* [PATCH 07/30] qspawn: reduce local vars, de-anonymize rd_hdr
2019-12-25 7:50 6% [PATCH 00/30] www: eliminate most per-request closures Eric Wong
@ 2019-12-25 7:50 7% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2019-12-25 7:50 UTC (permalink / raw)
To: meta
rd_hdr() now becomes a named subroutine instead of a per-call
local variable, so kilobytes of memory will not have to be
allocated for it on every ->psgi_return call.
---
lib/PublicInbox/Qspawn.pm | 79 ++++++++++++++++++++-------------------
1 file changed, 40 insertions(+), 39 deletions(-)
diff --git a/lib/PublicInbox/Qspawn.pm b/lib/PublicInbox/Qspawn.pm
index 6cb28b9a..1985dccd 100644
--- a/lib/PublicInbox/Qspawn.pm
+++ b/lib/PublicInbox/Qspawn.pm
@@ -162,12 +162,11 @@ sub psgi_qx {
$self->{qx_arg} = $qx_arg;
$self->{qx_fh} = $qx_fh;
$self->{qx_buf} = \$qx_buf;
- my $rpipe; # comes from popen_rd
my $async = $env->{'pi-httpd.async'};
my $cb = sub {
my ($r, $buf);
reread:
- $r = sysread($rpipe, $buf, 65536);
+ $r = sysread($self->{rpipe}, $buf, 65536);
if ($async) {
$async->async_pass($env->{'psgix.io'}, $qx_fh, \$buf);
} elsif (defined $r) {
@@ -180,10 +179,9 @@ reread:
};
$limiter ||= $def_limiter ||= PublicInbox::Qspawn::Limiter->new(32);
$self->start($limiter, sub { # start_cb, may run later, much later...
- ($rpipe) = @_; # popen_rd result
if ($async) {
- # PublicInbox::HTTPD::Async->new($rpipe, $cb, $end_obj)
- $async = $async->($rpipe, $cb, undef, $self);
+ # PublicInbox::HTTPD::Async->new(rpipe, $cb, $end_obj)
+ $async = $async->($self->{rpipe}, $cb, undef, $self);
# $cb will call ->async_pass or ->close
} else { # generic PSGI
$cb->() while $self->{qx_fh};
@@ -215,6 +213,32 @@ sub event_step {
$fh->close if $fh; # async-only (psgi_return)
}
+sub rd_hdr ($) {
+ my ($self) = @_;
+ # typically used for reading CGI headers
+ # we must loop until EAGAIN for EPOLLET in HTTPD/Async.pm
+ # We also need to check EINTR for generic PSGI servers.
+ my $ret;
+ my $total_rd = 0;
+ my $hdr_buf = $self->{hdr_buf};
+ 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);
+ } else {
+ # caller should notify us when it's ready:
+ return if $! == EAGAIN;
+ next if $! == EINTR; # immediate retry
+ log_err($self->{psgi_env}, "error reading header: $!");
+ $ret = [ 500, [], [ "Internal error\n" ] ];
+ }
+ } until (defined $ret);
+ delete $self->{parse_hdr}; # done parsing headers
+ $ret;
+}
+
# Used for streaming the stdout of one process as a PSGI response.
#
# $env is the PSGI env.
@@ -240,43 +264,20 @@ sub event_step {
sub psgi_return {
my ($self, $env, $limiter, $parse_hdr) = @_;
$self->{psgi_env} = $env;
- my $rpipe;
- my $buf = '';
- my $rd_hdr = sub {
- # typically used for reading CGI headers
- # we must loop until EAGAIN for EPOLLET in HTTPD/Async.pm
- # We also need to check EINTR for generic PSGI servers.
- my $ret;
- my $total_rd = 0;
- do {
- my $r = sysread($rpipe, $buf, 4096, length($buf));
- if (defined($r)) {
- $total_rd += $r;
- $ret = $parse_hdr->($r ? $total_rd : 0, \$buf);
- } else {
- # caller should notify us when it's ready:
- return if $! == EAGAIN;
- next if $! == EINTR; # immediate retry
- log_err($env, "error reading header: $!");
- $ret = [ 500, [], [ "Internal error\n" ] ];
- }
- } until (defined $ret);
- $ret;
- };
-
+ $self->{hdr_buf} = \(my $hdr_buf = '');
+ $self->{parse_hdr} = $parse_hdr;
my $wcb = delete $env->{'qspawn.wcb'}; # or PSGI server supplies it
my $async = $env->{'pi-httpd.async'};
my $cb = sub {
- my $r = $rd_hdr->() or return;
- $rd_hdr = undef; # done reading headers
+ my $r = rd_hdr($self) or return;
my $filter = delete $env->{'qspawn.filter'};
if (scalar(@$r) == 3) { # error
if ($async) {
# calls rpipe->close && ->event_step
$async->close;
} else {
- $rpipe->close;
+ $self->{rpipe}->close;
event_step($self);
}
$wcb->($r);
@@ -285,12 +286,13 @@ sub psgi_return {
my $fh = $wcb->($r); # scalar @$r == 2
$fh = filter_fh($fh, $filter) if $filter;
$self->{fh} = $fh;
- $async->async_pass($env->{'psgix.io'}, $fh, \$buf);
+ $async->async_pass($env->{'psgix.io'}, $fh,
+ delete($self->{hdr_buf}));
} else { # for synchronous PSGI servers
require PublicInbox::GetlineBody;
- $r->[2] = PublicInbox::GetlineBody->new($rpipe,
+ $r->[2] = PublicInbox::GetlineBody->new($self->{rpipe},
\&event_step, $self,
- $buf, $filter);
+ ${$self->{hdr_buf}}, $filter);
$wcb->($r);
}
@@ -300,14 +302,13 @@ sub psgi_return {
};
$limiter ||= $def_limiter ||= PublicInbox::Qspawn::Limiter->new(32);
my $start_cb = sub { # may run later, much later...
- ($rpipe) = @_;
if ($async) {
- # PublicInbox::HTTPD::Async->new($rpipe, $cb, $cb_arg,
+ # PublicInbox::HTTPD::Async->new(rpipe, $cb, $cb_arg,
# $end_obj)
- $async = $async->($rpipe, $cb, undef, $self);
+ $async = $async->($self->{rpipe}, $cb, undef, $self);
# $cb will call ->async_pass or ->close
} else { # generic PSGI
- $cb->() while $rd_hdr;
+ $cb->() while $self->{parse_hdr};
}
};
^ permalink raw reply related [relevance 7%]
* [PATCH 00/30] www: eliminate most per-request closures
@ 2019-12-25 7:50 6% Eric Wong
2019-12-25 7:50 7% ` [PATCH 07/30] qspawn: reduce local vars, de-anonymize rd_hdr 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 6%]
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 6% [PATCH 00/30] www: eliminate most per-request closures Eric Wong
2019-12-25 7:50 7% ` [PATCH 07/30] qspawn: reduce local vars, de-anonymize rd_hdr 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).