since typical filesystems
struggle with giant Maildirs.
I chose 50K since it's a bit more than what LKML typically sees
in a month and still manages to give acceptable performance on
my ancient Centrino laptop.
There were also no responses to my original proposal at:
<https://public-inbox.org/meta/20200519090000.GA24273@dcvr/>
so no objections, either :>
---
lib/PublicInbox/IMAP.pm | 134 ++++++++++++++++++++++++++++++----------
1 file changed, 100 insertions(+), 34 deletions(-)
diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index ffa76bb0266..959dcfbe328 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -16,7 +16,7 @@ package PublicInbox::IMAP;
use strict;
use base qw(PublicInbox::DS);
use fields qw(imapd logged_in ibx long_cb -login_tag
- -idle_tag -idle_max);
+ uid_min -idle_tag -idle_max);
use PublicInbox::Eml;
use PublicInbox::EmlContentFoo qw(parse_content_disposition);
use PublicInbox::DS qw(now);
@@ -34,6 +34,9 @@ die "neither Email::Address::XS nor Mail::Address loaded: $@" if !$Address;
sub LINE_MAX () { 512 } # does RFC 3501 have a limit like RFC 977?
+# changing this will cause grief for clients which cache
+sub UID_BLOCK () { 50_000 }
+
my %FETCH_NEED_BLOB = ( # for future optimization
'BODY[HEADER]' => 1,
'BODY[TEXT]' => 1,
@@ -128,6 +131,7 @@ sub cmd_login ($$$$) {
sub cmd_close ($$) {
my ($self, $tag) = @_;
+ delete $self->{uid_min};
delete $self->{ibx} ? "$tag OK Close done\r\n"
: "$tag BAD No mailbox\r\n";
}
@@ -188,12 +192,67 @@ sub cmd_done ($$) {
"$idle_tag OK Idle done\r\n";
}
+sub ensure_old_ranges_exist ($$$) {
+ my ($self, $ibx, $uid_min) = @_;
+ my $groups = $self->{imapd}->{groups};
+ my $mailbox = $ibx->{newsgroup};
+ my @created;
+ $uid_min -= UID_BLOCK;
+ my $uid_end = $uid_min + UID_BLOCK - 1;
+ while ($uid_min > 0) {
+ my $sub_mailbox = "$mailbox.$uid_min-$uid_end";
+ last if exists $groups->{$sub_mailbox};
+ $groups->{$sub_mailbox} = $ibx;
+ $uid_end -= UID_BLOCK;
+ $uid_min -= UID_BLOCK;
+ push @created, $sub_mailbox;
+ }
+ return unless @created;
+ my $l = $self->{imapd}->{inboxlist};
+ grep {
+ / \Q$mailbox\E\r\n\z/ and s/\(\\HasNoChildren/\(\\HasChildren/;
+ } @$l;
+ push @$l, map { qq[* LIST (\\HasNoChildren) "." $_\r\n] } @created;
+}
+
sub cmd_examine ($$$) {
my ($self, $tag, $mailbox) = @_;
- my $ibx = $self->{imapd}->{groups}->{$mailbox} or
- return "$tag NO Mailbox doesn't exist: $mailbox\r\n";
- my $mm = $ibx->mm;
- my $max = $mm->max // 0;
+ my ($ibx, $mm, $max);
+
+ if ($mailbox =~ /\A(.+)\.([0-9]+)-([0-9]+)\z/) {
+ # old mail: inbox.comp.foo.$uid_min-$uid_end
+ my ($mb_top, $uid_min, $uid_end) = ($1, $2 + 0, $3 + 0);
+ $ibx = $self->{imapd}->{groups}->{lc $mb_top};
+ if (!$ibx || ($uid_end % UID_BLOCK) != 0 ||
+ ($uid_min + UID_BLOCK - 1) != $uid_end) {
+ return "$tag NO Mailbox doesn't exist: $mailbox\r\n";
+ }
+ $mm = $ibx->mm;
+ $max = $mm->max // 0;
+
+ # don't let users create inboxes w/ not-yet-possible range:
+ $uid_min > $max and
+ return "$tag NO Mailbox doesn't exist: $mailbox\r\n";
+
+ $max = $uid_min + UID_BLOCK + 1;
+ $self->{uid_min} = $uid_min;
+ ensure_old_ranges_exist($self, $ibx, $uid_min);
+ } else { # current mailbox (most recent UID_BLOCK messages)
+ $ibx = $self->{imapd}->{groups}->{lc $mailbox} or
+ return "$tag NO Mailbox doesn't exist: $mailbox\r\n";
+
+ $mm = $ibx->mm;
+ $max = $mm->max // 0;
+
+ my $uid_min = UID_BLOCK * int($max/UID_BLOCK) + 1;
+ if ($uid_min == 1) { # normal inbox with <UID_BLOCK messages
+ delete $self->{uid_min}; # implicit cmd_close
+ } else { # we have a giant inbox:
+ $self->{uid_min} = $uid_min;
+ ensure_old_ranges_exist($self, $ibx, $uid_min);
+ }
+ }
+
# RFC 3501 2.3.1.1 - "A good UIDVALIDITY value to use in
# this case is a 32-bit representation of the creation
# date/time of the mailbox"
@@ -208,11 +267,11 @@ sub cmd_examine ($$$) {
* $max RECENT\r
* FLAGS (\\Seen)\r
* OK [PERMANENTFLAGS ()] Read-only mailbox\r
+* OK [UNSEEN $max]\r
+* OK [UIDNEXT $uidnext]\r
+* OK [UIDVALIDITY $uidvalidity]\r
+$tag OK [READ-ONLY] EXAMINE/SELECT done\r
EOF
- $ret .= "* OK [UNSEEN $max]\r\n" if $max;
- $ret .= "* OK [UIDNEXT $uidnext]\r\n" if defined $uidnext;
- $ret .= "* OK [UIDVALIDITY $uidvalidity]\r\n" if defined $uidvalidity;
- $ret .= "$tag OK [READ-ONLY] EXAMINE/SELECT done\r\n";
}
sub _esc ($) {
@@ -357,12 +416,12 @@ sub fetch_body ($;$) {
}
sub dummy_message ($$) {
- my ($seqno, $ibx) = @_;
+ my ($self, $seqno) = @_;
my $ret = <<EOF;
From: nobody\@localhost\r
To: nobody\@localhost\r
Date: Thu, 01 Jan 1970 00:00:00 +0000\r
-Message-ID: <dummy-$seqno\@$ibx->{newsgroup}>\r
+Message-ID: <dummy-$seqno\@$self->{ibx}->{newsgroup}>\r
Subject: dummy message #$seqno\r
\r
You're seeing this message because your IMAP client didn't use UIDs.\r
@@ -390,13 +449,13 @@ sub requeue_once ($) {
sub uid_fetch_cb { # called by git->cat_async via git_async_cat
my ($bref, $oid, $type, $size, $fetch_m_arg) = @_;
- my ($self, undef, $ibx, $msgs, undef, $want) = @$fetch_m_arg;
+ my ($self, undef, $msgs, undef, $want) = @$fetch_m_arg;
my $smsg = shift @$msgs or die 'BUG: no smsg';
if (!defined($oid)) {
# it's possible to have TOCTOU if an admin runs
# public-inbox-(edit|purge), just move onto the next message
return requeue_once($self) unless defined $want->{-seqno};
- $bref = dummy_message($smsg->{num}, $ibx);
+ $bref = dummy_message($self, $smsg->{num});
} else {
$smsg->{blob} eq $oid or die "BUG: $smsg->{blob} != $oid";
}
@@ -446,7 +505,7 @@ sub uid_fetch_cb { # called by git->cat_async via git_async_cat
}
sub range_step ($$) {
- my ($ibx, $range_csv) = @_;
+ my ($self, $range_csv) = @_;
my ($beg, $end, $range);
if ($$range_csv =~ s/\A([^,]+),//) {
$range = $1;
@@ -458,39 +517,46 @@ sub range_step ($$) {
($beg, $end) = ($1 + 0, $2 + 0);
} elsif ($range =~ /\A([0-9]+):\*\z/) {
$beg = $1 + 0;
- $end = $ibx->mm->max // 0;
+ $end = $self->{ibx}->mm->max // 0;
$beg = $end if $beg > $end;
} elsif ($range =~ /\A[0-9]+\z/) {
$beg = $end = $range + 0;
+ undef $range;
} else {
return 'BAD fetch range';
}
+ if (defined($range) && (my $uid_min = $self->{uid_min})) {
+ my $uid_end = $uid_min + UID_BLOCK - 1;
+ $beg = $uid_min if $beg < $uid_min;
+ $end = $uid_end if $end > $uid_end;
+ }
[ $beg, $end, $$range_csv ];
}
sub refill_range ($$$) {
- my ($ibx, $msgs, $range_info) = @_;
+ my ($self, $msgs, $range_info) = @_;
my ($beg, $end, $range_csv) = @$range_info;
- if (scalar(@$msgs = @{$ibx->over->query_xover($beg, $end)})) {
+ if (scalar(@$msgs = @{$self->{ibx}->over->query_xover($beg, $end)})) {
$range_info->[0] = $msgs->[-1]->{num} + 1;
return;
}
return 'OK Fetch done' if !$range_csv;
- my $next_range = range_step($ibx, \$range_csv);
+ my $next_range = range_step($self, \$range_csv);
return $next_range if !ref($next_range); # error
@$range_info = @$next_range;
undef; # keep looping
}
sub uid_fetch_m { # long_response
- my ($self, $tag, $ibx, $msgs, $range_info, $want) = @_;
+ my ($self, $tag, $msgs, $range_info, $want) = @_;
while (!@$msgs) { # rare
- if (my $end = refill_range($ibx, $msgs, $range_info)) {
+ if (my $end = refill_range($self, $msgs, $range_info)) {
$self->write(\"$tag $end\r\n");
return;
}
}
- git_async_cat($ibx->git, $msgs->[0]->{blob}, \&uid_fetch_cb, \@_);
+ git_async_cat($self->{ibx}->git, $msgs->[0]->{blob},
+ \&uid_fetch_cb, \@_);
}
sub cmd_status ($$$;@) {
@@ -698,9 +764,9 @@ sub fetch_common ($$$$) {
} sort keys %partial ];
}
$range_csv = 'bad' if $range_csv !~ $valid_range;
- my $range_info = range_step($ibx, \$range_csv);
+ my $range_info = range_step($self, \$range_csv);
return "$tag $range_info\r\n" if !ref($range_info);
- [ $tag, $ibx, [], $range_info, \%want ];
+ [ $tag, [], $range_info, \%want ];
}
sub cmd_uid_fetch ($$$;@) {
@@ -712,9 +778,9 @@ sub cmd_uid_fetch ($$$;@) {
}
sub seq_fetch_m { # long_response
- my ($self, $tag, $ibx, $msgs, $range_info, $want) = @_;
+ my ($self, $tag, $msgs, $range_info, $want) = @_;
while (!@$msgs) { # rare
- if (my $end = refill_range($ibx, $msgs, $range_info)) {
+ if (my $end = refill_range($self, $msgs, $range_info)) {
$self->write(\"$tag $end\r\n");
return;
}
@@ -722,13 +788,13 @@ sub seq_fetch_m { # long_response
my $seq = $want->{-seqno}++;
my $cur_num = $msgs->[0]->{num};
if ($cur_num == $seq) { # as expected
- git_async_cat($ibx->git, $msgs->[0]->{blob},
+ git_async_cat($self->{ibx}->git, $msgs->[0]->{blob},
\&uid_fetch_cb, \@_);
} elsif ($cur_num > $seq) {
# send dummy messages until $seq catches up to $cur_num
my $smsg = bless { num => $seq, ts => 0 }, 'PublicInbox::Smsg';
unshift @$msgs, $smsg;
- my $bref = dummy_message($seq, $ibx);
+ my $bref = dummy_message($self, $seq);
uid_fetch_cb($bref, undef, undef, undef, \@_);
$smsg; # blessed response since uid_fetch_cb requeues
} else { # should not happen
@@ -741,14 +807,14 @@ sub cmd_fetch ($$$;@) {
my $args = fetch_common($self, $tag, $range_csv, \@want);
ref($args) eq 'ARRAY' ? do {
my $want = $args->[-1];
- $want->{-seqno} = $args->[3]->[0]; # $beg == $range_info->[0];
+ $want->{-seqno} = $args->[2]->[0]; # $beg == $range_info->[0];
long_response($self, \&seq_fetch_m, @$args)
} : $args; # error
}
sub uid_search_all { # long_response
- my ($self, $tag, $ibx, $num) = @_;
- my $uids = $ibx->mm->ids_after($num);
+ my ($self, $tag, $num) = @_;
+ my $uids = $self->{ibx}->mm->ids_after($num);
if (scalar(@$uids)) {
$self->msg_more(join(' ', '', @$uids));
} else {
@@ -758,8 +824,8 @@ sub uid_search_all { # long_response
}
sub uid_search_uid_range { # long_response
- my ($self, $tag, $ibx, $beg, $end) = @_;
- my $uids = $ibx->mm->msg_range($beg, $end, 'num');
+ my ($self, $tag, $beg, $end) = @_;
+ my $uids = $self->{ibx}->mm->msg_range($beg, $end, 'num');
if (@$uids) {
$self->msg_more(join('', map { " $_->[0]" } @$uids));
} else {
@@ -775,14 +841,14 @@ sub cmd_uid_search ($$$;) {
if ($arg eq 'ALL' && !@rest) {
$self->msg_more('* SEARCH');
my $num = 0;
- long_response($self, \&uid_search_all, $tag, $ibx, \$num);
+ long_response($self, \&uid_search_all, $tag, \$num);
} elsif ($arg eq 'UID' && scalar(@rest) == 1) {
if ($rest[0] =~ /\A([0-9]+):([0-9]+|\*)\z/s) {
my ($beg, $end) = ($1, $2);
$end = $ibx->mm->max if $end eq '*';
$self->msg_more('* SEARCH');
long_response($self, \&uid_search_uid_range,
- $tag, $ibx, \$beg, $end);
+ $tag, \$beg, $end);
} elsif ($rest[0] =~ /\A[0-9]+\z/s) {
my $uid = $rest[0];
$uid = $ibx->over->get_art($uid) ? " $uid" : '';
^ permalink raw reply related [relevance 7%]
* [PATCH 00/82] public-inbox-imapd: read-only IMAP server
@ 2020-06-10 7:03 6% Eric Wong
2020-06-10 7:04 7% ` [PATCH 41/82] imap: break giant inboxes into sub-inboxes of 50K messages 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 6%]
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 6% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
2020-06-10 7:04 7% ` [PATCH 41/82] imap: break giant inboxes into sub-inboxes of 50K messages 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).