about summary refs log tree commit homepage
diff options
context:
space:
mode:
-rw-r--r--MANIFEST2
-rw-r--r--lib/PublicInbox/NDC_PP.pm29
-rw-r--r--lib/PublicInbox/Over.pm5
-rw-r--r--lib/PublicInbox/SearchIdx.pm5
-rw-r--r--lib/PublicInbox/Spawn.pm63
-rw-r--r--t/nodatacow.t34
6 files changed, 134 insertions, 4 deletions
diff --git a/MANIFEST b/MANIFEST
index f46a0776..d312e305 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -156,6 +156,7 @@ lib/PublicInbox/MboxGz.pm
 lib/PublicInbox/MsgIter.pm
 lib/PublicInbox/MsgTime.pm
 lib/PublicInbox/Msgmap.pm
+lib/PublicInbox/NDC_PP.pm
 lib/PublicInbox/NNTP.pm
 lib/PublicInbox/NNTPD.pm
 lib/PublicInbox/NNTPdeflate.pm
@@ -309,6 +310,7 @@ t/multi-mid.t
 t/nntp.t
 t/nntpd-tls.t
 t/nntpd.t
+t/nodatacow.t
 t/nulsubject.t
 t/over.t
 t/plack-2-txt-bodies.eml
diff --git a/lib/PublicInbox/NDC_PP.pm b/lib/PublicInbox/NDC_PP.pm
new file mode 100644
index 00000000..0d20030d
--- /dev/null
+++ b/lib/PublicInbox/NDC_PP.pm
@@ -0,0 +1,29 @@
+# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+
+# Pure-perl class for Linux non-Inline::C users to disable COW for btrfs
+package PublicInbox::NDC_PP;
+use strict;
+use v5.10.1;
+
+sub set_nodatacow ($) {
+        my ($fd) = @_;
+        return if $^O ne 'linux';
+        defined(my $path = readlink("/proc/self/fd/$fd")) or return;
+        open my $mh, '<', '/proc/self/mounts' or return;
+        for (grep(/ btrfs /, <$mh>)) {
+                my (undef, $mnt_path, $type) = split(/ /);
+                next if $type ne 'btrfs'; # in case of false-positive from grep
+
+                # weird chars are escaped as octal
+                $mnt_path =~ s/\\(0[0-9]{2})/chr(oct($1))/egs;
+                $mnt_path .= '/' unless $mnt_path =~ m!/\z!;
+                if (index($path, $mnt_path) == 0) {
+                        # error goes to stderr, but non-fatal for us
+                        system('chattr', '+C', $path);
+                        last;
+                }
+        }
+}
+
+1;
diff --git a/lib/PublicInbox/Over.pm b/lib/PublicInbox/Over.pm
index f32743c0..0146414c 100644
--- a/lib/PublicInbox/Over.pm
+++ b/lib/PublicInbox/Over.pm
@@ -18,7 +18,12 @@ sub dbh_new {
         my $f = delete $self->{filename};
         if (!-f $f) { # SQLite defaults mode to 0644, we want 0666
                 if ($rw) {
+                        require PublicInbox::Spawn;
                         open my $fh, '+>>', $f or die "failed to open $f: $!";
+                        PublicInbox::Spawn::set_nodatacow(fileno($fh));
+                        my $j = "$f-journal";
+                        open $fh, '+>>', $j or die "failed to open $j: $!";
+                        PublicInbox::Spawn::set_nodatacow(fileno($fh));
                 } else {
                         $self->{filename} = $f; # die on stat() below:
                 }
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 1fc57410..aa8d8ce3 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -125,8 +125,11 @@ sub idx_acquire {
 
                 # don't create empty Xapian directories if we don't need Xapian
                 my $is_shard = defined($self->{shard});
-                if (!$is_shard || ($is_shard && need_xapian($self))) {
+                if (!-d $dir && (!$is_shard ||
+                                ($is_shard && need_xapian($self)))) {
                         File::Path::mkpath($dir);
+                        opendir my $dh, $dir or die "opendir($dir): $!\n";
+                        PublicInbox::Spawn::set_nodatacow(fileno($dh));
                 }
         }
         return unless defined $flag;
diff --git a/lib/PublicInbox/Spawn.pm b/lib/PublicInbox/Spawn.pm
index db679b77..50f31851 100644
--- a/lib/PublicInbox/Spawn.pm
+++ b/lib/PublicInbox/Spawn.pm
@@ -10,6 +10,9 @@
 # daemons (inside the PSGI code (-httpd) and -nntpd).  The short-lived
 # scripts (-mda, -index, -learn, -init) either use IPC::run or standard
 # Perl routines.
+#
+# There'll probably be more OS-level C stuff here, down the line.
+# We don't want too many DSOs: https://udrepper.livejournal.com/8790.html
 
 package PublicInbox::Spawn;
 use strict;
@@ -25,6 +28,7 @@ my $vfork_spawn = <<'VFORK_SPAWN';
 #include <sys/resource.h>
 #include <unistd.h>
 #include <stdlib.h>
+#include <errno.h>
 
 /* some platforms need alloca.h, but some don't */
 #if defined(__GNUC__) && !defined(alloca)
@@ -144,12 +148,51 @@ int pi_fork_exec(SV *redirref, SV *file, SV *cmdref, SV *envref, SV *rlimref,
 }
 VFORK_SPAWN
 
+# btrfs on Linux is copy-on-write (COW) by default.  As of Linux 5.7,
+# this still leads to fragmentation for SQLite and Xapian files where
+# random I/O happens, so we disable COW just for SQLite files and Xapian
+# directories.  Disabling COW disables checksumming, so we only do this
+# for regeneratable files, and not canonical git storage (git doesn't
+# checksum refs, only data under $GIT_DIR/objects).
+my $set_nodatacow = $^O eq 'linux' ? <<'SET_NODATACOW' : '';
+#include <sys/ioctl.h>
+#include <sys/vfs.h>
+#include <linux/magic.h>
+#include <linux/fs.h>
+#include <errno.h>
+#include <stdio.h>
+#include <string.h>
+
+void set_nodatacow(int fd)
+{
+        struct statfs buf;
+        int val = 0;
+
+        if (fstatfs(fd, &buf) < 0) {
+                fprintf(stderr, "fstatfs: %s\\n", strerror(errno));
+                return;
+        }
+
+        /* only btrfs is known to have this problem, so skip for non-btrfs */
+        if (buf.f_type != BTRFS_SUPER_MAGIC)
+                return;
+
+        if (ioctl(fd, FS_IOC_GETFLAGS, &val) < 0) {
+                fprintf(stderr, "FS_IOC_GET_FLAGS: %s\\n", strerror(errno));
+                return;
+        }
+        val |= FS_NOCOW_FL;
+        if (ioctl(fd, FS_IOC_SETFLAGS, &val) < 0)
+                fprintf(stderr, "FS_IOC_SET_FLAGS: %s\\n", strerror(errno));
+}
+SET_NODATACOW
+
 my $inline_dir = $ENV{PERL_INLINE_DIRECTORY} //= (
                 $ENV{XDG_CACHE_HOME} //
                 ( ($ENV{HOME} // '/nonexistent').'/.cache' )
         ).'/public-inbox/inline-c';
 
-$vfork_spawn = undef unless -d $inline_dir && -w _;
+$set_nodatacow = $vfork_spawn = undef unless -d $inline_dir && -w _;
 if (defined $vfork_spawn) {
         # Inline 0.64 or later has locking in multi-process env,
         # but we support 0.5 on Debian wheezy
@@ -158,14 +201,21 @@ if (defined $vfork_spawn) {
                 my $f = "$inline_dir/.public-inbox.lock";
                 open my $fh, '>', $f or die "failed to open $f: $!\n";
                 flock($fh, LOCK_EX) or die "LOCK_EX failed on $f: $!\n";
-                eval 'use Inline C => $vfork_spawn';
+                eval 'use Inline C => $vfork_spawn . $set_nodatacow';
                 my $err = $@;
+                my $ndc_err;
+                if ($err && $set_nodatacow) { # missing Linux kernel headers
+                        $ndc_err = $err;
+                        undef $set_nodatacow;
+                        eval 'use Inline C => $vfork_spawn';
+                }
                 flock($fh, LOCK_UN) or die "LOCK_UN failed on $f: $!\n";
                 die $err if $err;
+                warn $ndc_err if $ndc_err;
         };
         if ($@) {
                 warn "Inline::C failed for vfork: $@\n";
-                $vfork_spawn = undef;
+                $set_nodatacow = $vfork_spawn = undef;
         }
 }
 
@@ -173,6 +223,13 @@ unless (defined $vfork_spawn) {
         require PublicInbox::SpawnPP;
         *pi_fork_exec = \&PublicInbox::SpawnPP::pi_fork_exec
 }
+unless ($set_nodatacow) {
+        require PublicInbox::NDC_PP;
+        no warnings 'once';
+        *set_nodatacow = \&PublicInbox::NDC_PP::set_nodatacow;
+}
+undef $set_nodatacow;
+undef $vfork_spawn;
 
 sub which ($) {
         my ($file) = @_;
diff --git a/t/nodatacow.t b/t/nodatacow.t
new file mode 100644
index 00000000..87b6bdf7
--- /dev/null
+++ b/t/nodatacow.t
@@ -0,0 +1,34 @@
+#!perl -w
+# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+use strict;
+use Test::More;
+use File::Temp qw(tempfile);
+use PublicInbox::TestCommon;
+use PublicInbox::Spawn qw(which);
+use_ok 'PublicInbox::NDC_PP';
+
+SKIP: {
+        my $nr = 2;
+        skip 'test is Linux-only', $nr if $^O ne 'linux';
+        my $dir = $ENV{BTRFS_TESTDIR};
+        skip 'BTRFS_TESTDIR not defined', $nr unless defined $dir;
+        skip 'chattr(1) not installed', $nr unless which('chattr');
+        my $lsattr = which('lsattr') or skip 'lsattr(1) not installed', $nr;
+        my ($fh, $name) = tempfile(DIR => $dir, UNLINK => 1);
+        BAIL_OUT "tempfile: $!" unless $fh && defined($name);
+        my $pp_sub = \&PublicInbox::NDC_PP::set_nodatacow;
+        $pp_sub->(fileno($fh));
+        my $res = xqx([$lsattr, $name]);
+        like($res, qr/C/, "`C' attribute set with pure Perl");
+
+        my $ic_sub = \&PublicInbox::Spawn::set_nodatacow;
+        $pp_sub == $ic_sub and
+                skip 'Inline::C or Linux kernel headers missing', 1;
+        ($fh, $name) = tempfile(DIR => $dir, UNLINK => 1);
+        $ic_sub->(fileno($fh));
+        $res = xqx([$lsattr, $name]);
+        like($res, qr/C/, "`C' attribute set with Inline::C");
+};
+
+done_testing;