Yes, I think AIO could be the best you can do.
It is correct that current code does not really works with AIO, and even Windows uses a “read 0 bytes” trick to effectively convert AIO-like WSARecv() into read-readiness notification.
But maybe you could use buffered VIO, I think this would help.
Where is this buffer ? It is in thd->net.vio->read_buffer.
It is not usually allocated and, which means, you would have to change the code to pass VIO_BUFFERED_READ flag into vio_init(), during THD initialization, if threadpool is used.
set vio->read_pos = vio->read_buffer;
set vio->read_end = vio_read_pos + number_of_bytes_read;
I think that would be it basically.
Except that SSL connections will not work.
It does not use the underlying vio->read and vio->write for transport, as of today. It is possible somehow in OpenSSL to use custom read/writes, through obscure BIO interface, but it is not yet done. From looking at the code, currently OpenSSL just reads directly from a socket.
From: GUESNET, ETIENNE (ext)
Sent: Wednesday, 18 September 2019 11:20
To: Vladislav Vaintroub; maria-developers@lists.launchpad.net
Subject: RE: [Maria-developers] Implementation of Threadpool
Hi Vladislav,
> IOCP sounds really like a better API, in case you can use it.
The IOCP documentation said (man CreateIoCompletionPort):
Note: This subroutine only works with file descriptors of sockets, or regular files for use with the Asynchronous I/O (AIO) subsystem. It does not work with file descriptors of other types.
It will be difficult to bypass these restriction. Note it is public and documented restriction, I will probably find other trouble during development.
From: Vladislav Vaintroub <vvaintroub@gmail.com>
Sent: Tuesday, September 17, 2019 6:04 PM
To: GUESNET, ETIENNE (ext) <etienne.guesnet.external@atos.net>; maria-developers@lists.launchpad.net
Subject: RE: [Maria-developers] Implementation of Threadpool
I now read the docs for the AIX pollset API, and it does not seem an easy thing to use for the threadpool.
https://www.ibm.com/support/knowledgecenter/en/ssw_aix_71/p_bostechref/pollset.html
The main hurdle is that there is no “one-shot” behaviour, so you will need to pollset_ctl(PS_DELETE) each returned descriptor, and
pollset_ctl(PS_ADD) it later. That would be a good workaround, but very surprising behaviour of the pollset is that pollset_ctl() waits for pollset_poll() to complete, which makes it not better than a normal poll() really. I’ve no idea what IBM folks were thinking of when they designed this API.
As for normal poll(2)
The problem with it, is that if one does not immediately drain data from readable socket, poll() will busy-loop returning the same fds again and again.
It is possible to fix busy loop, by clearing pollfd.events flag, but then again we need reset pollfd.events soon, after threadpool_process_request(). And for that, we’d need to somehow interrupt poll() , modify the fds array, issue poll() again. There will be a lot of interrupts, I’m afraid. I foresee a busy loop either way, which makes poll(2) not a very good option. Unless you can figure out how to drain all data from socket immediately after it becomes readable.
IOCP sounds really like a better API, in case you can use it.
From: Vladislav Vaintroub
Sent: Tuesday, 17 September 2019 15:20
To: GUESNET, ETIENNE (ext); maria-developers@lists.launchpad.net
Subject: RE: [Maria-developers] Implementation of Threadpool
Hi Etienne,
The reason why there is no poll/select implementation is that the systems that we support all have something better then poll/select, which can be used instead. So yes, “no interest” would fit. The main factor is of course that we have no access to those commercial Unix distributions that have neither of IOCP,epoll, kevent or ports
The notification property that we want to have here is that, once there is some data on a socket coming from client, the socket is returned, and is taken out of the “poll set”. Socket returns to the “poll set” once command(e.g SQL query , or anything else that client-server protocol understands) is fully processed. We’d like to avoid multiple notifications on a socket, until client command is fully processed, otherwise different threads from the pool will try to process client’s command at the same time.
This is the only thing we need, and this is something that poll/select do not provide.
As for Solaris ports –
existing Solaris implementation is based on ports, and as far as I could test, it had this one-shot behaviour, which is that we need, I.e port_get() only returns a single event, and then there must be a new port_associate() to reenable the socket/return it to “poll-set”. The documentation confirms this observation
“Objects of type PORT_SOURCE_FD are file descriptors. The event types for PORT_SOURCE_FD objects are described in poll(2). At most one event notification will be generated per associated file descriptor. For example, if a file descriptor is associated with a port for the POLLRDNORM event and data is available on the file descriptor at the time the port_associate() function is called, an event is immediately sent to the port. If data is not yet available, one event is sent to the port when data first becomes available.”
I read somewhere IOCP would exist on AIX, so I hoped existing Windows code in threadpol_generic.cc would be of some help, if someone eventually ports that to AIX . Although, admittedly Windows code, uses a trick to reading zero bytes in ReadFile/WSARecv, which effectively translates asynchronous IO to “poll-like” notification modes.
From: GUESNET, ETIENNE (ext)
Sent: Tuesday, 17 September 2019 14:13
To: maria-developers@lists.launchpad.net
Subject: [Maria-developers] Implementation of Threadpool
Hi,
I am implementing a threadpool system to AIX. The AIX equivalent of epoll / kqueue on AIX is pollset (and IOCP, but partial implementation only). However, pollset has only a level-trigger mode and MariaDB needs edge-trigger (see comments of sql/threadpoll_generic.h file). Adding a pollset support in MariaDB would be difficult, and probably not so efficient, as we need to simulate the edge-trigger behavior.
Obviously, AIX has poll and select support. MariaDB has not. Is there a reason to don’t implement threadpoll through poll or select? No interest? Performance issues?
MariaDB currently works on AIX without threadpool; in term of efficiency, do you know what can be obtained using threadpool with poll/select or a more modern solution?
As far I know, SunOS/Solaris/Illumos threadpoll system (called “port”) is also level-trigger only, but I do not find specific functions to manage this.
Thanks!
Etienne Guesnet.