Login | Register For Free | Help
Search for: (Advanced)

Mailing List Archive: NTop: Misc

Problems with pfcount

 

 

First page Previous page 1 2 Next page Last page  View All NTop misc RSS feed   Index | Next | Previous | View Threaded


sallynbird at gmail

Oct 31, 2011, 1:21 PM

Post #1 of 30 (1626 views)
Permalink
Problems with pfcount

I'm having problems getting pfcount to work. I have two machines
connected back-to-back: (A) has a Silicom NIC ; and (B) has a
NetEffect 10GbE NIC. I launch pfcount on A. Then on B I start
pinging A. pfcount continually reports zero packets received.

=========================
Absolute Stats: [0 pkts rcvd][0 pkts dropped]
Total Pkts=0/Dropped=0.0 %
0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
=========================
Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
=========================

The only relevant log messages I see are:

ixgbe 0000:06:00.0: eth2: NIC Link is Down
ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
device eth0 entered promiscuous mode
device eth0 left promiscuous mode
[PF_RING] --> handle_hw_filtering_rule(command=0)
[PF_RING] --> handle_hw_filtering_rule(command=0)
[PF_RING] --> handle_hw_filtering_rule(command=1)
[PF_RING] --> handle_hw_filtering_rule(command=1)

As I look around I don't see the problem. I can see the packets as
they are transmitted on B. And the RX packet count for eth2 that is
displayed by ifconfig increments appropriately on A. But pfcount
doesn't see them. Anyone have any suggestions?

ifconfig -i eth2
-------------------
eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:1066541584248 (993.2 GiB) TX bytes:0 (0.0 b)
Memory:fd7e0000-fd800000

cat /proc/net/pfring/info
--------------------------
PF_RING Version : 5.0.0 ($Revision: exported$)
Ring slots : 4096
Slot version : 13
Capture TX : Yes [RX+TX]
IP Defragment : No
Socket Mode : Standard
Transparent mode : Yes (mode 0)
Total rings : 1
Total plugins : 0

cat /proc/net/pfring/<pid>-eth2.30
--------------------------------------------
Bound Device : eth2
Slot Version : 13 [5.0.0]
Active : 1
Breed : DNA
Sampling Rate : 1
Capture Direction : RX+TX
Appl. Name : pfcount
IP Defragment : No
BPF Filtering : Disabled
# Sw Filt. Rules : 0
# Hw Filt. Rules : 0
Poll Pkt Watermark : 128
Num Poll Calls : 1461
Channel Id : 0
Num Slots : 8192
Tot Memory : 33685504 bytes

ethtool -i eth2
-------------------
driver: ixgbe
version: 3.3.9-DNA
firmware-version: 1.3-0
bus-info: 0000:06:00.0

ethtool eth2
----------------
Settings for eth2:
Supported ports: [ FIBRE ]
Supported link modes: 10000baseT/Full
Supports auto-negotiation: No
Advertised link modes: 10000baseT/Full
Advertised auto-negotiation: No
Speed: 10000Mb/s
Duplex: Full
Port: FIBRE
PHYAD: 0
Transceiver: external
Auto-negotiation: off
Supports Wake-on: d
Wake-on: d
Current message level: 0x00000007 (7)
Link detected: yes
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


pk.khobdeh at nsn

Oct 31, 2011, 2:05 PM

Post #2 of 30 (1600 views)
Permalink
Re: Problems with pfcount [In reply to]

Did you try sniffing with wireshark or something and see if you are
getting anything there.

-----Original Message-----
From: ntop-misc-bounces [at] listgateway
[mailto:ntop-misc-bounces [at] listgateway] On Behalf Of ext Scott L
Sent: Monday, October 31, 2011 3:21 PM
To: ntop-misc [at] listgateway
Subject: [Ntop-misc] Problems with pfcount

I'm having problems getting pfcount to work. I have two machines
connected back-to-back: (A) has a Silicom NIC ; and (B) has a NetEffect
10GbE NIC. I launch pfcount on A. Then on B I start pinging A.
pfcount continually reports zero packets received.

=========================
Absolute Stats: [0 pkts rcvd][0 pkts dropped] Total Pkts=0/Dropped=0.0 %
0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
========================= Actual Stats: 0 pkts [1'000.06 ms][0.00
pkt/sec] =========================

The only relevant log messages I see are:

ixgbe 0000:06:00.0: eth2: NIC Link is Down ixgbe 0000:06:00.0: eth2: NIC
Link is Up 10 Gbps, Flow Control: RX/TX device eth0 entered promiscuous
mode device eth0 left promiscuous mode [PF_RING] -->
handle_hw_filtering_rule(command=0)
[PF_RING] --> handle_hw_filtering_rule(command=0)
[PF_RING] --> handle_hw_filtering_rule(command=1)
[PF_RING] --> handle_hw_filtering_rule(command=1)

As I look around I don't see the problem. I can see the packets as
they are transmitted on B. And the RX packet count for eth2 that is
displayed by ifconfig increments appropriately on A. But pfcount
doesn't see them. Anyone have any suggestions?

ifconfig -i eth2
-------------------
eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:1066541584248 (993.2 GiB) TX bytes:0 (0.0 b)
Memory:fd7e0000-fd800000

cat /proc/net/pfring/info
--------------------------
PF_RING Version : 5.0.0 ($Revision: exported$)
Ring slots : 4096
Slot version : 13
Capture TX : Yes [RX+TX]
IP Defragment : No
Socket Mode : Standard
Transparent mode : Yes (mode 0)
Total rings : 1
Total plugins : 0

cat /proc/net/pfring/<pid>-eth2.30
--------------------------------------------
Bound Device : eth2
Slot Version : 13 [5.0.0]
Active : 1
Breed : DNA
Sampling Rate : 1
Capture Direction : RX+TX
Appl. Name : pfcount
IP Defragment : No
BPF Filtering : Disabled
# Sw Filt. Rules : 0
# Hw Filt. Rules : 0
Poll Pkt Watermark : 128
Num Poll Calls : 1461
Channel Id : 0
Num Slots : 8192
Tot Memory : 33685504 bytes

ethtool -i eth2
-------------------
driver: ixgbe
version: 3.3.9-DNA
firmware-version: 1.3-0
bus-info: 0000:06:00.0

ethtool eth2
----------------
Settings for eth2:
Supported ports: [ FIBRE ]
Supported link modes: 10000baseT/Full
Supports auto-negotiation: No
Advertised link modes: 10000baseT/Full
Advertised auto-negotiation: No
Speed: 10000Mb/s
Duplex: Full
Port: FIBRE
PHYAD: 0
Transceiver: external
Auto-negotiation: off
Supports Wake-on: d
Wake-on: d
Current message level: 0x00000007 (7)
Link detected: yes
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


dprovan at bivio

Oct 31, 2011, 2:21 PM

Post #3 of 30 (1600 views)
Permalink
Re: Problems with pfcount [In reply to]

"pfcount -i eth2"? The messages about promiscuous mode
suggest pfcount is looking at eth0. You can confirm
that by looking at the pfcount output that comes before
what you quoted.
-don

-----Original Message-----
From: ntop-misc-bounces [at] listgateway
[mailto:ntop-misc-bounces [at] listgateway] On Behalf Of Scott L
Sent: Monday, October 31, 2011 1:21 PM
To: ntop-misc [at] listgateway
Subject: [Ntop-misc] Problems with pfcount

I'm having problems getting pfcount to work. I have two machines
connected back-to-back: (A) has a Silicom NIC ; and (B) has a
NetEffect 10GbE NIC. I launch pfcount on A. Then on B I start
pinging A. pfcount continually reports zero packets received.

=========================
Absolute Stats: [0 pkts rcvd][0 pkts dropped]
Total Pkts=0/Dropped=0.0 %
0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
=========================
Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
=========================

The only relevant log messages I see are:

ixgbe 0000:06:00.0: eth2: NIC Link is Down
ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
device eth0 entered promiscuous mode
device eth0 left promiscuous mode
[PF_RING] --> handle_hw_filtering_rule(command=0)
[PF_RING] --> handle_hw_filtering_rule(command=0)
[PF_RING] --> handle_hw_filtering_rule(command=1)
[PF_RING] --> handle_hw_filtering_rule(command=1)

As I look around I don't see the problem. I can see the packets as
they are transmitted on B. And the RX packet count for eth2 that is
displayed by ifconfig increments appropriately on A. But pfcount
doesn't see them. Anyone have any suggestions?

ifconfig -i eth2
-------------------
eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:1066541584248 (993.2 GiB) TX bytes:0 (0.0 b)
Memory:fd7e0000-fd800000

cat /proc/net/pfring/info
--------------------------
PF_RING Version : 5.0.0 ($Revision: exported$)
Ring slots : 4096
Slot version : 13
Capture TX : Yes [RX+TX]
IP Defragment : No
Socket Mode : Standard
Transparent mode : Yes (mode 0)
Total rings : 1
Total plugins : 0

cat /proc/net/pfring/<pid>-eth2.30
--------------------------------------------
Bound Device : eth2
Slot Version : 13 [5.0.0]
Active : 1
Breed : DNA
Sampling Rate : 1
Capture Direction : RX+TX
Appl. Name : pfcount
IP Defragment : No
BPF Filtering : Disabled
# Sw Filt. Rules : 0
# Hw Filt. Rules : 0
Poll Pkt Watermark : 128
Num Poll Calls : 1461
Channel Id : 0
Num Slots : 8192
Tot Memory : 33685504 bytes

ethtool -i eth2
-------------------
driver: ixgbe
version: 3.3.9-DNA
firmware-version: 1.3-0
bus-info: 0000:06:00.0

ethtool eth2
----------------
Settings for eth2:
Supported ports: [ FIBRE ]
Supported link modes: 10000baseT/Full
Supports auto-negotiation: No
Advertised link modes: 10000baseT/Full
Advertised auto-negotiation: No
Speed: 10000Mb/s
Duplex: Full
Port: FIBRE
PHYAD: 0
Transceiver: external
Auto-negotiation: off
Supports Wake-on: d
Wake-on: d
Current message level: 0x00000007 (7)
Link detected: yes
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Oct 31, 2011, 3:10 PM

Post #4 of 30 (1601 views)
Permalink
Re: Problems with pfcount [In reply to]

I am using pfcount -i eth2. Here's the beginning of the pfcount output.

Using PF_RING v.5.0.0
Capturing from eth2 [00:E0:ED:FF:18:08]
# Device RX channels: 8
# Polling threads: 1
=========================

=s=

On Mon, Oct 31, 2011 at 3:21 PM, Don Provan <dprovan [at] bivio> wrote:
> "pfcount -i eth2"? The messages about promiscuous mode
> suggest pfcount is looking at eth0. You can confirm
> that by looking at the pfcount output that comes before
> what you quoted.
> -don
>
> -----Original Message-----
> From: ntop-misc-bounces [at] listgateway
> [mailto:ntop-misc-bounces [at] listgateway] On Behalf Of Scott L
> Sent: Monday, October 31, 2011 1:21 PM
> To: ntop-misc [at] listgateway
> Subject: [Ntop-misc] Problems with pfcount
>
> I'm having problems getting pfcount to work.  I have two machines
> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
> NetEffect 10GbE NIC.  I launch pfcount on A.  Then on B I start
> pinging A.  pfcount continually reports zero packets received.
>
> =========================
> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
> Total Pkts=0/Dropped=0.0 %
> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
> =========================
> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
> =========================
>
> The only relevant log messages I see are:
>
> ixgbe 0000:06:00.0: eth2: NIC Link is Down
> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
> device eth0 entered promiscuous mode
> device eth0 left promiscuous mode
> [PF_RING] --> handle_hw_filtering_rule(command=0)
> [PF_RING] --> handle_hw_filtering_rule(command=0)
> [PF_RING] --> handle_hw_filtering_rule(command=1)
> [PF_RING] --> handle_hw_filtering_rule(command=1)
>
> As I look around I don't see the problem.  I can see the packets as
> they are transmitted on B.   And the RX packet count for eth2 that is
> displayed by ifconfig increments appropriately on A.  But pfcount
> doesn't see them.  Anyone have any suggestions?
>
> ifconfig -i eth2
> -------------------
> eth2      Link encap:Ethernet  HWaddr 00:E0:ED:FF:18:08
>          inet addr:10.0.2.45  Bcast:10.0.2.255  Mask:255.255.255.0
>          inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>          UP BROADCAST RUNNING PROMISC MULTICAST  MTU:1500  Metric:1
>          RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
>          TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>          collisions:0 txqueuelen:1000
>          RX bytes:1066541584248 (993.2 GiB)  TX bytes:0 (0.0 b)
>          Memory:fd7e0000-fd800000
>
> cat /proc/net/pfring/info
> --------------------------
> PF_RING Version     : 5.0.0 ($Revision: exported$)
> Ring slots          : 4096
> Slot version        : 13
> Capture TX          : Yes [RX+TX]
> IP Defragment       : No
> Socket Mode         : Standard
> Transparent mode    : Yes (mode 0)
> Total rings         : 1
> Total plugins       : 0
>
> cat /proc/net/pfring/<pid>-eth2.30
> --------------------------------------------
> Bound Device       : eth2
> Slot Version       : 13 [5.0.0]
> Active             : 1
> Breed              : DNA
> Sampling Rate      : 1
> Capture Direction  : RX+TX
> Appl. Name         : pfcount
> IP Defragment      : No
> BPF Filtering      : Disabled
> # Sw Filt. Rules   : 0
> # Hw Filt. Rules   : 0
> Poll Pkt Watermark : 128
> Num Poll Calls     : 1461
> Channel Id         : 0
> Num Slots          : 8192
> Tot Memory         : 33685504 bytes
>
> ethtool -i eth2
> -------------------
> driver: ixgbe
> version: 3.3.9-DNA
> firmware-version: 1.3-0
> bus-info: 0000:06:00.0
>
> ethtool eth2
> ----------------
> Settings for eth2:
>        Supported ports: [ FIBRE ]
>        Supported link modes:   10000baseT/Full
>        Supports auto-negotiation: No
>        Advertised link modes:  10000baseT/Full
>        Advertised auto-negotiation: No
>        Speed: 10000Mb/s
>        Duplex: Full
>        Port: FIBRE
>        PHYAD: 0
>        Transceiver: external
>        Auto-negotiation: off
>        Supports Wake-on: d
>        Wake-on: d
>        Current message level: 0x00000007 (7)
>        Link detected: yes
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


deri at ntop

Nov 1, 2011, 1:34 AM

Post #5 of 30 (1591 views)
Permalink
Re: Problems with pfcount [In reply to]

Scott
please redo your tests using the code in PF_RING's SVN. From the interface names (we now call them dnaX) i see that you are using old stuff

Luca

On Oct 31, 2011, at 9:21 PM, Scott L wrote:

> I'm having problems getting pfcount to work. I have two machines
> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
> NetEffect 10GbE NIC. I launch pfcount on A. Then on B I start
> pinging A. pfcount continually reports zero packets received.
>
> =========================
> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
> Total Pkts=0/Dropped=0.0 %
> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
> =========================
> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
> =========================
>
> The only relevant log messages I see are:
>
> ixgbe 0000:06:00.0: eth2: NIC Link is Down
> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
> device eth0 entered promiscuous mode
> device eth0 left promiscuous mode
> [PF_RING] --> handle_hw_filtering_rule(command=0)
> [PF_RING] --> handle_hw_filtering_rule(command=0)
> [PF_RING] --> handle_hw_filtering_rule(command=1)
> [PF_RING] --> handle_hw_filtering_rule(command=1)
>
> As I look around I don't see the problem. I can see the packets as
> they are transmitted on B. And the RX packet count for eth2 that is
> displayed by ifconfig increments appropriately on A. But pfcount
> doesn't see them. Anyone have any suggestions?
>
> ifconfig -i eth2
> -------------------
> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
> RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:1066541584248 (993.2 GiB) TX bytes:0 (0.0 b)
> Memory:fd7e0000-fd800000
>
> cat /proc/net/pfring/info
> --------------------------
> PF_RING Version : 5.0.0 ($Revision: exported$)
> Ring slots : 4096
> Slot version : 13
> Capture TX : Yes [RX+TX]
> IP Defragment : No
> Socket Mode : Standard
> Transparent mode : Yes (mode 0)
> Total rings : 1
> Total plugins : 0
>
> cat /proc/net/pfring/<pid>-eth2.30
> --------------------------------------------
> Bound Device : eth2
> Slot Version : 13 [5.0.0]
> Active : 1
> Breed : DNA
> Sampling Rate : 1
> Capture Direction : RX+TX
> Appl. Name : pfcount
> IP Defragment : No
> BPF Filtering : Disabled
> # Sw Filt. Rules : 0
> # Hw Filt. Rules : 0
> Poll Pkt Watermark : 128
> Num Poll Calls : 1461
> Channel Id : 0
> Num Slots : 8192
> Tot Memory : 33685504 bytes
>
> ethtool -i eth2
> -------------------
> driver: ixgbe
> version: 3.3.9-DNA
> firmware-version: 1.3-0
> bus-info: 0000:06:00.0
>
> ethtool eth2
> ----------------
> Settings for eth2:
> Supported ports: [ FIBRE ]
> Supported link modes: 10000baseT/Full
> Supports auto-negotiation: No
> Advertised link modes: 10000baseT/Full
> Advertised auto-negotiation: No
> Speed: 10000Mb/s
> Duplex: Full
> Port: FIBRE
> PHYAD: 0
> Transceiver: external
> Auto-negotiation: off
> Supports Wake-on: d
> Wake-on: d
> Current message level: 0x00000007 (7)
> Link detected: yes
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc

---
We can't solve problems by using the same kind of thinking we used when we created them - Albert Einstein

_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Nov 9, 2011, 11:05 AM

Post #6 of 30 (1560 views)
Permalink
Re: Problems with pfcount [In reply to]

I've updated my PF_RING code and I'm not seeing any difference (i.e.,
pfcount -i eth2 still shows 0 packets received but ifconfig shows
packets being received). Here's what I'm seeing with the new version:

ifconfig eth2
-------------------
eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
RX packets:210 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
Memory:fd7e0000-fd800000

cat /proc/net/pfring/info
-----------------------------------
PF_RING Version : 5.1.0 ($Revision: 4972$)
Ring slots : 4096
Slot version : 13
Capture TX : Yes [RX+TX]
IP Defragment : No
Socket Mode : Standard
Transparent mode : Yes (mode 0)
Total rings : 1
Total plugins : 0

cat /proc/net/pfring/<pid>-eth2.1
------------------------------------------------
Bound Device : eth2
Slot Version : 13 [5.1.0]
Active : 1
Breed : Non-DNA
Sampling Rate : 1
Capture Direction : RX+TX
Appl. Name : pfcount
IP Defragment : No
BPF Filtering : Disabled
# Sw Filt. Rules : 0
# Hw Filt. Rules : 0
Poll Pkt Watermark : 128
Num Poll Calls : 1503
Channel Id : -1
Cluster Id : 0
Min Num Slots : 6871
Bucket Len : 128
Slot Len : 304 [bucket+header]
Tot Memory : 2097152
Tot Packets : 0
Tot Pkt Lost : 0
Tot Insert : 0
Tot Read : 0
Insert Offset : 0
Remove Offset : 0
Tot Fwd Ok : 0
Tot Fwd Errors : 0
Num Free Slots : 6871

ethtool -i eth2
----------------------
driver: ixgbe
version: 3.3.9-DNA
firmware-version: 1.3-0
bus-info: 0000:06:00.0

ethtool eth2
----------------------
Settings for eth2:
Supported ports: [ FIBRE ]
Supported link modes: 10000baseT/Full
Supports auto-negotiation: No
Advertised link modes: 10000baseT/Full
Advertised auto-negotiation: No
Speed: 10000Mb/s
Duplex: Full
Port: FIBRE
PHYAD: 0
Transceiver: external
Auto-negotiation: off
Supports Wake-on: d
Wake-on: d
Current message level: 0x00000007 (7)
Link detected: yes


I also tried pfcount -i dna:eth2, but got the following error:

pfring_open error (pf_ring not loaded or perhaps you use quick mode
and have already a socket bound to dna:eth2 ?)

but:

Module Size Used by
pf_ring 335476 0
ip6t_REJECT 5856 2
nf_conntrack_ipv6 21880 2
ip6table_filter 4016 1
ip6_tables 19664 1 ip6table_filter
ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
dm_multipath 17304 0
uinput 9248 0
ixgbe 202760 0
amd64_edac_mod 29632 0
i2c_nforce2 9048 0
dca 6708 1 ixgbe
edac_core 43516 4 amd64_edac_mod
forcedeth 54764 0
mlx4_core 84128 0
shpchp 34636 0
serio_raw 6644 0
pata_acpi 5152 0
pata_amd 14260 0
ata_generic 5924 0
sata_nv 25228 2
radeon 507616 1
ttm 41952 1 radeon
drm_kms_helper 25360 1 radeon
drm 171168 3 radeon,ttm,drm_kms_helper
i2c_algo_bit 6020 1 radeon
i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit

Any thoughts? Thanks for your help.

=s=

On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri <deri [at] ntop> wrote:
> Scott
> please redo your tests using the code in PF_RING's SVN. From the interface names (we now call them dnaX) i see that you are using old stuff
>
> Luca
>
> On Oct 31, 2011, at 9:21 PM, Scott L wrote:
>
>> I'm having problems getting pfcount to work.  I have two machines
>> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
>> NetEffect 10GbE NIC.  I launch pfcount on A.  Then on B I start
>> pinging A.  pfcount continually reports zero packets received.
>>
>> =========================
>> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
>> Total Pkts=0/Dropped=0.0 %
>> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
>> =========================
>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>> =========================
>>
>> The only relevant log messages I see are:
>>
>> ixgbe 0000:06:00.0: eth2: NIC Link is Down
>> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
>> device eth0 entered promiscuous mode
>> device eth0 left promiscuous mode
>> [PF_RING] --> handle_hw_filtering_rule(command=0)
>> [PF_RING] --> handle_hw_filtering_rule(command=0)
>> [PF_RING] --> handle_hw_filtering_rule(command=1)
>> [PF_RING] --> handle_hw_filtering_rule(command=1)
>>
>> As I look around I don't see the problem.  I can see the packets as
>> they are transmitted on B.   And the RX packet count for eth2 that is
>> displayed by ifconfig increments appropriately on A.  But pfcount
>> doesn't see them.  Anyone have any suggestions?
>>
>> ifconfig -i eth2
>> -------------------
>> eth2      Link encap:Ethernet  HWaddr 00:E0:ED:FF:18:08
>>          inet addr:10.0.2.45  Bcast:10.0.2.255  Mask:255.255.255.0
>>          inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>          UP BROADCAST RUNNING PROMISC MULTICAST  MTU:1500  Metric:1
>>          RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
>>          TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>          collisions:0 txqueuelen:1000
>>          RX bytes:1066541584248 (993.2 GiB)  TX bytes:0 (0.0 b)
>>          Memory:fd7e0000-fd800000
>>
>> cat /proc/net/pfring/info
>> --------------------------
>> PF_RING Version     : 5.0.0 ($Revision: exported$)
>> Ring slots          : 4096
>> Slot version        : 13
>> Capture TX          : Yes [RX+TX]
>> IP Defragment       : No
>> Socket Mode         : Standard
>> Transparent mode    : Yes (mode 0)
>> Total rings         : 1
>> Total plugins       : 0
>>
>> cat /proc/net/pfring/<pid>-eth2.30
>> --------------------------------------------
>> Bound Device       : eth2
>> Slot Version       : 13 [5.0.0]
>> Active             : 1
>> Breed              : DNA
>> Sampling Rate      : 1
>> Capture Direction  : RX+TX
>> Appl. Name         : pfcount
>> IP Defragment      : No
>> BPF Filtering      : Disabled
>> # Sw Filt. Rules   : 0
>> # Hw Filt. Rules   : 0
>> Poll Pkt Watermark : 128
>> Num Poll Calls     : 1461
>> Channel Id         : 0
>> Num Slots          : 8192
>> Tot Memory         : 33685504 bytes
>>
>> ethtool -i eth2
>> -------------------
>> driver: ixgbe
>> version: 3.3.9-DNA
>> firmware-version: 1.3-0
>> bus-info: 0000:06:00.0
>>
>> ethtool eth2
>> ----------------
>> Settings for eth2:
>>       Supported ports: [ FIBRE ]
>>       Supported link modes:   10000baseT/Full
>>       Supports auto-negotiation: No
>>       Advertised link modes:  10000baseT/Full
>>       Advertised auto-negotiation: No
>>       Speed: 10000Mb/s
>>       Duplex: Full
>>       Port: FIBRE
>>       PHYAD: 0
>>       Transceiver: external
>>       Auto-negotiation: off
>>       Supports Wake-on: d
>>       Wake-on: d
>>       Current message level: 0x00000007 (7)
>>       Link detected: yes
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
> ---
> We can't solve problems by using the same kind of thinking we used when we created them - Albert Einstein
>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


ccollord at hotmail

Nov 9, 2011, 12:11 PM

Post #7 of 30 (1554 views)
Permalink
Re: Problems with pfcount [In reply to]

Hi Scott,You'll see that error when you run pfcount without su permission (make sure you sudo or use root). Not sure if that's your problem or not, i'm still figuring this out myself...On the other hand it doesn't look like you're receiving much. Your RX packets are 210, whereas mine after an hour is...
eth2 Link encap:Ethernet HWaddr 0xxxxxxxxx:4c inet addr:0.0.0.1 Bcast:255.255.255.255 Mask:0.0.0.0 UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1 RX packets:172969631 errors:0 dropped:1 overruns:0 frame:0 TX packets:5 errors:0 dropped:0 overruns:0 carrier:0 collisions:0 txqueuelen:1000 RX bytes:116951083144 (116.9 GB) TX bytes:398 (398.0 B)




> Date: Wed, 9 Nov 2011 12:05:55 -0700
> From: sallynbird [at] gmail
> To: ntop-misc [at] listgateway
> Subject: Re: [Ntop-misc] Problems with pfcount
>
> I've updated my PF_RING code and I'm not seeing any difference (i.e.,
> pfcount -i eth2 still shows 0 packets received but ifconfig shows
> packets being received). Here's what I'm seeing with the new version:
>
> ifconfig eth2
> -------------------
> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
> RX packets:210 errors:0 dropped:0 overruns:0 frame:0
> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
> Memory:fd7e0000-fd800000
>
> cat /proc/net/pfring/info
> -----------------------------------
> PF_RING Version : 5.1.0 ($Revision: 4972$)
> Ring slots : 4096
> Slot version : 13
> Capture TX : Yes [RX+TX]
> IP Defragment : No
> Socket Mode : Standard
> Transparent mode : Yes (mode 0)
> Total rings : 1
> Total plugins : 0
>
> cat /proc/net/pfring/<pid>-eth2.1
> ------------------------------------------------
> Bound Device : eth2
> Slot Version : 13 [5.1.0]
> Active : 1
> Breed : Non-DNA
> Sampling Rate : 1
> Capture Direction : RX+TX
> Appl. Name : pfcount
> IP Defragment : No
> BPF Filtering : Disabled
> # Sw Filt. Rules : 0
> # Hw Filt. Rules : 0
> Poll Pkt Watermark : 128
> Num Poll Calls : 1503
> Channel Id : -1
> Cluster Id : 0
> Min Num Slots : 6871
> Bucket Len : 128
> Slot Len : 304 [bucket+header]
> Tot Memory : 2097152
> Tot Packets : 0
> Tot Pkt Lost : 0
> Tot Insert : 0
> Tot Read : 0
> Insert Offset : 0
> Remove Offset : 0
> Tot Fwd Ok : 0
> Tot Fwd Errors : 0
> Num Free Slots : 6871
>
> ethtool -i eth2
> ----------------------
> driver: ixgbe
> version: 3.3.9-DNA
> firmware-version: 1.3-0
> bus-info: 0000:06:00.0
>
> ethtool eth2
> ----------------------
> Settings for eth2:
> Supported ports: [ FIBRE ]
> Supported link modes: 10000baseT/Full
> Supports auto-negotiation: No
> Advertised link modes: 10000baseT/Full
> Advertised auto-negotiation: No
> Speed: 10000Mb/s
> Duplex: Full
> Port: FIBRE
> PHYAD: 0
> Transceiver: external
> Auto-negotiation: off
> Supports Wake-on: d
> Wake-on: d
> Current message level: 0x00000007 (7)
> Link detected: yes
>
>
> I also tried pfcount -i dna:eth2, but got the following error:
>
> pfring_open error (pf_ring not loaded or perhaps you use quick mode
> and have already a socket bound to dna:eth2 ?)
>
> but:
>
> Module Size Used by
> pf_ring 335476 0
> ip6t_REJECT 5856 2
> nf_conntrack_ipv6 21880 2
> ip6table_filter 4016 1
> ip6_tables 19664 1 ip6table_filter
> ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
> dm_multipath 17304 0
> uinput 9248 0
> ixgbe 202760 0
> amd64_edac_mod 29632 0
> i2c_nforce2 9048 0
> dca 6708 1 ixgbe
> edac_core 43516 4 amd64_edac_mod
> forcedeth 54764 0
> mlx4_core 84128 0
> shpchp 34636 0
> serio_raw 6644 0
> pata_acpi 5152 0
> pata_amd 14260 0
> ata_generic 5924 0
> sata_nv 25228 2
> radeon 507616 1
> ttm 41952 1 radeon
> drm_kms_helper 25360 1 radeon
> drm 171168 3 radeon,ttm,drm_kms_helper
> i2c_algo_bit 6020 1 radeon
> i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit
>
> Any thoughts? Thanks for your help.
>
> =s=
>
> On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri <deri [at] ntop> wrote:
> > Scott
> > please redo your tests using the code in PF_RING's SVN. From the interface names (we now call them dnaX) i see that you are using old stuff
> >
> > Luca
> >
> > On Oct 31, 2011, at 9:21 PM, Scott L wrote:
> >
> >> I'm having problems getting pfcount to work. I have two machines
> >> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
> >> NetEffect 10GbE NIC. I launch pfcount on A. Then on B I start
> >> pinging A. pfcount continually reports zero packets received.
> >>
> >> =========================
> >> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
> >> Total Pkts=0/Dropped=0.0 %
> >> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
> >> =========================
> >> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
> >> =========================
> >>
> >> The only relevant log messages I see are:
> >>
> >> ixgbe 0000:06:00.0: eth2: NIC Link is Down
> >> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
> >> device eth0 entered promiscuous mode
> >> device eth0 left promiscuous mode
> >> [PF_RING] --> handle_hw_filtering_rule(command=0)
> >> [PF_RING] --> handle_hw_filtering_rule(command=0)
> >> [PF_RING] --> handle_hw_filtering_rule(command=1)
> >> [PF_RING] --> handle_hw_filtering_rule(command=1)
> >>
> >> As I look around I don't see the problem. I can see the packets as
> >> they are transmitted on B. And the RX packet count for eth2 that is
> >> displayed by ifconfig increments appropriately on A. But pfcount
> >> doesn't see them. Anyone have any suggestions?
> >>
> >> ifconfig -i eth2
> >> -------------------
> >> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
> >> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
> >> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
> >> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
> >> RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
> >> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
> >> collisions:0 txqueuelen:1000
> >> RX bytes:1066541584248 (993.2 GiB) TX bytes:0 (0.0 b)
> >> Memory:fd7e0000-fd800000
> >>
> >> cat /proc/net/pfring/info
> >> --------------------------
> >> PF_RING Version : 5.0.0 ($Revision: exported$)
> >> Ring slots : 4096
> >> Slot version : 13
> >> Capture TX : Yes [RX+TX]
> >> IP Defragment : No
> >> Socket Mode : Standard
> >> Transparent mode : Yes (mode 0)
> >> Total rings : 1
> >> Total plugins : 0
> >>
> >> cat /proc/net/pfring/<pid>-eth2.30
> >> --------------------------------------------
> >> Bound Device : eth2
> >> Slot Version : 13 [5.0.0]
> >> Active : 1
> >> Breed : DNA
> >> Sampling Rate : 1
> >> Capture Direction : RX+TX
> >> Appl. Name : pfcount
> >> IP Defragment : No
> >> BPF Filtering : Disabled
> >> # Sw Filt. Rules : 0
> >> # Hw Filt. Rules : 0
> >> Poll Pkt Watermark : 128
> >> Num Poll Calls : 1461
> >> Channel Id : 0
> >> Num Slots : 8192
> >> Tot Memory : 33685504 bytes
> >>
> >> ethtool -i eth2
> >> -------------------
> >> driver: ixgbe
> >> version: 3.3.9-DNA
> >> firmware-version: 1.3-0
> >> bus-info: 0000:06:00.0
> >>
> >> ethtool eth2
> >> ----------------
> >> Settings for eth2:
> >> Supported ports: [ FIBRE ]
> >> Supported link modes: 10000baseT/Full
> >> Supports auto-negotiation: No
> >> Advertised link modes: 10000baseT/Full
> >> Advertised auto-negotiation: No
> >> Speed: 10000Mb/s
> >> Duplex: Full
> >> Port: FIBRE
> >> PHYAD: 0
> >> Transceiver: external
> >> Auto-negotiation: off
> >> Supports Wake-on: d
> >> Wake-on: d
> >> Current message level: 0x00000007 (7)
> >> Link detected: yes
> >> _______________________________________________
> >> Ntop-misc mailing list
> >> Ntop-misc [at] listgateway
> >> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
> >
> > ---
> > We can't solve problems by using the same kind of thinking we used when we created them - Albert Einstein
> >
> > _______________________________________________
> > Ntop-misc mailing list
> > Ntop-misc [at] listgateway
> > http://listgateway.unipi.it/mailman/listinfo/ntop-misc
> >
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Nov 10, 2011, 9:06 AM

Post #8 of 30 (1543 views)
Permalink
Re: Problems with pfcount [In reply to]

Chris,

Thanks for your response. I am running pfcount as root. I don't see
the error for "pfcount -i eth2" only for "pfcount -i dna:eth2".

In my configuration, I don't expect to receive much traffic. I am
connecting two machines with 10 GbE NICs back-to-back. So the only
traffic I expect to see (for now) are the pings that I am attempting
to send; so the number of received packets is on the order of what I
would expect.

=s=

On Wed, Nov 9, 2011 at 1:11 PM, Chris Collord <ccollord [at] hotmail> wrote:
> Hi Scott,
> You'll see that error when you run pfcount without su permission (make sure
> you sudo or use root).  Not sure if that's your problem or not, i'm still
> figuring this out myself...
> On the other hand it doesn't look like you're receiving much.  Your RX
> packets are 210, whereas mine after an hour is...
> eth2      Link encap:Ethernet  HWaddr 0xxxxxxxxx:4c
>           inet addr:0.0.0.1  Bcast:255.255.255.255  Mask:0.0.0.0
>            UP BROADCAST RUNNING PROMISC MULTICAST  MTU:1500  Metric:1
>           RX packets:172969631 errors:0 dropped:1 overruns:0 frame:0
>           TX packets:5 errors:0 dropped:0 overruns:0 carrier:0
>           collisions:0 txqueuelen:1000
>           RX bytes:116951083144 (116.9 GB)  TX bytes:398 (398.0 B)
>
>
>
>
>> Date: Wed, 9 Nov 2011 12:05:55 -0700
>> From: sallynbird [at] gmail
>> To: ntop-misc [at] listgateway
>> Subject: Re: [Ntop-misc] Problems with pfcount
>>
>> I've updated my PF_RING code and I'm not seeing any difference (i.e.,
>> pfcount -i eth2 still shows 0 packets received but ifconfig shows
>> packets being received). Here's what I'm seeing with the new version:
>>
>> ifconfig eth2
>> -------------------
>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>> RX packets:210 errors:0 dropped:0 overruns:0 frame:0
>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>> collisions:0 txqueuelen:1000
>> RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
>> Memory:fd7e0000-fd800000
>>
>> cat /proc/net/pfring/info
>> -----------------------------------
>> PF_RING Version : 5.1.0 ($Revision: 4972$)
>> Ring slots : 4096
>> Slot version : 13
>> Capture TX : Yes [RX+TX]
>> IP Defragment : No
>> Socket Mode : Standard
>> Transparent mode : Yes (mode 0)
>> Total rings : 1
>> Total plugins : 0
>>
>> cat /proc/net/pfring/<pid>-eth2.1
>> ------------------------------------------------
>> Bound Device : eth2
>> Slot Version : 13 [5.1.0]
>> Active : 1
>> Breed : Non-DNA
>> Sampling Rate : 1
>> Capture Direction : RX+TX
>> Appl. Name : pfcount
>> IP Defragment : No
>> BPF Filtering : Disabled
>> # Sw Filt. Rules : 0
>> # Hw Filt. Rules : 0
>> Poll Pkt Watermark : 128
>> Num Poll Calls : 1503
>> Channel Id : -1
>> Cluster Id : 0
>> Min Num Slots : 6871
>> Bucket Len : 128
>> Slot Len : 304 [bucket+header]
>> Tot Memory : 2097152
>> Tot Packets : 0
>> Tot Pkt Lost : 0
>> Tot Insert : 0
>> Tot Read : 0
>> Insert Offset : 0
>> Remove Offset : 0
>> Tot Fwd Ok : 0
>> Tot Fwd Errors : 0
>> Num Free Slots : 6871
>>
>> ethtool -i eth2
>> ----------------------
>> driver: ixgbe
>> version: 3.3.9-DNA
>> firmware-version: 1.3-0
>> bus-info: 0000:06:00.0
>>
>> ethtool eth2
>> ----------------------
>> Settings for eth2:
>> Supported ports: [ FIBRE ]
>> Supported link modes: 10000baseT/Full
>> Supports auto-negotiation: No
>> Advertised link modes: 10000baseT/Full
>> Advertised auto-negotiation: No
>> Speed: 10000Mb/s
>> Duplex: Full
>> Port: FIBRE
>> PHYAD: 0
>> Transceiver: external
>> Auto-negotiation: off
>> Supports Wake-on: d
>> Wake-on: d
>> Current message level: 0x00000007 (7)
>> Link detected: yes
>>
>>
>> I also tried pfcount -i dna:eth2, but got the following error:
>>
>> pfring_open error (pf_ring not loaded or perhaps you use quick mode
>> and have already a socket bound to dna:eth2 ?)
>>
>> but:
>>
>> Module Size Used by
>> pf_ring 335476 0
>> ip6t_REJECT 5856 2
>> nf_conntrack_ipv6 21880 2
>> ip6table_filter 4016 1
>> ip6_tables 19664 1 ip6table_filter
>> ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
>> dm_multipath 17304 0
>> uinput 9248 0
>> ixgbe 202760 0
>> amd64_edac_mod 29632 0
>> i2c_nforce2 9048 0
>> dca 6708 1 ixgbe
>> edac_core 43516 4 amd64_edac_mod
>> forcedeth 54764 0
>> mlx4_core 84128 0
>> shpchp 34636 0
>> serio_raw 6644 0
>> pata_acpi 5152 0
>> pata_amd 14260 0
>> ata_generic 5924 0
>> sata_nv 25228 2
>> radeon 507616 1
>> ttm 41952 1 radeon
>> drm_kms_helper 25360 1 radeon
>> drm 171168 3 radeon,ttm,drm_kms_helper
>> i2c_algo_bit 6020 1 radeon
>> i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit
>>
>> Any thoughts? Thanks for your help.
>>
>> =s=
>>
>> On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri <deri [at] ntop> wrote:
>> > Scott
>> > please redo your tests using the code in PF_RING's SVN. From the
>> > interface names (we now call them dnaX) i see that you are using old stuff
>> >
>> > Luca
>> >
>> > On Oct 31, 2011, at 9:21 PM, Scott L wrote:
>> >
>> >> I'm having problems getting pfcount to work.  I have two machines
>> >> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
>> >> NetEffect 10GbE NIC.  I launch pfcount on A.  Then on B I start
>> >> pinging A.  pfcount continually reports zero packets received.
>> >>
>> >> =========================
>> >> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
>> >> Total Pkts=0/Dropped=0.0 %
>> >> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
>> >> =========================
>> >> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>> >> =========================
>> >>
>> >> The only relevant log messages I see are:
>> >>
>> >> ixgbe 0000:06:00.0: eth2: NIC Link is Down
>> >> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
>> >> device eth0 entered promiscuous mode
>> >> device eth0 left promiscuous mode
>> >> [PF_RING] --> handle_hw_filtering_rule(command=0)
>> >> [PF_RING] --> handle_hw_filtering_rule(command=0)
>> >> [PF_RING] --> handle_hw_filtering_rule(command=1)
>> >> [PF_RING] --> handle_hw_filtering_rule(command=1)
>> >>
>> >> As I look around I don't see the problem.  I can see the packets as
>> >> they are transmitted on B.   And the RX packet count for eth2 that is
>> >> displayed by ifconfig increments appropriately on A.  But pfcount
>> >> doesn't see them.  Anyone have any suggestions?
>> >>
>> >> ifconfig -i eth2
>> >> -------------------
>> >> eth2      Link encap:Ethernet  HWaddr 00:E0:ED:FF:18:08
>> >>          inet addr:10.0.2.45  Bcast:10.0.2.255  Mask:255.255.255.0
>> >>          inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>> >>          UP BROADCAST RUNNING PROMISC MULTICAST  MTU:1500  Metric:1
>> >>          RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
>> >>          TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>> >>          collisions:0 txqueuelen:1000
>> >>          RX bytes:1066541584248 (993.2 GiB)  TX bytes:0 (0.0 b)
>> >>          Memory:fd7e0000-fd800000
>> >>
>> >> cat /proc/net/pfring/info
>> >> --------------------------
>> >> PF_RING Version     : 5.0.0 ($Revision: exported$)
>> >> Ring slots          : 4096
>> >> Slot version        : 13
>> >> Capture TX          : Yes [RX+TX]
>> >> IP Defragment       : No
>> >> Socket Mode         : Standard
>> >> Transparent mode    : Yes (mode 0)
>> >> Total rings         : 1
>> >> Total plugins       : 0
>> >>
>> >> cat /proc/net/pfring/<pid>-eth2.30
>> >> --------------------------------------------
>> >> Bound Device       : eth2
>> >> Slot Version       : 13 [5.0.0]
>> >> Active             : 1
>> >> Breed              : DNA
>> >> Sampling Rate      : 1
>> >> Capture Direction  : RX+TX
>> >> Appl. Name         : pfcount
>> >> IP Defragment      : No
>> >> BPF Filtering      : Disabled
>> >> # Sw Filt. Rules   : 0
>> >> # Hw Filt. Rules   : 0
>> >> Poll Pkt Watermark : 128
>> >> Num Poll Calls     : 1461
>> >> Channel Id         : 0
>> >> Num Slots          : 8192
>> >> Tot Memory         : 33685504 bytes
>> >>
>> >> ethtool -i eth2
>> >> -------------------
>> >> driver: ixgbe
>> >> version: 3.3.9-DNA
>> >> firmware-version: 1.3-0
>> >> bus-info: 0000:06:00.0
>> >>
>> >> ethtool eth2
>> >> ----------------
>> >> Settings for eth2:
>> >>       Supported ports: [ FIBRE ]
>> >>       Supported link modes:   10000baseT/Full
>> >>       Supports auto-negotiation: No
>> >>       Advertised link modes:  10000baseT/Full
>> >>       Advertised auto-negotiation: No
>> >>       Speed: 10000Mb/s
>> >>       Duplex: Full
>> >>       Port: FIBRE
>> >>       PHYAD: 0
>> >>       Transceiver: external
>> >>       Auto-negotiation: off
>> >>       Supports Wake-on: d
>> >>       Wake-on: d
>> >>       Current message level: 0x00000007 (7)
>> >>       Link detected: yes
>> >> _______________________________________________
>> >> Ntop-misc mailing list
>> >> Ntop-misc [at] listgateway
>> >> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>> >
>> > ---
>> > We can't solve problems by using the same kind of thinking we used when
>> > we created them - Albert Einstein
>> >
>> > _______________________________________________
>> > Ntop-misc mailing list
>> > Ntop-misc [at] listgateway
>> > http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>> >
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


shai_mus at hotmail

Nov 10, 2011, 9:09 AM

Post #9 of 30 (1547 views)
Permalink
Re: Problems with pfcount [In reply to]

Dear Scott,
I am also having problem with pfcount. Can you lend me a help on that too? Thank you.


> Date: Wed, 9 Nov 2011 12:05:55 -0700
> From: sallynbird [at] gmail
> To: ntop-misc [at] listgateway
> Subject: Re: [Ntop-misc] Problems with pfcount
>
> I've updated my PF_RING code and I'm not seeing any difference (i.e.,
> pfcount -i eth2 still shows 0 packets received but ifconfig shows
> packets being received). Here's what I'm seeing with the new version:
>
> ifconfig eth2
> -------------------
> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
> RX packets:210 errors:0 dropped:0 overruns:0 frame:0
> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
> Memory:fd7e0000-fd800000
>
> cat /proc/net/pfring/info
> -----------------------------------
> PF_RING Version : 5.1.0 ($Revision: 4972$)
> Ring slots : 4096
> Slot version : 13
> Capture TX : Yes [RX+TX]
> IP Defragment : No
> Socket Mode : Standard
> Transparent mode : Yes (mode 0)
> Total rings : 1
> Total plugins : 0
>
> cat /proc/net/pfring/<pid>-eth2.1
> ------------------------------------------------
> Bound Device : eth2
> Slot Version : 13 [5.1.0]
> Active : 1
> Breed : Non-DNA
> Sampling Rate : 1
> Capture Direction : RX+TX
> Appl. Name : pfcount
> IP Defragment : No
> BPF Filtering : Disabled
> # Sw Filt. Rules : 0
> # Hw Filt. Rules : 0
> Poll Pkt Watermark : 128
> Num Poll Calls : 1503
> Channel Id : -1
> Cluster Id : 0
> Min Num Slots : 6871
> Bucket Len : 128
> Slot Len : 304 [bucket+header]
> Tot Memory : 2097152
> Tot Packets : 0
> Tot Pkt Lost : 0
> Tot Insert : 0
> Tot Read : 0
> Insert Offset : 0
> Remove Offset : 0
> Tot Fwd Ok : 0
> Tot Fwd Errors : 0
> Num Free Slots : 6871
>
> ethtool -i eth2
> ----------------------
> driver: ixgbe
> version: 3.3.9-DNA
> firmware-version: 1.3-0
> bus-info: 0000:06:00.0
>
> ethtool eth2
> ----------------------
> Settings for eth2:
> Supported ports: [ FIBRE ]
> Supported link modes: 10000baseT/Full
> Supports auto-negotiation: No
> Advertised link modes: 10000baseT/Full
> Advertised auto-negotiation: No
> Speed: 10000Mb/s
> Duplex: Full
> Port: FIBRE
> PHYAD: 0
> Transceiver: external
> Auto-negotiation: off
> Supports Wake-on: d
> Wake-on: d
> Current message level: 0x00000007 (7)
> Link detected: yes
>
>
> I also tried pfcount -i dna:eth2, but got the following error:
>
> pfring_open error (pf_ring not loaded or perhaps you use quick mode
> and have already a socket bound to dna:eth2 ?)
>
> but:
>
> Module Size Used by
> pf_ring 335476 0
> ip6t_REJECT 5856 2
> nf_conntrack_ipv6 21880 2
> ip6table_filter 4016 1
> ip6_tables 19664 1 ip6table_filter
> ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
> dm_multipath 17304 0
> uinput 9248 0
> ixgbe 202760 0
> amd64_edac_mod 29632 0
> i2c_nforce2 9048 0
> dca 6708 1 ixgbe
> edac_core 43516 4 amd64_edac_mod
> forcedeth 54764 0
> mlx4_core 84128 0
> shpchp 34636 0
> serio_raw 6644 0
> pata_acpi 5152 0
> pata_amd 14260 0
> ata_generic 5924 0
> sata_nv 25228 2
> radeon 507616 1
> ttm 41952 1 radeon
> drm_kms_helper 25360 1 radeon
> drm 171168 3 radeon,ttm,drm_kms_helper
> i2c_algo_bit 6020 1 radeon
> i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit
>
> Any thoughts? Thanks for your help.
>
> =s=
>
> On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri <deri [at] ntop> wrote:
> > Scott
> > please redo your tests using the code in PF_RING's SVN. From the interface names (we now call them dnaX) i see that you are using old stuff
> >
> > Luca
> >
> > On Oct 31, 2011, at 9:21 PM, Scott L wrote:
> >
> >> I'm having problems getting pfcount to work. I have two machines
> >> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
> >> NetEffect 10GbE NIC. I launch pfcount on A. Then on B I start
> >> pinging A. pfcount continually reports zero packets received.
> >>
> >> =========================
> >> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
> >> Total Pkts=0/Dropped=0.0 %
> >> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
> >> =========================
> >> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
> >> =========================
> >>
> >> The only relevant log messages I see are:
> >>
> >> ixgbe 0000:06:00.0: eth2: NIC Link is Down
> >> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
> >> device eth0 entered promiscuous mode
> >> device eth0 left promiscuous mode
> >> [PF_RING] --> handle_hw_filtering_rule(command=0)
> >> [PF_RING] --> handle_hw_filtering_rule(command=0)
> >> [PF_RING] --> handle_hw_filtering_rule(command=1)
> >> [PF_RING] --> handle_hw_filtering_rule(command=1)
> >>
> >> As I look around I don't see the problem. I can see the packets as
> >> they are transmitted on B. And the RX packet count for eth2 that is
> >> displayed by ifconfig increments appropriately on A. But pfcount
> >> doesn't see them. Anyone have any suggestions?
> >>
> >> ifconfig -i eth2
> >> -------------------
> >> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
> >> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
> >> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
> >> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
> >> RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
> >> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
> >> collisions:0 txqueuelen:1000
> >> RX bytes:1066541584248 (993.2 GiB) TX bytes:0 (0.0 b)
> >> Memory:fd7e0000-fd800000
> >>
> >> cat /proc/net/pfring/info
> >> --------------------------
> >> PF_RING Version : 5.0.0 ($Revision: exported$)
> >> Ring slots : 4096
> >> Slot version : 13
> >> Capture TX : Yes [RX+TX]
> >> IP Defragment : No
> >> Socket Mode : Standard
> >> Transparent mode : Yes (mode 0)
> >> Total rings : 1
> >> Total plugins : 0
> >>
> >> cat /proc/net/pfring/<pid>-eth2.30
> >> --------------------------------------------
> >> Bound Device : eth2
> >> Slot Version : 13 [5.0.0]
> >> Active : 1
> >> Breed : DNA
> >> Sampling Rate : 1
> >> Capture Direction : RX+TX
> >> Appl. Name : pfcount
> >> IP Defragment : No
> >> BPF Filtering : Disabled
> >> # Sw Filt. Rules : 0
> >> # Hw Filt. Rules : 0
> >> Poll Pkt Watermark : 128
> >> Num Poll Calls : 1461
> >> Channel Id : 0
> >> Num Slots : 8192
> >> Tot Memory : 33685504 bytes
> >>
> >> ethtool -i eth2
> >> -------------------
> >> driver: ixgbe
> >> version: 3.3.9-DNA
> >> firmware-version: 1.3-0
> >> bus-info: 0000:06:00.0
> >>
> >> ethtool eth2
> >> ----------------
> >> Settings for eth2:
> >> Supported ports: [ FIBRE ]
> >> Supported link modes: 10000baseT/Full
> >> Supports auto-negotiation: No
> >> Advertised link modes: 10000baseT/Full
> >> Advertised auto-negotiation: No
> >> Speed: 10000Mb/s
> >> Duplex: Full
> >> Port: FIBRE
> >> PHYAD: 0
> >> Transceiver: external
> >> Auto-negotiation: off
> >> Supports Wake-on: d
> >> Wake-on: d
> >> Current message level: 0x00000007 (7)
> >> Link detected: yes
> >> _______________________________________________
> >> Ntop-misc mailing list
> >> Ntop-misc [at] listgateway
> >> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
> >
> > ---
> > We can't solve problems by using the same kind of thinking we used when we created them - Albert Einstein
> >
> > _______________________________________________
> > Ntop-misc mailing list
> > Ntop-misc [at] listgateway
> > http://listgateway.unipi.it/mailman/listinfo/ntop-misc
> >
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc


deri at ntop

Nov 14, 2011, 12:59 AM

Post #10 of 30 (1543 views)
Permalink
Re: Problems with pfcount [In reply to]

Hi all
you are using an old version of the code as now DNA interfaces are named
dnaX. Please fetch the latest code and drivers from SVN

Luca

On 11/10/2011 06:06 PM, Scott L wrote:
> Chris,
>
> Thanks for your response. I am running pfcount as root. I don't see
> the error for "pfcount -i eth2" only for "pfcount -i dna:eth2".
>
> In my configuration, I don't expect to receive much traffic. I am
> connecting two machines with 10 GbE NICs back-to-back. So the only
> traffic I expect to see (for now) are the pings that I am attempting
> to send; so the number of received packets is on the order of what I
> would expect.
>
> =s=
>
> On Wed, Nov 9, 2011 at 1:11 PM, Chris Collord<ccollord [at] hotmail> wrote:
>> Hi Scott,
>> You'll see that error when you run pfcount without su permission (make sure
>> you sudo or use root). Not sure if that's your problem or not, i'm still
>> figuring this out myself...
>> On the other hand it doesn't look like you're receiving much. Your RX
>> packets are 210, whereas mine after an hour is...
>> eth2 Link encap:Ethernet HWaddr 0xxxxxxxxx:4c
>> inet addr:0.0.0.1 Bcast:255.255.255.255 Mask:0.0.0.0
>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>> RX packets:172969631 errors:0 dropped:1 overruns:0 frame:0
>> TX packets:5 errors:0 dropped:0 overruns:0 carrier:0
>> collisions:0 txqueuelen:1000
>> RX bytes:116951083144 (116.9 GB) TX bytes:398 (398.0 B)
>>
>>
>>
>>
>>> Date: Wed, 9 Nov 2011 12:05:55 -0700
>>> From: sallynbird [at] gmail
>>> To: ntop-misc [at] listgateway
>>> Subject: Re: [Ntop-misc] Problems with pfcount
>>>
>>> I've updated my PF_RING code and I'm not seeing any difference (i.e.,
>>> pfcount -i eth2 still shows 0 packets received but ifconfig shows
>>> packets being received). Here's what I'm seeing with the new version:
>>>
>>> ifconfig eth2
>>> -------------------
>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>> RX packets:210 errors:0 dropped:0 overruns:0 frame:0
>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>> collisions:0 txqueuelen:1000
>>> RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
>>> Memory:fd7e0000-fd800000
>>>
>>> cat /proc/net/pfring/info
>>> -----------------------------------
>>> PF_RING Version : 5.1.0 ($Revision: 4972$)
>>> Ring slots : 4096
>>> Slot version : 13
>>> Capture TX : Yes [RX+TX]
>>> IP Defragment : No
>>> Socket Mode : Standard
>>> Transparent mode : Yes (mode 0)
>>> Total rings : 1
>>> Total plugins : 0
>>>
>>> cat /proc/net/pfring/<pid>-eth2.1
>>> ------------------------------------------------
>>> Bound Device : eth2
>>> Slot Version : 13 [5.1.0]
>>> Active : 1
>>> Breed : Non-DNA
>>> Sampling Rate : 1
>>> Capture Direction : RX+TX
>>> Appl. Name : pfcount
>>> IP Defragment : No
>>> BPF Filtering : Disabled
>>> # Sw Filt. Rules : 0
>>> # Hw Filt. Rules : 0
>>> Poll Pkt Watermark : 128
>>> Num Poll Calls : 1503
>>> Channel Id : -1
>>> Cluster Id : 0
>>> Min Num Slots : 6871
>>> Bucket Len : 128
>>> Slot Len : 304 [bucket+header]
>>> Tot Memory : 2097152
>>> Tot Packets : 0
>>> Tot Pkt Lost : 0
>>> Tot Insert : 0
>>> Tot Read : 0
>>> Insert Offset : 0
>>> Remove Offset : 0
>>> Tot Fwd Ok : 0
>>> Tot Fwd Errors : 0
>>> Num Free Slots : 6871
>>>
>>> ethtool -i eth2
>>> ----------------------
>>> driver: ixgbe
>>> version: 3.3.9-DNA
>>> firmware-version: 1.3-0
>>> bus-info: 0000:06:00.0
>>>
>>> ethtool eth2
>>> ----------------------
>>> Settings for eth2:
>>> Supported ports: [ FIBRE ]
>>> Supported link modes: 10000baseT/Full
>>> Supports auto-negotiation: No
>>> Advertised link modes: 10000baseT/Full
>>> Advertised auto-negotiation: No
>>> Speed: 10000Mb/s
>>> Duplex: Full
>>> Port: FIBRE
>>> PHYAD: 0
>>> Transceiver: external
>>> Auto-negotiation: off
>>> Supports Wake-on: d
>>> Wake-on: d
>>> Current message level: 0x00000007 (7)
>>> Link detected: yes
>>>
>>>
>>> I also tried pfcount -i dna:eth2, but got the following error:
>>>
>>> pfring_open error (pf_ring not loaded or perhaps you use quick mode
>>> and have already a socket bound to dna:eth2 ?)
>>>
>>> but:
>>>
>>> Module Size Used by
>>> pf_ring 335476 0
>>> ip6t_REJECT 5856 2
>>> nf_conntrack_ipv6 21880 2
>>> ip6table_filter 4016 1
>>> ip6_tables 19664 1 ip6table_filter
>>> ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
>>> dm_multipath 17304 0
>>> uinput 9248 0
>>> ixgbe 202760 0
>>> amd64_edac_mod 29632 0
>>> i2c_nforce2 9048 0
>>> dca 6708 1 ixgbe
>>> edac_core 43516 4 amd64_edac_mod
>>> forcedeth 54764 0
>>> mlx4_core 84128 0
>>> shpchp 34636 0
>>> serio_raw 6644 0
>>> pata_acpi 5152 0
>>> pata_amd 14260 0
>>> ata_generic 5924 0
>>> sata_nv 25228 2
>>> radeon 507616 1
>>> ttm 41952 1 radeon
>>> drm_kms_helper 25360 1 radeon
>>> drm 171168 3 radeon,ttm,drm_kms_helper
>>> i2c_algo_bit 6020 1 radeon
>>> i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit
>>>
>>> Any thoughts? Thanks for your help.
>>>
>>> =s=
>>>
>>> On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri<deri [at] ntop> wrote:
>>>> Scott
>>>> please redo your tests using the code in PF_RING's SVN. From the
>>>> interface names (we now call them dnaX) i see that you are using old stuff
>>>>
>>>> Luca
>>>>
>>>> On Oct 31, 2011, at 9:21 PM, Scott L wrote:
>>>>
>>>>> I'm having problems getting pfcount to work. I have two machines
>>>>> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
>>>>> NetEffect 10GbE NIC. I launch pfcount on A. Then on B I start
>>>>> pinging A. pfcount continually reports zero packets received.
>>>>>
>>>>> =========================
>>>>> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
>>>>> Total Pkts=0/Dropped=0.0 %
>>>>> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
>>>>> =========================
>>>>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>>>>> =========================
>>>>>
>>>>> The only relevant log messages I see are:
>>>>>
>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Down
>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
>>>>> device eth0 entered promiscuous mode
>>>>> device eth0 left promiscuous mode
>>>>> [PF_RING] --> handle_hw_filtering_rule(command=0)
>>>>> [PF_RING] --> handle_hw_filtering_rule(command=0)
>>>>> [PF_RING] --> handle_hw_filtering_rule(command=1)
>>>>> [PF_RING] --> handle_hw_filtering_rule(command=1)
>>>>>
>>>>> As I look around I don't see the problem. I can see the packets as
>>>>> they are transmitted on B. And the RX packet count for eth2 that is
>>>>> displayed by ifconfig increments appropriately on A. But pfcount
>>>>> doesn't see them. Anyone have any suggestions?
>>>>>
>>>>> ifconfig -i eth2
>>>>> -------------------
>>>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>> RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
>>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>> collisions:0 txqueuelen:1000
>>>>> RX bytes:1066541584248 (993.2 GiB) TX bytes:0 (0.0 b)
>>>>> Memory:fd7e0000-fd800000
>>>>>
>>>>> cat /proc/net/pfring/info
>>>>> --------------------------
>>>>> PF_RING Version : 5.0.0 ($Revision: exported$)
>>>>> Ring slots : 4096
>>>>> Slot version : 13
>>>>> Capture TX : Yes [RX+TX]
>>>>> IP Defragment : No
>>>>> Socket Mode : Standard
>>>>> Transparent mode : Yes (mode 0)
>>>>> Total rings : 1
>>>>> Total plugins : 0
>>>>>
>>>>> cat /proc/net/pfring/<pid>-eth2.30
>>>>> --------------------------------------------
>>>>> Bound Device : eth2
>>>>> Slot Version : 13 [5.0.0]
>>>>> Active : 1
>>>>> Breed : DNA
>>>>> Sampling Rate : 1
>>>>> Capture Direction : RX+TX
>>>>> Appl. Name : pfcount
>>>>> IP Defragment : No
>>>>> BPF Filtering : Disabled
>>>>> # Sw Filt. Rules : 0
>>>>> # Hw Filt. Rules : 0
>>>>> Poll Pkt Watermark : 128
>>>>> Num Poll Calls : 1461
>>>>> Channel Id : 0
>>>>> Num Slots : 8192
>>>>> Tot Memory : 33685504 bytes
>>>>>
>>>>> ethtool -i eth2
>>>>> -------------------
>>>>> driver: ixgbe
>>>>> version: 3.3.9-DNA
>>>>> firmware-version: 1.3-0
>>>>> bus-info: 0000:06:00.0
>>>>>
>>>>> ethtool eth2
>>>>> ----------------
>>>>> Settings for eth2:
>>>>> Supported ports: [ FIBRE ]
>>>>> Supported link modes: 10000baseT/Full
>>>>> Supports auto-negotiation: No
>>>>> Advertised link modes: 10000baseT/Full
>>>>> Advertised auto-negotiation: No
>>>>> Speed: 10000Mb/s
>>>>> Duplex: Full
>>>>> Port: FIBRE
>>>>> PHYAD: 0
>>>>> Transceiver: external
>>>>> Auto-negotiation: off
>>>>> Supports Wake-on: d
>>>>> Wake-on: d
>>>>> Current message level: 0x00000007 (7)
>>>>> Link detected: yes
>>>>> _______________________________________________
>>>>> Ntop-misc mailing list
>>>>> Ntop-misc [at] listgateway
>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>> ---
>>>> We can't solve problems by using the same kind of thinking we used when
>>>> we created them - Albert Einstein
>>>>
>>>> _______________________________________________
>>>> Ntop-misc mailing list
>>>> Ntop-misc [at] listgateway
>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>
>>> _______________________________________________
>>> Ntop-misc mailing list
>>> Ntop-misc [at] listgateway
>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>
>>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc

_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Nov 17, 2011, 4:48 PM

Post #11 of 30 (1540 views)
Permalink
Re: Problems with pfcount [In reply to]

Ah. I neglected to update the driver. I'm now seeing dnaX
interfaces. However, I'm still not receiving packets.

ifconfig dna0
------------------
dna0 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:0 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:0 (0.0 b) TX bytes:0 (0.0 b)
Memory:fd7e0000-fd800000

cat /proc/net/pf_ring/<pid>-dna0.8
--------------------------------------------------
Bound Device : dna0
Slot Version : 13 [5.1.0]
Active : 1
Breed : DNA
Sampling Rate : 1
Capture Direction : RX+TX
Appl. Name : pfcount
IP Defragment : No
BPF Filtering : Disabled
# Sw Filt. Rules : 0
# Hw Filt. Rules : 0
Poll Pkt Watermark : 128
Num Poll Calls : 1119
Channel Id : 0
Num RX Slots : 8192
Num TX Slots : 8192
Tot Memory : 34078720 bytes

cat /proc/net/pf_ring/info
----------------------------------------
PF_RING Version : 5.1.0 ($Revision: 4972$)
Ring slots : 4096
Slot version : 13
Capture TX : Yes [RX+TX]
IP Defragment : No
Socket Mode : Standard
Transparent mode : Yes (mode 0)
Total rings : 1
Total plugins : 0

ethtool -i dna0
-------------------------
driver: ixgbe
version: 3.6.7-DNA
firmware-version: 0x00011bab
bus-info: 0000:06:00.0

ethtool dna0
-----------------------
Settings for dna0:
Supported ports: [ FIBRE ]
Supported link modes: 10000baseT/Full
Supports auto-negotiation: No
Advertised link modes: 10000baseT/Full
Advertised auto-negotiation: No
Speed: 10000Mb/s
Duplex: Full
Port: FIBRE
PHYAD: 0
Transceiver: external
Auto-negotiation: off
Supports Wake-on: d
Wake-on: d
Current message level: 0x00000007 (7)
Link detected: yes

Any thoughts about why it's not working?

=s=


On Mon, Nov 14, 2011 at 1:59 AM, Luca Deri <deri [at] ntop> wrote:
> Hi all
> you are using an old version of the code as now DNA interfaces are named
> dnaX. Please fetch the latest code and drivers from SVN
>
> Luca
>
> On 11/10/2011 06:06 PM, Scott L wrote:
>>
>> Chris,
>>
>> Thanks for your response.  I am running pfcount as root.  I don't see
>> the error for "pfcount -i eth2" only for "pfcount -i dna:eth2".
>>
>> In my configuration, I don't expect to receive much traffic.  I am
>> connecting two machines with 10 GbE NICs back-to-back.  So the only
>> traffic I expect to see (for now) are the pings that I am attempting
>> to send; so the number of received packets is on the order of what I
>> would expect.
>>
>> =s=
>>
>> On Wed, Nov 9, 2011 at 1:11 PM, Chris Collord<ccollord [at] hotmail>
>>  wrote:
>>>
>>> Hi Scott,
>>> You'll see that error when you run pfcount without su permission (make
>>> sure
>>> you sudo or use root).  Not sure if that's your problem or not, i'm still
>>> figuring this out myself...
>>> On the other hand it doesn't look like you're receiving much.  Your RX
>>> packets are 210, whereas mine after an hour is...
>>> eth2      Link encap:Ethernet  HWaddr 0xxxxxxxxx:4c
>>>           inet addr:0.0.0.1  Bcast:255.255.255.255  Mask:0.0.0.0
>>>            UP BROADCAST RUNNING PROMISC MULTICAST  MTU:1500  Metric:1
>>>           RX packets:172969631 errors:0 dropped:1 overruns:0 frame:0
>>>           TX packets:5 errors:0 dropped:0 overruns:0 carrier:0
>>>           collisions:0 txqueuelen:1000
>>>           RX bytes:116951083144 (116.9 GB)  TX bytes:398 (398.0 B)
>>>
>>>
>>>
>>>
>>>> Date: Wed, 9 Nov 2011 12:05:55 -0700
>>>> From: sallynbird [at] gmail
>>>> To: ntop-misc [at] listgateway
>>>> Subject: Re: [Ntop-misc] Problems with pfcount
>>>>
>>>> I've updated my PF_RING code and I'm not seeing any difference (i.e.,
>>>> pfcount -i eth2 still shows 0 packets received but ifconfig shows
>>>> packets being received). Here's what I'm seeing with the new version:
>>>>
>>>> ifconfig eth2
>>>> -------------------
>>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>> RX packets:210 errors:0 dropped:0 overruns:0 frame:0
>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>> collisions:0 txqueuelen:1000
>>>> RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
>>>> Memory:fd7e0000-fd800000
>>>>
>>>> cat /proc/net/pfring/info
>>>> -----------------------------------
>>>> PF_RING Version : 5.1.0 ($Revision: 4972$)
>>>> Ring slots : 4096
>>>> Slot version : 13
>>>> Capture TX : Yes [RX+TX]
>>>> IP Defragment : No
>>>> Socket Mode : Standard
>>>> Transparent mode : Yes (mode 0)
>>>> Total rings : 1
>>>> Total plugins : 0
>>>>
>>>> cat /proc/net/pfring/<pid>-eth2.1
>>>> ------------------------------------------------
>>>> Bound Device : eth2
>>>> Slot Version : 13 [5.1.0]
>>>> Active : 1
>>>> Breed : Non-DNA
>>>> Sampling Rate : 1
>>>> Capture Direction : RX+TX
>>>> Appl. Name : pfcount
>>>> IP Defragment : No
>>>> BPF Filtering : Disabled
>>>> # Sw Filt. Rules : 0
>>>> # Hw Filt. Rules : 0
>>>> Poll Pkt Watermark : 128
>>>> Num Poll Calls : 1503
>>>> Channel Id : -1
>>>> Cluster Id : 0
>>>> Min Num Slots : 6871
>>>> Bucket Len : 128
>>>> Slot Len : 304 [bucket+header]
>>>> Tot Memory : 2097152
>>>> Tot Packets : 0
>>>> Tot Pkt Lost : 0
>>>> Tot Insert : 0
>>>> Tot Read : 0
>>>> Insert Offset : 0
>>>> Remove Offset : 0
>>>> Tot Fwd Ok : 0
>>>> Tot Fwd Errors : 0
>>>> Num Free Slots : 6871
>>>>
>>>> ethtool -i eth2
>>>> ----------------------
>>>> driver: ixgbe
>>>> version: 3.3.9-DNA
>>>> firmware-version: 1.3-0
>>>> bus-info: 0000:06:00.0
>>>>
>>>> ethtool eth2
>>>> ----------------------
>>>> Settings for eth2:
>>>> Supported ports: [ FIBRE ]
>>>> Supported link modes: 10000baseT/Full
>>>> Supports auto-negotiation: No
>>>> Advertised link modes: 10000baseT/Full
>>>> Advertised auto-negotiation: No
>>>> Speed: 10000Mb/s
>>>> Duplex: Full
>>>> Port: FIBRE
>>>> PHYAD: 0
>>>> Transceiver: external
>>>> Auto-negotiation: off
>>>> Supports Wake-on: d
>>>> Wake-on: d
>>>> Current message level: 0x00000007 (7)
>>>> Link detected: yes
>>>>
>>>>
>>>> I also tried pfcount -i dna:eth2, but got the following error:
>>>>
>>>> pfring_open error (pf_ring not loaded or perhaps you use quick mode
>>>> and have already a socket bound to dna:eth2 ?)
>>>>
>>>> but:
>>>>
>>>> Module Size Used by
>>>> pf_ring 335476 0
>>>> ip6t_REJECT 5856 2
>>>> nf_conntrack_ipv6 21880 2
>>>> ip6table_filter 4016 1
>>>> ip6_tables 19664 1 ip6table_filter
>>>> ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
>>>> dm_multipath 17304 0
>>>> uinput 9248 0
>>>> ixgbe 202760 0
>>>> amd64_edac_mod 29632 0
>>>> i2c_nforce2 9048 0
>>>> dca 6708 1 ixgbe
>>>> edac_core 43516 4 amd64_edac_mod
>>>> forcedeth 54764 0
>>>> mlx4_core 84128 0
>>>> shpchp 34636 0
>>>> serio_raw 6644 0
>>>> pata_acpi 5152 0
>>>> pata_amd 14260 0
>>>> ata_generic 5924 0
>>>> sata_nv 25228 2
>>>> radeon 507616 1
>>>> ttm 41952 1 radeon
>>>> drm_kms_helper 25360 1 radeon
>>>> drm 171168 3 radeon,ttm,drm_kms_helper
>>>> i2c_algo_bit 6020 1 radeon
>>>> i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit
>>>>
>>>> Any thoughts? Thanks for your help.
>>>>
>>>> =s=
>>>>
>>>> On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri<deri [at] ntop>  wrote:
>>>>>
>>>>> Scott
>>>>> please redo your tests using the code in PF_RING's SVN. From the
>>>>> interface names (we now call them dnaX) i see that you are using old
>>>>> stuff
>>>>>
>>>>> Luca
>>>>>
>>>>> On Oct 31, 2011, at 9:21 PM, Scott L wrote:
>>>>>
>>>>>> I'm having problems getting pfcount to work.  I have two machines
>>>>>> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
>>>>>> NetEffect 10GbE NIC.  I launch pfcount on A.  Then on B I start
>>>>>> pinging A.  pfcount continually reports zero packets received.
>>>>>>
>>>>>> =========================
>>>>>> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
>>>>>> Total Pkts=0/Dropped=0.0 %
>>>>>> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
>>>>>> =========================
>>>>>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>>>>>> =========================
>>>>>>
>>>>>> The only relevant log messages I see are:
>>>>>>
>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Down
>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
>>>>>> device eth0 entered promiscuous mode
>>>>>> device eth0 left promiscuous mode
>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=0)
>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=0)
>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=1)
>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=1)
>>>>>>
>>>>>> As I look around I don't see the problem.  I can see the packets as
>>>>>> they are transmitted on B.   And the RX packet count for eth2 that is
>>>>>> displayed by ifconfig increments appropriately on A.  But pfcount
>>>>>> doesn't see them.  Anyone have any suggestions?
>>>>>>
>>>>>> ifconfig -i eth2
>>>>>> -------------------
>>>>>> eth2      Link encap:Ethernet  HWaddr 00:E0:ED:FF:18:08
>>>>>>          inet addr:10.0.2.45  Bcast:10.0.2.255  Mask:255.255.255.0
>>>>>>          inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>>>          UP BROADCAST RUNNING PROMISC MULTICAST  MTU:1500  Metric:1
>>>>>>          RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
>>>>>>          TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>          collisions:0 txqueuelen:1000
>>>>>>          RX bytes:1066541584248 (993.2 GiB)  TX bytes:0 (0.0 b)
>>>>>>          Memory:fd7e0000-fd800000
>>>>>>
>>>>>> cat /proc/net/pfring/info
>>>>>> --------------------------
>>>>>> PF_RING Version     : 5.0.0 ($Revision: exported$)
>>>>>> Ring slots          : 4096
>>>>>> Slot version        : 13
>>>>>> Capture TX          : Yes [RX+TX]
>>>>>> IP Defragment       : No
>>>>>> Socket Mode         : Standard
>>>>>> Transparent mode    : Yes (mode 0)
>>>>>> Total rings         : 1
>>>>>> Total plugins       : 0
>>>>>>
>>>>>> cat /proc/net/pfring/<pid>-eth2.30
>>>>>> --------------------------------------------
>>>>>> Bound Device       : eth2
>>>>>> Slot Version       : 13 [5.0.0]
>>>>>> Active             : 1
>>>>>> Breed              : DNA
>>>>>> Sampling Rate      : 1
>>>>>> Capture Direction  : RX+TX
>>>>>> Appl. Name         : pfcount
>>>>>> IP Defragment      : No
>>>>>> BPF Filtering      : Disabled
>>>>>> # Sw Filt. Rules   : 0
>>>>>> # Hw Filt. Rules   : 0
>>>>>> Poll Pkt Watermark : 128
>>>>>> Num Poll Calls     : 1461
>>>>>> Channel Id         : 0
>>>>>> Num Slots          : 8192
>>>>>> Tot Memory         : 33685504 bytes
>>>>>>
>>>>>> ethtool -i eth2
>>>>>> -------------------
>>>>>> driver: ixgbe
>>>>>> version: 3.3.9-DNA
>>>>>> firmware-version: 1.3-0
>>>>>> bus-info: 0000:06:00.0
>>>>>>
>>>>>> ethtool eth2
>>>>>> ----------------
>>>>>> Settings for eth2:
>>>>>>       Supported ports: [ FIBRE ]
>>>>>>       Supported link modes:   10000baseT/Full
>>>>>>       Supports auto-negotiation: No
>>>>>>       Advertised link modes:  10000baseT/Full
>>>>>>       Advertised auto-negotiation: No
>>>>>>       Speed: 10000Mb/s
>>>>>>       Duplex: Full
>>>>>>       Port: FIBRE
>>>>>>       PHYAD: 0
>>>>>>       Transceiver: external
>>>>>>       Auto-negotiation: off
>>>>>>       Supports Wake-on: d
>>>>>>       Wake-on: d
>>>>>>       Current message level: 0x00000007 (7)
>>>>>>       Link detected: yes
>>>>>> _______________________________________________
>>>>>> Ntop-misc mailing list
>>>>>> Ntop-misc [at] listgateway
>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>
>>>>> ---
>>>>> We can't solve problems by using the same kind of thinking we used when
>>>>> we created them - Albert Einstein
>>>>>
>>>>> _______________________________________________
>>>>> Ntop-misc mailing list
>>>>> Ntop-misc [at] listgateway
>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>
>>>> _______________________________________________
>>>> Ntop-misc mailing list
>>>> Ntop-misc [at] listgateway
>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>
>>> _______________________________________________
>>> Ntop-misc mailing list
>>> Ntop-misc [at] listgateway
>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>
>>>
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


cardigliano at ntop

Nov 18, 2011, 1:29 AM

Post #12 of 30 (1520 views)
Permalink
Re: Problems with pfcount [In reply to]

Scott
Can you try with the latest stable release? (5.2.0)
Can I see the "lspci | grep 8259" and "ethtool -S dna0" output?

Alfredo

On Nov 18, 2011, at 1:48 AM, Scott L wrote:

> Ah. I neglected to update the driver. I'm now seeing dnaX
> interfaces. However, I'm still not receiving packets.
>
> ifconfig dna0
> ------------------
> dna0 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
> UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
> RX packets:0 errors:0 dropped:0 overruns:0 frame:0
> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:0 (0.0 b) TX bytes:0 (0.0 b)
> Memory:fd7e0000-fd800000
>
> cat /proc/net/pf_ring/<pid>-dna0.8
> --------------------------------------------------
> Bound Device : dna0
> Slot Version : 13 [5.1.0]
> Active : 1
> Breed : DNA
> Sampling Rate : 1
> Capture Direction : RX+TX
> Appl. Name : pfcount
> IP Defragment : No
> BPF Filtering : Disabled
> # Sw Filt. Rules : 0
> # Hw Filt. Rules : 0
> Poll Pkt Watermark : 128
> Num Poll Calls : 1119
> Channel Id : 0
> Num RX Slots : 8192
> Num TX Slots : 8192
> Tot Memory : 34078720 bytes
>
> cat /proc/net/pf_ring/info
> ----------------------------------------
> PF_RING Version : 5.1.0 ($Revision: 4972$)
> Ring slots : 4096
> Slot version : 13
> Capture TX : Yes [RX+TX]
> IP Defragment : No
> Socket Mode : Standard
> Transparent mode : Yes (mode 0)
> Total rings : 1
> Total plugins : 0
>
> ethtool -i dna0
> -------------------------
> driver: ixgbe
> version: 3.6.7-DNA
> firmware-version: 0x00011bab
> bus-info: 0000:06:00.0
>
> ethtool dna0
> -----------------------
> Settings for dna0:
> Supported ports: [ FIBRE ]
> Supported link modes: 10000baseT/Full
> Supports auto-negotiation: No
> Advertised link modes: 10000baseT/Full
> Advertised auto-negotiation: No
> Speed: 10000Mb/s
> Duplex: Full
> Port: FIBRE
> PHYAD: 0
> Transceiver: external
> Auto-negotiation: off
> Supports Wake-on: d
> Wake-on: d
> Current message level: 0x00000007 (7)
> Link detected: yes
>
> Any thoughts about why it's not working?
>
> =s=
>
>
> On Mon, Nov 14, 2011 at 1:59 AM, Luca Deri <deri [at] ntop> wrote:
>> Hi all
>> you are using an old version of the code as now DNA interfaces are named
>> dnaX. Please fetch the latest code and drivers from SVN
>>
>> Luca
>>
>> On 11/10/2011 06:06 PM, Scott L wrote:
>>>
>>> Chris,
>>>
>>> Thanks for your response. I am running pfcount as root. I don't see
>>> the error for "pfcount -i eth2" only for "pfcount -i dna:eth2".
>>>
>>> In my configuration, I don't expect to receive much traffic. I am
>>> connecting two machines with 10 GbE NICs back-to-back. So the only
>>> traffic I expect to see (for now) are the pings that I am attempting
>>> to send; so the number of received packets is on the order of what I
>>> would expect.
>>>
>>> =s=
>>>
>>> On Wed, Nov 9, 2011 at 1:11 PM, Chris Collord<ccollord [at] hotmail>
>>> wrote:
>>>>
>>>> Hi Scott,
>>>> You'll see that error when you run pfcount without su permission (make
>>>> sure
>>>> you sudo or use root). Not sure if that's your problem or not, i'm still
>>>> figuring this out myself...
>>>> On the other hand it doesn't look like you're receiving much. Your RX
>>>> packets are 210, whereas mine after an hour is...
>>>> eth2 Link encap:Ethernet HWaddr 0xxxxxxxxx:4c
>>>> inet addr:0.0.0.1 Bcast:255.255.255.255 Mask:0.0.0.0
>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>> RX packets:172969631 errors:0 dropped:1 overruns:0 frame:0
>>>> TX packets:5 errors:0 dropped:0 overruns:0 carrier:0
>>>> collisions:0 txqueuelen:1000
>>>> RX bytes:116951083144 (116.9 GB) TX bytes:398 (398.0 B)
>>>>
>>>>
>>>>
>>>>
>>>>> Date: Wed, 9 Nov 2011 12:05:55 -0700
>>>>> From: sallynbird [at] gmail
>>>>> To: ntop-misc [at] listgateway
>>>>> Subject: Re: [Ntop-misc] Problems with pfcount
>>>>>
>>>>> I've updated my PF_RING code and I'm not seeing any difference (i.e.,
>>>>> pfcount -i eth2 still shows 0 packets received but ifconfig shows
>>>>> packets being received). Here's what I'm seeing with the new version:
>>>>>
>>>>> ifconfig eth2
>>>>> -------------------
>>>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>> RX packets:210 errors:0 dropped:0 overruns:0 frame:0
>>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>> collisions:0 txqueuelen:1000
>>>>> RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
>>>>> Memory:fd7e0000-fd800000
>>>>>
>>>>> cat /proc/net/pfring/info
>>>>> -----------------------------------
>>>>> PF_RING Version : 5.1.0 ($Revision: 4972$)
>>>>> Ring slots : 4096
>>>>> Slot version : 13
>>>>> Capture TX : Yes [RX+TX]
>>>>> IP Defragment : No
>>>>> Socket Mode : Standard
>>>>> Transparent mode : Yes (mode 0)
>>>>> Total rings : 1
>>>>> Total plugins : 0
>>>>>
>>>>> cat /proc/net/pfring/<pid>-eth2.1
>>>>> ------------------------------------------------
>>>>> Bound Device : eth2
>>>>> Slot Version : 13 [5.1.0]
>>>>> Active : 1
>>>>> Breed : Non-DNA
>>>>> Sampling Rate : 1
>>>>> Capture Direction : RX+TX
>>>>> Appl. Name : pfcount
>>>>> IP Defragment : No
>>>>> BPF Filtering : Disabled
>>>>> # Sw Filt. Rules : 0
>>>>> # Hw Filt. Rules : 0
>>>>> Poll Pkt Watermark : 128
>>>>> Num Poll Calls : 1503
>>>>> Channel Id : -1
>>>>> Cluster Id : 0
>>>>> Min Num Slots : 6871
>>>>> Bucket Len : 128
>>>>> Slot Len : 304 [bucket+header]
>>>>> Tot Memory : 2097152
>>>>> Tot Packets : 0
>>>>> Tot Pkt Lost : 0
>>>>> Tot Insert : 0
>>>>> Tot Read : 0
>>>>> Insert Offset : 0
>>>>> Remove Offset : 0
>>>>> Tot Fwd Ok : 0
>>>>> Tot Fwd Errors : 0
>>>>> Num Free Slots : 6871
>>>>>
>>>>> ethtool -i eth2
>>>>> ----------------------
>>>>> driver: ixgbe
>>>>> version: 3.3.9-DNA
>>>>> firmware-version: 1.3-0
>>>>> bus-info: 0000:06:00.0
>>>>>
>>>>> ethtool eth2
>>>>> ----------------------
>>>>> Settings for eth2:
>>>>> Supported ports: [ FIBRE ]
>>>>> Supported link modes: 10000baseT/Full
>>>>> Supports auto-negotiation: No
>>>>> Advertised link modes: 10000baseT/Full
>>>>> Advertised auto-negotiation: No
>>>>> Speed: 10000Mb/s
>>>>> Duplex: Full
>>>>> Port: FIBRE
>>>>> PHYAD: 0
>>>>> Transceiver: external
>>>>> Auto-negotiation: off
>>>>> Supports Wake-on: d
>>>>> Wake-on: d
>>>>> Current message level: 0x00000007 (7)
>>>>> Link detected: yes
>>>>>
>>>>>
>>>>> I also tried pfcount -i dna:eth2, but got the following error:
>>>>>
>>>>> pfring_open error (pf_ring not loaded or perhaps you use quick mode
>>>>> and have already a socket bound to dna:eth2 ?)
>>>>>
>>>>> but:
>>>>>
>>>>> Module Size Used by
>>>>> pf_ring 335476 0
>>>>> ip6t_REJECT 5856 2
>>>>> nf_conntrack_ipv6 21880 2
>>>>> ip6table_filter 4016 1
>>>>> ip6_tables 19664 1 ip6table_filter
>>>>> ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
>>>>> dm_multipath 17304 0
>>>>> uinput 9248 0
>>>>> ixgbe 202760 0
>>>>> amd64_edac_mod 29632 0
>>>>> i2c_nforce2 9048 0
>>>>> dca 6708 1 ixgbe
>>>>> edac_core 43516 4 amd64_edac_mod
>>>>> forcedeth 54764 0
>>>>> mlx4_core 84128 0
>>>>> shpchp 34636 0
>>>>> serio_raw 6644 0
>>>>> pata_acpi 5152 0
>>>>> pata_amd 14260 0
>>>>> ata_generic 5924 0
>>>>> sata_nv 25228 2
>>>>> radeon 507616 1
>>>>> ttm 41952 1 radeon
>>>>> drm_kms_helper 25360 1 radeon
>>>>> drm 171168 3 radeon,ttm,drm_kms_helper
>>>>> i2c_algo_bit 6020 1 radeon
>>>>> i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit
>>>>>
>>>>> Any thoughts? Thanks for your help.
>>>>>
>>>>> =s=
>>>>>
>>>>> On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri<deri [at] ntop> wrote:
>>>>>>
>>>>>> Scott
>>>>>> please redo your tests using the code in PF_RING's SVN. From the
>>>>>> interface names (we now call them dnaX) i see that you are using old
>>>>>> stuff
>>>>>>
>>>>>> Luca
>>>>>>
>>>>>> On Oct 31, 2011, at 9:21 PM, Scott L wrote:
>>>>>>
>>>>>>> I'm having problems getting pfcount to work. I have two machines
>>>>>>> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
>>>>>>> NetEffect 10GbE NIC. I launch pfcount on A. Then on B I start
>>>>>>> pinging A. pfcount continually reports zero packets received.
>>>>>>>
>>>>>>> =========================
>>>>>>> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
>>>>>>> Total Pkts=0/Dropped=0.0 %
>>>>>>> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
>>>>>>> =========================
>>>>>>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>>>>>>> =========================
>>>>>>>
>>>>>>> The only relevant log messages I see are:
>>>>>>>
>>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Down
>>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
>>>>>>> device eth0 entered promiscuous mode
>>>>>>> device eth0 left promiscuous mode
>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=0)
>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=0)
>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=1)
>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=1)
>>>>>>>
>>>>>>> As I look around I don't see the problem. I can see the packets as
>>>>>>> they are transmitted on B. And the RX packet count for eth2 that is
>>>>>>> displayed by ifconfig increments appropriately on A. But pfcount
>>>>>>> doesn't see them. Anyone have any suggestions?
>>>>>>>
>>>>>>> ifconfig -i eth2
>>>>>>> -------------------
>>>>>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>>>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>>>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>>>> RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
>>>>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>> collisions:0 txqueuelen:1000
>>>>>>> RX bytes:1066541584248 (993.2 GiB) TX bytes:0 (0.0 b)
>>>>>>> Memory:fd7e0000-fd800000
>>>>>>>
>>>>>>> cat /proc/net/pfring/info
>>>>>>> --------------------------
>>>>>>> PF_RING Version : 5.0.0 ($Revision: exported$)
>>>>>>> Ring slots : 4096
>>>>>>> Slot version : 13
>>>>>>> Capture TX : Yes [RX+TX]
>>>>>>> IP Defragment : No
>>>>>>> Socket Mode : Standard
>>>>>>> Transparent mode : Yes (mode 0)
>>>>>>> Total rings : 1
>>>>>>> Total plugins : 0
>>>>>>>
>>>>>>> cat /proc/net/pfring/<pid>-eth2.30
>>>>>>> --------------------------------------------
>>>>>>> Bound Device : eth2
>>>>>>> Slot Version : 13 [5.0.0]
>>>>>>> Active : 1
>>>>>>> Breed : DNA
>>>>>>> Sampling Rate : 1
>>>>>>> Capture Direction : RX+TX
>>>>>>> Appl. Name : pfcount
>>>>>>> IP Defragment : No
>>>>>>> BPF Filtering : Disabled
>>>>>>> # Sw Filt. Rules : 0
>>>>>>> # Hw Filt. Rules : 0
>>>>>>> Poll Pkt Watermark : 128
>>>>>>> Num Poll Calls : 1461
>>>>>>> Channel Id : 0
>>>>>>> Num Slots : 8192
>>>>>>> Tot Memory : 33685504 bytes
>>>>>>>
>>>>>>> ethtool -i eth2
>>>>>>> -------------------
>>>>>>> driver: ixgbe
>>>>>>> version: 3.3.9-DNA
>>>>>>> firmware-version: 1.3-0
>>>>>>> bus-info: 0000:06:00.0
>>>>>>>
>>>>>>> ethtool eth2
>>>>>>> ----------------
>>>>>>> Settings for eth2:
>>>>>>> Supported ports: [ FIBRE ]
>>>>>>> Supported link modes: 10000baseT/Full
>>>>>>> Supports auto-negotiation: No
>>>>>>> Advertised link modes: 10000baseT/Full
>>>>>>> Advertised auto-negotiation: No
>>>>>>> Speed: 10000Mb/s
>>>>>>> Duplex: Full
>>>>>>> Port: FIBRE
>>>>>>> PHYAD: 0
>>>>>>> Transceiver: external
>>>>>>> Auto-negotiation: off
>>>>>>> Supports Wake-on: d
>>>>>>> Wake-on: d
>>>>>>> Current message level: 0x00000007 (7)
>>>>>>> Link detected: yes
>>>>>>> _______________________________________________
>>>>>>> Ntop-misc mailing list
>>>>>>> Ntop-misc [at] listgateway
>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>
>>>>>> ---
>>>>>> We can't solve problems by using the same kind of thinking we used when
>>>>>> we created them - Albert Einstein
>>>>>>
>>>>>> _______________________________________________
>>>>>> Ntop-misc mailing list
>>>>>> Ntop-misc [at] listgateway
>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>
>>>>> _______________________________________________
>>>>> Ntop-misc mailing list
>>>>> Ntop-misc [at] listgateway
>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>
>>>> _______________________________________________
>>>> Ntop-misc mailing list
>>>> Ntop-misc [at] listgateway
>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>
>>>>
>>> _______________________________________________
>>> Ntop-misc mailing list
>>> Ntop-misc [at] listgateway
>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc

_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Nov 18, 2011, 11:18 AM

Post #13 of 30 (1528 views)
Permalink
Re: Problems with pfcount [In reply to]

Alfredo,

I upgraded to 5.2.0 and saw some positive results. I received packets
for a while and then they mysteriously stopped. So far, the only way
that I've found to fix the problem is to reboot. The pfcount output
looks something like this (the duration during which I receive packets
seems to vary from reboot to reboot).

(at this point, I've just tested connectivity using pings)
=========================
Absolute Stats: [24 pkts rcvd][0 pkts dropped]
Total Pkts=24/Dropped=0.0 %
24 pkts - 2'352 bytes [1.71 pkt/sec - 0.00 Mbit/sec]
=========================
Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
=========================

(in this interval, I start sending UDP packets as fast as I can from
the other machine)
=========================
Absolute Stats: [24713 pkts rcvd][12653 pkts dropped]
Total Pkts=37366/Dropped=33.9 %
24'713 pkts - 36'492'694 bytes [1'647.42 pkt/sec - 19.46 Mbit/sec]
=========================
Actual Stats: 24689 pkts [1'000.05 ms][24'687.56 pkt/sec]
=========================

=========================
Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
Total Pkts=176656/Dropped=7.2 %
164'003 pkts - 242'363'314 bytes [10'249.49 pkt/sec - 121.17 Mbit/sec]
=========================
Actual Stats: 139290 pkts [1'000.05 ms][139'281.78 pkt/sec]
=========================

(mysteriously, I stop receiving packets in this interval)
=========================
Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
Total Pkts=176656/Dropped=7.2 %
164'003 pkts - 242'363'314 bytes [9'646.57 pkt/sec - 114.05 Mbit/sec]
=========================
Actual Stats: 0 pkts [1'000.07 ms][0.00 pkt/sec]
=========================

=========================
Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
Total Pkts=176656/Dropped=7.2 %
164'003 pkts - 242'363'314 bytes [9'110.65 pkt/sec - 107.71 Mbit/sec]
=========================
Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
=========================

lspci | grep 8259 returns nothing.

The entry for my DNA NICs looks like:

06:00.0 Ethernet controller: Intel Corporation Device 10fb (rev 01)
06:00.1 Ethernet controller: Intel Corporation Device 10fb (rev 01)

ethtool -S dna0
------------------------------
NIC statistics:
rx_packets: 176992
tx_packets: 0
rx_bytes: 262269024
tx_bytes: 0
rx_errors: 0
tx_errors: 0
rx_dropped: 0
tx_dropped: 0
multicast: 0
collisions: 0
rx_over_errors: 0
rx_crc_errors: 0
rx_frame_errors: 0
rx_fifo_errors: 0
rx_missed_errors: 0
tx_aborted_errors: 0
tx_carrier_errors: 0
tx_fifo_errors: 0
tx_heartbeat_errors: 0
rx_pkts_nic: 176992
tx_pkts_nic: 0
rx_bytes_nic: 262269024
tx_bytes_nic: 0
lsc_int: 2
tx_busy: 0
non_eop_descs: 0
broadcast: 0
rx_no_buffer_count: 0
tx_timeout_count: 0
tx_restart_queue: 0
rx_long_length_errors: 0
rx_short_length_errors: 0
tx_flow_control_xon: 0
rx_flow_control_xon: 0
tx_flow_control_xoff: 127567
rx_flow_control_xoff: 0
rx_csum_offload_errors: 0
alloc_rx_page_failed: 0
alloc_rx_buff_failed: 0
lro_aggregated: 0
lro_flushed: 0
lro_recycled: 0
rx_no_dma_resources: 0
hw_rsc_aggregated: 0
hw_rsc_flushed: 0
fdir_match: 0
fdir_miss: 0
fdir_overflow: 0
fcoe_bad_fccrc: 0
fcoe_last_errors: 0
rx_fcoe_dropped: 0
rx_fcoe_packets: 0
rx_fcoe_dwords: 0
tx_fcoe_packets: 0
tx_fcoe_dwords: 0
os2bmc_rx_by_bmc: 0
os2bmc_tx_by_bmc: 0
os2bmc_tx_by_host: 0
os2bmc_rx_by_host: 0
tx_queue_0_packets: 0
tx_queue_0_bytes: 0
rx_queue_0_packets: 0
rx_queue_0_bytes: 0


Thanks,

=s=

On Fri, Nov 18, 2011 at 2:29 AM, Alfredo Cardigliano
<cardigliano [at] ntop> wrote:
> Scott
> Can you try with the latest stable release? (5.2.0)
> Can I see the "lspci | grep 8259" and "ethtool -S dna0" output?
>
> Alfredo
>
> On Nov 18, 2011, at 1:48 AM, Scott L wrote:
>
>> Ah.  I neglected to update the driver.  I'm now seeing dnaX
>> interfaces.  However, I'm still not receiving packets.
>>
>> ifconfig dna0
>> ------------------
>> dna0      Link encap:Ethernet  HWaddr 00:E0:ED:FF:18:08
>>          inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>          UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
>>          RX packets:0 errors:0 dropped:0 overruns:0 frame:0
>>          TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>          collisions:0 txqueuelen:1000
>>          RX bytes:0 (0.0 b)  TX bytes:0 (0.0 b)
>>          Memory:fd7e0000-fd800000
>>
>> cat /proc/net/pf_ring/<pid>-dna0.8
>> --------------------------------------------------
>> Bound Device       : dna0
>> Slot Version       : 13 [5.1.0]
>> Active             : 1
>> Breed              : DNA
>> Sampling Rate      : 1
>> Capture Direction  : RX+TX
>> Appl. Name         : pfcount
>> IP Defragment      : No
>> BPF Filtering      : Disabled
>> # Sw Filt. Rules   : 0
>> # Hw Filt. Rules   : 0
>> Poll Pkt Watermark : 128
>> Num Poll Calls     : 1119
>> Channel Id         : 0
>> Num RX Slots       : 8192
>> Num TX Slots       : 8192
>> Tot Memory         : 34078720 bytes
>>
>> cat /proc/net/pf_ring/info
>> ----------------------------------------
>> PF_RING Version     : 5.1.0 ($Revision: 4972$)
>> Ring slots          : 4096
>> Slot version        : 13
>> Capture TX          : Yes [RX+TX]
>> IP Defragment       : No
>> Socket Mode         : Standard
>> Transparent mode    : Yes (mode 0)
>> Total rings         : 1
>> Total plugins       : 0
>>
>> ethtool -i dna0
>> -------------------------
>> driver: ixgbe
>> version: 3.6.7-DNA
>> firmware-version: 0x00011bab
>> bus-info: 0000:06:00.0
>>
>> ethtool dna0
>> -----------------------
>> Settings for dna0:
>>       Supported ports: [ FIBRE ]
>>       Supported link modes:   10000baseT/Full
>>       Supports auto-negotiation: No
>>       Advertised link modes:  10000baseT/Full
>>       Advertised auto-negotiation: No
>>       Speed: 10000Mb/s
>>       Duplex: Full
>>       Port: FIBRE
>>       PHYAD: 0
>>       Transceiver: external
>>       Auto-negotiation: off
>>       Supports Wake-on: d
>>       Wake-on: d
>>       Current message level: 0x00000007 (7)
>>       Link detected: yes
>>
>> Any thoughts about why it's not working?
>>
>> =s=
>>
>>
>> On Mon, Nov 14, 2011 at 1:59 AM, Luca Deri <deri [at] ntop> wrote:
>>> Hi all
>>> you are using an old version of the code as now DNA interfaces are named
>>> dnaX. Please fetch the latest code and drivers from SVN
>>>
>>> Luca
>>>
>>> On 11/10/2011 06:06 PM, Scott L wrote:
>>>>
>>>> Chris,
>>>>
>>>> Thanks for your response.  I am running pfcount as root.  I don't see
>>>> the error for "pfcount -i eth2" only for "pfcount -i dna:eth2".
>>>>
>>>> In my configuration, I don't expect to receive much traffic.  I am
>>>> connecting two machines with 10 GbE NICs back-to-back.  So the only
>>>> traffic I expect to see (for now) are the pings that I am attempting
>>>> to send; so the number of received packets is on the order of what I
>>>> would expect.
>>>>
>>>> =s=
>>>>
>>>> On Wed, Nov 9, 2011 at 1:11 PM, Chris Collord<ccollord [at] hotmail>
>>>>  wrote:
>>>>>
>>>>> Hi Scott,
>>>>> You'll see that error when you run pfcount without su permission (make
>>>>> sure
>>>>> you sudo or use root).  Not sure if that's your problem or not, i'm still
>>>>> figuring this out myself...
>>>>> On the other hand it doesn't look like you're receiving much.  Your RX
>>>>> packets are 210, whereas mine after an hour is...
>>>>> eth2      Link encap:Ethernet  HWaddr 0xxxxxxxxx:4c
>>>>>           inet addr:0.0.0.1  Bcast:255.255.255.255  Mask:0.0.0.0
>>>>>            UP BROADCAST RUNNING PROMISC MULTICAST  MTU:1500  Metric:1
>>>>>           RX packets:172969631 errors:0 dropped:1 overruns:0 frame:0
>>>>>           TX packets:5 errors:0 dropped:0 overruns:0 carrier:0
>>>>>           collisions:0 txqueuelen:1000
>>>>>           RX bytes:116951083144 (116.9 GB)  TX bytes:398 (398.0 B)
>>>>>
>>>>>
>>>>>
>>>>>
>>>>>> Date: Wed, 9 Nov 2011 12:05:55 -0700
>>>>>> From: sallynbird [at] gmail
>>>>>> To: ntop-misc [at] listgateway
>>>>>> Subject: Re: [Ntop-misc] Problems with pfcount
>>>>>>
>>>>>> I've updated my PF_RING code and I'm not seeing any difference (i.e.,
>>>>>> pfcount -i eth2 still shows 0 packets received but ifconfig shows
>>>>>> packets being received). Here's what I'm seeing with the new version:
>>>>>>
>>>>>> ifconfig eth2
>>>>>> -------------------
>>>>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>>> RX packets:210 errors:0 dropped:0 overruns:0 frame:0
>>>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>>> collisions:0 txqueuelen:1000
>>>>>> RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
>>>>>> Memory:fd7e0000-fd800000
>>>>>>
>>>>>> cat /proc/net/pfring/info
>>>>>> -----------------------------------
>>>>>> PF_RING Version : 5.1.0 ($Revision: 4972$)
>>>>>> Ring slots : 4096
>>>>>> Slot version : 13
>>>>>> Capture TX : Yes [RX+TX]
>>>>>> IP Defragment : No
>>>>>> Socket Mode : Standard
>>>>>> Transparent mode : Yes (mode 0)
>>>>>> Total rings : 1
>>>>>> Total plugins : 0
>>>>>>
>>>>>> cat /proc/net/pfring/<pid>-eth2.1
>>>>>> ------------------------------------------------
>>>>>> Bound Device : eth2
>>>>>> Slot Version : 13 [5.1.0]
>>>>>> Active : 1
>>>>>> Breed : Non-DNA
>>>>>> Sampling Rate : 1
>>>>>> Capture Direction : RX+TX
>>>>>> Appl. Name : pfcount
>>>>>> IP Defragment : No
>>>>>> BPF Filtering : Disabled
>>>>>> # Sw Filt. Rules : 0
>>>>>> # Hw Filt. Rules : 0
>>>>>> Poll Pkt Watermark : 128
>>>>>> Num Poll Calls : 1503
>>>>>> Channel Id : -1
>>>>>> Cluster Id : 0
>>>>>> Min Num Slots : 6871
>>>>>> Bucket Len : 128
>>>>>> Slot Len : 304 [bucket+header]
>>>>>> Tot Memory : 2097152
>>>>>> Tot Packets : 0
>>>>>> Tot Pkt Lost : 0
>>>>>> Tot Insert : 0
>>>>>> Tot Read : 0
>>>>>> Insert Offset : 0
>>>>>> Remove Offset : 0
>>>>>> Tot Fwd Ok : 0
>>>>>> Tot Fwd Errors : 0
>>>>>> Num Free Slots : 6871
>>>>>>
>>>>>> ethtool -i eth2
>>>>>> ----------------------
>>>>>> driver: ixgbe
>>>>>> version: 3.3.9-DNA
>>>>>> firmware-version: 1.3-0
>>>>>> bus-info: 0000:06:00.0
>>>>>>
>>>>>> ethtool eth2
>>>>>> ----------------------
>>>>>> Settings for eth2:
>>>>>> Supported ports: [ FIBRE ]
>>>>>> Supported link modes: 10000baseT/Full
>>>>>> Supports auto-negotiation: No
>>>>>> Advertised link modes: 10000baseT/Full
>>>>>> Advertised auto-negotiation: No
>>>>>> Speed: 10000Mb/s
>>>>>> Duplex: Full
>>>>>> Port: FIBRE
>>>>>> PHYAD: 0
>>>>>> Transceiver: external
>>>>>> Auto-negotiation: off
>>>>>> Supports Wake-on: d
>>>>>> Wake-on: d
>>>>>> Current message level: 0x00000007 (7)
>>>>>> Link detected: yes
>>>>>>
>>>>>>
>>>>>> I also tried pfcount -i dna:eth2, but got the following error:
>>>>>>
>>>>>> pfring_open error (pf_ring not loaded or perhaps you use quick mode
>>>>>> and have already a socket bound to dna:eth2 ?)
>>>>>>
>>>>>> but:
>>>>>>
>>>>>> Module Size Used by
>>>>>> pf_ring 335476 0
>>>>>> ip6t_REJECT 5856 2
>>>>>> nf_conntrack_ipv6 21880 2
>>>>>> ip6table_filter 4016 1
>>>>>> ip6_tables 19664 1 ip6table_filter
>>>>>> ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
>>>>>> dm_multipath 17304 0
>>>>>> uinput 9248 0
>>>>>> ixgbe 202760 0
>>>>>> amd64_edac_mod 29632 0
>>>>>> i2c_nforce2 9048 0
>>>>>> dca 6708 1 ixgbe
>>>>>> edac_core 43516 4 amd64_edac_mod
>>>>>> forcedeth 54764 0
>>>>>> mlx4_core 84128 0
>>>>>> shpchp 34636 0
>>>>>> serio_raw 6644 0
>>>>>> pata_acpi 5152 0
>>>>>> pata_amd 14260 0
>>>>>> ata_generic 5924 0
>>>>>> sata_nv 25228 2
>>>>>> radeon 507616 1
>>>>>> ttm 41952 1 radeon
>>>>>> drm_kms_helper 25360 1 radeon
>>>>>> drm 171168 3 radeon,ttm,drm_kms_helper
>>>>>> i2c_algo_bit 6020 1 radeon
>>>>>> i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit
>>>>>>
>>>>>> Any thoughts? Thanks for your help.
>>>>>>
>>>>>> =s=
>>>>>>
>>>>>> On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri<deri [at] ntop>  wrote:
>>>>>>>
>>>>>>> Scott
>>>>>>> please redo your tests using the code in PF_RING's SVN. From the
>>>>>>> interface names (we now call them dnaX) i see that you are using old
>>>>>>> stuff
>>>>>>>
>>>>>>> Luca
>>>>>>>
>>>>>>> On Oct 31, 2011, at 9:21 PM, Scott L wrote:
>>>>>>>
>>>>>>>> I'm having problems getting pfcount to work.  I have two machines
>>>>>>>> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
>>>>>>>> NetEffect 10GbE NIC.  I launch pfcount on A.  Then on B I start
>>>>>>>> pinging A.  pfcount continually reports zero packets received.
>>>>>>>>
>>>>>>>> =========================
>>>>>>>> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
>>>>>>>> Total Pkts=0/Dropped=0.0 %
>>>>>>>> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
>>>>>>>> =========================
>>>>>>>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>>>>>>>> =========================
>>>>>>>>
>>>>>>>> The only relevant log messages I see are:
>>>>>>>>
>>>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Down
>>>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
>>>>>>>> device eth0 entered promiscuous mode
>>>>>>>> device eth0 left promiscuous mode
>>>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=0)
>>>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=0)
>>>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=1)
>>>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=1)
>>>>>>>>
>>>>>>>> As I look around I don't see the problem.  I can see the packets as
>>>>>>>> they are transmitted on B.   And the RX packet count for eth2 that is
>>>>>>>> displayed by ifconfig increments appropriately on A.  But pfcount
>>>>>>>> doesn't see them.  Anyone have any suggestions?
>>>>>>>>
>>>>>>>> ifconfig -i eth2
>>>>>>>> -------------------
>>>>>>>> eth2      Link encap:Ethernet  HWaddr 00:E0:ED:FF:18:08
>>>>>>>>          inet addr:10.0.2.45  Bcast:10.0.2.255  Mask:255.255.255.0
>>>>>>>>          inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>>>>>          UP BROADCAST RUNNING PROMISC MULTICAST  MTU:1500  Metric:1
>>>>>>>>          RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
>>>>>>>>          TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>>>          collisions:0 txqueuelen:1000
>>>>>>>>          RX bytes:1066541584248 (993.2 GiB)  TX bytes:0 (0.0 b)
>>>>>>>>          Memory:fd7e0000-fd800000
>>>>>>>>
>>>>>>>> cat /proc/net/pfring/info
>>>>>>>> --------------------------
>>>>>>>> PF_RING Version     : 5.0.0 ($Revision: exported$)
>>>>>>>> Ring slots          : 4096
>>>>>>>> Slot version        : 13
>>>>>>>> Capture TX          : Yes [RX+TX]
>>>>>>>> IP Defragment       : No
>>>>>>>> Socket Mode         : Standard
>>>>>>>> Transparent mode    : Yes (mode 0)
>>>>>>>> Total rings         : 1
>>>>>>>> Total plugins       : 0
>>>>>>>>
>>>>>>>> cat /proc/net/pfring/<pid>-eth2.30
>>>>>>>> --------------------------------------------
>>>>>>>> Bound Device       : eth2
>>>>>>>> Slot Version       : 13 [5.0.0]
>>>>>>>> Active             : 1
>>>>>>>> Breed              : DNA
>>>>>>>> Sampling Rate      : 1
>>>>>>>> Capture Direction  : RX+TX
>>>>>>>> Appl. Name         : pfcount
>>>>>>>> IP Defragment      : No
>>>>>>>> BPF Filtering      : Disabled
>>>>>>>> # Sw Filt. Rules   : 0
>>>>>>>> # Hw Filt. Rules   : 0
>>>>>>>> Poll Pkt Watermark : 128
>>>>>>>> Num Poll Calls     : 1461
>>>>>>>> Channel Id         : 0
>>>>>>>> Num Slots          : 8192
>>>>>>>> Tot Memory         : 33685504 bytes
>>>>>>>>
>>>>>>>> ethtool -i eth2
>>>>>>>> -------------------
>>>>>>>> driver: ixgbe
>>>>>>>> version: 3.3.9-DNA
>>>>>>>> firmware-version: 1.3-0
>>>>>>>> bus-info: 0000:06:00.0
>>>>>>>>
>>>>>>>> ethtool eth2
>>>>>>>> ----------------
>>>>>>>> Settings for eth2:
>>>>>>>>       Supported ports: [ FIBRE ]
>>>>>>>>       Supported link modes:   10000baseT/Full
>>>>>>>>       Supports auto-negotiation: No
>>>>>>>>       Advertised link modes:  10000baseT/Full
>>>>>>>>       Advertised auto-negotiation: No
>>>>>>>>       Speed: 10000Mb/s
>>>>>>>>       Duplex: Full
>>>>>>>>       Port: FIBRE
>>>>>>>>       PHYAD: 0
>>>>>>>>       Transceiver: external
>>>>>>>>       Auto-negotiation: off
>>>>>>>>       Supports Wake-on: d
>>>>>>>>       Wake-on: d
>>>>>>>>       Current message level: 0x00000007 (7)
>>>>>>>>       Link detected: yes
>>>>>>>> _______________________________________________
>>>>>>>> Ntop-misc mailing list
>>>>>>>> Ntop-misc [at] listgateway
>>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>
>>>>>>> ---
>>>>>>> We can't solve problems by using the same kind of thinking we used when
>>>>>>> we created them - Albert Einstein
>>>>>>>
>>>>>>> _______________________________________________
>>>>>>> Ntop-misc mailing list
>>>>>>> Ntop-misc [at] listgateway
>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>
>>>>>> _______________________________________________
>>>>>> Ntop-misc mailing list
>>>>>> Ntop-misc [at] listgateway
>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>
>>>>> _______________________________________________
>>>>> Ntop-misc mailing list
>>>>> Ntop-misc [at] listgateway
>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>
>>>>>
>>>> _______________________________________________
>>>> Ntop-misc mailing list
>>>> Ntop-misc [at] listgateway
>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>
>>> _______________________________________________
>>> Ntop-misc mailing list
>>> Ntop-misc [at] listgateway
>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


cardigliano at ntop

Nov 18, 2011, 12:26 PM

Post #14 of 30 (1531 views)
Permalink
Re: Problems with pfcount [In reply to]

Scott
prior to further investigate on this strange issue, are you sure the problem is on the rx side? how are you generating the traffic?
The card seems to be an X520 (82599), right?

Regards
Alfredo

On Nov 18, 2011, at 8:18 PM, Scott L wrote:

> Alfredo,
>
> I upgraded to 5.2.0 and saw some positive results. I received packets
> for a while and then they mysteriously stopped. So far, the only way
> that I've found to fix the problem is to reboot. The pfcount output
> looks something like this (the duration during which I receive packets
> seems to vary from reboot to reboot).
>
> (at this point, I've just tested connectivity using pings)
> =========================
> Absolute Stats: [24 pkts rcvd][0 pkts dropped]
> Total Pkts=24/Dropped=0.0 %
> 24 pkts - 2'352 bytes [1.71 pkt/sec - 0.00 Mbit/sec]
> =========================
> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
> =========================
>
> (in this interval, I start sending UDP packets as fast as I can from
> the other machine)
> =========================
> Absolute Stats: [24713 pkts rcvd][12653 pkts dropped]
> Total Pkts=37366/Dropped=33.9 %
> 24'713 pkts - 36'492'694 bytes [1'647.42 pkt/sec - 19.46 Mbit/sec]
> =========================
> Actual Stats: 24689 pkts [1'000.05 ms][24'687.56 pkt/sec]
> =========================
>
> =========================
> Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
> Total Pkts=176656/Dropped=7.2 %
> 164'003 pkts - 242'363'314 bytes [10'249.49 pkt/sec - 121.17 Mbit/sec]
> =========================
> Actual Stats: 139290 pkts [1'000.05 ms][139'281.78 pkt/sec]
> =========================
>
> (mysteriously, I stop receiving packets in this interval)
> =========================
> Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
> Total Pkts=176656/Dropped=7.2 %
> 164'003 pkts - 242'363'314 bytes [9'646.57 pkt/sec - 114.05 Mbit/sec]
> =========================
> Actual Stats: 0 pkts [1'000.07 ms][0.00 pkt/sec]
> =========================
>
> =========================
> Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
> Total Pkts=176656/Dropped=7.2 %
> 164'003 pkts - 242'363'314 bytes [9'110.65 pkt/sec - 107.71 Mbit/sec]
> =========================
> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
> =========================
>
> lspci | grep 8259 returns nothing.
>
> The entry for my DNA NICs looks like:
>
> 06:00.0 Ethernet controller: Intel Corporation Device 10fb (rev 01)
> 06:00.1 Ethernet controller: Intel Corporation Device 10fb (rev 01)
>
> ethtool -S dna0
> ------------------------------
> NIC statistics:
> rx_packets: 176992
> tx_packets: 0
> rx_bytes: 262269024
> tx_bytes: 0
> rx_errors: 0
> tx_errors: 0
> rx_dropped: 0
> tx_dropped: 0
> multicast: 0
> collisions: 0
> rx_over_errors: 0
> rx_crc_errors: 0
> rx_frame_errors: 0
> rx_fifo_errors: 0
> rx_missed_errors: 0
> tx_aborted_errors: 0
> tx_carrier_errors: 0
> tx_fifo_errors: 0
> tx_heartbeat_errors: 0
> rx_pkts_nic: 176992
> tx_pkts_nic: 0
> rx_bytes_nic: 262269024
> tx_bytes_nic: 0
> lsc_int: 2
> tx_busy: 0
> non_eop_descs: 0
> broadcast: 0
> rx_no_buffer_count: 0
> tx_timeout_count: 0
> tx_restart_queue: 0
> rx_long_length_errors: 0
> rx_short_length_errors: 0
> tx_flow_control_xon: 0
> rx_flow_control_xon: 0
> tx_flow_control_xoff: 127567
> rx_flow_control_xoff: 0
> rx_csum_offload_errors: 0
> alloc_rx_page_failed: 0
> alloc_rx_buff_failed: 0
> lro_aggregated: 0
> lro_flushed: 0
> lro_recycled: 0
> rx_no_dma_resources: 0
> hw_rsc_aggregated: 0
> hw_rsc_flushed: 0
> fdir_match: 0
> fdir_miss: 0
> fdir_overflow: 0
> fcoe_bad_fccrc: 0
> fcoe_last_errors: 0
> rx_fcoe_dropped: 0
> rx_fcoe_packets: 0
> rx_fcoe_dwords: 0
> tx_fcoe_packets: 0
> tx_fcoe_dwords: 0
> os2bmc_rx_by_bmc: 0
> os2bmc_tx_by_bmc: 0
> os2bmc_tx_by_host: 0
> os2bmc_rx_by_host: 0
> tx_queue_0_packets: 0
> tx_queue_0_bytes: 0
> rx_queue_0_packets: 0
> rx_queue_0_bytes: 0
>
>
> Thanks,
>
> =s=
>
> On Fri, Nov 18, 2011 at 2:29 AM, Alfredo Cardigliano
> <cardigliano [at] ntop> wrote:
>> Scott
>> Can you try with the latest stable release? (5.2.0)
>> Can I see the "lspci | grep 8259" and "ethtool -S dna0" output?
>>
>> Alfredo
>>
>> On Nov 18, 2011, at 1:48 AM, Scott L wrote:
>>
>>> Ah. I neglected to update the driver. I'm now seeing dnaX
>>> interfaces. However, I'm still not receiving packets.
>>>
>>> ifconfig dna0
>>> ------------------
>>> dna0 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>> UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
>>> RX packets:0 errors:0 dropped:0 overruns:0 frame:0
>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>> collisions:0 txqueuelen:1000
>>> RX bytes:0 (0.0 b) TX bytes:0 (0.0 b)
>>> Memory:fd7e0000-fd800000
>>>
>>> cat /proc/net/pf_ring/<pid>-dna0.8
>>> --------------------------------------------------
>>> Bound Device : dna0
>>> Slot Version : 13 [5.1.0]
>>> Active : 1
>>> Breed : DNA
>>> Sampling Rate : 1
>>> Capture Direction : RX+TX
>>> Appl. Name : pfcount
>>> IP Defragment : No
>>> BPF Filtering : Disabled
>>> # Sw Filt. Rules : 0
>>> # Hw Filt. Rules : 0
>>> Poll Pkt Watermark : 128
>>> Num Poll Calls : 1119
>>> Channel Id : 0
>>> Num RX Slots : 8192
>>> Num TX Slots : 8192
>>> Tot Memory : 34078720 bytes
>>>
>>> cat /proc/net/pf_ring/info
>>> ----------------------------------------
>>> PF_RING Version : 5.1.0 ($Revision: 4972$)
>>> Ring slots : 4096
>>> Slot version : 13
>>> Capture TX : Yes [RX+TX]
>>> IP Defragment : No
>>> Socket Mode : Standard
>>> Transparent mode : Yes (mode 0)
>>> Total rings : 1
>>> Total plugins : 0
>>>
>>> ethtool -i dna0
>>> -------------------------
>>> driver: ixgbe
>>> version: 3.6.7-DNA
>>> firmware-version: 0x00011bab
>>> bus-info: 0000:06:00.0
>>>
>>> ethtool dna0
>>> -----------------------
>>> Settings for dna0:
>>> Supported ports: [ FIBRE ]
>>> Supported link modes: 10000baseT/Full
>>> Supports auto-negotiation: No
>>> Advertised link modes: 10000baseT/Full
>>> Advertised auto-negotiation: No
>>> Speed: 10000Mb/s
>>> Duplex: Full
>>> Port: FIBRE
>>> PHYAD: 0
>>> Transceiver: external
>>> Auto-negotiation: off
>>> Supports Wake-on: d
>>> Wake-on: d
>>> Current message level: 0x00000007 (7)
>>> Link detected: yes
>>>
>>> Any thoughts about why it's not working?
>>>
>>> =s=
>>>
>>>
>>> On Mon, Nov 14, 2011 at 1:59 AM, Luca Deri <deri [at] ntop> wrote:
>>>> Hi all
>>>> you are using an old version of the code as now DNA interfaces are named
>>>> dnaX. Please fetch the latest code and drivers from SVN
>>>>
>>>> Luca
>>>>
>>>> On 11/10/2011 06:06 PM, Scott L wrote:
>>>>>
>>>>> Chris,
>>>>>
>>>>> Thanks for your response. I am running pfcount as root. I don't see
>>>>> the error for "pfcount -i eth2" only for "pfcount -i dna:eth2".
>>>>>
>>>>> In my configuration, I don't expect to receive much traffic. I am
>>>>> connecting two machines with 10 GbE NICs back-to-back. So the only
>>>>> traffic I expect to see (for now) are the pings that I am attempting
>>>>> to send; so the number of received packets is on the order of what I
>>>>> would expect.
>>>>>
>>>>> =s=
>>>>>
>>>>> On Wed, Nov 9, 2011 at 1:11 PM, Chris Collord<ccollord [at] hotmail>
>>>>> wrote:
>>>>>>
>>>>>> Hi Scott,
>>>>>> You'll see that error when you run pfcount without su permission (make
>>>>>> sure
>>>>>> you sudo or use root). Not sure if that's your problem or not, i'm still
>>>>>> figuring this out myself...
>>>>>> On the other hand it doesn't look like you're receiving much. Your RX
>>>>>> packets are 210, whereas mine after an hour is...
>>>>>> eth2 Link encap:Ethernet HWaddr 0xxxxxxxxx:4c
>>>>>> inet addr:0.0.0.1 Bcast:255.255.255.255 Mask:0.0.0.0
>>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>>> RX packets:172969631 errors:0 dropped:1 overruns:0 frame:0
>>>>>> TX packets:5 errors:0 dropped:0 overruns:0 carrier:0
>>>>>> collisions:0 txqueuelen:1000
>>>>>> RX bytes:116951083144 (116.9 GB) TX bytes:398 (398.0 B)
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>>> Date: Wed, 9 Nov 2011 12:05:55 -0700
>>>>>>> From: sallynbird [at] gmail
>>>>>>> To: ntop-misc [at] listgateway
>>>>>>> Subject: Re: [Ntop-misc] Problems with pfcount
>>>>>>>
>>>>>>> I've updated my PF_RING code and I'm not seeing any difference (i.e.,
>>>>>>> pfcount -i eth2 still shows 0 packets received but ifconfig shows
>>>>>>> packets being received). Here's what I'm seeing with the new version:
>>>>>>>
>>>>>>> ifconfig eth2
>>>>>>> -------------------
>>>>>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>>>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>>>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>>>> RX packets:210 errors:0 dropped:0 overruns:0 frame:0
>>>>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>> collisions:0 txqueuelen:1000
>>>>>>> RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
>>>>>>> Memory:fd7e0000-fd800000
>>>>>>>
>>>>>>> cat /proc/net/pfring/info
>>>>>>> -----------------------------------
>>>>>>> PF_RING Version : 5.1.0 ($Revision: 4972$)
>>>>>>> Ring slots : 4096
>>>>>>> Slot version : 13
>>>>>>> Capture TX : Yes [RX+TX]
>>>>>>> IP Defragment : No
>>>>>>> Socket Mode : Standard
>>>>>>> Transparent mode : Yes (mode 0)
>>>>>>> Total rings : 1
>>>>>>> Total plugins : 0
>>>>>>>
>>>>>>> cat /proc/net/pfring/<pid>-eth2.1
>>>>>>> ------------------------------------------------
>>>>>>> Bound Device : eth2
>>>>>>> Slot Version : 13 [5.1.0]
>>>>>>> Active : 1
>>>>>>> Breed : Non-DNA
>>>>>>> Sampling Rate : 1
>>>>>>> Capture Direction : RX+TX
>>>>>>> Appl. Name : pfcount
>>>>>>> IP Defragment : No
>>>>>>> BPF Filtering : Disabled
>>>>>>> # Sw Filt. Rules : 0
>>>>>>> # Hw Filt. Rules : 0
>>>>>>> Poll Pkt Watermark : 128
>>>>>>> Num Poll Calls : 1503
>>>>>>> Channel Id : -1
>>>>>>> Cluster Id : 0
>>>>>>> Min Num Slots : 6871
>>>>>>> Bucket Len : 128
>>>>>>> Slot Len : 304 [bucket+header]
>>>>>>> Tot Memory : 2097152
>>>>>>> Tot Packets : 0
>>>>>>> Tot Pkt Lost : 0
>>>>>>> Tot Insert : 0
>>>>>>> Tot Read : 0
>>>>>>> Insert Offset : 0
>>>>>>> Remove Offset : 0
>>>>>>> Tot Fwd Ok : 0
>>>>>>> Tot Fwd Errors : 0
>>>>>>> Num Free Slots : 6871
>>>>>>>
>>>>>>> ethtool -i eth2
>>>>>>> ----------------------
>>>>>>> driver: ixgbe
>>>>>>> version: 3.3.9-DNA
>>>>>>> firmware-version: 1.3-0
>>>>>>> bus-info: 0000:06:00.0
>>>>>>>
>>>>>>> ethtool eth2
>>>>>>> ----------------------
>>>>>>> Settings for eth2:
>>>>>>> Supported ports: [ FIBRE ]
>>>>>>> Supported link modes: 10000baseT/Full
>>>>>>> Supports auto-negotiation: No
>>>>>>> Advertised link modes: 10000baseT/Full
>>>>>>> Advertised auto-negotiation: No
>>>>>>> Speed: 10000Mb/s
>>>>>>> Duplex: Full
>>>>>>> Port: FIBRE
>>>>>>> PHYAD: 0
>>>>>>> Transceiver: external
>>>>>>> Auto-negotiation: off
>>>>>>> Supports Wake-on: d
>>>>>>> Wake-on: d
>>>>>>> Current message level: 0x00000007 (7)
>>>>>>> Link detected: yes
>>>>>>>
>>>>>>>
>>>>>>> I also tried pfcount -i dna:eth2, but got the following error:
>>>>>>>
>>>>>>> pfring_open error (pf_ring not loaded or perhaps you use quick mode
>>>>>>> and have already a socket bound to dna:eth2 ?)
>>>>>>>
>>>>>>> but:
>>>>>>>
>>>>>>> Module Size Used by
>>>>>>> pf_ring 335476 0
>>>>>>> ip6t_REJECT 5856 2
>>>>>>> nf_conntrack_ipv6 21880 2
>>>>>>> ip6table_filter 4016 1
>>>>>>> ip6_tables 19664 1 ip6table_filter
>>>>>>> ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
>>>>>>> dm_multipath 17304 0
>>>>>>> uinput 9248 0
>>>>>>> ixgbe 202760 0
>>>>>>> amd64_edac_mod 29632 0
>>>>>>> i2c_nforce2 9048 0
>>>>>>> dca 6708 1 ixgbe
>>>>>>> edac_core 43516 4 amd64_edac_mod
>>>>>>> forcedeth 54764 0
>>>>>>> mlx4_core 84128 0
>>>>>>> shpchp 34636 0
>>>>>>> serio_raw 6644 0
>>>>>>> pata_acpi 5152 0
>>>>>>> pata_amd 14260 0
>>>>>>> ata_generic 5924 0
>>>>>>> sata_nv 25228 2
>>>>>>> radeon 507616 1
>>>>>>> ttm 41952 1 radeon
>>>>>>> drm_kms_helper 25360 1 radeon
>>>>>>> drm 171168 3 radeon,ttm,drm_kms_helper
>>>>>>> i2c_algo_bit 6020 1 radeon
>>>>>>> i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit
>>>>>>>
>>>>>>> Any thoughts? Thanks for your help.
>>>>>>>
>>>>>>> =s=
>>>>>>>
>>>>>>> On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri<deri [at] ntop> wrote:
>>>>>>>>
>>>>>>>> Scott
>>>>>>>> please redo your tests using the code in PF_RING's SVN. From the
>>>>>>>> interface names (we now call them dnaX) i see that you are using old
>>>>>>>> stuff
>>>>>>>>
>>>>>>>> Luca
>>>>>>>>
>>>>>>>> On Oct 31, 2011, at 9:21 PM, Scott L wrote:
>>>>>>>>
>>>>>>>>> I'm having problems getting pfcount to work. I have two machines
>>>>>>>>> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
>>>>>>>>> NetEffect 10GbE NIC. I launch pfcount on A. Then on B I start
>>>>>>>>> pinging A. pfcount continually reports zero packets received.
>>>>>>>>>
>>>>>>>>> =========================
>>>>>>>>> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
>>>>>>>>> Total Pkts=0/Dropped=0.0 %
>>>>>>>>> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
>>>>>>>>> =========================
>>>>>>>>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>>>>>>>>> =========================
>>>>>>>>>
>>>>>>>>> The only relevant log messages I see are:
>>>>>>>>>
>>>>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Down
>>>>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
>>>>>>>>> device eth0 entered promiscuous mode
>>>>>>>>> device eth0 left promiscuous mode
>>>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=0)
>>>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=0)
>>>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=1)
>>>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=1)
>>>>>>>>>
>>>>>>>>> As I look around I don't see the problem. I can see the packets as
>>>>>>>>> they are transmitted on B. And the RX packet count for eth2 that is
>>>>>>>>> displayed by ifconfig increments appropriately on A. But pfcount
>>>>>>>>> doesn't see them. Anyone have any suggestions?
>>>>>>>>>
>>>>>>>>> ifconfig -i eth2
>>>>>>>>> -------------------
>>>>>>>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>>>>>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>>>>>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>>>>>> RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
>>>>>>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>>>> collisions:0 txqueuelen:1000
>>>>>>>>> RX bytes:1066541584248 (993.2 GiB) TX bytes:0 (0.0 b)
>>>>>>>>> Memory:fd7e0000-fd800000
>>>>>>>>>
>>>>>>>>> cat /proc/net/pfring/info
>>>>>>>>> --------------------------
>>>>>>>>> PF_RING Version : 5.0.0 ($Revision: exported$)
>>>>>>>>> Ring slots : 4096
>>>>>>>>> Slot version : 13
>>>>>>>>> Capture TX : Yes [RX+TX]
>>>>>>>>> IP Defragment : No
>>>>>>>>> Socket Mode : Standard
>>>>>>>>> Transparent mode : Yes (mode 0)
>>>>>>>>> Total rings : 1
>>>>>>>>> Total plugins : 0
>>>>>>>>>
>>>>>>>>> cat /proc/net/pfring/<pid>-eth2.30
>>>>>>>>> --------------------------------------------
>>>>>>>>> Bound Device : eth2
>>>>>>>>> Slot Version : 13 [5.0.0]
>>>>>>>>> Active : 1
>>>>>>>>> Breed : DNA
>>>>>>>>> Sampling Rate : 1
>>>>>>>>> Capture Direction : RX+TX
>>>>>>>>> Appl. Name : pfcount
>>>>>>>>> IP Defragment : No
>>>>>>>>> BPF Filtering : Disabled
>>>>>>>>> # Sw Filt. Rules : 0
>>>>>>>>> # Hw Filt. Rules : 0
>>>>>>>>> Poll Pkt Watermark : 128
>>>>>>>>> Num Poll Calls : 1461
>>>>>>>>> Channel Id : 0
>>>>>>>>> Num Slots : 8192
>>>>>>>>> Tot Memory : 33685504 bytes
>>>>>>>>>
>>>>>>>>> ethtool -i eth2
>>>>>>>>> -------------------
>>>>>>>>> driver: ixgbe
>>>>>>>>> version: 3.3.9-DNA
>>>>>>>>> firmware-version: 1.3-0
>>>>>>>>> bus-info: 0000:06:00.0
>>>>>>>>>
>>>>>>>>> ethtool eth2
>>>>>>>>> ----------------
>>>>>>>>> Settings for eth2:
>>>>>>>>> Supported ports: [ FIBRE ]
>>>>>>>>> Supported link modes: 10000baseT/Full
>>>>>>>>> Supports auto-negotiation: No
>>>>>>>>> Advertised link modes: 10000baseT/Full
>>>>>>>>> Advertised auto-negotiation: No
>>>>>>>>> Speed: 10000Mb/s
>>>>>>>>> Duplex: Full
>>>>>>>>> Port: FIBRE
>>>>>>>>> PHYAD: 0
>>>>>>>>> Transceiver: external
>>>>>>>>> Auto-negotiation: off
>>>>>>>>> Supports Wake-on: d
>>>>>>>>> Wake-on: d
>>>>>>>>> Current message level: 0x00000007 (7)
>>>>>>>>> Link detected: yes
>>>>>>>>> _______________________________________________
>>>>>>>>> Ntop-misc mailing list
>>>>>>>>> Ntop-misc [at] listgateway
>>>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>>
>>>>>>>> ---
>>>>>>>> We can't solve problems by using the same kind of thinking we used when
>>>>>>>> we created them - Albert Einstein
>>>>>>>>
>>>>>>>> _______________________________________________
>>>>>>>> Ntop-misc mailing list
>>>>>>>> Ntop-misc [at] listgateway
>>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>>
>>>>>>> _______________________________________________
>>>>>>> Ntop-misc mailing list
>>>>>>> Ntop-misc [at] listgateway
>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>
>>>>>> _______________________________________________
>>>>>> Ntop-misc mailing list
>>>>>> Ntop-misc [at] listgateway
>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>
>>>>>>
>>>>> _______________________________________________
>>>>> Ntop-misc mailing list
>>>>> Ntop-misc [at] listgateway
>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>
>>>> _______________________________________________
>>>> Ntop-misc mailing list
>>>> Ntop-misc [at] listgateway
>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>
>>> _______________________________________________
>>> Ntop-misc mailing list
>>> Ntop-misc [at] listgateway
>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc

_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Nov 21, 2011, 5:01 PM

Post #15 of 30 (1501 views)
Permalink
Re: Problems with pfcount [In reply to]

Alfredo,

One new observation... When pfcount stops recording packets, if I run
the load_dna_driver.sh script again and then run pfcount again it will
detect packets again for a little while before it "locks up" again.
At the very least, this seems like pretty good evidence that it's not
a TX problem.

I have two servers: (1) Server A has a Silicom 10GbE NIC
(82599-based); and (2) Server B has a NetEffect 10GbE NIC. I have a
simple program on Server B that generates UDP packets. This code has
been used in other applications and we've never seen this problem
before.

I performed two experiments to further convince myself that this isn't
a TX problem. First, when pfcount (on Server A) stopped counting
incoming packets, I rebooted Server A and left the packet generation
code running on Server B. When Server A finished booting, pfcount
briefly reported packets again. In the same circumstance, I rebooted
Server B and the problem persisted.

Second, these two servers are also connected through a separate
network and I can send use my program to send packets across that
interface indefinitely. Moreover, tcpdump on Server B shows that
packets are being sent to Server A after pfcount stops recording
packets.

There are probably explanations of these results that are consistent
with a TX issue, but it looks like an RX issue to me.

=s=

On Fri, Nov 18, 2011 at 1:26 PM, Alfredo Cardigliano
<cardigliano [at] ntop> wrote:
> Scott
> prior to further investigate on this strange issue, are you sure the problem is on the rx side? how are you generating the traffic?
> The card seems to be an X520 (82599), right?
>
> Regards
> Alfredo
>
> On Nov 18, 2011, at 8:18 PM, Scott L wrote:
>
>> Alfredo,
>>
>> I upgraded to 5.2.0 and saw some positive results.  I received packets
>> for a while and then they mysteriously stopped.  So far, the only way
>> that I've found to fix the problem is to reboot.  The pfcount output
>> looks something like this (the duration during which I receive packets
>> seems to vary from reboot to reboot).
>>
>> (at this point, I've just tested connectivity using pings)
>> =========================
>> Absolute Stats: [24 pkts rcvd][0 pkts dropped]
>> Total Pkts=24/Dropped=0.0 %
>> 24 pkts - 2'352 bytes [1.71 pkt/sec - 0.00 Mbit/sec]
>> =========================
>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>> =========================
>>
>> (in this interval, I start sending UDP packets as fast as I can from
>> the other machine)
>> =========================
>> Absolute Stats: [24713 pkts rcvd][12653 pkts dropped]
>> Total Pkts=37366/Dropped=33.9 %
>> 24'713 pkts - 36'492'694 bytes [1'647.42 pkt/sec - 19.46 Mbit/sec]
>> =========================
>> Actual Stats: 24689 pkts [1'000.05 ms][24'687.56 pkt/sec]
>> =========================
>>
>> =========================
>> Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
>> Total Pkts=176656/Dropped=7.2 %
>> 164'003 pkts - 242'363'314 bytes [10'249.49 pkt/sec - 121.17 Mbit/sec]
>> =========================
>> Actual Stats: 139290 pkts [1'000.05 ms][139'281.78 pkt/sec]
>> =========================
>>
>> (mysteriously, I stop receiving packets in this interval)
>> =========================
>> Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
>> Total Pkts=176656/Dropped=7.2 %
>> 164'003 pkts - 242'363'314 bytes [9'646.57 pkt/sec - 114.05 Mbit/sec]
>> =========================
>> Actual Stats: 0 pkts [1'000.07 ms][0.00 pkt/sec]
>> =========================
>>
>> =========================
>> Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
>> Total Pkts=176656/Dropped=7.2 %
>> 164'003 pkts - 242'363'314 bytes [9'110.65 pkt/sec - 107.71 Mbit/sec]
>> =========================
>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>> =========================
>>
>> lspci | grep 8259 returns nothing.
>>
>> The entry for my DNA NICs looks like:
>>
>> 06:00.0 Ethernet controller: Intel Corporation Device 10fb (rev 01)
>> 06:00.1 Ethernet controller: Intel Corporation Device 10fb (rev 01)
>>
>> ethtool -S dna0
>> ------------------------------
>> NIC statistics:
>>     rx_packets: 176992
>>     tx_packets: 0
>>     rx_bytes: 262269024
>>     tx_bytes: 0
>>     rx_errors: 0
>>     tx_errors: 0
>>     rx_dropped: 0
>>     tx_dropped: 0
>>     multicast: 0
>>     collisions: 0
>>     rx_over_errors: 0
>>     rx_crc_errors: 0
>>     rx_frame_errors: 0
>>     rx_fifo_errors: 0
>>     rx_missed_errors: 0
>>     tx_aborted_errors: 0
>>     tx_carrier_errors: 0
>>     tx_fifo_errors: 0
>>     tx_heartbeat_errors: 0
>>     rx_pkts_nic: 176992
>>     tx_pkts_nic: 0
>>     rx_bytes_nic: 262269024
>>     tx_bytes_nic: 0
>>     lsc_int: 2
>>     tx_busy: 0
>>     non_eop_descs: 0
>>     broadcast: 0
>>     rx_no_buffer_count: 0
>>     tx_timeout_count: 0
>>     tx_restart_queue: 0
>>     rx_long_length_errors: 0
>>     rx_short_length_errors: 0
>>     tx_flow_control_xon: 0
>>     rx_flow_control_xon: 0
>>     tx_flow_control_xoff: 127567
>>     rx_flow_control_xoff: 0
>>     rx_csum_offload_errors: 0
>>     alloc_rx_page_failed: 0
>>     alloc_rx_buff_failed: 0
>>     lro_aggregated: 0
>>     lro_flushed: 0
>>     lro_recycled: 0
>>     rx_no_dma_resources: 0
>>     hw_rsc_aggregated: 0
>>     hw_rsc_flushed: 0
>>     fdir_match: 0
>>     fdir_miss: 0
>>     fdir_overflow: 0
>>     fcoe_bad_fccrc: 0
>>     fcoe_last_errors: 0
>>     rx_fcoe_dropped: 0
>>     rx_fcoe_packets: 0
>>     rx_fcoe_dwords: 0
>>     tx_fcoe_packets: 0
>>     tx_fcoe_dwords: 0
>>     os2bmc_rx_by_bmc: 0
>>     os2bmc_tx_by_bmc: 0
>>     os2bmc_tx_by_host: 0
>>     os2bmc_rx_by_host: 0
>>     tx_queue_0_packets: 0
>>     tx_queue_0_bytes: 0
>>     rx_queue_0_packets: 0
>>     rx_queue_0_bytes: 0
>>
>>
>> Thanks,
>>
>> =s=
>>
>> On Fri, Nov 18, 2011 at 2:29 AM, Alfredo Cardigliano
>> <cardigliano [at] ntop> wrote:
>>> Scott
>>> Can you try with the latest stable release? (5.2.0)
>>> Can I see the "lspci | grep 8259" and "ethtool -S dna0" output?
>>>
>>> Alfredo
>>>
>>> On Nov 18, 2011, at 1:48 AM, Scott L wrote:
>>>
>>>> Ah.  I neglected to update the driver.  I'm now seeing dnaX
>>>> interfaces.  However, I'm still not receiving packets.
>>>>
>>>> ifconfig dna0
>>>> ------------------
>>>> dna0      Link encap:Ethernet  HWaddr 00:E0:ED:FF:18:08
>>>>          inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>          UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
>>>>          RX packets:0 errors:0 dropped:0 overruns:0 frame:0
>>>>          TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>          collisions:0 txqueuelen:1000
>>>>          RX bytes:0 (0.0 b)  TX bytes:0 (0.0 b)
>>>>          Memory:fd7e0000-fd800000
>>>>
>>>> cat /proc/net/pf_ring/<pid>-dna0.8
>>>> --------------------------------------------------
>>>> Bound Device       : dna0
>>>> Slot Version       : 13 [5.1.0]
>>>> Active             : 1
>>>> Breed              : DNA
>>>> Sampling Rate      : 1
>>>> Capture Direction  : RX+TX
>>>> Appl. Name         : pfcount
>>>> IP Defragment      : No
>>>> BPF Filtering      : Disabled
>>>> # Sw Filt. Rules   : 0
>>>> # Hw Filt. Rules   : 0
>>>> Poll Pkt Watermark : 128
>>>> Num Poll Calls     : 1119
>>>> Channel Id         : 0
>>>> Num RX Slots       : 8192
>>>> Num TX Slots       : 8192
>>>> Tot Memory         : 34078720 bytes
>>>>
>>>> cat /proc/net/pf_ring/info
>>>> ----------------------------------------
>>>> PF_RING Version     : 5.1.0 ($Revision: 4972$)
>>>> Ring slots          : 4096
>>>> Slot version        : 13
>>>> Capture TX          : Yes [RX+TX]
>>>> IP Defragment       : No
>>>> Socket Mode         : Standard
>>>> Transparent mode    : Yes (mode 0)
>>>> Total rings         : 1
>>>> Total plugins       : 0
>>>>
>>>> ethtool -i dna0
>>>> -------------------------
>>>> driver: ixgbe
>>>> version: 3.6.7-DNA
>>>> firmware-version: 0x00011bab
>>>> bus-info: 0000:06:00.0
>>>>
>>>> ethtool dna0
>>>> -----------------------
>>>> Settings for dna0:
>>>>       Supported ports: [ FIBRE ]
>>>>       Supported link modes:   10000baseT/Full
>>>>       Supports auto-negotiation: No
>>>>       Advertised link modes:  10000baseT/Full
>>>>       Advertised auto-negotiation: No
>>>>       Speed: 10000Mb/s
>>>>       Duplex: Full
>>>>       Port: FIBRE
>>>>       PHYAD: 0
>>>>       Transceiver: external
>>>>       Auto-negotiation: off
>>>>       Supports Wake-on: d
>>>>       Wake-on: d
>>>>       Current message level: 0x00000007 (7)
>>>>       Link detected: yes
>>>>
>>>> Any thoughts about why it's not working?
>>>>
>>>> =s=
>>>>
>>>>
>>>> On Mon, Nov 14, 2011 at 1:59 AM, Luca Deri <deri [at] ntop> wrote:
>>>>> Hi all
>>>>> you are using an old version of the code as now DNA interfaces are named
>>>>> dnaX. Please fetch the latest code and drivers from SVN
>>>>>
>>>>> Luca
>>>>>
>>>>> On 11/10/2011 06:06 PM, Scott L wrote:
>>>>>>
>>>>>> Chris,
>>>>>>
>>>>>> Thanks for your response.  I am running pfcount as root.  I don't see
>>>>>> the error for "pfcount -i eth2" only for "pfcount -i dna:eth2".
>>>>>>
>>>>>> In my configuration, I don't expect to receive much traffic.  I am
>>>>>> connecting two machines with 10 GbE NICs back-to-back.  So the only
>>>>>> traffic I expect to see (for now) are the pings that I am attempting
>>>>>> to send; so the number of received packets is on the order of what I
>>>>>> would expect.
>>>>>>
>>>>>> =s=
>>>>>>
>>>>>> On Wed, Nov 9, 2011 at 1:11 PM, Chris Collord<ccollord [at] hotmail>
>>>>>>  wrote:
>>>>>>>
>>>>>>> Hi Scott,
>>>>>>> You'll see that error when you run pfcount without su permission (make
>>>>>>> sure
>>>>>>> you sudo or use root).  Not sure if that's your problem or not, i'm still
>>>>>>> figuring this out myself...
>>>>>>> On the other hand it doesn't look like you're receiving much.  Your RX
>>>>>>> packets are 210, whereas mine after an hour is...
>>>>>>> eth2      Link encap:Ethernet  HWaddr 0xxxxxxxxx:4c
>>>>>>>           inet addr:0.0.0.1  Bcast:255.255.255.255  Mask:0.0.0.0
>>>>>>>            UP BROADCAST RUNNING PROMISC MULTICAST  MTU:1500  Metric:1
>>>>>>>           RX packets:172969631 errors:0 dropped:1 overruns:0 frame:0
>>>>>>>           TX packets:5 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>>           collisions:0 txqueuelen:1000
>>>>>>>           RX bytes:116951083144 (116.9 GB)  TX bytes:398 (398.0 B)
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>> Date: Wed, 9 Nov 2011 12:05:55 -0700
>>>>>>>> From: sallynbird [at] gmail
>>>>>>>> To: ntop-misc [at] listgateway
>>>>>>>> Subject: Re: [Ntop-misc] Problems with pfcount
>>>>>>>>
>>>>>>>> I've updated my PF_RING code and I'm not seeing any difference (i.e.,
>>>>>>>> pfcount -i eth2 still shows 0 packets received but ifconfig shows
>>>>>>>> packets being received). Here's what I'm seeing with the new version:
>>>>>>>>
>>>>>>>> ifconfig eth2
>>>>>>>> -------------------
>>>>>>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>>>>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>>>>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>>>>> RX packets:210 errors:0 dropped:0 overruns:0 frame:0
>>>>>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>>> collisions:0 txqueuelen:1000
>>>>>>>> RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
>>>>>>>> Memory:fd7e0000-fd800000
>>>>>>>>
>>>>>>>> cat /proc/net/pfring/info
>>>>>>>> -----------------------------------
>>>>>>>> PF_RING Version : 5.1.0 ($Revision: 4972$)
>>>>>>>> Ring slots : 4096
>>>>>>>> Slot version : 13
>>>>>>>> Capture TX : Yes [RX+TX]
>>>>>>>> IP Defragment : No
>>>>>>>> Socket Mode : Standard
>>>>>>>> Transparent mode : Yes (mode 0)
>>>>>>>> Total rings : 1
>>>>>>>> Total plugins : 0
>>>>>>>>
>>>>>>>> cat /proc/net/pfring/<pid>-eth2.1
>>>>>>>> ------------------------------------------------
>>>>>>>> Bound Device : eth2
>>>>>>>> Slot Version : 13 [5.1.0]
>>>>>>>> Active : 1
>>>>>>>> Breed : Non-DNA
>>>>>>>> Sampling Rate : 1
>>>>>>>> Capture Direction : RX+TX
>>>>>>>> Appl. Name : pfcount
>>>>>>>> IP Defragment : No
>>>>>>>> BPF Filtering : Disabled
>>>>>>>> # Sw Filt. Rules : 0
>>>>>>>> # Hw Filt. Rules : 0
>>>>>>>> Poll Pkt Watermark : 128
>>>>>>>> Num Poll Calls : 1503
>>>>>>>> Channel Id : -1
>>>>>>>> Cluster Id : 0
>>>>>>>> Min Num Slots : 6871
>>>>>>>> Bucket Len : 128
>>>>>>>> Slot Len : 304 [bucket+header]
>>>>>>>> Tot Memory : 2097152
>>>>>>>> Tot Packets : 0
>>>>>>>> Tot Pkt Lost : 0
>>>>>>>> Tot Insert : 0
>>>>>>>> Tot Read : 0
>>>>>>>> Insert Offset : 0
>>>>>>>> Remove Offset : 0
>>>>>>>> Tot Fwd Ok : 0
>>>>>>>> Tot Fwd Errors : 0
>>>>>>>> Num Free Slots : 6871
>>>>>>>>
>>>>>>>> ethtool -i eth2
>>>>>>>> ----------------------
>>>>>>>> driver: ixgbe
>>>>>>>> version: 3.3.9-DNA
>>>>>>>> firmware-version: 1.3-0
>>>>>>>> bus-info: 0000:06:00.0
>>>>>>>>
>>>>>>>> ethtool eth2
>>>>>>>> ----------------------
>>>>>>>> Settings for eth2:
>>>>>>>> Supported ports: [ FIBRE ]
>>>>>>>> Supported link modes: 10000baseT/Full
>>>>>>>> Supports auto-negotiation: No
>>>>>>>> Advertised link modes: 10000baseT/Full
>>>>>>>> Advertised auto-negotiation: No
>>>>>>>> Speed: 10000Mb/s
>>>>>>>> Duplex: Full
>>>>>>>> Port: FIBRE
>>>>>>>> PHYAD: 0
>>>>>>>> Transceiver: external
>>>>>>>> Auto-negotiation: off
>>>>>>>> Supports Wake-on: d
>>>>>>>> Wake-on: d
>>>>>>>> Current message level: 0x00000007 (7)
>>>>>>>> Link detected: yes
>>>>>>>>
>>>>>>>>
>>>>>>>> I also tried pfcount -i dna:eth2, but got the following error:
>>>>>>>>
>>>>>>>> pfring_open error (pf_ring not loaded or perhaps you use quick mode
>>>>>>>> and have already a socket bound to dna:eth2 ?)
>>>>>>>>
>>>>>>>> but:
>>>>>>>>
>>>>>>>> Module Size Used by
>>>>>>>> pf_ring 335476 0
>>>>>>>> ip6t_REJECT 5856 2
>>>>>>>> nf_conntrack_ipv6 21880 2
>>>>>>>> ip6table_filter 4016 1
>>>>>>>> ip6_tables 19664 1 ip6table_filter
>>>>>>>> ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
>>>>>>>> dm_multipath 17304 0
>>>>>>>> uinput 9248 0
>>>>>>>> ixgbe 202760 0
>>>>>>>> amd64_edac_mod 29632 0
>>>>>>>> i2c_nforce2 9048 0
>>>>>>>> dca 6708 1 ixgbe
>>>>>>>> edac_core 43516 4 amd64_edac_mod
>>>>>>>> forcedeth 54764 0
>>>>>>>> mlx4_core 84128 0
>>>>>>>> shpchp 34636 0
>>>>>>>> serio_raw 6644 0
>>>>>>>> pata_acpi 5152 0
>>>>>>>> pata_amd 14260 0
>>>>>>>> ata_generic 5924 0
>>>>>>>> sata_nv 25228 2
>>>>>>>> radeon 507616 1
>>>>>>>> ttm 41952 1 radeon
>>>>>>>> drm_kms_helper 25360 1 radeon
>>>>>>>> drm 171168 3 radeon,ttm,drm_kms_helper
>>>>>>>> i2c_algo_bit 6020 1 radeon
>>>>>>>> i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit
>>>>>>>>
>>>>>>>> Any thoughts? Thanks for your help.
>>>>>>>>
>>>>>>>> =s=
>>>>>>>>
>>>>>>>> On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri<deri [at] ntop>  wrote:
>>>>>>>>>
>>>>>>>>> Scott
>>>>>>>>> please redo your tests using the code in PF_RING's SVN. From the
>>>>>>>>> interface names (we now call them dnaX) i see that you are using old
>>>>>>>>> stuff
>>>>>>>>>
>>>>>>>>> Luca
>>>>>>>>>
>>>>>>>>> On Oct 31, 2011, at 9:21 PM, Scott L wrote:
>>>>>>>>>
>>>>>>>>>> I'm having problems getting pfcount to work.  I have two machines
>>>>>>>>>> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
>>>>>>>>>> NetEffect 10GbE NIC.  I launch pfcount on A.  Then on B I start
>>>>>>>>>> pinging A.  pfcount continually reports zero packets received.
>>>>>>>>>>
>>>>>>>>>> =========================
>>>>>>>>>> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
>>>>>>>>>> Total Pkts=0/Dropped=0.0 %
>>>>>>>>>> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
>>>>>>>>>> =========================
>>>>>>>>>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>>>>>>>>>> =========================
>>>>>>>>>>
>>>>>>>>>> The only relevant log messages I see are:
>>>>>>>>>>
>>>>>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Down
>>>>>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
>>>>>>>>>> device eth0 entered promiscuous mode
>>>>>>>>>> device eth0 left promiscuous mode
>>>>>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=0)
>>>>>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=0)
>>>>>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=1)
>>>>>>>>>> [PF_RING] -->  handle_hw_filtering_rule(command=1)
>>>>>>>>>>
>>>>>>>>>> As I look around I don't see the problem.  I can see the packets as
>>>>>>>>>> they are transmitted on B.   And the RX packet count for eth2 that is
>>>>>>>>>> displayed by ifconfig increments appropriately on A.  But pfcount
>>>>>>>>>> doesn't see them.  Anyone have any suggestions?
>>>>>>>>>>
>>>>>>>>>> ifconfig -i eth2
>>>>>>>>>> -------------------
>>>>>>>>>> eth2      Link encap:Ethernet  HWaddr 00:E0:ED:FF:18:08
>>>>>>>>>>          inet addr:10.0.2.45  Bcast:10.0.2.255  Mask:255.255.255.0
>>>>>>>>>>          inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>>>>>>>          UP BROADCAST RUNNING PROMISC MULTICAST  MTU:1500  Metric:1
>>>>>>>>>>          RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
>>>>>>>>>>          TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>>>>>          collisions:0 txqueuelen:1000
>>>>>>>>>>          RX bytes:1066541584248 (993.2 GiB)  TX bytes:0 (0.0 b)
>>>>>>>>>>          Memory:fd7e0000-fd800000
>>>>>>>>>>
>>>>>>>>>> cat /proc/net/pfring/info
>>>>>>>>>> --------------------------
>>>>>>>>>> PF_RING Version     : 5.0.0 ($Revision: exported$)
>>>>>>>>>> Ring slots          : 4096
>>>>>>>>>> Slot version        : 13
>>>>>>>>>> Capture TX          : Yes [RX+TX]
>>>>>>>>>> IP Defragment       : No
>>>>>>>>>> Socket Mode         : Standard
>>>>>>>>>> Transparent mode    : Yes (mode 0)
>>>>>>>>>> Total rings         : 1
>>>>>>>>>> Total plugins       : 0
>>>>>>>>>>
>>>>>>>>>> cat /proc/net/pfring/<pid>-eth2.30
>>>>>>>>>> --------------------------------------------
>>>>>>>>>> Bound Device       : eth2
>>>>>>>>>> Slot Version       : 13 [5.0.0]
>>>>>>>>>> Active             : 1
>>>>>>>>>> Breed              : DNA
>>>>>>>>>> Sampling Rate      : 1
>>>>>>>>>> Capture Direction  : RX+TX
>>>>>>>>>> Appl. Name         : pfcount
>>>>>>>>>> IP Defragment      : No
>>>>>>>>>> BPF Filtering      : Disabled
>>>>>>>>>> # Sw Filt. Rules   : 0
>>>>>>>>>> # Hw Filt. Rules   : 0
>>>>>>>>>> Poll Pkt Watermark : 128
>>>>>>>>>> Num Poll Calls     : 1461
>>>>>>>>>> Channel Id         : 0
>>>>>>>>>> Num Slots          : 8192
>>>>>>>>>> Tot Memory         : 33685504 bytes
>>>>>>>>>>
>>>>>>>>>> ethtool -i eth2
>>>>>>>>>> -------------------
>>>>>>>>>> driver: ixgbe
>>>>>>>>>> version: 3.3.9-DNA
>>>>>>>>>> firmware-version: 1.3-0
>>>>>>>>>> bus-info: 0000:06:00.0
>>>>>>>>>>
>>>>>>>>>> ethtool eth2
>>>>>>>>>> ----------------
>>>>>>>>>> Settings for eth2:
>>>>>>>>>>       Supported ports: [ FIBRE ]
>>>>>>>>>>       Supported link modes:   10000baseT/Full
>>>>>>>>>>       Supports auto-negotiation: No
>>>>>>>>>>       Advertised link modes:  10000baseT/Full
>>>>>>>>>>       Advertised auto-negotiation: No
>>>>>>>>>>       Speed: 10000Mb/s
>>>>>>>>>>       Duplex: Full
>>>>>>>>>>       Port: FIBRE
>>>>>>>>>>       PHYAD: 0
>>>>>>>>>>       Transceiver: external
>>>>>>>>>>       Auto-negotiation: off
>>>>>>>>>>       Supports Wake-on: d
>>>>>>>>>>       Wake-on: d
>>>>>>>>>>       Current message level: 0x00000007 (7)
>>>>>>>>>>       Link detected: yes
>>>>>>>>>> _______________________________________________
>>>>>>>>>> Ntop-misc mailing list
>>>>>>>>>> Ntop-misc [at] listgateway
>>>>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>>>
>>>>>>>>> ---
>>>>>>>>> We can't solve problems by using the same kind of thinking we used when
>>>>>>>>> we created them - Albert Einstein
>>>>>>>>>
>>>>>>>>> _______________________________________________
>>>>>>>>> Ntop-misc mailing list
>>>>>>>>> Ntop-misc [at] listgateway
>>>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>>>
>>>>>>>> _______________________________________________
>>>>>>>> Ntop-misc mailing list
>>>>>>>> Ntop-misc [at] listgateway
>>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>
>>>>>>> _______________________________________________
>>>>>>> Ntop-misc mailing list
>>>>>>> Ntop-misc [at] listgateway
>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>
>>>>>>>
>>>>>> _______________________________________________
>>>>>> Ntop-misc mailing list
>>>>>> Ntop-misc [at] listgateway
>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>
>>>>> _______________________________________________
>>>>> Ntop-misc mailing list
>>>>> Ntop-misc [at] listgateway
>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>
>>>> _______________________________________________
>>>> Ntop-misc mailing list
>>>> Ntop-misc [at] listgateway
>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>
>>> _______________________________________________
>>> Ntop-misc mailing list
>>> Ntop-misc [at] listgateway
>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


cardigliano at ntop

Nov 22, 2011, 1:24 AM

Post #16 of 30 (1501 views)
Permalink
Re: Problems with pfcount [In reply to]

Scott
I agree with you, it looks like an rx problem.
Please make sure that everything is in sync (recompile all the PF_RING package from svn: drivers,
kernel module, library, applications), and if the problem is still there we may need to debug it on
your server (if possible), since it is not reproducible on our.

Regards
Alfredo

On Nov 22, 2011, at 2:01 AM, Scott L wrote:

> Alfredo,
>
> One new observation... When pfcount stops recording packets, if I run
> the load_dna_driver.sh script again and then run pfcount again it will
> detect packets again for a little while before it "locks up" again.
> At the very least, this seems like pretty good evidence that it's not
> a TX problem.
>
> I have two servers: (1) Server A has a Silicom 10GbE NIC
> (82599-based); and (2) Server B has a NetEffect 10GbE NIC. I have a
> simple program on Server B that generates UDP packets. This code has
> been used in other applications and we've never seen this problem
> before.
>
> I performed two experiments to further convince myself that this isn't
> a TX problem. First, when pfcount (on Server A) stopped counting
> incoming packets, I rebooted Server A and left the packet generation
> code running on Server B. When Server A finished booting, pfcount
> briefly reported packets again. In the same circumstance, I rebooted
> Server B and the problem persisted.
>
> Second, these two servers are also connected through a separate
> network and I can send use my program to send packets across that
> interface indefinitely. Moreover, tcpdump on Server B shows that
> packets are being sent to Server A after pfcount stops recording
> packets.
>
> There are probably explanations of these results that are consistent
> with a TX issue, but it looks like an RX issue to me.
>
> =s=
>
> On Fri, Nov 18, 2011 at 1:26 PM, Alfredo Cardigliano
> <cardigliano [at] ntop> wrote:
>> Scott
>> prior to further investigate on this strange issue, are you sure the problem is on the rx side? how are you generating the traffic?
>> The card seems to be an X520 (82599), right?
>>
>> Regards
>> Alfredo
>>
>> On Nov 18, 2011, at 8:18 PM, Scott L wrote:
>>
>>> Alfredo,
>>>
>>> I upgraded to 5.2.0 and saw some positive results. I received packets
>>> for a while and then they mysteriously stopped. So far, the only way
>>> that I've found to fix the problem is to reboot. The pfcount output
>>> looks something like this (the duration during which I receive packets
>>> seems to vary from reboot to reboot).
>>>
>>> (at this point, I've just tested connectivity using pings)
>>> =========================
>>> Absolute Stats: [24 pkts rcvd][0 pkts dropped]
>>> Total Pkts=24/Dropped=0.0 %
>>> 24 pkts - 2'352 bytes [1.71 pkt/sec - 0.00 Mbit/sec]
>>> =========================
>>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>>> =========================
>>>
>>> (in this interval, I start sending UDP packets as fast as I can from
>>> the other machine)
>>> =========================
>>> Absolute Stats: [24713 pkts rcvd][12653 pkts dropped]
>>> Total Pkts=37366/Dropped=33.9 %
>>> 24'713 pkts - 36'492'694 bytes [1'647.42 pkt/sec - 19.46 Mbit/sec]
>>> =========================
>>> Actual Stats: 24689 pkts [1'000.05 ms][24'687.56 pkt/sec]
>>> =========================
>>>
>>> =========================
>>> Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
>>> Total Pkts=176656/Dropped=7.2 %
>>> 164'003 pkts - 242'363'314 bytes [10'249.49 pkt/sec - 121.17 Mbit/sec]
>>> =========================
>>> Actual Stats: 139290 pkts [1'000.05 ms][139'281.78 pkt/sec]
>>> =========================
>>>
>>> (mysteriously, I stop receiving packets in this interval)
>>> =========================
>>> Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
>>> Total Pkts=176656/Dropped=7.2 %
>>> 164'003 pkts - 242'363'314 bytes [9'646.57 pkt/sec - 114.05 Mbit/sec]
>>> =========================
>>> Actual Stats: 0 pkts [1'000.07 ms][0.00 pkt/sec]
>>> =========================
>>>
>>> =========================
>>> Absolute Stats: [164003 pkts rcvd][12653 pkts dropped]
>>> Total Pkts=176656/Dropped=7.2 %
>>> 164'003 pkts - 242'363'314 bytes [9'110.65 pkt/sec - 107.71 Mbit/sec]
>>> =========================
>>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>>> =========================
>>>
>>> lspci | grep 8259 returns nothing.
>>>
>>> The entry for my DNA NICs looks like:
>>>
>>> 06:00.0 Ethernet controller: Intel Corporation Device 10fb (rev 01)
>>> 06:00.1 Ethernet controller: Intel Corporation Device 10fb (rev 01)
>>>
>>> ethtool -S dna0
>>> ------------------------------
>>> NIC statistics:
>>> rx_packets: 176992
>>> tx_packets: 0
>>> rx_bytes: 262269024
>>> tx_bytes: 0
>>> rx_errors: 0
>>> tx_errors: 0
>>> rx_dropped: 0
>>> tx_dropped: 0
>>> multicast: 0
>>> collisions: 0
>>> rx_over_errors: 0
>>> rx_crc_errors: 0
>>> rx_frame_errors: 0
>>> rx_fifo_errors: 0
>>> rx_missed_errors: 0
>>> tx_aborted_errors: 0
>>> tx_carrier_errors: 0
>>> tx_fifo_errors: 0
>>> tx_heartbeat_errors: 0
>>> rx_pkts_nic: 176992
>>> tx_pkts_nic: 0
>>> rx_bytes_nic: 262269024
>>> tx_bytes_nic: 0
>>> lsc_int: 2
>>> tx_busy: 0
>>> non_eop_descs: 0
>>> broadcast: 0
>>> rx_no_buffer_count: 0
>>> tx_timeout_count: 0
>>> tx_restart_queue: 0
>>> rx_long_length_errors: 0
>>> rx_short_length_errors: 0
>>> tx_flow_control_xon: 0
>>> rx_flow_control_xon: 0
>>> tx_flow_control_xoff: 127567
>>> rx_flow_control_xoff: 0
>>> rx_csum_offload_errors: 0
>>> alloc_rx_page_failed: 0
>>> alloc_rx_buff_failed: 0
>>> lro_aggregated: 0
>>> lro_flushed: 0
>>> lro_recycled: 0
>>> rx_no_dma_resources: 0
>>> hw_rsc_aggregated: 0
>>> hw_rsc_flushed: 0
>>> fdir_match: 0
>>> fdir_miss: 0
>>> fdir_overflow: 0
>>> fcoe_bad_fccrc: 0
>>> fcoe_last_errors: 0
>>> rx_fcoe_dropped: 0
>>> rx_fcoe_packets: 0
>>> rx_fcoe_dwords: 0
>>> tx_fcoe_packets: 0
>>> tx_fcoe_dwords: 0
>>> os2bmc_rx_by_bmc: 0
>>> os2bmc_tx_by_bmc: 0
>>> os2bmc_tx_by_host: 0
>>> os2bmc_rx_by_host: 0
>>> tx_queue_0_packets: 0
>>> tx_queue_0_bytes: 0
>>> rx_queue_0_packets: 0
>>> rx_queue_0_bytes: 0
>>>
>>>
>>> Thanks,
>>>
>>> =s=
>>>
>>> On Fri, Nov 18, 2011 at 2:29 AM, Alfredo Cardigliano
>>> <cardigliano [at] ntop> wrote:
>>>> Scott
>>>> Can you try with the latest stable release? (5.2.0)
>>>> Can I see the "lspci | grep 8259" and "ethtool -S dna0" output?
>>>>
>>>> Alfredo
>>>>
>>>> On Nov 18, 2011, at 1:48 AM, Scott L wrote:
>>>>
>>>>> Ah. I neglected to update the driver. I'm now seeing dnaX
>>>>> interfaces. However, I'm still not receiving packets.
>>>>>
>>>>> ifconfig dna0
>>>>> ------------------
>>>>> dna0 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>> UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
>>>>> RX packets:0 errors:0 dropped:0 overruns:0 frame:0
>>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>> collisions:0 txqueuelen:1000
>>>>> RX bytes:0 (0.0 b) TX bytes:0 (0.0 b)
>>>>> Memory:fd7e0000-fd800000
>>>>>
>>>>> cat /proc/net/pf_ring/<pid>-dna0.8
>>>>> --------------------------------------------------
>>>>> Bound Device : dna0
>>>>> Slot Version : 13 [5.1.0]
>>>>> Active : 1
>>>>> Breed : DNA
>>>>> Sampling Rate : 1
>>>>> Capture Direction : RX+TX
>>>>> Appl. Name : pfcount
>>>>> IP Defragment : No
>>>>> BPF Filtering : Disabled
>>>>> # Sw Filt. Rules : 0
>>>>> # Hw Filt. Rules : 0
>>>>> Poll Pkt Watermark : 128
>>>>> Num Poll Calls : 1119
>>>>> Channel Id : 0
>>>>> Num RX Slots : 8192
>>>>> Num TX Slots : 8192
>>>>> Tot Memory : 34078720 bytes
>>>>>
>>>>> cat /proc/net/pf_ring/info
>>>>> ----------------------------------------
>>>>> PF_RING Version : 5.1.0 ($Revision: 4972$)
>>>>> Ring slots : 4096
>>>>> Slot version : 13
>>>>> Capture TX : Yes [RX+TX]
>>>>> IP Defragment : No
>>>>> Socket Mode : Standard
>>>>> Transparent mode : Yes (mode 0)
>>>>> Total rings : 1
>>>>> Total plugins : 0
>>>>>
>>>>> ethtool -i dna0
>>>>> -------------------------
>>>>> driver: ixgbe
>>>>> version: 3.6.7-DNA
>>>>> firmware-version: 0x00011bab
>>>>> bus-info: 0000:06:00.0
>>>>>
>>>>> ethtool dna0
>>>>> -----------------------
>>>>> Settings for dna0:
>>>>> Supported ports: [ FIBRE ]
>>>>> Supported link modes: 10000baseT/Full
>>>>> Supports auto-negotiation: No
>>>>> Advertised link modes: 10000baseT/Full
>>>>> Advertised auto-negotiation: No
>>>>> Speed: 10000Mb/s
>>>>> Duplex: Full
>>>>> Port: FIBRE
>>>>> PHYAD: 0
>>>>> Transceiver: external
>>>>> Auto-negotiation: off
>>>>> Supports Wake-on: d
>>>>> Wake-on: d
>>>>> Current message level: 0x00000007 (7)
>>>>> Link detected: yes
>>>>>
>>>>> Any thoughts about why it's not working?
>>>>>
>>>>> =s=
>>>>>
>>>>>
>>>>> On Mon, Nov 14, 2011 at 1:59 AM, Luca Deri <deri [at] ntop> wrote:
>>>>>> Hi all
>>>>>> you are using an old version of the code as now DNA interfaces are named
>>>>>> dnaX. Please fetch the latest code and drivers from SVN
>>>>>>
>>>>>> Luca
>>>>>>
>>>>>> On 11/10/2011 06:06 PM, Scott L wrote:
>>>>>>>
>>>>>>> Chris,
>>>>>>>
>>>>>>> Thanks for your response. I am running pfcount as root. I don't see
>>>>>>> the error for "pfcount -i eth2" only for "pfcount -i dna:eth2".
>>>>>>>
>>>>>>> In my configuration, I don't expect to receive much traffic. I am
>>>>>>> connecting two machines with 10 GbE NICs back-to-back. So the only
>>>>>>> traffic I expect to see (for now) are the pings that I am attempting
>>>>>>> to send; so the number of received packets is on the order of what I
>>>>>>> would expect.
>>>>>>>
>>>>>>> =s=
>>>>>>>
>>>>>>> On Wed, Nov 9, 2011 at 1:11 PM, Chris Collord<ccollord [at] hotmail>
>>>>>>> wrote:
>>>>>>>>
>>>>>>>> Hi Scott,
>>>>>>>> You'll see that error when you run pfcount without su permission (make
>>>>>>>> sure
>>>>>>>> you sudo or use root). Not sure if that's your problem or not, i'm still
>>>>>>>> figuring this out myself...
>>>>>>>> On the other hand it doesn't look like you're receiving much. Your RX
>>>>>>>> packets are 210, whereas mine after an hour is...
>>>>>>>> eth2 Link encap:Ethernet HWaddr 0xxxxxxxxx:4c
>>>>>>>> inet addr:0.0.0.1 Bcast:255.255.255.255 Mask:0.0.0.0
>>>>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>>>>> RX packets:172969631 errors:0 dropped:1 overruns:0 frame:0
>>>>>>>> TX packets:5 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>>> collisions:0 txqueuelen:1000
>>>>>>>> RX bytes:116951083144 (116.9 GB) TX bytes:398 (398.0 B)
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>>> Date: Wed, 9 Nov 2011 12:05:55 -0700
>>>>>>>>> From: sallynbird [at] gmail
>>>>>>>>> To: ntop-misc [at] listgateway
>>>>>>>>> Subject: Re: [Ntop-misc] Problems with pfcount
>>>>>>>>>
>>>>>>>>> I've updated my PF_RING code and I'm not seeing any difference (i.e.,
>>>>>>>>> pfcount -i eth2 still shows 0 packets received but ifconfig shows
>>>>>>>>> packets being received). Here's what I'm seeing with the new version:
>>>>>>>>>
>>>>>>>>> ifconfig eth2
>>>>>>>>> -------------------
>>>>>>>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>>>>>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>>>>>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>>>>>> RX packets:210 errors:0 dropped:0 overruns:0 frame:0
>>>>>>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>>>> collisions:0 txqueuelen:1000
>>>>>>>>> RX bytes:21420 (20.9 KiB) TX bytes:0 (0.0 b)
>>>>>>>>> Memory:fd7e0000-fd800000
>>>>>>>>>
>>>>>>>>> cat /proc/net/pfring/info
>>>>>>>>> -----------------------------------
>>>>>>>>> PF_RING Version : 5.1.0 ($Revision: 4972$)
>>>>>>>>> Ring slots : 4096
>>>>>>>>> Slot version : 13
>>>>>>>>> Capture TX : Yes [RX+TX]
>>>>>>>>> IP Defragment : No
>>>>>>>>> Socket Mode : Standard
>>>>>>>>> Transparent mode : Yes (mode 0)
>>>>>>>>> Total rings : 1
>>>>>>>>> Total plugins : 0
>>>>>>>>>
>>>>>>>>> cat /proc/net/pfring/<pid>-eth2.1
>>>>>>>>> ------------------------------------------------
>>>>>>>>> Bound Device : eth2
>>>>>>>>> Slot Version : 13 [5.1.0]
>>>>>>>>> Active : 1
>>>>>>>>> Breed : Non-DNA
>>>>>>>>> Sampling Rate : 1
>>>>>>>>> Capture Direction : RX+TX
>>>>>>>>> Appl. Name : pfcount
>>>>>>>>> IP Defragment : No
>>>>>>>>> BPF Filtering : Disabled
>>>>>>>>> # Sw Filt. Rules : 0
>>>>>>>>> # Hw Filt. Rules : 0
>>>>>>>>> Poll Pkt Watermark : 128
>>>>>>>>> Num Poll Calls : 1503
>>>>>>>>> Channel Id : -1
>>>>>>>>> Cluster Id : 0
>>>>>>>>> Min Num Slots : 6871
>>>>>>>>> Bucket Len : 128
>>>>>>>>> Slot Len : 304 [bucket+header]
>>>>>>>>> Tot Memory : 2097152
>>>>>>>>> Tot Packets : 0
>>>>>>>>> Tot Pkt Lost : 0
>>>>>>>>> Tot Insert : 0
>>>>>>>>> Tot Read : 0
>>>>>>>>> Insert Offset : 0
>>>>>>>>> Remove Offset : 0
>>>>>>>>> Tot Fwd Ok : 0
>>>>>>>>> Tot Fwd Errors : 0
>>>>>>>>> Num Free Slots : 6871
>>>>>>>>>
>>>>>>>>> ethtool -i eth2
>>>>>>>>> ----------------------
>>>>>>>>> driver: ixgbe
>>>>>>>>> version: 3.3.9-DNA
>>>>>>>>> firmware-version: 1.3-0
>>>>>>>>> bus-info: 0000:06:00.0
>>>>>>>>>
>>>>>>>>> ethtool eth2
>>>>>>>>> ----------------------
>>>>>>>>> Settings for eth2:
>>>>>>>>> Supported ports: [ FIBRE ]
>>>>>>>>> Supported link modes: 10000baseT/Full
>>>>>>>>> Supports auto-negotiation: No
>>>>>>>>> Advertised link modes: 10000baseT/Full
>>>>>>>>> Advertised auto-negotiation: No
>>>>>>>>> Speed: 10000Mb/s
>>>>>>>>> Duplex: Full
>>>>>>>>> Port: FIBRE
>>>>>>>>> PHYAD: 0
>>>>>>>>> Transceiver: external
>>>>>>>>> Auto-negotiation: off
>>>>>>>>> Supports Wake-on: d
>>>>>>>>> Wake-on: d
>>>>>>>>> Current message level: 0x00000007 (7)
>>>>>>>>> Link detected: yes
>>>>>>>>>
>>>>>>>>>
>>>>>>>>> I also tried pfcount -i dna:eth2, but got the following error:
>>>>>>>>>
>>>>>>>>> pfring_open error (pf_ring not loaded or perhaps you use quick mode
>>>>>>>>> and have already a socket bound to dna:eth2 ?)
>>>>>>>>>
>>>>>>>>> but:
>>>>>>>>>
>>>>>>>>> Module Size Used by
>>>>>>>>> pf_ring 335476 0
>>>>>>>>> ip6t_REJECT 5856 2
>>>>>>>>> nf_conntrack_ipv6 21880 2
>>>>>>>>> ip6table_filter 4016 1
>>>>>>>>> ip6_tables 19664 1 ip6table_filter
>>>>>>>>> ipv6 298864 28 ip6t_REJECT,nf_conntrack_ipv6
>>>>>>>>> dm_multipath 17304 0
>>>>>>>>> uinput 9248 0
>>>>>>>>> ixgbe 202760 0
>>>>>>>>> amd64_edac_mod 29632 0
>>>>>>>>> i2c_nforce2 9048 0
>>>>>>>>> dca 6708 1 ixgbe
>>>>>>>>> edac_core 43516 4 amd64_edac_mod
>>>>>>>>> forcedeth 54764 0
>>>>>>>>> mlx4_core 84128 0
>>>>>>>>> shpchp 34636 0
>>>>>>>>> serio_raw 6644 0
>>>>>>>>> pata_acpi 5152 0
>>>>>>>>> pata_amd 14260 0
>>>>>>>>> ata_generic 5924 0
>>>>>>>>> sata_nv 25228 2
>>>>>>>>> radeon 507616 1
>>>>>>>>> ttm 41952 1 radeon
>>>>>>>>> drm_kms_helper 25360 1 radeon
>>>>>>>>> drm 171168 3 radeon,ttm,drm_kms_helper
>>>>>>>>> i2c_algo_bit 6020 1 radeon
>>>>>>>>> i2c_core 28608 4 i2c_nforce2,radeon,drm,i2c_algo_bit
>>>>>>>>>
>>>>>>>>> Any thoughts? Thanks for your help.
>>>>>>>>>
>>>>>>>>> =s=
>>>>>>>>>
>>>>>>>>> On Tue, Nov 1, 2011 at 2:34 AM, Luca Deri<deri [at] ntop> wrote:
>>>>>>>>>>
>>>>>>>>>> Scott
>>>>>>>>>> please redo your tests using the code in PF_RING's SVN. From the
>>>>>>>>>> interface names (we now call them dnaX) i see that you are using old
>>>>>>>>>> stuff
>>>>>>>>>>
>>>>>>>>>> Luca
>>>>>>>>>>
>>>>>>>>>> On Oct 31, 2011, at 9:21 PM, Scott L wrote:
>>>>>>>>>>
>>>>>>>>>>> I'm having problems getting pfcount to work. I have two machines
>>>>>>>>>>> connected back-to-back: (A) has a Silicom NIC ; and (B) has a
>>>>>>>>>>> NetEffect 10GbE NIC. I launch pfcount on A. Then on B I start
>>>>>>>>>>> pinging A. pfcount continually reports zero packets received.
>>>>>>>>>>>
>>>>>>>>>>> =========================
>>>>>>>>>>> Absolute Stats: [0 pkts rcvd][0 pkts dropped]
>>>>>>>>>>> Total Pkts=0/Dropped=0.0 %
>>>>>>>>>>> 0 pkts - 0 bytes [0.00 pkt/sec - 0.00 Mbit/sec]
>>>>>>>>>>> =========================
>>>>>>>>>>> Actual Stats: 0 pkts [1'000.06 ms][0.00 pkt/sec]
>>>>>>>>>>> =========================
>>>>>>>>>>>
>>>>>>>>>>> The only relevant log messages I see are:
>>>>>>>>>>>
>>>>>>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Down
>>>>>>>>>>> ixgbe 0000:06:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
>>>>>>>>>>> device eth0 entered promiscuous mode
>>>>>>>>>>> device eth0 left promiscuous mode
>>>>>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=0)
>>>>>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=0)
>>>>>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=1)
>>>>>>>>>>> [PF_RING] --> handle_hw_filtering_rule(command=1)
>>>>>>>>>>>
>>>>>>>>>>> As I look around I don't see the problem. I can see the packets as
>>>>>>>>>>> they are transmitted on B. And the RX packet count for eth2 that is
>>>>>>>>>>> displayed by ifconfig increments appropriately on A. But pfcount
>>>>>>>>>>> doesn't see them. Anyone have any suggestions?
>>>>>>>>>>>
>>>>>>>>>>> ifconfig -i eth2
>>>>>>>>>>> -------------------
>>>>>>>>>>> eth2 Link encap:Ethernet HWaddr 00:E0:ED:FF:18:08
>>>>>>>>>>> inet addr:10.0.2.45 Bcast:10.0.2.255 Mask:255.255.255.0
>>>>>>>>>>> inet6 addr: fe80::2e0:edff:feff:1808/64 Scope:Link
>>>>>>>>>>> UP BROADCAST RUNNING PROMISC MULTICAST MTU:1500 Metric:1
>>>>>>>>>>> RX packets:719669104 errors:0 dropped:0 overruns:0 frame:0
>>>>>>>>>>> TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
>>>>>>>>>>> collisions:0 txqueuelen:1000
>>>>>>>>>>> RX bytes:1066541584248 (993.2 GiB) TX bytes:0 (0.0 b)
>>>>>>>>>>> Memory:fd7e0000-fd800000
>>>>>>>>>>>
>>>>>>>>>>> cat /proc/net/pfring/info
>>>>>>>>>>> --------------------------
>>>>>>>>>>> PF_RING Version : 5.0.0 ($Revision: exported$)
>>>>>>>>>>> Ring slots : 4096
>>>>>>>>>>> Slot version : 13
>>>>>>>>>>> Capture TX : Yes [RX+TX]
>>>>>>>>>>> IP Defragment : No
>>>>>>>>>>> Socket Mode : Standard
>>>>>>>>>>> Transparent mode : Yes (mode 0)
>>>>>>>>>>> Total rings : 1
>>>>>>>>>>> Total plugins : 0
>>>>>>>>>>>
>>>>>>>>>>> cat /proc/net/pfring/<pid>-eth2.30
>>>>>>>>>>> --------------------------------------------
>>>>>>>>>>> Bound Device : eth2
>>>>>>>>>>> Slot Version : 13 [5.0.0]
>>>>>>>>>>> Active : 1
>>>>>>>>>>> Breed : DNA
>>>>>>>>>>> Sampling Rate : 1
>>>>>>>>>>> Capture Direction : RX+TX
>>>>>>>>>>> Appl. Name : pfcount
>>>>>>>>>>> IP Defragment : No
>>>>>>>>>>> BPF Filtering : Disabled
>>>>>>>>>>> # Sw Filt. Rules : 0
>>>>>>>>>>> # Hw Filt. Rules : 0
>>>>>>>>>>> Poll Pkt Watermark : 128
>>>>>>>>>>> Num Poll Calls : 1461
>>>>>>>>>>> Channel Id : 0
>>>>>>>>>>> Num Slots : 8192
>>>>>>>>>>> Tot Memory : 33685504 bytes
>>>>>>>>>>>
>>>>>>>>>>> ethtool -i eth2
>>>>>>>>>>> -------------------
>>>>>>>>>>> driver: ixgbe
>>>>>>>>>>> version: 3.3.9-DNA
>>>>>>>>>>> firmware-version: 1.3-0
>>>>>>>>>>> bus-info: 0000:06:00.0
>>>>>>>>>>>
>>>>>>>>>>> ethtool eth2
>>>>>>>>>>> ----------------
>>>>>>>>>>> Settings for eth2:
>>>>>>>>>>> Supported ports: [ FIBRE ]
>>>>>>>>>>> Supported link modes: 10000baseT/Full
>>>>>>>>>>> Supports auto-negotiation: No
>>>>>>>>>>> Advertised link modes: 10000baseT/Full
>>>>>>>>>>> Advertised auto-negotiation: No
>>>>>>>>>>> Speed: 10000Mb/s
>>>>>>>>>>> Duplex: Full
>>>>>>>>>>> Port: FIBRE
>>>>>>>>>>> PHYAD: 0
>>>>>>>>>>> Transceiver: external
>>>>>>>>>>> Auto-negotiation: off
>>>>>>>>>>> Supports Wake-on: d
>>>>>>>>>>> Wake-on: d
>>>>>>>>>>> Current message level: 0x00000007 (7)
>>>>>>>>>>> Link detected: yes
>>>>>>>>>>> _______________________________________________
>>>>>>>>>>> Ntop-misc mailing list
>>>>>>>>>>> Ntop-misc [at] listgateway
>>>>>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>>>>
>>>>>>>>>> ---
>>>>>>>>>> We can't solve problems by using the same kind of thinking we used when
>>>>>>>>>> we created them - Albert Einstein
>>>>>>>>>>
>>>>>>>>>> _______________________________________________
>>>>>>>>>> Ntop-misc mailing list
>>>>>>>>>> Ntop-misc [at] listgateway
>>>>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>>>>
>>>>>>>>> _______________________________________________
>>>>>>>>> Ntop-misc mailing list
>>>>>>>>> Ntop-misc [at] listgateway
>>>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>>
>>>>>>>> _______________________________________________
>>>>>>>> Ntop-misc mailing list
>>>>>>>> Ntop-misc [at] listgateway
>>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>>>
>>>>>>>>
>>>>>>> _______________________________________________
>>>>>>> Ntop-misc mailing list
>>>>>>> Ntop-misc [at] listgateway
>>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>
>>>>>> _______________________________________________
>>>>>> Ntop-misc mailing list
>>>>>> Ntop-misc [at] listgateway
>>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>>>
>>>>> _______________________________________________
>>>>> Ntop-misc mailing list
>>>>> Ntop-misc [at] listgateway
>>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>
>>>> _______________________________________________
>>>> Ntop-misc mailing list
>>>> Ntop-misc [at] listgateway
>>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>>>
>>> _______________________________________________
>>> Ntop-misc mailing list
>>> Ntop-misc [at] listgateway
>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc

_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Nov 22, 2011, 11:26 AM

Post #17 of 30 (1491 views)
Permalink
Re: Problems with pfcount [In reply to]

Alfredo,

I'm currently running the 5.2.0 tarball. Should I upgrade to the head
of the devel branch (i.e., 5.2.1)? Or?

=s=

On Tue, Nov 22, 2011 at 2:24 AM, Alfredo Cardigliano
<cardigliano [at] ntop> wrote:
> Scott
> I agree with you, it looks like an rx problem.
> Please make sure that everything is in sync (recompile all the PF_RING package from svn: drivers,
> kernel module, library, applications), and if the problem is still there we may need to debug it on
> your server (if possible), since it is not reproducible on our.
>
> Regards
> Alfredo
>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


cardigliano at ntop

Nov 22, 2011, 11:36 AM

Post #18 of 30 (1492 views)
Permalink
Re: Problems with pfcount [In reply to]

On Nov 22, 2011, at 8:26 PM, Scott L wrote:

> Alfredo,
>
> I'm currently running the 5.2.0 tarball. Should I upgrade to the head
> of the devel branch (i.e., 5.2.1)? Or?

Scott
please try downloading the latest svn rev:
svn co https://svn.ntop.org/svn/ntop/trunk/PF_RING
recompiling/reloading everything.
As I said, if this does not help, we may need to debug it on your server.

Alfredo

>
> =s=
>
> On Tue, Nov 22, 2011 at 2:24 AM, Alfredo Cardigliano
> <cardigliano [at] ntop> wrote:
>> Scott
>> I agree with you, it looks like an rx problem.
>> Please make sure that everything is in sync (recompile all the PF_RING package from svn: drivers,
>> kernel module, library, applications), and if the problem is still there we may need to debug it on
>> your server (if possible), since it is not reproducible on our.
>>
>> Regards
>> Alfredo
>>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc

_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Nov 22, 2011, 4:39 PM

Post #19 of 30 (1489 views)
Permalink
Re: Problems with pfcount [In reply to]

Alfredo,

I've downloaded the latest svn revision (Revision 5022), rebuilt and
reloaded everything. I'm still seeing the problem. Any thoughts on
what I should be looking for to try to identify the problem?

=s=


On Tue, Nov 22, 2011 at 12:36 PM, Alfredo Cardigliano
<cardigliano [at] ntop> wrote:
>
> Scott
> please try downloading the latest svn rev:
> svn co https://svn.ntop.org/svn/ntop/trunk/PF_RING
> recompiling/reloading everything.
> As I said, if this does not help, we may need to debug it on your server.
>
> Alfredo
>
>>
>> =s=
>>
>> On Tue, Nov 22, 2011 at 2:24 AM, Alfredo Cardigliano
>> <cardigliano [at] ntop> wrote:
>>> Scott
>>> I agree with you, it looks like an rx problem.
>>> Please make sure that everything is in sync (recompile all the PF_RING package from svn: drivers,
>>> kernel module, library, applications), and if the problem is still there we may need to debug it on
>>> your server (if possible), since it is not reproducible on our.
>>>
>>> Regards
>>> Alfredo
>>>
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


cardigliano at ntop

Nov 22, 2011, 11:53 PM

Post #20 of 30 (1493 views)
Permalink
Re: Problems with pfcount [In reply to]

Scott
just one more question, is your system 32 or 64 bit based?
As I told you, this is a strange issue and I need to reproduce/debug
it in order to identify the cause.

Alfredo

On Nov 23, 2011, at 1:39 AM, Scott L wrote:

> Alfredo,
>
> I've downloaded the latest svn revision (Revision 5022), rebuilt and
> reloaded everything. I'm still seeing the problem. Any thoughts on
> what I should be looking for to try to identify the problem?
>
> =s=
>
>
> On Tue, Nov 22, 2011 at 12:36 PM, Alfredo Cardigliano
> <cardigliano [at] ntop> wrote:
>>
>> Scott
>> please try downloading the latest svn rev:
>> svn co https://svn.ntop.org/svn/ntop/trunk/PF_RING
>> recompiling/reloading everything.
>> As I said, if this does not help, we may need to debug it on your server.
>>
>> Alfredo
>>
>>>
>>> =s=
>>>
>>> On Tue, Nov 22, 2011 at 2:24 AM, Alfredo Cardigliano
>>> <cardigliano [at] ntop> wrote:
>>>> Scott
>>>> I agree with you, it looks like an rx problem.
>>>> Please make sure that everything is in sync (recompile all the PF_RING package from svn: drivers,
>>>> kernel module, library, applications), and if the problem is still there we may need to debug it on
>>>> your server (if possible), since it is not reproducible on our.
>>>>
>>>> Regards
>>>> Alfredo
>>>>
>>> _______________________________________________
>>> Ntop-misc mailing list
>>> Ntop-misc [at] listgateway
>>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>
>> _______________________________________________
>> Ntop-misc mailing list
>> Ntop-misc [at] listgateway
>> http://listgateway.unipi.it/mailman/listinfo/ntop-misc
>>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc

_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Nov 23, 2011, 9:34 AM

Post #21 of 30 (1487 views)
Permalink
Re: Problems with pfcount [In reply to]

Alfredo,

We're currently running a 64-bit kernel. Also, our system is
AMD-based (dual-socket quad-core Opterons).

=s=

On Wed, Nov 23, 2011 at 12:53 AM, Alfredo Cardigliano
<cardigliano [at] ntop> wrote:
> Scott
> just one more question, is your system 32 or 64 bit based?
> As I told you, this is a strange issue and I need to reproduce/debug
> it in order to identify the cause.
>
> Alfredo
>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Nov 29, 2011, 9:20 AM

Post #22 of 30 (1463 views)
Permalink
Re: Problems with pfcount [In reply to]

Alfredo,

I noticed that our machine is running an older kernel (2.6.31.5-127).
The PF_RING webpage states that it works with kernels 2.6.18 and newer
so I hadn't given it much thought. But given our strange problem, I'm
wondering if you have had success with kernels of a similar vintage?
Should we upgrade to a newer version?

Also, given your question about a 32-bit or 64-bit kernel, have you
noticed that one or the other works better with PF_RING?

=s=

On Wed, Nov 23, 2011 at 10:34 AM, Scott L <sallynbird [at] gmail> wrote:
> Alfredo,
>
> We're currently running a 64-bit kernel.  Also, our system is
> AMD-based (dual-socket quad-core Opterons).
>
> =s=
>
> On Wed, Nov 23, 2011 at 12:53 AM, Alfredo Cardigliano
> <cardigliano [at] ntop> wrote:
>> Scott
>> just one more question, is your system 32 or 64 bit based?
>> As I told you, this is a strange issue and I need to reproduce/debug
>> it in order to identify the cause.
>>
>> Alfredo
>>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


cardigliano at ntop

Nov 29, 2011, 9:46 AM

Post #23 of 30 (1464 views)
Permalink
Re: Problems with pfcount [In reply to]

Scott
actually we recommend kernels > 2.6.18 with vanilla PF_RING, not with DNA. However 2.6.31 should be fine.
Upgrading to a newer version is not a bad idea, if possible. Currently we are mainly using 2.6.36 and newer kernels.
A asked you about 32/64bit just because there was an old 32bit dna library in svn.

Regards
Alfredo


On Nov 29, 2011, at 6:20 PM, Scott L wrote:

> Alfredo,
>
> I noticed that our machine is running an older kernel (2.6.31.5-127).
> The PF_RING webpage states that it works with kernels 2.6.18 and newer
> so I hadn't given it much thought. But given our strange problem, I'm
> wondering if you have had success with kernels of a similar vintage?
> Should we upgrade to a newer version?
>
> Also, given your question about a 32-bit or 64-bit kernel, have you
> noticed that one or the other works better with PF_RING?
>
> =s=
>
> On Wed, Nov 23, 2011 at 10:34 AM, Scott L <sallynbird [at] gmail> wrote:
>> Alfredo,
>>
>> We're currently running a 64-bit kernel. Also, our system is
>> AMD-based (dual-socket quad-core Opterons).
>>
>> =s=
>>
>> On Wed, Nov 23, 2011 at 12:53 AM, Alfredo Cardigliano
>> <cardigliano [at] ntop> wrote:
>>> Scott
>>> just one more question, is your system 32 or 64 bit based?
>>> As I told you, this is a strange issue and I need to reproduce/debug
>>> it in order to identify the cause.
>>>
>>> Alfredo
>>>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc

_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


sallynbird at gmail

Nov 29, 2011, 4:07 PM

Post #24 of 30 (1464 views)
Permalink
Re: Problems with pfcount [In reply to]

Alfredo,

We looked at the statistics produced by our switch and discovered that
when pfcount stops reporting received packets, we start seeing Pause
frames from the Silicom NIC. This would account for the fact that we
stop seeing packets. Have you seen this issue before? Any idea how
we might resolve it?

=s=

On Tue, Nov 29, 2011 at 10:46 AM, Alfredo Cardigliano
<cardigliano [at] ntop> wrote:
> Scott
> actually we recommend kernels > 2.6.18 with vanilla PF_RING, not with DNA. However 2.6.31 should be fine.
> Upgrading to a newer version is not a bad idea, if possible. Currently we are mainly using 2.6.36 and newer kernels.
> A asked you about 32/64bit just because there was an old 32bit dna library in svn.
>
> Regards
> Alfredo
>
_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc


cardigliano at ntop

Nov 29, 2011, 5:07 PM

Post #25 of 30 (1466 views)
Permalink
Re: Problems with pfcount [In reply to]

Scott
it is possible that the flow control slows down a link, but in your case it just stops.
If you want you can try with these commands to see if something changes:
ethtool -A dna0 autoneg off
ethtool -A dna0 off
ethtool -A dna0 tx off

Alfredo

On Nov 30, 2011, at 1:07 AM, Scott L wrote:

> Alfredo,
>
> We looked at the statistics produced by our switch and discovered that
> when pfcount stops reporting received packets, we start seeing Pause
> frames from the Silicom NIC. This would account for the fact that we
> stop seeing packets. Have you seen this issue before? Any idea how
> we might resolve it?
>
> =s=
>
> On Tue, Nov 29, 2011 at 10:46 AM, Alfredo Cardigliano
> <cardigliano [at] ntop> wrote:
>> Scott
>> actually we recommend kernels > 2.6.18 with vanilla PF_RING, not with DNA. However 2.6.31 should be fine.
>> Upgrading to a newer version is not a bad idea, if possible. Currently we are mainly using 2.6.36 and newer kernels.
>> A asked you about 32/64bit just because there was an old 32bit dna library in svn.
>>
>> Regards
>> Alfredo
>>
> _______________________________________________
> Ntop-misc mailing list
> Ntop-misc [at] listgateway
> http://listgateway.unipi.it/mailman/listinfo/ntop-misc

_______________________________________________
Ntop-misc mailing list
Ntop-misc [at] listgateway
http://listgateway.unipi.it/mailman/listinfo/ntop-misc

First page Previous page 1 2 Next page Last page  View All NTop misc RSS feed   Index | Next | Previous | View Threaded
 
 


Interested in having your list archived? Contact Gossamer Threads
 
  Web Applications & Managed Hosting Powered by Gossamer Threads Inc.