* [PATCH 15/52] v2: some changes for ExtSearchIdx compatibility
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
We'll be using per-sync-state {ibx} refs instead, so make parts
of the v2 indexing code less-dependent on $self->{ibx} where
$self is a V2Writable object.
---
lib/PublicInbox/InboxWritable.pm | 21 ++++++++++++++
lib/PublicInbox/V2Writable.pm | 49 +++++++++++---------------------
lib/PublicInbox/Xapcmd.pm | 2 +-
3 files changed, 38 insertions(+), 34 deletions(-)
diff --git a/lib/PublicInbox/InboxWritable.pm b/lib/PublicInbox/InboxWritable.pm
index 752f1997..e97c7e2d 100644
--- a/lib/PublicInbox/InboxWritable.pm
+++ b/lib/PublicInbox/InboxWritable.pm
@@ -298,4 +298,25 @@ sub warn_ignore_cb {
}
}
+# v2+ only
+sub git_dir_n { "$_[0]->{inboxdir}/git/$_[1].git" }
+
+# v2+ only
+sub git_dir_latest {
+ my ($self, $max) = @_;
+ $$max = -1;
+ my $pfx = "$self->{inboxdir}/git";
+ return unless -d $pfx;
+ my $latest;
+ opendir my $dh, $pfx or die "opendir $pfx: $!\n";
+ while (defined(my $git_dir = readdir($dh))) {
+ $git_dir =~ m!\A([0-9]+)\.git\z! or next;
+ if ($1 > $$max) {
+ $$max = $1;
+ $latest = "$pfx/$git_dir";
+ }
+ }
+ $latest;
+}
+
1;
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 667a11f8..6af50f5d 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -120,7 +120,7 @@ sub init_inbox {
$self->idx_init;
$self->{mm}->skip_artnum($skip_artnum) if defined $skip_artnum;
my $epoch_max = -1;
- git_dir_latest($self, \$epoch_max);
+ $self->{ibx}->git_dir_latest(\$epoch_max);
if (defined $skip_epoch && $epoch_max == -1) {
$epoch_max = $skip_epoch;
}
@@ -320,12 +320,13 @@ sub idx_init {
sub _replace_oids ($$$) {
my ($self, $mime, $replace_map) = @_;
$self->done;
- my $pfx = "$self->{ibx}->{inboxdir}/git";
+ my $ibx = $self->{ibx};
+ my $pfx = "$ibx->{inboxdir}/git";
my $rewrites = []; # epoch => commit
my $max = $self->{epoch_max};
unless (defined($max)) {
- defined(my $latest = git_dir_latest($self, \$max)) or return;
+ defined(my $latest = $ibx->git_dir_latest(\$max)) or return;
$self->{epoch_max} = $max;
}
@@ -748,23 +749,6 @@ sub git_init {
$git_dir
}
-sub git_dir_latest {
- my ($self, $max) = @_;
- $$max = -1;
- my $pfx = "$self->{ibx}->{inboxdir}/git";
- return unless -d $pfx;
- my $latest;
- opendir my $dh, $pfx or die "opendir $pfx: $!\n";
- while (defined(my $git_dir = readdir($dh))) {
- $git_dir =~ m!\A([0-9]+)\.git\z! or next;
- if ($1 > $$max) {
- $$max = $1;
- $latest = "$pfx/$git_dir";
- }
- }
- $latest;
-}
-
sub importer {
my ($self) = @_;
my $im = $self->{im};
@@ -783,7 +767,7 @@ sub importer {
}
my $epoch = 0;
my $max;
- my $latest = git_dir_latest($self, \$max);
+ my $latest = $self->{ibx}->git_dir_latest(\$max);
if (defined $latest) {
my $git = PublicInbox::Git->new($latest);
my $packed_bytes = $git->packed_bytes;
@@ -977,8 +961,6 @@ sub update_last_commit {
last_epoch_commit($self, $i, $cmt);
}
-sub git_dir_n ($$) { "$_[0]->{ibx}->{inboxdir}/git/$_[1].git" }
-
sub last_commits ($$) {
my ($self, $epoch_max) = @_;
my $heads = [];
@@ -989,8 +971,8 @@ sub last_commits ($$) {
}
# returns a revision range for git-log(1)
-sub log_range ($$$$$) {
- my ($self, $sync, $git, $i, $tip) = @_;
+sub log_range ($$$$) {
+ my ($sync, $git, $i, $tip) = @_;
my $opt = $sync->{-opt};
my $pr = $opt->{-progress} if (($opt->{verbose} || 0) > 1);
my $cur = $sync->{ranges}->[$i] or do {
@@ -1043,14 +1025,14 @@ sub sync_prepare ($$$) {
my ($self, $sync, $epoch_max) = @_;
my $pr = $sync->{-opt}->{-progress};
my $regen_max = 0;
- my $head = $self->{ibx}->{ref_head} || 'HEAD';
+ my $head = $sync->{ibx}->{ref_head} || 'HEAD';
# reindex stops at the current heads and we later rerun index_sync
# without {reindex}
my $reindex_heads = $self->last_commits($epoch_max) if $sync->{reindex};
for (my $i = $epoch_max; $i >= 0; $i--) {
- my $git_dir = git_dir_n($self, $i);
+ 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);
if ($reindex_heads) {
@@ -1059,7 +1041,7 @@ sub sync_prepare ($$$) {
chomp(my $tip = $git->qx(qw(rev-parse -q --verify), $head));
next if $?; # new repo
- my $range = log_range($self, $sync, $git, $i, $tip) or next;
+ my $range = log_range($sync, $git, $i, $tip) or next;
# can't use 'rev-list --count' if we use --diff-filter
$pr->("$i.git counting $range ... ") if $pr;
# Don't bump num_highwater on --reindex by using {D}.
@@ -1067,7 +1049,7 @@ sub sync_prepare ($$$) {
# because we want NNTP article number gaps from unindexed
# messages to show up in mirrors, too.
$sync->{D} //= $sync->{reindex} ? {} : undef; # OID_BIN => NR
- my $stk = log2stack($sync, $git, $range, $self->{ibx});
+ my $stk = log2stack($sync, $git, $range, $sync->{ibx});
my $nr = $stk ? $stk->num_records : 0;
$pr->("$nr\n") if $pr;
$sync->{stacks}->[$i] = $stk if $stk;
@@ -1143,7 +1125,7 @@ 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 ($$$$) {
+sub unindex_epoch ($$$$) {
my ($self, $sync, $git, $unindex_range) = @_;
my $unindexed = $sync->{unindexed} //= {}; # $mid0 => $num
my $before = scalar keys %$unindexed;
@@ -1216,11 +1198,11 @@ sub index_xap_step ($$$;$) {
sub index_epoch ($$$) {
my ($self, $sync, $i) = @_;
- my $git_dir = git_dir_n($self, $i);
+ my $git_dir = $sync->{ibx}->git_dir_n($i);
-d $git_dir or return; # missing epochs are fine
my $git = PublicInbox::Git->new($git_dir);
if (my $unindex_range = delete $sync->{unindex_range}->{$i}) { # rare
- unindex($self, $sync, $git, $unindex_range);
+ unindex_epoch($self, $sync, $git, $unindex_range);
}
defined(my $stk = $sync->{stacks}->[$i]) or return;
$sync->{stacks}->[$i] = undef;
@@ -1284,7 +1266,7 @@ sub index_sync {
my $pr = $opt->{-progress};
my $epoch_max;
- my $latest = git_dir_latest($self, \$epoch_max);
+ my $latest = $self->{ibx}->git_dir_latest(\$epoch_max);
return unless defined $latest;
my $seq = $opt->{sequential_shard};
@@ -1301,6 +1283,7 @@ sub index_sync {
reindex => $opt->{reindex},
-opt => $opt,
v2w => $self,
+ ibx => $self->{ibx},
};
$sync->{ranges} = sync_ranges($self, $sync, $epoch_max);
if (sync_prepare($self, $sync, $epoch_max)) {
diff --git a/lib/PublicInbox/Xapcmd.pm b/lib/PublicInbox/Xapcmd.pm
index 6a74daf9..4332943c 100644
--- a/lib/PublicInbox/Xapcmd.pm
+++ b/lib/PublicInbox/Xapcmd.pm
@@ -110,7 +110,7 @@ sub prepare_reindex ($$$) {
}
} else { # v2
my $max;
- $im->git_dir_latest(\$max) or return;
+ $ibx->git_dir_latest(\$max) or return;
my $from = $opt->{reindex}->{from};
my $mm = $ibx->mm;
my $v = PublicInbox::Search::SCHEMA_VERSION();
^ 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 15/52] v2: some changes for ExtSearchIdx compatibility 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 15/52] v2: some changes for ExtSearchIdx compatibility 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).