- people - netdevconf.info

0x14: nutnbolts talk, Application Device Queues (ADQ) for system-level network I/O performance improvements
by Jamal Hadi Salim 30 Jan '20

30 Jan '20

ADQ(Application Device Queues) support has been in the kernel for a while now. ADQ enables network application data to be isolated to specific (symmetric rx/tx) hardware netdevice queue pair(s). Application specific-data is ingressed towards these dedicated queues and rate controlled in the egress direction - all using policy definitions. ADQ uses standard Linux interfaces to achieve its goals. In this talk, Amritha Nambiar, Kiran Patil and Sridhar Samudrala will: - dig into the details of ADQ architecture and operations. - illustrate collected data on how ADQ helps to improve predictability by reducing jitter, lowering latency and improving throughput. - show, via an example application, how developers can take advantage of ADQ. Amritha et al will also discuss future plans for ADQ such as enabling busy polling on AF_XDP sockets by associating a NAPI_ID to an AF_XDP socket at bind time. More info: https://netdevconf.info/0x14/session.html?talk-ADQ-for-system-level-network… Reminder, registration is now open and early bird is still in effect. https://netdevconf.info/0x14/registration.html cheers, jamal

1 0

0x14: Bronze Sponsor, IPv4 Unicast Extensions Project
by Jamal Hadi Salim 29 Jan '20

29 Jan '20

New Sponsor, the IPv4 Unicast Extensions Project. We are grateful for your support! Thank you. IPv4 Unicast Extensions Project is working on extending the unicast portion of the IPv4 address space, including hundreds of millions of addresses that are currently reserved, or are very underutilized. This extension will make more IPv4 addresses usable for providing globally reachable services during the long transition to IPv6, reducing the price of IPv4 addresses to end users. cheers, jamal

1 0

0x14: Moonshot talk, Linux Kernel Network Scripting with Lua
by Jamal Hadi Salim 29 Jan '20

29 Jan '20

I'll spend a bit more time summarizing this talk because it will no doubt generate passions in (some) people and curiosity in others. If you thought that eBPF is the only approach to extend the kernel, think again. In this talk, Lourival Vieira Neto et al describe a framework, Lunatik, which facilitates dynamically injecting Lua scripts into the kernel to extend kernel mechanisms. Some context: what is Lua? 1) It is a scripting language that is very widely deployed as an embededable _extension language_. Game programming in particular predominantly uses it for extensions. Openwrt uses it as config language and there are many others listed here: https://en.wikipedia.org/wiki/List_of_applications_using_Lua. Wide deployment means it has seen exposure in many environments. The _extension 2) It is a tiny language (the whole language is about 200KB) that is designed to be easy to embed - in particular in C 3) It is considered relatively secure. Despite the wide deployment over many years there have been very few CVEs reported against Lua in more than a decade. See: https://www.cvedetails.com/product/28436/LUA-LUA.html?vendor_id=13641) Why scripting? Extending kernels with scripts is nothing new. But: The simple answer to this question is to compare a compiler driven approach (think C) vs a scripting language(think Bash or python). The former requires a complex development environment (think eBPF needing latest clang, gcc, correct libbpf, etc) while the later provides faster turnarounds to development and deployment (you need a kernel with the Lua VM but not much after that in terms of tooling) and of course, a much simpler and stable ABI. Script based execution is often not as performant but often more usable relatively speaking. And back to the talk... The Lunatik framework has rich coverage across different kernel hooks and has been used to script different Linux subsystems such as CPUfreq, Sockets, RCU, ULP, Netfilter, and now XDP. Lunatik has been around for a while, just not upstreamed - and to give a little sample space of its deployment: NFLua is currently deployed _in production in over 20 million home routers_! You dont want a rogue script kill your kernel and system. Lourival et al will discuss the challenges and approach taken in allowing script injection into the kernel while still maintaining correctness, isolation, and liveness. They will then describe NFLua and introduce XPDLua, which allows users to extend XDP with Lua. XDPLua aims to replace NFLua. The authors will detail how Lua can be used within XDP: as a standalone to directly invoke currently exposed eBPF helpers or alternatively have eBPF programs invoke Lua scripts. And last but not least: Lourival et al will provide comparison performance data for packet filtering between with Iptables, eBPF, NFLua and XDPLua. sounds exciting? Come to the conference, listen, learn, and engage the speakers! More info: https://netdevconf.info/0x14/session.html?talk-linux-network-scripting-with… Reminder, registration is now open and early bird is still in effect. https://netdevconf.info/0x14/registration.html cheers, jamal

2 1

0x14: nutsnbolts talk, Storage application performance boost with zero thrashing networking stack
by Jamal Hadi Salim 29 Jan '20

29 Jan '20

There has been an ongoing effort in the community to get Zero-copy working over the last few years - with much success. While both MSG_ZEROCOPY (zero copy transmit) and socket mmap (zero copy receive) have been out in the wild for sometime now, there are no known high scale open source application consumers of these interfaces. In this talk, Or Gerlitz will describe how he makes use of these interfaces to integrate into spdk(https://spdk.io/) - an open source storage framework which uses sockets for nvme-over-tcp in a smart NIC environment. The goal is to use kernel uAPIs while achieving high scale performance. Or will delve into MSG_ZEROCPOY and the challenges that he had to deal with. He will describe the need for an app author to understand and how to best tie-in their app state machine to the interfaces: to address both transactions responses from the peer app and zero-copy notifications from the local socket provider. Should the app use ZC with all or nothing approach or sometimes yes and other-times no? Come to the talk to get the answer and advise on how to effectively use these interfaces. In addition Or will spend time going into the performance analysis details correlating I/O performance visavis CPU cost (which is often tricky to get right with traditional tools like profiler/flame-graphs). More info: https://netdevconf.info/0x14/session.html?talk-storage-application-performa… Reminder, registration is now open and early bird is still in effect. https://netdevconf.info/0x14/registration.html cheers, jamal

1 0

0x14: nutsnbolts talk, Media Redundancy Protocol
by Jamal Hadi Salim 28 Jan '20

28 Jan '20

MRP(Media Redundancy Protocol) is an open standard for ring topologies in industrial ethernet networks defined in common standards-based protocol(IEC 62439-2). In an MRP-enabled network each Ethernet switch is connected to two other switches forming a ring. An MRP-enabled ring can overcome single link point of failures at worst case recovery time of 30ms - which is faster than STP. In this talk Horatiu Vultur will describe the MRP protocol in some detail. They will then proceed to discuss the effort to add support to the kernel; different implementation approaches considered and eventual implementation path taken after receiving feedback on the mailing list. And last but not least, future work will be discussed including hardware offload of MRP as well as preliminary results comparing hardware-offloaded MRP vs non-offloaded version. More info: https://netdevconf.info/0x14/session.html?talk-adding-MRP-to-the-linux-kern… Reminder, registration is now open and early bird is still in effect. https://netdevconf.info/0x14/registration.html cheers, jamal

1 0

0x14: nutsnbolts talk, Extend segment routing for another source routing protocol named RPL
by Jamal Hadi Salim 28 Jan '20

28 Jan '20

RPL is an IPv6 Routing Protocol for Low-Power and Lossy Networks defined in RFC 6550. RFC 6550 defines a mode that is known as "storing" mode. RFC 6554 defines a "non-storing" mode of route propogation. While there are several other RPL open source implementations, they all implement RPL using the "storing" mode which propagates routes via ICMPv6. There are no open source "non-storing" mode implementations. In this talk, Alexander Aring et al will discuss an implementation that uses "non-storing" mode (RFC 6554). In the storing mode(per RFC 6554), route propagation is done via the IPv6 Routing Header. Aring et al discuss the architecture, interface approach, challenges that they overcame and outstanding future work. More info: https://netdevconf.info/0x14/session.html?talk-extend-segment-routing-for-R… Reminder, registration is now open and early bird is still in effect. https://netdevconf.info/0x14/registration.html cheers, jamal

1 0

0x14: nutsnbolts talk, Implementation of IPv6 IOAM in Linux Kernel
by Jamal Hadi Salim 28 Jan '20

28 Jan '20

Operations, Administration, and Maintenance (OAM) refers to a set of techniques and mechanisms for performing fault detection, isolation and performance measurements. Classical approaches such are traceroute, ping, etc can now be improved by collecting more granular and precise per-packet telemetry. The IETF is currently in the process of standardizing In-situ OAM (IOAM) to allow collecting operational information along a path. In this talk Justin Iurman et al discuss an implementation of IOAM for the Linux kernel with IPv6 as the encapsulation protocol. They will discuss the details of their approach and demonstrate evaluation results. More info: https://netdevconf.info/0x14/session.html?talk-implementation-of-IPv6-IOAM-… Reminder, registration is now open and early bird is still in effect. https://netdevconf.info/0x14/registration.html cheers, jamal

1 0

0x14: Free Range Routing workshop
by Jamal Hadi Salim 28 Jan '20

28 Jan '20

The PC has accepted a new workshop session. Donald Sharp and David Lamparter will chair the FRRouting (https://frrouting.org/) workshop. Current agenda for the workshop includes: * Where to put kernel boundary conventions: * Current Status on netconf/yang models * Status of using kernel nexthop groups FRR * FRR feature rundown: Recent past and future work * Installing FRR for kernel developers For more details: https://netdevconf.info/0x14/session.html?workshop-FRR Reminder, registration is now open and early bird is still in effect. https://netdevconf.info/0x14/registration.html cheers, jamal

1 0

0x14: nutsnbolts talks, Hierarchical Token Bucket
by Jamal Hadi Salim 27 Jan '20

27 Jan '20

Hierarchial bandwith management is a very important packet service for a lot of networking use cases (ranging from large data centres to service provider use cases, etc). Over the last decade, the TC Hierarchical Token Bucket(HTB) qdisc has emerged as the most popular non-work conserving queueing discipline for enabling this service in Linux. HTB is quite flexible and versatile, but at large scale (think thousands to million flows) it comes at a cost: 1) cpu cycles predominantly due to stalls caused by shared queus lock contentions 2)extensive memory costs when adding many flows. At 0x14 we have two sessions that are addressing this issue in different ways. Our first talk is from Yosef Kuperman, Rony Efraim and Maxim Mikityanskiy and focuses on offloading HTB to the NIC hardware (Mellanox cnx5). Flow classification takes place in the TC egress clsact to avoid any sorts of (queue) locking. Packets are tagged and the offloaded HTB uses these tags as flow/classids to select the correct queue in the hierarchy. Kuperman et al will go over the challenges they overcame, show performance numbers and solicit feedback. More Info: https://netdevconf.info/0x14/session.html?talk-hierarchical-QoS-hardware-of… Our second talk is from the Google folks Stanislav Fomichev, Eric Dumazet, Willem de Bruijn, Vlad Dumitrescu, Bill Sommerfeld and Peter Oskolkov. Google has for many years utilized HTB and consequently faced scaling challenges. With the recent introduction of Early Departure Time model (See Van Jacobson's keynote on EDT in netdev 0x12), an opportunity has opened up to achieve the same packet service in a more efficient way. In this talk, Stan et al describe how they moved away from HTB altogether. The packet service is created using composition of BPF, FQ and EDT. The authors will provide performance numbers, discuss some of the outstanding challenges and solicit feedback from the community. More info: https://www.netdevconf.info/0x14/session.html?talk-replacing-HTB-with-EDT-a… Reminder, registration is now open and early bird is still in effect. https://netdevconf.info/0x14/registration.html cheers, jamal

1 0

0x14: New Bronze sponsor, Meter!
by Jamal Hadi Salim 26 Jan '20

26 Jan '20

We are pleased to announce Bronze sponsorship from Meter[meter.com]! Thank you for your support Meter. Meter is the easiest way to get the best Internet and WiFi for offices. Meter takes care of everything, from ISP selection and installation to ongoing support and network management. Meter combines powerful software, custom hardware, and dedicated experts to provide dramatically better Internet speed, security, and reliability. More info: https://netdevconf.info/0x14/news.html?bronze-sponsor-meter-com cheers, jamal

1 0

0x14: nutsnbolts talk, Kernels of Splitting TCP in the Clouds
by Jamal Hadi Salim 26 Jan '20

26 Jan '20

In this talk Markuze Alex et al describe how they improved, by orders of magnitude, client download times of a global overlay network across public clouds. The overlay network known as the Pathway project (operated by VMware Research) interconnects geographical spread of public clouds and their vast compute and networking infrastructure The secret sauce? KTCP, a Kernel module running on a modified Linux Kernel which implements novel TCP splicing. Markuze and co. will discuss why their approach is different relative to the many approaches already out in the wild that implement TCP proxying. They will present numbers against classical approaches which demonstrate that KTCP is able to considerably increase the link utilization by TCP connections and reduce the connection latency close to its theoretical minimum. More info: https://netdevconf.info/0x14/session.html?talk-kernels-of-splitting-TCP-in-… cheers, jamal

1 0

0x14: moonshot, BP4: Byte-code for Programmable Protocol-independent PDU Processing
by Jamal Hadi Salim 25 Jan '20

25 Jan '20

Tom Herbert loves moonshots and three-letter acronyms. First it was XDP and now it is BP4. In this talk, Tom will introduce BP4 - a Domain Specific Language for programmable dataplanes based on unifying the best features of eBPF and P4. The goal of BP4 is “write once, run anywhere, run well!” BP4 is intended to run in _both software and hardware_ execution environments. Central to a BP4 program is a dynamically programmable parser that supports a wide variety of protocols and permits support for new protocols to be added on the fly. The BP4 parser semantics include native support for parsing Variable Length Headers (VLH) that contains TLVs, flag-fields, or variable length arrays. Tom will describe the first PoC for BP4 which leverages the eBPF infrastructure. The PoC implements a flow dissector as a BP4 program by essentially replicating the functionality of the current Linux kernel flow_dissector with extra functionality to handle TLV and flag-fields. The programmable flow dissector will then be used as the basis for a dynamic tc-flower classification (which will allow protocols to be programmed and dynamically added for tc-flower processing). More info: https://netdevconf.info/0x14/session.html?talk-BP4-byte-code-for-programmab… Reminder, registration is now open and early bird is still in effect. https://netdevconf.info/0x14/registration.html cheers, jamal

1 0

0x14: 'Tis A TLS Festival folks!
by Jamal Hadi Salim 24 Jan '20

24 Jan '20

TLS aint cheap on the CPU. The trend on Internet traffic is indicating that the majority of internet traffic is being encrypted with TLS. In other words the most common packets are using TLS! For this reason, we need to pay more attention to TLS performance. At 0x14 we have a small TLS festival. And its all about improving performance. In the first talk, Pawel Szymanski and Manasi Deval that assert the claim that you can achive good performance by letting the CPU do its thing. Use modern CPU instructions like X86 AESNI. They run experiments that compare user-mode TLS, Kernel TLS write and kernel TLS Sendfile to contrast various bottlenecks in each one with regards to encryption and authentication, cost of system calls and the memory bandwidth. They will present their results during the talk. The talk will also provide some insight on which of the three approaches is best suited for different type of application scenarios. More info: https://netdevconf.info/0x14/session.html?talk-TLS-performance-characteriza… And in the second TLS talk, Tariq Toukan, Bar Tuaf and Tal Gilboa discuss offloading of TLS to the NIC. They start by reviewing the life cycle of a HW offloaded kTLS connection and the driver-HW interaction in order to support it. They will then present their experiments where NginX TLS activity is offloaded to the Mellanox ConnectX-6Dx NIC (using mlx5e driver). And finally, they present their experimental results which show significant performance speed-up gained by offloading kTLS operations to the HW. More info: https://netdevconf.info/0x14/session.html?talk-kTLS-HW-offload-implementati… In the third talk, Alexander Krizhanovsky and Ivan Koveshnikov continue their quest(see netdev 0x12 talk) to investigate and improve TLS handshake by moving it into the kernel (currently user space handled). In continuation from 0x12, Alexander and Ivan have been experimenting with new kernel approaches to reduce some perf culprits involved in completing a TLS handshake, namely dynamic memory allocation and big integer initialization. They will present their results which quantify the new approach. The talk will cover many other perf topics related to TLS handshake. More info: https://netdevconf.info/0x14/session.html?talk-performance-study-of-kernel-… Reminder, registration is now open and early bird is still in effect. https://netdevconf.info/0x14/registration.html cheers, jamal

1 0

0x14, Registration open!
by Jamal Hadi Salim 23 Jan '20

23 Jan '20

Sorry, resend to fix the hotel link.. We are pleased to announce the opening of registration for Netdev 0x14. Netdev 0x14 conference will be held in downtown Vancouver, Canada March 17-20, 2020 at the Pinnacle Hotel Harbourfront https://www.pinnacleharbourfronthotel.com We took your feedback from 0x13 and made some changes: - the conference is now 4 days (instead of 3). - From day 2 onwards we are going to experiment with breakout rooms. Instead of infinite _great talks_, we are introducing break out sessions. Attendees interested in specific discussions, after a talk or otherwise, can grab an available break out room and have more discussions. We are still deciding on the exact schedule for the break outs. - Having lunch at the location proved very good for the schedule and the collaboration. So we will be feeding you, again. Our main motivation is to bring the community together to the idea-exchange fountain we call Netdev conf. Since this is now a 4 day event - our costs have gone up. We do not aim to make profit from the event; however, to recoup some of the cost we have raised our registration fee. Cost is: CDN $475 for early bird registration which expires on February 17th 11:59PM Eastern time. Starting Feb 17th onwards, the price goes up to CDN $575. Students are 50% off (ID required) More details on registration: https://www.netdevconf.info/0x14/registration.html If you need financial assistance, note that we do provide bursaries (but slightly constrained this time): https://www.netdevconf.info/0x14/bursaries.html If you need a visa to attend and need an invitation letter, please dont procrastinate and contact us at: registrar(a)netdevconf.info more info at: https://www.netdevconf.info/0x14/travel.html cheers, jamal _______________________________________________ people mailing list people(a)netdevconf.org https://lists.netdevconf.info/cgi-bin/mailman/listinfo/people

1 0

0x14, Registration open!
by Jamal Hadi Salim 23 Jan '20

23 Jan '20

We are pleased to announce the opening of registration for Netdev 0x14. Netdev 0x14 conference will be held in downtown Vancouver, Canada March 17-20, 2020 at the Pinnacle Hotel Harbourfront https://pinnacleharbourfronthotel.com We took your feedback from 0x13 and made some changes: - the conference is now 4 days (instead of 3). - From day 2 onwards we are going to experiment with breakout rooms. Instead of infinite _great talks_, we are introducing break out sessions. Attendees interested in specific discussions, after a talk or otherwise, can grab an available break out room and have more discussions. We are still deciding on the exact schedule for the break outs. - Having lunch at the location proved very good for the schedule and the collaboration. So we will be feeding you, again. Our main motivation is to bring the community together to the idea-exchange fountain we call Netdev conf. Since this is now a 4 day event - our costs have gone up. We do not aim to make profit from the event; however, to recoup some of the cost we have raised our registration fee. Cost is: CDN $475 for early bird registration which expires on February 17th 11:59PM Eastern time. Starting Feb 17th onwards, the price goes up to CDN $575. Students are 50% off (ID required) More details on registration: https://www.netdevconf.org/0x14/registration.html If you need financial assistance, note that we do provide bursaries (but slightly constrained this time): https://www.netdevconf.org/0x14/bursaries.html If you need a visa to attend and need an invitation letter, please dont procrastinate and contact us at: registra(a)netdevconf.org more info at: https://www.netdevconf.org/0x14/travel.html cheers, jamal

1 0

0x14: Workshop, Netfilter
by Jamal Hadi Salim 23 Jan '20

23 Jan '20

Pablo Neira Ayuso will chair a netfilter workshop that will cover updates in the Netfilter land since the last NetDev conference such as: * Summary of asorted updates. * Updates on the next generation packet classification framework. * Connection tracking support for bridge. * Hardware offloads. More info: https://netdevconf.info/0x14/session.html?workshop-netfilter cheers, jamal

1 0

0x14: New workshop, Hardware acceleration and offload
by Jamal Hadi Salim 23 Jan '20

23 Jan '20

Tom Herbert will chair a workshop on hardware acceleration and offload in Network Interface Cards. Tentative agenda for the workgroup include the following topics: - New work in checksum and segmentation offloads - TC flower offload - XDP hints - XDP/eBPF offload - Receive packet steering - Netfilter offload - OVS offload - Application specific hardware queues More info: https://netdevconf.info/0x14/session.html?workshop-hardware-acceleration-an… cheers, jamal

1 0

congestion control in the bufferbloated age
by Dave Taht 23 Jan '20

23 Jan '20

I am unsure if I will make netdevconf this year, as increasingly interesting as the agenda seems. Might make it, might not. my talk at linux.conf.au last week was quite droll with lots of funny bits, and perhaps next year y'all might enjoy something like it, instead of something more serious? https://blog.apnic.net/2020/01/22/bufferbloat-may-be-solved-but-its-not-ove… I figure this time next year writing something more serious will be feasible as the l4s vs sce debate will have settled, and I'll plan on that. -- Make Music, Not War Dave Täht CTO, TekLibre, LLC http://www.teklibre.com Tel: 1-831-435-0729

1 0

0x14: Tutorial, How to add AF_XDP zero-copy support to drivers
by Jamal Hadi Salim 23 Jan '20

23 Jan '20

AF_XDP is a relatively new technology optimized for high performance packet processing. It provides an abstraction over hardware rings, so the application can handle packets in a low-level, yet hardware-agnostic fashion. With conforming drivers, AF_XDP also provides zero-copy packet handling capabilities to the application. At its basic level AF_XDP works works fine with a lot of conforming drivers. Adding zero-copy support is more challenging. Maxim Mikityanskiy has been through trial-by-fire writting zero copy AF_XDP support and came out unscathed. In this tutorial, Maxim instructs on how a driver author would go about adding AF_XDP zero copy support using the mlx5e driver as an example. More info: https://netdevconf.info/0x14/session.html?tutorial-adding-AF_XDP-zero-copy-… cheers, jamal

1 0

0x14: nutsnbolts talk, NVMe-over-TCP ≈ NVMe-over-RDMA
by Jamal Hadi Salim 22 Jan '20

22 Jan '20

Networks are getting faster but so is storage. It is not uncommon anymore for a single high performance storage device to deliver as much as a million read/write operations per second. For traditional remote storage accesses CPU requirements have become unsustainable. The recently merged NVMe-over-TCP has improved performance lowering CPU utilization. However, despite of its advantages of being able to use commodity NICs, NVMe-over-TCP's performance is still significantly worse than NVMe-over-RDMA. Rachit Agarwal, Qizhe Cai, and Jaehyun Hwang have some new ideas on how to significantly improve the status quo. They will discuss a design, implementation and evaluation of several new ideas within NVMe-over-TCP. Their design maintains all the desirable properties of NVMe-over-TCP (unmodified applications, unmodified TCP/IP stack, etc.), and yet, saturates a 100Gbps link for remote accesses using CPU utilization _similar to state-of-the-art user-space and RDMA-based solutions_. More information: https://bit.ly/2Ri6hJd cheers, jamal

1 0

0x14: nutsnbolts talk, Hardware Acceleration of Container Networking Interfaces
by Jamal Hadi Salim 22 Jan '20

22 Jan '20

In this talk Amritha Nambiar, Sridhar Samudrala, and Kiran Patil will discuss the current approaches used in offloading of container network interfaces. The talk will cover macvlan, ipvlan and subdevice functions in addition to some of the newly proposed generic interfaces to create virtual interfaces from a parent pci device. Challenges and limitations of the different approaches as well new ideas will be discussed. More information: https://www.netdevconf.info/0x14/session.html?talk-hardware-acceleration-of… cheers, jamal

1 0

0x14: Tutorial, Programming QUIC
by Jamal Hadi Salim 22 Jan '20

22 Jan '20

So you've heard of this new shiny transport called QUIC. You've even been to several presentations on QUIC at 0x12 and 0x13. And you are wondering how to write applications that run using QUIC transport. Or ... maybe you happen to know that if you pulled apart the Chromium tree and perform some tooling kungfu you could get QUIC infra sufficient for you to write a client or a server... Dmitri Tikhonov has a better idea. Why dont you show up in Vancouver for 0x14? He will be giving a tutorial on how to write applications on top of HTTP/3 QUIC based on the lsquic library. The tutorial will be instructor-led and will start with a (very) short QUIC and HTTP/3 basics introduction followed with a delve into the innards of the lsquic library and leading to interactive coding of simple echo server and client programs. And, of course more.. All the demoed code will be made available on github. More info: https://bit.ly/30HDNvy cheers, jamal

1 0

0x14: moonshot talk, Complex Network Services With eBPF
by Jamal Hadi Salim 21 Jan '20

21 Jan '20

The PC has accepted another moonshot talk! eBPF is great, but: unfortunately it gravitates to the appliance world model (lumping data and control in one pile) - which is ideal for solving simple one-off business problems. Writing complex network services with eBPF is a lot more painful. In this moonshot talk, Sebastiano Miano et al introduce the Polycube project that eases ability to write complex network services with eBPF. Polycube network services have an architecture that moves away from the appliance model by separating data from control and management plane. With its model-driven architecture, Polycube exposes REST APIs for service management. This talk will go into some detail of the Polycube APIs and abstractions and then illustrate the power of Polycube with a small live demo. More information: https://bit.ly/2NM9fDL cheers, jamal

1 0

0x14: Transport workshop
by Jamal Hadi Salim 21 Jan '20

21 Jan '20

Neal Cardwell, Yuchung Cheng and Soheil Hassas Yeganeh will chair the Transport workshop. The workshop will have many discussions on current topics in transport-layer issues in the kernel, including (but not limited to): - different protocols in the Linux kernel: TCP, MPTCP, SCTP, ... - congestion control, loss recovery, and protocol improvements - new development, performance work, measurement, real-world production experience - eBPF integration with the transport layer - etc The workshop will consist of slide presentations and extended group discussions. More information: https://netdevconf.info/0x14/session.html?workshop-transport cheers, jamal

1 0

0x14: XDP workshop
by Jamal Hadi Salim 20 Jan '20

20 Jan '20

Saeed Mahameed will chair the netdev 0x14 XDP workshop. Many discussions on a variety of XDP issues will take place - including follow ups on outstanding challenges, updates on existing features and new ideas on a variety of topics ranging from performance, acceleration and many more. Come and be part of the discussions. Current Workshop agenda (subject to update) includes: - XDP HW metadata hints - XDP on hosts pain points summary - XDP egress, development status and use case - Page pool skb recycling - Performance gains seen with iommu - Death-by-a-thousand-paper-cuts parable (related to XDP!) - etc More information: https://netdevconf.info/0x14/session.html?workshop-XDP cheers, jamal

1 0