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 3/3] over+msgmap: do not store filename after DBI->connect
Date: Tue, 14 Jul 2020 02:14:32 +0000	[thread overview]
Message-ID: <20200714021432.11024-4-e@yhbt.net> (raw)
In-Reply-To: <20200714021432.11024-1-e@yhbt.net>

SQLite already knows the filename internally, so avoid having it
as a long-lived Perl SV to save some bytes when there's many
inboxes and open DBs.
---
 lib/PublicInbox/Inbox.pm   |  4 ++--
 lib/PublicInbox/Msgmap.pm  | 14 ++++++++------
 lib/PublicInbox/Over.pm    | 30 ++++++++++++++++++++++--------
 lib/PublicInbox/OverIdx.pm |  2 +-
 t/nntpd.t                  |  2 +-
 5 files changed, 34 insertions(+), 18 deletions(-)

diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index 3d9754dc..267be4e3 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -204,9 +204,9 @@ sub search ($;$) {
 sub over ($) {
 	my ($self) = @_;
 	my $srch = search($self, 1) or return;
-	$self->{over} ||= eval {
+	$self->{over} //= eval {
 		my $over = $srch->{over_ro};
-		$over->dbh_new; # may fail
+		$over->connect; # may fail
 		$over;
 	}
 }
diff --git a/lib/PublicInbox/Msgmap.pm b/lib/PublicInbox/Msgmap.pm
index e86fb854..38ec7858 100644
--- a/lib/PublicInbox/Msgmap.pm
+++ b/lib/PublicInbox/Msgmap.pm
@@ -229,9 +229,9 @@ sub mid_set {
 
 sub DESTROY {
 	my ($self) = @_;
-	delete $self->{dbh};
-	my $f = $self->{filename};
+	my $dbh = $self->{dbh} or return;
 	if (($self->{pid} // 0) == $$) {
+		my $f = $dbh->sqlite_db_filename;
 		unlink $f or warn "failed to unlink $f: $!\n";
 	}
 }
@@ -239,8 +239,9 @@ sub DESTROY {
 sub atfork_parent {
 	my ($self) = @_;
 	$self->{pid} or die "not a temporary clone\n";
-	delete $self->{dbh} and die "tmp_clone dbh not prepared for parent";
-	my $dbh = $self->{dbh} = PublicInbox::Over::dbh_new($self, 1);
+	my $dbh = $self->{dbh} and die "tmp_clone dbh not prepared for parent";
+	$self->{filename} = $dbh->sqlite_db_filename;
+	$dbh = $self->{dbh} = PublicInbox::Over::dbh_new($self, 1);
 	$dbh->do('PRAGMA synchronous = OFF');
 }
 
@@ -249,9 +250,10 @@ sub atfork_prepare {
 	$self->{pid} or die "not a temporary clone\n";
 	$self->{pid} == $$ or
 		die "BUG: atfork_prepare not called from $self->{pid}\n";
-	$self->{dbh} or die "temporary clone not open\n";
+	my $dbh = $self->{dbh} or die "temporary clone not open\n";
+
 	# must clobber prepared statements
-	%$self = (filename => $self->{filename}, pid => $$);
+	%$self = (filename => $dbh->sqlite_db_filename, pid => $$);
 }
 
 sub skip_artnum {
diff --git a/lib/PublicInbox/Over.pm b/lib/PublicInbox/Over.pm
index 5d285057..e3f26456 100644
--- a/lib/PublicInbox/Over.pm
+++ b/lib/PublicInbox/Over.pm
@@ -15,9 +15,13 @@ use constant DEFAULT_LIMIT => 1000;
 
 sub dbh_new {
 	my ($self, $rw) = @_;
-	my $f = $self->{filename};
-	if ($rw && !-f $f) { # SQLite defaults mode to 0644, we want 0666
-		open my $fh, '+>>', $f or die "failed to open $f: $!";
+	my $f = delete $self->{filename};
+	if (!-f $f) { # SQLite defaults mode to 0644, we want 0666
+		if ($rw) {
+			open my $fh, '+>>', $f or die "failed to open $f: $!";
+		} else {
+			$self->{filename} = $f; # die on stat() below:
+		}
 	}
 	my (@st, $st, $dbh);
 	my $tries = 0;
@@ -44,9 +48,14 @@ sub new {
 	bless { filename => $f }, $class;
 }
 
-sub disconnect { $_[0]->{dbh} = undef }
+sub disconnect {
+	my ($self) = @_;
+	if (my $dbh = delete $self->{dbh}) {
+		$self->{filename} = $dbh->sqlite_db_filename;
+	}
+}
 
-sub connect { $_[0]->{dbh} ||= $_[0]->dbh_new }
+sub connect { $_[0]->{dbh} //= $_[0]->dbh_new }
 
 sub load_from_row ($;$) {
 	my ($smsg, $cull) = @_;
@@ -258,13 +267,18 @@ SELECT COUNT(num) FROM over WHERE num > ? AND num <= ?
 
 sub check_inodes {
 	my ($self) = @_;
-	if (my @st = stat($self->{filename})) { # did st_dev, st_ino change?
+	my $dbh = $self->{dbh} or return;
+	my $f = $dbh->sqlite_db_filename;
+	if (my @st = stat($f)) { # did st_dev, st_ino change?
 		my $st = pack('dd', $st[0], $st[1]);
 
 		# don't actually reopen, just let {dbh} be recreated later
-		delete($self->{dbh}) if ($st ne ($self->{st} // $st));
+		if ($st ne ($self->{st} // $st)) {
+			delete($self->{dbh});
+			$self->{filename} = $f;
+		}
 	} else {
-		warn "W: stat $self->{filename}: $!\n";
+		warn "W: stat $f: $!\n";
 	}
 }
 
diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 13aa2d74..ea8da723 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -431,7 +431,7 @@ sub rollback_lazy {
 sub disconnect {
 	my ($self) = @_;
 	die "in transaction" if $self->{txn};
-	$self->{dbh} = undef;
+	$self->SUPER::disconnect;
 }
 
 sub create {
diff --git a/t/nntpd.t b/t/nntpd.t
index 954e6e75..aaf6661d 100644
--- a/t/nntpd.t
+++ b/t/nntpd.t
@@ -343,7 +343,7 @@ Date: Fri, 02 Oct 1993 00:00:00 +0000
 		$im->add($ex);
 		$im->done;
 		{
-			my $f = $ibx->mm->{filename};
+			my $f = $ibx->mm->{dbh}->sqlite_db_filename;
 			my $tmp = "$tmpdir/tmp.sqlite3";
 			$ibx->mm->{dbh}->sqlite_backup_to_file($tmp);
 			delete $ibx->{mm};

      parent reply	other threads:[~2020-07-14  2:14 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-14  2:14 [PATCH 0/3] avoid msgmap reopens in long-lived processes Eric Wong
2020-07-14  2:14 ` [PATCH 1/3] over: unset sqlite_unicode attribute Eric Wong
2020-07-14  2:14 ` [PATCH 2/3] nntpd+imapd: detect unlinked msgmap Eric Wong
2020-07-14  2:14 ` Eric Wong [this message]

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=20200714021432.11024-4-e@yhbt.net \
    --to=e@yhbt.net \
    --cc=meta@public-inbox.org \
    --subject='Re: [PATCH 3/3] over+msgmap: do not store filename after DBI->connect' \
    /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

This inbox may be cloned and mirrored by anyone:

	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

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V1 meta meta/ https://public-inbox.org/meta \
		meta@public-inbox.org
	public-inbox-index meta

Example config snippet for mirrors.
Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://7fh6tueqddpjyxjmgtdiueylzoqt6pt7hec3pukyptlmohoowvhde4yd.onion/inbox.comp.mail.public-inbox.meta
	nntp://ie5yzdi7fg72h7s4sdcztq5evakq23rdt33mfyfcddc5u3ndnw24ogqd.onion/inbox.comp.mail.public-inbox.meta
	nntp://4uok3hntl7oi7b4uf4rtfwefqeexfzil2w6kgk2jn5z2f764irre7byd.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.io/gmane.mail.public-inbox.general
 note: .onion URLs require Tor: https://www.torproject.org/

code repositories for project(s) associated with this inbox:

	https://80x24.org/public-inbox.git

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