* [PATCH 26/38] www: drop {obuf} use entirely, for now
2022-09-10 8:16 7% [PATCH 00/38] www: reduce memory usage Eric Wong
@ 2022-09-10 8:17 6% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2022-09-10 8:17 UTC (permalink / raw)
To: meta
This may help us identify hot spots and reduce pad space
as needed.
---
lib/PublicInbox/GzipFilter.pm | 13 ++++++-------
lib/PublicInbox/View.pm | 21 ++++++++-------------
lib/PublicInbox/ViewVCS.pm | 3 ++-
lib/PublicInbox/WwwAtomStream.pm | 8 ++++----
4 files changed, 20 insertions(+), 25 deletions(-)
diff --git a/lib/PublicInbox/GzipFilter.pm b/lib/PublicInbox/GzipFilter.pm
index 77d570b6..eb0046ce 100644
--- a/lib/PublicInbox/GzipFilter.pm
+++ b/lib/PublicInbox/GzipFilter.pm
@@ -130,11 +130,11 @@ sub write {
# similar to ->translate; use this when we're sure we know we have
# more data to buffer after this
sub zmore {
- my $self = $_[0]; # $_[1] => input
+ my $self = shift; # $_[1] => input
http_out($self);
my $err;
- for (delete $self->{obuf}, @_[1..$#_]) {
- $err = $self->{gz}->deflate($_ // next, $self->{zbuf});
+ for (@_) {
+ $err = $self->{gz}->deflate($_, $self->{zbuf});
die "gzip->deflate: $err" if $err != Z_OK;
}
undef;
@@ -142,13 +142,12 @@ sub zmore {
# flushes and returns the final bit of gzipped data
sub zflush ($;@) {
- my $self = $_[0]; # $_[1..Inf] => final input (optional)
+ my $self = shift; # $_[1..Inf] => final input (optional)
my $zbuf = delete $self->{zbuf};
my $gz = delete $self->{gz};
my $err;
- # it's a bug iff $gz is undef w/ $obuf or $_[1..]
- for (delete $self->{obuf}, @_[1..$#_]) {
- $err = $gz->deflate($_ // next, $zbuf);
+ for (@_) { # it's a bug iff $gz is undef if @_ isn't empty, here:
+ $err = $gz->deflate($_, $zbuf);
die "gzip->deflate: $err" if $err != Z_OK;
}
$gz // return ''; # not a bug, recursing on DS->write failure
diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index 3dbf8bac..630f1e42 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -43,7 +43,7 @@ sub msg_page_i {
$ctx->zmore('</pre><hr>');
}
html_footer($ctx, $ctx->{first_hdr}) if !$ctx->{smsg};
- delete($ctx->{obuf}) // \'';
+ \''; # XXX TODO cleanup
} else { # called by WwwStream::async_next or getline
$ctx->{smsg}; # may be undef
}
@@ -245,9 +245,8 @@ sub eml_entry {
# scan through all parts, looking for displayable text
$ctx->{mhref} = $mhref;
$ctx->{changed_href} = "#e$id"; # for diffstat "files? changed,"
- $ctx->{obuf} = \$rv;
+ $ctx->zmore($rv); # XXX $rv is small, reuse below
$eml->each_part(\&add_text_body, $ctx, 1); # expensive
- $ctx->zmore; # TODO: remove once add_text_body is updated
# add the footer
$rv = "\n<a\nhref=#$id_m\nid=e$id>^</a> ".
@@ -560,13 +559,9 @@ sub add_text_body { # callback for each_part
my ($part, $depth, $idx) = @$p;
my $ct = $part->content_type || 'text/plain';
my $fn = $part->filename;
- my $rv = $ctx->{obuf} //= \(my $obuf = '');
my ($s, $err) = msg_part_text($part, $ct);
- $s // return $$rv .= (attach_link($ctx, $ct, $p, $fn) // '');
- if ($part->{is_submsg}) {
- $$rv .= submsg_hdr($ctx, $part);
- $$rv .= "\n";
- }
+ $s // return $ctx->zmore(attach_link($ctx, $ct, $p, $fn) // '');
+ my $buf = $part->{is_submsg} ? submsg_hdr($ctx, $part)."\n" : '';
# makes no difference to browsers, and don't screw up filename
# link generation in diffs with the extra '%0D'
@@ -614,10 +609,11 @@ sub add_text_body { # callback for each_part
undef $s; # free memory
if (defined($fn) || ($depth > 0 && !$part->{is_submsg}) || $err) {
# badly-encoded message with $err? tell the world about it!
- $$rv .= attach_link($ctx, $ct, $p, $fn, $err);
- $$rv .= "\n";
+ $buf .= attach_link($ctx, $ct, $p, $fn, $err) . "\n";
}
delete $part->{bdy}; # save memory
+ $ctx->zmore($buf);
+ undef $buf;
for my $cur (@sections) { # $cur may be huge
if ($cur =~ /\A>/) {
# we use a <span> here to allow users to specify
@@ -722,7 +718,6 @@ sub _msg_page_prepare {
}
$ctx->{-linkify}->linkify_mids('..', \$hbuf); # escapes HTML
$ctx->zmore($hbuf .= "\n");
- ${$ctx->{obuf}} = ''; # TODO remove
1;
}
@@ -842,7 +837,7 @@ EOF
$foot .= qq(<a\nhref="#R">reply</a>);
# $skel may be big for big threads, don't append it to $foot
$skel .= '</pre>' . ($related // '');
- $ctx->zmore($foot, $skel .= msg_reply($ctx, $hdr)); # flushes obuf
+ $ctx->zmore($foot, $skel .= msg_reply($ctx, $hdr));
}
sub ghost_parent {
diff --git a/lib/PublicInbox/ViewVCS.pm b/lib/PublicInbox/ViewVCS.pm
index d3ac1a7d..57ab378d 100644
--- a/lib/PublicInbox/ViewVCS.pm
+++ b/lib/PublicInbox/ViewVCS.pm
@@ -205,7 +205,8 @@ EOM
$ctx->zmore("---\n patch is too large to show\n");
} else { # prepare flush_diff:
read($fh, $x, -s _);
- $ctx->{obuf} = \$bdy;
+ $ctx->zmore($bdy);
+ undef $bdy;
$ctx->{-apfx} = $ctx->{-spfx} = $upfx;
$x =~ s/\r?\n/\n/gs;
$ctx->{-anchors} = {} if $x =~ /^diff --git /sm;
diff --git a/lib/PublicInbox/WwwAtomStream.pm b/lib/PublicInbox/WwwAtomStream.pm
index 09c79a8a..cdfbf393 100644
--- a/lib/PublicInbox/WwwAtomStream.pm
+++ b/lib/PublicInbox/WwwAtomStream.pm
@@ -146,15 +146,15 @@ sub feed_entry {
my $name = ascii_html(join(', ', PublicInbox::Address::names($from)));
$email = ascii_html($email // $ctx->{ibx}->{-primary_address});
- my $s = delete($ctx->{emit_header}) ? atom_header($ctx, $title) : '';
- $s .= "<entry><author><name>$name</name><email>$email</email>" .
+ $ctx->zmore(
+ (delete($ctx->{emit_header}) ? atom_header($ctx, $title) : '').
+ "<entry><author><name>$name</name><email>$email</email>" .
"</author>$title$updated" .
qq(<link\nhref="$href"/>).
"<id>$uuid</id>$irt" .
qq{<content\ntype="xhtml">} .
qq{<div\nxmlns="http://www.w3.org/1999/xhtml">} .
- qq(<pre\nstyle="white-space:pre-wrap">);
- $ctx->{obuf} = \$s;
+ qq(<pre\nstyle="white-space:pre-wrap">));
$ctx->{mhref} = $href;
$ctx->{changed_href} = "${href}#related";
$eml->each_part(\&PublicInbox::View::add_text_body, $ctx, 1);
^ permalink raw reply related [relevance 6%]
* [PATCH 00/38] www: reduce memory usage
@ 2022-09-10 8:16 7% Eric Wong
2022-09-10 8:17 6% ` [PATCH 26/38] www: drop {obuf} use entirely, for now Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2022-09-10 8:16 UTC (permalink / raw)
To: meta
I'm over the moon with this series since this drops dozens of
megabytes of scratchpad use while providing tiny speedups along
the way. For me, that's a 10-15% reduction in memory use under
public-inbox-netd w/ mwrap-perl[1] overhead.
This scratchpad use has been bothering me for a long time
(since I fixed all the other leaks, including one in the core
Encode module).
There's more coming, of course, but this series is big enough
and shown good results on https://yhbt.net/lore/
Also, it also provides a good pattern/guidance going forward
on how to efficiently implement future features.
I actually started out in this series trying to buffer
everything using gzip to avoid space-wasting uncompressed
strings living in memory. Unfortunately,
Compress::Raw::Zlib::deflate calls proved too expensive to call
frequently for short strings.
Going back to `.=' ops via a ->zadd method brought back some of
the speed while consolidating the scratchpad to a single place;
but I didn't like the performance regression.
I kept those detours in the history presented here since I
figure it's worth showing
Finally relying on PerlIO::scalar with print|say ops proved to
be the fastest since OO ->method dispatch overhead can be avoided
and there's no scratchpad use at all from these, either.
As before, we still call C:R:Z:deflate after every full message
and flush to the socket periodically.
I may even consider using PerlIO::gzip in the future, but that's
a non-standard module. However, I definitely took inspiration
from it since I saw that it would buffer uncompressed data into
memory before compressing it.
There's also a few small simplifications and speedups I noticed
along the way, and several other bugfixes I posted independently
while working on this series.
[1] I used https://80x24.org/mwrap-perl.git to check malloc use
Eric Wong (38):
xt: fold perf-obfuscate into perf-msgview, future-proof
www: gzip_filter: implicitly flush {obuf} on zmore/zflush
view: rework single message page to compress earlier
www_atom_stream: require 200 response
www_stream: aresponse assumes 200, too
www_text: reduce parameter passing for response header
viewvcs: use shorter and simpler ctx->html_done
www_listing: consolidate some ->zmore dispatches
www_listing: avoid unnecessary work for common cases
www: viewdiff: use return value for diff_hunk
view: simplify _parent_headers
view: eml_entry: reduce manipulation of ctx->{obuf}
gzip_filter: ->translate can reuse zmore/zflush
view: remove multipart_text_as_html
view: reduce subroutine calls for submsg_hdr
view: attach_link: reduce obuf manipulation
viewdiff: reuse existing string in diff_before_or_after
view: _th_index_lite: avoid one s///, improve symmetry
view: _th_index_lite: use `//' defined-or op
view: reduce ascii_html calls and {obuf} use
view: html_footer: golf out a few lines
view: html_footer: remove obuf dependency
view: html_footer: avoid escaping " in a few places
viewdiff: diff_hunk: shorten conditionals, slightly
view: switch a few things to ctx->zmore
www: drop {obuf} use entirely, for now
www: switch to zadd for the majority of buffering
www: use PerlIO::scalar (zfh) for buffering
viewdiff: diff_before_or_after: avoid extra capture
viewdiff: diff_header: shorten function, slightly
www_static: switch to `print $zfh', and optimize
httpd/async: describe which ->write subs it can call
translate: support multiple buffer args
gzip_filter: write: use multi-arg translate
feed: new_html_i: switch from zmore to `print $zfh'
mbox*: use multi-arg ->translate and ->write
www_listing: switch to `print $zfh'
viewvcs: switch to `print $zfh'
Documentation/mknews.perl | 3 +-
MANIFEST | 1 -
lib/PublicInbox/CompressNoop.pm | 4 +-
lib/PublicInbox/Feed.pm | 12 +-
lib/PublicInbox/GzipFilter.pm | 62 +++---
lib/PublicInbox/HTTPD/Async.pm | 9 +-
lib/PublicInbox/Mbox.pm | 11 +-
lib/PublicInbox/MboxGz.pm | 3 +-
lib/PublicInbox/SearchView.pm | 8 +-
lib/PublicInbox/View.pm | 312 ++++++++++++-------------------
lib/PublicInbox/ViewDiff.pm | 115 +++++-------
lib/PublicInbox/ViewVCS.pm | 17 +-
lib/PublicInbox/WwwAtomStream.pm | 19 +-
lib/PublicInbox/WwwListing.pm | 40 ++--
lib/PublicInbox/WwwStatic.pm | 32 ++--
lib/PublicInbox/WwwStream.pm | 23 ++-
lib/PublicInbox/WwwText.pm | 35 ++--
t/psgi_v2.t | 4 +-
xt/perf-msgview.t | 10 +-
xt/perf-obfuscate.t | 66 -------
20 files changed, 320 insertions(+), 466 deletions(-)
delete mode 100644 xt/perf-obfuscate.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 --
2022-09-10 8:16 7% [PATCH 00/38] www: reduce memory usage Eric Wong
2022-09-10 8:17 6% ` [PATCH 26/38] www: drop {obuf} use entirely, for now 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).