On Thu, Dec 19, 2019 at 10:35 AM adam radford wrote:
>
> e1000-devel list,
>
> Problem:
>
> With kernel 4.19.29 and igb 5.4.0-k on Intel E5-2618Lv4 and E5-2648Lv4
> servers:
> Using the default 8 MSI-X vectors (combined TX/RX queues), after 2
> days to 30 days of runtime we suddenly see unhan
Before you start complaining about what the driver is or isn't doing
you should probably understand that both the Linux and FreeBSD drivers
do have to create a PF VSI as that is the default VSI type if I am not
mistaken. Do you know what the goal is in creating multiple PF VSIs? I
don't see the rea
On Wed, Dec 4, 2019 at 10:56 AM Eddy Geez wrote:
>
> On Tue, Dec 3, 2019 at 6:22 PM Alexander Duyck
> wrote:
> > On Tue, Dec 3, 2019 at 12:40 PM Eddy Geez wrote:
> > >
> > > BLUF:
> > > Is there any way to bring the interface physically up immediately
On Tue, Dec 3, 2019 at 12:40 PM Eddy Geez wrote:
>
> BLUF:
> Is there any way to bring the interface physically up immediately
> when the e1000e driver loads so auto-negotiation can start?
>
> Greetings!
>
> I am evaluating some Intel NUCs that will be diskless and rely on
> PXE netbooting.
>
> I
On Tue, Oct 15, 2019 at 2:11 PM Michał Purzyński
wrote:
>
> Is the RSS redirection table (ethtool -X ) ignored when interrupts are
> pinned to cores?
>
> I configured a card with 12 queues and pinned all of them to cores on a
> local NUMA nodes. Card is local to node 1, so with 12 cores per CPU I
On Fri, Jun 7, 2019 at 7:39 AM Lennart Sorensen
wrote:
>
> On Wed, May 22, 2019 at 10:39:56AM -0400, Lennart Sorensen wrote:
> > OK I applied those two patches and get this:
> >
> > i40e: Intel(R) Ethernet Connection XL710 Network Driver - version 2.1.7-k
> > i40e: Copyright (c) 2013 - 2014 Intel
On Tue, May 21, 2019 at 10:55 AM Lennart Sorensen
wrote:
>
> On Tue, May 21, 2019 at 09:51:33AM -0700, Alexander Duyck wrote:
> > I think we need to narrow this down a bit more. Let's try forcing the
> > lookup table all to one value and see if traffic is sti
On Mon, Apr 15, 2019 at 11:22 AM Joseph Yasi wrote:
>
> Hello,
> I reported a regression that happened after upgrading from 5.0.6 to 5.0.7:
> https://bugzilla.kernel.org/show_bug.cgi?id=203175
>
> This is fixed by reverting commit
> 7f0a3a436e88a71b96694c029f01a9a8eade3d5d e1000e: fix cyclic reset
On Mon, Jul 30, 2018 at 4:43 PM, Àbéjídé Àyodélé
wrote:
>> Is it always the OOM errors followed by the Tx timeout?
>
> Yes, I believe I have the dmesg from one of the earlier incidence, I can
> clean that up and make it public if you want.
There shouldn't be any need. Basically what you want to c
On Mon, Jul 30, 2018 at 1:25 PM, Àbéjídé Àyodélé
wrote:
> Hi Alex,
>
> Thanks for responding!
>
>> Have you been seeing this as a
>> reproducible issue or is this something that has only occurred once?
>
> It has occurred 3 times so far, we usually stop the hosts we see the issue
> on for a long w
On Sat, Jul 28, 2018 at 5:44 PM, Àbéjídé Àyodélé
wrote:
> Hi friends,
>
> On one of our machines at work, we observed a sequence of events starting
> from an OOM in a secondary cgroup which ends up in the bond interface being
> down for a period of up to 12 seconds. Below is some piece of dmesg ab
t; Kojedzinszky Richárd
> Euronet Magyarorszag Informatika Zrt.
>
> On Mon, 28 May 2018, Alexander Duyck wrote:
>
>> Date: Mon, 28 May 2018 10:39:40 -0700
>> From: Alexander Duyck
>> To: Kojedzinszky Richárd
>> Cc: e1000-devel@lists.sourceforge.net
>>
On Fri, May 25, 2018 at 11:33 AM, Michael Yartys
wrote:
> I'm running OpenWrt on a NETGEAR R7800, and I'm trying to connect my laptop
> to one of the LAN ports. I've run the tests you suggested:
>
> -
>
> [telia@lulz ~]$ unam
On Fri, May 25, 2018 at 10:25 AM, Andre Ruiz wrote:
>
> Alex,
>
> The tests I'm making at work and at home, both to cheap 8 port switches, one
> is an Encore Gigabit Switch and the other is a TP-Link Fast Ethernet Switch.
> Although they are cheap hardware, both behave well in normal conditions.
>
On Mon, May 28, 2018 at 12:09 AM, Kojedzinszky Richárd
wrote:
> Dear developers,
>
> We have a X8DTU Supermicro system with onboard lan gigabit interfaces, we
> run debian stretch on it, we use it for virtualisation with xen.
> Unfortunately, we periodically end up with igb tx timeouts on the host
On Fri, May 25, 2018 at 3:19 AM, Michael Yartys
wrote:
> Hi
>
> The connection doesn't work and I get no traffic. I tried rebooting with the
> cable plugged in, but I still experience no connectivity. Here's the dmesg
> output from e1000e:
>
> [telia@lulz ~]$ dmesg | grep -e1000e
> [3.011443
On Thu, May 24, 2018 at 6:54 PM, Andre Ruiz wrote:
>
> Alex,
>
> In fact, sometimes it won't pass traffic at all and sometimes it will work
> at 10Mbit/s. I still cannot tell what causes each scenario. The common
> aspect is the 10Mbit/Full part. IIRC a failed link speed negotiation will
> make it
Thanks for the input.
Michael, do you know if your problem exhibits itself similarly? Does a
reboot allow you to connect, and then you lose connectivity after
suspending/resuming the laptop? Also I would be curious if we are
seeing any messages in the dmesg log as I would interpret us reporting
a
On Thu, May 24, 2018 at 11:24 AM, Michael Yartys via E1000-devel
wrote:
>
>
> I also experience this issue on my Dell Latitude E6420 running Fedora 28 with
> an Intel 82579LM.
>
> [telia@lulz ~]$ lspci | grep Ethernet
> 00:19.0 Ethernet controller: Intel Corporation 82579LM Gigabit Network
> Con
fter getting it working. If there's value
> in seeing the old state, I can reboot and send it to you easily enough.
>
>
> Thanks again,
> - Kevin
>
>
> On 05/09/2018 12:53 PM, Alexander Duyck wrote:
>> Hi Kevin,
>>
>> The issue with the BIOS is that it
; in a moment - no need to
> spam the list with that.
>
>
> Can you tell me what cryptic acronyms I need to repair in coreboot so
> those kernel options aren't necessary?
>
>
>
> Huge help, thanks again,
>
> - Kevin
>
>
> On 05/07/2018 12:40 PM, Alexander
On Sat, May 5, 2018 at 6:09 PM, Kevin Cody-Little wrote:
>
> Folks,
>
>
> I bought into parts for a new home firewall thinking it would provide an
> IOMMU. As it turns out, that's a "cancelled feature" on AM1 systems, and
> now I've got an ET in my hands that may as well be a PT.
You can still al
On Sat, Mar 31, 2018 at 1:16 PM, Ran Shalit wrote:
> On Sat, Mar 31, 2018 at 8:24 PM, Alexander Duyck
> wrote:
>> On Sat, Mar 31, 2018 at 1:09 AM, Ran Shalit wrote:
>>> On Fri, Mar 30, 2018 at 8:08 PM, Alexander Duyck
>>> wrote:
>>>> On Thu, M
On Sat, Mar 31, 2018 at 1:09 AM, Ran Shalit wrote:
> On Fri, Mar 30, 2018 at 8:08 PM, Alexander Duyck
> wrote:
>> On Thu, Mar 29, 2018 at 10:35 PM, Ran Shalit wrote:
>>> On Fri, Mar 30, 2018 at 12:34 AM, Ran Shalit wrote:
>>>> On Thu, Mar 29, 2018 at 9:3
On Thu, Mar 29, 2018 at 10:35 PM, Ran Shalit wrote:
> On Fri, Mar 30, 2018 at 12:34 AM, Ran Shalit wrote:
>> On Thu, Mar 29, 2018 at 9:36 PM, Alexander Duyck
>> wrote:
>>> On Thu, Mar 29, 2018 at 11:18 AM, Ran Shalit wrote:
>>>> On Thu, Mar 29, 2018 at
On Tue, Mar 27, 2018 at 1:52 AM, Ran Shalit wrote:
> On Thu, Mar 22, 2018 at 7:31 PM, Alexander Duyck
> wrote:
>> On Thu, Mar 22, 2018 at 9:11 AM, Ran Shalit wrote:
>>> On Mon, Mar 19, 2018 at 10:23 PM, Alexander Duyck
>>> wrote:
>>>> On Mon, M
On Thu, Mar 22, 2018 at 9:11 AM, Ran Shalit wrote:
> On Mon, Mar 19, 2018 at 10:23 PM, Alexander Duyck
> wrote:
>> On Mon, Mar 19, 2018 at 12:31 PM, Ran Shalit wrote:
>>> On Mon, Mar 19, 2018 at 6:27 PM, Alexander Duyck
>>> wrote:
>>>> On Mon,
On Tue, Mar 20, 2018 at 2:33 PM, Ran Shalit wrote:
> Hello,
>
> We tested the time it gets for successful boot from powerup, and we
> are surprised to see that using a switch in the middle (100M) gives
> better result.
> I don't understand how it can be.
Setting up a 100M connection is much simpl
On Mon, Mar 12, 2018 at 7:02 PM, Sylvia Else wrote:
> When configuring the rx part of the interface, the e1000_main.c module
> enables receive on the adapter before it has initialised the buffer
> addresses. The resulting race with the arrival of the first packet can lead
> to the adapter and the
On Mon, Mar 19, 2018 at 12:31 PM, Ran Shalit wrote:
> On Mon, Mar 19, 2018 at 6:27 PM, Alexander Duyck
> wrote:
>> On Mon, Mar 19, 2018 at 9:07 AM, Ran Shalit wrote:
>>> Hello,
>>>
>>>
>>>
>>> I am using igb driver:
>>>
>>
On Mon, Mar 19, 2018 at 9:07 AM, Ran Shalit wrote:
> Hello,
>
>
>
> I am using igb driver:
>
> cat output/build/linux-4.10.17/.config | grep IGB
>
> CONFIG_IGB=y
>
> CONFIG_IGB_HWMON=y
>
> CONFIG_IGBVF=y
>
>
>
> But every boot is takes a lot of time till ethernet is ready.
>
> I try to disable aut
I agree with Todd, we need way more information on this.
For example, if we had the dmesg we could tell if the Tx hang message
is being reported or not. If not it might point to a problem with the
interrupts on the device. If I recall correctly the igb driver should
be generating an interrupt ever
On Tue, Jan 23, 2018 at 3:46 PM, Ben Greear wrote:
> Hello,
>
> Anyone have any more suggestions for making e1000e work better? This is
> from a 4.9.65+ kernel,
> with these additional e1000e patches applied:
>
> e1000e: Fix error path in link detection
> e1000e: Fix wrong comment related to link
Hi Avi,
Having to zero out the IPv4 checksum seems to imply that the outer IP
checksum is being recomputed by hardware. That shouldn't be the case
normally unless we are running TSO since the IP header shouldn't be
changing as the hardware requires all the fields be present. Do you
know if the pro
Hi Avi,
You might review the slides and watch the presentations available at:
https://www.netdevconf.org/2.2/session.html?klassert-ipsec-workshop
As far as the code you can review it directly in Jeff's tree at:
https://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git/log/?h=dev-que
On Wed, Nov 22, 2017 at 9:43 AM, Boris Lukashev
wrote:
> Good afternoon all, and happy Thanksgiving as applicable. Sofar on IRC
> suggested i reach out to this ML with my inquiry regarding VFIO for
> the x540 ixgbe driver.
>
> Our use case is to run a SecurityOnion instance in a VM atop a
> harden
an index into a table that yields a row - which of those
>> cores would be used? The packet could you go a core 8 or 9 or 12?
>>
>>
>> On Wed, Nov 22, 2017 at 5:55 PM, Alexander Duyck
>> wrote:
>>>
>>> Comments inline below.
>>>
>>>
Comments inline below.
On Wed, Nov 22, 2017 at 8:23 AM, Michał Purzyński
wrote:
> Hello!
>
> How do I read the indirection table, then one that can be shown with
> ethtool -x? What is the meaning of columns vs rows and what those numbers
> are trying to tell me? I'm guessing it's kind of like a w
On Mon, Nov 20, 2017 at 3:35 PM, Sarah Newman wrote:
> On 11/20/2017 02:56 PM, Alexander Duyck wrote:
>> On Mon, Nov 20, 2017 at 2:38 PM, Sarah Newman
>> wrote:
>>> On 11/20/2017 08:36 AM, Alexander Duyck wrote:
>>>> Hi Sarah,
>>>>
>>>
On Mon, Nov 20, 2017 at 2:38 PM, Sarah Newman wrote:
> On 11/20/2017 08:36 AM, Alexander Duyck wrote:
>> Hi Sarah,
>>
>> I am adding the netdev mailing list as I am not certain this is an
>> i350 specific issue. The traces themselves aren't anything I recognize
&g
Hi Sarah,
I am adding the netdev mailing list as I am not certain this is an
i350 specific issue. The traces themselves aren't anything I recognize
as an existing issue. From what I can tell it looks like you are
running Xen, so would I be correct in assuming you are bridging
between VMs? If so ar
On Thu, Oct 26, 2017 at 8:25 AM, Paweł Staszewski wrote:
> Server after runing for about 40 hours is starting to loose all links on all
> nics.
>
> Warning from : Kernel 4.12.14
>
> Latest working kernel 4.11.12
>
> all kernels >4.14 - have same problem but less in debug info
>
>
> Below warning f
On Mon, Oct 16, 2017 at 3:53 AM, Lluís Vilanova wrote:
> Alexander Duyck writes:
>
>> On Fri, Oct 13, 2017 at 11:26 PM, Lluís Vilanova wrote:
>>> Hi! I'm not sure if this is the right venue for this question, so feel free
>>> to
>>> redirect me
On Fri, Oct 13, 2017 at 11:26 PM, Lluís Vilanova wrote:
> Hi! I'm not sure if this is the right venue for this question, so feel free to
> redirect me.
>
> I'm trying to put some "additional information" on client-generated packets to
> direct them to specific queues of a X540-AT2 nic (server runn
On Wed, Oct 11, 2017 at 7:00 AM, Leonardo Amaral - Listas
wrote:
> Hello List!
>
> In the issue https://github.com/luigirizzo/netmap/issues/355, Giuseppe made
> this patch (
> https://github.com/luigirizzo/netmap/issues/355#issuecomment-331156069 )
> that fixed a bit the kernel panic issues and af
On Tue, Sep 19, 2017 at 2:42 AM, Stefan Bühler
wrote:
> Hi Alex,
>
> On 09/19/2017 01:52 AM, Alexander Duyck wrote:
>> On Mon, Sep 18, 2017 at 9:45 AM, Stefan Bühler
>> wrote:
>>> Hi,
>>>
>>> I've got an X710 ethernet controller; and when I ad
On Mon, Sep 18, 2017 at 9:45 AM, Stefan Bühler
wrote:
> Hi,
>
> I've got an X710 ethernet controller; and when I add nested VLANs the
> "inner" tag gets lost unless I disable the txvlan feature (`ethtool -K
> ens1f0 txvlan off`).
>
> This is my setup:
>
> /sbin/ip link add link ens1f0 name vlan12
> Regards,
> Mattias
>
> On Tue, Aug 22, 2017 at 6:58 PM, Alexander Duyck
> wrote:
>>
>> On Tue, Aug 22, 2017 at 5:16 AM, Mattias Barthel
>> wrote:
>> > Hello,
>> >
>> >
>> > I am trying to add hw timestamping to the igbvf driver in
On Tue, Aug 22, 2017 at 5:16 AM, Mattias Barthel wrote:
> Hello,
>
>
> I am trying to add hw timestamping to the igbvf driver in a KVM guest.
>
> But some of the registers I need to access are offset further away than the
> BAR0 size (16k).
>
> pci :00:0d.0: reg 10: [mem 0xfebd4000-0xfebd7fff]
On Tue, Aug 1, 2017 at 8:29 AM, Codrut Grosu wrote:
>Hi,
>
> We believe there might be a bug in the i40evf driver.
>
> We think that there is race issue between i40evf_reset_task and i40evf_down
> / i40evf_open.
> The reason is that the functions napi_enable / napi_disable must be called
tgen from a separate machine. Stock pktgen isn't good at
> reporting
> received pkts last I checked, so it may be more difficult to easily view the
> problem.
>
> I'll be happy to set up my tool on your Fedora 24 or similar VM or machine
> if you
> want.
>
>
Can you include the pktgen script you are running?
Also when you say you are driving traffic through the bridge are you
sending from something external on the system or are you actually
directing the traffic from pktgen into the bridge directly?
- Alex
On Thu, Mar 16, 2017 at 3:49 PM, Ben Greear
L, node);
>
> ..
>
> ..
>
>
>
> cpu is set to the index of the queue, and then translated to node.
>
> The kzalloc_node() function allocates the vector on the appropriate numa
> node.
>
>
>
> My goal is to override the default values that cpu_to_node
sk #to set the affinity hint
> for the first 4
> ethtool –set-cpu-mask eth1 0 1
> ethtool –set-cpu-mask eth1 1 2
> ethtool –set-cpu-mask eth1 2 4
>
> Thanks,
> Tal Abudi
>
> On Sun, Mar 5, 2017 at 8:06 PM, Alexander Duyck
> wrote:
>>
>> On Sun, Mar 5, 2017
On Sun, Mar 5, 2017 at 8:47 AM, Tal Abudi wrote:
> Hi All
>
> I’m looking for a nice way to pass parameters (list of integers) to each
> ixgbe interface.
>
> Creating /sys entries seems too complex and so I thought about ethtool.
Why mess around with /sys when there is already
/proc/irq/*/smp_aff
I went through the email below and cut out the information I consider
to be noise. What we are left with is the key bits such as kernel
version (2.6.37), driver version (igb-5.0.6), and other critical
information such as memory and interrupt layouts.
So looking over the Tx hang error reports it l
On Thu, Feb 16, 2017 at 7:53 AM, Kieran Tyrrell wrote:
> Hi,
>
> We are developing a system using an i210 with an ARM SoC, and require multi
> queue support, but the SoC doesn’t support MSI-X.
>
> Looking through the sources it appears it would take considerable effort to
> modify igb to support m
On Tue, Dec 6, 2016 at 3:22 PM, Ben Greear wrote:
> We put 3 10-g dual-port ixgbe NICs and 4 4-port I350 NICs in a 2U rackmount,
> and one of the ixgbe ports
> fails to come up. This previously worked before reboot, so maybe it is a
> race somehow. Kernel is 4.4.11+,
> but not hacks to ixgbe or
On Thu, Nov 24, 2016 at 10:13 AM, Yashar Nezami wrote:
> I have attached the log below.
>
> Basically I'm installing the XL710-QDA2 on Ubuntu 16.01.
>
> uname -a
> Linux x300 4.4.0-47-generic #68-Ubuntu SMP Wed Oct 26 19:39:52 UTC 2016
> x86_64 x86_64 x86_64 GNU/Linux
>
> I have followed the drive
On Wed, Nov 9, 2016 at 3:16 AM, 张东亚 wrote:
> Hi Alexander,
>
> Thanks a lot for your reply, the following code is excerpted from function
> ixgbe_probe in ixgbe_main.c of 4.1.5 driver code.
>
> #ifdef HAVE_ENCAP_TSO_OFFLOAD
> netdev->features |= NETIF_F_GSO_UDP_TUNNEL;
> #endif
As far as I know t
On Mon, Nov 7, 2016 at 11:42 PM, 张东亚 wrote:
> Hi,
>
> I am now research on VXLAN OFFLOAD of intel 82599 NIC with openvswitch
> 2.6.0, after reading some code and does the test, and I have concluded it
> seems if the VXLAN endpoint ip is configured on a vlan interface like
> eth0.100, VXLAN OFFLOAD
yński
wrote:
> Did I ruin DDIO with DCA=2 parameter to X520?
>
> Looking at the driver code, I just enabled DCA instead.
>
>> On 1 Nov 2016, at 20:56, Alexander Duyck wrote:
>>
>> On Tue, Nov 1, 2016 at 12:04 PM, Michał Purzyński
>> wrote:
>>> Lookin
On Tue, Nov 1, 2016 at 12:04 PM, Michał Purzyński
wrote:
> Looking through some old posts on e1000 I found that one can detect if DCA
> is enabled with ethregs. Are these registers per queue? Here, the X520 is
> configured with a single queue and the highest bits are set only for
> DCA_RXCTRL[000]
On Tue, Nov 1, 2016 at 8:16 AM, Matias Vara wrote:
> Hi everyone, I am facing an issue with the ixgbe 10G Network card version
> 4.4.6. I am in XenServer which is based on CentOS and the issue only appers
> on FCOE machines. I am getting the following message during crash:
>
> [2016-10-28 09:43:58
On Tue, Nov 1, 2016 at 8:16 AM, Matias Vara wrote:
> Hi everyone, I am facing an issue with the ixgbe 10G Network card version
> 4.4.6. I am in XenServer which is based on CentOS and the issue only appers
> on FCOE machines. I am getting the following message during crash:
>
> [2016-10-28 09:43:5
On Sun, Oct 16, 2016 at 4:52 AM, Michał Purzyński
wrote:
> Could you fill me in on how the bounce buffer approach to memory management
> in IXGBE and I40E works?
>
> Why do you allocate the same amount of memory in ixgbe_setup_rx_resources()
> twice?
> First time with a call to rx_ring->rx_buffer_
On Fri, Oct 14, 2016 at 8:47 AM, Tal Abudi wrote:
> Hi All
> Maybe a silly question.. But...
> When testing high performance (packet-rate) on a system with igb/ixgbe
> nics, is there difference if i turn multi queue off or I set each queues
> affinity to the same CPU ?
>
> My hunch says that MQ of
;
> We need autoneg on out ports, but could do without flow control. Is that
> possible to configure? "autoneg on rx off" does not do it . It looks like
> autoneg enables/negotiates pause.
>
> Best
> John
>
>
> On 10/13/2016 04:09 PM, Alexander Duyck wrote
On Wed, Oct 12, 2016 at 2:53 PM, John Osswald wrote:
> We have multiple systems (and system types) experiencing a kernel panic,
> when they upgrade to Debian 8. We tried the native Debian IGB driver, as
> well as, IGB 5.3.5.3, with no difference in behavior. The common element is
> that they are
, that's a last question in this series. Thank you a lot, Suricata
> community really appreciates Intel's help :-)
>
>
> On Mon, Sep 26, 2016 at 3:46 AM, Alexander Duyck
> wrote:
>>
>> Okay, I'll just paste
you will need to add more CPU power in order
to be able to handle the load as you are currently maxing out the one
thread you are using.
- Alex
On Sun, Sep 25, 2016 at 4:47 PM, Michał Purzyński
wrote:
>
> Sent off list, because files are around a MB.
>
> On Mon, Sep 26, 2016 at 1:28 AM
to the
root complex and not some secondary bus on a PCIe switch that is
actually downgrading the link between the device and the CPU socket.
> On Sat, Sep 24, 2016 at 3:20 AM, Alexander Duyck
> wrote:
>>
>> Well as a general rule anything over about 80usecs for
>> Interr
to all cards in this system).
>
> I could see the same issue sending traffic to just one card.
>
> Of course a single core is swamped with ACK-ing hardware IRQ and then doing
> softIRQ (which seems to be mostly memcpy?). But then again, I don't see
> errors about lacking buffer
tion is a scam and they actively avoid publishing
> motherboard layout.
>
> Any other place I could look for hints?
>
>
> On Fri, Sep 23, 2016 at 7:01 PM, Alexander Duyck
> wrote:
>>
>> On Fri, Sep 23, 2016 at 1:10 AM, Michał Purzyński
>> wrote:
>> &g
On Thu, Sep 22, 2016 at 5:40 PM, Michał Purzyński
wrote:
> What's the current status ofI/O and ixgbe driver and 82599 cards? Is it
> even used? How's the performance?
>
> If it is used, do you know in which stage exactly? Is it used to copy data
> from driver buffers (those that card does DMA into
On Fri, Sep 23, 2016 at 1:10 AM, Michał Purzyński
wrote:
> Hello.
>
> On my IDS workload with af_packet I can see rx_missed_errors growing while
> rx_no_buffer_count does not. Basically every other kind of rx_ error
> counter is 0, including rx_no_dma_resources. It's an 82599 based card.
>
> I don
just like cache missed, we need to handle that anyway.
>
> Hank
>
> On Thu, Sep 8, 2016 at 10:16 AM, Alexander Duyck
> wrote:
>>
>> So the lspci looks good. It looks like everything is optimal there.
>> From what I can tell it looks like the NICs are in slots associa
s
placed there by DDIO.
I hope you find some of this information useful.
- Alex
On Thu, Sep 8, 2016 at 8:58 AM, Hank Liu wrote:
> Hi Alex,
>
> see attached. thanks!
>
> Hank
>
> On Wed, Sep 7, 2016 at 7:32 PM, Alexander Duyck
> wrote:
>>
>> Can you send me
or rx_no_dma_resource when BW is up
> to 8 Gbps...
>
> On Wed, Sep 7, 2016 at 3:42 PM, Hank Liu wrote:
>>
>> HI Alexander,
>>
>> Thanks for your input. Will give it a try.
>>
>>
>> Hank
>>
>> On Wed, Sep 7, 2016 at 3:23 PM, Alexander Duyck
On Wed, Sep 7, 2016 at 2:19 PM, Rustad, Mark D wrote:
> Hank Liu wrote:
>
>>> *From:* Hank Liu [mailto:hank.tz...@gmail.com]
>>> *Sent:* Wednesday, September 07, 2016 10:20 AM
>>> *To:* Skidmore, Donald C
>>> *Cc:* e1000-devel@lists.sourceforge.net
>>> *Subject:* Re: [E1000-devel] Intel 82599 AX
socket buffers are mapped into userspace. That's what
> I use currently, with a great success.
Okay so it sounds like you are already familiar with it then, good to know.
> On Sun, Sep 4, 2016 at 7:20 PM, Alexander Duyck
> wrote:
>>
>> On Sun, Sep 4, 2016 at 2:50 AM
On Sun, Sep 4, 2016 at 2:50 AM, Michał Purzyński
wrote:
> My IXGBE data path journey made me ask questions, like the one above.
> Basically (I'm skipping a few steps here):
>
> 1. packet arrives to the card and is verified by MAC
> 2. packet is placed in the card's FIFO (which is small)
> 3. lots
On Fri, Aug 26, 2016 at 7:45 AM, Auer, Jens wrote:
> Hi,
>
> how does Perfect Filter (PF) work? According to the Readme,
>
>
> Perfect filter is an interface to load the filter table that funnels all flow
> into queue_0 unless an alternative queue is specified using "action". In that
> case, any f
On Fri, Aug 26, 2016 at 3:18 AM, Auer, Jens wrote:
> Hi,
>
> we are experiencing packet reordering and thus bandwidth drops due to
> retransmissions on our servers. We are using RedHat 7.2 on HP Servers
> connected to a HP Aruba 1920 10GB switch. I can easily reproduce the issues
> by running i
---Original Message-
> From: Hasan Jamal [mailto:hja...@connecttech.com]
> Sent: August-04-16 4:44 PM
> To: 'Alexander Duyck'; 'Fujinaka, Todd'
> Cc: e1000-devel@lists.sourceforge.net
> Subject: Re: [E1000-devel] Intel's Ethernet 10G 2P X710 Adapter driver for
>
On Sun, Aug 7, 2016 at 9:37 AM, Tal Abudi wrote:
> Hi All
> I have a question regarding symmetric RSS hashing.
> Until now I’ve been using a relatively old combination of
> kernel/drivers/ethtool and I implemented some patches I found in the
> mailing list to allow Toeplitz symmetric RSS so C2S an
Hi Jamal,
The driver tarball should work with any architecture, though as Todd
said it probably hasn't been tested with ARM architecture.
I would recommend giving it a try and if you see any build errors then
probably post them back on the list, and if needed I can probably pull
in the necessary
On Fri, Jul 29, 2016 at 4:37 PM, Dominic Curran
wrote:
> Hi
>
> This question refers to igb codebase.
> I have a question regarding the setting of hw->mac.autoneg.
>
> Is it correct to say for igb driver:
>"if speed=1000 and duplex=FULL and media_type=COPPER then only
> auto-negotiate enable
On Fri, Jul 29, 2016 at 1:59 PM, Alexey Muranov
wrote:
> On 27 Jul 2016, at 17:45, Alexander Duyck wrote:
>
>> Other than that I can't think of too many other ways to modify the
>> EEPROM without actually going in and modifying it yourself. I believe
>> the e1000e
icy
>>
>> * Advanced > Wake On LAN
>>
>> * Advanced > Network Stack Configuration > Ipv4 PXE Support
>>
>> * Advanced > Network Stack Configuration > Ipv6 PXE Support
>>
>> but this did not change the EEPROM damp. I pasted it at the bott
On Tue, Jul 26, 2016 at 3:22 AM, Alexey Muranov
wrote:
>
I executed bootutil64e from Intel Ethernet Connections Boot Utility (
https://downloadcenter.intel.com/download/19186 ) under Ubuntu, here is the
output:
Intel(R) Ethernet Flash Firmware Utility
BootUtil ver
The flash and NVM are two separate items. The flash enables things
like PXE booting and iSCSI whereas the NVM stores things like the
Network Address.
One workaround that you might be able to use would be to just modify
your driver to skip over the loop that actually invokes the NVM check.
If you
On Wed, Jul 20, 2016 at 11:16 PM, Mattias Barthel wrote:
> Hello,
>
> I am using the HW timestamp all RX packets option in the I350 for my
> special application.
> There is a requirement to keep the HW timestamping clock intact if the link
> goes down.
> Now, if the link goes down, the IGB watchdo
On Wed, Jul 20, 2016 at 3:41 AM, wrote:
> From: Zhu Yanjun
>
> With the original enum, when a several bits state is set, it is
> possible that the wrong test occurs.
>
> For example,
>
> a state is 0x3, its bits are 11. When testing a state 0x2 whose
> bits are 10, it is difficult to confirm tha
On Wed, Jul 13, 2016 at 11:53 PM, ayuj wrote:
>> > in a back-to-back senario.
>>
>> Have you tried mapping the priorities to something other than TC 0?
>> I'm thinking that may be part of the issue. In order to use DCB you
>> need to be using multiple traffic classes.
>>
>> One question I would h
On Mon, Jul 11, 2016 at 1:31 AM, ayuj wrote:
> I just checked TLV's. Below are the details:
>
>
> OS :- CentOS 7.2
> kernel 3.10.0-327.el7.x86_64
> lldpad:- lldpad v0.9.46
> dcbtool:- v0.9.46
> ixgbe :- ixgbe-4.3.15
>
> steps followed:-
>
> # modporbe ixgbe
> # service lldpad start
> Redirecti
000:00:1f.6: The NVM Checksum Is Not Valid
> [5.907340] e1000e: probe of :00:1f.6 failed with error -5
>
>
> - Alexey.
>
> On 11 Jul 2016, at 01:11, Alexander Duyck wrote:
>
>> It might be useful if you can provide the dmesg output for your system
>> aft
It might be useful if you can provide the dmesg output for your system
after boot. More often then not when a device doesn't load when the
driver is loaded there is usually something in the error log
indicating an issue such as an EEPROM problem or whatnot. If you
could provide that we can probab
On Sun, Jul 10, 2016 at 2:22 AM, Olivier Doucet wrote:
>
>>On Sat, Jul 9, 2016 at 1:13 AM, Olivier Doucet wrote:
>>> I'm trying to filter ICMP trafic directly on network cards and tried to do
>>> it with ethtool :
>>> $ethtool --config-ntuple eth2 flow-type ether proto 1 action -1
>>> rmgr: Can
On Sat, Jul 9, 2016 at 1:13 AM, Olivier Doucet wrote:
> Hello,
>
> I'm using ixgbe 4.4.6 + ethtool 4.5 and Intel Ethernet controller 82599EB
>
> I'm trying to filter ICMP trafic directly on network cards and tried to do it
> with ethtool :
> $ethtool --config-ntuple eth2 flow-type ether proto 1 a
1 - 100 of 418 matches
Mail list logo
