From 3eec2f7792040f75f3988c520f308e2445baf645 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Mon, 7 Mar 2022 10:57:37 +0000
Subject: index|extindex: support --dangerous flag

This enables Xapian::DB_DANGEROUS to support in-place updates.
This can speed up the initial index and reduce I/O at the cost
of preventing concurrent readers and being unsafe in the face of
any abnormal terminations.  This is more dangerous than
--no-fsync.  --no-fsync is only unsafe in the event of a power
loss or kernel crash; --dangerous is unsafe even on SIGKILL.
---
 lib/PublicInbox/ExtSearchIdx.pm | 3 ++-
 lib/PublicInbox/MiscIdx.pm      | 1 +
 lib/PublicInbox/SearchIdx.pm    | 9 ++++++++-
 3 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'lib')

diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm
index 4b46fa16..7c44a1a4 100644
--- a/lib/PublicInbox/ExtSearchIdx.pm
+++ b/lib/PublicInbox/ExtSearchIdx.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # Detached/external index cross inbox search indexing support
@@ -59,6 +59,7 @@ sub new {
 		nproc_shards({ nproc => $opt->{jobs} });
 	my $oidx = PublicInbox::OverIdx->new("$self->{xpfx}/over.sqlite3");
 	$self->{-no_fsync} = $oidx->{-no_fsync} = 1 if !$opt->{fsync};
+	$self->{-dangerous} = 1 if $opt->{dangerous};
 	$self->{oidx} = $oidx;
 	$self
 }
diff --git a/lib/PublicInbox/MiscIdx.pm b/lib/PublicInbox/MiscIdx.pm
index dc15442d..5faf5c66 100644
--- a/lib/PublicInbox/MiscIdx.pm
+++ b/lib/PublicInbox/MiscIdx.pm
@@ -31,6 +31,7 @@ sub new {
 	PublicInbox::Syscall::nodatacow_dir($mi_dir);
 	my $flags = $PublicInbox::SearchIdx::DB_CREATE_OR_OPEN;
 	$flags |= $PublicInbox::SearchIdx::DB_NO_SYNC if $eidx->{-no_fsync};
+	$flags |= $PublicInbox::SearchIdx::DB_DANGEROUS if $eidx->{-dangerous};
 	$json //= PublicInbox::Config::json();
 	bless {
 		mi_dir => $mi_dir,
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 95b14c3a..85fae4ad 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -30,6 +30,7 @@ our @EXPORT_OK = qw(log2stack is_ancestor check_size prepare_stack
 my $X = \%PublicInbox::Search::X;
 our ($DB_CREATE_OR_OPEN, $DB_OPEN);
 our $DB_NO_SYNC = 0;
+our $DB_DANGEROUS = 0;
 our $BATCH_BYTES = $ENV{XAPIAN_FLUSH_THRESHOLD} ? 0x7fffffff :
 	# assume a typical 64-bit system has 8x more RAM than a
 	# typical 32-bit system:
@@ -115,7 +116,10 @@ sub load_xapian_writable () {
 	my $ver = (eval($xap.'::major_version()') << 16) |
 		(eval($xap.'::minor_version()') << 8) |
 		eval($xap.'::revision()');
-	$DB_NO_SYNC = 0x4 if $ver >= 0x10400;
+	if ($ver >= 0x10400) {
+		$DB_NO_SYNC = 0x4;
+		$DB_DANGEROUS = 0x10;
+	}
 	# Xapian v1.2.21..v1.2.24 were missing close-on-exec on OFD locks
 	$X->{CLOEXEC_UNSET} = 1 if $ver >= 0x010215 && $ver <= 0x010218;
 	1;
@@ -142,6 +146,9 @@ sub idx_acquire {
 			require PublicInbox::Syscall;
 			PublicInbox::Syscall::nodatacow_dir($dir);
 			$self->{-set_has_threadid_once} = 1;
+			if (($self->{ibx} // $self->{eidx})->{-dangerous}) {
+				$flag |= $DB_DANGEROUS;
+			}
 		}
 	}
 	return unless defined $flag;
-- 
cgit v1.2.3-24-ge0c7