From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 6/9] extsearchidx: checkpoint releases locks
Date: Tue, 15 Dec 2020 02:02:21 +0000 [thread overview]
Message-ID: <20201215020224.11739-7-e@80x24.org> (raw)
In-Reply-To: <20201215020224.11739-1-e@80x24.org>
--reindex can take many hours or days, ensure we release
locks according to --batch-size so automated fetch+index
jobs can write new data to indices while we update old data.
---
lib/PublicInbox/ExtSearchIdx.pm | 19 ++++++-------------
lib/PublicInbox/V2Writable.pm | 2 +-
2 files changed, 7 insertions(+), 14 deletions(-)
diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm
index f29a84e3..3b021a1b 100644
--- a/lib/PublicInbox/ExtSearchIdx.pm
+++ b/lib/PublicInbox/ExtSearchIdx.pm
@@ -404,7 +404,7 @@ sub _reindex_finalize ($$$) {
my $orig_smsg = $req->{orig_smsg} // die 'BUG: no {orig_smsg}';
my $docid = $smsg->{num} = $orig_smsg->{num};
$self->{oidx}->add_overview($eml, $smsg); # may rethread
- $self->{transact_bytes} += $smsg->{bytes};
+ check_batch_limit({ %$sync, new_smsg => $smsg });
if ($nr == 1) { # likely, all good
$self->idx_shard($docid)->shard_reindex_docid($docid);
return;
@@ -537,18 +537,8 @@ sub eidxq_process ($$) { # for reindexing
warn "E: #$docid does not exist in over\n";
}
$del->execute($docid);
+ ++${$sync->{nr}};
- my $cur = ++${$sync->{nr}};
-
- # shards flush on their own, just don't queue up too many
- # deletes
- if ($self->{transact_bytes} >= $self->{batch_bytes}) {
- $self->git->async_wait_all;
- $self->{oidx}->commit_lazy;
- $self->{oidx}->begin_lazy;
- $pr->("reindexed $cur/$tot\n") if $pr;
- $self->{transact_bytes} = 0;
- }
# this is only for SIGUSR1, shards do their own accounting:
reindex_checkpoint($self, $sync) if ${$sync->{need_checkpoint}};
}
@@ -709,7 +699,10 @@ sub eidx_sync { # main entry point
for my $ibx (@{$self->{ibx_list}}) {
$ibx->{-ibx_id} //= $self->{oidx}->ibx_id($ibx->eidx_key);
}
- eidx_reindex($self, $sync) if delete($opt->{reindex});
+ if (delete($opt->{reindex})) {
+ $sync->{checkpoint_unlocks} = 1;
+ eidx_reindex($self, $sync);
+ }
# don't use $_ here, it'll get clobbered by reindex_checkpoint
for my $ibx (@{$self->{ibx_list}}) {
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 572eb418..97dbf328 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -884,7 +884,7 @@ sub reindex_checkpoint ($$) {
my $mm_tmp = $sync->{mm_tmp};
$mm_tmp->atfork_prepare if $mm_tmp;
die 'BUG: {im} during reindex' if $self->{im};
- if ($self->{ibx_map}) {
+ if ($self->{ibx_map} && !$sync->{checkpoint_unlocks}) {
checkpoint($self, 1); # no need to release lock on pure index
} else {
$self->done; # release lock
next prev parent reply other threads:[~2020-12-15 2:02 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-11 3:37 [PATCH] extindex: preliminary --reindex support Eric Wong
2020-12-12 19:53 ` [PATCH 2/1] extindex: reindex: drop stale rows from over.sqlite3 Eric Wong
2020-12-15 2:02 ` [PATCH 0/9] extindex: --reindex support Eric Wong
2020-12-15 2:02 ` [PATCH 1/9] extindex: preliminary " Eric Wong
2020-12-15 2:02 ` [PATCH 2/9] extindex: delete stale messages from over.sqlite3 Eric Wong
2020-12-15 2:02 ` [PATCH 3/9] over: sort xref3 by xnum if ibx_id repeats Eric Wong
2020-12-15 2:02 ` [PATCH 4/9] extindex: support --rethread and content bifurcation Eric Wong
2020-12-15 2:02 ` [PATCH 5/9] extsearchidx: reindex works on Xapian, too Eric Wong
2020-12-15 2:02 ` Eric Wong [this message]
2020-12-15 2:02 ` [PATCH 7/9] extsearchidx: simplify reindex code paths Eric Wong
2020-12-15 2:02 ` [PATCH 8/9] extsearchidx: reindex releases over.sqlite3 handles properly Eric Wong
2020-12-15 2:02 ` [PATCH 9/9] searchidxshard: simplify newline elimination Eric Wong
2020-12-16 6:40 ` [PATCH 0/9] extindex: --reindex support Eric Wong
2020-12-16 23:04 ` [PATCH 10/9] extsearchidx: lock eidxq on full --reindex 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=20201215020224.11739-7-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).