v2writable: rename {partitions} field to {shards}

[public-inbox.git] / lib / PublicInbox / V2Writable.pm

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 09ed4e7b99ff096d194a9e59ff79a9569b745c0f..aa13aa8fb4722d7215422182bbcc024b5efacacf 100644 (file)
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -23,7 +23,14 @@ use IO::Handle;
 # an estimate of the post-packed size to the raw uncompressed size
 my $PACKING_FACTOR = 0.4;
 
-# assume 2 cores if GNU nproc(1) is not available
+# SATA storage lags behind what CPUs are capable of, so relying on
+# nproc(1) can be misleading and having extra Xapian partions is a
+# waste of FDs and space.  It can also lead to excessive IO latency
+# and slow things down.  Users on NVME or other fast storage can
+# use the NPROC env or switches in our script/public-inbox-* programs
+# to increase Xapian partitions.
+our $NPROC_MAX_DEFAULT = 4;
+
 sub nproc_parts ($) {
        my ($creat_opt) = @_;
        if (ref($creat_opt) eq 'HASH') {
@@ -32,20 +39,27 @@ sub nproc_parts ($) {
                }
        }
 
-       my $n = int($ENV{NPROC} || `nproc 2>/dev/null` || 2);
+       my $n = $ENV{NPROC};
+       if (!$n) {
+               chomp($n = `nproc 2>/dev/null`);
+               # assume 2 cores if GNU nproc(1) is not available
+               $n = 2 if !$n;
+               $n = $NPROC_MAX_DEFAULT if $n > $NPROC_MAX_DEFAULT;
+       }
+
        # subtract for the main process and git-fast-import
        $n -= 1;
        $n < 1 ? 1 : $n;
 }
 
-sub count_partitions ($) {
+sub count_shards ($) {
        my ($self) = @_;
        my $nparts = 0;
        my $xpfx = $self->{xpfx};
 
        # always load existing partitions in case core count changes:
-       # Also, partition count may change while -watch is running
-       # due to -compact
+       # Also, shard count may change while -watch is running
+       # due to "xcpdb --reshard"
        if (-d $xpfx) {
                foreach my $part (<$xpfx/*>) {
                        -d $part && $part =~ m!/[0-9]+\z! or next;
@@ -89,7 +103,7 @@ sub new {
                rotate_bytes => int((1024 * 1024 * 1024) / $PACKING_FACTOR),
                last_commit => [], # git repo -> commit
        };
-       $self->{partitions} = count_partitions($self) || nproc_parts($creat);
+       $self->{shards} = count_shards($self) || nproc_parts($creat);
        bless $self, $class;
 }
 
@@ -120,7 +134,7 @@ sub add {
 sub do_idx ($$$$$$$) {
        my ($self, $msgref, $mime, $len, $num, $oid, $mid0) = @_;
        $self->{over}->add_overview($mime, $len, $num, $oid, $mid0);
-       my $npart = $self->{partitions};
+       my $npart = $self->{shards};
        my $part = $num % $npart;
        my $idx = idx_part($self, $part);
        $idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
@@ -274,14 +288,14 @@ sub idx_init {
                $self->lock_acquire unless ($opt && $opt->{-skip_lock});
                $over->create;
 
-               # -compact can change partition count while -watch is idle
-               my $nparts = count_partitions($self);
-               if ($nparts && $nparts != $self->{partitions}) {
-                       $self->{partitions} = $nparts;
+               # xcpdb can change shard count while -watch is idle
+               my $nparts = count_shards($self);
+               if ($nparts && $nparts != $self->{shards}) {
+                       $self->{shards} = $nparts;
                }
 
                # need to create all parts before initializing msgmap FD
-               my $max = $self->{partitions} - 1;
+               my $max = $self->{shards} - 1;
 
                # idx_parts must be visible to all forked processes
                my $idx = $self->{idx_parts} = [];