* [PATCH 05/26] xapcmd: new module for wrapping Xapian commands
2019-05-23 9:36 7% [PATCH 00/26] xcpdb: ease Xapian DB format migrations Eric Wong
@ 2019-05-23 9:36 6% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2019-05-23 9:36 UTC (permalink / raw)
To: meta
Port public-inbox-compact(1) over to using it, and we will need
to wrap copydatabase(1) to ease glass migrations, too.
---
MANIFEST | 1 +
lib/PublicInbox/Xapcmd.pm | 65 ++++++++++++++++++++++++++++++++++
script/public-inbox-compact | 70 ++-----------------------------------
3 files changed, 68 insertions(+), 68 deletions(-)
create mode 100644 lib/PublicInbox/Xapcmd.pm
diff --git a/MANIFEST b/MANIFEST
index 2b101fa..dfc1f66 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -139,6 +139,7 @@ lib/PublicInbox/WwwHighlight.pm
lib/PublicInbox/WwwListing.pm
lib/PublicInbox/WwwStream.pm
lib/PublicInbox/WwwText.pm
+lib/PublicInbox/Xapcmd.pm
sa_config/Makefile
sa_config/README
sa_config/root/etc/spamassassin/public-inbox.pre
diff --git a/lib/PublicInbox/Xapcmd.pm b/lib/PublicInbox/Xapcmd.pm
new file mode 100644
index 0000000..586d7e6
--- /dev/null
+++ b/lib/PublicInbox/Xapcmd.pm
@@ -0,0 +1,65 @@
+# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+package PublicInbox::Xapcmd;
+use strict;
+use warnings;
+use PublicInbox::Spawn qw(which spawn);
+use PublicInbox::Over;
+use File::Temp qw(tempdir);
+use File::Path qw(remove_tree);
+
+sub commit_changes ($$$) {
+ my ($im, $old, $new) = @_;
+ my @st = stat($old) or die "failed to stat($old): $!\n";
+
+ my $over = "$old/over.sqlite3";
+ if (-f $over) {
+ $over = PublicInbox::Over->new($over);
+ $over->connect->sqlite_backup_to_file("$new/over.sqlite3");
+ }
+ rename($old, "$new/old") or die "rename $old => $new/old: $!\n";
+ chmod($st[2] & 07777, $new) or die "chmod $old: $!\n";
+ rename($new, $old) or die "rename $new => $old: $!\n";
+ $im->lock_release;
+ remove_tree("$old/old") or die "failed to remove $old/old: $!\n";
+}
+
+sub run {
+ my ($ibx, $cmd) = @_;
+ my $dir = $ibx->{mainrepo} or die "no mainrepo in inbox\n";
+ which($cmd->[0]) or die "$cmd->[0] not found in PATH\n";
+ $ibx->umask_prepare;
+ my $old = $ibx->search->xdir(1);
+ -d $old or die "$old does not exist\n";
+ my $new = tempdir($cmd->[0].'-XXXXXXXX', CLEANUP => 1, DIR => $dir);
+ my $v = $ibx->{version} || 1;
+ my @cmds;
+ if ($v == 1) {
+ push @cmds, [@$cmd, $old, $new];
+ } else {
+ opendir my $dh, $old or die "Failed to opendir $old: $!\n";
+ while (defined(my $dn = readdir($dh))) {
+ if ($dn =~ /\A\d+\z/) {
+ push @cmds, [@$cmd, "$old/$dn", "$new/$dn"];
+ } elsif ($dn eq '.' || $dn eq '..') {
+ } elsif ($dn =~ /\Aover\.sqlite3/) {
+ } else {
+ warn "W: skipping unknown dir: $old/$dn\n"
+ }
+ }
+ die "No Xapian parts found in $old\n" unless @cmds;
+ }
+ my $im = $ibx->importer(0);
+ $ibx->with_umask(sub {
+ $im->lock_acquire;
+ my %pids = map {; spawn($_) => join(' ', @$_) } @cmds;
+ while (scalar keys %pids) {
+ my $pid = waitpid(-1, 0);
+ my $desc = delete $pids{$pid};
+ die "$desc failed: $?\n" if $?;
+ }
+ commit_changes($im, $old, $new);
+ });
+}
+
+1;
diff --git a/script/public-inbox-compact b/script/public-inbox-compact
index 395eec3..4aa6273 100755
--- a/script/public-inbox-compact
+++ b/script/public-inbox-compact
@@ -8,9 +8,7 @@ use PublicInbox::Search;
use PublicInbox::Config;
use PublicInbox::InboxWritable;
use Cwd 'abs_path';
-use File::Temp qw(tempdir);
-use File::Path qw(remove_tree);
-use PublicInbox::Spawn qw(spawn);
+use PublicInbox::Xapcmd;
my $usage = "Usage: public-inbox-compact REPO_DIR\n";
my $dir = shift or die $usage;
my $config = eval { PublicInbox::Config->new };
@@ -31,71 +29,7 @@ unless ($ibx) {
};
$ibx = PublicInbox::Inbox->new($ibx);
}
-my $v = ($ibx->{version} || 1);
$ibx = PublicInbox::InboxWritable->new($ibx);
-$ibx->umask_prepare;
-
-sub commit_changes ($$$) {
- my ($im, $old, $new) = @_;
- my @st = stat($old) or die "failed to stat($old): $!\n";
-
- my $over = "$old/over.sqlite3";
- if (-f $over) {
- require PublicInbox::Over;
- $over = PublicInbox::Over->new($over);
- $over->connect->sqlite_backup_to_file("$new/over.sqlite3");
- }
- rename($old, "$new/old") or die "rename $old => $new/old: $!\n";
- chmod($st[2] & 07777, $new) or die "chmod $old: $!\n";
- rename($new, $old) or die "rename $new => $old: $!\n";
- $im->lock_release;
- remove_tree("$old/old") or die "failed to remove $old/old: $!\n";
-}
# we rely on --no-renumber to keep docids synched to NNTP
-my @compact = qw(xapian-compact --no-renumber);
-if ($v == 2) {
- require PublicInbox::V2Writable;
- my $v2w = PublicInbox::V2Writable->new($ibx);
- my $xap_v = 'xap'.PublicInbox::Search::SCHEMA_VERSION;
- my $old = "$dir/$xap_v";
- opendir my $dh, $old or die "Failed to opendir $old: $!\n";
- my $new = tempdir('compact-XXXXXXXX', CLEANUP => 1, DIR => $dir);
- $ibx->with_umask(sub {
- $v2w->lock_acquire;
- my %pids;
- while (defined(my $dn = readdir($dh))) {
- if ($dn =~ /\A\d+\z/) {
- my $cmd = [ @compact, "$old/$dn", "$new/$dn" ];
- $pids{spawn($cmd)} = join(' ', @$cmd);
- } elsif ($dn eq '.' || $dn eq '..') {
- } elsif ($dn =~ /\Aover\.sqlite3/) {
- } else {
- warn "W: skipping unknown Xapian DB: $old/$dn\n"
- }
- }
- close $dh;
- die "No Xapian parts found in $old\n" unless keys %pids;
- while (scalar keys %pids) {
- my $pid = waitpid(-1, 0);
- my $desc = delete $pids{$pid};
- die "$desc failed: $?\n" if $?;
- }
- commit_changes($v2w, $old, $new);
- });
-} elsif ($v == 1) {
- require PublicInbox::Import;
- my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
- my $xap_v = 'xapian'.PublicInbox::Search::SCHEMA_VERSION;
- my $v1_root = "$dir/public-inbox";
- my $old = "$v1_root/$xap_v";
- -d $old or die "$old does not exist\n";
- my $new = tempdir('compact-XXXXXXXX', CLEANUP => 1, DIR => $v1_root);
- $ibx->with_umask(sub {
- $im->lock_acquire;
- PublicInbox::Import::run_die([@compact, $old, $new]);
- commit_changes($im, $old, $new);
- });
-} else {
- die "Unsupported inbox version: $v\n";
-}
+PublicInbox::Xapcmd::run($ibx, [qw(xapian-compact --no-renumber)]);
--
EW
^ permalink raw reply related [relevance 6%]
* [PATCH 00/26] xcpdb: ease Xapian DB format migrations
@ 2019-05-23 9:36 7% Eric Wong
2019-05-23 9:36 6% ` [PATCH 05/26] xapcmd: new module for wrapping Xapian commands Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2019-05-23 9:36 UTC (permalink / raw)
To: meta
I've noticed performance problems in Xapian's old chert
backend which seem alleviated with the new glass backend;
particularly related to phrase searches.
Unfortunately, the tool distributed with Xapian for updating DB
formats, copydatabase(1), is extremely slow and blocking updates
for hours at a time to perform the migration is not acceptable.
(That's right, "copydatabase" is NOT a Postgres command!)
So, I've written "public-inbox-xcpdb" and gotten it to perform
the bulk copy operation without holding inbox.lock and have it
deal gracefully with Xapian DB modifications. xcpdb is still
slow, but I've (finally!) implemented partial reindexing to
allow it to minimize the lock time and not stall -mda or -watch
processes while it is working.
There's a bunch of cleanups along the way, too; and it should
make future changes to repartition the Xapian DB on existing v2
inboxes easier.
Eric Wong (26):
t/convert-compact: skip on missing xapian-compact(1)
v1writable: retire in favor of InboxWritable
doc: document the reason for --no-renumber
search: reenable phrase search on non-chert Xapian
xapcmd: new module for wrapping Xapian commands
admin: hoist out resolve_inboxes for -compact and -index
xapcmd: support spawn options
xcpdb: new tool which wraps Xapian's copydatabase(1)
xapcmd: do not cleanup on errors
admin: move index_inbox over
xcpdb: implement using Perl bindings
xapcmd: xcpdb supports compaction
v2writable: hoist out log_range sub for readability
xcpdb: use fine-grained locking
xcpdb: implement progress reporting
xcpdb: cleanup error handling and diagnosis
xapcmd: avoid EXDEV when finalizing changes
doc: xcpdb: update to reflect the current state
xapcmd: use "print STDERR" for progress reporting
xcpdb: show re-indexing progress
xcpdb: remove temporary directories on aborts
compact: reuse infrastructure from xcpdb
xcpdb|compact: support some xapian-compact switches
xapcmd: cleanup on interrupted xcpdb "--compact"
xcpdb|compact: support --jobs/-j flag like gmake(1)
xapcmd: do not reset %SIG until last Xtmpdir is done
Documentation/include.mk | 6 +-
Documentation/public-inbox-v1-format.pod | 4 +
Documentation/public-inbox-v2-format.pod | 4 +
Documentation/public-inbox-xcpdb.pod | 57 ++++
MANIFEST | 4 +-
lib/PublicInbox/Admin.pm | 66 ++++
lib/PublicInbox/InboxWritable.pm | 35 ++-
lib/PublicInbox/Search.pm | 48 +--
lib/PublicInbox/SearchIdx.pm | 34 ++-
lib/PublicInbox/V1Writable.pm | 34 ---
lib/PublicInbox/V2Writable.pm | 109 ++++---
lib/PublicInbox/Xapcmd.pm | 370 +++++++++++++++++++++++
script/public-inbox-compact | 102 +------
script/public-inbox-index | 102 +------
script/public-inbox-init | 13 +-
script/public-inbox-xcpdb | 19 ++
t/cgi.t | 4 +-
t/convert-compact.t | 4 +
t/indexlevels-mirror.t | 27 +-
t/init.t | 4 +-
t/nntpd.t | 15 +-
t/search.t | 1 +
t/v2mirror.t | 1 +
23 files changed, 740 insertions(+), 323 deletions(-)
create mode 100644 Documentation/public-inbox-xcpdb.pod
delete mode 100644 lib/PublicInbox/V1Writable.pm
create mode 100644 lib/PublicInbox/Xapcmd.pm
create mode 100755 script/public-inbox-xcpdb
--
EW
^ permalink raw reply [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2019-05-23 9:36 7% [PATCH 00/26] xcpdb: ease Xapian DB format migrations Eric Wong
2019-05-23 9:36 6% ` [PATCH 05/26] xapcmd: new module for wrapping Xapian commands Eric Wong
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).