* [PATCH 30/30] search: retry_reopen passes user arg to callback
2019-12-25 7:50 7% [PATCH 00/30] www: eliminate most per-request closures Eric Wong
@ 2019-12-25 7:51 6% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2019-12-25 7:51 UTC (permalink / raw)
To: meta
This allows callers to pass named (not anonymous) subs.
Update all retry_reopen callers to use this feature, and
fix some places where we failed to use retry_reopen :x
---
lib/PublicInbox/ExtMsg.pm | 12 ++++++------
lib/PublicInbox/Mbox.pm | 7 +++----
lib/PublicInbox/Search.pm | 16 +++++++---------
lib/PublicInbox/SearchMsg.pm | 9 +++++----
lib/PublicInbox/SearchView.pm | 34 +++++++++++++++-------------------
5 files changed, 36 insertions(+), 42 deletions(-)
diff --git a/lib/PublicInbox/ExtMsg.pm b/lib/PublicInbox/ExtMsg.pm
index 0138d373..0f3e392d 100644
--- a/lib/PublicInbox/ExtMsg.pm
+++ b/lib/PublicInbox/ExtMsg.pm
@@ -29,6 +29,10 @@ our @EXT_URL = map { ascii_html($_) } (
sub PARTIAL_MAX () { 100 }
+sub mids_from_mset { # Search::retry_reopen callback
+ [ map { PublicInbox::SearchMsg::from_mitem($_)->mid } $_[0]->items ];
+}
+
sub search_partial ($$) {
my ($srch, $mid) = @_;
return if length($mid) < $MIN_PARTIAL_LEN;
@@ -65,12 +69,8 @@ sub search_partial ($$) {
# Search::Xapian::QueryParserError or even:
# "something terrible happened at ../Search/Xapian/Enquire.pm"
my $mset = eval { $srch->query($m, $opt) } or next;
-
- my @mids = map {
- my $doc = $_->get_document;
- PublicInbox::SearchMsg->load_doc($doc)->mid;
- } $mset->items;
- return \@mids if scalar(@mids);
+ my $mids = $srch->retry_reopen(\&mids_from_mset, $mset);
+ return $mids if scalar(@$mids);
}
}
diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 3fdda5ea..1f9ac6ec 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -12,6 +12,7 @@ use strict;
use warnings;
use PublicInbox::MID qw/mid_escape/;
use PublicInbox::Hval qw/to_filename/;
+use PublicInbox::SearchMsg;
use Email::Simple;
use Email::MIME::Encode;
@@ -204,10 +205,8 @@ sub results_cb {
my $srch = $ctx->{srch};
while (1) {
while (my $mi = (($mset->items)[$ctx->{iter}++])) {
- my $doc = $mi->get_document;
- my $smsg = $srch->retry_reopen(sub {
- PublicInbox::SearchMsg->load_doc($doc);
- }) or next;
+ my $smsg = PublicInbox::SearchMsg::from_mitem($mi,
+ $srch) or next;
return $smsg;
}
# refill result set
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 65c6ee83..eb1a1446 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -231,15 +231,15 @@ sub query {
}
sub retry_reopen {
- my ($self, $cb) = @_;
+ my ($self, $cb, $arg) = @_;
for my $i (1..10) {
if (wantarray) {
my @ret;
- eval { @ret = $cb->() };
+ eval { @ret = $cb->($arg) };
return @ret unless $@;
} else {
my $ret;
- eval { $ret = $cb->() };
+ eval { $ret = $cb->($arg) };
return $ret unless $@;
}
# Exception: The revision being read has been discarded -
@@ -259,11 +259,11 @@ sub retry_reopen {
sub _do_enquire {
my ($self, $query, $opts) = @_;
- retry_reopen($self, sub { _enquire_once($self, $query, $opts) });
+ retry_reopen($self, \&_enquire_once, [ $self, $query, $opts ]);
}
-sub _enquire_once {
- my ($self, $query, $opts) = @_;
+sub _enquire_once { # retry_reopen callback
+ my ($self, $query, $opts) = @{$_[0]};
my $xdb = xdb($self);
my $enquire = $X{Enquire}->new($xdb);
$enquire->set_query($query);
@@ -281,9 +281,7 @@ sub _enquire_once {
my $limit = $opts->{limit} || 50;
my $mset = $enquire->get_mset($offset, $limit);
return $mset if $opts->{mset};
- my @msgs = map {
- PublicInbox::SearchMsg->load_doc($_->get_document);
- } $mset->items;
+ my @msgs = map { PublicInbox::SearchMsg::from_mitem($_) } $mset->items;
return \@msgs unless wantarray;
($mset->get_matches_estimated, \@msgs)
diff --git a/lib/PublicInbox/SearchMsg.pm b/lib/PublicInbox/SearchMsg.pm
index 53882f73..ea54ba8a 100644
--- a/lib/PublicInbox/SearchMsg.pm
+++ b/lib/PublicInbox/SearchMsg.pm
@@ -92,10 +92,11 @@ sub psgi_cull ($) {
}
# Only called by PSGI interface, not NNTP
-sub load_doc {
- my ($class, $doc) = @_;
- my $self = bless {}, $class;
- psgi_cull(load_expand($self, $doc));
+sub from_mitem {
+ my ($mitem, $srch) = @_;
+ return $srch->retry_reopen(\&from_mitem, $mitem) if $srch;
+ my $self = bless {}, __PACKAGE__;
+ psgi_cull(load_expand($self, $mitem->get_document));
}
# :bytes and :lines metadata in RFC 3977
diff --git a/lib/PublicInbox/SearchView.pm b/lib/PublicInbox/SearchView.pm
index 8cffdedb..6587d37f 100644
--- a/lib/PublicInbox/SearchView.pm
+++ b/lib/PublicInbox/SearchView.pm
@@ -88,17 +88,6 @@ retry:
PublicInbox::WwwStream->response($ctx, $code, $cb);
}
-# allow undef for individual doc loads...
-sub load_doc_retry {
- my ($srch, $mitem) = @_;
-
- eval {
- $srch->retry_reopen(sub {
- PublicInbox::SearchMsg->load_doc($mitem->get_document)
- });
- }
-}
-
# display non-nested search results similar to what users expect from
# regular WWW search engines:
sub mset_summary {
@@ -114,7 +103,7 @@ sub mset_summary {
foreach my $m ($mset->items) {
my $rank = sprintf("%${pad}d", $m->get_rank + 1);
my $pct = get_pct($m);
- my $smsg = load_doc_retry($srch, $m);
+ my $smsg = PublicInbox::SearchMsg::from_mitem($m, $srch);
unless ($smsg) {
eval {
$m = "$m ".$m->get_docid . " expired\n";
@@ -270,14 +259,19 @@ sub get_pct ($) {
$n > 99 ? 99 : $n;
}
+sub load_msgs {
+ my ($mset) = @_;
+ [ map {
+ my $mi = $_;
+ my $smsg = PublicInbox::SearchMsg::from_mitem($mi);
+ $smsg->{pct} = get_pct($mi);
+ $smsg;
+ } ($mset->items) ]
+}
+
sub mset_thread {
my ($ctx, $mset, $q) = @_;
- my $msgs = $ctx->{-inbox}->search->retry_reopen(sub { [ map {
- my $i = $_;
- my $smsg = PublicInbox::SearchMsg->load_doc($i->get_document);
- $smsg->{pct} = get_pct($i);
- $smsg;
- } ($mset->items) ]});
+ my $msgs = $ctx->{-inbox}->search->retry_reopen(\&load_msgs, $mset);
my $r = $q->{r};
my $rootset = PublicInbox::SearchThread::thread($msgs,
$r ? \&sort_relevance : \&PublicInbox::View::sort_ds,
@@ -345,7 +339,9 @@ sub adump {
sub adump_i {
my ($ctx) = @_;
while (my $mi = shift @{$ctx->{items}}) {
- my $smsg = load_doc_retry($ctx->{srch}, $mi) or next;
+ my $smsg = eval {
+ PublicInbox::SearchMsg::from_mitem($mi, $ctx->{srch});
+ } or next;
$ctx->{-inbox}->smsg_mime($smsg) and return $smsg;
}
}
^ permalink raw reply related [relevance 6%]
* [PATCH 00/30] www: eliminate most per-request closures
@ 2019-12-25 7:50 7% Eric Wong
2019-12-25 7:51 6% ` [PATCH 30/30] search: retry_reopen passes user arg to callback Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2019-12-25 7:50 UTC (permalink / raw)
To: meta
Closures (aka "anonymous subs") tack several KB of memory onto
every WWW request/response, decreasing scalability and
performance of our WWW endpoints. They also increase human
review time to check for reference cycles.
Similar changes to -nntpd and the generic parts of -httpd were
also done recently:
https://public-inbox.org/meta/20191221235319.27082-1-e@80x24.org/
https://public-inbox.org/meta/20191221080007.27810-1-e@80x24.org/
These could still use some naming improvements, and it's been
pretty tiring writing the same-ish commit message over and over.
All these changes around eliminating closures also make it
easier to port our codebase to languages which lack closures.
Fwiw, I've been brainstorming ideas to create a new, refcounted
language where cyclic references are impossible by design. Such
a design would not be possible if closures were implemented; but
doable otherwise by taking a hint from *nix FSes.
Eric Wong (30):
git: allow async_cat to pass arg to callback
httpd/async: support passing arg to callbacks
qspawn: remove some anonymous subs for psgi_qx
qspawn: disambiguate command vs PSGI env
qspawn: replace anonymous $end callbacks w/ event_step
msg_iter: provide means to stop using anonymous subs
qspawn: reduce local vars, de-anonymize rd_hdr
httpd/async: get rid of ephemeral main_cb
qspawn: psgi_return: initial cb can be named
qspawn: psgi_return_start: hoist out from psgi_return
qspawn: psgi_qx: eliminate anonymous subs
qspawn: drop "qspawn.filter" support, for now
qspawn: psgi_return: allow non-anon parse_hdr callback
githttpbackend: split out wwwstatic
www: lazy load Plack::Util
mboxgz: pass $ctx to callback to avoid anon subs
feed: avoid anonymous subs
config: each_inbox: pass user arg to callback
view: avoid anon sub in stream_thread
view: msg_html: stop using an anonymous sub
contentid: no anonymous sub
wwwtext: avoid anonymous sub in response
searchview: pass named subs to Www*Stream
view: thread_html: pass named sub to WwwStream
searchview: remove anonymous sub when sorting threads by relevance
view: msg_iter calls add_body_text directly
wwwattach: avoid anonymous sub for msg_iter
viewvcs: avoid anonymous sub for HTML response
solvergit: allow passing arg to user-supplied callback
search: retry_reopen passes user arg to callback
MANIFEST | 1 +
lib/PublicInbox/Cgit.pm | 19 +-
lib/PublicInbox/Config.pm | 11 +-
lib/PublicInbox/ContentId.pm | 53 +++---
lib/PublicInbox/ExtMsg.pm | 58 +++---
lib/PublicInbox/Feed.pm | 51 +++--
lib/PublicInbox/GetlineBody.pm | 12 +-
lib/PublicInbox/Git.pm | 14 +-
lib/PublicInbox/GitHTTPBackend.pm | 99 +---------
lib/PublicInbox/HTTPD/Async.pm | 56 +++---
lib/PublicInbox/Mbox.pm | 131 +++++++------
lib/PublicInbox/MboxGz.pm | 2 +-
lib/PublicInbox/MsgIter.pm | 8 +-
lib/PublicInbox/NewsWWW.pm | 16 +-
lib/PublicInbox/Qspawn.pm | 296 +++++++++++++++---------------
lib/PublicInbox/Search.pm | 16 +-
lib/PublicInbox/SearchMsg.pm | 9 +-
lib/PublicInbox/SearchView.pm | 100 +++++-----
lib/PublicInbox/SolverGit.pm | 149 ++++++++-------
lib/PublicInbox/View.pm | 187 ++++++++++---------
lib/PublicInbox/ViewVCS.pm | 111 ++++++-----
lib/PublicInbox/WWW.pm | 2 +-
lib/PublicInbox/WwwAtomStream.pm | 2 +-
lib/PublicInbox/WwwAttach.pm | 49 ++---
lib/PublicInbox/WwwListing.pm | 37 ++--
lib/PublicInbox/WwwStatic.pm | 105 +++++++++++
lib/PublicInbox/WwwText.pm | 20 +-
t/git.t | 21 +++
t/qspawn.t | 19 +-
29 files changed, 882 insertions(+), 772 deletions(-)
create mode 100644 lib/PublicInbox/WwwStatic.pm
^ 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 --
2019-12-25 7:50 7% [PATCH 00/30] www: eliminate most per-request closures Eric Wong
2019-12-25 7:51 6% ` [PATCH 30/30] search: retry_reopen passes user arg to callback 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).