* [PATCH 78/82] imap: misc cleanups and notes
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
Note some of our limitations for potential hackers.
We'll be renaming "UID_BLOCK" to "UID_SLICE", since "block" is
overused term and "slice" isn't used in our codebase. Also,
document how "slice" and "epochs" are similar concepts for
different clients.
---
lib/PublicInbox/IMAP.pm | 38 +++++++++++++++++++++++++-------------
lib/PublicInbox/IMAPD.pm | 2 +-
2 files changed, 26 insertions(+), 14 deletions(-)
diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index 67bc32ab59b..1ba3a3ff1bb 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -7,7 +7,16 @@
# slow storage.
#
# data notes:
-# * NNTP article numbers are UIDs
+#
+# * NNTP article numbers are UIDs, mm->created_at is UIDVALIDITY
+#
+# * public-inboxes are sliced into mailboxes of 50K messages
+# to not overload MUAs: $NEWSGROUP_NAME.$SLICE_INDEX
+# Slices are similar in concept to v2 "epochs". Epochs
+# are for the limitations of git clients, while slices are
+# for the limitations of IMAP clients.
+#
+# * sequence numbers are estimated based on slice
package PublicInbox::IMAP;
use strict;
@@ -37,7 +46,7 @@ die "neither Email::Address::XS nor Mail::Address loaded: $@" if !$Address;
sub LINE_MAX () { 8000 } # RFC 2683 3.2.1.5
# changing this will cause grief for clients which cache
-sub UID_BLOCK () { 50_000 }
+sub UID_SLICE () { 50_000 }
# these values area also used for sorting
sub NEED_SMSG () { 1 }
@@ -187,7 +196,7 @@ sub on_inbox_unlock {
my ($self, $ibx) = @_;
my $new = $ibx->over->max;
my $uid_base = $self->{uid_base} // 0;
- my $uid_end = $uid_base + UID_BLOCK;
+ my $uid_end = $uid_base + UID_SLICE;
defined(my $old = $self->{-idle_max}) or die 'BUG: -idle_max unset';
$new = $uid_end if $new > $uid_end;
if ($new > $old) {
@@ -226,7 +235,7 @@ sub cmd_idle ($$) {
my $ibx = $self->{ibx} or return "$tag BAD no mailbox selected\r\n";
$self->{-idle_tag} = $tag;
my $max = $ibx->over->max;
- my $uid_end = $self->{uid_base} + UID_BLOCK;
+ my $uid_end = $self->{uid_base} + UID_SLICE;
my $sock = $self->{sock} or return;
my $fd = fileno($sock);
# only do inotify on most recent slice
@@ -260,12 +269,12 @@ sub cmd_done ($$) {
"$idle_tag OK Idle done\r\n";
}
-sub ensure_ranges_exist ($$$) {
+sub ensure_slices_exist ($$$) {
my ($imapd, $ibx, $max) = @_;
defined(my $mb_top = $ibx->{newsgroup}) or return;
my $mailboxes = $imapd->{mailboxes};
my @created;
- for (my $i = int($max/UID_BLOCK); $i >= 0; --$i) {
+ for (my $i = int($max/UID_SLICE); $i >= 0; --$i) {
my $sub_mailbox = "$mb_top.$i";
last if exists $mailboxes->{$sub_mailbox};
$mailboxes->{$sub_mailbox} = $ibx;
@@ -281,14 +290,14 @@ sub inbox_lookup ($$) {
my ($self, $mailbox) = @_;
my ($ibx, $exists, $uidnext, $uid_base);
if ($mailbox =~ /\A(.+)\.([0-9]+)\z/) {
- # old mail: inbox.comp.foo.$uid_block_idx
+ # old mail: inbox.comp.foo.$SLICE_IDX
my $mb_top = $1;
- $uid_base = $2 * UID_BLOCK;
+ $uid_base = $2 * UID_SLICE;
$ibx = $self->{imapd}->{mailboxes}->{lc $mailbox} or return;
my $max;
($exists, $uidnext, $max) = $ibx->over->imap_status($uid_base,
- $uid_base + UID_BLOCK);
- ensure_ranges_exist($self->{imapd}, $ibx, $max);
+ $uid_base + UID_SLICE);
+ ensure_slices_exist($self->{imapd}, $ibx, $max);
} else { # check for dummy inboxes
$mailbox = lc $mailbox;
$ibx = $self->{imapd}->{mailboxes}->{$mailbox} or return;
@@ -296,7 +305,7 @@ sub inbox_lookup ($$) {
# 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, $z->over->max);
+ ensure_slices_exist($self->{imapd}, $z, $z->over->max);
}
$uid_base = $exists = 0;
@@ -580,7 +589,7 @@ sub op_crlf_bdy { ${$_[4]->{bdy}} =~ s/(?<!\r)\n/\r\n/sg if $_[4]->{bdy} }
sub uid_clamp ($$$) {
my ($self, $beg, $end) = @_;
my $uid_min = $self->{uid_base} + 1;
- my $uid_end = $uid_min + UID_BLOCK - 1;
+ my $uid_end = $uid_min + UID_SLICE - 1;
$$beg = $uid_min if $$beg < $uid_min;
$$end = $uid_end if $$end > $uid_end;
}
@@ -595,7 +604,7 @@ sub range_step ($$) {
$$range_csv = undef;
}
my $uid_base = $self->{uid_base};
- my $uid_end = $uid_base + UID_BLOCK;
+ my $uid_end = $uid_base + UID_SLICE;
if ($range =~ /\A([0-9]+):([0-9]+)\z/) {
($beg, $end) = ($1 + 0, $2 + 0);
uid_clamp($self, \$beg, \$end);
@@ -1206,6 +1215,9 @@ sub args_ok ($$) { # duplicated from PublicInbox::NNTP
# returns 1 if we can continue, 0 if not due to buffered writes or disconnect
sub process_line ($$) {
my ($self, $l) = @_;
+
+ # TODO: IMAP allows literals for big requests to upload messages
+ # (which we don't support) but maybe some big search queries use it.
my ($tag, $req, @args) = parse_line('[ \t]+', 0, $l);
pop(@args) if (@args && !defined($args[-1]));
if (@args && uc($req) eq 'UID') {
diff --git a/lib/PublicInbox/IMAPD.pm b/lib/PublicInbox/IMAPD.pm
index e4dc90e8d0e..fe50de0f7cd 100644
--- a/lib/PublicInbox/IMAPD.pm
+++ b/lib/PublicInbox/IMAPD.pm
@@ -44,7 +44,7 @@ sub imapd_refresh_ibx { # pi_config->each_inbox cb
# this case is a 32-bit representation of the creation
# date/time of the mailbox"
defined($ibx->{uidvalidity} = $mm->created_at) or return;
- PublicInbox::IMAP::ensure_ranges_exist($imapd, $ibx, $mm->max // 0);
+ PublicInbox::IMAP::ensure_slices_exist($imapd, $ibx, $mm->max // 0);
# preload to avoid fragmentation:
$ibx->description;
^ 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 78/82] imap: misc cleanups and notes 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 78/82] imap: misc cleanups and notes 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).