* [PATCH 13/30] qspawn: psgi_return: allow non-anon parse_hdr callback
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
Callers can supply an arg to parse_hdr, now, eliminating the
need for closures to capture local variables.
---
lib/PublicInbox/Cgit.pm | 12 ++++----
lib/PublicInbox/GitHTTPBackend.pm | 12 ++++----
lib/PublicInbox/Qspawn.pm | 7 +++--
lib/PublicInbox/ViewVCS.pm | 48 +++++++++++++++++--------------
4 files changed, 44 insertions(+), 35 deletions(-)
diff --git a/lib/PublicInbox/Cgit.pm b/lib/PublicInbox/Cgit.pm
index 353f4162..094f146e 100644
--- a/lib/PublicInbox/Cgit.pm
+++ b/lib/PublicInbox/Cgit.pm
@@ -95,6 +95,12 @@ my @PASS_ENV = qw(
);
# XXX: cgit filters may care about more variables...
+sub cgit_parse_hdr { # {parse_hdr} for Qspawn
+ my ($r, $bref) = @_;
+ my $res = parse_cgi_headers($r, $bref) or return; # incomplete
+ $res;
+}
+
sub call {
my ($self, $env) = @_;
my $path_info = $env->{PATH_INFO};
@@ -123,11 +129,7 @@ sub call {
my $rdr = input_prepare($env) or return r(500);
my $qsp = PublicInbox::Qspawn->new($self->{cmd}, $cgi_env, $rdr);
my $limiter = $self->{pi_config}->limiter('-cgit');
- $qsp->psgi_return($env, $limiter, sub {
- my ($r, $bref) = @_;
- my $res = parse_cgi_headers($r, $bref) or return; # incomplete
- $res;
- });
+ $qsp->psgi_return($env, $limiter, \&cgit_parse_hdr);
}
1;
diff --git a/lib/PublicInbox/GitHTTPBackend.pm b/lib/PublicInbox/GitHTTPBackend.pm
index ec8e6516..537a1947 100644
--- a/lib/PublicInbox/GitHTTPBackend.pm
+++ b/lib/PublicInbox/GitHTTPBackend.pm
@@ -184,6 +184,12 @@ sub prepare_range {
($code, $len);
}
+sub git_parse_hdr { # {parse_hdr} for Qspawn
+ my ($r, $bref, $dumb_args) = @_;
+ my $res = parse_cgi_headers($r, $bref) or return; # incomplete
+ $res->[0] == 403 ? serve_dumb(@$dumb_args) : $res;
+}
+
# returns undef if 403 so it falls back to dumb HTTP
sub serve_smart {
my ($env, $git, $path) = @_;
@@ -204,11 +210,7 @@ sub serve_smart {
$env{PATH_TRANSLATED} = "$git->{git_dir}/$path";
my $rdr = input_prepare($env) or return r(500);
my $qsp = PublicInbox::Qspawn->new([qw(git http-backend)], \%env, $rdr);
- $qsp->psgi_return($env, $limiter, sub { # parse_hdr
- my ($r, $bref) = @_;
- my $res = parse_cgi_headers($r, $bref) or return; # incomplete
- $res->[0] == 403 ? serve_dumb($env, $git, $path) : $res;
- });
+ $qsp->psgi_return($env, $limiter, \&git_parse_hdr, [$env, $git, $path]);
}
sub input_prepare {
diff --git a/lib/PublicInbox/Qspawn.pm b/lib/PublicInbox/Qspawn.pm
index d1a34bea..1a2b70e7 100644
--- a/lib/PublicInbox/Qspawn.pm
+++ b/lib/PublicInbox/Qspawn.pm
@@ -215,12 +215,13 @@ sub rd_hdr ($) {
my $ret;
my $total_rd = 0;
my $hdr_buf = $self->{hdr_buf};
+ my ($ph_cb, $ph_arg) = @{$self->{parse_hdr}};
do {
my $r = sysread($self->{rpipe}, $$hdr_buf, 4096,
length($$hdr_buf));
if (defined($r)) {
$total_rd += $r;
- $ret = $self->{parse_hdr}->($total_rd, $hdr_buf);
+ $ret = $ph_cb->($total_rd, $hdr_buf, $ph_arg);
} else {
# caller should notify us when it's ready:
return if $! == EAGAIN;
@@ -298,10 +299,10 @@ sub psgi_return_start { # may run later, much later...
# psgix.io. 3-element arrays means the body is available
# immediately (or streamed via ->getline (pull-based)).
sub psgi_return {
- my ($self, $env, $limiter, $parse_hdr) = @_;
+ my ($self, $env, $limiter, $parse_hdr, $hdr_arg) = @_;
$self->{psgi_env} = $env;
$self->{hdr_buf} = \(my $hdr_buf = '');
- $self->{parse_hdr} = $parse_hdr;
+ $self->{parse_hdr} = [ $parse_hdr, $hdr_arg ];
$limiter ||= $def_limiter ||= PublicInbox::Qspawn::Limiter->new(32);
# the caller already captured the PSGI write callback from
diff --git a/lib/PublicInbox/ViewVCS.pm b/lib/PublicInbox/ViewVCS.pm
index 886e10cb..7618b198 100644
--- a/lib/PublicInbox/ViewVCS.pm
+++ b/lib/PublicInbox/ViewVCS.pm
@@ -42,35 +42,39 @@ sub html_page ($$$) {
$wcb ? $wcb->($res) : $res;
}
+sub stream_blob_parse_hdr { # {parse_hdr} for Qspawn
+ my ($r, $bref, $ctx) = @_;
+ my ($res, $logref) = delete @$ctx{qw(-res -logref)};
+ my ($git, $oid, $type, $size, $di) = @$res;
+ my @cl = ('Content-Length', $size);
+ if (!defined $r) { # error
+ html_page($ctx, 500, $logref);
+ } elsif (index($$bref, "\0") >= 0) {
+ [200, [qw(Content-Type application/octet-stream), @cl] ];
+ } else {
+ my $n = bytes::length($$bref);
+ if ($n >= $BIN_DETECT || $n == $size) {
+ return [200, [ 'Content-Type',
+ 'text/plain; charset=UTF-8', @cl ] ];
+ }
+ if ($r == 0) {
+ warn "premature EOF on $oid $$logref\n";
+ return html_page($ctx, 500, $logref);
+ }
+ undef; # bref keeps growing
+ }
+}
+
sub stream_large_blob ($$$$) {
my ($ctx, $res, $logref, $fn) = @_;
+ $ctx->{-logref} = $logref;
+ $ctx->{-res} = $res;
my ($git, $oid, $type, $size, $di) = @$res;
my $cmd = ['git', "--git-dir=$git->{git_dir}", 'cat-file', $type, $oid];
my $qsp = PublicInbox::Qspawn->new($cmd);
- my @cl = ('Content-Length', $size);
my $env = $ctx->{env};
- $env->{'public-inbox.tmpgit'} = $git; # for {-tmp}/File::Temp::Dir
$env->{'qspawn.wcb'} = delete $ctx->{-wcb};
- $qsp->psgi_return($env, undef, sub {
- my ($r, $bref) = @_;
- if (!defined $r) { # error
- html_page($ctx, 500, $logref);
- } elsif (index($$bref, "\0") >= 0) {
- my $ct = 'application/octet-stream';
- [200, ['Content-Type', $ct, @cl ] ];
- } else {
- my $n = bytes::length($$bref);
- if ($n >= $BIN_DETECT || $n == $size) {
- my $ct = 'text/plain; charset=UTF-8';
- return [200, ['Content-Type', $ct, @cl] ];
- }
- if ($r == 0) {
- warn "premature EOF on $oid $$logref\n";
- return html_page($ctx, 500, $logref);
- }
- undef; # bref keeps growing
- }
- });
+ $qsp->psgi_return($env, undef, \&stream_blob_parse_hdr, $ctx);
}
sub show_other_result ($$) {
^ 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 13/30] qspawn: psgi_return: allow non-anon parse_hdr 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 7:50 5% ` [PATCH 13/30] qspawn: psgi_return: allow non-anon parse_hdr 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).