| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <alpine.LRH.2.11.1407111119290.20203@diagnostix.dwd.de>
Date: Fri, 11 Jul 2014 12:03:06 +0000 (UTC)
From: Holger Kiehl <Holger.Kiehl@....de>
To: Shahed Shaikh <shahed.shaikh@...gic.com>
cc: netdev <netdev@...r.kernel.org>,
Dept-HSG Linux NIC Dev <Dept-HSGLinuxNICDev@...gic.com>
Subject: RE: qlcnic very high TX values, as of 3.13.x
Hello Shahed,
first thank you for the very quick reply!
On Fri, 11 Jul 2014, Shahed Shaikh wrote:
>> -----Original Message-----
>> From: netdev-owner@...r.kernel.org [mailto:netdev-
>> owner@...r.kernel.org] On Behalf Of Holger Kiehl
>> Sent: Friday, July 11, 2014 2:43 PM
>> To: netdev
>> Subject: qlcnic very high TX values, as of 3.13.x
>>
>> Hello,
>
> Hi Holger,
>
>>
>> upgrading from 3.10.x to the next stable series 3.14.x I noticed that ifconfig
>> reports very high TX values. Taking the qlcnic source from
>> 3.15.5 and compile it under 3.14.12, the problem remains. Going backwards
>> always just copying the qlcnic source from the older kernels to the 3.14.12
>> tree, I noticed that the 3.12.x kernel was the last version that does not
>> generate those high TX values. So the problem started with the qlcnic driver
>> in 3.13.x. However, comparing 3.13.x and 3.14.x the numbers go higher in
>> 3.14.x much quicker. In 3.14.x I get TX values in Terabytes very quickly after
>> boot. I once even got Petabyte values!
>
> Can you please provide qlcnic driver version used in 3.12.x?
> Please use "ethtool -i ethX" to get this info.
>
driver: qlcnic
version: 5.3.50
firmware-version: 4.14.26
bus-info: 0000:1a:00.0
supports-statistics: yes
supports-test: yes
supports-eeprom-access: yes
supports-register-dump: yes
supports-priv-flags: no
> Also, can you please provide driver statistics o/p with both kernels (3.12.x and 3.14.x).
> Please use "ethtool -S ethX" command to collect driver statistics.
> This would tell us if QLogic adapter indeed sent huge traffic or it's a bug in Tx statistics as part of ifconfig command.
>
Here the statistics for 3.12.x driver (several hours active):
NIC statistics:
tx_ring_0 xmit_on: 0
tx_ring_0 xmit_off: 0
tx_ring_0 xmit_called: 1442286
tx_ring_0 xmit_finished: 1442286
tx_ring_1 xmit_on: 0
tx_ring_1 xmit_off: 0
tx_ring_1 xmit_called: 3723601
tx_ring_1 xmit_finished: 3723601
tx_ring_2 xmit_on: 0
tx_ring_2 xmit_off: 0
tx_ring_2 xmit_called: 1834668
tx_ring_2 xmit_finished: 1834668
tx_ring_3 xmit_on: 0
tx_ring_3 xmit_off: 0
tx_ring_3 xmit_called: 1912342
tx_ring_3 xmit_finished: 1912342
xmit_called: 8908221
xmit_finished: 8912897
rx_dropped: 0
tx_dropped: 0
csummed: 30901897
rx_pkts: 28205500
lro_pkts: 2730164
rx_bytes: 7086023644
tx_bytes: 100481331016
lrobytes: 17026517020
lso_frames: 5596745
xmit_on: 0
xmit_off: 0
skb_alloc_failure: 0
null rxbuf: 0
rx dma map error: 0
tx dma map error: 0
mac_filter_limit_overrun: 0
spurious intr: 0
mac_tx_frames: 71784854
mac_tx_bytes: 104815920774
mac_tx_mcast_pkts: 0
mac_tx_bcast_pkts: 0
mac_tx_pause_cnt: 0
mac_tx_ctrl_pkt: 0
mac_tx_lt_64b_pkts: 0
mac_tx_lt_127b_pkts: 0
mac_tx_lt_255b_pkts: 0
mac_tx_lt_511b_pkts: 0
mac_tx_lt_1023b_pkts: 0
mac_tx_lt_1518b_pkts: 0
mac_tx_gt_1518b_pkts: 0
mac_rx_frames: 40264667
mac_rx_bytes: 24815536295
mac_rx_mcast_pkts: 115503
mac_rx_bcast_pkts: 0
mac_rx_pause_cnt: 0
mac_rx_ctrl_pkt: 0
And here the statistics for 3.14.x driver (several minutes active):
NIC statistics:
tx_queue_0 xmit_on: 0
tx_queue_0 xmit_off: 0
tx_queue_0 xmit_called: 70828
tx_queue_0 xmit_finished: 70828
tx_queue_0 tx_bytes: 9745074
tx_queue_1 xmit_on: 0
tx_queue_1 xmit_off: 0
tx_queue_1 xmit_called: 10177
tx_queue_1 xmit_finished: 10177
tx_queue_1 tx_bytes: 3113256
tx_queue_2 xmit_on: 0
tx_queue_2 xmit_off: 0
tx_queue_2 xmit_called: 144260
tx_queue_2 xmit_finished: 144260
tx_queue_2 tx_bytes: 20228745
tx_queue_3 xmit_on: 0
tx_queue_3 xmit_off: 0
tx_queue_3 xmit_called: 7772
tx_queue_3 xmit_finished: 7772
tx_queue_3 tx_bytes: 1633447
xmit_on: 0
xmit_off: 0
xmit_called: 232147086
xmit_finished: 232145654
tx dma map error: 0
tx_bytes: 34305725918
tx_dropped: 0
rx dma map error: 0
rx_pkts: 811052
rx_bytes: 1120370109
rx_dropped: 0
null rxbuf: 0
csummed: 809679
lro_pkts: 0
lrobytes: 0
lso_frames: 743
skb_alloc_failure: 0
mac_filter_limit_overrun: 0
spurious intr: 0
mac_tx_frames: 235650
mac_tx_bytes: 35821610
mac_tx_mcast_pkts: 0
mac_tx_bcast_pkts: 0
mac_tx_pause_cnt: 0
mac_tx_ctrl_pkt: 0
mac_tx_lt_64b_pkts: 0
mac_tx_lt_127b_pkts: 0
mac_tx_lt_255b_pkts: 0
mac_tx_lt_511b_pkts: 0
mac_tx_lt_1023b_pkts: 0
mac_tx_lt_1518b_pkts: 0
mac_tx_gt_1518b_pkts: 0
mac_rx_frames: 828024
mac_rx_bytes: 1122192441
mac_rx_mcast_pkts: 16903
mac_rx_bcast_pkts: 0
mac_rx_pause_cnt: 0
mac_rx_ctrl_pkt: 0
mac_rx_lt_64b_pkts: 0
mac_rx_lt_127b_pkts: 0
mac_rx_lt_255b_pkts: 0
mac_rx_lt_511b_pkts: 0
mac_rx_lt_1023b_pkts: 0
mac_rx_lt_1518b_pkts: 0
mac_rx_gt_1518b_pkts: 0
mac_rx_length_error: 0
mac_rx_length_small: 0
mac_rx_length_large: 0
mac_rx_jabber: 0
mac_rx_dropped: 2
mac_crc_error: 0
mac_align_error: 0
eswitch_frames: 0
eswitch_bytes: 0
eswitch_multicast_frames: 0
eswitch_broadcast_frames: 0
eswitch_unicast_frames: 0
eswitch_error_free_frames: 0
eswitch_error_free_bytes: 0
Here just for completnes the output of ethtool -i with 3.14 driver:
driver: qlcnic
version: 5.3.55
firmware-version: 4.14.26
bus-info: 0000:1a:00.0
supports-statistics: yes
supports-test: yes
supports-eeprom-access: yes
supports-register-dump: yes
supports-priv-flags: no
I am quite shure that there is no traffic going out, since I can see
this with my distribution software running there (ifconfig reports
30 GiB, my software under 1 MB).
Thank you for looking into this!
Regards,
Holger
> Thanks,
> Shahed
>>
>> Hardware is the following:
>>
>> HP ProLiant DL380 G7
>> 2 x Intel Xeon X5690 (24 cores with hypertreading)
>> 106 GByte Ram
>> 1 x NC523SFP 10Gb 2-port Server Adapter Board Chip rev 0x54 (qlcnic)
>> 1 x Intel Corporation 82599ES 10-Gigabit SFI/SFP+ Network Connection
>> (ixgbe)
>>
>> The qlcnic and ixgbe cards are bonded together in fault-tolerance
>> (active-backup) mode. And even when I switch to the Intel card, after I get
>> crazy TX values on qlcnic card, the TX vaules on this card still go up at a very
>> quick rate. This only stops when I reset the card (reload the module). Also,
>> there is no differnce if I compile the driver in or use it as module. There are
>> no strange messages in /var/log/messages or dmesg. Here the output with
>> the 3.13.x driver in
>> 3.14.12 when system boots:
>>
>> [ 18.229195] QLogic 1/10 GbE Converged/Intelligent Ethernet Driver
>> v5.3.52
>> [ 18.229415] qlcnic 0000:1a:00.0: 2048KB memory map
>> [ 18.854134] qlcnic 0000:1a:00.0: Default minidump capture mask 0x1f
>> [ 19.602491] qlcnic 0000:1a:00.0: FW dump enabled
>> [ 19.631257] qlcnic 0000:1a:00.0: Supports FW dump capability
>> [ 19.667072] qlcnic 0000:1a:00.0: Driver v5.3.52, firmware v4.14.26
>> [ 19.704279] qlcnic 0000:1a:00.0: Set 4 Tx rings
>> [ 19.733001] qlcnic 0000:1a:00.0: Set 4 SDS rings
>> [ 19.898808] qlcnic: 2c:27:d7:50:04:48: NC523SFP 10Gb 2-port Server
>> Adapter Board Chip rev 0x54
>> [ 19.949325] qlcnic 0000:1a:00.0: irq 129 for MSI/MSI-X
>> [ 19.949329] qlcnic 0000:1a:00.0: irq 130 for MSI/MSI-X
>> [ 19.949333] qlcnic 0000:1a:00.0: irq 131 for MSI/MSI-X
>> [ 19.949336] qlcnic 0000:1a:00.0: irq 132 for MSI/MSI-X
>> [ 19.949340] qlcnic 0000:1a:00.0: irq 133 for MSI/MSI-X
>> [ 19.949343] qlcnic 0000:1a:00.0: irq 134 for MSI/MSI-X
>> [ 19.949347] qlcnic 0000:1a:00.0: irq 135 for MSI/MSI-X
>> [ 19.949350] qlcnic 0000:1a:00.0: irq 136 for MSI/MSI-X
>> [ 19.949369] qlcnic 0000:1a:00.0: using msi-x interrupts
>> [ 19.982782] qlcnic 0000:1a:00.0: Set 4 Tx queues
>> [ 20.055099] qlcnic 0000:1a:00.0: eth2: XGbE port initialized
>> [ 20.090408] qlcnic 0000:1a:00.1: 2048KB memory map
>> [ 20.179836] qlcnic 0000:1a:00.1: Default minidump capture mask 0x1f
>> [ 20.217848] qlcnic 0000:1a:00.1: FW dump enabled
>> [ 20.246979] qlcnic 0000:1a:00.1: Supports FW dump capability
>> [ 20.282318] qlcnic 0000:1a:00.1: Driver v5.3.52, firmware v4.14.26
>> [ 20.320238] qlcnic 0000:1a:00.1: Set 4 Tx rings
>> [ 20.350038] qlcnic 0000:1a:00.1: Set 4 SDS rings
>> [ 20.429714] qlcnic 0000:1a:00.1: irq 137 for MSI/MSI-X
>> [ 20.429718] qlcnic 0000:1a:00.1: irq 138 for MSI/MSI-X
>> [ 20.429722] qlcnic 0000:1a:00.1: irq 139 for MSI/MSI-X
>> [ 20.429726] qlcnic 0000:1a:00.1: irq 140 for MSI/MSI-X
>> [ 20.429729] qlcnic 0000:1a:00.1: irq 141 for MSI/MSI-X
>> [ 20.429732] qlcnic 0000:1a:00.1: irq 142 for MSI/MSI-X
>> [ 20.429736] qlcnic 0000:1a:00.1: irq 143 for MSI/MSI-X
>> [ 20.429739] qlcnic 0000:1a:00.1: irq 144 for MSI/MSI-X
>> [ 20.429757] qlcnic 0000:1a:00.1: using msi-x interrupts
>> [ 20.458895] qlcnic 0000:1a:00.1: Set 4 Tx queues
>> [ 20.486907] qlcnic 0000:1a:00.1: eth3: XGbE port initialized
>>
>> My kernel config can be downloaded here:
>>
>> ftp://ftp.dwd.de/pub/afd/test/.config
>>
>> Please, just ask if I need to provide more details and please CC me, since I am
>> not on the list.
>>
>> Thanks,
>> Holger
>> --
>> To unsubscribe from this list: send the line "unsubscribe netdev" in the body
>> of a message to majordomo@...r.kernel.org More majordomo info at
>> http://vger.kernel.org/majordomo-info.html
>
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists