[dpdk-dev] DPDK and forked processes

[Eads, Gage]

Hi all,

Does DPDK support forking secondary processes after executing rte_eal_init()? The l2fwd_fork example and at least one application (OpenEM: https://sourceforge.net/projects/eventmachine/) use this model, and they do so by fixing up the EAL internals (e.g. manually changing process_type from primary to secondary) at the start of the child process. This feels like a hack, and I can't find any documentation describing this model.

Moreover, this approach doesn't appear to be compatible with recent EAL changes. For instance, the multi-process communication creates a couple handler threads ("rte_mp_handle" and "rte_mp_async") during EAL initialization. The child processes won't inherit these threads, and so won't be able to participate in multi-process comms. This means the reworked memory subsystem and upcoming device hotplug support (http://mails.dpdk.org/archives/dev/2018-July/107704.html) won't work with this fork-after-init model.

This is just one example - there may be other features/subsystems that won't work. As far as I can tell there is no official stance (though the l2fwd_fork example implies it's supported, IMO); I think either DPDK should either drop the example and not support this model, or support it and either document its limitations or resolve them. This model could be an interesting way to run multi-process DPDK on an ASLR-enabled system, but supporting this wouldn't be trivial.

Thanks,
Gage

[Burakov, Anatoly]

Post by Eads, Gage
Hi all,
Does DPDK support forking secondary processes after executing
rte_eal_init()? The l2fwd_fork example and at least one application
(OpenEM: https://sourceforge.net/projects/eventmachine/) use this model,
and they do so by fixing up the EAL internals (e.g. manually changing
process_type from primary to secondary) at the start of the child
process. This feels like a hack, and I can’t find any documentation
describing this model.
Moreover, this approach doesn’t appear to be compatible with recent EAL
changes. For instance, the multi-process communication creates a couple
handler threads (“rte_mp_handle” and “rte_mp_async”) during EAL
initialization. The child processes won’t inherit these threads, and so
won’t be able to participate in multi-process comms. This means the
reworked memory subsystem and upcoming device hotplug support
(http://mails.dpdk.org/archives/dev/2018-July/107704.html) won’t work
with this fork-after-init model.
This is just one example – there may be other features/subsystems that
won’t work. As far as I can tell there is no official stance (though the
l2fwd_fork example implies it’s supported, IMO); I think either DPDK
should either drop the example and not support this model, or support it
and either document its limitations or resolve them. This model could be
an interesting way to run multi-process DPDK on an ASLR-enabled system,
but supporting this wouldn’t be trivial.
Thanks,
Gage

I think it's a very bad idea to use such a model in recent versions of
DPDK. As you have correctly pointed out, IPC will not work in such a
scenario, and given how our memory subsystem relies on IPC, this is a
recipe for memory corruption and divergent memory maps (since
technically both initial and forked processes believe they are primary).

Even hacking rte_config to make DPDK think it's a secondary process will
not work, because the initialization has already completed, but all of
the threads (IPC, interrupt, etc.) are gone and correct IPC socket was
not created, which means the process becomes invisible to the primary
for all intents and purposes.

We _could_ introduce some kind of "official DPDK fork" function that
would fork the process and then restart interrupt, IPC etc. stuff on an
already running instance of DPDK, but that seems like a workaround for a
problem that shouldn't exist in the first place, because such usage is
fundamentally incompatible with DPDK as it stands now.

[Eads, Gage]

As this discussion has broad implications for DPDK, is it a good candidate for a techboard meeting topic?

-----Original Message-----
From: Burakov, Anatoly
Sent: Monday, July 16, 2018 10:09 AM
Subject: Re: DPDK and forked processes

Post by Eads, Gage
Hi all,
Does DPDK support forking secondary processes after executing
rte_eal_init()? The l2fwd_fork example and at least one application
(OpenEM: https://sourceforge.net/projects/eventmachine/) use this
model, and they do so by fixing up the EAL internals (e.g. manually
changing process_type from primary to secondary) at the start of the
child process. This feels like a hack, and I can’t find any
documentation describing this model.
Moreover, this approach doesn’t appear to be compatible with recent
EAL changes. For instance, the multi-process communication creates a
couple handler threads (“rte_mp_handle” and “rte_mp_async”) during EAL
initialization. The child processes won’t inherit these threads, and
so won’t be able to participate in multi-process comms. This means the
reworked memory subsystem and upcoming device hotplug support
(http://mails.dpdk.org/archives/dev/2018-July/107704.html) won’t work
with this fork-after-init model.
This is just one example – there may be other features/subsystems that
won’t work. As far as I can tell there is no official stance (though
the l2fwd_fork example implies it’s supported, IMO); I think either
DPDK should either drop the example and not support this model, or
support it and either document its limitations or resolve them. This
model could be an interesting way to run multi-process DPDK on an
ASLR-enabled system, but supporting this wouldn’t be trivial.
Thanks,
Gage

I think it's a very bad idea to use such a model in recent versions of DPDK. As you
have correctly pointed out, IPC will not work in such a scenario, and given how
our memory subsystem relies on IPC, this is a recipe for memory corruption and
divergent memory maps (since technically both initial and forked processes
believe they are primary).
Even hacking rte_config to make DPDK think it's a secondary process will not
work, because the initialization has already completed, but all of the threads
(IPC, interrupt, etc.) are gone and correct IPC socket was not created, which
means the process becomes invisible to the primary for all intents and purposes.
We _could_ introduce some kind of "official DPDK fork" function that would fork
the process and then restart interrupt, IPC etc. stuff on an already running
instance of DPDK, but that seems like a workaround for a problem that shouldn't
exist in the first place, because such usage is fundamentally incompatible with
DPDK as it stands now.

[Thomas Monjalon]

Post by Eads, Gage
As this discussion has broad implications for DPDK, is it a good candidate for a techboard meeting topic?

We can discuss it in techboard, but usually we prefer discussing topics
whose resolution is not clear.
In this case, I think everybody agree with Anatoly, isn't it?

Post by Eads, Gage

-----Original Message-----
From: Burakov, Anatoly
Sent: Monday, July 16, 2018 10:09 AM
Subject: Re: DPDK and forked processes

Post by Eads, Gage
Hi all,
Does DPDK support forking secondary processes after executing
rte_eal_init()? The l2fwd_fork example and at least one application
(OpenEM: https://sourceforge.net/projects/eventmachine/) use this
model, and they do so by fixing up the EAL internals (e.g. manually
changing process_type from primary to secondary) at the start of the
child process. This feels like a hack, and I can’t find any
documentation describing this model.
Moreover, this approach doesn’t appear to be compatible with recent
EAL changes. For instance, the multi-process communication creates a
couple handler threads (“rte_mp_handle” and “rte_mp_async”) during EAL
initialization. The child processes won’t inherit these threads, and
so won’t be able to participate in multi-process comms. This means the
reworked memory subsystem and upcoming device hotplug support
(http://mails.dpdk.org/archives/dev/2018-July/107704.html) won’t work
with this fork-after-init model.
This is just one example – there may be other features/subsystems that
won’t work. As far as I can tell there is no official stance (though
the l2fwd_fork example implies it’s supported, IMO); I think either
DPDK should either drop the example and not support this model, or
support it and either document its limitations or resolve them. This
model could be an interesting way to run multi-process DPDK on an
ASLR-enabled system, but supporting this wouldn’t be trivial.
Thanks,
Gage

I think it's a very bad idea to use such a model in recent versions of DPDK. As you
have correctly pointed out, IPC will not work in such a scenario, and given how
our memory subsystem relies on IPC, this is a recipe for memory corruption and
divergent memory maps (since technically both initial and forked processes
believe they are primary).
Even hacking rte_config to make DPDK think it's a secondary process will not
work, because the initialization has already completed, but all of the threads
(IPC, interrupt, etc.) are gone and correct IPC socket was not created, which
means the process becomes invisible to the primary for all intents and purposes.
We _could_ introduce some kind of "official DPDK fork" function that would fork
the process and then restart interrupt, IPC etc. stuff on an already running
instance of DPDK, but that seems like a workaround for a problem that shouldn't
exist in the first place, because such usage is fundamentally incompatible with
DPDK as it stands now.
--
Thanks,
Anatoly

[Stephen Hemminger]

On Fri, 27 Jul 2018 17:03:48 +0200

Post by Thomas Monjalon

Post by Eads, Gage
As this discussion has broad implications for DPDK, is it a good candidate for a techboard meeting topic?

We can discuss it in techboard, but usually we prefer discussing topics
whose resolution is not clear.
In this case, I think everybody agree with Anatoly, isn't it?

I would prefer that decisions like this be done by rough consensus on the mailing list.

As far as applications messing with internals, in reality any application can change
anything. Just don't come crying to DPDK community for help.

[Eads, Gage]

Agreed on both points. I'll submit a patchset to remove the l2fwd_fork example and its user-guide, so it doesn't appear that DPDK supports this model. If anyone on the ML disagrees, they can respond here or on the patch thread.

-----Original Message-----
Sent: Friday, July 27, 2018 11:00 AM
Subject: Re: DPDK and forked processes
On Fri, 27 Jul 2018 17:03:48 +0200

Post by Thomas Monjalon

Post by Eads, Gage
As this discussion has broad implications for DPDK, is it a good candidate for

a techboard meeting topic?

Post by Thomas Monjalon
We can discuss it in techboard, but usually we prefer discussing
topics whose resolution is not clear.
In this case, I think everybody agree with Anatoly, isn't it?

I would prefer that decisions like this be done by rough consensus on the mailing list.
As far as applications messing with internals, in reality any application can
change anything. Just don't come crying to DPDK community for help.