[Koha-patches] [PATCH] Bug 11078 Add locking to rebuild_zebra.pl

[Doug Kingston]

This patch adds locking to rebuild_zebra.pl to ensure that simultaneous
changes are prevented (as one is likely to overwrite the other).
Incremental updates in daemon mode will skipped if the lock is busy
and they will be picked up on the next pass.  Non-daemon mode
invocations will wait for the lock to clear and then proceed.
Supporting changes made to Makefile.PL and templates for the new
locking directory (paralleling the other zebra lock directories).
We stash the zebra_lockdir in koha-conf.xml so rebuild_zebra.pl
can find it.
---
 Makefile.PL                               |    5 ++++-
 debian/templates/koha-conf-site.xml.in    |    1 +
 etc/koha-conf.xml                         |    1 +
 misc/bin/koha-zebra-ctl.sh                |    1 +
 misc/migration_tools/rebuild_zebra.pl     |   26 +++++++++++++++++++++++++-
 skel/var/lock/koha/zebradb/rebuild/README |    1 +
 6 files changed, 33 insertions(+), 2 deletions(-)
 create mode 100644 skel/var/lock/koha/zebradb/rebuild/README

diff --git a/Makefile.PL b/Makefile.PL
index 66f9a0f..7d5eb4a 100644
--- a/Makefile.PL
+++ b/Makefile.PL
@@ -186,7 +186,9 @@ Directory for Zebra configuration files.
 
 =item ZEBRA_LOCK_DIR
 
-Directory for Zebra's lock files.
+Directory for Zebra's lock files.  This includes subdirs for authorities,
+biblios, and the zebra rebuild function.  Any activity to reindex
+zebra from koha should interlock here with rebuild_zebra.pl.
 
 =item ZEBRA_DATA_DIR
 
@@ -318,6 +320,7 @@ my $target_map = {
   './skel/var/lib/koha/zebradb/biblios/register'  => { target => 'ZEBRA_DATA_DIR', trimdir => 6 },
   './skel/var/lib/koha/zebradb/biblios/shadow'  => { target => 'ZEBRA_DATA_DIR', trimdir => 6 },
   './skel/var/lib/koha/zebradb/biblios/tmp'  => { target => 'ZEBRA_DATA_DIR', trimdir => 6 },
+  './skel/var/lock/koha/zebradb/rebuild' => { target => 'ZEBRA_LOCK_DIR', trimdir => 6 },
   './skel/var/lib/koha/plugins' => { target => 'PLUGINS_DIR', trimdir => 6 },
   './sms'                       => 'INTRANET_CGI_DIR',
   './suggestion'                => 'INTRANET_CGI_DIR',
diff --git a/debian/templates/koha-conf-site.xml.in b/debian/templates/koha-conf-site.xml.in
index 9bf090b..371b1d2 100644
--- a/debian/templates/koha-conf-site.xml.in
+++ b/debian/templates/koha-conf-site.xml.in
@@ -280,6 +280,7 @@
  <memcached_namespace>__MEMCACHED_NAMESPACE__</memcached_namespace>
  <zebra_bib_index_mode>__BIBLIOS_INDEXING_MODE__</zebra_bib_index_mode>
  <zebra_auth_index_mode>__AUTHORITIES_INDEXING_MODE__</zebra_auth_index_mode>
+ <zebra_lockdir>/var/lock/koha/__KOHASITE__</zebra_lockdir>
  <queryparser_config>/etc/koha/searchengine/queryparser.yaml</queryparser_config>
 </config>
 
diff --git a/etc/koha-conf.xml b/etc/koha-conf.xml
index d42f041..3bdbdf9 100644
--- a/etc/koha-conf.xml
+++ b/etc/koha-conf.xml
@@ -296,6 +296,7 @@ __PAZPAR2_TOGGLE_XML_POST__
  <useldapserver>0</useldapserver><!-- see C4::Auth_with_ldap for extra configs you must add if you want to turn this on -->
  <zebra_bib_index_mode>__BIB_INDEX_MODE__</zebra_bib_index_mode>
  <zebra_auth_index_mode>__AUTH_INDEX_MODE__</zebra_auth_index_mode>
+ <zebra_lockdir>__ZEBRA_LOCK_DIR__</zebra_lockdir>
  <queryparser_config>__KOHA_CONF_DIR__/searchengine/queryparser.yaml</queryparser_config>
 </config>
 </yazgfs>
diff --git a/misc/bin/koha-zebra-ctl.sh b/misc/bin/koha-zebra-ctl.sh
index 397eb19..82b9162 100755
--- a/misc/bin/koha-zebra-ctl.sh
+++ b/misc/bin/koha-zebra-ctl.sh
@@ -65,6 +65,7 @@ case "$1" in
         mkdir -p $LOCKDIR
         mkdir -p $LOCKDIR/biblios
         mkdir -p $LOCKDIR/authorities
+        mkdir -p $LOCKDIR/rebuild
         if [[ $EUID -eq 0 ]]; then
             chown -R $USER:$GROUP $LOCKDIR
         fi
diff --git a/misc/migration_tools/rebuild_zebra.pl b/misc/migration_tools/rebuild_zebra.pl
index 7e0c83a..1e9b300 100755
--- a/misc/migration_tools/rebuild_zebra.pl
+++ b/misc/migration_tools/rebuild_zebra.pl
@@ -5,6 +5,7 @@ use strict;
 
 use C4::Context;
 use Getopt::Long;
+use Fcntl qw(:flock);
 use File::Temp qw/ tempdir /;
 use File::Path;
 use C4::Biblio;
@@ -153,12 +154,21 @@ my $dbh = C4::Context->dbh;
 my ($biblionumbertagfield,$biblionumbertagsubfield) = &GetMarcFromKohaField("biblio.biblionumber","");
 my ($biblioitemnumbertagfield,$biblioitemnumbertagsubfield) = &GetMarcFromKohaField("biblioitems.biblioitemnumber","");
 
+# Protect again simultaneous update of the zebra index by using a lock file.
+# Create our own lock directory if its missing.  This shouild be created
+# by koha-zebra-ctl.sh.
+
+my $lockdir = C4::Context->config("zebra_lockdir") // "/var/lock";
+mkpath($lockdir, 0, oct(755)) unless (-d $lockdir);
+my $lockfile = $lockdir . "/rebuild..LCK";
+
 if ( $verbose_logging ) {
     print "Zebra configuration information\n";
     print "================================\n";
     print "Zebra biblio directory      = $biblioserverdir\n";
     print "Zebra authorities directory = $authorityserverdir\n";
     print "Koha directory              = $kohadir\n";
+    print "Lockfile                    = $lockfile\n";
     print "BIBLIONUMBER in :     $biblionumbertagfield\$$biblionumbertagsubfield\n";
     print "BIBLIOITEMNUMBER in : $biblioitemnumbertagfield\$$biblioitemnumbertagsubfield\n";
     print "================================\n";
@@ -170,13 +180,27 @@ if ($do_munge) {
 
 my $tester = XML::LibXML->new();
 
+# The main work is done here by calling do_one_pass().  We have added locking
+# avoid race conditions between Full rebuilds and incremental updates either from
+# daemon mode or periodic invocation from cron.  The race can lead to an updated
+# record being overwritten by a rebuild if the update is applied after the export
+# by the rebuild and before the rebuild finishes (more likely to effect large
+# catalogs).
+open my $LockFH, q{>}, $lockfile or die "$lockfile: $!";
 if ($daemon_mode) {
     while (1) {
-        do_one_pass() if ( zebraqueue_not_empty() );
+        # For incremental updates, skip the update if the updates are locked
+        if (flock($LockFH, LOCK_EX|LOCK_NB)) {
+            do_one_pass() if ( zebraqueue_not_empty() );
+            flock($LockFH, LOCK_UN);
+        }
         sleep $daemon_sleep;
     }
 } else {
+    # all one-off invocations, wait for the lock to free
+    flock($LockFH, LOCK_EX);
     do_one_pass();
+    flock($LockFH, LOCK_UN);
 }
 
 
diff --git a/skel/var/lock/koha/zebradb/rebuild/README b/skel/var/lock/koha/zebradb/rebuild/README
new file mode 100644
index 0000000..98b4c5b
--- /dev/null
+++ b/skel/var/lock/koha/zebradb/rebuild/README
@@ -0,0 +1 @@
+Zebra rebuild lock dir
-- 
1.7.9.5