* [PATCH 58/82] imap: compile UID FETCH to opcodes
2020-06-10 7:03 7% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
@ 2020-06-10 7:04 4% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-06-10 7:04 UTC (permalink / raw)
To: meta
This is just a hair faster and cacheable in the future, if we
need it. Most notably, this avoids doing PublicInbox::Eml->new
for simple "RFC822", "BODY[]", and "RFC822.SIZE" requests.
---
lib/PublicInbox/IMAP.pm | 188 +++++++++++++++++++++++++---------------
t/imap.t | 16 ++++
2 files changed, 134 insertions(+), 70 deletions(-)
diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index 8307343cf15..3fae81112aa 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -40,22 +40,26 @@ 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,
- 'BODY[]' => 1,
- 'RFC822.HEADER' => 1,
- 'RFC822.SIZE' => 1, # needs CRLF conversion :<
- 'RFC822.TEXT' => 1,
- BODY => 1,
- BODYSTRUCTURE => 1,
- ENVELOPE => 1,
- FLAGS => 0,
- INTERNALDATE => 0,
- RFC822 => 1,
- UID => 0,
+# these values area also used for sorting
+sub NEED_BLOB () { 1 }
+sub NEED_EML () { NEED_BLOB|2 }
+my $OP_EML_NEW = [ NEED_EML - 1, \&op_eml_new ];
+
+my %FETCH_NEED = ( # for future optimization
+ 'BODY[HEADER]' => [ NEED_EML, \&emit_rfc822_header ],
+ 'BODY[TEXT]' => [ NEED_EML, \&emit_rfc822_text ],
+ 'BODY[]' => [ NEED_BLOB, \&emit_rfc822 ],
+ 'RFC822.HEADER' => [ NEED_EML, \&emit_rfc822_header ],
+ 'RFC822.TEXT' => [ NEED_EML, \&emit_rfc822_text ],
+ 'RFC822.SIZE' => [ NEED_BLOB, \&emit_rfc822_size ],
+ RFC822 => [ NEED_BLOB, \&emit_rfc822 ],
+ BODY => [ NEED_EML, \&emit_body ],
+ BODYSTRUCTURE => [ NEED_EML, \&emit_bodystructure ],
+ ENVELOPE => [ NEED_EML, \&emit_envelope ],
+ FLAGS => [ 0, \&emit_flags ],
+ INTERNALDATE => [ 0, \&emit_internaldate ],
);
-my %FETCH_ATT = map { $_ => [ $_ ] } keys %FETCH_NEED_BLOB;
+my %FETCH_ATT = map { $_ => [ $_ ] } keys %FETCH_NEED;
# aliases (RFC 3501 section 6.4.5)
$FETCH_ATT{FAST} = [ qw(FLAGS INTERNALDATE RFC822.SIZE) ];
@@ -63,9 +67,10 @@ $FETCH_ATT{ALL} = [ @{$FETCH_ATT{FAST}}, 'ENVELOPE' ];
$FETCH_ATT{FULL} = [ @{$FETCH_ATT{ALL}}, 'BODY' ];
for my $att (keys %FETCH_ATT) {
- my %h = map { $_ => 1 } @{$FETCH_ATT{$att}};
+ my %h = map { $_ => $FETCH_NEED{$_} } @{$FETCH_ATT{$att}};
$FETCH_ATT{$att} = \%h;
}
+undef %FETCH_NEED;
my $valid_range = '[0-9]+|[0-9]+:[0-9]+|[0-9]+:\*';
$valid_range = qr/\A(?:$valid_range)(?:,(?:$valid_range))*\z/;
@@ -417,7 +422,7 @@ sub requeue_once ($) {
sub uid_fetch_cb { # called by git->cat_async via git_async_cat
my ($bref, $oid, $type, $size, $fetch_m_arg) = @_;
- my ($self, undef, $msgs, undef, $want) = @$fetch_m_arg;
+ my ($self, undef, $msgs, undef, $ops, $partial) = @$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
@@ -426,51 +431,72 @@ sub uid_fetch_cb { # called by git->cat_async via git_async_cat
} else {
$smsg->{blob} eq $oid or die "BUG: $smsg->{blob} != $oid";
}
-
$$bref =~ s/(?<!\r)\n/\r\n/sg; # make strict clients happy
# fixup old bug from import (pre-a0c07cba0e5d8b6a)
$$bref =~ s/\A[\r\n]*From [^\r\n]*\r\n//s;
-
$self->msg_more("* $smsg->{num} FETCH (UID $smsg->{num}");
-
- $want->{'RFC822.SIZE'} and
- $self->msg_more(' RFC822.SIZE '.length($$bref));
- $want->{INTERNALDATE} and
- $self->msg_more(' INTERNALDATE "'.$smsg->internaldate.'"');
- $want->{FLAGS} and $self->msg_more(' FLAGS ()');
- for ('RFC822', 'BODY[]') {
- $want->{$_} or next;
- $self->msg_more(" $_ {".length($$bref)."}\r\n");
- $self->msg_more($$bref);
+ my $eml;
+ for (my $i = 0; $i < @$ops;) {
+ my $k = $ops->[$i++];
+ $ops->[$i++]->($self, $k, $smsg, $bref, $eml);
}
+ partial_emit($self, $partial, $eml) if $partial;
+ $self->msg_more(")\r\n");
+ requeue_once($self);
+}
- my $eml = PublicInbox::Eml->new($bref);
+sub emit_rfc822 {
+ my ($self, $k, undef, $bref) = @_;
+ $self->msg_more(" $k {" . length($$bref)."}\r\n");
+ $self->msg_more($$bref);
+}
- $want->{ENVELOPE} and
- $self->msg_more(' ENVELOPE '.eml_envelope($eml));
+# Mail::IMAPClient::message_string cares about this by default
+# (->Ignoresizeerrors attribute)
+sub emit_rfc822_size {
+ my ($self, $k, undef, $bref) = @_;
+ $self->msg_more(' RFC822.SIZE ' . length($$bref));
+}
- for ('RFC822.HEADER', 'BODY[HEADER]') {
- $want->{$_} or next;
- $self->msg_more(" $_ {".length(${$eml->{hdr}})."}\r\n");
- $self->msg_more(${$eml->{hdr}});
- }
- for ('RFC822.TEXT', 'BODY[TEXT]') {
- $want->{$_} or next;
- $self->msg_more(" $_ {".length($$bref)."}\r\n");
- $self->msg_more($$bref);
- }
- $want->{BODYSTRUCTURE} and
- $self->msg_more(' BODYSTRUCTURE '.fetch_body($eml, 1));
- $want->{BODY} and
- $self->msg_more(' BODY '.fetch_body($eml));
- if (my $partial = $want->{-partial}) {
- partial_emit($self, $partial, $eml);
- }
- $self->msg_more(")\r\n");
- requeue_once($self);
+sub emit_internaldate {
+ my ($self, undef, $smsg) = @_;
+ $self->msg_more(' INTERNALDATE "'.$smsg->internaldate.'"');
+}
+
+sub emit_flags { $_[0]->msg_more(' FLAGS ()') }
+
+sub emit_envelope {
+ my ($self, undef, undef, undef, $eml) = @_;
+ $self->msg_more(' ENVELOPE '.eml_envelope($eml));
+}
+
+sub emit_rfc822_header {
+ my ($self, $k, undef, undef, $eml) = @_;
+ $self->msg_more(" $k {".length(${$eml->{hdr}})."}\r\n");
+ $self->msg_more(${$eml->{hdr}});
+}
+
+# n.b. this is sorted to be after any emit_eml_new ops
+sub emit_rfc822_text {
+ my ($self, $k, undef, $bref) = @_;
+ $self->msg_more(" $k {".length($$bref)."}\r\n");
+ $self->msg_more($$bref);
+}
+
+sub emit_bodystructure {
+ my ($self, undef, undef, undef, $eml) = @_;
+ $self->msg_more(' BODYSTRUCTURE '.fetch_body($eml, 1));
+}
+
+sub emit_body {
+ my ($self, undef, undef, undef, $eml) = @_;
+ $self->msg_more(' BODY '.fetch_body($eml));
}
+# set $eml once ($_[4] == $eml, $_[3] == $bref)
+sub op_eml_new { $_[4] = PublicInbox::Eml->new($_[3]) }
+
sub uid_clamp ($$$) {
my ($self, $beg, $end) = @_;
my $uid_min = $self->{uid_min} or return;
@@ -521,7 +547,7 @@ sub refill_range ($$$) {
}
sub uid_fetch_m { # long_response
- my ($self, $tag, $msgs, $range_info, $want) = @_;
+ my ($self, $tag, $msgs, $range_info) = @_; # \@ops, \@partial
while (!@$msgs) { # rare
if (my $end = refill_range($self, $msgs, $range_info)) {
$self->write(\"$tag $end\r\n");
@@ -710,42 +736,64 @@ sub partial_emit ($$$) {
}
}
-sub fetch_common ($$$$) {
- my ($self, $tag, $range_csv, $want) = @_;
- my $ibx = $self->{ibx} or return "$tag BAD No mailbox selected\r\n";
+sub fetch_compile ($) {
+ my ($want) = @_;
if ($want->[0] =~ s/\A\(//s) {
- $want->[-1] =~ s/\)\z//s or return "$tag BAD no rparen\r\n";
+ $want->[-1] =~ s/\)\z//s or return 'BAD no rparen';
}
- my (%partial, %want);
+ my (%partial, %seen, @op);
+ my $need = 0;
while (defined(my $att = shift @$want)) {
$att = uc($att);
+ next if $att eq 'UID'; # always returned
$att =~ s/\ABODY\.PEEK\[/BODY\[/; # we're read-only
my $x = $FETCH_ATT{$att};
if ($x) {
- %want = (%want, %$x);
+ while (my ($k, $fl_cb) = each %$x) {
+ next if $seen{$k}++;
+ $need |= $fl_cb->[0];
+
+ # insert a special op to convert $bref to $eml
+ # the first time we need it
+ if ($need == NEED_EML && !$seen{$need}++) {
+ push @op, $OP_EML_NEW;
+ }
+ # $fl_cb = [ flags, \&emit_foo ]
+ push @op, [ @$fl_cb , $k ];
+ }
} elsif (!partial_prepare(\%partial, $want, $att)) {
- return "$tag BAD param: $att\r\n";
+ return "BAD param: $att";
}
}
+ my @r;
# stabilize partial order for consistency and ease-of-debugging:
if (scalar keys %partial) {
- $want{-partial} = [ map {;
- [ $_, @{$partial{$_}} ]
- } sort keys %partial ];
+ $need = NEED_EML;
+ push @op, $OP_EML_NEW if !$seen{$need}++;
+ $r[2] = [ map { [ $_, @{$partial{$_}} ] } sort keys %partial ];
}
- $range_csv = 'bad' if $range_csv !~ $valid_range;
- my $range_info = range_step($self, \$range_csv);
- return "$tag $range_info\r\n" if !ref($range_info);
- [ $tag, [], $range_info, \%want ];
+
+ $r[0] = $need;
+
+ # r[1] = [ $key1, $cb1, $key2, $cb2, ... ]
+ use sort 'stable'; # makes output more consistent
+ $r[1] = [ map { ($_->[2], $_->[1]) } sort { $a->[0] <=> $b->[0] } @op ];
+ @r;
}
sub cmd_uid_fetch ($$$;@) {
my ($self, $tag, $range_csv, @want) = @_;
- my $args = fetch_common($self, $tag, $range_csv, \@want);
- ref($args) eq 'ARRAY' ?
- long_response($self, \&uid_fetch_m, @$args) :
- $args; # error
+ my $ibx = $self->{ibx} or return "$tag BAD No mailbox selected\r\n";
+ my ($need, $ops, $partial) = fetch_compile(\@want);
+ return "$tag $need\r\n" unless $ops;
+
+ $range_csv = 'bad' if $range_csv !~ $valid_range;
+ my $range_info = range_step($self, \$range_csv);
+ return "$tag $range_info\r\n" if !ref($range_info);
+
+ long_response($self, \&uid_fetch_m,
+ $tag, [], $range_info, $ops, $partial);
}
sub parse_date ($) { # 02-Oct-1993
diff --git a/t/imap.t b/t/imap.t
index 47e86ef42c7..2401237c8a0 100644
--- a/t/imap.t
+++ b/t/imap.t
@@ -107,4 +107,20 @@ EOF
}, 'structure matches expected');
}
+{
+ my $fetch_compile = \&PublicInbox::IMAP::fetch_compile;
+ my ($cb, $ops, $partial) = $fetch_compile->(['BODY[]']);
+ is($partial, undef, 'no partial fetch data');
+ is_deeply($ops,
+ [ 'BODY[]', \&PublicInbox::IMAP::emit_rfc822 ],
+ 'proper key and op compiled for BODY[]');
+
+ ($cb, $ops, $partial) = $fetch_compile->(['BODY', 'BODY[]']);
+ is_deeply($ops, [
+ 'BODY[]', \&PublicInbox::IMAP::emit_rfc822,
+ undef, \&PublicInbox::IMAP::op_eml_new,
+ 'BODY', \&PublicInbox::IMAP::emit_body,
+ ], 'placed op_eml_new before emit_body');
+}
+
done_testing;
^ permalink raw reply related [relevance 4%]
* [PATCH 00/82] public-inbox-imapd: read-only IMAP server
@ 2020-06-10 7:03 7% Eric Wong
2020-06-10 7:04 4% ` [PATCH 58/82] imap: compile UID FETCH to opcodes 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 7:04 4% ` [PATCH 58/82] imap: compile UID FETCH to opcodes 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).