Can anyone please confirm if this is expected behavior? The documentation
included in the gzipped tar, as well as on the site, does not explain this
clearly.
The documentation in drivers/README.drivers suggests that DNA-enabled
adapters, adapters specified by 'adapters_to_enable', should only be
affected, while others should not. This is evidenced by the fact that on my
eth0 interface I can send and receive ICMP on it while DNA is enabled for
eth1. What isn't explained is why TCP/UDP traffic, such as SSH or DNS
lookups, on eth0 fails after passing 'adapters_to_enable' for eth1 only.
In drivers/DNA/README.DNA it states:
*"The DNA driver allows you bypass the kernel and let your applications
manipulate the card directly.This means that as soon as you have installed
this driver, only DNA-aware applications will beable to play with the
card."*
Which seems to suggest that if the driver is loaded, then all adapters can
only be used with PF_RING-aware applications. But in the code for the IGB
driver (igb_dna.c) you have:
*void dna_check_enable_adapter(struct igb_adapter *adapter) {
adapter->dna.dna_enabled = 0; /* Default */
if(strcmp(adapter->netdev->name, "eth0") == 0) return; /* We never enable
DNA on eth0 as this might be the management interface */ *
Which contradicts that statement from README.DNA.
Lastly, in the PF_RING User's Guide, the e1000 driver is missing from the
list of DNA-aware drivers available, but the e1000 driver most certainly
exists and is in the PF_RING distribution, as well as listed on the ntop
site as one of the supported drivers.
So, expected behavior? Not expected behavior?
Thanks.
Ben
On Mon, Dec 9, 2013 at 10:39 AM, Ben Cole <[email protected]> wrote:
> Greetings,
>
> I've been having quite a bit of difficulty getting the e1000-NAPI-DNA
> drivers working for my Intel 82546EB NICs. The drivers load fine, and I can
> create the DNA interface, but this disrupts to-the-box traffic on non-DNA
> interfaces.
>
> I can't find this documented anywhere, but is there a way around this?
> I've passed the 'adapters_to_enable' parameter to the module, and a dna0
> adapter is only created for the specified NIC. Should the NICs that have
> not been specified still function as NAPI? If so, shouldn't they still
> function normally?
>
> Please let me know, otherwise I might need to install a separate NIC card,
> since all of the NICs currently in the box use e1000.
>
> System information follows:
>
> Hardware: Sun Fire X4100
>
> 00:01.0 PCI bridge [0604]: Advanced Micro Devices [AMD] AMD-8131 PCI-X
> Bridge [1022:7450] (rev 13)
> 00:01.1 PIC [0800]: Advanced Micro Devices [AMD] AMD-8131 PCI-X IOAPIC
> [1022:7451] (rev 01)
> 00:02.0 PCI bridge [0604]: Advanced Micro Devices [AMD] AMD-8131 PCI-X
> Bridge [1022:7450] (rev 13)
> 00:02.1 PIC [0800]: Advanced Micro Devices [AMD] AMD-8131 PCI-X IOAPIC
> [1022:7451] (rev 01)
> 00:06.0 PCI bridge [0604]: Advanced Micro Devices [AMD] AMD-8111 PCI
> [1022:7460] (rev 07)
> 00:07.0 ISA bridge [0601]: Advanced Micro Devices [AMD] AMD-8111 LPC
> [1022:7468] (rev 05)
> 00:07.1 IDE interface [0101]: Advanced Micro Devices [AMD] AMD-8111 IDE
> [1022:7469] (rev 03)
> 00:07.2 SMBus [0c05]: Advanced Micro Devices [AMD] AMD-8111 SMBus 2.0
> [1022:746a] (rev 02)
> 00:07.3 Bridge [0680]: Advanced Micro Devices [AMD] AMD-8111 ACPI
> [1022:746b] (rev 05)
> 00:18.0 Host bridge [0600]: Advanced Micro Devices [AMD] K8
> [Athlon64/Opteron] HyperTransport Technology Configuration [1022:1100]
> 00:18.1 Host bridge [0600]: Advanced Micro Devices [AMD] K8
> [Athlon64/Opteron] Address Map [1022:1101]
> 00:18.2 Host bridge [0600]: Advanced Micro Devices [AMD] K8
> [Athlon64/Opteron] DRAM Controller [1022:1102]
> 00:18.3 Host bridge [0600]: Advanced Micro Devices [AMD] K8
> [Athlon64/Opteron] Miscellaneous Control [1022:1103]
> 00:19.0 Host bridge [0600]: Advanced Micro Devices [AMD] K8
> [Athlon64/Opteron] HyperTransport Technology Configuration [1022:1100]
> 00:19.1 Host bridge [0600]: Advanced Micro Devices [AMD] K8
> [Athlon64/Opteron] Address Map [1022:1101]
> 00:19.2 Host bridge [0600]: Advanced Micro Devices [AMD] K8
> [Athlon64/Opteron] DRAM Controller [1022:1102]
> 00:19.3 Host bridge [0600]: Advanced Micro Devices [AMD] K8
> [Athlon64/Opteron] Miscellaneous Control [1022:1103]
> 01:01.0 Ethernet controller [0200]: Intel Corporation 82546EB Gigabit
> Ethernet Controller (Copper) [8086:1010] (rev 03)
> 01:01.1 Ethernet controller [0200]: Intel Corporation 82546EB Gigabit
> Ethernet Controller (Copper) [8086:1010] (rev 03)
> 01:02.0 Ethernet controller [0200]: Intel Corporation 82546EB Gigabit
> Ethernet Controller (Copper) [8086:1010] (rev 03)
> 01:02.1 Ethernet controller [0200]: Intel Corporation 82546EB Gigabit
> Ethernet Controller (Copper) [8086:1010] (rev 03)
> 02:03.0 SCSI storage controller [0100]: LSI Logic / Symbios Logic SAS1064
> PCI-X Fusion-MPT SAS [1000:0050] (rev 02)
> 03:00.0 USB controller [0c03]: Advanced Micro Devices [AMD] AMD-8111 USB
> OHCI [1022:7464] (rev 0b)
> 03:00.1 USB controller [0c03]: Advanced Micro Devices [AMD] AMD-8111 USB
> OHCI [1022:7464] (rev 0b)
> 03:03.0 VGA compatible controller [0300]: Advanced Micro Devices [AMD] nee
> ATI Rage XL [1002:4752] (rev 27)
> 04:01.0 PCI bridge [0604]: Advanced Micro Devices [AMD] AMD-8131 PCI-X
> Bridge [1022:7450] (rev 13)
> 04:01.1 PIC [0800]: Advanced Micro Devices [AMD] AMD-8131 PCI-X IOAPIC
> [1022:7451] (rev 01)
> 04:02.0 PCI bridge [0604]: Advanced Micro Devices [AMD] AMD-8131 PCI-X
> Bridge [1022:7450] (rev 13)
> 04:02.1 PIC [0800]: Advanced Micro Devices [AMD] AMD-8131 PCI-X IOAPIC
> [1022:7451] (rev 01)
>
>
> OS: Centos 6 kernel 2.6.32-431.el6.x86_64
>
> Ben
>
_______________________________________________
Ntop-misc mailing list
[email protected]
http://listgateway.unipi.it/mailman/listinfo/ntop-misc
