From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 31/52] v2writable: reduce scope of epoch-aware code
Date: Tue, 27 Oct 2020 07:54:32 +0000 [thread overview]
Message-ID: <20201027075453.19163-32-e@80x24.org> (raw)
In-Reply-To: <20201027075453.19163-1-e@80x24.org>
And clearly label it. We may try to reuse some of this for v1
indexing code paths.
---
lib/PublicInbox/V2Writable.pm | 72 +++++++++++++++++------------------
1 file changed, 35 insertions(+), 37 deletions(-)
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index d417b125..c8b01a3d 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -954,14 +954,14 @@ sub index_oid { # cat_async callback
# only update last_commit for $i on reindex iff newer than current
# $sync will be used by subclasses
sub update_last_commit {
- my ($self, $sync, $git, $i, $cmt) = @_;
- my $last = last_epoch_commit($self, $i);
- if (defined $last && is_ancestor($git, $last, $cmt)) {
+ my ($self, $sync, $unit, $cmt) = @_;
+ my $last = last_epoch_commit($self, $unit->{epoch});
+ if (defined $last && is_ancestor($unit->{git}, $last, $cmt)) {
my @cmd = (qw(rev-list --count), "$last..$cmt");
- chomp(my $n = $git->qx(@cmd));
+ chomp(my $n = $unit->{git}->qx(@cmd));
return if $n ne '' && $n == 0;
}
- last_epoch_commit($self, $i, $cmt);
+ last_epoch_commit($self, $unit->{epoch}, $cmt);
}
sub last_commits {
@@ -974,10 +974,11 @@ sub last_commits {
}
# returns a revision range for git-log(1)
-sub log_range ($$$$) {
- my ($sync, $git, $i, $tip) = @_;
+sub log_range ($$$) {
+ my ($sync, $unit, $tip) = @_;
my $opt = $sync->{-opt};
my $pr = $opt->{-progress} if (($opt->{verbose} || 0) > 1);
+ my $i = $unit->{epoch};
my $cur = $sync->{ranges}->[$i] or do {
$pr->("$i.git indexing all of $tip\n") if $pr;
return $tip; # all of it
@@ -991,9 +992,9 @@ sub log_range ($$$$) {
my $range = "$cur..$tip";
$pr->("$i.git checking contiguity... ") if $pr;
- if (is_ancestor($git, $cur, $tip)) { # common case
+ if (is_ancestor($unit->{git}, $cur, $tip)) { # common case
$pr->("OK\n") if $pr;
- my $n = $git->qx(qw(rev-list --count), $range);
+ my $n = $unit->{git}->qx(qw(rev-list --count), $range);
chomp($n);
if ($n == 0) {
$sync->{ranges}->[$i] = undef;
@@ -1005,9 +1006,9 @@ sub log_range ($$$$) {
$pr->("FAIL\n") if $pr;
warn <<"";
discontiguous range: $range
-Rewritten history? (in $git->{git_dir})
+Rewritten history? (in $unit->{git}->{git_dir})
- chomp(my $base = $git->qx('merge-base', $tip, $cur));
+ chomp(my $base = $unit->{git}->qx('merge-base', $tip, $cur));
if ($base) {
$range = "$base..$tip";
warn "found merge-base: $base\n"
@@ -1016,10 +1017,10 @@ Rewritten history? (in $git->{git_dir})
warn "discarding history at $cur\n";
}
warn <<"";
-reindexing $git->{git_dir} starting at
+reindexing $unit->{git}->{git_dir} starting at
$range
- $sync->{unindex_range}->{$i} = "$base..$cur";
+ $unit->{unindex_range} = "$base..$cur";
}
$range;
}
@@ -1045,13 +1046,14 @@ sub sync_prepare ($$) {
my $git_dir = $sync->{ibx}->git_dir_n($i);
-d $git_dir or next; # missing epochs are fine
my $git = PublicInbox::Git->new($git_dir);
+ my $unit = { git => $git, epoch => $i };
if ($reindex_heads) {
$head = $reindex_heads->[$i] or next;
}
chomp(my $tip = $git->qx(qw(rev-parse -q --verify), $head));
-
next if $?; # new repo
- my $range = log_range($sync, $git, $i, $tip) or next;
+
+ my $range = log_range($sync, $unit, $tip) or next;
# can't use 'rev-list --count' if we use --diff-filter
$pr->("$i.git counting $range ... ") if $pr;
# Don't bump num_highwater on --reindex by using {D}.
@@ -1062,7 +1064,8 @@ sub sync_prepare ($$) {
my $stk = log2stack($sync, $git, $range);
my $nr = $stk ? $stk->num_records : 0;
$pr->("$nr\n") if $pr;
- $sync->{stacks}->[$i] = $stk if $stk;
+ $unit->{stack} = $stk; # may be undef
+ unshift @{$sync->{todo}}, $unit;
$regen_max += $nr;
}
@@ -1136,14 +1139,14 @@ sub git { $_[0]->{ibx}->git }
# this is rare, it only happens when we get discontiguous history in
# a mirror because the source used -purge or -edit
-sub unindex_epoch ($$$$) {
- my ($self, $sync, $git, $unindex_range) = @_;
+sub unindex_todo ($$$) {
+ my ($self, $sync, $unit) = @_;
+ my $unindex_range = delete($unit->{unindex_range}) // return;
my $unindexed = $sync->{unindexed} //= {}; # $mid0 => $num
my $before = scalar keys %$unindexed;
# order does not matter, here:
- my @cmd = qw(log --raw -r
- --no-notes --no-color --no-abbrev --no-renames);
- my $fh = $git->popen(@cmd, $unindex_range);
+ my $fh = $unit->{git}->popen(qw(log --raw -r --no-notes --no-color
+ --no-abbrev --no-renames), $unindex_range);
local $sync->{in_unindex} = 1;
my $unindex_oid = $self->can('unindex_oid');
while (<$fh>) {
@@ -1158,7 +1161,8 @@ sub unindex_epoch ($$$$) {
return if $before == $after;
# ensure any blob can not longer be accessed via dumb HTTP
- PublicInbox::Import::run_die(['git', "--git-dir=$git->{git_dir}",
+ PublicInbox::Import::run_die(['git',
+ "--git-dir=$unit->{git}->{git_dir}",
qw(-c gc.reflogExpire=now gc --prune=all --quiet)]);
}
@@ -1206,22 +1210,17 @@ sub index_xap_step ($$$;$) {
}
}
-sub index_epoch ($$$) {
- my ($self, $sync, $i) = @_;
-
- my $git_dir = $sync->{ibx}->git_dir_n($i);
- -d $git_dir or return; # missing epochs are fine
- my $git = PublicInbox::Git->new($git_dir);
- if (my $unindex_range = delete $sync->{unindex_range}->{$i}) { # rare
- unindex_epoch($self, $sync, $git, $unindex_range);
- }
- defined(my $stk = $sync->{stacks}->[$i]) or return;
- $sync->{stacks}->[$i] = undef;
+sub index_todo ($$$) {
+ my ($self, $sync, $unit) = @_;
+ unindex_todo($self, $sync, $unit);
+ my $stk = delete($unit->{stack}) or return;
my $all = $self->git;
my $index_oid = $self->can('index_oid');
my $unindex_oid = $self->can('unindex_oid');
+ my ($pfx) = ($unit->{git}->{git_dir} =~ m!/([^/]+)\z!g);
+ $pfx //= $unit->{git}->{git_dir};
while (my ($f, $at, $ct, $oid) = $stk->pop_rec) {
- $self->{current_info} = "$i.git $oid";
+ $self->{current_info} = "$pfx $oid";
my $req = { %$sync, autime => $at, cotime => $ct, oid => $oid };
if ($f eq 'm') {
if ($sync->{max_size}) {
@@ -1237,7 +1236,7 @@ sub index_epoch ($$$) {
}
}
$all->async_wait_all;
- $self->update_last_commit($sync, $git, $i, $stk->{latest_cmt});
+ $self->update_last_commit($sync, $unit, $stk->{latest_cmt});
}
sub xapian_only {
@@ -1292,7 +1291,6 @@ sub index_sync {
$self->{oidx}->rethread_prepare($opt);
my $sync = {
need_checkpoint => \(my $bool = 0),
- unindex_range => {}, # EPOCH => oid_old..oid_new
reindex => $opt->{reindex},
-opt => $opt,
self => $self,
@@ -1316,7 +1314,7 @@ sub index_sync {
}
}
# work forwards through history
- index_epoch($self, $sync, $_) for (0..$epoch_max);
+ index_todo($self, $sync, $_) for @{$sync->{todo}};
$self->{oidx}->rethread_done($opt);
$self->done;
next prev parent reply other threads:[~2020-10-27 7:54 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-27 7:54 [PATCH 00/52] detached external index: mostly Eric Wong
2020-10-27 7:54 ` [PATCH 01/52] doc/standards: add RFCs for URL schemes Eric Wong
2020-11-05 7:54 ` [PATCH v2] " Eric Wong
2020-10-27 7:54 ` [PATCH 02/52] search: hoist out _xdb_sharded for v2 inboxes Eric Wong
2020-10-27 7:54 ` [PATCH 03/52] extsearch: start mocking out Eric Wong
2020-10-27 7:54 ` [PATCH 04/52] searchidx: expose INDEXLEVELS as `our' Eric Wong
2020-10-27 7:54 ` [PATCH 05/52] v2writable: add git method Eric Wong
2020-10-27 7:54 ` [PATCH 06/52] v2writable: make OO calls to last_commit-related methods Eric Wong
2020-10-27 7:54 ` [PATCH 07/52] search: xdb_sharded: make this a public method for ExtSearch Eric Wong
2020-10-27 7:54 ` [PATCH 08/52] searchidx: introduce "xref3" concept Eric Wong
2020-10-27 7:54 ` [PATCH 09/52] v2writable: prepare initialization for external indices Eric Wong
2020-10-27 7:54 ` [PATCH 10/52] v2writable: hoist out write_alternates Eric Wong
2020-10-27 7:54 ` [PATCH 11/52] searchidxshard: allow msgref to be undef Eric Wong
2020-10-27 7:54 ` [PATCH 12/52] v2writable: idx_shard: simplify callers Eric Wong
2020-10-27 7:54 ` [PATCH 13/52] v2writable: count_shards: allow working without {ibx} Eric Wong
2020-10-27 7:54 ` [PATCH 14/52] overidx: introduce changes for external index Eric Wong
2020-10-27 7:54 ` [PATCH 15/52] v2: some changes for ExtSearchIdx compatibility Eric Wong
2020-10-27 7:54 ` [PATCH 16/52] inboxwritable: eidx_key for external index Eric Wong
2020-10-27 7:54 ` [PATCH 17/52] v2writable: rename remaining "remote" terminology Eric Wong
2020-10-27 7:54 ` [PATCH 18/52] v2writable: checkpoint: account for lack of {mm} Eric Wong
2020-10-27 7:54 ` [PATCH 19/52] extsearchidx: initial implementation Eric Wong
2020-10-27 7:54 ` [PATCH 20/52] searchidx: index eidx_key as a boolean term Eric Wong
2020-10-27 7:54 ` [PATCH 21/52] searchidx: xref3 delete support Eric Wong
2020-10-27 7:54 ` [PATCH 22/52] searchidxshard: special init for eidx Eric Wong
2020-10-27 7:54 ` [PATCH 23/52] searchidx: put {ibx} into $sync state Eric Wong
2020-10-27 7:54 ` [PATCH 24/52] searchidx: log2stack: simplify callers Eric Wong
2020-10-27 7:54 ` [PATCH 25/52] v2writable: more generic sync setup code Eric Wong
2020-10-27 7:54 ` [PATCH 26/52] v2writable: allow OO method references Eric Wong
2020-10-27 7:54 ` [PATCH 27/52] v2writable: rename {v2w} field to {self} Eric Wong
2020-10-27 7:54 ` [PATCH 28/52] v2writable: make *last_commits and sync_prepare OO methods Eric Wong
2020-10-27 7:54 ` [PATCH 29/52] v2writable: move size check init to sync_prepare Eric Wong
2020-10-27 7:54 ` [PATCH 30/52] extsearchidx: more compatibility with V2Writable callers Eric Wong
2020-10-27 7:54 ` Eric Wong [this message]
2020-10-27 7:54 ` [PATCH 32/52] extsearchidx: remove {unindex_range} field Eric Wong
2020-10-27 7:54 ` [PATCH 33/52] v2writable: pass oid to uindex_oid Eric Wong
2020-10-27 7:54 ` [PATCH 34/52] extsearchidx: sync unit updates Eric Wong
2020-10-27 7:54 ` [PATCH 35/52] searchidx: export prepare_stack Eric Wong
2020-10-27 7:54 ` [PATCH 36/52] extsearchidx: sync updates Eric Wong
2020-10-27 7:54 ` [PATCH 37/52] searchidx: reduce inbox-dependency, wrap ->with_umask Eric Wong
2020-10-27 7:54 ` [PATCH 38/52] searchidx: favor $sync->{ibx} (over $self->{ibx}) Eric Wong
2020-10-27 7:54 ` [PATCH 39/52] Makefile.PL: do not build manpage if POD is missing Eric Wong
2020-10-27 7:54 ` [PATCH 40/52] script: add preliminary eindex implementation Eric Wong
2020-10-27 7:54 ` [PATCH 41/52] index: eindex wiring Eric Wong
2020-10-27 7:54 ` [PATCH 42/52] over: store xref3 data in over.sqlite3 Eric Wong
2020-10-27 7:54 ` [PATCH 43/52] searchidx: remove xref3 support for Xapian Eric Wong
2020-10-27 7:54 ` [PATCH 44/52] t/extsearch.t: verify results and xref3 ordering Eric Wong
2020-10-27 7:54 ` [PATCH 45/52] t/v2writable: remove pointless ->barrier call Eric Wong
2020-10-27 7:54 ` [PATCH 46/52] extsearch: wire up smsg_eml Eric Wong
2020-10-27 7:54 ` [PATCH 47/52] extsearchidx: handle edits Eric Wong
2020-10-27 7:54 ` [PATCH 48/52] extsearch: wire up remaining Inbox-like methods for WWW Eric Wong
2020-10-27 7:54 ` [PATCH 49/52] searchidx: ignore exceptions from ->remove_term Eric Wong
2020-10-27 7:54 ` [PATCH 50/52] extsearchidx: set current_info in warning callbacks Eric Wong
2020-10-27 7:54 ` [PATCH 51/52] extsearchidx: support --batch-size checkpoints Eric Wong
2020-11-03 9:08 ` Eric Wong
2020-10-27 7:54 ` [PATCH 52/52] searchidxshard: make warnings with eidx_key less confusing Eric Wong
2020-10-27 12:08 ` [PATCH 00/52] detached external index: mostly Konstantin Ryabitsev
2020-11-10 18:53 ` detached external index: performance note Eric Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://public-inbox.org/README
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201027075453.19163-32-e@80x24.org \
--to=e@80x24.org \
--cc=meta@public-inbox.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).