From: "Laatz, Kevin" <kevin.laatz@intel.com> To: Jakub Kicinski <jakub.kicinski@netronome.com> Cc: Jonathan Lemon <jonathan.lemon@gmail.com>, netdev@vger.kernel.org, ast@kernel.org, daniel@iogearbox.net, bjorn.topel@intel.com, magnus.karlsson@intel.com, bpf@vger.kernel.org, intel-wired-lan@lists.osuosl.org, bruce.richardson@intel.com, ciara.loftus@intel.com Subject: Re: [PATCH 00/11] XDP unaligned chunk placement support Date: Fri, 28 Jun 2019 17:19:09 +0100 [thread overview] Message-ID: <f0ca817a-02b4-df22-d01b-7bc07171a4dc@intel.com> (raw) In-Reply-To: <20190627142534.4f4b8995@cakuba.netronome.com> On 27/06/2019 22:25, Jakub Kicinski wrote: > On Thu, 27 Jun 2019 12:14:50 +0100, Laatz, Kevin wrote: >> On the application side (xdpsock), we don't have to worry about the user >> defined headroom, since it is 0, so we only need to account for the >> XDP_PACKET_HEADROOM when computing the original address (in the default >> scenario). > That assumes specific layout for the data inside the buffer. Some NICs > will prepend information like timestamp to the packet, meaning the > packet would start at offset XDP_PACKET_HEADROOM + metadata len.. Yes, if NICs prepend extra data to the packet that would be a problem for using this feature in isolation. However, if we also add in support for in-order RX and TX rings, that would no longer be an issue. However, even for NICs which do prepend data, this patchset should not break anything that is currently working. > > I think that's very limiting. What is the challenge in providing > aligned addresses, exactly? The challenges are two-fold: 1) it prevents using arbitrary buffer sizes, which will be an issue supporting e.g. jumbo frames in future. 2) higher level user-space frameworks which may want to use AF_XDP, such as DPDK, do not currently support having buffers with 'fixed' alignment. The reason that DPDK uses arbitrary placement is that: - it would stop things working on certain NICs which need the actual writable space specified in units of 1k - therefore we need 2k + metadata space. - we place padding between buffers to avoid constantly hitting the same memory channels when accessing memory. - it allows the application to choose the actual buffer size it wants to use. We make use of the above to allow us to speed up processing significantly and also reduce the packet buffer memory size. Not having arbitrary buffer alignment also means an AF_XDP driver for DPDK cannot be a drop-in replacement for existing drivers in those frameworks. Even with a new capability to allow an arbitrary buffer alignment, existing apps will need to be modified to use that new capability.
WARNING: multiple messages have this Message-ID (diff)
From: Laatz, Kevin <kevin.laatz@intel.com> To: intel-wired-lan@osuosl.org Subject: [Intel-wired-lan] [PATCH 00/11] XDP unaligned chunk placement support Date: Fri, 28 Jun 2019 17:19:09 +0100 [thread overview] Message-ID: <f0ca817a-02b4-df22-d01b-7bc07171a4dc@intel.com> (raw) In-Reply-To: <20190627142534.4f4b8995@cakuba.netronome.com> On 27/06/2019 22:25, Jakub Kicinski wrote: > On Thu, 27 Jun 2019 12:14:50 +0100, Laatz, Kevin wrote: >> On the application side (xdpsock), we don't have to worry about the user >> defined headroom, since it is 0, so we only need to account for the >> XDP_PACKET_HEADROOM when computing the original address (in the default >> scenario). > That assumes specific layout for the data inside the buffer. Some NICs > will prepend information like timestamp to the packet, meaning the > packet would start at offset XDP_PACKET_HEADROOM + metadata len.. Yes, if NICs prepend extra data to the packet that would be a problem for using this feature in isolation. However, if we also add in support for in-order RX and TX rings, that would no longer be an issue. However, even for NICs which do prepend data, this patchset should not break anything that is currently working. > > I think that's very limiting. What is the challenge in providing > aligned addresses, exactly? The challenges are two-fold: 1) it prevents using arbitrary buffer sizes, which will be an issue supporting e.g. jumbo frames in future. 2) higher level user-space frameworks which may want to use AF_XDP, such as DPDK, do not currently support having buffers with 'fixed' alignment. ??? The reason that DPDK uses arbitrary placement is that: ??? ??? - it would stop things working on certain NICs which need the actual writable space specified in units of 1k - therefore we need 2k + metadata space. ??? ??? - we place padding between buffers to avoid constantly hitting the same memory channels when accessing memory. ??? ??? - it allows the application to choose the actual buffer size it wants to use. ??? We make use of the above to allow us to speed up processing significantly and also reduce the packet buffer memory size. ??? Not having arbitrary buffer alignment also means an AF_XDP driver for DPDK cannot be a drop-in replacement for existing drivers in those frameworks. Even with a new capability to allow an arbitrary buffer alignment, existing apps will need to be modified to use that new capability.
next prev parent reply other threads:[~2019-06-28 16:19 UTC|newest] Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-06-20 8:39 [PATCH 00/11] XDP unaligned chunk placement support Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 01/11] i40e: simplify Rx buffer recycle Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 02/11] ixgbe: " Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 03/11] xdp: add offset param to zero_copy_allocator Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 04/11] i40e: add offset to zca_free Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 05/11] ixgbe: " Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 06/11] xsk: add support to allow unaligned chunk placement Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 07/11] libbpf: add flags to umem config Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 08/11] samples/bpf: add unaligned chunks mode support to xdpsock Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 09/11] samples/bpf: add buffer recycling for unaligned chunks " Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 10/11] samples/bpf: use hugepages in xdpsock app Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-20 8:39 ` [PATCH 11/11] doc/af_xdp: include unaligned chunk case Kevin Laatz 2019-06-20 8:39 ` [Intel-wired-lan] " Kevin Laatz 2019-06-24 15:38 ` [PATCH 00/11] XDP unaligned chunk placement support Björn Töpel 2019-06-24 15:38 ` [Intel-wired-lan] " =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?= 2019-06-25 13:12 ` Laatz, Kevin 2019-06-25 13:12 ` [Intel-wired-lan] " Laatz, Kevin 2019-06-25 18:44 ` Jonathan Lemon 2019-06-25 18:44 ` [Intel-wired-lan] " Jonathan Lemon 2019-06-27 11:14 ` Laatz, Kevin 2019-06-27 11:14 ` [Intel-wired-lan] " Laatz, Kevin 2019-06-27 21:25 ` Jakub Kicinski 2019-06-27 21:25 ` [Intel-wired-lan] " Jakub Kicinski 2019-06-28 16:19 ` Laatz, Kevin [this message] 2019-06-28 16:19 ` Laatz, Kevin 2019-06-28 16:51 ` Björn Töpel 2019-06-28 16:51 ` [Intel-wired-lan] " =?unknown-8bit?q?Bj=C3=B6rn_T=C3=B6pel?= 2019-06-28 20:08 ` Jakub Kicinski 2019-06-28 20:08 ` [Intel-wired-lan] " Jakub Kicinski 2019-06-28 20:25 ` Jakub Kicinski 2019-06-28 20:25 ` [Intel-wired-lan] " Jakub Kicinski 2019-06-28 20:29 ` Jonathan Lemon 2019-06-28 20:29 ` [Intel-wired-lan] " Jonathan Lemon 2019-07-01 14:44 ` Laatz, Kevin 2019-07-01 21:20 ` Jakub Kicinski 2019-07-01 21:20 ` [Intel-wired-lan] " Jakub Kicinski 2019-07-02 9:27 ` Richardson, Bruce 2019-07-02 9:27 ` [Intel-wired-lan] " Richardson, Bruce 2019-07-02 16:33 ` Jonathan Lemon 2019-07-02 16:33 ` [Intel-wired-lan] " Jonathan Lemon 2019-07-01 14:58 ` Laatz, Kevin 2019-07-01 14:58 ` [Intel-wired-lan] " Laatz, Kevin 2019-06-20 9:09 Kevin Laatz
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=f0ca817a-02b4-df22-d01b-7bc07171a4dc@intel.com \ --to=kevin.laatz@intel.com \ --cc=ast@kernel.org \ --cc=bjorn.topel@intel.com \ --cc=bpf@vger.kernel.org \ --cc=bruce.richardson@intel.com \ --cc=ciara.loftus@intel.com \ --cc=daniel@iogearbox.net \ --cc=intel-wired-lan@lists.osuosl.org \ --cc=jakub.kicinski@netronome.com \ --cc=jonathan.lemon@gmail.com \ --cc=magnus.karlsson@intel.com \ --cc=netdev@vger.kernel.org \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.