Date | Commit message (Collapse) |
|
Since we have EPOLL_CTL_DEL implemented for the poll(2) and
kqueue backends, we can rely on Perl refcounting to gently
close(2) the underlying file descriptors as references get
dropped.
This may be beneficial in the future if we want to drop a
descriptor from the event loop without actually closing it.
|
|
EV_DISPATCH is actually a better match for EPOLLONESHOT
semantics than EV_ONESHOT in that it doesn't require EV_ADD
for every mod operation.
Blindly using EV_ADD everywhere forces the FreeBSD kernel to
do extra allocations up front, so it's best avoided.
|
|
Linux pipes default to 65536 bytes in size, and we want to read
external processes as fast as possible now that we don't use
Danga::Socket or buffer to heap.
However, drop the buffer ASAP if we need to wait on anything;
since idle buffers can be idle for eons. This lets other
execution contexts can reuse that memory right away.
|
|
With DS buffering to a temporary file nowadays, applying
backpressure to git-http-backend(1) hurts overall memory
usage of the system. Instead, try to get git-http-backend(1)
to finish as quickly as possible and use edge-triggered
notifications to reduce wakeups on our end.
|
|
We can close directly in event_step without bad side effects,
and then we also don't need to take a reason arg from worker_quit,
since we weren't logging it anywhere.
|
|
The master process only dies once and we close ourselves right
away. So it doesn't matter if it's level-triggered or
edge-triggered, actually, but one-shot is most consistent with
our use and keeps the kernel from doing extra work.
|
|
It's barely any effort at all to support HTTPS now that we have
NNTPS support and can share all the code for writing daemons.
However, we still depend on Varnish to avoid hug-of-death
situations, so supporting reverse-proxying will be required.
|
|
We need to be careful about handling EAGAIN on write(2)
failures deal with SSL_WANT_READ vs SSL_WANT_WRITE as
appropriate.
|
|
Our hacks in EvCleanup::next_tick and EvCleanup::asap were due
to the fact "closed" sockets were deferred and could not wake
up the event loop, causing certain actions to be delayed until
an event fired.
Instead, ensure we don't sleep if there are pending sockets to
close.
We can then remove most of the EvCleanup stuff
While we're at it, split out immediate timer handling into a
separate array so we don't need to deal with time calculations
for the event loop.
|
|
We don't need extra wakeups from the kernel when we know a
listener is already active.
|
|
Don't use epoll or kqueue to watch for anything unless we hit
EAGAIN, since we don't know if a socket is SSL or not.
|
|
We'll be reusing requeue in other places to reduce trips to
the kernel to retrieve "hot" descriptors.
|
|
Doing this for HTTP cuts the memory usage of 10K
idle-after-one-request HTTP clients from 92 MB to 47 MB.
The savings over the equivalent NNTP change in commit
6f173864f5acac89769a67739b8c377510711d49,
("nntp: lazily allocate and stash rbuf") seems down to the
size of HTTP requests and the fact HTTP is a client-sends-first
protocol where as NNTP is server-sends-first.
|
|
Knowing which message failed a spam check is tough when I have
many Maildirs and don't have a search indexing tool setup for
spam mail.
|
|
Chances are we already have extra buffer space following the
expensive LF => CRLF conversion that we can safely append an
extra CRLF in those places without incurring a copy of the
full string buffer.
While we're at it, document where our pain points are in terms
of memory usage, since tracking/controlling memory use isn't
exactly obvious in high-level languages.
Perhaps we should start storing messages in git as CRLF...
|
|
When dealing with ~30MB messages, we can save another ~30MB by
splitting the header and body processing and not appending the
body string back to the header.
We'll rely on buffering in gzip or kernel (via MSG_MORE)
to prevent silly packet sizes.
|
|
Email::Simple->new will split the head from the body in-place,
and we can avoid using Email::Simple::body. This saves us from
holding an extra copy of the message in memory, and saves us
around ~30MB when operating on ~30MB messages.
|
|
We don't need some of the array elements returned from
art_lookup, anymore (and haven't used them in years).
We can also shorten the lifetime of the Email::Simple object by
relying on the fact Email::Simple->new will modify it's arg if
given a SCALARREF and allow us to avoid Email::Simple::body
calls.
Unfortunately, this doesn't seem to provide any noticeable
improvement in memory usage when dealing with a 30+ MB test
message, since our previous use of ->body_set('') was saving
some memory, but forcing a LF-only body to be CRLF was making
Perl allocate extra space for s///sg.
|
|
On Linux systems with epoll support, we don't want to be
clobbering defined subs in the t/ds-poll.t test; so use
OO ->method dispatch instead and require users to explicitly
import subs via EXPORT_OK.
|
|
* origin/nntp-tls: (59 commits)
ds: ->write must not clobber empty wbuf array
Makefile: skip DSKQXS in global syntax check
ds: reduce overhead of tempfile creation
Revert "ci: require IO::KQueue on FreeBSD, for now"
ds: reimplement IO::Poll support to look like epoll
ds: split out IO::KQueue-specific code
daemon: use FreeBSD accept filters on non-NNTP
daemon: set TCP_DEFER_ACCEPT on everything but NNTP
nntp: send greeting immediately for plain sockets
ci: require IO::KQueue on FreeBSD, for now
nntp: lazily allocate and stash rbuf
ds: flush_write runs ->write callbacks even if closed
nntp: simplify long response logic and fix nesting
ds: always use EV_ADD with EV_SET
nntp: reduce allocations for greeting
ds: allow ->write callbacks to syswrite directly
daemon: use SSL_MODE_RELEASE_BUFFERS
t/nntpd-tls: slow client connection test
nntp: call SSL_shutdown in normal cases
ds|nntp: use CORE::close on socket
...
|
|
Displaying full path names of installed modules could expose
unnecessary information about user home directory names or other
potentially sensitive information. However, displaying a module
name could still be useful for diagnosing problems, so map full
paths to the relevant part of the path name which is relevant to
the package name.
Reported-by: Ali Alnubani <alialnu@mellanox.com>
https://public-inbox.org/meta/20190611193815.c4uovtlp574bid6x@dcvr/
|
|
"INSERT OR IGNORE" still bumps the auto-increment counter in
SQLite, which causes gaps to appear in NNTP article numbering.
This bug appeared in v2 repos where V2Writable may call ->add
repeatedly on the same message. This bug is apparent with
public-inbox-watch and work-in-progress IMAP watchers which may
rescan and (attempt to) reinsert the same message on mailbox
changes.
Most uses of public-inbox-mda were not affected, unless the
same message is actually delivered multiple times to the mda.
v1 is not affected, either, since deduplication is only based
on Message-ID and msgmap never sees the duplicate.
Reported-by: "Eric W. Biederman" <ebiederm@xmission.com>
|
|
We need to account for ->write(CODE) calls doing ->write(SCALARREF),
otherwise flush_write may see the wrong ->{wbuf} field.
|
|
We end up buffering giant things to the FS sometimes, and open()
is not a cheap syscall; so being forced to do it twice to get a
file description with O_APPEND is gross when we can just use
O_EXCL ourselves and loop on EEXIST.
|
|
At least the subset of epoll we use. EPOLLET might be
difficult to emulate if we end up using it.
|
|
We don't need to code multiple event loops or have branches in
watch() if we can easily make the IO::KQueue-based interface
look like our lower-level epoll_* API.
|
|
Similar to TCP_DEFER_ACCEPT on Linux, FreeBSD has a 'dataready'
accept filter which we can use to reduce wakeups when doing
TLS negotiation or plain HTTP. There's also a 'httpready'
which we can use for plain HTTP connections.
|
|
This Linux-specific option can save us some wakeups during
the TLS negotiation phase, and it can help with ordinary HTTP,
too.
Plain NNTP (and in the future, POP3) are the only things which
require the server send messages, first.
|
|
A tiny write() for the greeting on a just accept()-ed TCP socket
won't fail with EAGAIN, so we can avoid the extra epoll syscall
traffic with plain sockets.
|
|
Allocating a per-client buffer up front is unnecessary and
wastes a hash slot. For the majority of (non-malicious)
clients, we won't need to store rbuf in a long-lived object
associated with a client socket at all.
This saves around 10M on 64-bit with 20K connected-but-idle
clients.
|
|
We may need to rely on cleanup code running in enqueued
callbacks, so ensure we call it when flush_write happens.
|
|
We can get rid of the {long_res} field and reuse the write
buffer ordering logic to prevent nesting of responses from
requeue.
On FreeBSD, this fixes a problem of callbacks firing twice
because kqueue as event_step is now our only callback entry
point.
There's a slight change in the stdout "logging" format, in
that we can no longer distinguish between writes blocked
due to slow clients or deferred long responses. Not sure
if this affects anybody parsing logs or not, but preserving
the old format could prove expensive and not worth the
effort.
|
|
kqueue EV_ONESHOT semantics are different than epoll
EPOLLONESHOT. epoll only disables watches for that event while
keeping the item in the rbtree for future EPOLL_CTL_MOD. kqueue
removes the watch from the filter set entirely, necessitating
the use of EV_ADD for future modifications.
|
|
No need to allocate a new PerlIO::scalar filehandle for every
client, instead we can now pass the same CODE reference which
calls DS->write on a reused string reference.
|
|
We can bypass buffering when wbuf is empty when it's called
from a CODE reference passed to ->write.
|
|
34K per idle connection adds up to large amounts of memory;
especially with the speed of malloc nowadays compared to the
cost of cache misses or worse, swapping.
|
|
This is in accordance with TLS standards and will be needed
to support session caching/reuse in the future. However, we
don't issue shutdown(2) since we know not to inadvertantly
share our sockets with other processes.
|
|
IO::Socket::SSL will try to re-bless back to the original class
on TLS negotiation failure. Unfortunately, the original class
is 'GLOB', and re-blessing to 'GLOB' takes away all the IO::Handle
methods, because Filehandle/IO are a special case in Perl5.
Anyways, since we already use syswrite() and sysread() as functions
on our socket, we might as well use CORE::close(), as well (and
it plays nicely with tied classes).
|
|
I don't want to specify "--listen" in my systemd .service files,
so map 563 to NNTPS automatically (and 443 to HTTPS, but HTTPS
support doesn't work, yet).
|
|
It kinda, barely works, and I'm most happy I got it working
without any modifications to the main NNTP::event_step callback
thanks to the DS->write(CODE) support we inherited from
Danga::Socket.
|
|
This will be needed for NNTPS support, since we need
to negotiate the TLS connection before writing the
greeting and we can reuse the existing buffer layer
to enqueue writes.
|
|
Instead of ENOMEM (or fragmentation/swap storms), using tempfile
buffers opens us up to filesystem and storage-related errors
(e.g. ENOSPC, EFBIG, EIO, EROFS). Log these errors, drop the
particular client, and try to limp by with whateve we have left.
|
|
It may make sense to use PerlIO::mmap or PerlIO::scalar for
DS write buffering with IO::Socket::SSL or similar (since we can't
use MSG_MORE), so that means we need to go through buffering
in userspace for the common case; while still being easily
compatible with slow clients.
And it also simplifies GitHTTPBackend slightly.
Maybe it can make sense for HTTP input buffering, too...
|
|
We can be smarter about requeuing clients to run and avoid
excessive epoll_ctl calls since we can trust event_step to do
the right thing depending on the state of the client.
|
|
Both NNTP and HTTP have common needs and we can factor
out some common code to make dealing with IO::Socket::SSL
easier.
|
|
It should not matter because our rbuf is always from
a socket without encoding layers, but this makes things
easier to follow.
|
|
They're never called; the only way to break out of that loop
is the PostEventLoop callback.
|
|
No point in keeping a one-line wrapper sub around.
|
|
We can reduce the amount of short-lived anonymous subs we
create by passing $self to code references.
|
|
YAGNI
Followup-to: commit 30ab5cf82b9d47242640f748a0f9a088ca783e32
("ds: reduce Errno imports and drop ->close reason")
|