freebsd-skq/sys
Marko Zec 2aca58e16f Introduce DXR as an IPv4 longest prefix matching / FIB module
DXR maintains compressed lookup structures with a trivial search
procedure.  A two-stage trie is indexed by the more significant bits of
the search key (IPv4 address), while the remaining bits are used for
finding the next hop in a sorted array.  The tradeoff between memory
footprint and search speed depends on the split between the trie and
the remaining binary search.  The default of 20 bits of the key being
used for trie indexing yields good performance (see below) with
footprints of around 2.5 Bytes per prefix with current BGP snapshots.

Rebuilding lookup structures takes some time, which is compensated for by
batching several RIB change requests into a single FIB update, i.e. FIB
synchronization with the RIB may be delayed for a fraction of a second.
RIB to FIB synchronization, next-hop table housekeeping, and lockless
lookup capability is provided by the FIB_ALGO infrastructure.

DXR works well on modern CPUs with several MBytes of caches, especially
in VMs, where is outperforms other currently available IPv4 FIB
algorithms by a large margin.

Synthetic single-thread LPM throughput test method:

kldload test_lookup; kldload dpdk_lpm4; kldload fib_dxr
sysctl net.route.test.run_lps_rnd=N
sysctl net.route.test.run_lps_seq=N

where N is the number of randomly generated keys (IPv4 addresses) which
should be chosen so that each test iteration runs for several seconds.

Each reported score represents the best of three runs, in million
lookups per second (MLPS), for two bechmarks (RND & SEQ) with two FIBs:

host: single interface address, local subnet route + default route
BGP: snapshot from linx.routeviews.org, 887957 prefixes, 496 next hops

Bhyve VM on an Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60 GHz:
inet.algo         host, RND    host, SEQ    BGP, RND    BGP, SEQ
bsearch4             40.6         20.2         N/A         N/A
radix4                7.8          3.8         1.2         0.6
radix4_lockless      18.0          9.0         1.6         0.8
dpdk_lpm4            14.4          5.0        14.6         5.0
dxr                  70.3         34.7        43.0        19.5

Intel(R) Core(TM) i5-5300U CPU @ 2.30 GHz:
inet.algo         host, RND    host, SEQ    BGP, RND    BGP, SEQ
bsearch4             47.0         23.1         N/A         N/A
radix4                8.5          4.2         1.9         1.0
radix4_lockless      19.2          9.5         2.5         1.2
dpdk_lpm4            31.2          9.4        31.6         9.3
dxr                  84.9         41.4        51.7        23.6

Intel(R) Core(TM) i7-4771 CPU @ 3.50 GHz:
inet.algo         host, RND    host, SEQ    BGP, RND    BGP, SEQ
bsearch4             59.5         29.4         N/A         N/A
radix4               10.8          5.5         2.5         1.3
radix4_lockless      24.7         12.0         3.1         1.6
dpdk_lpm4            29.1          9.0        30.2         9.1
dxr                 101.3         49.9        69.8        32.5

AMD Ryzen 7 3700X 8-Core Processor @ 3.60 GHz:
inet.algo         host, RND    host, SEQ    BGP, RND    BGP, SEQ
bsearch4             70.8         35.4         N/A         N/A
radix4               14.4          7.2         2.8         1.4
radix4_lockless      30.2         15.1         3.7         1.8
dpdk_lpm4            29.9          9.0        30.0         8.9
dxr                 163.3         81.5        99.5        44.4

AMD Ryzen 5 5600X 6-Core Processor @ 3.70 GHz:
inet.algo         host, RND    host, SEQ    BGP, RND    BGP, SEQ
bsearch4             93.6         46.7         N/A         N/A
radix4               18.9          9.3         4.3         2.1
radix4_lockless      37.2         18.6         5.3         2.7
dpdk_lpm4            51.8         15.1        51.6        14.9
dxr                 218.2        103.3       114.0        49.0

Reviewed by:	melifaro
MFC after:	1 week
Differential Revision: https://reviews.freebsd.org/D29821
2021-05-05 13:45:52 +02:00
..
amd64 linux(4): fix ptrace(2) to properly handle orig_rax 2021-05-04 15:21:06 +01:00
arm Also enable IPIs on 32-bit arm 2021-05-03 08:36:57 +00:00
arm64 Enable IPIs on CPU 0 on arm and arm64 2021-05-02 07:43:34 +00:00
bsm
cam cam: fix integer overflow during inquiry 2021-05-03 15:20:17 +01:00
cddl fbt: Remove some handling for multiple CTF containers 2021-04-02 17:49:13 -04:00
compat linux(4): make linkat(2) handle AT_EMPTY_PATH 2021-05-04 13:09:46 +01:00
conf riscv: Remove old qemu compatibility code 2021-04-27 16:22:04 -05:00
contrib zfs: restore copyright disclaimer change from 4b84b4cca 2021-04-26 22:16:50 +02:00
crypto ossl: Don't encryt/decrypt too much data for chacha20. 2021-04-01 15:49:07 -07:00
ddb ddb: replace watchpoint set/clear functions 2021-03-29 12:05:44 -03:00
dev cxgbe(4): Use ifaddr_event_ext instead of ifaddr_event for CLIP management. 2021-05-04 20:16:25 -07:00
dts dts: Bump the freebsd branding version to 5.10 2021-03-23 15:02:21 +01:00
fs nfsclient: Copy only initialized fields in nfs_getattr() 2021-05-04 08:53:57 -04:00
gdb gdb: report specific stop reason for watchpoints 2021-03-30 11:36:41 -03:00
geom gmirror: Pre-allocate the timeout event structure 2021-03-11 15:45:15 -05:00
gnu Remove the old dts imported tree. 2021-01-15 20:09:55 +01:00
i386 Create VM_MEMATTR_DEVICE on all architectures 2021-04-12 06:15:31 +00:00
isa Remove more remnants of sio(4) 2021-04-07 14:33:02 -04:00
kern kern/intr: declare interrupt vectors unsigned 2021-05-03 13:24:30 -04:00
kgssapi opencrypto: Introduce crypto_dispatch_async() 2021-02-08 09:19:19 -05:00
libkern x86: remove gcov kernel support 2021-04-02 15:41:51 +03:00
mips OCF: Remove support for asymmetric cryptographic operations. 2021-04-12 14:28:43 -07:00
modules Introduce DXR as an IPv4 longest prefix matching / FIB module 2021-05-05 13:45:52 +02:00
net ifconfig: Minor documentation fix 2021-05-03 14:38:52 +03:00
net80211 net80211: prefix get_random_bytes() with net80211_ 2021-03-24 22:16:09 +00:00
netgraph netgraph/ng_bridge: learn MACs via control message 2021-05-04 22:14:59 +02:00
netinet Introduce DXR as an IPv4 longest prefix matching / FIB module 2021-05-05 13:45:52 +02:00
netinet6 Add missing sockaddr length and family validation to various protocols 2021-05-03 13:35:19 -04:00
netipsec Add missing sockaddr length and family validation to various protocols 2021-05-03 13:35:19 -04:00
netpfil pf: Fix IP checksum on reassembly 2021-04-30 08:19:46 +02:00
netsmb
nfs Fix panic when using BOOTP to resolve root path. 2021-03-28 14:02:40 -05:00
nfsclient nfs: Cleanup dead files 2021-03-17 06:16:31 +11:00
nfsserver nfs: Cleanup dead files 2021-03-17 06:16:31 +11:00
nlm
ofed Add missing sockaddr length and family validation to various protocols 2021-05-03 13:35:19 -04:00
opencrypto OCF: Remove support for asymmetric cryptographic operations. 2021-04-12 14:28:43 -07:00
powerpc powerpc/xive: Remove POWER9 DD1 IRQ bits 2021-05-01 16:18:02 -05:00
riscv riscv: Remove old qemu compatibility code 2021-04-27 16:22:04 -05:00
rpc nfsd: fix a NFSv4.1 Linux client mount stuck in CLOSE_WAIT 2021-04-27 15:32:35 -07:00
security tcp_input/syncache: acquire only read lock on PCB for SYN,!ACK packets 2021-04-12 08:25:31 -07:00
sys param.h: Fix typos 2021-05-05 00:50:35 -06:00
teken
tests Revise FIB lookups per second benchmarking routines. 2021-05-05 12:28:17 +02:00
tools newbus: remove support for SINGLETON 2021-04-26 11:41:08 -06:00
ufs b_vflags update requries bufobj lock 2021-04-15 15:47:42 +03:00
vm Improve UMA cache reclamation. 2021-05-02 19:45:23 -04:00
x86 Wait longer for a previous IPI to be sent 2021-04-30 13:32:29 -05:00
xdr
xen xen: move x86-specific xen_vector_callback_enabled to sys/x86 2021-03-15 14:20:21 +01:00
Makefile