Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 08 Aug 2014 21:00:38 -0400
From:      Mike Tancsa <mike@sentex.net>
To:        Jack Vogel <jfvogel@gmail.com>
Cc:        "stable@freebsd.org" <stable@freebsd.org>
Subject:   Re: svn commit: r267935 - head/sys/dev/e1000
Message-ID:  <53E572B6.1090908@sentex.net>
In-Reply-To: <53E536AC.9060304@sentex.net>
References:  <201406262133.s5QLXXP8029811@svn.freebsd.org> <b0afc76e77f28b14683094e1b59a4ccf@eumx.net> <CALCpEUFL26Pg%2BpYoP4KKEAzBsFF8fDunMewy%2BgqwU7o4ob8Zeg@mail.gmail.com> <CAFOYbcnLBW-AUHQx7KMQsxRE_Xy-1_ia2dCY4MeGV_8LWgrHDw@mail.gmail.com> <CAPyFy2AvMf42QGsYDrEb5E6%2Bse8scF9BXcwUugjCtx4t2D8sJA@mail.gmail.com> <CAFOYbc=i%2B=Gv6=_WPcXSo=Ds1Y3mw6mtevPGCxQ5HJPtu55mOw@mail.gmail.com> <20140804212220.GC48614@rancor.immure.com> <CAFOYbc=5wyo%2BbKwxdhsORH6WRRRDZReitL5wrCnp9dgT7qAVrQ@mail.gmail.com> <20140805130144.GF40246@rancor.immure.com> <CAFOYbcmuA1aiDCkHuJK%2B0EfO%2BnfGr4UrnJ7zB1rnPaSJn4AyQA@mail.gmail.com> <53E51D62.9000507@sentex.net> <53E52762.7040300@sentex.net> <53E536AC.9060304@sentex.net>

next in thread | previous in thread | raw e-mail | index | archive | help
On 8/8/2014 4:44 PM, Mike Tancsa wrote:
> On 8/8/2014 3:39 PM, Mike Tancsa wrote:
>> time and then see if disabling msix makes any difference.
>>
>> Debug output post ifconfig down and up shows

disabling msix allows the backup to complete without wedging the nic. 
However, I still ran into an error near the end which was at least 
recoverable on its own.  The speed diffrence is reminiscent of this thread.

http://lists.freebsd.org/pipermail/freebsd-stable/2014-June/079119.html

normally, a level zero dump would blast across at ~ 100Mb.  With msix 
disabled, I was able to average 700Mb on this particular NIC.


Aug  8 18:23:58 zoo kernel: em0: Watchdog timeout -- resetting
Aug  8 18:23:58 zoo kernel: em0: Queue(0) tdh = 158, hw tdt = 118
Aug  8 18:23:58 zoo kernel: em0: TX(0) desc avail = 31,Next TX to Clean 
= 149
Aug  8 18:23:58 zoo kernel: em0: link state changed to DOWN
Aug  8 18:24:02 zoo kernel: em0: link state changed to UP
Aug  8 18:24:06 zoo kernel: newnfs server 
192.168.x.x:/zbackup1/zoobackup: is alive again
Aug  8 18:24:07 zoo last message repeated 19 times


jhb, this box is zoo.freebsd.org in case you are curious.

	---Mike



>>
>>
>> Interface is RUNNING and ACTIVE
>> em0: hw tdh = 947, hw tdt = 947
>> em0: hw rdh = 97, hw rdt = 96
>> em0: Tx Queue Status = 0
>> em0: TX descriptors avail = 1024
>> em0: Tx Descriptors avail failure = 50
>> em0: RX discarded packets = 0
>> em0: RX Next to Check = 97
>> em0: RX Next to Refresh = 96
>
> And while in a hung state, the nic thinks its still active and
> forwarding.  I am going to see if disabling msi-x has any help here. If
> not, I will roll back the driver for now.
>
> Aug  8 16:42:21 zoo kernel: Interface is RUNNING and ACTIVE
> Aug  8 16:42:21 zoo kernel: em0: hw tdh = 411, hw tdt = 134
> Aug  8 16:42:21 zoo kernel: em0: hw rdh = 688, hw rdt = 687
> Aug  8 16:42:21 zoo kernel: em0: Tx Queue Status = 1
> Aug  8 16:42:21 zoo kernel: em0: TX descriptors avail = 261
> Aug  8 16:42:21 zoo kernel: em0: Tx Descriptors avail failure = 50
> Aug  8 16:42:21 zoo kernel: em0: RX discarded packets = 0
> Aug  8 16:42:21 zoo kernel: em0: RX Next to Check = 688
> Aug  8 16:42:21 zoo kernel: em0: RX Next to Refresh = 687
> dev.em.0.%desc: Intel(R) PRO/1000 Network Connection 7.4.2
> dev.em.0.%driver: em
> dev.em.0.%location: slot=0 function=0
> dev.em.0.%pnpinfo: vendor=0x8086 device=0x10d3 subvendor=0x8086
> subdevice=0xa01f class=0x020000
> dev.em.0.%parent: pci4
> dev.em.0.nvm: -1
> dev.em.0.debug: -1
> dev.em.0.fc: 3
> dev.em.0.rx_int_delay: 0
> dev.em.0.tx_int_delay: 66
> dev.em.0.rx_abs_int_delay: 66
> dev.em.0.tx_abs_int_delay: 66
> dev.em.0.itr: 488
> dev.em.0.rx_processing_limit: 100
> dev.em.0.eee_control: 1
> dev.em.0.link_irq: 8266
> dev.em.0.mbuf_alloc_fail: 0
> dev.em.0.cluster_alloc_fail: 0
> dev.em.0.dropped: 0
> dev.em.0.tx_dma_fail: 0
> dev.em.0.rx_overruns: 0
> dev.em.0.watchdog_timeouts: 1
> dev.em.0.device_control: 1477444168
> dev.em.0.rx_control: 67141634
> dev.em.0.fc_high_water: 18432
> dev.em.0.fc_low_water: 16932
> dev.em.0.queue0.txd_head: 411
> dev.em.0.queue0.txd_tail: 142
> dev.em.0.queue0.tx_irq: 833840
> dev.em.0.queue0.no_desc_avail: 50
> dev.em.0.queue0.rxd_head: 688
> dev.em.0.queue0.rxd_tail: 687
> dev.em.0.queue0.rx_irq: 1567748
> dev.em.0.mac_stats.excess_coll: 0
> dev.em.0.mac_stats.single_coll: 0
> dev.em.0.mac_stats.multiple_coll: 0
> dev.em.0.mac_stats.late_coll: 0
> dev.em.0.mac_stats.collision_count: 0
> dev.em.0.mac_stats.symbol_errors: 0
> dev.em.0.mac_stats.sequence_errors: 0
> dev.em.0.mac_stats.defer_count: 0
> dev.em.0.mac_stats.missed_packets: 8290
> dev.em.0.mac_stats.recv_no_buff: 0
> dev.em.0.mac_stats.recv_undersize: 0
> dev.em.0.mac_stats.recv_fragmented: 0
> dev.em.0.mac_stats.recv_oversize: 0
> dev.em.0.mac_stats.recv_jabber: 0
> dev.em.0.mac_stats.recv_errs: 0
> dev.em.0.mac_stats.crc_errs: 0
> dev.em.0.mac_stats.alignment_errs: 0
> dev.em.0.mac_stats.coll_ext_errs: 0
> dev.em.0.mac_stats.xon_recvd: 0
> dev.em.0.mac_stats.xon_txd: 0
> dev.em.0.mac_stats.xoff_recvd: 0
> dev.em.0.mac_stats.xoff_txd: 0
> dev.em.0.mac_stats.total_pkts_recvd: 7512226
> dev.em.0.mac_stats.good_pkts_recvd: 7503936
> dev.em.0.mac_stats.bcast_pkts_recvd: 3120
> dev.em.0.mac_stats.mcast_pkts_recvd: 8
> dev.em.0.mac_stats.rx_frames_64: 3190
> dev.em.0.mac_stats.rx_frames_65_127: 7070773
> dev.em.0.mac_stats.rx_frames_128_255: 337062
> dev.em.0.mac_stats.rx_frames_256_511: 1073
> dev.em.0.mac_stats.rx_frames_512_1023: 1483
> dev.em.0.mac_stats.rx_frames_1024_1522: 90355
> dev.em.0.mac_stats.good_octets_recvd: 711645613
> dev.em.0.mac_stats.good_octets_txd: 21278718407
> dev.em.0.mac_stats.total_pkts_txd: 14406827
> dev.em.0.mac_stats.good_pkts_txd: 14406827
> dev.em.0.mac_stats.bcast_pkts_txd: 65
> dev.em.0.mac_stats.mcast_pkts_txd: 11
> dev.em.0.mac_stats.tx_frames_64: 421
> dev.em.0.mac_stats.tx_frames_65_127: 183151
> dev.em.0.mac_stats.tx_frames_128_255: 28761
> dev.em.0.mac_stats.tx_frames_256_511: 10267
> dev.em.0.mac_stats.tx_frames_512_1023: 289241
> dev.em.0.mac_stats.tx_frames_1024_1522: 13894986
> dev.em.0.mac_stats.tso_txd: 1322639
> dev.em.0.mac_stats.tso_ctx_fail: 0
> dev.em.0.interrupts.asserts: 71
> dev.em.0.interrupts.rx_pkt_timer: 0
> dev.em.0.interrupts.rx_abs_timer: 0
> dev.em.0.interrupts.tx_pkt_timer: 0
> dev.em.0.interrupts.tx_abs_timer: 0
> dev.em.0.interrupts.tx_queue_empty: 0
> dev.em.0.interrupts.tx_queue_min_thresh: 0
> dev.em.0.interrupts.rx_desc_min_thresh: 0
> dev.em.0.interrupts.rx_overrun: 1
>
>
> 0-zoo-# ifconfig em0 down
> 0-zoo-# ifconfig em0 up
> 0-zoo-# sysctl -a dev.em.0.debug=1
> 0-zoo-# Interface is RUNNING and ACTIVE
> em0: hw tdh = 1017, hw tdt = 1017
> em0: hw rdh = 462, hw rdt = 461
> em0: Tx Queue Status = 0
> em0: TX descriptors avail = 1024
> em0: Tx Descriptors avail failure = 50
> em0: RX discarded packets = 0
> em0: RX Next to Check = 462
> em0: RX Next to Refresh = 461
>
>
>
>
>


-- 
-------------------
Mike Tancsa, tel +1 519 651 3400
Sentex Communications, mike@sentex.net
Providing Internet services since 1994 www.sentex.net
Cambridge, Ontario Canada   http://www.tancsa.com/



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?53E572B6.1090908>