* [PATCH 72/82] imap: FETCH: more granular CRLF conversion
2020-06-10 7:03 7% [PATCH 00/82] public-inbox-imapd: read-only IMAP server Eric Wong
@ 2020-06-10 7:05 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-06-10 7:05 UTC (permalink / raw)
To: meta
This speeds up requests from mutt for HEADER.FIELDS by around 10%
since we don't waste time doing CRLF conversion on large message
bodies that get discarded, anyways.
---
lib/PublicInbox/IMAP.pm | 80 ++++++++++++++++++++++++++---------------
t/imap.t | 29 +++++++++------
2 files changed, 70 insertions(+), 39 deletions(-)
diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index e9fa338b5fe..3cc68e66872 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -40,20 +40,27 @@ sub UID_BLOCK () { 50_000 }
# these values area also used for sorting
sub NEED_SMSG () { 1 }
sub NEED_BLOB () { NEED_SMSG|2 }
-sub NEED_EML () { NEED_BLOB|4 }
-my $OP_EML_NEW = [ NEED_EML - 1, \&op_eml_new ];
+sub CRLF_BREF () { 4 }
+sub EML_HDR () { 8 }
+sub CRLF_HDR () { 16 }
+sub EML_BDY () { 32 }
+sub CRLF_BDY () { 64 }
+my $OP_EML_NEW = [ EML_HDR - 1, \&op_eml_new ];
+my $OP_CRLF_BREF = [ CRLF_BREF, \&op_crlf_bref ];
+my $OP_CRLF_HDR = [ CRLF_HDR, \&op_crlf_hdr ];
+my $OP_CRLF_BDY = [ CRLF_BDY, \&op_crlf_bdy ];
my %FETCH_NEED = (
- '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 ],
+ 'BODY[HEADER]' => [ NEED_BLOB|EML_HDR|CRLF_HDR, \&emit_rfc822_header ],
+ 'BODY[TEXT]' => [ NEED_BLOB|EML_BDY|CRLF_BDY, \&emit_rfc822_text ],
+ 'BODY[]' => [ NEED_BLOB|CRLF_BREF, \&emit_rfc822 ],
+ 'RFC822.HEADER' => [ NEED_BLOB|EML_HDR|CRLF_HDR, \&emit_rfc822_header ],
+ 'RFC822.TEXT' => [ NEED_BLOB|EML_BDY|CRLF_BDY, \&emit_rfc822_text ],
'RFC822.SIZE' => [ NEED_SMSG, \&emit_rfc822_size ],
- RFC822 => [ NEED_BLOB, \&emit_rfc822 ],
- BODY => [ NEED_EML, \&emit_body ],
- BODYSTRUCTURE => [ NEED_EML, \&emit_bodystructure ],
- ENVELOPE => [ NEED_EML, \&emit_envelope ],
+ RFC822 => [ NEED_BLOB|CRLF_BREF, \&emit_rfc822 ],
+ BODY => [ NEED_BLOB|EML_HDR|EML_BDY, \&emit_body ],
+ BODYSTRUCTURE => [ NEED_BLOB|EML_HDR|EML_BDY, \&emit_bodystructure ],
+ ENVELOPE => [ NEED_BLOB|EML_HDR, \&emit_envelope ],
FLAGS => [ 0, \&emit_flags ],
INTERNALDATE => [ NEED_SMSG, \&emit_internaldate ],
);
@@ -494,10 +501,6 @@ sub fetch_blob_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;
fetch_run_ops($self, $self->{uid_base}, $smsg, $bref, $ops, $partial);
requeue_once($self);
}
@@ -554,6 +557,18 @@ sub emit_body {
# set $eml once ($_[4] == $eml, $_[3] == $bref)
sub op_eml_new { $_[4] = PublicInbox::Eml->new($_[3]) }
+# s/From / fixes old bug from import (pre-a0c07cba0e5d8b6a)
+sub to_crlf_full {
+ ${$_[0]} =~ s/(?<!\r)\n/\r\n/sg;
+ ${$_[0]} =~ s/\A[\r\n]*From [^\r\n]*\r\n//s;
+}
+
+sub op_crlf_bref { to_crlf_full($_[3]) }
+
+sub op_crlf_hdr { to_crlf_full($_[4]->{hdr}) }
+
+sub op_crlf_bdy { ${$_[4]->{bdy}} =~ s/(?<!\r)\n/\r\n/sg if $_[4]->{bdy} }
+
sub uid_clamp ($$$) {
my ($self, $beg, $end) = @_;
my $uid_min = $self->{uid_base} + 1;
@@ -790,8 +805,8 @@ sub partial_hdr_get {
join('', ($str =~ m/($hdrs_re)/g), "\r\n");
}
-sub partial_prepare ($$$) {
- my ($partial, $want, $att) = @_;
+sub partial_prepare ($$$$) {
+ my ($need, $partial, $want, $att) = @_;
# recombine [ "BODY[1.HEADER.FIELDS", "(foo", "bar)]" ]
# back to: "BODY[1.HEADER.FIELDS (foo bar)]"
@@ -804,6 +819,7 @@ sub partial_prepare ($$$) {
(?:\.(HEADER|MIME|TEXT))? # 2 - section_name
\](?:<([0-9]+)(?:\.([0-9]+))?>)?\z/sx) { # 3, 4
$partial->{$att} = [ \&partial_body, $1, $2, $3, $4 ];
+ $$need |= CRLF_BREF|EML_HDR|EML_BDY;
} elsif ($att =~ /\ABODY\[(?:([0-9]+(?:\.[0-9]+)*)\.)? # 1 - section_idx
(?:HEADER\.FIELDS(\.NOT)?)\x20 # 2
\(([A-Z0-9\-\x20]+)\) # 3 - hdrs
@@ -812,6 +828,7 @@ sub partial_prepare ($$$) {
: \&partial_hdr_get,
$1, undef, $4, $5 ];
$tmp->[2] = hdrs_regexp($3);
+ $$need |= CRLF_HDR|EML_HDR;
} else {
undef;
}
@@ -857,16 +874,9 @@ sub fetch_compile ($) {
while (my ($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 , $k ];
+ push @op, [ @$fl_cb, $k ];
}
- } elsif (!partial_prepare(\%partial, $want, $att)) {
+ } elsif (!partial_prepare(\$need, \%partial, $want, $att)) {
return "BAD param: $att";
}
}
@@ -874,11 +884,25 @@ sub fetch_compile ($) {
# stabilize partial order for consistency and ease-of-debugging:
if (scalar keys %partial) {
- $need = NEED_EML;
- push @op, $OP_EML_NEW if !$seen{$need}++;
+ $need |= NEED_BLOB;
$r[2] = [ map { [ $_, @{$partial{$_}} ] } sort keys %partial ];
}
+ push @op, $OP_EML_NEW if ($need & (EML_HDR|EML_BDY));
+
+ # do we need CRLF conversion?
+ if ($need & CRLF_BREF) {
+ push @op, $OP_CRLF_BREF;
+ } elsif (my $crlf = ($need & (CRLF_HDR|CRLF_BDY))) {
+ if ($crlf == (CRLF_HDR|CRLF_BDY)) {
+ push @op, $OP_CRLF_BREF;
+ } elsif ($need & CRLF_HDR) {
+ push @op, $OP_CRLF_HDR;
+ } else {
+ push @op, $OP_CRLF_BDY;
+ }
+ }
+
$r[0] = $need & NEED_BLOB ? \&fetch_blob :
($need & NEED_SMSG ? \&fetch_smsg : \&fetch_uid);
diff --git a/t/imap.t b/t/imap.t
index 2401237c8a0..81b3d844e76 100644
--- a/t/imap.t
+++ b/t/imap.t
@@ -70,21 +70,26 @@ EOF
{
my $partial_prepare = \&PublicInbox::IMAP::partial_prepare;
my $x = {};
- my $r = $partial_prepare->($x, [], my $p = 'BODY[9]');
+ my $n = 0;
+ my $r = $partial_prepare->(\$n, $x, [], my $p = 'BODY[9]');
ok($r, $p);
- $r = $partial_prepare->($x, [], $p = 'BODY[9]<5>');
+ $r = $partial_prepare->(\$n, $x, [], $p = 'BODY[9]<5>');
ok($r, $p);
- $r = $partial_prepare->($x, [], $p = 'BODY[9]<5.1>');
+ $r = $partial_prepare->(\$n, $x, [], $p = 'BODY[9]<5.1>');
ok($r, $p);
- $r = $partial_prepare->($x, [], $p = 'BODY[1.1]');
+ $r = $partial_prepare->(\$n, $x, [], $p = 'BODY[1.1]');
ok($r, $p);
- $r = $partial_prepare->($x, [], $p = 'BODY[HEADER.FIELDS (DATE FROM)]');
+ $r = $partial_prepare->(\$n, $x, [],
+ $p = 'BODY[HEADER.FIELDS (DATE FROM)]');
ok($r, $p);
- $r = $partial_prepare->($x, [], $p = 'BODY[HEADER.FIELDS.NOT (TO)]');
+ $r = $partial_prepare->(\$n, $x, [],
+ $p = 'BODY[HEADER.FIELDS.NOT (TO)]');
ok($r, $p);
- $r = $partial_prepare->($x, [], $p = 'BODY[HEDDER.FIELDS.NOT (TO)]');
+ $r = $partial_prepare->(\$n, $x, [],
+ $p = 'BODY[HEDDER.FIELDS.NOT (TO)]');
ok(!$r, "rejected misspelling $p");
- $r = $partial_prepare->($x, [], $p = 'BODY[1.1.HEADER.FIELDS (TO)]');
+ $r = $partial_prepare->(\$n, $x, [],
+ $p = 'BODY[1.1.HEADER.FIELDS (TO)]');
ok($r, $p);
my $partial_body = \&PublicInbox::IMAP::partial_body;
my $partial_hdr_get = \&PublicInbox::IMAP::partial_hdr_get;
@@ -111,12 +116,14 @@ EOF
my $fetch_compile = \&PublicInbox::IMAP::fetch_compile;
my ($cb, $ops, $partial) = $fetch_compile->(['BODY[]']);
is($partial, undef, 'no partial fetch data');
- is_deeply($ops,
- [ 'BODY[]', \&PublicInbox::IMAP::emit_rfc822 ],
- 'proper key and op compiled for BODY[]');
+ is_deeply($ops, [
+ undef, \&PublicInbox::IMAP::op_crlf_bref,
+ 'BODY[]', \&PublicInbox::IMAP::emit_rfc822
+ ], 'proper key and op compiled for BODY[]');
($cb, $ops, $partial) = $fetch_compile->(['BODY', 'BODY[]']);
is_deeply($ops, [
+ undef, \&PublicInbox::IMAP::op_crlf_bref,
'BODY[]', \&PublicInbox::IMAP::emit_rfc822,
undef, \&PublicInbox::IMAP::op_eml_new,
'BODY', \&PublicInbox::IMAP::emit_body,
^ permalink raw reply related [relevance 5%]
* [PATCH 00/82] public-inbox-imapd: read-only IMAP server
@ 2020-06-10 7:03 7% Eric Wong
2020-06-10 7:05 5% ` [PATCH 72/82] imap: FETCH: more granular CRLF conversion 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 5% ` [PATCH 72/82] imap: FETCH: more granular CRLF conversion 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).