user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 15/43] mboxgz: reduce hash depth
Date: Sun,  5 Jul 2020 23:27:31 +0000	[thread overview]
Message-ID: <20200705232759.3161-16-e@yhbt.net> (raw)
In-Reply-To: <20200705232759.3161-1-e@yhbt.net>

We can bless $ctx directly into a MboxGz object to reduce
hash lookups and allocations.
---
 lib/PublicInbox/MboxGz.pm | 39 ++++++++++++++++-----------------------
 1 file changed, 16 insertions(+), 23 deletions(-)

diff --git a/lib/PublicInbox/MboxGz.pm b/lib/PublicInbox/MboxGz.pm
index 8c9010afb..598b10347 100644
--- a/lib/PublicInbox/MboxGz.pm
+++ b/lib/PublicInbox/MboxGz.pm
@@ -10,20 +10,10 @@ use PublicInbox::GitAsyncCat;
 *msg_hdr = \&PublicInbox::Mbox::msg_hdr;
 *msg_body = \&PublicInbox::Mbox::msg_body;
 
-sub new {
-	my ($class, $ctx, $cb) = @_;
-	$ctx->{base_url} = $ctx->{-inbox}->base_url($ctx->{env});
-	bless {
-		gz => PublicInbox::GzipFilter::gzip_or_die(),
-		cb => $cb,
-		ctx => $ctx
-	}, $class;
-}
-
 # this is public-inbox-httpd-specific
 sub mboxgz_blob_cb { # git->cat_async callback
 	my ($bref, $oid, $type, $size, $self) = @_;
-	my $http = $self->{ctx}->{env}->{'psgix.io'} or return; # client abort
+	my $http = $self->{env}->{'psgix.io'} or return; # client abort
 	my $smsg = delete $self->{smsg} or die 'BUG: no smsg';
 	if (!defined($oid)) {
 		# it's possible to have TOCTOU if an admin runs
@@ -32,7 +22,7 @@ sub mboxgz_blob_cb { # git->cat_async callback
 	} else {
 		$smsg->{blob} eq $oid or die "BUG: $smsg->{blob} != $oid";
 	}
-	$self->zmore(msg_hdr($self->{ctx},
+	$self->zmore(msg_hdr($self,
 				PublicInbox::Eml->new($bref)->header_obj,
 				$smsg->{mid}));
 
@@ -45,8 +35,8 @@ sub mboxgz_blob_cb { # git->cat_async callback
 # this is public-inbox-httpd-specific
 sub async_step ($) {
 	my ($self) = @_;
-	if (my $smsg = $self->{smsg} = $self->{cb}->($self->{ctx})) {
-		git_async_cat($self->{ctx}->{-inbox}->git, $smsg->{blob},
+	if (my $smsg = $self->{smsg} = $self->{cb}->($self)) {
+		git_async_cat($self->{-inbox}->git, $smsg->{blob},
 				\&mboxgz_blob_cb, $self);
 	} elsif (my $out = delete $self->{http_out}) {
 		$out->write($self->zflush);
@@ -64,17 +54,20 @@ sub async_next {
 sub close { !!delete($_[0]->{http_out}) }
 
 sub response {
-	my ($class, $ctx, $cb, $fn) = @_;
-	my $self = $class->new($ctx, $cb);
+	my ($class, $self, $cb, $fn) = @_;
+	$self->{base_url} = $self->{-inbox}->base_url($self->{env});
+	$self->{cb} = $cb;
+	$self->{gz} = PublicInbox::GzipFilter::gzip_or_die();
+	bless $self, $class;
 	# http://www.iana.org/assignments/media-types/application/gzip
 	$fn = defined($fn) && $fn ne '' ? to_filename($fn) : 'no-subject';
 	my $h = [ qw(Content-Type application/gzip),
 		'Content-Disposition', "inline; filename=$fn.mbox.gz" ];
-	if ($ctx->{env}->{'pi-httpd.async'}) {
+	if ($self->{env}->{'pi-httpd.async'}) {
 		sub {
 			my ($wcb) = @_; # -httpd provided write callback
 			$self->{http_out} = $wcb->([200, $h]);
-			$self->{ctx}->{env}->{'psgix.io'}->{forward} = $self;
+			$self->{env}->{'psgix.io'}->{forward} = $self;
 			async_step($self); # start stepping
 		};
 	} else { # generic PSGI
@@ -85,15 +78,15 @@ sub response {
 # called by Plack::Util::foreach or similar (generic PSGI)
 sub getline {
 	my ($self) = @_;
-	my $ctx = $self->{ctx} or return;
-	while (my $smsg = $self->{cb}->($ctx)) {
-		my $mref = $ctx->{-inbox}->msg_by_smsg($smsg) or next;
+	my $cb = $self->{cb} or return;
+	while (my $smsg = $cb->($self)) {
+		my $mref = $self->{-inbox}->msg_by_smsg($smsg) or next;
 		my $h = PublicInbox::Eml->new($mref)->header_obj;
-		$self->zmore(msg_hdr($ctx, $h, $smsg->{mid}));
+		$self->zmore(msg_hdr($self, $h, $smsg->{mid}));
 		return $self->translate(msg_body($$mref));
 	}
 	# signal that we're done and can return undef next call:
-	delete $self->{ctx};
+	delete $self->{cb};
 	$self->zflush;
 }
 

  parent reply	other threads:[~2020-07-05 23:28 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-05 23:27 [PATCH 00/43] www: async git cat-file w/ -httpd Eric Wong
2020-07-05 23:27 ` [PATCH 01/43] gzipfilter: minor cleanups Eric Wong
2020-07-05 23:27 ` [PATCH 02/43] wwwstream: oneshot: perform gzip without middleware Eric Wong
2020-07-05 23:27 ` [PATCH 03/43] www*stream: gzip ->getline responses Eric Wong
2020-07-05 23:27 ` [PATCH 04/43] wwwtext: gzip text/plain responses, as well Eric Wong
2020-07-05 23:27 ` [PATCH 05/43] wwwtext: switch to html_oneshot Eric Wong
2020-07-05 23:27 ` [PATCH 06/43] www: need: use WwwStream::html_oneshot Eric Wong
2020-07-05 23:27 ` [PATCH 07/43] wwwlisting: use GzipFilter for HTML Eric Wong
2020-07-05 23:27 ` [PATCH 08/43] gzipfilter: replace Compress::Raw::Deflate usages Eric Wong
2020-07-05 23:27 ` [PATCH 09/43] {gzip,noop}filter: ->zmore returns undef, always Eric Wong
2020-07-05 23:27 ` [PATCH 10/43] mbox: remove html_oneshot import Eric Wong
2020-07-05 23:27 ` [PATCH 11/43] wwwstatic: support gzipped directory listings Eric Wong
2020-07-05 23:27 ` [PATCH 12/43] qspawn: learn to gzip streaming responses Eric Wong
2020-07-05 23:27 ` [PATCH 13/43] stop auto-loading Plack::Middleware::Deflater Eric Wong
2020-07-05 23:27 ` [PATCH 14/43] mboxgz: do asynchronous git blob retrievals Eric Wong
2020-07-05 23:27 ` Eric Wong [this message]
2020-07-05 23:27 ` [PATCH 16/43] mbox: async blob fetch for "single message" raw mboxrd Eric Wong
2020-07-05 23:27 ` [PATCH 17/43] wwwatomstream: simplify feed_update callers Eric Wong
2020-07-05 23:27 ` [PATCH 18/43] wwwatomstream: use PublicInbox::Inbox->modified for feed_updated Eric Wong
2020-07-05 23:27 ` [PATCH 19/43] wwwatomstream: reuse $ctx as $self Eric Wong
2020-07-05 23:27 ` [PATCH 20/43] xt/httpd-async-stream: allow more options Eric Wong
2020-07-05 23:27 ` [PATCH 21/43] wwwatomstream: support async blob fetch Eric Wong
2020-07-05 23:27 ` [PATCH 22/43] wwwstream: reduce object graph depth Eric Wong
2020-07-05 23:27 ` [PATCH 23/43] wwwstream: reduce blob fetch paths for ->getline Eric Wong
2020-07-05 23:27 ` [PATCH 24/43] www: start making gzipfilter the parent response class Eric Wong
2020-07-05 23:27 ` [PATCH 25/43] remove unused/redundant zlib-related imports Eric Wong
2020-07-05 23:27 ` [PATCH 26/43] wwwstream: use parent.pm and no warnings Eric Wong
2020-07-05 23:27 ` [PATCH 27/43] wwwstream: subclass off GzipFilter Eric Wong
2020-07-05 23:27 ` [PATCH 28/43] view: make /$INBOX/$MSGID/ permalink async Eric Wong
2020-07-05 23:27 ` [PATCH 29/43] view: /$INBOX/$MSGID/t/ reads blobs asynchronously Eric Wong
2020-07-05 23:27 ` [PATCH 30/43] view: update /$INBOX/$MSGID/T/ to be async Eric Wong
2020-07-05 23:27 ` [PATCH 31/43] feed: generate_i: eliminate pointless loop Eric Wong
2020-07-05 23:27 ` [PATCH 32/43] feed: /$INBOX/new.html fetches blobs asynchronously Eric Wong
2020-07-05 23:27 ` [PATCH 33/43] ssearchview: /$INBOX/?q=$QUERY&x=t uses async blobs Eric Wong
2020-07-05 23:27 ` [PATCH 34/43] view: eml_entry: reduce parameters Eric Wong
2020-07-05 23:27 ` [PATCH 35/43] view: /$INBOX/$MSGID/t/: avoid extra hash lookup in eml case Eric Wong
2020-07-05 23:27 ` [PATCH 36/43] wwwstream: eliminate ::response, use html_oneshot Eric Wong
2020-07-05 23:27 ` [PATCH 37/43] www: update internal docs Eric Wong
2020-07-05 23:27 ` [PATCH 38/43] view: simplify eml_entry callers further Eric Wong
2020-07-05 23:27 ` [PATCH 39/43] wwwtext: simplify gzf_maybe use Eric Wong
2020-07-05 23:27 ` [PATCH 40/43] wwwattach: support async blob retrievals Eric Wong
2020-07-05 23:27 ` [PATCH 41/43] gzipfilter: drop HTTP connection on bugs or data corruption Eric Wong
2020-07-05 23:27 ` [PATCH 42/43] daemon: warn on missing blobs Eric Wong
2020-07-05 23:27 ` [PATCH 43/43] gzipfilter: check http->{forward} for client disconnects 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=20200705232759.3161-16-e@yhbt.net \
    --to=e@yhbt.net \
    --cc=meta@public-inbox.org \
    --subject='Re: [PATCH 15/43] mboxgz: reduce hash depth' \
    /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

user/dev discussion of public-inbox itself

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://public-inbox.org/meta
	git clone --mirror http://czquwvybam4bgbro.onion/meta
	git clone --mirror http://hjrcffqmbrq6wope.onion/meta
	git clone --mirror http://ou63pmih66umazou.onion/meta

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V1 meta meta/ https://public-inbox.org/meta \
		meta@public-inbox.org
	public-inbox-index meta

Example config snippet for mirrors.
Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://7fh6tueqddpjyxjmgtdiueylzoqt6pt7hec3pukyptlmohoowvhde4yd.onion/inbox.comp.mail.public-inbox.meta
	nntp://ie5yzdi7fg72h7s4sdcztq5evakq23rdt33mfyfcddc5u3ndnw24ogqd.onion/inbox.comp.mail.public-inbox.meta
	nntp://4uok3hntl7oi7b4uf4rtfwefqeexfzil2w6kgk2jn5z2f764irre7byd.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.io/gmane.mail.public-inbox.general
 note: .onion URLs require Tor: https://www.torproject.org/

code repositories for project(s) associated with this inbox:

	https://80x24.org/public-inbox.git

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git