* [PATCH 07/36] lei_to_mail: start atomic and compressed mbox writing
2020-12-31 13:51 7% [PATCH 00/36] another round of lei stuff Eric Wong
@ 2020-12-31 13:51 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-12-31 13:51 UTC (permalink / raw)
To: meta
We'll allow using multiple workers to write to a single
mbox (which could be compressed). This is can be done
safely with O_APPEND + syswrite for uncompressed files,
and using a lock when piping to pigz/gzip/bzip2/xz.
---
lib/PublicInbox/LeiToMail.pm | 99 ++++++++++++++++++++++++++++++++--
lib/PublicInbox/ProcessPipe.pm | 21 ++++++--
t/lei_to_mail.t | 47 ++++++++++++++++
3 files changed, 158 insertions(+), 9 deletions(-)
diff --git a/lib/PublicInbox/LeiToMail.pm b/lib/PublicInbox/LeiToMail.pm
index b0d4b664..ebb50c50 100644
--- a/lib/PublicInbox/LeiToMail.pm
+++ b/lib/PublicInbox/LeiToMail.pm
@@ -6,6 +6,12 @@ package PublicInbox::LeiToMail;
use strict;
use v5.10.1;
use PublicInbox::Eml;
+use PublicInbox::Lock;
+use PublicInbox::ProcessPipe;
+use PublicInbox::Spawn qw(which spawn);
+use Symbol qw(gensym);
+use File::Temp ();
+use IO::Handle; # ->autoflush
my %kw2char = ( # Maildir characters
draft => 'D',
@@ -45,10 +51,14 @@ sub _mbox_hdr_buf ($$$) {
$buf;
}
-sub write_in_full_atomic ($$) {
- my ($fh, $buf) = @_;
- defined(my $w = syswrite($fh, $$buf)) or die "write: $!";
- $w == length($$buf) or die "short write: $w != ".length($$buf);
+sub write_in_full ($$$) {
+ my ($fh, $buf, $atomic) = @_;
+ if ($atomic) {
+ defined(my $w = syswrite($fh, $$buf)) or die "write: $!";
+ $w == length($$buf) or die "short write: $w != ".length($$buf);
+ } else {
+ print $fh $$buf or die "print: $!";
+ }
}
sub eml2mboxrd ($;$) {
@@ -106,4 +116,85 @@ sub eml2mboxcl2 {
$buf;
}
+sub mkmaildir ($) {
+ my ($maildir) = @_;
+ for (qw(new tmp cur)) {
+ my $d = "$maildir/$_";
+ next if -d $d;
+ require File::Path;
+ if (!File::Path::mkpath($d) && !-d $d) {
+ die "failed to mkpath($d): $!\n";
+ }
+ }
+}
+
+sub git_to_mail { # git->cat_async callback
+ my ($bref, $oid, $type, $size, $arg) = @_;
+ if ($type ne 'blob') {
+ if ($type eq 'missing') {
+ warn "missing $oid\n";
+ } else {
+ warn "unexpected type=$type for $oid\n";
+ }
+ }
+ if ($size > 0) {
+ my ($write_cb, $kw) = @$arg;
+ $write_cb->($bref, $oid, $kw);
+ }
+}
+
+sub reap_compress { # dwaitpid callback
+ my ($lei, $pid) = @_;
+ my $cmd = delete $lei->{"pid.$pid"};
+ return if $? == 0;
+ $lei->fail("@$cmd failed", $? >> 8);
+}
+
+sub compress_dst {
+ my ($out, $sfx, $lei) = @_;
+ my $cmd = [];
+ if ($sfx eq 'gz') {
+ $cmd->[0] = which($lei->{env}->{GZIP} // 'pigz') //
+ which('gzip') //
+ die "pigz or gzip missing for $sfx\n";
+ # TODO: use IO::Compress::Gzip
+ push @$cmd, '-c'; # stdout
+ push @$cmd, '--rsyncable' if $lei->{opt}->{rsyncable};
+ } else {
+ die "TODO $sfx"
+ }
+ pipe(my ($r, $w)) or die "pipe: $!";
+ my $rdr = { 0 => $r, 1 => $out, 2 => $lei->{2} };
+ my $pid = spawn($cmd, $lei->{env}, $rdr);
+ $lei->{"pid.$pid"} = $cmd;
+ my $pp = gensym;
+ tie *$pp, 'PublicInbox::ProcessPipe', $pid, $w, \&reap_compress, $lei;
+ my $tmp = File::Temp->new("$sfx.lock-XXXXXX", TMPDIR => 1);
+ my $pipe_lk = ($lei->{opt}->{jobs} // 0) > 1 ? bless({
+ lock_path => $tmp->filename,
+ tmp => $tmp
+ }, 'PublicInbox::Lock') : undef;
+ ($pp, $pipe_lk);
+}
+
+sub write_cb {
+ my ($cls, $dst, $lei) = @_;
+ if ($dst =~ s!\A(mbox(?:rd|cl|cl2|o))?:!!) {
+ my $m = "eml2$1";
+ my $eml2mbox = $cls->can($m) or die "$cls->$m missing";
+ my ($out, $pipe_lk);
+ open $out, '>>', $dst or die "open $dst: $!";
+ my $atomic = !!(($lei->{opt}->{jobs} // 0) > 1);
+ if ($dst =~ /\.(gz|bz2|xz)\z/) {
+ ($out, $pipe_lk) = compress_dst($out, $1, $lei);
+ }
+ sub {
+ my ($buf, $oid, $kw) = @_;
+ $buf = $eml2mbox->(PublicInbox::Eml->new($buf), $kw);
+ my $lock = $pipe_lk->lock_for_scope if $pipe_lk;
+ write_in_full($out, $buf, $atomic);
+ }
+ }
+}
+
1;
diff --git a/lib/PublicInbox/ProcessPipe.pm b/lib/PublicInbox/ProcessPipe.pm
index 2ce7eb8f..c9234f42 100644
--- a/lib/PublicInbox/ProcessPipe.pm
+++ b/lib/PublicInbox/ProcessPipe.pm
@@ -4,28 +4,39 @@
# a tied handle for auto reaping of children tied to a pipe, see perltie(1)
package PublicInbox::ProcessPipe;
use strict;
-use warnings;
+use v5.10.1;
sub TIEHANDLE {
- my ($class, $pid, $fh) = @_;
- bless { pid => $pid, fh => $fh }, $class;
+ my ($class, $pid, $fh, $cb, $arg) = @_;
+ bless { pid => $pid, fh => $fh, cb => $cb, arg => $arg }, $class;
}
sub READ { read($_[0]->{fh}, $_[1], $_[2], $_[3] || 0) }
sub READLINE { readline($_[0]->{fh}) }
+sub WRITE {
+ use bytes qw(length);
+ syswrite($_[0]->{fh}, $_[1], $_[2] // length($_[1]), $_[3] // 0);
+}
+
+sub PRINT {
+ my $self = shift;
+ print { $self->{fh} } @_;
+}
+
sub CLOSE {
my $fh = delete($_[0]->{fh});
my $ret = defined $fh ? close($fh) : '';
- my $pid = delete $_[0]->{pid};
+ my ($pid, $cb, $arg) = delete @{$_[0]}{qw(pid cb arg)};
if (defined $pid) {
# PublicInbox::DS may not be loaded
- eval { PublicInbox::DS::dwaitpid($pid, undef, undef) };
+ eval { PublicInbox::DS::dwaitpid($pid, $cb, $arg) };
if ($@) { # ok, not in the event loop, work synchronously
waitpid($pid, 0);
$ret = '' if $?;
+ $cb->($arg, $pid) if $cb;
}
}
$ret;
diff --git a/t/lei_to_mail.t b/t/lei_to_mail.t
index 089a422e..231cf543 100644
--- a/t/lei_to_mail.t
+++ b/t/lei_to_mail.t
@@ -62,4 +62,51 @@ for my $mbox (qw(mboxrd mboxo mboxcl mboxcl2)) {
}
}
+my ($tmpdir, $for_destroy) = tmpdir();
+local $ENV{TMPDIR} = $tmpdir;
+open my $err, '>>', "$tmpdir/lei.err" or BAIL_OUT $!;
+my $lei = { 2 => $err };
+my $buf = <<'EOM';
+From: x@example.com
+Subject: x
+
+blah
+EOM
+my $fn = "$tmpdir/x.mbox";
+my $orig = do {
+ my $wcb = PublicInbox::LeiToMail->write_cb("mboxcl2:$fn", $lei);
+ is(ref $wcb, 'CODE', 'write_cb returned callback');
+ ok(-f $fn && !-s _, 'empty file created');
+ $wcb->(\(my $dup = $buf), 'deadbeef', [ qw(seen) ]);
+ undef $wcb;
+ open my $fh, '<', $fn or BAIL_OUT $!;
+ my $raw = do { local $/; <$fh> };
+ like($raw, qr/^blah\n/sm, 'wrote content');
+ unlink $fn or BAIL_OUT $!;
+
+ local $lei->{opt} = { jobs => 2 };
+ $wcb = PublicInbox::LeiToMail->write_cb("mboxcl2:$fn", $lei);
+ $wcb->(\($dup = $buf), 'deadbeef', [ qw(seen) ]);
+ undef $wcb;
+ open $fh, '<', $fn or BAIL_OUT $!;
+ is($raw, do { local $/; <$fh> }, 'jobs > 1');
+ $raw;
+};
+SKIP: {
+ use PublicInbox::Spawn qw(which);
+ my $gzip = which('gzip') or skip 'gzip not found', 1;
+ my $wcb = PublicInbox::LeiToMail->write_cb("mboxcl2:$fn.gz", $lei);
+ $wcb->(\(my $dup = $buf), 'deadbeef', [ qw(seen) ]);
+ undef $wcb;
+ my $uncompressed = xqx([$gzip, '-dc', "$fn.gz"]);
+ is($uncompressed, $orig, 'gzip works');
+
+ local $lei->{opt} = { jobs => 2 };
+ unlink "$fn.gz" or die "unlink $!";
+ $wcb = PublicInbox::LeiToMail->write_cb("mboxcl2:$fn.gz", $lei);
+ $wcb->(\(my $dupe = $buf), 'deadbeef', [ qw(seen) ]);
+ undef $wcb;
+ is(xqx([$gzip, '-dc', "$fn.gz"]), $orig);
+}
+
done_testing;
^ permalink raw reply related [relevance 5%]
* [PATCH 00/36] another round of lei stuff
@ 2020-12-31 13:51 7% Eric Wong
2020-12-31 13:51 5% ` [PATCH 07/36] lei_to_mail: start atomic and compressed mbox writing Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-12-31 13:51 UTC (permalink / raw)
To: meta
This is against lei branch @ commit
0c8106d44f317175e122744b43407bf067183175 in
https://public-inbox.org/public-inbox.git
Infrastructure stuff for reading + writing local Maildirs and a
bunch of mbox formats are done (including gz/bz2/xz support)
and it's usage should be familiar to mairix(1) users.
Infrastructure for deduplication + augmenting search results
in place and tested.
Going to skip MH and MMDF for now; but IMAP/JMAP might happen
sooner but deduplication needs low-latency.
"extinbox" renamed "external"
Basic infrastructure like PublicInbox::IPC and SharedKV
should've been done and in use ages ago... I look forward to
using them, at least.
Some DS safety fixes since lei will use it in stranger ways
than current.
Bad enough we have messages with duplicate Message-IDs, lei will
need to deal with Unsent/Drafts messages w/o Message-IDs at all!
Eric Wong (36):
import: respect init.defaultBranch
lei_store: use per-machine refname as git HEAD
revert "lei_store: use per-machine refname as git HEAD"
lei_to_mail: initial implementation for writing mbox formats
sharedkv: fork()-friendly key-value store
sharedkv: split out index_values
lei_to_mail: start atomic and compressed mbox writing
mboxreader: new class for reading various mbox formats
lei_to_mail: start --augment, dedupe, bz2 and xz
lei: implement various deduplication strategies
lei_to_mail: lazy-require LeiDedupe
lei_to_mail: support for non-seekable outputs
lei_to_mail: support Maildir, fix+test --augment
ipc: generic IPC dispatch based on Storable
ipc: support Sereal
lei_store: add ->set_eml, ->add_eml can return smsg
lei: rename "extinbox" => "external"
mid: use defined-or with `push' for uniqueness check
mid: hoist out mids_in sub
lei_store: handle messages without Message-ID at all
ipc: use shutdown(2), base atfork* callback
lei_to_mail: unlink mboxes if not augmenting
lei: add --mfolder as an option
spawn: move run_die here from PublicInbox::Import
init: remove embedded UnlinkMe package
t/run.perl: avoid uninitialized var on incomplete test
gcf2client: reap process on DESTROY
lei_to_mail: open FIFOs O_WRONLY so we block
searchidxshard: call DS->Reset at worker start
t/ipc.t: test for references via `die'
use PublicInbox::DS for dwaitpid
syscall: SFD_NONBLOCK can be a constant, again
lei: avoid Spawn package when starting daemon
avoid calling waitpid from children in DESTROY
ds: clobber $in_loop first at reset
on_destroy: support PID owner guard
MANIFEST | 12 +-
lib/PublicInbox/DS.pm | 42 +-
lib/PublicInbox/DSKQXS.pm | 4 +-
lib/PublicInbox/Daemon.pm | 4 +-
lib/PublicInbox/Gcf2Client.pm | 18 +-
lib/PublicInbox/Git.pm | 7 +-
lib/PublicInbox/IPC.pm | 165 ++++++++
lib/PublicInbox/Import.pm | 36 +-
lib/PublicInbox/LEI.pm | 44 +--
lib/PublicInbox/LeiDedupe.pm | 100 +++++
.../{LeiExtinbox.pm => LeiExternal.pm} | 18 +-
lib/PublicInbox/LeiStore.pm | 32 +-
lib/PublicInbox/LeiToMail.pm | 361 ++++++++++++++++++
lib/PublicInbox/LeiXSearch.pm | 2 +-
lib/PublicInbox/Lock.pm | 17 +-
lib/PublicInbox/MID.pm | 15 +-
lib/PublicInbox/MboxReader.pm | 127 ++++++
lib/PublicInbox/OnDestroy.pm | 5 +
lib/PublicInbox/OverIdx.pm | 2 +
lib/PublicInbox/ProcessPipe.pm | 34 +-
lib/PublicInbox/Qspawn.pm | 43 +--
lib/PublicInbox/SearchIdxShard.pm | 1 +
lib/PublicInbox/SharedKV.pm | 148 +++++++
lib/PublicInbox/Sigfd.pm | 4 +-
lib/PublicInbox/Smsg.pm | 6 +-
lib/PublicInbox/Spawn.pm | 9 +-
lib/PublicInbox/Syscall.pm | 4 +-
lib/PublicInbox/TestCommon.pm | 25 +-
lib/PublicInbox/V2Writable.pm | 10 +-
script/lei | 17 +-
script/public-inbox-init | 32 +-
script/public-inbox-watch | 4 +-
t/convert-compact.t | 4 +-
t/index-git-times.t | 3 +-
t/ipc.t | 80 ++++
t/lei.t | 22 +-
t/lei_dedupe.t | 59 +++
t/lei_store.t | 47 ++-
t/lei_to_mail.t | 246 ++++++++++++
t/lei_xsearch.t | 2 +-
t/mbox_reader.t | 75 ++++
t/on_destroy.t | 9 +
t/plack.t | 4 +-
t/run.perl | 3 +-
t/shared_kv.t | 58 +++
t/sigfd.t | 6 +-
46 files changed, 1755 insertions(+), 211 deletions(-)
create mode 100644 lib/PublicInbox/IPC.pm
create mode 100644 lib/PublicInbox/LeiDedupe.pm
rename lib/PublicInbox/{LeiExtinbox.pm => LeiExternal.pm} (75%)
create mode 100644 lib/PublicInbox/LeiToMail.pm
create mode 100644 lib/PublicInbox/MboxReader.pm
create mode 100644 lib/PublicInbox/SharedKV.pm
create mode 100644 t/ipc.t
create mode 100644 t/lei_dedupe.t
create mode 100644 t/lei_to_mail.t
create mode 100644 t/mbox_reader.t
create mode 100644 t/shared_kv.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 --
2020-12-31 13:51 7% [PATCH 00/36] another round of lei stuff Eric Wong
2020-12-31 13:51 5% ` [PATCH 07/36] lei_to_mail: start atomic and compressed mbox writing 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).