zeeshanul huq - Sun Microsystems - Beijing China wrote:
Brain,
Brian Xu - Sun Microsystems - Beijing China wrote:
zeeshanul huq - Sun Microsystems - Beijing China wrote:
Hi Brian,
The overhead of it is not only dma binding, but also unbinding.
If no copybuf is used, the overhead of the unbinding is quite quite
small comparing to the binding.
I'm sure it is quite quite smaller. But I'm also thinking of the
overhead of maintaining the dma handlers list for each packet. If we
can use single dma handler for each packet, maintaining of it will be
much easier. In that case, unbinding has to be much faster.
And some other shortages are:
1) we have to hold the MBLKs until packet transmition complete. With
bcopy we are able to free them immediately. So when the system are
near to running out of MBLKs, bcopy works better.
I don't know when running out of MBLKs occurs. When the system is
short of kernel memory?
I observed it from time to time during netstress test running with a
large number of UDP sessions.
If it is the case, then the extra bcopy also consumes kernel memory.
I think there is some difference. In our NIC driver, we use
pre-alloced dedicated memory resource for bcopy. On the other hand,
MBLKs are more widely sharable resource and so they are more easy to
get exhausted in some cases .
Ok. I see.
Thanks,
Brian
2) In some driver like bge, it only has a small number of TX buffer
descriptor. With bcopy, it ensures one BD per transmit packet, while
it may require more than one with dma_bind. so using dma bind, it
will run out of Tx BD more quicker during heavy traffic.
Yes. This is reasonable.
That's part of the reasons why we use both bcopy and dma_bind in our
NIC driver. I agree we need a more faster dma binding and unbinding
solution.
What I suggested is one way to get much faster dma binding.
Of course, the original binding is also kept to meet the bcopy
requirement.
Thanks,
Brian
Regards,
Zeeshanul Huq
Garrett D'Amore wrote:
Brian Xu - Sun Microsystems - Beijing China wrote:
Hi there,
I have a question here:
Why all of the NIC drivers have to bcopy the MBLKs for transmit?
(some of them bcopy always, and some others bcopy under a
threshold of the packet length).
I think one of the reason is the overhead of the setup of dma on
the fly is greater than the overhead of bcopy for short packets. I
want to know if this is the case and if there are any other reasons.
Yes. For any packet reasonably sized bcopy (ETHERMTU or smaller)
is faster on *all* recent hardware. (This is confirmed on even an
older 300MHz Via C3.) (Hmm... I've heard that for some Niagra
systems this might not be true, however. But I've not tested it
myself.)
I think the situation is different with jumbo frames, though.
If what I guess is the major cause, I have a proposal and I want
to hear your advice whether it makes sense.
The most time-consuming action for the dma setup is the dma bind,
more specific, calling into the VM layer to get the PFN for the
vaddr(hat_getpfnum()), since it need to search the huge page
table. While for the MBLKs, essentially which are slab objects,
the PFN has already been determined in the slab layer, and for
most of their usage, we only touch the magazine layer, where the
PFN is a pre determined one. That is, the PFN should be considered
as a constructed state, but we don't leverage it for dma bind.
In storage, we have a field 'b_shadow' in buf(9S) to store the
pages which are recently used, through which the PFNs can be
easily got. so in
the case that b_shadow works, ddi_dma_buf_bind_handle() is much
faster than the ddi_dma_mem_bind_handle().
Another example, moving the dma bind of the HBA driver(mpt) from
Tx path to the kmem cache constrcutor, mpt driver got 26%
throughput increment. See CR6707308.
If the mblk could store the PFN info and we had a
ddi_dma_mblk_bind_handle() like interface, then I think it will
benefit the performance of the NIC drivers. I consulted the PAE,
and got a answer that the bcopy is typically about 10-15% of a
NIC TX workload.
There are things that can do to make DMA faster, better, and
simpler. In an ideal world, the GLDv3 could do most of this work,
and the mblk could just carry the ddi_dma_cookie with it.
-- Garrett
Thanks,
Brian
_______________________________________________
driver-discuss mailing list
driver-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/driver-discuss
_______________________________________________
networking-discuss mailing list
networking-disc...@opensolaris.org
_______________________________________________
networking-discuss mailing list
networking-disc...@opensolaris.org
_______________________________________________
driver-discuss mailing list
driver-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/driver-discuss
