* [PATCH 16/30] mboxgz: pass $ctx to callback to avoid anon subs
2019-12-25 7:50 7% [PATCH 00/30] www: eliminate most per-request closures Eric Wong
@ 2019-12-25 7:50 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2019-12-25 7:50 UTC (permalink / raw)
To: meta
Another place where we can rid ourselves of most anonymous subs
by passing the $ctx arg to the callback.
---
lib/PublicInbox/Mbox.pm | 132 +++++++++++++++++++++-----------------
lib/PublicInbox/MboxGz.pm | 2 +-
2 files changed, 73 insertions(+), 61 deletions(-)
diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index c50a118b..3fdda5ea 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -134,28 +134,30 @@ sub msg_body ($) {
$_[0] .= "\n";
}
+sub thread_cb {
+ my ($ctx) = @_;
+ my $msgs = $ctx->{msgs};
+ while (1) {
+ if (my $smsg = shift @$msgs) {
+ return $smsg;
+ }
+ # refill result set
+ $ctx->{msgs} = $msgs = $ctx->{over}->get_thread($ctx->{mid},
+ $ctx->{prev});
+ return unless @$msgs;
+ $ctx->{prev} = $msgs->[-1];
+ }
+}
+
sub thread_mbox {
my ($ctx, $over, $sfx) = @_;
eval { require PublicInbox::MboxGz };
- return sub { need_gzip(@_) } if $@;
- my $mid = $ctx->{mid};
- my $msgs = $over->get_thread($mid, {});
+ return need_gzip() if $@;
+ my $msgs = $ctx->{msgs} = $over->get_thread($ctx->{mid}, {});
return [404, [qw(Content-Type text/plain)], []] if !@$msgs;
- my $prev = $msgs->[-1];
- my $i = 0;
- my $cb = sub {
- while (1) {
- if (my $smsg = $msgs->[$i++]) {
- return $smsg;
- }
- # refill result set
- $msgs = $over->get_thread($mid, $prev);
- return unless @$msgs;
- $prev = $msgs->[-1];
- $i = 0;
- }
- };
- PublicInbox::MboxGz->response($ctx, $cb, $msgs->[0]->subject);
+ $ctx->{prev} = $msgs->[-1];
+ $ctx->{over} = $over; # bump refcnt
+ PublicInbox::MboxGz->response($ctx, \&thread_cb, $msgs->[0]->subject);
}
sub emit_range {
@@ -170,72 +172,82 @@ sub emit_range {
mbox_all($ctx, $query);
}
+sub all_ids_cb {
+ my ($ctx) = @_;
+ my $ids = $ctx->{ids};
+ do {
+ while ((my $num = shift @$ids)) {
+ my $smsg = $ctx->{over}->get_art($num) or next;
+ return $smsg;
+ }
+ $ctx->{ids} = $ids = $ctx->{mm}->ids_after(\($ctx->{prev}));
+ } while (@$ids);
+}
+
sub mbox_all_ids {
my ($ctx) = @_;
- my $prev = 0;
my $ibx = $ctx->{-inbox};
- my $ids = $ibx->mm->ids_after(\$prev) or return
+ my $prev = 0;
+ my $mm = $ctx->{mm} = $ibx->mm;
+ my $ids = $mm->ids_after(\$prev) or return
[404, [qw(Content-Type text/plain)], ["No results found\n"]];
- my $i = 0;
- my $over = $ibx->over or
+ $ctx->{over} = $ibx->over or
return PublicInbox::WWW::need($ctx, 'Overview');
- my $cb = sub {
- do {
- while ((my $num = $ids->[$i++])) {
- my $smsg = $over->get_art($num) or next;
- return $smsg;
- }
- $ids = $ibx->mm->ids_after(\$prev);
- $i = 0;
- } while (@$ids);
- undef;
- };
- return PublicInbox::MboxGz->response($ctx, $cb, 'all');
+ $ctx->{ids} = $ids;
+ $ctx->{prev} = $prev;
+ return PublicInbox::MboxGz->response($ctx, \&all_ids_cb, 'all');
+}
+
+sub results_cb {
+ my ($ctx) = @_;
+ my $mset = $ctx->{mset};
+ 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;
+ return $smsg;
+ }
+ # refill result set
+ $mset = $ctx->{mset} = $srch->query($ctx->{query},
+ $ctx->{qopts});
+ my $size = $mset->size or return;
+ $ctx->{qopts}->{offset} += $size;
+ $ctx->{iter} = 0;
+ }
}
sub mbox_all {
my ($ctx, $query) = @_;
eval { require PublicInbox::MboxGz };
- return sub { need_gzip(@_) } if $@;
+ return need_gzip() if $@;
return mbox_all_ids($ctx) if $query eq '';
- my $opts = { mset => 2 };
- my $srch = $ctx->{-inbox}->search or
+ my $qopts = $ctx->{qopts} = { mset => 2 };
+ my $srch = $ctx->{srch} = $ctx->{-inbox}->search or
return PublicInbox::WWW::need($ctx, 'Search');;
- my $mset = $srch->query($query, $opts);
- $opts->{offset} = $mset->size or
+ my $mset = $ctx->{mset} = $srch->query($query, $qopts);
+ $qopts->{offset} = $mset->size or
return [404, [qw(Content-Type text/plain)],
["No results found\n"]];
- my $i = 0;
- my $cb = sub { # called by MboxGz->getline
- while (1) {
- while (my $mi = (($mset->items)[$i++])) {
- my $doc = $mi->get_document;
- my $smsg = $srch->retry_reopen(sub {
- PublicInbox::SearchMsg->load_doc($doc);
- }) or next;
- return $smsg;
- }
- # refill result set
- $mset = $srch->query($query, $opts);
- my $size = $mset->size or return;
- $opts->{offset} += $size;
- $i = 0;
- }
- };
- PublicInbox::MboxGz->response($ctx, $cb, 'results-'.$query);
+ $ctx->{iter} = 0;
+ $ctx->{query} = $query;
+ PublicInbox::MboxGz->response($ctx, \&results_cb, 'results-'.$query);
}
sub need_gzip {
- my $fh = $_[0]->([501, ['Content-Type' => 'text/html']]);
my $title = 'gzipped mbox not available';
- $fh->write(<<EOF);
+ my $body = <<EOF;
<html><head><title>$title</title><body><pre>$title
The administrator needs to install the Compress::Raw::Zlib Perl module
to support gzipped mboxes.
<a href="../">Return to index</a></pre></body></html>
EOF
- $fh->close;
+
+ [501,[qw(Content-Type text/html Content-Length), bytes::length($body)],
+ [ $body ] ];
}
1;
diff --git a/lib/PublicInbox/MboxGz.pm b/lib/PublicInbox/MboxGz.pm
index ef560426..2b873451 100644
--- a/lib/PublicInbox/MboxGz.pm
+++ b/lib/PublicInbox/MboxGz.pm
@@ -42,7 +42,7 @@ sub getline {
my $ctx = $self->{ctx} or return;
my $gz = $self->{gz};
my $buf = delete($self->{buf});
- while (my $smsg = $self->{cb}->()) {
+ while (my $smsg = $self->{cb}->($ctx)) {
my $mref = $ctx->{-inbox}->msg_by_smsg($smsg) or next;
my $h = Email::Simple->new($mref)->header_obj;
^ permalink raw reply related [relevance 5%]
* [PATCH 00/30] www: eliminate most per-request closures
@ 2019-12-25 7:50 7% Eric Wong
2019-12-25 7:50 5% ` [PATCH 16/30] mboxgz: pass $ctx to callback to avoid anon subs 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 7:50 5% ` [PATCH 16/30] mboxgz: pass $ctx to callback to avoid anon subs 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).