* [PATCH 36/52] extsearchidx: sync updates
2020-10-27 7:54 7% [PATCH 00/52] detached external index: mostly Eric Wong
@ 2020-10-27 7:54 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-10-27 7:54 UTC (permalink / raw)
To: meta
A couple of more things to prepare us to run syncs on
both v1 and v2 inboxes.
---
lib/PublicInbox/ExtSearchIdx.pm | 26 ++++++++++++++++++++++----
1 file changed, 22 insertions(+), 4 deletions(-)
diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm
index 32c57188..790ee921 100644
--- a/lib/PublicInbox/ExtSearchIdx.pm
+++ b/lib/PublicInbox/ExtSearchIdx.pm
@@ -19,10 +19,12 @@ use v5.10.1;
use parent qw(PublicInbox::ExtSearch PublicInbox::Lock);
use Carp qw(croak carp);
use PublicInbox::Search;
-use PublicInbox::SearchIdx qw(crlf_adjust);
+use PublicInbox::SearchIdx qw(crlf_adjust prepare_stack);
use PublicInbox::OverIdx;
+use PublicInbox::MID qw(mids);
use PublicInbox::V2Writable;
use PublicInbox::InboxWritable;
+use PublicInbox::ContentHash qw(content_hash);
use PublicInbox::Eml;
use File::Spec;
@@ -54,6 +56,7 @@ sub new {
sub attach_inbox {
my ($self, $ibx) = @_;
+ $ibx = PublicInbox::InboxWritable->new($ibx);
my $key = $ibx->eidx_key;
if (!$ibx->over || !$ibx->mm) {
warn "W: skipping $key (unindexed)\n";
@@ -120,7 +123,7 @@ sub do_xpost ($$) {
}
# called by V2Writable::sync_prepare
-sub artnum_max { $_[0]->{oidx}->get_counter('eidx_docid') }
+sub artnum_max { $_[0]->{oidx}->eidx_max }
sub index_unseen ($) {
my ($req) = @_;
@@ -174,7 +177,7 @@ sub ck_existing { # git->cat_async callback
my $smsg = $req->{cur_smsg} or die 'BUG: {cur_smsg} missing';
return if is_bad_blob($oid, $type, $size, $smsg->{blob});
my $cur = PublicInbox::Eml->new($bref);
- if (content_digest($cur) eq $req->{chash}) {
+ if (content_hash($cur) eq $req->{chash}) {
push @{$req->{indexed}}, $smsg; # for do_xpost
} # else { index_unseen later }
do_step($req);
@@ -248,12 +251,13 @@ sub _sync_inbox ($$$) {
my $epoch_max;
defined($ibx->git_dir_latest(\$epoch_max)) or return;
$sync->{epoch_max} = $epoch_max;
- sync_prepare($self, $sync) or return;
+ sync_prepare($self, $sync) or return; # fills $sync->{todo}
} elsif ($v == 1) {
my $uv = $ibx->uidvalidity;
my $lc = $self->{oidx}->eidx_meta("lc-v1:$ekey//$uv");
my $stk = prepare_stack($sync, $lc ? "$lc..HEAD" : 'HEAD');
my $unit = { stack => $stk, git => $ibx->git };
+ push @{$sync->{todo}}, $unit;
} else {
warn "E: $ekey unsupported inbox version (v$v)\n";
return;
@@ -267,10 +271,23 @@ sub eidx_sync { # main entry point
$self->{oidx}->rethread_prepare($opt);
_sync_inbox($self, $opt, $_) for (@{$self->{ibx_list}});
+
$self->{oidx}->rethread_done($opt);
+
PublicInbox::V2Writable::done($self);
}
+sub update_last_commit {
+ my ($self, $sync, $unit, $latest_cmt) = @_;
+
+ my $ALL = $self->git;
+ # while (scalar(@{$ALL->{inflight_c}}) || scalar(@{$ALL->{inflight}})) {
+ # $ALL->check_async_wait;
+ # $ALL->cat_async_wait;
+ # }
+ # TODO
+}
+
sub idx_init { # similar to V2Writable
my ($self, $opt) = @_;
return if $self->{idx_shards};
@@ -315,5 +332,6 @@ no warnings 'once';
*index_todo = \&PublicInbox::V2Writable::index_todo;
*count_shards = \&PublicInbox::V2Writable::count_shards;
*atfork_child = \&PublicInbox::V2Writable::atfork_child;
+*idx_shard = \&PublicInbox::V2Writable::idx_shard;
1;
^ permalink raw reply related [relevance 5%]
* [PATCH 00/52] detached external index: mostly
@ 2020-10-27 7:54 7% Eric Wong
2020-10-27 7:54 5% ` [PATCH 36/52] extsearchidx: sync updates Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-10-27 7:54 UTC (permalink / raw)
To: meta
...and mostly wired up for WWW, but requires manual config
editing atm. Needs docs and tests, and IMAP support.
This will also form the basis of a mairix workalike client.
Not sure about the usability aspects, but I think this can
replace the need for per-inbox Xapian DBs and save a truckload
of disk space (and more importantly: cache space). Per-inbox
over.sqlite3 remains required for compatibility with NNTP/IMAP
and existing WWW code.
I don't know if the command-line tool is going to be called
public-inbox-eindex or public-inbox-extindex, but probably the
latter...
"xindex" could be confusing, and "eindex" rhymes with "reindex"
which could also be confusing. But I'm even more easily
confused than usual these days :x
Performance isn't great, it took 30+ hours to index my mirror of
lore on a SATA SSD, but the entire index is <200GB due to
deduplication between cross posts. -compact isn't working with
these indices, yet, but will sometime...
More changes on the way, still trying fix my brain and get
through this year...
Eric Wong (52):
doc/standards: add RFCs for URL schemes
search: hoist out _xdb_sharded for v2 inboxes
extsearch: start mocking out
searchidx: expose INDEXLEVELS as `our'
v2writable: add git method
v2writable: make OO calls to last_commit-related methods
search: xdb_sharded: make this a public method for ExtSearch
searchidx: introduce "xref3" concept
v2writable: prepare initialization for external indices
v2writable: hoist out write_alternates
searchidxshard: allow msgref to be undef
v2writable: idx_shard: simplify callers
v2writable: count_shards: allow working without {ibx}
overidx: introduce changes for external index
v2: some changes for ExtSearchIdx compatibility
inboxwritable: eidx_key for external index
v2writable: rename remaining "remote" terminology
v2writable: checkpoint: account for lack of {mm}
extsearchidx: initial implementation
searchidx: index eidx_key as a boolean term
searchidx: xref3 delete support
searchidxshard: special init for eidx
searchidx: put {ibx} into $sync state
searchidx: log2stack: simplify callers
v2writable: more generic sync setup code
v2writable: allow OO method references
v2writable: rename {v2w} field to {self}
v2writable: make *last_commits and sync_prepare OO methods
v2writable: move size check init to sync_prepare
extsearchidx: more compatibility with V2Writable callers
v2writable: reduce scope of epoch-aware code
extsearchidx: remove {unindex_range} field
v2writable: pass oid to uindex_oid
extsearchidx: sync unit updates
searchidx: export prepare_stack
extsearchidx: sync updates
searchidx: reduce inbox-dependency, wrap ->with_umask
searchidx: favor $sync->{ibx} (over $self->{ibx})
Makefile.PL: do not build manpage if POD is missing
script: add preliminary eindex implementation
index: eindex wiring
over: store xref3 data in over.sqlite3
searchidx: remove xref3 support for Xapian
t/extsearch.t: verify results and xref3 ordering
t/v2writable: remove pointless ->barrier call
extsearch: wire up smsg_eml
extsearchidx: handle edits
extsearch: wire up remaining Inbox-like methods for WWW
searchidx: ignore exceptions from ->remove_term
extsearchidx: set current_info in warning callbacks
extsearchidx: support --batch-size checkpoints
searchidxshard: make warnings with eidx_key less confusing
Documentation/standards.perl | 3 +
MANIFEST | 4 +
Makefile.PL | 16 +-
lib/PublicInbox/Config.pm | 12 +
lib/PublicInbox/ExtSearch.pm | 69 +++++
lib/PublicInbox/ExtSearchIdx.pm | 404 ++++++++++++++++++++++++++++++
lib/PublicInbox/Inbox.pm | 53 ++--
lib/PublicInbox/InboxWritable.pm | 23 ++
lib/PublicInbox/Over.pm | 19 ++
lib/PublicInbox/OverIdx.pm | 122 ++++++++-
lib/PublicInbox/Search.pm | 62 ++---
lib/PublicInbox/SearchIdx.pm | 135 +++++++---
lib/PublicInbox/SearchIdxShard.pm | 77 +++++-
lib/PublicInbox/V2Writable.pm | 310 ++++++++++++-----------
lib/PublicInbox/WWW.pm | 3 +-
lib/PublicInbox/Xapcmd.pm | 2 +-
script/public-inbox-eindex | 43 ++++
script/public-inbox-index | 3 +-
t/extsearch.t | 75 ++++++
t/over.t | 24 ++
t/search.t | 2 -
t/v2writable.t | 3 +-
22 files changed, 1204 insertions(+), 260 deletions(-)
create mode 100644 lib/PublicInbox/ExtSearch.pm
create mode 100644 lib/PublicInbox/ExtSearchIdx.pm
create mode 100644 script/public-inbox-eindex
create mode 100644 t/extsearch.t
^ 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 --
2020-10-27 7:54 7% [PATCH 00/52] detached external index: mostly Eric Wong
2020-10-27 7:54 5% ` [PATCH 36/52] extsearchidx: sync updates 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).