user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 14/34] watch: support IMAP polling
Date: Sat, 27 Jun 2020 10:03:40 +0000	[thread overview]
Message-ID: <20200627100400.9871-15-e@yhbt.net> (raw)
In-Reply-To: <20200627100400.9871-1-e@yhbt.net>

Not all IMAP servers support IDLE, and IDLE may be prohibitively
expensive for some IMAP servers with many inboxes.  So allow
configuring a imap.$IMAP_URL.pollInterval=SECONDS to poll
mailboxes.

We'll also need to poll for NNTP servers in the future.
---
 lib/PublicInbox/WatchMaildir.pm | 64 ++++++++++++++++++++++++++++++---
 t/imapd.t                       | 39 ++++++++++++++++++--
 2 files changed, 95 insertions(+), 8 deletions(-)

diff --git a/lib/PublicInbox/WatchMaildir.pm b/lib/PublicInbox/WatchMaildir.pm
index 431350be277..ac980d9b0f1 100644
--- a/lib/PublicInbox/WatchMaildir.pm
+++ b/lib/PublicInbox/WatchMaildir.pm
@@ -202,8 +202,9 @@ sub quit {
 	if (my $imap_pid = $self->{-imap_pid}) {
 		kill('QUIT', $imap_pid);
 	}
-	if (my $idle_pids = $self->{idle_pids}) {
-		kill('QUIT', $_) for (keys %$idle_pids);
+	for (qw(idle_pids poll_pids)) {
+		my $pids = $self->{$_} or next;
+		kill('QUIT', $_) for (keys %$pids);
 	}
 	if (my $idle_mic = $self->{idle_mic}) {
 		eval { $idle_mic->done };
@@ -237,12 +238,12 @@ sub imap_section ($) {
 sub cfg_intvl ($$) {
 	my ($cfg, $key) = @_;
 	defined(my $v = $cfg->{lc($key)}) or return;
-	$v =~ /\A[0-9]+\z/s and return $v + 0;
+	$v =~ /\A[0-9]+(?:\.[0-9]+)?\z/s and return $v + 0;
 	if (ref($v) eq 'ARRAY') {
 		$v = join(', ', @$v);
 		warn "W: $key has multiple values: $v\nW: $key ignored\n";
 	} else {
-		warn "W: $key=$v is not an integer value in seconds\n";
+		warn "W: $key=$v is not a numeric value in seconds\n";
 	}
 }
 
@@ -460,6 +461,7 @@ sub watch_imap_idle_1 ($$$) {
 sub watch_atfork_child ($) {
 	my ($self) = @_;
 	delete $self->{idle_pids};
+	delete $self->{poll_pids};
 	PublicInbox::DS->Reset;
 	PublicInbox::Sigfd::sig_setmask($self->{oldset});
 	%SIG = (%SIG, %{$self->{sig}});
@@ -504,6 +506,52 @@ sub event_step {
 	goto(&fs_scan_step) if $self->{mdre};
 }
 
+sub watch_imap_fetch_all ($$) {
+	my ($self, $uris) = @_;
+	for my $uri (@$uris) {
+		my $sec = imap_section($uri);
+		my $mic_arg = $self->{mic_arg}->{$sec} or
+			die "BUG: no Mail::IMAPClient->new arg for $sec";
+		my $mic = PublicInbox::IMAPClient->new(%$mic_arg) or next;
+		my $err = imap_fetch_all($self, $mic, $uri);
+		last if $self->{quit};
+		warn $err, "\n" if $err;
+	}
+}
+
+sub imap_fetch_fork ($$$) {
+	my ($self, $intvl, $uris) = @_;
+	return if $self->{quit};
+	$self->{mics} = {}; # going to be forking, so disconnect
+	defined(my $pid = fork) or die "fork: $!";
+	if ($pid == 0) {
+		watch_atfork_child($self);
+		watch_imap_fetch_all($self, $uris);
+		_exit(0);
+	}
+	$self->{poll_pids}->{$pid} = [ $intvl, $uris ];
+	PublicInbox::DS::dwaitpid($pid, \&imap_fetch_reap, $self);
+}
+
+sub imap_fetch_cb ($$$) {
+	my ($self, $intvl, $uris) = @_;
+	sub { imap_fetch_fork($self, $intvl, $uris) };
+}
+
+sub imap_fetch_reap { # PublicInbox::DS::dwaitpid callback
+	my ($self, $pid) = @_;
+	my $intvl_uris = delete $self->{poll_pids}->{$pid} or
+		die "BUG: PID=$pid (unknown) reaped: \$?=$?\n";
+	return if $self->{quit};
+	my ($intvl, $uris) = @$intvl_uris;
+	if ($?) {
+		warn "W: PID=$pid died: \$?=$?\n",
+			map { $_->as_string."\n" } @$uris;
+	}
+	warn('I: will check ', $_->as_string, " in ${intvl}s\n") for @$uris;
+	PublicInbox::DS::add_timer($intvl, imap_fetch_cb($self, $intvl, $uris));
+}
+
 sub watch_imap_init ($) {
 	my ($self) = @_;
 	eval { require PublicInbox::IMAPClient } or
@@ -542,7 +590,13 @@ sub watch_imap_init ($) {
 		$self->{idle_todo} = $idle;
 		PublicInbox::DS::requeue($self); # ->event_step to fork
 	}
-	# TODO: polling
+	return unless scalar keys %$poll;
+	$self->{poll_pids} = {};
+
+	# poll all URIs for a given interval sequentially
+	while (my ($intvl, $uris) = each %$poll) {
+		PublicInbox::DS::requeue(imap_fetch_cb($self, $intvl, $uris));
+	}
 }
 
 sub watch {
diff --git a/t/imapd.t b/t/imapd.t
index cc87a127851..ee3a3b26767 100644
--- a/t/imapd.t
+++ b/t/imapd.t
@@ -443,6 +443,7 @@ ok($mic->logout, 'logged out');
 {
 	use_ok 'PublicInbox::WatchMaildir';
 	use_ok 'PublicInbox::InboxIdle';
+	my $old_env = { HOME => $ENV{HOME} };
 	my $home = "$tmpdir/watch_home";
 	mkdir $home or BAIL_OUT $!;
 	mkdir "$home/.public-inbox" or BAIL_OUT $!;
@@ -464,13 +465,45 @@ ok($mic->logout, 'logged out');
 	my $cb = sub { PublicInbox::DS->SetPostLoopCallback(sub {}) };
 	my $obj = bless \$cb, 'PublicInbox::TestCommon::InboxWakeup';
 	$cfg->each_inbox(sub { $_[0]->subscribe_unlock('ident', $obj) });
-	open my $err, '+>', undef or BAIL_OUT $!;
-	my $w = start_script(['-watch'], undef, { 2 => $err });
+	my $watcherr = "$tmpdir/watcherr";
+	open my $err_wr, '>', $watcherr or BAIL_OUT $!;
+	open my $err, '<', $watcherr or BAIL_OUT $!;
+	my $w = start_script(['-watch'], undef, { 2 => $err_wr });
+
+	diag 'waiting for initial fetch...';
+	PublicInbox::DS->EventLoop;
+	diag 'inbox unlocked on initial fetch, waiting for IDLE';
+
+	tick until (grep(/I: \S+ idling/, <$err>));
+	open my $fh, '<', 't/iso-2202-jp.eml' or BAIL_OUT $!;
+	$old_env->{ORIGINAL_RECIPIENT} = $addr;
+	ok(run_script([qw(-mda --no-precheck)], $old_env, { 0 => $fh }),
+		'delivered a message for IDLE to kick -watch');
+	diag 'waiting for IMAP IDLE wakeup';
+	PublicInbox::DS->SetPostLoopCallback(undef);
+	PublicInbox::DS->EventLoop;
+	diag 'inbox unlocked on IDLE wakeup';
+
+	# try again with polling
+	xsys(qw(git config), "--file=$home/.public-inbox/config",
+		"imap.imap://$ihost:$iport.PollInterval", 0.11) == 0
+		or BAIL_OUT "git config $?";
+	$w->kill('HUP');
+	diag 'waiting for -watch reload + initial fetch';
+	tick until (grep(/I: will check/, <$err>));
+
+	open $fh, '<', 't/psgi_attach.eml' or BAIL_OUT $!;
+	ok(run_script([qw(-mda --no-precheck)], $old_env, { 0 => $fh }),
+		'delivered a message for -watch PollInterval');
+
+	diag 'waiting for PollInterval wakeup';
+	PublicInbox::DS->SetPostLoopCallback(undef);
 	PublicInbox::DS->EventLoop;
-	diag 'inbox unlocked';
+	diag 'inbox unlocked (poll)';
 	$w->kill;
 	$w->join;
 	is($?, 0, 'no error in exited -watch process');
+
 	$cfg->each_inbox(sub { shift->unsubscribe_unlock('ident') });
 	$ii->close;
 	PublicInbox::DS->Reset;

  parent reply	other threads:[~2020-06-27 10:04 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-27 10:03 [PATCH 00/34] watch: add IMAP and NNTP support Eric Wong
2020-06-27 10:03 ` [PATCH 01/34] inboxwritable: ensure ssoma.lock exists on init Eric Wong
2020-06-27 10:03 ` [PATCH 02/34] inbox: warn on ->on_inbox_unlock exception Eric Wong
2020-06-27 10:03 ` [PATCH 03/34] IMAPTracker: Add a helper to track our place in reading imap mailboxes Eric Wong
2020-06-27 10:03 ` [PATCH 04/34] imaptracker: use ~/.local/share/public-inbox/imap.sqlite3 Eric Wong
2020-06-27 10:03 ` [PATCH 05/34] watchmaildir: hoist out compile_watchheaders Eric Wong
2020-06-27 10:03 ` [PATCH 06/34] watchmaildir: fix check for spam vs ham inbox conflicts Eric Wong
2020-06-27 10:03 ` [PATCH 07/34] URI IMAP support Eric Wong
2020-06-27 10:03 ` [PATCH 08/34] watch: preliminary " Eric Wong
2020-06-27 10:03 ` [PATCH 09/34] kqnotify|fake_inotify: detect Maildir write ops Eric Wong
2020-06-27 10:03 ` [PATCH 10/34] watch: remove Filesys::Notify::Simple dependency Eric Wong
2020-06-27 10:03 ` [PATCH 11/34] watch: use signalfd for Maildir watching Eric Wong
2020-06-27 19:05   ` Kyle Meyer
2020-06-27 22:32     ` Eric Wong
2020-06-27 10:03 ` [PATCH 12/34] ds: remove fields.pm usage Eric Wong
2020-06-27 10:03 ` [PATCH 13/34] watch: wire up IMAP IDLE reapers to DS Eric Wong
2020-06-27 10:03 ` Eric Wong [this message]
2020-06-27 10:03 ` [PATCH 15/34] config: support ->urlmatch method for -watch Eric Wong
2020-06-27 10:03 ` [PATCH 16/34] watch: stop importers before forking Eric Wong
2020-06-27 10:03 ` [PATCH 17/34] watch: use UID SEARCH to avoid empty UID FETCH Eric Wong
2020-06-27 10:03 ` [PATCH 18/34] ds: add_timer: allow passing arg to callback Eric Wong
2020-06-27 10:03 ` [PATCH 19/34] imaptracker: add {url} field to reduce args Eric Wong
2020-06-27 10:03 ` [PATCH 20/34] imaptracker: drop {dbname} field Eric Wong
2020-06-27 10:03 ` [PATCH 21/34] watch: avoid long transaction to IMAPTracker Eric Wong
2020-06-27 10:03 ` [PATCH 22/34] watch: support imap.fetchBatchSize parameter Eric Wong
2020-06-27 10:03 ` [PATCH 23/34] watch: imap: be quiet about disconnecting on quit Eric Wong
2020-06-27 10:03 ` [PATCH 24/34] watch: support multiple watch: directives per-inbox Eric Wong
2020-06-27 10:03 ` [PATCH 25/34] watch: remove {mdir} array Eric Wong
2020-06-27 10:03 ` [PATCH 26/34] watch: just use ->urlmatch Eric Wong
2020-06-27 10:03 ` [PATCH 27/34] testcommon: $ENV{TAIL} supports non-@ARGV redirects Eric Wong
2020-06-27 10:03 ` [PATCH 28/34] watch: add NNTP support Eric Wong
2020-06-27 19:06   ` Kyle Meyer
2020-06-27 10:03 ` [PATCH 29/34] watch: show user-specified URL consistently Eric Wong
2020-06-27 10:03 ` [PATCH 30/34] watch: enable autoflush for STDOUT and STDERR Eric Wong
2020-06-27 10:03 ` [PATCH 31/34] watch: use our own "git credential" wrapper Eric Wong
2020-06-27 10:03 ` [PATCH 32/34] watch: support ~/.netrc via Net::Netrc Eric Wong
2020-06-27 10:03 ` [PATCH 33/34] imaptracker: use flock(2) around writes Eric Wong
2020-06-27 10:04 ` [PATCH 34/34] watch: simplify internal structures Eric Wong
2020-06-29 10:34 ` [PATCH 0/5] watch: Maildir fixes Eric Wong
2020-06-29 10:34   ` [PATCH 1/5] watch: check for duplicates in ->over before spamcheck Eric Wong
2020-06-29 10:34   ` [PATCH 2/5] watch: show path for warnings from spam messages Eric Wong
2020-06-29 10:34   ` [PATCH 3/5] watch: ensure SIGCHLD works in forked children Eric Wong
2020-06-29 10:34   ` [PATCH 4/5] spawn: unblock SIGCHLD in subprocess Eric Wong
2020-07-07  6:17     ` [PATCH 6/5] t/spawn: fix test reliability Eric Wong
2020-06-29 10:34   ` [PATCH 5/5] watch: make waitpid() synchronous for Maildir scans Eric Wong
2020-06-29 10:37     ` Eric Wong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://public-inbox.org/README

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200627100400.9871-15-e@yhbt.net \
    --to=e@yhbt.net \
    --cc=meta@public-inbox.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).