[Oisf-devel] suricata testing

Victor Julien victor at inliniac.net
Fri May 14 09:52:56 EDT 2010


rmkml wrote:
> Hi SDT (Suricata Devel Team),
> Im start playing with 16 core server for suricata (v0.9.1pre git12may).
> Im test with sp*rent test center gig and udp only src_port=dst_port=1024, size 1460 (zero filled) at this time on IDS mode.
> system is rhelv5.5i386 without pfring, but in this test, it's not a pb for me.
> network card is internal Broadcom NetXtreme II Gigabit Ethernet Driver bnx2 v2.0.2 (Aug 21, 2009).
> 
> 1) with all my personal signatures (+old community rules)
> -- 7565 signatures processed. 8 are IP-only rules, 6567 are inspecting packet payload, 1490 inspect application layer
> result: 1597% cpu (16core), udp frame rate sending by sp*rent 12.668/18.496.000octet/148MBit (15% sending possibility)
> suricata stats.log file:
>   decoder.pkts              | Decode1             | 4076896
>   decoder.pkts_per_sec      | Decode1             | 15044.714286
>   decoder.bytes             | Decode1             | 5935960576
>   decoder.bytes_per_sec     | Decode1             | 21905104.000000
>   decoder.mbit_per_sec      | Decode1             | 175.240832
>   decoder.ipv4              | Decode1             | 4076896
>   decoder.ethernet          | Decode1             | 4076896
>   decoder.udp               | Decode1             | 4076896
>   decoder.avg_pkt_size      | Decode1             | 1456.000000
>   decoder.max_pkt_size      | Decode1             | 1456
>   (removed all field contains 0)
> top output:
>   top - 14:42:59 up 1 day, 22:06, 4 users, load average: 16.36, 13.77, 9.79
>   Tasks: 236 total,   2 running, 234 sleeping,   0 stopped,   0 zombie
>   Cpu0  :  6.9%us, 13.9%sy, 79.2%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu1  :100.0%us,  0.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu2  :100.0%us,  0.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu3  :100.0%us,  0.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu4  : 99.0%us,  1.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu5  :100.0%us,  0.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu6  : 99.0%us,  1.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu7  : 99.0%us,  1.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu8  :100.0%us,  0.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu9  : 99.0%us,  1.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu10 : 99.0%us,  1.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu11 :100.0%us,  0.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu12 :100.0%us,  0.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu13 :100.0%us,  0.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu14 :100.0%us,  0.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
>   Cpu15 : 95.0%us,  0.0%sy,  0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 5.0%si, 0.0%st
>   Mem:  12464792k total, 12057272k used,   407520k free,   170072k buffers
>   Swap: 10482404k total,     2144k used, 10480260k free,  9272564k cached
>    PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
>   8059 root      15   0  504m 253m 1348 S 1595.9  2.1 119:10.11 suricata
> 
> 2) same test without signature on suricata:
> top output:
>     PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
>   10660 root      15   0  280m  31m 1312 S 88.3  0.3   0:30.11 suricata
> 
> 3) suricata without signature receiving 1Gbit rate:
> top output:
>   top - 14:55:16 up 1 day, 22:18,  4 users,  load average: 4.53, 5.69, 7.99
>   Tasks: 236 total,   1 running, 235 sleeping,   0 stopped,   0 zombie
>   Cpu0  : 29.4%us, 60.8%sy, 0.0%ni,  9.8%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu1  :  1.0%us, 12.9%sy, 0.0%ni, 86.1%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu2  :  0.0%us, 10.9%sy, 0.0%ni, 89.1%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu3  :  1.0%us, 14.7%sy, 0.0%ni, 84.3%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu4  :  0.0%us, 12.0%sy, 0.0%ni, 88.0%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu5  :  1.0%us, 12.0%sy, 0.0%ni, 87.0%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu6  :  0.0%us, 11.0%sy, 0.0%ni, 89.0%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu7  :  0.0%us, 13.9%sy, 0.0%ni, 86.1%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu8  :  0.0%us, 11.9%sy, 0.0%ni, 88.1%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu9  :  0.0%us, 13.1%sy, 0.0%ni, 86.9%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu10 :  1.0%us, 10.9%sy, 0.0%ni, 88.1%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu11 :  0.0%us, 13.0%sy, 0.0%ni, 87.0%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu12 :  0.0%us, 12.0%sy, 0.0%ni, 88.0%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu13 :  1.0%us, 13.9%sy, 0.0%ni, 85.1%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu14 :  1.0%us, 13.0%sy, 0.0%ni, 86.0%id, 0.0%wa, 0.0%hi,  0.0%si, 0.0%st
>   Cpu15 :  0.0%us, 13.1%sy, 0.0%ni, 72.7%id, 0.0%wa, 0.0%hi, 14.1%si, 0.0%st
> Mem:  12464792k total, 11836420k used,   628372k free,   170492k buffers
> Swap: 10482404k total,     2144k used, 10480260k free,  9273984k cached
>    PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  COMMAND
> 10660 root      15   0  280m  31m 1312 S 284.3  0.3  10:42.76 suricata
> suricata stats.log file:
>   decoder.pkts              | Decode1             | 27887010
>   decoder.pkts_per_sec      | Decode1             | 126469.500000
>   decoder.bytes             | Decode1             | 40603486560
>   decoder.bytes_per_sec     | Decode1             | 184139592.000000
>   decoder.mbit_per_sec      | Decode1             | 1473.116736
>   decoder.ipv4              | Decode1             | 27887010
>   decoder.ethernet          | Decode1             | 27887010
>   decoder.udp               | Decode1             | 27887010
>   decoder.avg_pkt_size      | Decode1             | 1456.000000
>   decoder.max_pkt_size      | Decode1             | 1456

Interesting numbers rmkml, thanks. The pkts_per_sec, bytes_per_sec and
mbit_per_sec counters are completely unreliable at this point, fixing
them is still on our todo list.

Did both test runs send the same amount of packets? I see that the sigs
run did 4M packets, the bare run 27M.

Cheers,
Victor

-- 
---------------------------------------------
Victor Julien
http://www.inliniac.net/
PGP: http://www.inliniac.net/victorjulien.asc
---------------------------------------------



More information about the Oisf-devel mailing list