1 2 3 HOWTO for the linux packet generator 4 ------------------------------------ 5 6Date: 041221 7 8Enable CONFIG_NET_PKTGEN to compile and build pktgen.o either in kernel 9or as module. Module is preferred. insmod pktgen if needed. Once running 10pktgen creates a thread on each CPU where each thread has affinity to its CPU. 11Monitoring and controlling is done via /proc. Easiest to select a suitable 12a sample script and configure. 13 14On a dual CPU: 15 16ps aux | grep pkt 17root 129 0.3 0.0 0 0 ? SW 2003 523:20 [pktgen/0] 18root 130 0.3 0.0 0 0 ? SW 2003 509:50 [pktgen/1] 19 20 21For monitoring and control pktgen creates: 22 /proc/net/pktgen/pgctrl 23 /proc/net/pktgen/kpktgend_X 24 /proc/net/pktgen/ethX 25 26 27Tuning NIC for max performance 28============================== 29 30The default NIC setting are (likely) not tuned for pktgen's artificial 31overload type of benchmarking, as this could hurt the normal use-case. 32 33Specifically increasing the TX ring buffer in the NIC: 34 # ethtool -G ethX tx 1024 35 36A larger TX ring can improve pktgen's performance, while it can hurt 37in the general case, 1) because the TX ring buffer might get larger 38than the CPUs L1/L2 cache, 2) because it allow more queueing in the 39NIC HW layer (which is bad for bufferbloat). 40 41One should be careful to conclude, that packets/descriptors in the HW 42TX ring cause delay. Drivers usually delay cleaning up the 43ring-buffers (for various performance reasons), thus packets stalling 44the TX ring, might just be waiting for cleanup. 45 46This cleanup issues is specifically the case, for the driver ixgbe 47(Intel 82599 chip). This driver (ixgbe) combine TX+RX ring cleanups, 48and the cleanup interval is affected by the ethtool --coalesce setting 49of parameter "rx-usecs". 50 51For ixgbe use e.g "30" resulting in approx 33K interrupts/sec (1/30*10^6): 52 # ethtool -C ethX rx-usecs 30 53 54 55Viewing threads 56=============== 57/proc/net/pktgen/kpktgend_0 58Name: kpktgend_0 max_before_softirq: 10000 59Running: 60Stopped: eth1 61Result: OK: max_before_softirq=10000 62 63Most important the devices assigned to thread. Note! A device can only belong 64to one thread. 65 66 67Viewing devices 68=============== 69 70Parm section holds configured info. Current hold running stats. 71Result is printed after run or after interruption. Example: 72 73/proc/net/pktgen/eth1 74 75Params: count 10000000 min_pkt_size: 60 max_pkt_size: 60 76 frags: 0 delay: 0 clone_skb: 1000000 ifname: eth1 77 flows: 0 flowlen: 0 78 dst_min: 10.10.11.2 dst_max: 79 src_min: src_max: 80 src_mac: 00:00:00:00:00:00 dst_mac: 00:04:23:AC:FD:82 81 udp_src_min: 9 udp_src_max: 9 udp_dst_min: 9 udp_dst_max: 9 82 src_mac_count: 0 dst_mac_count: 0 83 Flags: 84Current: 85 pkts-sofar: 10000000 errors: 39664 86 started: 1103053986245187us stopped: 1103053999346329us idle: 880401us 87 seq_num: 10000011 cur_dst_mac_offset: 0 cur_src_mac_offset: 0 88 cur_saddr: 0x10a0a0a cur_daddr: 0x20b0a0a 89 cur_udp_dst: 9 cur_udp_src: 9 90 flows: 0 91Result: OK: 13101142(c12220741+d880401) usec, 10000000 (60byte,0frags) 92 763292pps 390Mb/sec (390805504bps) errors: 39664 93 94Configuring threads and devices 95================================ 96This is done via the /proc interface easiest done via pgset in the scripts 97 98Examples: 99 100 pgset "clone_skb 1" sets the number of copies of the same packet 101 pgset "clone_skb 0" use single SKB for all transmits 102 pgset "burst 8" uses xmit_more API to queue 8 copies of the same 103 packet and update HW tx queue tail pointer once. 104 "burst 1" is the default 105 pgset "pkt_size 9014" sets packet size to 9014 106 pgset "frags 5" packet will consist of 5 fragments 107 pgset "count 200000" sets number of packets to send, set to zero 108 for continuous sends until explicitly stopped. 109 110 pgset "delay 5000" adds delay to hard_start_xmit(). nanoseconds 111 112 pgset "dst 10.0.0.1" sets IP destination address 113 (BEWARE! This generator is very aggressive!) 114 115 pgset "dst_min 10.0.0.1" Same as dst 116 pgset "dst_max 10.0.0.254" Set the maximum destination IP. 117 pgset "src_min 10.0.0.1" Set the minimum (or only) source IP. 118 pgset "src_max 10.0.0.254" Set the maximum source IP. 119 pgset "dst6 fec0::1" IPV6 destination address 120 pgset "src6 fec0::2" IPV6 source address 121 pgset "dstmac 00:00:00:00:00:00" sets MAC destination address 122 pgset "srcmac 00:00:00:00:00:00" sets MAC source address 123 124 pgset "queue_map_min 0" Sets the min value of tx queue interval 125 pgset "queue_map_max 7" Sets the max value of tx queue interval, for multiqueue devices 126 To select queue 1 of a given device, 127 use queue_map_min=1 and queue_map_max=1 128 129 pgset "src_mac_count 1" Sets the number of MACs we'll range through. 130 The 'minimum' MAC is what you set with srcmac. 131 132 pgset "dst_mac_count 1" Sets the number of MACs we'll range through. 133 The 'minimum' MAC is what you set with dstmac. 134 135 pgset "flag [name]" Set a flag to determine behaviour. Current flags 136 are: IPSRC_RND # IP source is random (between min/max) 137 IPDST_RND # IP destination is random 138 UDPSRC_RND, UDPDST_RND, 139 MACSRC_RND, MACDST_RND 140 TXSIZE_RND, IPV6, 141 MPLS_RND, VID_RND, SVID_RND 142 FLOW_SEQ, 143 QUEUE_MAP_RND # queue map random 144 QUEUE_MAP_CPU # queue map mirrors smp_processor_id() 145 UDPCSUM, 146 IPSEC # IPsec encapsulation (needs CONFIG_XFRM) 147 NODE_ALLOC # node specific memory allocation 148 149 pgset spi SPI_VALUE Set specific SA used to transform packet. 150 151 pgset "udp_src_min 9" set UDP source port min, If < udp_src_max, then 152 cycle through the port range. 153 154 pgset "udp_src_max 9" set UDP source port max. 155 pgset "udp_dst_min 9" set UDP destination port min, If < udp_dst_max, then 156 cycle through the port range. 157 pgset "udp_dst_max 9" set UDP destination port max. 158 159 pgset "mpls 0001000a,0002000a,0000000a" set MPLS labels (in this example 160 outer label=16,middle label=32, 161 inner label=0 (IPv4 NULL)) Note that 162 there must be no spaces between the 163 arguments. Leading zeros are required. 164 Do not set the bottom of stack bit, 165 that's done automatically. If you do 166 set the bottom of stack bit, that 167 indicates that you want to randomly 168 generate that address and the flag 169 MPLS_RND will be turned on. You 170 can have any mix of random and fixed 171 labels in the label stack. 172 173 pgset "mpls 0" turn off mpls (or any invalid argument works too!) 174 175 pgset "vlan_id 77" set VLAN ID 0-4095 176 pgset "vlan_p 3" set priority bit 0-7 (default 0) 177 pgset "vlan_cfi 0" set canonical format identifier 0-1 (default 0) 178 179 pgset "svlan_id 22" set SVLAN ID 0-4095 180 pgset "svlan_p 3" set priority bit 0-7 (default 0) 181 pgset "svlan_cfi 0" set canonical format identifier 0-1 (default 0) 182 183 pgset "vlan_id 9999" > 4095 remove vlan and svlan tags 184 pgset "svlan 9999" > 4095 remove svlan tag 185 186 187 pgset "tos XX" set former IPv4 TOS field (e.g. "tos 28" for AF11 no ECN, default 00) 188 pgset "traffic_class XX" set former IPv6 TRAFFIC CLASS (e.g. "traffic_class B8" for EF no ECN, default 00) 189 190 pgset stop aborts injection. Also, ^C aborts generator. 191 192 pgset "rate 300M" set rate to 300 Mb/s 193 pgset "ratep 1000000" set rate to 1Mpps 194 195Example scripts 196=============== 197 198A collection of small tutorial scripts for pktgen is in examples dir. 199 200pktgen.conf-1-1 # 1 CPU 1 dev 201pktgen.conf-1-2 # 1 CPU 2 dev 202pktgen.conf-2-1 # 2 CPU's 1 dev 203pktgen.conf-2-2 # 2 CPU's 2 dev 204pktgen.conf-1-1-rdos # 1 CPU 1 dev w. route DoS 205pktgen.conf-1-1-ip6 # 1 CPU 1 dev ipv6 206pktgen.conf-1-1-ip6-rdos # 1 CPU 1 dev ipv6 w. route DoS 207pktgen.conf-1-1-flows # 1 CPU 1 dev multiple flows. 208 209Run in shell: ./pktgen.conf-X-Y It does all the setup including sending. 210 211 212Interrupt affinity 213=================== 214Note when adding devices to a specific CPU there good idea to also assign 215/proc/irq/XX/smp_affinity so the TX-interrupts gets bound to the same CPU. 216as this reduces cache bouncing when freeing skb's. 217 218Enable IPsec 219============ 220Default IPsec transformation with ESP encapsulation plus Transport mode 221could be enabled by simply setting: 222 223pgset "flag IPSEC" 224pgset "flows 1" 225 226To avoid breaking existing testbed scripts for using AH type and tunnel mode, 227user could use "pgset spi SPI_VALUE" to specify which formal of transformation 228to employ. 229 230 231Current commands and configuration options 232========================================== 233 234** Pgcontrol commands: 235 236start 237stop 238 239** Thread commands: 240 241add_device 242rem_device_all 243max_before_softirq 244 245 246** Device commands: 247 248count 249clone_skb 250debug 251 252frags 253delay 254 255src_mac_count 256dst_mac_count 257 258pkt_size 259min_pkt_size 260max_pkt_size 261 262mpls 263 264udp_src_min 265udp_src_max 266 267udp_dst_min 268udp_dst_max 269 270flag 271 IPSRC_RND 272 IPDST_RND 273 UDPSRC_RND 274 UDPDST_RND 275 MACSRC_RND 276 MACDST_RND 277 TXSIZE_RND 278 IPV6 279 MPLS_RND 280 VID_RND 281 SVID_RND 282 FLOW_SEQ 283 QUEUE_MAP_RND 284 QUEUE_MAP_CPU 285 UDPCSUM 286 IPSEC 287 NODE_ALLOC 288 289dst_min 290dst_max 291 292src_min 293src_max 294 295dst_mac 296src_mac 297 298clear_counters 299 300dst6 301src6 302 303flows 304flowlen 305 306rate 307ratep 308 309References: 310ftp://robur.slu.se/pub/Linux/net-development/pktgen-testing/ 311ftp://robur.slu.se/pub/Linux/net-development/pktgen-testing/examples/ 312 313Paper from Linux-Kongress in Erlangen 2004. 314ftp://robur.slu.se/pub/Linux/net-development/pktgen-testing/pktgen_paper.pdf 315 316Thanks to: 317Grant Grundler for testing on IA-64 and parisc, Harald Welte, Lennert Buytenhek 318Stephen Hemminger, Andi Kleen, Dave Miller and many others. 319 320 321Good luck with the linux net-development. 322