[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [PATCH 0/2] xennet: improve RX NBL batching and fix TX doorbell coalescing


  • To: david ambu <david.preetham@xxxxxxxxxx>, win-pv-devel@xxxxxxxxxxxxxxxxxxxx
  • From: Tu Dinh <ngoc-tu.dinh@xxxxxxxxxx>
  • Date: Fri, 18 Sep 2026 13:57:37 +0200
  • Authentication-results: eu.smtp.expurgate.cloud; dkim=pass header.s=selector1 header.d=vates.tech header.i="@vates.tech" header.h="From:Subject:Date:Message-ID:To:MIME-Version:Content-Type:In-Reply-To:References:Feedback-ID"
  • Delivery-date: Fri, 18 Sep 2026 11:57:46 +0000
  • Feedback-id: default:8631fc262581453bbf619ec5b2062170:Sweego
  • List-id: Developer list for the Windows PV Drivers subproject <win-pv-devel.lists.xenproject.org>

On 17/09/2026 17:43, david ambu wrote:
> This series addresses two independent throughput issues in xennet.
> 
> Patch 1 — NBL batching on the receive path:
> 
>    The receive path previously called NdisMIndicateReceiveNetBufferLists
>    once per NBL (batch size of 1), causing excessive NDIS stack overhead
>    on high-throughput workloads. This patch raises NblBatchMax to 32
>    (configurable up to 64), groups consecutive NBLs with the same
>    EtherType into a single indicate call with
>    NDIS_RECEIVE_FLAGS_SINGLE_ETHER_TYPE, and fixes __ReceiverPushPackets
>    to move KeMemoryBarrier before the Returned/Indicated reads and return
>    early when the queue is empty.
> 
> Patch 2 — TX doorbell coalescing across NBL boundaries:
> 
>    __TransmitterSendNetBufferList computed the More flag as
>    (NET_BUFFER_NEXT_NB(NetBuffer) != NULL), which evaluates to FALSE for
>    the last NB of every NBL even when the outer loop still has additional
>    NBLs to submit. This caused a premature doorbell ring between
>    back-to-back NBLs. Fixed by passing MoreNbls from the outer loop.
> 
>    Note: a companion fix in xenvif is also required —
>    TransmitterQueuePacket unconditionally reset More = FALSE for
>    non-RSS traffic, overriding the value passed in from xennet.
> 
> Performance (iperf2, 60 s, 3 runs, Windows PV guest):
> 
>    Single-stream TCP:  4,606 -> 6,056 Mbps  (+31.5%)
>    8-stream TCP:      14,663 -> 18,679 Mbps  (+27.4%)
>    8-stream UDP:       1,117 ->  1,230 Mbps  (+10.1%)
>    Single-stream UDP:    327 ->    329 Mbps  (no change, expected)

Thanks for the patches, they look very promising. We'll need to do some 
research on our end to validate the findings.

> 
> david ambu (2):
>    xennet: improve NBL batching receive path
>    xennet: fix TX doorbell coalescing — More flag dropped at NBL
>      boundaries
> 
>   src/xennet.inf           |   6 +++
>   src/xennet/adapter.c     |  13 +++++
>   src/xennet/adapter.h     |   8 +++
>   src/xennet/receiver.c    | 108 +++++++++++++++++++++++++++++----------
>   src/xennet/transmitter.c |   9 ++--
>   5 files changed, 114 insertions(+), 30 deletions(-)
> 



--
Ngoc Tu Dinh | Vates XCP-ng Developer

XCP-ng & Xen Orchestra - Vates solutions

web: https://vates.tech

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.