Re: XDP redirect measurements, gotchas and tracepoints

On Mon, Aug 28, 2017 at 09:14:20AM -0700, John Fastabend wrote:

On 08/28/2017 09:02 AM, Andy Gospodarek wrote:

quoted

On Fri, Aug 25, 2017 at 08:28:55AM -0700, Michael Chan wrote:

quoted

On Fri, Aug 25, 2017 at 8:10 AM, John Fastabend
[off-list ref] wrote:

quoted

On 08/25/2017 05:45 AM, Jesper Dangaard Brouer wrote:

quoted

On Thu, 24 Aug 2017 20:36:28 -0700
Michael Chan [off-list ref] wrote:

quoted

On Wed, Aug 23, 2017 at 1:29 AM, Jesper Dangaard Brouer
[off-list ref] wrote:

quoted

On Tue, 22 Aug 2017 23:59:05 -0700
Michael Chan [off-list ref] wrote:

quoted

On Tue, Aug 22, 2017 at 6:06 PM, Alexander Duyck
[off-list ref] wrote:

quoted

On Tue, Aug 22, 2017 at 1:04 PM, Michael Chan [off-list ref] wrote:

quoted

Right, but it's conceivable to add an API to "return" the buffer to
the input device, right?

Yes, I would really like to see an API like this.

quoted

quoted

You could, it is just added complexity. "just free the buffer" in
ixgbe usually just amounts to one atomic operation to decrement the
total page count since page recycling is already implemented in the
driver. You still would have to unmap the buffer regardless of if you
were recycling it or not so all you would save is 1.000015259 atomic
operations per packet. The fraction is because once every 64K uses we
have to bulk update the count on the page.

If the buffer is returned to the input device, the input device can
keep the DMA mapping.  All it needs to do is to dma_sync it back to
the input device when the buffer is returned.

Yes, exactly, return to the input device. I really think we should
work on a solution where we can keep the DMA mapping around.  We have
an opportunity here to make ndo_xdp_xmit TX queues use a specialized
page return call, to achieve this. (I imagine other arch's have a high
DMA overhead than Intel)

I'm not sure how the API should look.  The ixgbe recycle mechanism and
splitting the page (into two packets) actually complicates things, and
tie us into a page-refcnt based model.  We could get around this by
each driver implementing a page-return-callback, that allow us to
return the page to the input device?  Then, drivers implementing the
1-packet-per-page can simply check/read the page-refcnt, and if it is
"1" DMA-sync and reuse it in the RX queue.

Yeah, based on Alex' description, it's not clear to me whether ixgbe
redirecting to a non-intel NIC or vice versa will actually work.  It
sounds like the output device has to make some assumptions about how
the page was allocated by the input device.

Yes, exactly. We are tied into a page refcnt based scheme.

Besides the ixgbe page recycle scheme (which keeps the DMA RX-mapping)
is also tied to the RX queue size, plus how fast the pages are returned.
This makes it very hard to tune.  As I demonstrated, default ixgbe
settings does not work well with XDP_REDIRECT.  I needed to increase
TX-ring size, but it broke page recycling (dropping perf from 13Mpps to
10Mpps) so I also needed it increase RX-ring size.  But perf is best if
RX-ring size is smaller, thus two contradicting tuning needed.

The changes to decouple the ixgbe page recycle scheme (1pg per descriptor
split into two halves being the default) from the number of descriptors
doesn't look too bad IMO. It seems like it could be done by having some
extra pages allocated upfront and pulling those in when we need another
page.

This would be a nice iterative step we could take on the existing API.

quoted

quoted

With buffer return API,
each driver can cleanly recycle or free its own buffers properly.

Yes, exactly. And RX-driver can implement a special memory model for
this queue.  E.g. RX-driver can know this is a dedicated XDP RX-queue
which is never used for SKBs, thus opening for new RX memory models.

Another advantage of a return API.  There is also an opportunity for
avoiding the DMA map on TX. As we need to know the from-device.  Thus,
we can add a DMA API, where we can query if the two devices uses the
same DMA engine, and can reuse the same DMA address the RX-side already
knows.

quoted

Let me discuss this further with Andy to see if we can come up with a
good scheme.

Sound good, looking forward to hear what you come-up with :-)

I guess by this thread we will see a broadcom nic with redirect support
soon ;)

Yes, Andy actually has finished the coding for XDP_REDIRECT, but the
buffer recycling scheme has some problems.  We can make it work for
Broadcom to Broadcom only, but we want a better solution.

(Sorry for the radio silence I was AFK last week...)

I finished it a little while ago, but Michael and I both have concerns
that in a heterogenous hardware setup one can quickly run into issues
and haven't had time to work-up a few solutions before bringing this up
formally.  It also isn't a major problem until the second
optimized/native XDP driver appears on the scene.

I can run a test where XDP redirects from an ixgbe <-> bnxt_en based
device I get OOM kills after only a few seconds, due to the lack of
feedback between the different drivers that the pointer to xdp->data can
be freed/reused/etc and the different buffer allocation schemes used.

hmm so how do you get OOM here, I expect the number of in-flight xdp
bufs should be limited by the number of xdps that can be posted to the
outgoing interface. If we are hitting OOM that _should_ mean the size of
the tx queue is too large. Ixgbe should be free'ing the buffer if an error
is returned from xdp xmit routines (will check this today). And bnxt should
return an error if we hit some high water mark on xmit.

I reconfigured the hardware after I was done with the bnxt_en devel, but I
should be able to set it up and provide some more detail.  Let me repro it and
debug a bit more.

quoted

Initially I did not think this was an issue and that xdp_do_flush_map()
would handle this, but I think there is a still a need to be able to
signal back to the receving device that the buffer allocated has been
xmitted by the transmitter and can be freed.  Since there is really no
guarantee that completion of an XDP_REDIRECT action means that it is
safe to free area pointed to by xdp->data area that contains the packet
to be xmitted.  Since the packet done interrupt handler in a driver
cannot signal back the the receiving driver that the buffer is now safe
to reuse/free there is a chance for trouble.  

There should be some high water mark on how many outstanding packets
can be in-flight. At the moment I assumed this was something related to
queue lengths a more explicit high water mark could added to the xmit path
and tracked in xdp infrastructure.

quoted

I was hoping to spend some time this week cooking up a patch that just
did not allow use of XDP_REDIRECT when the ifindex of the outgoing
device did not match that of the device to which the XDP prog was
attached, but that probably is not worth the trouble when we would just
fix it for real.  (It would also require some really terrible hacks to
enforce this in the kernel when all that is being done is setting up a
map that contains the redirect table, so it is probably not useful.)

I would prefer to solve the problem vs limiting the implementation

Agreed.

quoted

The basic prototype would be something like this:

(rx packet interrupt on eth0, leads to napi_poll)
napi_poll (eth0)
  call xdp_prog (eth0)
    xdp_do_redirect (eth0)
      ndo_xdp_xmit (eth1)
      mark buffer with information netdev/ring/etc
      place buffer on tx ring for eth1

(tx done interrupt on eth1, leads to napi_poll)
napi_poll (eth1)
  process tx interrupt (eth1)
    look up information about netdev/ring/etc
    ndo_xdp_data_free (eth0, ring, etc)

Thoughts?