eBPF & Switch Abstractions
1 like403 views
eBPF (extended Berkeley Packet Filter) has been shown to be a flexible kernel construct used for a variety of use cases, such as load balancing, intrusion detection systems (IDS), tracing and many others. One such emerging use case revolves around the proposal made by William Tu for the use of eBPF as a data path for Open vSwitch. However, there are broader switching use cases developing around the use of eBPF capable hardware. This talk is designed to explore the bottlenecks that exist in generalising the application of eBPF further to both container switching as well as physical switching.
Ad
More Related Content
What's hot (20)
Similar to eBPF & Switch Abstractions (20)
Ad
More from Netronome (20)
Ad
Recently uploaded (20)
eBPF & Switch Abstractions
- 1. ©"2018"NETRONOME"SYSTEMS,"INC. 1 eBPF & Switch Abstractions Nick Viljoen <[email protected]> Networking Track Vancouver, 14 November 2018
- 2. ©"2018"NETRONOME"SYSTEMS,"INC. 2 Contents ○ Background ○ The"MultiCHost"NIC"Abstraction ○ The"Switchdev"Based"MultiCHost"NIC"Abstraction ○ Currently"upstream"(as"of"2"weeks"ago) ○ Boot ○ Setting"Switchdev"Mode ○ Loading"Qdiscs ○ Next"Steps"(currently"being"upstreamed) ○ Generalising Qdisc Offload ○ Adding"clsact"Qdiscs"(u32,"cls_bpf) ○ Future"Work
- 4. ©"2018"NETRONOME"SYSTEMS,"INC. 4 Background:"HW ○ Many"core,"fully"programmable"network"processor ○ 48K96"preprocessing"cores ○ 54K120"programmable"cores,"8"threads"per"core,"MIMT ○ up"to"4"PCIe ○ Up to 40"ports"supported ○ ~17MB"of"on"chip"memory ○ 2K24GB of DRAM ○ Distributed"&"Transactional"memory architecture ○ Low"power ○ ~"10K35W"(dependent"on"chip"+"frequency)
- 5. ©"2018"NETRONOME"SYSTEMS,"INC. 5 Background:"HW"Datapath Pre processing Accelerators IMU/EMU PCIe PCIe PCIe Phy Ports Reorder PCIe PCIe PCIe Phy Ports CLSCTM C P LU AT Processing*Islands =*Flow*Processing*Core*(FPC)
- 6. ©"2018"NETRONOME"SYSTEMS,"INC. 6 Background:"eBPF"Offload"Architecture ○ Program"is"written"in"standard"manner ○ LLVM"compiled"as"normal ○ The"nfp’s"jit"is"called"like"any"other" architectures"jit" ○ This"converts"the"BPF"bytecode"to"NFP" machine"code ○ Translation"reuses"the"verifier" infrastructure"in"kernel ○ Defining the FPC datapath code using BPF bpf_prog.c LLVM bpf_prog.c Verifier Host"JIT NFP"JIT NFPHost"CPU
- 13. ©"2018"NETRONOME"SYSTEMS,"INC. 13 3"Key"Steps ○ Initialisation"(.probe) ○ App"Initialisation ○ vNIC"Allocation ○ Entering"Switchdev"Mode"(.devlink_eswitch_set) ○ Spawning"Representors ○ Qdisc"Setup"(.ndo_tc_setup) ○ Attaching"Qdisc"to"struct"nfp_abm_link
- 15. ©"2018"NETRONOME"SYSTEMS,"INC. 15 Devlink Devlink(dev(eswitch(show devlink dev(eswitch(set devlink sb(pool(show devlink sb(pool(set devlink.c nfp_devlink.c nfp_shared_buf.c nfp_app.c ctrl.c nfp_app_eswitch_mode_get() nfp_app_eswitch_mode_set() nfp_shared_buf_pool_get() nfp_shared_buf_pool_set() nfp_mbox_cmd() nfp_mbox_cmd() app=>type=>eswitch_mode_get() app=>type=>eswitch_mode_set() nfp_abm_ctrl_qm_enable struct"nfp_abm struct"nfp_abm_link nfp_abm_eswitch_mode_get nfp_abm_spawn_repr struct"nfp_repr eswitch_mode_get eswitch_mode_set sb_pool_get sb_pool_set struct"nfp_abm_link main.c Entering"Switchdev"Mode Driver Kernel App" Abstraction User"Space
- 18. ©"2018"NETRONOME"SYSTEMS,"INC. 18 Items"Covered ○ Generalising"Qdisc"Offload ○ Structure"changes ○ nfp_abm_link ○ nfp_qdisc ○ The"clsact"Qdisc ○ Motivation ○ Architecture
- 24. ©"2018"NETRONOME"SYSTEMS,"INC. 24 Items"Covered ○ Firmware"and"BPF"JIT ○ Flow"Processing"Core"Datapath ○ cls_bpf"and"Switchdev ○ Architecture ○ XDP"for"Multihost"Systems ○ Problems ○ Proposed"Abstraction
- 27. ©"2018"NETRONOME"SYSTEMS,"INC. 27 XDP"on"Multi=Host"systems ○ Challenges"that"have"to"be"solved ○ XDP"is"an"RX"exclusive"hook ○ Heterogenous"architecture"support"is"nascent ○ Security ○ However"more"and"more"of"the"potential"problems"are"falling"away ○ e.g"David"Ahern’s"recent"work"on"exposing"the"FIB"table
- 29. ©"2018"NETRONOME"SYSTEMS,"INC. 29 Summary ○ Proposing"a"fully"flexible"datapath"for"a"multiHhost"NIC ○ Achieved"through"a"combination"of"switchdev,"qdisc"offload,"cls_bpf"and"XDP ○ Work"in"progress ○ Switchdev"architecture"and"qdisc"offload"has"been"upstreamed ○ Next"is"simple"clsact"support ○ Followed"by"cls_bpf"&"XDP ○ Provides"potential"for"BPF"defined"pipelines"in"heterogenous"architectures ○ See"Jakub’s"talk"at"the"microconference"for"more!
- 30. ©"2018"NETRONOME"SYSTEMS,"INC. 30 Credit"(Team) ○ Jakub"Kicinski ○ Jiong"Wang ○ Quentin"Monnet ○ David Beckett ○ Edwin"Peer ○ Johan Moraal ○ Mary Pham