Hi Derek
what if you run pfcount -i zc:eth5 ? 
Just to make sure: did you try manually removing all pf_ring.ko and ixgbe_zc.ko 
occurrences before reinstalling pf_ring and drivers, to force dkms reinstalling 
the modules?

Alfredo

> On 3 Nov 2016, at 01:53, Spransy, Derek <[email protected]> wrote:
> 
> Hi Alfredo,
> 
> As far as I can tell that is the case. I actually removed all pf_ring and 
> n2disk components before I updated them and reinstalled the RPMs from scratch 
> (with no errors reported). 
> 
> lsmod output:
> pf_ring               691110  2 
> ixgbe_zc              303005  0 
> ptp                     9614  2 ixgbe_zc,tg3
> 
> $ ls -la /lib/modules/2.6.32-642.4.2.el6.x86_64/extra/
> total 1900
> drwxr-xr-x 2 root root   4096 Nov  2 15:47 .
> drwxr-xr-x 7 root root   4096 Nov  2 15:48 ..
> -rw-r--r-- 1 root root 436768 Nov  2 15:42 e1000e_zc.ko
> -rw-r--r-- 1 root root 519912 Nov  2 15:47 i40e_zc.ko
> -rw-r--r-- 1 root root 322016 Nov  2 15:41 igb_zc.ko
> -rw-r--r-- 1 root root 479520 Nov  2 15:45 ixgbe_zc.ko
> -rw-r--r-- 1 root root 171616 Nov  2 15:43 pf_ring.ko
> 
> $ cat /proc/net/pf_ring/info 
> PF_RING Version          : 6.4.1 
> (6.4.1-stable:c1fbe364b3cc3f5992f489190ddbb79131109926)
> Total rings              : 0
> 
> Standard (non ZC) Options
> Ring slots               : 65534
> Slot version             : 16
> Capture TX               : Yes [RX+TX]
> IP Defragment            : No
> Socket Mode              : Standard
> Total plugins            : 0
> Cluster Fragment Queue   : 0
> Cluster Fragment Discard : 0
> 
> $ cat /proc/net/pf_ring/dev/eth5/info 
> Name:              eth5
> Index:             8
> Address:           90:E2:BA:11:0C:34
> Polling Mode:      NAPI/ZC
> Type:              Ethernet
> Family:            Intel ixgbe 82599
> Max # TX Queues:   1
> # Used RX Queues:  1
> Num RX Slots:      32768
> Num TX Slots:      32768
> 
> Thanks,
> Derek
> 
> 
> 
> From: [email protected] 
> <[email protected]> on behalf of Alfredo Cardigliano 
> <[email protected]>
> Sent: Wednesday, November 2, 2016 6:40 PM
> To: [email protected]
> Subject: Re: [Ntop-misc] n2disk dumping with RHEL6 Kernel 
> 2.6.32-642.4.2.el6.x86_64
>  
> Hi Derek
> could you double check that all the .ko modules (drivers and pf_ring kernel 
> module) have been reinstalled by DKMS and reloaded?
> Alternatively, any chance to get ssh access to the machine?
> 
> Alfredo
> 
>> On 2 Nov 2016, at 21:18, Spransy, Derek <[email protected] 
>> <mailto:[email protected]>> wrote:
>> 
>> Hello,
>> 
>> Today we upgraded our RHEL6 n2disk box to kernel 2.6.32-642.4.2.el6.x86_64 
>> (addresses the dirty cow vulnerability). After the upgrade n2disk is 
>> dumping. I went ahead and upgraded n2disk (2.6.161102) and pfring 
>> (6.4.1-960) to their latest available stable versions and ran into the same 
>> issue. zcount is able to open the zc interface properly. n2disk startup 
>> looks like:
>> 
>> 02/Nov/2016 16:07:59 [n2disk.c:4809] Welcome to n2disk10g v.2.6.161102 
>> (r4670) [SandyBridge]
>> 02/Nov/2016 16:07:59 [n2disk.c:4836] Running on 2 node(s) system with 24 
>> core(s). NUMA affinity set to node 1.
>> 02/Nov/2016 16:07:59 [n2disk.c:4865] Using PF_RING for packet capture
>> 02/Nov/2016 16:07:59 [n2disk.c:4891] WARNING: If you are using standard 
>> drivers (packet capture via kernel) please disable time-pulse thread
>> 02/Nov/2016 16:07:59 [n2disk.c:4894] Multithread support enabled
>> 02/Nov/2016 16:07:59 [n2disk.c:5008] Dump files max size is set to 1024 MB
>> 02/Nov/2016 16:07:59 [n2disk.c:5025] Buffer memory is set to 3 GB (x 3 pcap 
>> files)
>> 02/Nov/2016 16:07:59 [n2disk.c:5060] Using directory /data1/captures for 
>> dump files
>> 02/Nov/2016 16:07:59 [n2disk.c:5065] No sub-directories will be created
>> 02/Nov/2016 16:07:59 [n2disk.c:5070] Up to 43000 files will be written 
>> before overwriting
>> 02/Nov/2016 16:07:59 [n2disk.c:5080] Dump files max duration is set to 600 
>> sec
>> 02/Nov/2016 16:07:59 [n2disk.c:5096] Dumping data in 0.1 MB chunks
>> 02/Nov/2016 16:07:59 [n2disk.c:5139] Index processing memory is set to 847 
>> MB (x 3 index files)
>> 02/Nov/2016 16:08:02 [n2disk.c:5329] Memory allocated successfully
>> 02/Nov/2016 16:08:02 [n2disk.c:3597] Using time pulse timestamps
>> 02/Nov/2016 16:08:02 [n2disk.c:3630] Started PF_RING packet reader thread 
>> for device zc:eth5
>> 
>> /var/log/messages then reports:
>> abrt[5405]: Saved core dump of pid 5128 (/usr/local/bin/n2disk10g) to 
>> /var/spool/abrt/ccpp-2016-
>> 11-02-16:02:10-5128 (5941956608 bytes)
>> 
>> Any ideas?
>> 
>> Thanks,
>> Derek
>> 
>> 
>> 
>> 
>> This e-mail message (including any attachments) is for the sole use of
>> the intended recipient(s) and may contain confidential and privileged
>> information. If the reader of this message is not the intended
>> recipient, you are hereby notified that any dissemination, distribution
>> or copying of this message (including any attachments) is strictly
>> prohibited.
>> 
>> If you have received this message in error, please contact
>> the sender by reply e-mail message and destroy all copies of the
>> original message (including attachments).
>> _______________________________________________
>> Ntop-misc mailing list
>> [email protected] <mailto:[email protected]>
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc 
>> <http://listgateway.unipi.it/mailman/listinfo/ntop-misc>
> _______________________________________________
> Ntop-misc mailing list
> [email protected] <mailto:[email protected]>
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc 
> <http://listgateway.unipi.it/mailman/listinfo/ntop-misc>
_______________________________________________
Ntop-misc mailing list
[email protected]
http://listgateway.unipi.it/mailman/listinfo/ntop-misc

Reply via email to