* [PATCH 18/20] xapcmd: favor 'shard' over 'part' in local variables
2019-06-15 8:46 7% [PATCH 00/20] v2: use consistent terminology Eric Wong
@ 2019-06-15 8:47 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2019-06-15 8:47 UTC (permalink / raw)
To: meta
Yet another step to keeping our naming consistent with Xapian
terminology.
---
lib/PublicInbox/Xapcmd.pm | 70 +++++++++++++++++++--------------------
1 file changed, 35 insertions(+), 35 deletions(-)
diff --git a/lib/PublicInbox/Xapcmd.pm b/lib/PublicInbox/Xapcmd.pm
index 5e4ac87..819d782 100644
--- a/lib/PublicInbox/Xapcmd.pm
+++ b/lib/PublicInbox/Xapcmd.pm
@@ -17,13 +17,13 @@ our @COMPACT_OPT = qw(jobs|j=i quiet|q blocksize|b=s no-full|n fuller|F);
sub commit_changes ($$$) {
my ($ibx, $tmp, $opt) = @_;
- my $new_parts = $opt->{reshard};
+ my $reshard = $opt->{reshard};
my $reindex = $opt->{reindex};
my $im = $ibx->importer(0);
$im->lock_acquire if !$opt->{-coarse_lock};
$SIG{INT} or die 'BUG: $SIG{INT} not handled';
- my @old_part;
+ my @old_shard;
while (my ($old, $new) = each %$tmp) {
my @st = stat($old);
@@ -41,7 +41,7 @@ sub commit_changes ($$$) {
}
if (!defined($new)) { # culled shard
- push @old_part, $old;
+ push @old_shard, $old;
next;
}
@@ -58,7 +58,7 @@ sub commit_changes ($$$) {
die "failed to remove $prev: $!\n";
}
}
- remove_tree(@old_part);
+ remove_tree(@old_shard);
$tmp->done;
if (!$opt->{-coarse_lock}) {
$opt->{-skip_lock} = 1;
@@ -66,9 +66,9 @@ sub commit_changes ($$$) {
if ($im->can('count_shards')) {
my $pr = $opt->{-progress};
my $n = $im->count_shards;
- if (defined $new_parts && $n != $new_parts) {
+ if (defined $reshard && $n != $reshard) {
die
-"BUG: counted $n shards after resharding to $new_parts";
+"BUG: counted $n shards after resharding to $reshard";
}
my $prev = $im->{shards};
if ($pr && $prev != $n) {
@@ -171,17 +171,17 @@ sub run {
my $tmp = PublicInbox::Xtmpdirs->new;
my $v = $ibx->{version} ||= 1;
my @q;
- my $new_parts = $opt->{reshard};
- if (defined $new_parts && $new_parts <= 0) {
+ my $reshard = $opt->{reshard};
+ if (defined $reshard && $reshard <= 0) {
die "--reshard must be a positive number\n";
}
# we want temporary directories to be as deep as possible,
# so v2 shards can keep "xap$SCHEMA_VERSION" on a separate FS.
if ($v == 1) {
- if (defined $new_parts) {
+ if (defined $reshard) {
warn
-"--reshard=$new_parts ignored for v1 $ibx->{mainrepo}\n";
+"--reshard=$reshard ignored for v1 $ibx->{mainrepo}\n";
}
my $old_parent = dirname($old);
same_fs_or_die($old_parent, $old);
@@ -191,28 +191,28 @@ sub run {
push @q, [ $old, $wip ];
} else {
opendir my $dh, $old or die "Failed to opendir $old: $!\n";
- my @old_parts;
+ my @old_shards;
while (defined(my $dn = readdir($dh))) {
if ($dn =~ /\A[0-9]+\z/) {
- push @old_parts, $dn;
+ push @old_shards, $dn;
} elsif ($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 @old_parts;
+ die "No Xapian shards found in $old\n" unless @old_shards;
- my ($src, $max_part);
- if (!defined($new_parts) || $new_parts == scalar(@old_parts)) {
+ my ($src, $max_shard);
+ if (!defined($reshard) || $reshard == scalar(@old_shards)) {
# 1:1 copy
- $max_part = scalar(@old_parts) - 1;
+ $max_shard = scalar(@old_shards) - 1;
} else {
# M:N copy
- $max_part = $new_parts - 1;
- $src = [ map { "$old/$_" } @old_parts ];
+ $max_shard = $reshard - 1;
+ $src = [ map { "$old/$_" } @old_shards ];
}
- foreach my $dn (0..$max_part) {
+ foreach my $dn (0..$max_shard) {
my $tmpl = "$dn-XXXXXXXX";
my $wip = tempdir($tmpl, DIR => $old);
same_fs_or_die($old, $wip);
@@ -220,7 +220,7 @@ sub run {
push @q, [ $src // $cur , $wip ];
$tmp->{$cur} = $wip;
}
- # mark old parts to be unlinked
+ # mark old shards to be unlinked
if ($src) {
$tmp->{$_} ||= undef for @$src;
}
@@ -305,7 +305,7 @@ sub compact ($$) {
}
sub cpdb_loop ($$$;$$) {
- my ($src, $dst, $pr_data, $cur_part, $new_parts) = @_;
+ my ($src, $dst, $pr_data, $cur_shard, $reshard) = @_;
my ($pr, $fmt, $nr, $pfx);
if ($pr_data) {
$pr = $pr_data->{pr};
@@ -326,9 +326,9 @@ sub cpdb_loop ($$$;$$) {
eval {
for (; $it != $end; $it++) {
my $docid = $it->get_docid;
- if (defined $new_parts) {
- my $dst_part = $docid % $new_parts;
- next if $dst_part != $cur_part;
+ if (defined $reshard) {
+ my $dst_shard = $docid % $reshard;
+ next if $dst_shard != $cur_shard;
}
my $doc = $src->get_document($docid);
$dst->replace_document($docid, $doc);
@@ -350,14 +350,14 @@ sub cpdb_loop ($$$;$$) {
sub cpdb ($$) {
my ($args, $opt) = @_;
my ($old, $new) = @$args;
- my ($src, $cur_part);
- my $new_parts;
+ my ($src, $cur_shard);
+ my $reshard;
if (ref($old) eq 'ARRAY') {
- ($cur_part) = ($new =~ m!xap[0-9]+/([0-9]+)\b!);
- defined $cur_part or
+ ($cur_shard) = ($new =~ m!xap[0-9]+/([0-9]+)\b!);
+ defined $cur_shard or
die "BUG: could not extract shard # from $new";
- $new_parts = $opt->{reshard};
- defined $new_parts or die 'BUG: got array src w/o --reshard';
+ $reshard = $opt->{reshard};
+ defined $reshard or die 'BUG: got array src w/o --reshard';
# resharding, M:N copy means have full read access
foreach (@$old) {
@@ -410,8 +410,8 @@ sub cpdb ($$) {
# we can only estimate when resharding,
# because removed spam causes slight imbalance
my $est = '';
- if (defined $cur_part && $new_parts > 1) {
- $tot = int($tot/$new_parts);
+ if (defined $cur_shard && $reshard > 1) {
+ $tot = int($tot/$reshard);
$est = 'around ';
}
my $fmt = "$pfx % ".length($tot)."u/$tot\n";
@@ -422,15 +422,15 @@ sub cpdb ($$) {
};
} while (cpdb_retryable($src, $pfx));
- if (defined $new_parts) {
+ if (defined $reshard) {
# we rely on document IDs matching NNTP article number,
- # so we can't have the combined DB support rewriting
+ # so we can't have the Xapian sharding DB support rewriting
# document IDs. Thus we iterate through each shard
# individually.
$src = undef;
foreach (@$old) {
my $old = Search::Xapian::Database->new($_);
- cpdb_loop($old, $dst, $pr_data, $cur_part, $new_parts);
+ cpdb_loop($old, $dst, $pr_data, $cur_shard, $reshard);
}
} else {
cpdb_loop($src, $dst, $pr_data);
--
EW
^ permalink raw reply related [relevance 5%]
* [PATCH 00/20] v2: use consistent terminology
@ 2019-06-15 8:46 7% Eric Wong
2019-06-15 8:47 5% ` [PATCH 18/20] xapcmd: favor 'shard' over 'part' in local variables Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2019-06-15 8:46 UTC (permalink / raw)
To: meta
Modern Xapian docs and code refer to multi-DB uses as "shards";
so replace the term "partition" with the term "shard". This
way, we'll minimize the learning curve for people new to
public-inbox or Xapian.
We also still had a few places where we referred to git epochs
as "partitions", so fix those up and be consistent with the
majority of our own docs and code.
Eric Wong (20):
doc: rename our Xapian "partitions" to "shards"
v2writable: update comments regarding xcpdb --reshard
admin|xapcmd: user-facing messages say "shard"
rename reference to git epochs as "partitions"
searchidxpart: start using "shard" in user-visible places
v2writable: count_partitions => count_shards
v2writable: rename {partitions} field to {shards}
tests: change messages to use "shard" instead of partition
inboxwritable: s/partitions/shards/ in local var
v2: rename SearchIdxPart => SearchIdxShard
xapcmd: update comments referencing "partitions"
search*: rename {partition} => {shard}
v2writable: avoid "part" in internal subs and fields
v2writable: rename local vars to match Xapian terminology
adminedit: "part" => "shard" for local variables
v2writable: use "epoch" consistently when referring to git repos
search: use "shard" for local variable
xapcmd: favor 'shard' over 'part' in local variables
t/xcpdb-reshard: use 'shard' term in local variables
comments: replace "partition" with "shard"
Documentation/public-inbox-v2-format.pod | 10 +-
Documentation/public-inbox-xcpdb.pod | 11 +-
MANIFEST | 2 +-
lib/PublicInbox/Admin.pm | 4 +-
lib/PublicInbox/AdminEdit.pm | 12 +-
lib/PublicInbox/Inbox.pm | 18 +--
lib/PublicInbox/InboxWritable.pm | 4 +-
lib/PublicInbox/Search.pm | 14 +--
lib/PublicInbox/SearchIdx.pm | 19 +--
.../{SearchIdxPart.pm => SearchIdxShard.pm} | 30 ++---
lib/PublicInbox/V2Writable.pm | 109 +++++++++---------
lib/PublicInbox/WWW.pm | 12 +-
lib/PublicInbox/WwwListing.pm | 2 +-
lib/PublicInbox/WwwStream.pm | 12 +-
lib/PublicInbox/Xapcmd.pm | 96 +++++++--------
t/indexlevels-mirror.t | 2 +-
t/psgi_v2.t | 2 +-
t/v2writable.t | 4 +-
t/view.t | 2 +-
t/xcpdb-reshard.t | 14 +--
20 files changed, 188 insertions(+), 191 deletions(-)
rename lib/PublicInbox/{SearchIdxPart.pm => SearchIdxShard.pm} (78%)
--
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 --
2019-06-15 8:46 7% [PATCH 00/20] v2: use consistent terminology Eric Wong
2019-06-15 8:47 5% ` [PATCH 18/20] xapcmd: favor 'shard' over 'part' in local variables 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).