<div dir="ltr">Sadly, we have migrated to el repo 4.4.69 lt kernels. It was too difficult to maintain patches for the stock kernel modules on rhel7. :/<div><br></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Wed, May 31, 2017 at 11:15 AM, Cooper F. Nelson <span dir="ltr"><<a href="mailto:cnelson@ucsd.edu" target="_blank">cnelson@ucsd.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">It looks like this doesn't work anymore on current kernel revisions.<br>
<br>
Does anyone have specific "known good" kernel/suricata revision that<br>
this patch works with (so I can revert to it?)<br>
<br>
Thanks,<br>
-Coop<br>
<div class="HOEnZb"><div class="h5"><br>
On 12/29/2016 3:20 AM, erik clark wrote:<br>
> Yes, thats the patch at <a href="http://marc.info" rel="noreferrer" target="_blank">marc.info</a> in the previous email. Please note the<br>
> submitter of that patch. :)<br>
><br>
> On Thu, Dec 29, 2016 at 4:10 AM, Peter Manev <<a href="mailto:petermanev@gmail.com">petermanev@gmail.com</a>> wrote:<br>
><br>
>><br>
>><br>
>> On 28 Dec 2016, at 15:00, erik clark <<a href="mailto:philosnef@gmail.com">philosnef@gmail.com</a>> wrote:<br>
>><br>
>> (patch for ixgbe)<br>
>> <a href="http://marc.info/?l=linux-netdev&m=148181173415107&w=2" rel="noreferrer" target="_blank">http://marc.info/?l=linux-<wbr>netdev&m=148181173415107&w=2</a><br>
>><br>
>> (patch to ixgbe/src/kompat.h since it wont compile on rhel7.3 due to<br>
>> kernel version issues. None of this is pf_ring specific)<br>
>> <a href="https://raw.githubusercontent.com/ntop/PF_RING/41b6eb733e295" rel="noreferrer" target="_blank">https://raw.githubusercontent.<wbr>com/ntop/PF_RING/41b6eb733e295</a><br>
>> c91375b135d2816dbdd09b4b548/<wbr>drivers/intel/ixgbe/ixgbe-4.1.<br>
>> 5-zc/src/kcompat.h<br>
>><br>
>><br>
>> In a different mail you mentioned that there is also a patch from Red Hat<br>
>> with regards to at-packet not working on this kernel version - is this<br>
>> fixed/working now?<br>
>><br>
>><br>
>> (ethtool arguments and irq setting)<br>
>><br>
>> ethtool -C em1 rx-usecs 1 adaptive-rx off<br>
>> ethtool -G em1 rx 4096 tx 4096<br>
>> for x in tso gro lro gso rx tx sg; do ethtool -K em1 $x off; done<br>
>> /opt/src/ixgbe-4.4.6/scripts/<wbr>set_irq_affinity em1<br>
>> ethtool -X em1 hkey 6d:5a:6d:5a:6d:5a:6d:5a:6d:5a:<br>
>> 6d:5a:6d:5a:6d:5a:6d:5a:6d:5a:<wbr>6d:5a:6d:5a:6d:5a:6d:5a:6d:5a:<br>
>> 6d:5a:6d:5a:6d:5a:6d:5a:6d:5a<br>
>> ethtool -N em1 rx-flow-hash tcp4 sdfn<br>
>> ethtool -N em1 rx-flow-hash udp4 sdfn<br>
>><br>
>><br>
>> Can you confirm all flows are good for tcp/udp/4/6?<br>
>> (And how do you confirm it?)<br>
>><br>
>><br>
>><br>
>><br>
>> I have 64 cores, and set_irq_affinity pulls a full set of 63 rss queues.<br>
>> Thanks!<br>
>><br>
>> On Sat, Dec 24, 2016 at 1:28 PM, erik clark <<a href="mailto:philosnef@gmail.com">philosnef@gmail.com</a>> wrote:<br>
>><br>
>>> I will post that on Wednesday when I get back to work. Its 6? ethtool<br>
>>> statements, and 2 ixgbe patches (for rhel7 at least). Anything else should<br>
>>> be just 1 patch. This is running the 4.4.6 ixgbe released from intel<br>
>>> directly. This has worked for the most recent 3 kernels under RHEL7.<br>
>>><br>
>>> On Sat, Dec 24, 2016 at 12:51 PM, Peter Manev <<a href="mailto:petermanev@gmail.com">petermanev@gmail.com</a>><br>
>>> wrote:<br>
>>><br>
>>>><br>
>>>><br>
>>>>> On 24 Dec 2016, at 18:22, erik clark <<a href="mailto:philosnef@gmail.com">philosnef@gmail.com</a>> wrote:<br>
>>>>><br>
>>>>> I have seen several places commenting that you should set the RSS<br>
>>>> queue to 1. However, when examining af_packet with Bro, a patch released<br>
>>>> from Redhat for the ixgbe kernel module, and some ethtool tweaking, we have<br>
>>>> found that (for Bro at least) running a full 63 (we have 54 cores) RSS<br>
>>>> queues vastly improves performance, and keeps state intact across sessions.<br>
>>>>><br>
>>>>> Based on this update, which fixes the broken implementation of setting<br>
>>>> a symmetric hash in the hardware of the card<br>
>>>><br>
>>>> Can you please share a bit in a bit more detail-<br>
>>>> Which ixgbe/kernel version that is ?<br>
>>>> Which patch is it ?<br>
>>>> What is the ethtool tweaking procedure?<br>
>>>><br>
>>>> Thanks<br>
>>>><br>
>>>>> (again ixgbe, not tested with i40e), is it still necessary to run one<br>
>>>> queue? If so, you can't run Bro and Suri on the same box with af_packet and<br>
>>>> get equivalent performance out of both tools. Having run Suri with 63<br>
>>>> queues for a week now, it seems performance is considerably better than<br>
>>>> with pf_ring, and I can not find any unusual behavior in my alerts...<br>
>>>>><br>
>>>>> ______________________________<wbr>_________________<br>
>>>>> Suricata IDS Users mailing list: <a href="mailto:oisf-users@openinfosecfoundation.org">oisf-users@<wbr>openinfosecfoundation.org</a><br>
>>>>> Site: <a href="http://suricata-ids.org" rel="noreferrer" target="_blank">http://suricata-ids.org</a> | Support:<br>
>>>> <a href="http://suricata-ids.org/support/" rel="noreferrer" target="_blank">http://suricata-ids.org/<wbr>support/</a><br>
>>>>> List: <a href="https://lists.openinfosecfoundation.org/mailman/listinfo/ois" rel="noreferrer" target="_blank">https://lists.<wbr>openinfosecfoundation.org/<wbr>mailman/listinfo/ois</a><br>
>>>> f-users<br>
>>>><br>
>>><br>
>>><br>
>><br>
><br>
><br>
><br>
> ______________________________<wbr>_________________<br>
> Suricata IDS Users mailing list: <a href="mailto:oisf-users@openinfosecfoundation.org">oisf-users@<wbr>openinfosecfoundation.org</a><br>
> Site: <a href="http://suricata-ids.org" rel="noreferrer" target="_blank">http://suricata-ids.org</a> | Support: <a href="http://suricata-ids.org/support/" rel="noreferrer" target="_blank">http://suricata-ids.org/<wbr>support/</a><br>
> List: <a href="https://lists.openinfosecfoundation.org/mailman/listinfo/oisf-users" rel="noreferrer" target="_blank">https://lists.<wbr>openinfosecfoundation.org/<wbr>mailman/listinfo/oisf-users</a><br>
><br>
<br>
<br>
</div></div><span class="HOEnZb"><font color="#888888">--<br>
Cooper Nelson<br>
IT Security - Information Technology Services<br>
University of California San Diego<br>
<a href="tel:%28858%29%20534-6487" value="+18585346487">(858) 534-6487</a> - <a href="mailto:cnelson@ucsd.edu">cnelson@ucsd.edu</a><br>
<a href="https://cybersecurity.ucsd.edu" rel="noreferrer" target="_blank">https://cybersecurity.ucsd.edu</a><br>
<br>
</font></span></blockquote></div><br></div>