I'm experiencing a similar problem.  Do you have an ftp server I can upload the 
capture file to?

-----Original Message-----
From: [email protected] 
[mailto:[email protected]] On Behalf Of Alfredo Cardigliano
Sent: Monday, July 29, 2013 1:51 AM
To: [email protected]
Subject: Re: [Ntop-misc] Packet loss with TCP ACK flag

Hi
it is strange the cluster does not recognize the actual number of rx packets, 
and it treats ACK packets in the same way of others.
Could you provide a pcap with the traffic you are using in order to reproduce 
this issue?

Thanks
Alfredo

On Jul 29, 2013, at 7:37 AM, 박주건 <[email protected]> wrote:

> Dear all,
> 
> I’m testing performance of PF_RING with the DNA/libzero license using STC 
> (Spirent Test Center).
> I constructed the following environment to perform the test.
> STC ---- pfdnacluster_mt_rss_frwd app.(dna0<->dna1) --- STC
> 
> The STC transmits the busty TCP/IP packets (20G bi-directional) to the 
> PF_RING application, and then the application just passes (without any 
> additional manipulation) the incoming packets to the STC RX port.
> 
> In this test, I have encountered a very strange issue with packet loss during 
> bypass a particular type of packets. All packets are bypassed normally except 
> the packets with TCP ACK flag.
> 
> However, when the STC sends the packets with TCP ACK flag (2,349,625 packets 
> with ACK flag), the PF_RING application drops a number of incoming packets 
> (around 10%), and it occurs even in the lower bandwidth settings. All others 
> (SYN, PSH, FIN, RST) are flowed pretty well.
> Furthermore, dna_cluster_stats(), which is used to acquired statistical data, 
> does not seem to recognize the actual number of RX packets.
> I have already checked that the STC operates normally via DPDK platform. 
> 
> Do you have any ideas what the problem is ,and how to fix it?
> 
> 
> Configuration details are as follows:
> 
> Xeon X5690 with Intel ixgbe 82599 NIC, 2.6.32-220.13.1.el6.x86_64
> 
> pf_ring and ixgbe drivers with:
> insmod pf_ring.ko transparent_mode=2 enable_tx_capture=0 insmod 
> ixgbe.ko allow_unsupported_sfp=1,1 RSS=8,8
> 
> ---------------------------------------------
> # cat /proc/net/pf_ring/info
> PF_RING Version          : 5.6.0 ($Revision: exported$)
> total rings              : 26
> 
> Standard (non DNA) Options
> Ring slots               : 4096
> Slot version             : 15
> Capture TX               : No [RX only]
> IP Defragment            : No
> Socket Mode              : Standard
> Transparent mode         : No [mode 2]
> Total plugins            : 0
> Cluster Fragment Queue   : 0
> Cluster Fragment Discard : 0
> ----------------------------------------------
> 
> # cat /proc/net/pf_ring/dev/dna0/info
> Name:              dna0
> Index:             122
> Polling Mode:      DNA
> Type:              Ethernet
> Family:            Intel ixgbe 82599
> Max # TX Queues:   8
> ----------------------------------------------
> 
> cat 6055-dna0.11
> Bound Device(s)    :
> Active             : 1
> Breed              : DNA
> Sampling Rate      : 1
> Capture Direction  : RX+TX
> Socket Mode        : TX only
> Appl. Name         : pfdnacluster-dna0-channel-0
> IP Defragment      : No
> BPF Filtering      : Disabled
> # Sw Filt. Rules   : 0
> # Hw Filt. Rules   : 0
> Poll Pkt Watermark : 128
> Num Poll Calls     : 0
> Channel Id         : 0
> Num RX Slots       : 8192
> Num TX Slots       : 8192
> Tot Memory         : 25952256 bytes
> ----------------------------------------------
> _______________________________________________
> Ntop-misc mailing list
> [email protected]
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc

_______________________________________________
Ntop-misc mailing list
[email protected]
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