From: "Kuruvinakunnel, George" <george.kuruvinakunnel@intel.com>
To: "Fijalkowski, Maciej" <maciej.fijalkowski@intel.com>,
"intel-wired-lan@lists.osuosl.org"
<intel-wired-lan@lists.osuosl.org>
Cc: "joamaki@gmail.com" <joamaki@gmail.com>,
"Lobakin, Alexandr" <alexandr.lobakin@intel.com>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
"toke@redhat.com" <toke@redhat.com>,
"bjorn@kernel.org" <bjorn@kernel.org>,
"kuba@kernel.org" <kuba@kernel.org>,
"bpf@vger.kernel.org" <bpf@vger.kernel.org>,
"davem@davemloft.net" <davem@davemloft.net>,
"Karlsson, Magnus" <magnus.karlsson@intel.com>
Subject: RE: [Intel-wired-lan] [PATCH v7 intel-next 7/9] ice: optimize XDP_TX workloads
Date: Fri, 3 Sep 2021 06:50:07 +0000 [thread overview]
Message-ID: <PH0PR11MB51448A83D389CE43D822D72EE2CF9@PH0PR11MB5144.namprd11.prod.outlook.com> (raw)
In-Reply-To: <20210819120004.34392-8-maciej.fijalkowski@intel.com>
> From: Intel-wired-lan <intel-wired-lan-bounces@osuosl.org> On Behalf Of Maciej
> Fijalkowski
> Sent: Thursday, August 19, 2021 5:30 PM
> To: intel-wired-lan@lists.osuosl.org
> Cc: joamaki@gmail.com; Lobakin, Alexandr <alexandr.lobakin@intel.com>;
> netdev@vger.kernel.org; toke@redhat.com; bjorn@kernel.org; kuba@kernel.org;
> bpf@vger.kernel.org; davem@davemloft.net; Karlsson, Magnus
> <magnus.karlsson@intel.com>
> Subject: [Intel-wired-lan] [PATCH v7 intel-next 7/9] ice: optimize XDP_TX workloads
>
> Optimize Tx descriptor cleaning for XDP. Current approach doesn't really scale
> and chokes when multiple flows are handled.
>
> Introduce two ring fields, @next_dd and @next_rs that will keep track of descriptor
> that should be looked at when the need for cleaning arise and the descriptor that
> should have the RS bit set, respectively.
>
> Note that at this point the threshold is a constant (32), but it is something that we
> could make configurable.
>
> First thing is to get away from setting RS bit on each descriptor. Let's do this only
> once NTU is higher than the currently @next_rs value. In such case, grab the
> tx_desc[next_rs], set the RS bit in descriptor and advance the @next_rs by a 32.
>
> Second thing is to clean the Tx ring only when there are less than 32 free entries.
> For that case, look up the tx_desc[next_dd] for a DD bit.
> This bit is written back by HW to let the driver know that xmit was successful. It will
> happen only for those descriptors that had RS bit set. Clean only 32 descriptors
> and advance the DD bit.
>
> Actual cleaning routine is moved from ice_napi_poll() down to the
> ice_xmit_xdp_ring(). It is safe to do so as XDP ring will not get any SKBs in there
> that would rely on interrupts for the cleaning. Nice side effect is that for rare case
> of Tx fallback path (that next patch is going to introduce) we don't have to trigger
> the SW irq to clean the ring.
>
> With those two concepts, ring is kept at being almost full, but it is guaranteed that
> driver will be able to produce Tx descriptors.
>
> This approach seems to work out well even though the Tx descriptors are
> produced in one-by-one manner. Test was conducted with the ice HW bombarded
> with packets from HW generator, configured to generate 30 flows.
>
> Xdp2 sample yields the following results:
> <snip>
> proto 17: 79973066 pkt/s
> proto 17: 80018911 pkt/s
> proto 17: 80004654 pkt/s
> proto 17: 79992395 pkt/s
> proto 17: 79975162 pkt/s
> proto 17: 79955054 pkt/s
> proto 17: 79869168 pkt/s
> proto 17: 79823947 pkt/s
> proto 17: 79636971 pkt/s
> </snip>
>
> As that sample reports the Rx'ed frames, let's look at sar output.
> It says that what we Rx'ed we do actually Tx, no noticeable drops.
> Average: IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s
> rxmcst/s %ifutil
> Average: ens4f1 79842324.00 79842310.40 4678261.17 4678260.38 0.00
> 0.00 0.00 38.32
>
> with tx_busy staying calm.
>
> When compared to a state before:
> Average: IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s
> rxmcst/s %ifutil
> Average: ens4f1 90919711.60 42233822.60 5327326.85 2474638.04 0.00
> 0.00 0.00 43.64
>
> it can be observed that the amount of txpck/s is almost doubled, meaning that the
> performance is improved by around 90%. All of this due to the drops in the driver,
> previously the tx_busy stat was bumped at a 7mpps rate.
>
> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
> ---
> drivers/net/ethernet/intel/ice/ice_main.c | 9 ++-
> drivers/net/ethernet/intel/ice/ice_txrx.c | 21 +++---
> drivers/net/ethernet/intel/ice/ice_txrx.h | 10 ++-
> drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 73 ++++++++++++++++---
> 4 files changed, 88 insertions(+), 25 deletions(-)
>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com>
next prev parent reply other threads:[~2021-09-03 6:50 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-19 11:59 [PATCH v7 intel-next 0/9] XDP_TX improvements for ice Maciej Fijalkowski
2021-08-19 11:59 ` [PATCH v7 intel-next 1/9] ice: remove ring_active from ice_ring Maciej Fijalkowski
2021-09-13 6:47 ` [Intel-wired-lan] " G, GurucharanX
2021-08-19 11:59 ` [PATCH v7 intel-next 2/9] ice: move ice_container_type onto ice_ring_container Maciej Fijalkowski
2021-09-13 6:50 ` [Intel-wired-lan] " G, GurucharanX
2021-08-19 11:59 ` [PATCH v7 intel-next 3/9] ice: split ice_ring onto Tx/Rx separate structs Maciej Fijalkowski
2021-09-22 18:28 ` [Intel-wired-lan] " G, GurucharanX
2021-08-19 11:59 ` [PATCH v7 intel-next 4/9] ice: unify xdp_rings accesses Maciej Fijalkowski
2021-09-03 6:37 ` [Intel-wired-lan] " Kuruvinakunnel, George
2021-08-19 12:00 ` [PATCH v7 intel-next 5/9] ice: do not create xdp_frame on XDP_TX Maciej Fijalkowski
2021-09-03 6:40 ` [Intel-wired-lan] " Kuruvinakunnel, George
2021-08-19 12:00 ` [PATCH v7 intel-next 6/9] ice: propagate xdp_ring onto rx_ring Maciej Fijalkowski
2021-09-03 6:45 ` [Intel-wired-lan] " Kuruvinakunnel, George
2021-08-19 12:00 ` [PATCH v7 intel-next 7/9] ice: optimize XDP_TX workloads Maciej Fijalkowski
2021-09-03 6:50 ` Kuruvinakunnel, George [this message]
2021-08-19 12:00 ` [PATCH v7 intel-next 8/9] ice: introduce XDP_TX fallback path Maciej Fijalkowski
2021-09-03 6:50 ` [Intel-wired-lan] " Kuruvinakunnel, George
2021-08-19 12:00 ` [PATCH v7 intel-next 9/9] ice: make use of ice_for_each_* macros Maciej Fijalkowski
2021-09-22 18:26 ` [Intel-wired-lan] " G, GurucharanX
2021-08-25 7:57 ` [Intel-wired-lan] [PATCH v7 intel-next 0/9] XDP_TX improvements for ice Magnus Karlsson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=PH0PR11MB51448A83D389CE43D822D72EE2CF9@PH0PR11MB5144.namprd11.prod.outlook.com \
--to=george.kuruvinakunnel@intel.com \
--cc=alexandr.lobakin@intel.com \
--cc=bjorn@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=davem@davemloft.net \
--cc=intel-wired-lan@lists.osuosl.org \
--cc=joamaki@gmail.com \
--cc=kuba@kernel.org \
--cc=maciej.fijalkowski@intel.com \
--cc=magnus.karlsson@intel.com \
--cc=netdev@vger.kernel.org \
--cc=toke@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).