extindex: --watch for inotify-based updates

This reuses existing InboxIdle infrastructure to update external
indices based on per-inbox updates.  This is an alternative to
auto-updating external indices via the -index command and also
works with existing uses of -mda and public-inbox-watch.

Using inotify (or EVFILT_VNODE) allows watching thousands of
inboxes without having to scan every single one at every
invocation.

This is especially beneficial in cases where an external index
is not writable to the users writing to per-inbox indices.

1 files changed, 15 insertions, 4 deletions

diff --git a/script/public-inbox-extindex b/script/public-inbox-extindex
index 17ad59fa..607baa3e 100644
--- a/script/public-inbox-extindex
+++ b/script/public-inbox-extindex
@@ -11,6 +11,7 @@ usage: public-inbox-extindex [options] EXTINDEX_DIR [INBOX_DIR]
   Create and update external (detached) search indices
 
   --no-fsync          speed up indexing, risk corruption on power outage
+  --watch             run persistently and watch for inbox updates
   -L LEVEL            `medium', or `full' (default: full)
   --all               index all configured inboxes
   --jobs=NUM          set or disable parallelization (NUM=0)
@@ -27,7 +28,7 @@ GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i
                 fsync|sync!
                 indexlevel|index-level|L=s max_size|max-size=s
                 batch_size|batch-size=s
-                gc
+                gc commit-interval=i watch
                 all help|h))
         or die $help;
 if ($opt->{help}) { print $help; exit 0 };
@@ -41,7 +42,8 @@ my $cfg = PublicInbox::Config->new;
 my @ibxs;
 if ($opt->{gc}) {
         die "E: inbox paths must not be specified with --gc\n" if @ARGV;
-        die "E: --all not compatible --gc\n" if $opt->{all};
+        die "E: --all not compatible with --gc\n" if $opt->{all};
+        die "E: --watch is not compatible with --gc\n" if $opt->{watch};
 } else {
         @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg);
 }
@@ -56,6 +58,15 @@ if ($opt->{gc}) {
         $eidx->attach_config($cfg);
         $eidx->eidx_gc($opt);
 } else {
-        $eidx->attach_inbox($_) for @ibxs;
-        $eidx->eidx_sync($opt);
+        if ($opt->{all}) {
+                $eidx->attach_config($cfg);
+        } else {
+                $eidx->attach_inbox($_) for @ibxs;
+        }
+        if ($opt->{watch}) {
+                $cfg = undef; # save memory only after SIGHUP
+                $eidx->eidx_watch($opt);
+        } else {
+                $eidx->eidx_sync($opt);
+        }
 }