---------- Forwarded message ----------
From: Welisson <[email protected]>
Date: 2012/6/7
Subject: Re: [E1000-devel] Packet Loss driver igb
To: Bokhan Artem <[email protected]>


Hi Bokhan,
Sorry in delay respond.
To count my packets lost i am use the command ping 192.168.0.2 -s 1024  to
any hosts where see the lost.
My network below,

<--->Upstrean<--> router-edge(this is here)<----->pppoe's servers<----->
customers

P.S: Recently i am update the version kernel to 3.2.19, but not resolved.
The conf. of power manager in Bios this is all Maximun Performance, and
kernel removed options Power Manager, but same thus i have the loss.

ethtool -i eth4
driver: igb
version: 3.2.10-k

firmware-version: 1.5-1
bus-info: 0000:07:00.0

Regards
Welisson


2012/3/4 Bokhan Artem <[email protected]>

>  You do not have any errors at nic. Probably some other hardware loses
> packets. How do you count lost packets? Describe your network.
>
> 04.03.2012 2:24, Welisson пишет:
>
> Sorry Bokhan,
> Following result of command bellow.
>  ethtool -S eth4
> NIC statistics:
>      rx_packets: 7263913628
>      tx_packets: 8747598287
>      rx_bytes: 2464378673600
>      tx_bytes: 8639557156341
>      rx_broadcast: 44878
>      tx_broadcast: 125857
>      rx_multicast: 1806927
>      tx_multicast: 1569245
>      multicast: 1806927
>       collisions: 0
>      rx_crc_errors: 0
>      rx_no_buffer_count: 0
>      rx_missed_errors: 0
>      tx_aborted_errors: 0
>      tx_carrier_errors: 0
>      tx_window_errors: 0
>      tx_abort_late_coll: 0
>      tx_deferred_ok: 0
>      tx_single_coll_ok: 0
>      tx_multi_coll_ok: 0
>      tx_timeout_count: 0
>      rx_long_length_errors: 0
>       rx_short_length_errors: 0
>      rx_align_errors: 0
>      tx_tcp_seg_good: 0
>      tx_tcp_seg_failed: 0
>      rx_flow_control_xon: 0
>      rx_flow_control_xoff: 0
>       tx_flow_control_xon: 0
>      tx_flow_control_xoff: 0
>      rx_long_byte_count: 2464378673600
>      tx_dma_out_of_sync: 0
>      tx_smbus: 0
>      rx_smbus: 0
>      dropped_smbus: 0
>      rx_errors: 0
>      tx_errors: 0
>      tx_dropped: 0
>      rx_length_errors: 0
>      rx_over_errors: 0
>      rx_frame_errors: 0
>      rx_fifo_errors: 0
>       tx_fifo_errors: 0
>      tx_heartbeat_errors: 0
>      tx_queue_0_packets: 28643071
>      tx_queue_0_bytes: 12868911573
>      tx_queue_0_restart: 0
>      tx_queue_1_packets: 1564502044
>      tx_queue_1_bytes: 1572436942978
>      tx_queue_1_restart: 0
>      tx_queue_2_packets: 1250862870
>      tx_queue_2_bytes: 1217175782241
>      tx_queue_2_restart: 0
>      tx_queue_3_packets: 1178214642
>      tx_queue_3_bytes: 1152493173846
>      tx_queue_3_restart: 0
>      tx_queue_4_packets: 1191175728
>      tx_queue_4_bytes: 1177069762738
>      tx_queue_4_restart: 0
>      tx_queue_5_packets: 1195290594
>      tx_queue_5_bytes: 1173186363711
>      tx_queue_5_restart: 0
>      tx_queue_6_packets: 1166480030
>      tx_queue_6_bytes: 1134686878270
>      tx_queue_6_restart: 0
>      tx_queue_7_packets: 1172429314
>      tx_queue_7_bytes: 1159135953772
>      tx_queue_7_restart: 0
>      rx_queue_0_packets: 913225737
>      rx_queue_0_bytes: 301962745937
>      rx_queue_0_drops: 0
>      rx_queue_0_csum_err: 0
>      rx_queue_0_alloc_failed: 0
>      rx_queue_1_packets: 914107009
>      rx_queue_1_bytes: 305308109057
>      rx_queue_1_drops: 0
>      rx_queue_1_csum_err: 0
>      rx_queue_1_alloc_failed: 0
>      rx_queue_2_packets: 884392073
>      rx_queue_2_bytes: 292775571534
>      rx_queue_2_drops: 0
>      rx_queue_2_csum_err: 0
>      rx_queue_2_alloc_failed: 0
>      rx_queue_3_packets: 905867155
>      rx_queue_3_bytes: 304553264988
>      rx_queue_3_drops: 0
>      rx_queue_3_csum_err: 0
>      rx_queue_3_alloc_failed: 0
>      rx_queue_4_packets: 901414852
>      rx_queue_4_bytes: 296216840175
>      rx_queue_4_drops: 0
>      rx_queue_4_csum_err: 0
>      rx_queue_4_alloc_failed: 0
>      rx_queue_5_packets: 906832178
>      rx_queue_5_bytes: 306427939590
>      rx_queue_5_drops: 0
>      rx_queue_5_csum_err: 0
>      rx_queue_5_alloc_failed: 0
>      rx_queue_6_packets: 928393565
>      rx_queue_6_bytes: 323459406099
>      rx_queue_6_drops: 0
>      rx_queue_6_csum_err: 0
>      rx_queue_6_alloc_failed: 0
>      rx_queue_7_packets: 909681064
>      rx_queue_7_bytes: 304619142810
>      rx_queue_7_drops: 0
>      rx_queue_7_csum_err: 0
>      rx_queue_7_alloc_failed: 0
>
>  ethtool -a eth4
> Pause parameters for eth4:
> Autonegotiate: on
> RX: on
> TX: off
>  ethtool -k eth4
> Offload parameters for eth4:
> rx-checksumming: off
> tx-checksumming: off
> scatter-gather: off
> tcp-segmentation-offload: off
> udp-fragmentation-offload: off
> generic-segmentation-offload: off
> generic-receive-offload: off
> large-receive-offload: off
> ntuple-filters: off
> receive-hashing: off
>
>  ethtool -g eth4
> Ring parameters for eth4:
> Pre-set maximums:
> RX: 4096
> RX Mini: 0
> RX Jumbo: 0
> TX: 4096
> Current hardware settings:
> RX: 4096
> RX Mini: 0
> RX Jumbo: 0
> TX: 4096
>
>  ethtool -c eth4
> all values = 0
>
>  still have a packet loss ranging from 1-2%, -s 1024, but at or below 512
> have lost, but is 0%.
> 2012/1/24 Bokhan Artem <[email protected]>
>
>>
>> Btw, check ethtool -S ethX for errors.
>>
>>
>> On 24.01.2012 22:22, Bokhan Artem wrote:
>>
>>> On 24.01.2012 21:58, Welisson wrote:
>>>
>>>> Hi Bokhan,
>>>>
>>>> I tried using the latest version (3.2.10) of the driver, but it does the
>>>> balance between the core so I decided to leave the driver's default
>>>> version of
>>>> ubuntu.
>>>>
>>> By unknown to me reason it is necessary to force that manually sometimes.
>>>
>>> cat /etc/modprobe.d/igb.conf
>>> options igb RSS=4,4 QueuePairs=0,0
>>>
>>> Look "modinfo igb" for help. Dont forget to update initramfs.
>>>
>>> dmesg | grep igb
>>> [    1.641096] igb 0000:01:00.0: PCI INT A ->  GSI 16 (level, low) ->
>>>  IRQ 16
>>> [    1.641117] igb 0000:01:00.0: setting latency timer to 64
>>> [    1.641331] igb: 0000:01:00.0: igb_validate_option: RSS - RSS
>>> multiqueue
>>> receive count set to 4
>>> [    1.641333] igb: 0000:01:00.0: igb_validate_option: QueuePairs -
>>> TX/RX queue
>>> pairs for interrupt handling Disabled
>>> [    1.641373] igb 0000:01:00.0: irq 34 for MSI/MSI-X
>>> [    1.641378] igb 0000:01:00.0: irq 35 for MSI/MSI-X
>>> [    1.641383] igb 0000:01:00.0: irq 36 for MSI/MSI-X
>>> [    1.641388] igb 0000:01:00.0: irq 37 for MSI/MSI-X
>>> [    1.641393] igb 0000:01:00.0: irq 38 for MSI/MSI-X
>>> [    1.641398] igb 0000:01:00.0: irq 39 for MSI/MSI-X
>>> [    1.641404] igb 0000:01:00.0: irq 40 for MSI/MSI-X
>>> [    1.641409] igb 0000:01:00.0: irq 41 for MSI/MSI-X
>>> [    1.641414] igb 0000:01:00.0: irq 42 for MSI/MSI-X
>>> [    1.886555] igb 0000:01:00.0: Intel(R) Gigabit Ethernet Network
>>> Connection
>>> [    1.886558] igb 0000:01:00.0: eth0: (PCIe:2.5GT/s:Width x4)
>>> 00:1b:21:8c:b9:40
>>> [    1.886636] igb 0000:01:00.0: eth0: PBA No: E43709-005
>>> [    1.886638] igb 0000:01:00.0: Using MSI-X interrupts. 4 rx queue(s),
>>> 4 tx
>>> queue(s)
>>> [    1.886654] igb 0000:01:00.1: PCI INT B ->  GSI 17 (level, low) ->
>>>  IRQ 17
>>> [    1.886673] igb 0000:01:00.1: setting latency timer to 64
>>> [    1.886886] igb: 0000:01:00.1: igb_validate_option: RSS - RSS
>>> multiqueue
>>> receive count set to 4
>>> [    1.886888] igb: 0000:01:00.1: igb_validate_option: QueuePairs -
>>> TX/RX queue
>>> pairs for interrupt handling Disabled
>>> [    1.886925] igb 0000:01:00.1: irq 44 for MSI/MSI-X
>>> [    1.886930] igb 0000:01:00.1: irq 45 for MSI/MSI-X
>>> [    1.886935] igb 0000:01:00.1: irq 46 for MSI/MSI-X
>>> [    1.886940] igb 0000:01:00.1: irq 47 for MSI/MSI-X
>>> [    1.886945] igb 0000:01:00.1: irq 48 for MSI/MSI-X
>>> [    1.886950] igb 0000:01:00.1: irq 49 for MSI/MSI-X
>>> [    1.886954] igb 0000:01:00.1: irq 50 for MSI/MSI-X
>>> [    1.886959] igb 0000:01:00.1: irq 51 for MSI/MSI-X
>>> [    1.886964] igb 0000:01:00.1: irq 52 for MSI/MSI-X
>>> [    2.136175] igb 0000:01:00.1: Intel(R) Gigabit Ethernet Network
>>> Connection
>>> [    2.136178] igb 0000:01:00.1: eth1: (PCIe:2.5GT/s:Width x4)
>>> 00:1b:21:8c:b9:41
>>> [    2.136256] igb 0000:01:00.1: eth1: PBA No: E43709-005
>>> [    2.136259] igb 0000:01:00.1: Using MSI-X interrupts. 4 rx queue(s),
>>> 4 tx
>>> queue(s)
>>>
>>>  ls -la /proc/acpi/processor/CPU0/
>>>> total 0
>>>>
>>>>  We have Ubuntu 10.04 LTS with 2.6.32-server kernel version. I do not
>>> know
>>> anything about "/proc/acpi/processor/CPU0/power" in other
>>> distros/kernels. You
>>> may google that or just disable powersaving options in BIOS. I also have
>>> "power
>>> management:        no".
>>>
>>> cat /proc/acpi/processor/CPU0/info
>>> processor id:            0
>>> acpi id:                 1
>>> bus mastering control:   yes
>>> power management:        no
>>> throttling control:      no
>>> limit interface:         no
>>>
>>>
>>>  2012/1/24 Bokhan Artem<[email protected]<mailto:[email protected]>>
>>>>
>>>>     On 24.01.2012 20:09, Welisson wrote:
>>>>
>>>>>     The problema is that when the traffic to up 500 or 700 Mbp/s, i
>>>>> have packet
>>>>>     loss 1% at  3% in my other servers.
>>>>>
>>>>     This resolved similar problem:
>>>>
>>>>     - Update your driver to the last version
>>>>     - Disable C-states other then C0-C1 in bios
>>>>     - Check your driver version supports queues
>>>>     - Check that you have several rx/tx queues spread over all CPU
>>>> cores.
>>>>
>>>>
>>>>     *cat /proc/acpi/processor/CPU0/power*
>>>>
>>>>     active state:            C0
>>>>     max_cstate:              C8
>>>>     maximum allowed latency: 2000000000 usec
>>>>     states:
>>>>         C1:                  type[C1] promotion[--] demotion[--]
>>>> latency[000]
>>>>     usage[00000000] duration[00000000000000000000]
>>>>
>>>>     *modinfo igb*
>>>>
>>>>     filename:       /lib/modules/2.6.32-32-server/kernel/igb/igb.ko
>>>>     version:        3.0.22
>>>>
>>>>     *cat /proc/interrupts  | grep eth0*
>>>>
>>>>      44:          0          0          1          0   PCI-MSI-edge
>>>>  eth0
>>>>      45:  105862872          0          2          0   PCI-MSI-edge
>>>>  eth0-rx-0
>>>>      46:          0  108392651          0          2   PCI-MSI-edge
>>>>  eth0-rx-1
>>>>      47:          0          0  106273251          2   PCI-MSI-edge
>>>>  eth0-rx-2
>>>>      48:          2          0          0  107610662   PCI-MSI-edge
>>>>  eth0-rx-3
>>>>      49:   86453979          0          0          0   PCI-MSI-edge
>>>>  eth0-tx-0
>>>>      50:          0   86477489          0          0   PCI-MSI-edge
>>>>  eth0-tx-1
>>>>      51:          0          2   95241899          0   PCI-MSI-edge
>>>>  eth0-tx-2
>>>>      52:          0          0          2   88540674   PCI-MSI-edge
>>>>  eth0-tx-3
>>>>
>>>>
>>>>
>>>>>     Load average 0.10
>>>>>
>>>>>     Anyone else have this problem, but this does not happen with my
>>>>> broadcom
>>>>>     nic.
>>>>>
>>>>>
>>>>>
>>>>>
>>>>> ------------------------------------------------------------------------------
>>>>>     Keep Your Developer Skills Current with LearnDevNow!
>>>>>     The most comprehensive online learning library for Microsoft
>>>>> developers
>>>>>     is just $99.99! Visual Studio, SharePoint, SQL - plus HTML5, CSS3,
>>>>> MVC3,
>>>>>     Metro Style Apps, more. Free future releases when you subscribe
>>>>> now!
>>>>>     http://p.sf.net/sfu/learndevnow-d2d
>>>>>
>>>>>
>>>>>     _______________________________________________
>>>>>     E1000-devel mailing list
>>>>>     [email protected]<mailto:
>>>>> [email protected]>
>>>>>     https://lists.sourceforge.net/lists/listinfo/e1000-devel
>>>>>     To learn more about Intel&#174; Ethernet, visithttp://
>>>>> communities.intel.com/community/wired
>>>>>
>>>>
>>>>
>>>
>>> ------------------------------------------------------------------------------
>>> Keep Your Developer Skills Current with LearnDevNow!
>>> The most comprehensive online learning library for Microsoft developers
>>> is just $99.99! Visual Studio, SharePoint, SQL - plus HTML5, CSS3, MVC3,
>>> Metro Style Apps, more. Free future releases when you subscribe now!
>>> http://p.sf.net/sfu/learndevnow-d2d
>>> _______________________________________________
>>> E1000-devel mailing list
>>> [email protected]
>>> https://lists.sourceforge.net/lists/listinfo/e1000-devel
>>> To learn more about Intel&#174; Ethernet, visit
>>> http://communities.intel.com/community/wired
>>>
>>
>>
>
>
------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and 
threat landscape has changed and how IT managers can respond. Discussions 
will include endpoint security, mobile security and the latest in malware 
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
E1000-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/e1000-devel
To learn more about Intel&#174; Ethernet, visit 
http://communities.intel.com/community/wired

Reply via email to