user/dev discussion of public-inbox itself
 help / color / Atom feed
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 54/57] ds: split out IO::KQueue-specific code
Date: Mon, 24 Jun 2019 02:52:55 +0000
Message-ID: <20190624025258.25592-55-e@80x24.org> (raw)
In-Reply-To: <20190624025258.25592-1-e@80x24.org>

We don't need to code multiple event loops or have branches in
watch() if we can easily make the IO::KQueue-based interface
look like our lower-level epoll_* API.
---
 MANIFEST                   |   1 +
 lib/PublicInbox/DS.pm      | 121 ++++++++-----------------------------
 lib/PublicInbox/DSKQXS.pm  |  73 ++++++++++++++++++++++
 lib/PublicInbox/Syscall.pm |   9 +--
 4 files changed, 99 insertions(+), 105 deletions(-)
 create mode 100644 lib/PublicInbox/DSKQXS.pm

diff --git a/MANIFEST b/MANIFEST
index 26ff0d0d..52c4790e 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -77,6 +77,7 @@ lib/PublicInbox/Cgit.pm
 lib/PublicInbox/Config.pm
 lib/PublicInbox/ContentId.pm
 lib/PublicInbox/DS.pm
+lib/PublicInbox/DSKQXS.pm
 lib/PublicInbox/Daemon.pm
 lib/PublicInbox/Emergency.pm
 lib/PublicInbox/EvCleanup.pm
diff --git a/lib/PublicInbox/DS.pm b/lib/PublicInbox/DS.pm
index d38e2d20..d6ef0b8d 100644
--- a/lib/PublicInbox/DS.pm
+++ b/lib/PublicInbox/DS.pm
@@ -36,14 +36,9 @@ use Errno  qw(EAGAIN EINVAL);
 use Carp   qw(croak confess carp);
 use File::Temp qw(tempfile);
 
-our $HAVE_KQUEUE = eval { require IO::KQueue; IO::KQueue->import; 1 };
-
 our (
-     $HaveEpoll,                 # Flag -- is epoll available?  initially undefined.
-     $HaveKQueue,
      %DescriptorMap,             # fd (num) -> PublicInbox::DS object
-     $Epoll,                     # Global epoll fd (for epoll mode only)
-     $KQueue,                    # Global kqueue fd ref (for kqueue mode only)
+     $Epoll,                     # Global epoll fd (or DSKQXS ref)
      $_io,                       # IO::Handle for Epoll
      @ToClose,                   # sockets to close when event loop is done
 
@@ -74,13 +69,8 @@ sub Reset {
     $PostLoopCallback = undef;
     $DoneInit = 0;
 
-    # NOTE kqueue is close-on-fork, and we don't account for it, yet
-    # OTOH, we (public-inbox) don't need this sub outside of tests...
-    POSIX::close($$KQueue) if !$_io && $KQueue && $$KQueue >= 0;
-    $KQueue = undef;
-
-    $_io = undef; # close $Epoll
-    $Epoll = undef;
+    $_io = undef; # closes real $Epoll FD
+    $Epoll = undef; # may call DSKQXS::DESTROY
 
     *EventLoop = *FirstTimeEventLoop;
 }
@@ -152,21 +142,17 @@ sub _InitPoller
     return if $DoneInit;
     $DoneInit = 1;
 
-    if ($HAVE_KQUEUE) {
-        $KQueue = IO::KQueue->new();
-        $HaveKQueue = defined $KQueue;
-        if ($HaveKQueue) {
-            *EventLoop = *KQueueEventLoop;
-        }
-    }
-    elsif (PublicInbox::Syscall::epoll_defined()) {
-        $Epoll = eval { epoll_create(1024); };
-        $HaveEpoll = defined $Epoll && $Epoll >= 0;
-        if ($HaveEpoll) {
-            set_cloexec($Epoll);
-            *EventLoop = *EpollEventLoop;
-        }
+    if (!PublicInbox::Syscall::epoll_defined())  {
+        $Epoll = eval {
+            require PublicInbox::DSKQXS;
+            PublicInbox::DSKQXS->import;
+            PublicInbox::DSKQXS->new;
+        };
+    } else {
+        $Epoll = epoll_create();
+        set_cloexec($Epoll) if (defined($Epoll) && $Epoll >= 0);
     }
+    *EventLoop = *EpollEventLoop;
 }
 
 =head2 C<< CLASS->EventLoop() >>
@@ -180,11 +166,7 @@ sub FirstTimeEventLoop {
 
     _InitPoller();
 
-    if ($HaveEpoll) {
-        EpollEventLoop($class);
-    } elsif ($HaveKQueue) {
-        KQueueEventLoop($class);
-    }
+    EventLoop($class);
 }
 
 sub now () { clock_gettime(CLOCK_MONOTONIC) }
@@ -218,11 +200,7 @@ sub RunTimers {
     return $timeout;
 }
 
-### The epoll-based event loop. Gets installed as EventLoop if IO::Epoll loads
-### okay.
 sub EpollEventLoop {
-    my $class = shift;
-
     while (1) {
         my @events;
         my $i;
@@ -241,30 +219,6 @@ sub EpollEventLoop {
     }
 }
 
-### The kqueue-based event loop. Gets installed as EventLoop if IO::KQueue works
-### okay.
-sub KQueueEventLoop {
-    my $class = shift;
-
-    while (1) {
-        my $timeout = RunTimers();
-        my @ret = eval { $KQueue->kevent($timeout) };
-        if (my $err = $@) {
-            # workaround https://rt.cpan.org/Ticket/Display.html?id=116615
-            if ($err =~ /Interrupted system call/) {
-                @ret = ();
-            } else {
-                die $err;
-            }
-        }
-
-        foreach my $kev (@ret) {
-            $DescriptorMap{$kev->[0]}->event_step;
-        }
-        return unless PostEventLoop();
-    }
-}
-
 =head2 C<< CLASS->SetPostLoopCallback( CODEREF ) >>
 
 Sets post loop callback function.  Pass a subref and it will be
@@ -314,17 +268,6 @@ sub PostEventLoop {
     return $keep_running;
 }
 
-# map EPOLL* bits to kqueue EV_* flags for EV_SET
-sub kq_flag ($$) {
-    my ($bit, $ev) = @_;
-    if ($ev & $bit) {
-        my $fl = EV_ADD() | EV_ENABLE();
-        ($ev & EPOLLONESHOT) ? ($fl|EV_ONESHOT()) : $fl;
-    } else {
-        EV_ADD() | EV_DISABLE();
-    }
-}
-
 #####################################################################
 ### PublicInbox::DS-the-object code
 #####################################################################
@@ -353,21 +296,13 @@ sub new {
 
     _InitPoller();
 
-    if ($HaveEpoll) {
-retry:
-        if (epoll_ctl($Epoll, EPOLL_CTL_ADD, $fd, $ev)) {
-            if ($! == EINVAL && ($ev & EPOLLEXCLUSIVE)) {
-                $ev &= ~EPOLLEXCLUSIVE;
-                goto retry;
-            }
-            die "couldn't add epoll watch for $fd: $!\n";
+    if (epoll_ctl($Epoll, EPOLL_CTL_ADD, $fd, $ev)) {
+        if ($! == EINVAL && ($ev & EPOLLEXCLUSIVE)) {
+            $ev &= ~EPOLLEXCLUSIVE;
+            goto retry;
         }
+        die "couldn't add epoll watch for $fd: $!\n";
     }
-    elsif ($HaveKQueue) {
-        $KQueue->EV_SET($fd, EVFILT_READ(), kq_flag(EPOLLIN, $ev));
-        $KQueue->EV_SET($fd, EVFILT_WRITE(), kq_flag(EPOLLOUT, $ev));
-    }
-
     Carp::cluck("PublicInbox::DS::new blowing away existing descriptor map for fd=$fd ($DescriptorMap{$fd})")
         if $DescriptorMap{$fd};
 
@@ -396,11 +331,9 @@ sub close {
 
     # if we're using epoll, we have to remove this from our epoll fd so we stop getting
     # notifications about it
-    if ($HaveEpoll) {
-        my $fd = fileno($sock);
-        epoll_ctl($Epoll, EPOLL_CTL_DEL, $fd, 0) and
-            confess("EPOLL_CTL_DEL: $!");
-    }
+    my $fd = fileno($sock);
+    epoll_ctl($Epoll, EPOLL_CTL_DEL, $fd, 0) and
+        confess("EPOLL_CTL_DEL: $!");
 
     # we explicitly don't delete from DescriptorMap here until we
     # actually close the socket, as we might be in the middle of
@@ -596,14 +529,8 @@ sub msg_more ($$) {
 sub watch ($$) {
     my ($self, $ev) = @_;
     my $sock = $self->{sock} or return;
-    my $fd = fileno($sock);
-    if ($HaveEpoll) {
-        epoll_ctl($Epoll, EPOLL_CTL_MOD, $fd, $ev) and
-            confess("EPOLL_CTL_MOD $!");
-    } elsif ($HaveKQueue) {
-        $KQueue->EV_SET($fd, EVFILT_READ(), kq_flag(EPOLLIN, $ev));
-        $KQueue->EV_SET($fd, EVFILT_WRITE(), kq_flag(EPOLLOUT, $ev));
-    }
+    epoll_ctl($Epoll, EPOLL_CTL_MOD, fileno($sock), $ev) and
+        confess("EPOLL_CTL_MOD $!");
     0;
 }
 
diff --git a/lib/PublicInbox/DSKQXS.pm b/lib/PublicInbox/DSKQXS.pm
new file mode 100644
index 00000000..38e13446
--- /dev/null
+++ b/lib/PublicInbox/DSKQXS.pm
@@ -0,0 +1,73 @@
+# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# Licensed the same as Danga::Socket (and Perl5)
+# License: GPL-1.0+ or Artistic-1.0-Perl
+#  <https://www.gnu.org/licenses/gpl-1.0.txt>
+#  <https://dev.perl.org/licenses/artistic.html>
+#
+# kqueue support via IO::KQueue XS module.  This makes kqueue look
+# like epoll to simplify the code in DS.pm.  This is NOT meant to be
+# an all encompassing emulation of epoll via IO::KQueue, but just to
+# support cases public-inbox-nntpd/httpd care about.
+# A pure-Perl version using syscall() is planned, and it should be
+# faster due to the lack of syscall overhead.
+package PublicInbox::DSKQXS;
+use strict;
+use warnings;
+use parent qw(IO::KQueue);
+use parent qw(Exporter);
+use IO::KQueue;
+use PublicInbox::Syscall qw(EPOLLONESHOT EPOLLIN EPOLLOUT EPOLL_CTL_DEL);
+our @EXPORT = qw(epoll_ctl epoll_wait);
+my $owner_pid = -1; # kqueue is close-on-fork (yes, fork, not exec)
+
+# map EPOLL* bits to kqueue EV_* flags for EV_SET
+sub kq_flag ($$) {
+	my ($bit, $ev) = @_;
+	if ($ev & $bit) {
+		my $fl = EV_ADD | EV_ENABLE;
+		($ev & EPOLLONESHOT) ? ($fl | EV_ONESHOT) : $fl;
+	} else {
+		EV_ADD | EV_DISABLE;
+	}
+}
+
+sub new {
+	my ($class) = @_;
+	die 'non-singleton use not supported' if $owner_pid == $$;
+	$owner_pid = $$;
+	$class->SUPER::new;
+}
+
+sub epoll_ctl {
+	my ($self, $op, $fd, $ev) = @_;
+	if ($op != EPOLL_CTL_DEL) {
+		$self->EV_SET($fd, EVFILT_READ, kq_flag(EPOLLIN, $ev));
+		$self->EV_SET($fd, EVFILT_WRITE, kq_flag(EPOLLOUT, $ev));
+	}
+	0;
+}
+
+sub epoll_wait {
+	my ($self, $maxevents, $timeout_msec, $events) = @_;
+	@$events = eval { $self->kevent($timeout_msec) };
+	if (my $err = $@) {
+		# workaround https://rt.cpan.org/Ticket/Display.html?id=116615
+		if ($err =~ /Interrupted system call/) {
+			@$events = ();
+		} else {
+			die $err;
+		}
+	}
+	# caller only cares for $events[$i]->[0]
+	scalar(@$events);
+}
+
+sub DESTROY {
+	my ($self) = @_;
+	if ($owner_pid == $$) {
+		POSIX::close($$self);
+		$owner_pid = -1;
+	}
+}
+
+1;
diff --git a/lib/PublicInbox/Syscall.pm b/lib/PublicInbox/Syscall.pm
index f1988e61..f53f3c82 100644
--- a/lib/PublicInbox/Syscall.pm
+++ b/lib/PublicInbox/Syscall.pm
@@ -248,14 +248,7 @@ sub sendfile_freebsd {
 
 sub epoll_defined { return $SYS_epoll_create ? 1 : 0; }
 
-# ARGS: (size) -- but in modern Linux 2.6, the
-# size doesn't even matter (radix tree now, not hash)
-sub epoll_create {
-    return -1 unless defined $SYS_epoll_create;
-    my $epfd = eval { syscall($SYS_epoll_create, $no_deprecated ? 0 : ($_[0]||100)+0) };
-    return -1 if $@;
-    return $epfd;
-}
+sub epoll_create { syscall($SYS_epoll_create, 0) }
 
 # epoll_ctl wrapper
 # ARGS: (epfd, op, fd, events_mask)
-- 
EW


  parent reply index

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-24  2:52 [PATCH 00/57] ds: shrink, TLS support, buffer writes to FS Eric Wong
2019-06-24  2:52 ` [PATCH 01/57] ds: get rid of {closed} field Eric Wong
2019-06-24  2:52 ` [PATCH 02/57] ds: get rid of more unused debug instance methods Eric Wong
2019-06-24  2:52 ` [PATCH 03/57] ds: use and export monotonic now() Eric Wong
2019-06-24  2:52 ` [PATCH 04/57] AddTimer: avoid clock_gettime for the '0' case Eric Wong
2019-06-24  2:52 ` [PATCH 05/57] ds: get rid of on_incomplete_write wrapper Eric Wong
2019-06-24  2:52 ` [PATCH 06/57] ds: lazy initialize wbuf_off Eric Wong
2019-06-24  2:52 ` [PATCH 07/57] ds: split out from ->flush_write and ->write Eric Wong
2019-06-24  2:52 ` [PATCH 08/57] ds: lazy-initialize wbuf Eric Wong
2019-06-24  2:52 ` [PATCH 09/57] ds: don't pass `events' arg to EPOLL_CTL_DEL Eric Wong
2019-06-24  2:52 ` [PATCH 10/57] ds: remove support for DS->write(undef) Eric Wong
2019-06-24  2:52 ` [PATCH 11/57] http: favor DS->write(strref) when reasonable Eric Wong
2019-06-24  2:52 ` [PATCH 12/57] ds: share send(..., MSG_MORE) logic Eric Wong
2019-06-24  2:52 ` [PATCH 13/57] ds: switch write buffering to use a tempfile Eric Wong
2019-06-24  2:52 ` [PATCH 14/57] ds: get rid of redundant and unnecessary POLL* constants Eric Wong
2019-06-24  2:52 ` [PATCH 15/57] syscall: get rid of unused EPOLL* constants Eric Wong
2019-06-24  2:52 ` [PATCH 16/57] syscall: get rid of unnecessary uname local vars Eric Wong
2019-06-24  2:52 ` [PATCH 17/57] ds: set event flags directly at initialization Eric Wong
2019-06-24  2:52 ` [PATCH 18/57] ds: import IO::KQueue namespace Eric Wong
2019-06-24  2:52 ` [PATCH 19/57] ds: share watch_chg between watch_read/watch_write Eric Wong
2019-06-24  2:52 ` [PATCH 20/57] ds: remove IO::Poll support (for now) Eric Wong
2019-06-24  2:52 ` [PATCH 21/57] ds: get rid of event_watch field Eric Wong
2019-06-24  2:52 ` [PATCH 22/57] httpd/async: remove EINTR check Eric Wong
2019-06-24  2:52 ` [PATCH 23/57] spawn: remove `Blocking' flag handling Eric Wong
2019-06-24  2:52 ` [PATCH 24/57] qspawn: describe where `$rpipe' come from Eric Wong
2019-06-24  2:52 ` [PATCH 25/57] http|nntp: favor "$! == EFOO" over $!{EFOO} checks Eric Wong
2019-06-24  2:52 ` [PATCH 26/57] ds: favor `delete' over assigning fields to `undef' Eric Wong
2019-06-24  2:52 ` [PATCH 27/57] http: don't pass extra args to PublicInbox::DS::close Eric Wong
2019-06-24  2:52 ` [PATCH 28/57] ds: pass $self to code references Eric Wong
2019-06-24  2:52 ` [PATCH 29/57] evcleanup: replace _run_asap with `event_step' callback Eric Wong
2019-06-24  2:52 ` [PATCH 30/57] ds: remove pointless exit calls Eric Wong
2019-06-24  2:52 ` [PATCH 31/57] http|nntp: be explicit about bytes::length on rbuf Eric Wong
2019-06-24  2:52 ` [PATCH 32/57] ds: hoist out do_read from NNTP and HTTP Eric Wong
2019-06-24  2:52 ` [PATCH 33/57] nntp: simplify re-arming/requeue logic Eric Wong
2019-06-24  2:52 ` [PATCH 34/57] allow use of PerlIO layers for filesystem writes Eric Wong
2019-06-24  2:52 ` [PATCH 35/57] ds: deal better with FS-related errors IO buffers Eric Wong
2019-06-24  2:52 ` [PATCH 36/57] nntp: wait for writability before sending greeting Eric Wong
2019-06-24  2:52 ` [PATCH 37/57] nntp: NNTPS and NNTP+STARTTLS working Eric Wong
2019-06-24  2:52 ` [PATCH 38/57] certs/create-certs.perl: fix cert validity on 32-bit Eric Wong
2019-06-24  2:52 ` [PATCH 39/57] daemon: map inherited sockets to well-known schemes Eric Wong
2019-06-24  2:52 ` [PATCH 40/57] ds|nntp: use CORE::close on socket Eric Wong
2019-06-24  2:52 ` [PATCH 41/57] nntp: call SSL_shutdown in normal cases Eric Wong
2019-06-24  2:52 ` [PATCH 42/57] t/nntpd-tls: slow client connection test Eric Wong
2019-06-24  2:52 ` [PATCH 43/57] daemon: use SSL_MODE_RELEASE_BUFFERS Eric Wong
2019-06-24  2:52 ` [PATCH 44/57] ds: allow ->write callbacks to syswrite directly Eric Wong
2019-06-24  2:52 ` [PATCH 45/57] nntp: reduce allocations for greeting Eric Wong
2019-06-24  2:52 ` [PATCH 46/57] ds: always use EV_ADD with EV_SET Eric Wong
2019-06-24  2:52 ` [PATCH 47/57] nntp: simplify long response logic and fix nesting Eric Wong
2019-06-24  2:52 ` [PATCH 48/57] ds: flush_write runs ->write callbacks even if closed Eric Wong
2019-06-24  2:52 ` [PATCH 49/57] nntp: lazily allocate and stash rbuf Eric Wong
2019-06-24  2:52 ` [PATCH 50/57] ci: require IO::KQueue on FreeBSD, for now Eric Wong
2019-06-24  2:52 ` [PATCH 51/57] nntp: send greeting immediately for plain sockets Eric Wong
2019-06-24  2:52 ` [PATCH 52/57] daemon: set TCP_DEFER_ACCEPT on everything but NNTP Eric Wong
2019-06-24  2:52 ` [PATCH 53/57] daemon: use FreeBSD accept filters on non-NNTP Eric Wong
2019-06-24  2:52 ` Eric Wong [this message]
2019-06-24  5:24   ` [PATCH 54/57] ds: split out IO::KQueue-specific code Eric Wong
2019-06-24  2:52 ` [PATCH 55/57] ds: reimplement IO::Poll support to look like epoll Eric Wong
2019-06-24  2:52 ` [PATCH 56/57] Revert "ci: require IO::KQueue on FreeBSD, for now" Eric Wong
2019-06-24  2:52 ` [PATCH 57/57] ds: reduce overhead of tempfile creation Eric Wong
2019-06-24  5:25 ` [PATCH 58/57] Makefile: skip DSKQXS in global syntax check Eric Wong
2019-06-24 18:28 ` [PATCH 59/57] ds: ->write must not clobber empty wbuf array Eric Wong

Reply instructions:

You may reply publically 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=20190624025258.25592-55-e@80x24.org \
    --to=e@80x24.org \
    --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

user/dev discussion of public-inbox itself

Archives are clonable:
	git clone --mirror https://public-inbox.org/meta
	git clone --mirror http://czquwvybam4bgbro.onion/meta
	git clone --mirror http://hjrcffqmbrq6wope.onion/meta
	git clone --mirror http://ou63pmih66umazou.onion/meta

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://ou63pmih66umazou.onion/inbox.comp.mail.public-inbox.meta
	nntp://czquwvybam4bgbro.onion/inbox.comp.mail.public-inbox.meta
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.org/gmane.mail.public-inbox.general

 note: .onion URLs require Tor: https://www.torproject.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox