NIC Flapping problem?
Aaron_Patten at Dell.com
Aaron_Patten at Dell.com
Fri Jun 16 09:30:29 CDT 2006
Peter,
When the machine hangs do you get a kernel panic?
If so could you please share it?
Also, what type of server are you running into this issue on?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Aaron Patten
Support Senior Analyst
Dell Enterprise Expert Center
MCP, CNA 5.1, DCNP, DCSP
EMC Proven Professional Associate
Aaron_Patten at dell.com
Work Hours: Monday - Friday 8:00 am to 5:00 pm CST
-----Original Message-----
From: linux-poweredge-bounces at dell.com
[mailto:linux-poweredge-bounces at dell.com] On Behalf Of
linux-poweredge-request at dell.com
Sent: Friday, June 16, 2006 6:00 AM
To: linux-poweredge-Lists
Subject: Linux-PowerEdge Digest, Vol 20, Issue 31
Send Linux-PowerEdge mailing list submissions to
linux-poweredge at dell.com
To subscribe or unsubscribe via the World Wide Web, visit
http://lists.us.dell.com/mailman/listinfo/linux-poweredge
or, via email, send a message with subject or body 'help' to
linux-poweredge-request at dell.com
You can reach the person managing the list at
linux-poweredge-owner at dell.com
When replying, please edit your Subject line so it is more specific than
"Re: Contents of Linux-PowerEdge digest..."
Today's Topics:
1. RE: NIC Flapping problem? (Peter.Talmadge at CyberTools.biz)
2. Re: aacraid and extremeley high iowait (r levins)
3. Re: IPMI on Fedora Core 5 on a PE SC430? (Jason Edgecombe)
4. Recreation of utility partition (Andrew D. Fant)
5. LTO tape drive speed slow on Redhat 4 (mcclnx mcc)
6. Re: LTO tape drive speed slow on Redhat 4 (Pauli Borodulin)
7. PERC5 and linux 2.4.x (Giulio Orsero)
----------------------------------------------------------------------
Message: 1
Date: Thu, 15 Jun 2006 14:24:07 -0400
From: Peter.Talmadge at CyberTools.biz
Subject: RE: NIC Flapping problem?
To: linux-poweredge at dell.com
Message-ID: <6.2.3.4.2.20060615142048.04017d60 at 66.189.86.251>
Content-Type: text/plain; charset="us-ascii"; format=flowed
Yes, we have checked and replaced all cables. They should be good.
At 01:48 PM 6/15/2006, Fred Skrotzki wrote:
>
>It also looks like it could be a cabling problem. Have you switched
>out the cable?
>
>-----Original Message-----
>From: linux-poweredge-bounces at dell.com
>[mailto:linux-poweredge-bounces at dell.com] On Behalf Of Yaman Saqqa
>Sent: Thursday, June 15, 2006 10:01 AM
>To: Peter.Talmadge at cybertools.biz
>Cc: linux-poweredge at dell.com
>Subject: Re: NIC Flapping problem?
>
>Try turning tso off. It worked for me.
>ethtool -K eth0 tso off
>
>Peter.Talmadge at cybertools.biz wrote:
> > Hi all,
> >
> > Sometimes our NIC will drop connection for no apparent reason, and
> > usually shortly thereafter come back online. However sometimes it
> > will freeze up the machine.
> >
> > We have tried many hardware solutions including switching out the
> > NIC's, switching the firewall and switch devices, and even switching
> > out the motherboard which had an onboard Gb card. Nothing seems to
> > cure it, and we never had these problems prior to upgrading to RHEL4
> > from RedHat 9.
> >
> > Our latest effort is to slow down the NIC to 100Mb. We have set the
> > card to 100Mb/full duplex/autonegotiation off. However, we have had
> > the NIC hang on us again yesterday. In the /var/log/messages file,
> > as
>
> > usual there is message like:
> >
> > Jun 14 12:30:19 maple kernel: NETDEV WATCHDOG: eth0: transmit
>timed out
> > Jun 14 12:30:23 maple kernel: e1000: eth0: e1000_watchdog: NIC
>Link
> > is Up 100 Mbps Full Duplex
> >
> > We are running a FortiGate60 firewall, and a D-Link Gigabit switch
> > that after this incident has been replaced by a Dell PowerConnect
> > 2708. The server is a PowerEdge 2650. I have tried to include some
> > diagnostics that might help below. Any help would be appreciated.
> > One other question, is this the official place to get the latest
> > e1000
>
> > driver version http://sourceforge.net/projects/e1000, and would it
> > help to update the driver?
> >
> > ethtools -S eth0:
> >
> > NIC statistics:
> > rx_packets: 47386363
> > tx_packets: 88662955
> > rx_bytes: 4111506176
> > tx_bytes: 2296849700
> > rx_errors: 39526
> > tx_errors: 0
> > rx_dropped: 0
> > tx_dropped: 0
> > multicast: 0
> > collisions: 0
> > rx_length_errors: 19930
> > rx_over_errors: 0
> > rx_crc_errors: 12476
> > rx_frame_errors: 7003
> > rx_fifo_errors: 117
> > rx_no_buffer_count: 0
> > rx_missed_errors: 117
> > tx_aborted_errors: 0
> > tx_carrier_errors: 0
> > tx_fifo_errors: 0
> > tx_heartbeat_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
> > rx_long_length_errors: 0
> > rx_short_length_errors: 0
> > rx_align_errors: 7003
> > tx_tcp_seg_good: 595533
> > 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: 4111506176
> > rx_csum_offload_good: 47135867
> > rx_csum_offload_errors: 52
> >
> > lspci -vv:
> >
> > 03:01.0 Ethernet controller: Intel Corporation 82544GC Gigabit
> > Ethernet Controller (LOM) (rev 02)
> > Subsystem: Dell PRO/1000 XT Network Connection
> > Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV+ VGASnoop-
> > ParErr- Stepping- SERR+ FastB2B-
> > Status: Cap+ 66Mhz+ UDF- FastB2B- ParErr- DEVSEL=medium
> > >TAbort- <TAbort- <MAbort- >SERR- <PERR-
> > Latency: 64 (63750ns min), Cache Line Size 10
> > Interrupt: pin A routed to IRQ 5
> > Region 0: Memory at fdae0000 (64-bit, non-prefetchable)
>[size=128K]
> > Region 2: Memory at fdac0000 (64-bit, non-prefetchable)
>[size=128K]
> > Region 4: I/O ports at dce0 [size=32]
> > Expansion ROM at fdb00000 [disabled] [size=128K]
> > Capabilities: [dc] Power Management version 2
> > Flags: PMEClk- DSI+ D1- D2- AuxCurrent=0mA
> > PME(D0+,D1-,D2-,D3hot+,D3cold+)
> > Status: D0 PME-Enable- DSel=0 DScale=1 PME-
> > Capabilities: [e4] PCI-X non-bridge device.
> > Command: DPERE- ERO+ RBC=0 OST=0
> > Status: Bus=3 Dev=1 Func=0 64bit+ 133MHz+ SCD-
> > USC-, DC=simple, DMMRBC=2, DMOST=0, DMCRS=1, RSCEM-
> > Capabilities: [f0] Message Signalled Interrupts: 64bit+
> > Queue=0/0 Enable-
> > Address: 0000000000000000 Data: 0000
> >
> > ifconfig:
> >
> > eth0 Link encap:Ethernet HWaddr 00:06:5B:F3:ED:9E
> > inet addr:10.10.10.67 Bcast:10.10.10.255
>Mask:255.255.255.0
> > inet6 addr: fe80::206:5bff:fef3:ed9e/64 Scope:Link
> > UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
> > RX packets:47388158 errors:39547 dropped:117 overruns:117
> > frame:39430
> > TX packets:88664487 errors:0 dropped:0 overruns:0
carrier:0
> > collisions:0 txqueuelen:1000
> > RX bytes:4111761171 (3.8 GiB) TX bytes:2297142353 (2.1
>GiB)
> > Base address:0xdce0 Memory:fdae0000-fdb00000
> >
> > _______________________________________________
> > Linux-PowerEdge mailing list
> > Linux-PowerEdge at dell.com
> > http://lists.us.dell.com/mailman/listinfo/linux-poweredge
> > Please read the FAQ at http://lists.us.dell.com/faq
> >
> >
>
>--
>yaman w saqqa
>sr_unix_administrator
>
>Integrant Inc.
>
>e ysaqqa at integrant.com.jo
>v 1 310 601-7486 x109 San Diego
>v 962 6 565-1762 x109 Amman
>
>_______________________________________________
>Linux-PowerEdge mailing list
>Linux-PowerEdge at dell.com
>http://lists.us.dell.com/mailman/listinfo/linux-poweredge
>Please read the FAQ at http://lists.us.dell.com/faq
>
>_______________________________________________
>Linux-PowerEdge mailing list
>Linux-PowerEdge at dell.com
>http://lists.us.dell.com/mailman/listinfo/linux-poweredge
>Please read the FAQ at http://lists.us.dell.com/faq
------------------------------
Message: 2
Date: Thu, 15 Jun 2006 18:40:53 +0000
From: "r levins" <rlevins at hotmail.com>
Subject: Re: aacraid and extremeley high iowait
To: smooge at gmail.com
Cc: linux-poweredge at dell.com
Message-ID: <BAY101-F10106AFA6C7EE4796E9037B6820 at phx.gbl>
Content-Type: text/plain; format=flowed
I also have similar problem with similar setup. I have CERC 1.5 / 6 ch
raid controller and it performs very poorly. Other than io waits the
capacity itself of this controller is poor. I am able to achieve at the
most 100 MB/second and that too with RAID 0.
>From: "Stephen John Smoogen" <smooge at gmail.com>
>CC: "linux-poweredge at dell.com" <linux-poweredge at dell.com>
>Subject: Re: aacraid and extremeley high iowait
>Date: Thu, 15 Jun 2006 12:14:38 -0600
>
>On 6/15/06, Kris Doosje <k.doosje at nido.nl> wrote:
> > I have the same problem on a PowerEdge 1800. I'm running Red Hat
>Enterprise AS 3 on the machine. In the machine are 6 SATA disks (80GB).
>Two raid arrays are configured: 2 disks in a RAID1, and 4 disks in a
RAID1+0.
>When I read or write a large amount of data, IOwait reaches values
>around 100% and the system becomes very, very slow.
> >
> > Because of this, the machine is almost not used at the moment, which
> > is
>a shame because it should be a very powerfull machine! Hopefully
>there's a solution to this problem..
> >
>
>I have talked to techs who have seen these issues with aacraid
>controllers. Some got acceptable performance with a BIOS updates to the
>system. The others just went with other hardware controllers and swore
>never to touch an aac again. The problems seemed to not be with the
>driver but with the controller itself under certain loads (they could
>simulate the same large waits with windows).
>
>
>--
>Stephen J Smoogen.
>CSIRT/Linux System Administrator
>
>_______________________________________________
>Linux-PowerEdge mailing list
>Linux-PowerEdge at dell.com
>http://lists.us.dell.com/mailman/listinfo/linux-poweredge
>Please read the FAQ at http://lists.us.dell.com/faq
_________________________________________________________________
Express yourself instantly with MSN Messenger! Download today - it's
FREE!
http://messenger.msn.click-url.com/go/onm00200471ave/direct/01/
------------------------------
Message: 3
Date: Thu, 15 Jun 2006 14:41:28 -0400
From: Jason Edgecombe <jedgecombe at carolina.rr.com>
Subject: Re: IPMI on Fedora Core 5 on a PE SC430?
To: John_Hull at dell.com
Cc: linux-poweredge at lists.us.dell.com
Message-ID: <4491A9D8.80904 at carolina.rr.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Are there any temperature sensors on the SC430?
If so, are they linux-accessible?
Thanks,
Jason
John_Hull at dell.com wrote:
> That's a good point on the 1425SC. For certain, though, the SC430 does
> not have one.
>
>
>> -----Original Message-----
>> From: Fred Skrotzki [mailto:fskrotzki at textwise.com]
>> Sent: Thursday, June 15, 2006 1:07 PM
>> To: Hull, John; linux-poweredge-Lists
>> Subject: RE: IPMI on Fedora Core 5 on a PE SC430?
>>
>> Not the case exactly. The 1425SC has a BMC on the motherboard and
>> OpenIPMI works great on that. We have not tested it with FC5 yet.
>>
>> -----Original Message-----
>> From: linux-poweredge-bounces at dell.com
>> [mailto:linux-poweredge-bounces at dell.com] On Behalf Of
>> John_Hull at dell.com
>> Sent: Thursday, June 15, 2006 1:50 PM
>> To: jedgecombe at carolina.rr.com; linux-poweredge at lists.us.dell.com
>> Subject: RE: IPMI on Fedora Core 5 on a PE SC430?
>>
>> You need to have a system with a Baseboard Management Controller
>> (BMC) included on the motherboard to use OpenIPMI.
>> None of the PowerEdge SC systems have one
>>
>>
>>> -----Original Message-----
>>> From: linux-poweredge-bounces at dell.com
>>> [mailto:linux-poweredge-bounces at dell.com] On Behalf Of
>>>
>> Jason Edgecombe
>>
>>> Sent: Thursday, June 15, 2006 12:42 PM
>>> To: linux-poweredge-Lists
>>> Subject: IPMI on Fedora Core 5 on a PE SC430?
>>>
>>> hi,
>>>
>>> I need to monitor the temperature sensors on a PowerEdge SC430. I'm
>>> running Fedora core 5 on it.
>>>
>>> I understand that I need to use IPMI for this. I install
>>>
>> the standard
>>
>>> OpenIPMI rpms via yum, but the kernel modules won't load.
>>> # modprobe ipmi_si
>>> FATAL: Error inserting ipmi_si
>>> (/lib/modules/2.6.16-1.2133_FC5smp/kernel/drivers/char/ipmi/ip
>>> mi_si.ko):
>>> No such device
>>>
>>> Im running kernel 2.6.16-1.2133_FC5smp.
>>>
>>> I've been a linux guy for 10+ years, but I'm an IPMI newbie.
>>> Any tips on getting this running would be appreciated.
>>>
>>> I've looked for a manual, but all I've found are the IPMI
>>>
>> specs which
>>
>>> aren't helpful.
>>>
>>> Thanks,
>>> Jason
>>>
------------------------------
Message: 4
Date: Thu, 15 Jun 2006 16:35:33 -0400
From: "Andrew D. Fant" <andrew.fant at tufts.edu>
Subject: Recreation of utility partition
To: linux-poweredge at dell.com
Message-ID: <4491C495.30300 at tufts.edu>
Content-Type: text/plain; charset=ISO-8859-1
Is there any good way to create/recreate the utility partition on a
power-edge server without having to boot and install the os under the
server assistant CD?
Thanks
--
Andrew Fant | The lion and the calf shall lie | Disclaimer:
andrew.fant at tufts.edu | down together, but the calf won't | Do you
REALLY
TCCS/USG | get much sleep. | think I can
Tufts University | W. Allen | speak for
Tufts?
------------------------------
Message: 5
Date: Fri, 16 Jun 2006 05:14:43 +0800 (CST)
From: mcclnx mcc <mcclnx at yahoo.com.tw>
Subject: LTO tape drive speed slow on Redhat 4
To: linux-poweredge at dell.com
Message-ID: <20060615211443.18149.qmail at web18603.mail.tpe.yahoo.com>
Content-Type: text/plain; charset=big5
We have IBM LTO tape drive connect to DELL 6800 server. This server has
Redhat AS 4.3 installed.
Initially I test "tar cvf /dev/st0 .", it can ONLY perform 4MB/sec
speed. After I disbale "direct I/O"
on ST, the speed up to 9MB/sec.
LTO tape drive speed supposely should around 15MB/sec -30MB/sec. does
anyone know how to make it run faster?
Thanks.
___________________________________________________
???s?? Yahoo!?_???Y???q?T 7.0?A?K?O?????q?????A???I
http://messenger.yahoo.com.tw/
------------------------------
Message: 6
Date: Fri, 16 Jun 2006 08:22:19 +0300
From: Pauli Borodulin <pauli.borodulin at uta.fi>
Subject: Re: LTO tape drive speed slow on Redhat 4
To: mcclnx mcc <mcclnx at yahoo.com.tw>
Cc: linux-poweredge at dell.com
Message-ID: <4492400B.2020700 at uta.fi>
Content-Type: text/plain; charset=Big5
mcclnx mcc wrote:
> We have IBM LTO tape drive connect to DELL 6800 server. This server
> has Redhat AS 4.3 installed.
> Initially I test "tar cvf /dev/st0 .", it can ONLY perform 4MB/sec
> speed. After I disbale "direct I/O"
> on ST, the speed up to 9MB/sec.
> LTO tape drive speed supposely should around 15MB/sec -30MB/sec. does
> anyone know how to make it run faster?
By default, Tar uses block size of 20*512B = 10kB. This is really small
and is a probable reason for your slowness. Most LTO systems in use
operate most efficiently with a 64kB blocksize, so try using that
instead. First configure the drive for variable block size by running
"mt setblk 0" (you may need to define the device with the -f parameter).
Then use "tar -b128 ..." to make the tar archives. It is also necessary
to use the same parameters when reading the tapes.
Br,
--
Pauli Borodulin <pauli.borodulin at uta.fi> Systems Analyst, tel. +358 3
3551 7892 Computer Centre / Room B4179 University of Tampere, Finland
------------------------------
Message: 7
Date: Fri, 16 Jun 2006 12:20:39 +0200
From: Giulio Orsero <giulioo at gmail.com>
Subject: PERC5 and linux 2.4.x
To: linux-poweredge at dell.com
Message-ID: <20060616102037.2E25AF815 at i3.golden.dom>
Content-Type: text/plain; charset=us-ascii
I see drivers for RHEL3 kernels, but not for stock 2.4.x kernels (source
code for RHEL won't compile on kernel.org due to variuos RHEL
differences).
Are there any plans to ever release megaraid_sas source code suited for
kernel.org 2.4.x kernels?
Thanks
--
giulioo at pobox.com
------------------------------
_______________________________________________
Linux-PowerEdge mailing list
Linux-PowerEdge at dell.com
http://lists.us.dell.com/mailman/listinfo/linux-poweredge
Please read the FAQ at http://lists.us.dell.com/faq
End of Linux-PowerEdge Digest, Vol 20, Issue 31
***********************************************
More information about the Linux-PowerEdge
mailing list