[Oisf-users] Capture loss ~50% reported using Myricom with Suri v 5.0.2

Erich Lerch erich.lerch at gmail.com
Fri Jun 19 20:17:14 UTC 2020


Hi

Craig is right, we also have huge numbers there, and no packet loss.
These settings really are important.

That's how we start suri:

SNF_NUM_RINGS=10 SNF_FLAGS=0x1 SNF_DATARING_SIZE=12884901888
SNF_DESCRING_SIZE=3221225472 LD_PRELOAD=... \
/opt/suricata/bin/suricata -v -c suricata.yaml -i snf0 -D

The "pcap" part from yuricata.yaml:

# ----------------------------
pcap:
  - interface: snf0
    threads: 10
    buffer-size: 2gb
    checksum-checks: no
    promisc: no
    snaplen: 1520
    bpf-filter: "<your_filter>"
# ----------------------------


Cheers,
Erich


On 19.06.20 20:29, Edgmand, Craig wrote:
> Hi Fatema,
> 
>  
> 
> That’s interesting because the way I read it from this article
> 
>  
> 
> https://redmine.openinfosecfoundation.org/projects/suricata/wiki/Myricom
> 
>  
> 
> You could set them on the command line like this…
> 
>  
> 
> SNF_NUM_RINGS=16 SNF_DATARING_SIZE=17179869184
> SNF_DESCRING_SIZE=4294967296 SNF_FLAGS=0x1 suricata -c suricata.yaml -i
> eth5 --runmode=workers
> 
>  
> 
>  
> 
> I only use Myricom cards on my Zeek servers so I haven’t tested it and
> it has no such restrictions.
> 
>  
> 
> Good luck,
> 
>  
> 
> Craig
> 
>  
> 
> *From:*fatema bannatwala <fatema.bannatwala at gmail.com>
> *Sent:* Friday, June 19, 2020 1:16 PM
> *To:* Edgmand, Craig <craig.edgmand at okstate.edu>
> *Cc:* Open Information Security Foundation
> <oisf-users at lists.openinfosecfoundation.org>
> *Subject:* Re: [Oisf-users] Capture loss ~50% reported using Myricom
> with Suri v 5.0.2
> 
>  
> 
> *CAUTION:*This email originated from outside of the organization. Do not
> click links or open attachments unless you recognize the sender and know
> the content is safe
> 
> Thanks Craig, I tried increasing SNF_DATARING_SIZE, but that variable
> gets overwritten and controlled by pcap.buffer-size in suricata.yml file
> which allows a max of 2gb, can't set more than that.
> 
> Hence setting SNF_DATARING_SIZE explicitly has no effect since. 
> 
>  
> 
> This has been done:
> 
> The following pull request opened by Myricom in the libpcap project
> indicates that a future SNF software release could provide support for
> setting the SNF_DATARING_SIZE via the pcap.buffer-size yaml setting:
> 
> Ref: https://github.com/the-tcpdump-group/libpcap/pull/435
> <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fthe-tcpdump-group%2Flibpcap%2Fpull%2F435&data=02%7C01%7Ccraig.edgmand%40okstate.edu%7Cd4444c14ab184963043408d8147cf441%7C2a69c91de8494e34a230cdf8b27e1964%7C0%7C0%7C637281874192318869&sdata=jhJDwiTawSglR4%2FOm33%2F685%2B2oXHYSnzu0ysXIj0%2BaE%3D&reserved=0>
> 
>  
> 
>  
> 
>  
> 
> On Fri, Jun 19, 2020 at 11:09 AM Edgmand, Craig
> <craig.edgmand at okstate.edu <mailto:craig.edgmand at okstate.edu>> wrote:
> 
>     Hi Fetema,
> 
>      
> 
>     Not an expert, but have you tried increasing these
> 
>      
> 
>     SNF_DATARING_SIZE=4096MB
> 
>     SNF_DESCRING_SIZE=1024MB
> 
>      
> 
>     If you have the memory, I would multiply these by a factor of 4.  On
>     my servers these numbers are huge. Might also increase buffer size.
> 
>      
> 
>     Thanks,
> 
>      
> 
>     Craig
> 
>      
> 
>     *From:*Oisf-users
>     <oisf-users-bounces at lists.openinfosecfoundation.org
>     <mailto:oisf-users-bounces at lists.openinfosecfoundation.org>> *On
>     Behalf Of *fatema bannatwala
>     *Sent:* Friday, June 19, 2020 12:59 PM
>     *To:* Open Information Security Foundation
>     <oisf-users at lists.openinfosecfoundation.org
>     <mailto:oisf-users at lists.openinfosecfoundation.org>>
>     *Subject:* [Oisf-users] Capture loss ~50% reported using Myricom
>     with Suri v 5.0.2
> 
>      
> 
>     *CAUTION:*This email originated from outside of the organization. Do
>     not click links or open attachments unless you recognize the sender
>     and know the content is safe
> 
>     Hello Experts,
> 
>      
> 
>     Need some help tuning down our prod suricata box running Suricata v
>     5.0.2 with Myricom NIC: 10G-PCIE-8B-S myri_snf 3.0.20.50894
> 
>      
> 
>     It is consistently reporting ~50% capture loss, calculated based off
>     of the capture.kernel_packets and capture.kernel_dropped values
>     reported in stats.log file.
> 
>      
> 
>     I have followed
>     the https://blog.inliniac.net/2012/07/10/suricata-on-myricom-capture-cards/
>     <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fblog.inliniac.net%2F2012%2F07%2F10%2Fsuricata-on-myricom-capture-cards%2F&data=02%7C01%7Ccraig.edgmand%40okstate.edu%7Cd4444c14ab184963043408d8147cf441%7C2a69c91de8494e34a230cdf8b27e1964%7C0%7C0%7C637281874192328864&sdata=5KgANusNnHK7cijv1B0rUDomBZaosOK8AuD9mTfd2Dg%3D&reserved=0>
> 
>     guide to pin the cpus to the worker nodes and use pcap.buffer_size
>     to increase the SNF dataring size, but no effect..
> 
>      
> 
>     We have one Myri card connected to p2p1 and two NUMA nodes, each
>     with 8 cores (16 HT):
> 
>     NUMA node0 CPU(s):     0-7,16-23
>     NUMA node1 CPU(s):     8-15,24-31
> 
>     OS: Centos 7
> 
>      
> 
>     Any help in the right direction would be appreciated! :)
> 
>      
> 
>     Thanks!
> 
>     Fatema
> 
>      
> 
>     Following is settings from suricata.yml file
> 
>      
> 
>     # Myricom support
> 
>     pcap:
> 
>       - interface: p2p1
> 
>         threads: 14
> 
>         buffer-size: 2gb
> 
>         checksum-checks: no
> 
>     pcap-file:
> 
>       checksum-checks: auto
> 
>      
> 
>     threading:
> 
>       set-cpu-affinity: yes
> 
>       cpu-affinity:
> 
>         - management-cpu-set:
> 
>             cpu: [ "0" ]
> 
>             mode: "balanced"
> 
>             prio:
> 
>               default: "low"
> 
>         - worker-cpu-set:
> 
>             cpu: [ "1-7","9-15" ]
> 
>             mode: "exclusive"
> 
>             prio:
> 
>               default: "high"
> 
>      
> 
>     Following is the currently recorded stats.log:
> 
>     ------------------------------------------------------------------------------------
> 
>     Date: 6/19/2020 -- 10:55:36 (uptime: 0d, 04h 04m 10s)
> 
>     ------------------------------------------------------------------------------------
> 
>     Counter                                       | TM Name            
>           | Value
> 
>     ------------------------------------------------------------------------------------
> 
>     capture.kernel_packets                        | Total              
>           | 28447139411
> 
>     capture.kernel_drops                          | Total              
>           | 27910518132
> 
>     capture.kernel_ifdrops                        | Total              
>           | 6034
> 
>     decoder.pkts                                  | Total              
>           | 536633135
> 
>      
> 
>      
> 
>     SNF parameters:
> 
>      
> 
>      
> 
>     SNF_APP_ID=32
> 
>     SNF_DATARING_SIZE=4096MB
> 
>     SNF_DESCRING_SIZE=1024MB
> 
>     SNF_NUM_RINGS=14
> 
>     SNF_FLAGS=0x1
> 
>      
> 
>     LD_PRELOAD="/opt/snf/lib/libpcap.so.1"
> 
>      
> 
>     OPTIONS="--user suricata --group suricata --pcap"
> 
> 
> _______________________________________________
> NOTE: this list will soon be closed. New topics should be brought to: https://forum.suricata.io
> 


More information about the Oisf-users mailing list