On 10/8/2010 3:18 PM, Richard Scobie wrote:
> Testing continues, reply below:
>
> Dan Williams wrote:
>> [ adding Dave, Maciej ]
>>
>> On 10/4/2010 1:13 PM, Brandeburg, Jesse wrote:
>>>
>>> Dan might be able to further help with the ioatdma portion, this sounds
>>> like a possible regression in 4.00 ioatdma?
>>
>> Smells that way. I'm traveling internationally this week, but I can try
>> to reproduce this on my 5400 next week when I'm back (unless Dave or
>> Maciej have a chance to take a look). Question below:
>>
>>>
>>> On Sat, 2 Oct 2010, Richard Scobie wrote:
>>>
>>>> I have a Tyan S5396 5400 based board, which has been running
>>>> 2.6.30.10-105.2.23.fc11.x86_64and has a PRO/1000 PT (82571EB) Quad
>>>> adapter, along with two onboard 80003ES2LAN adapters.
>>>>
>>>> This has performed fine with the ioatdma loaded and the BIOS is the
>>>> latest.
>>>>
>>>> dca service started, version 1.8
>>>> ioatdma 0000:00:0f.0: PCI INT A ->  GSI 16 (level, low) ->  IRQ 16
>>>> ioatdma 0000:00:0f.0: setting latency timer to 64
>>>> ioatdma 0000:00:0f.0: Intel(R) I/OAT DMA Engine found, 4 channels,
>>>> device version 0x20, driver version 3.64
>>>> alloc irq_desc for 62 on cpu 0 node 0
>>>> alloc kstat_irqs on cpu 0 node 0
>>>> ioatdma 0000:00:0f.0: irq 62 for MSI/MSI-X
>>>> alloc irq_desc for 63 on cpu 0 node 0
>>>> alloc kstat_irqs on cpu 0 node 0
>>>> ioatdma 0000:00:0f.0: irq 63 for MSI/MSI-X
>>>> alloc irq_desc for 64 on cpu 0 node 0
>>>> alloc kstat_irqs on cpu 0 node 0
>>>> ioatdma 0000:00:0f.0: irq 64 for MSI/MSI-X
>>>> alloc irq_desc for 65 on cpu 0 node 0
>>>> alloc kstat_irqs on cpu 0 node 0
>>>> ioatdma 0000:00:0f.0: irq 65 for MSI/MSI-X
>>>> ioatdma 0000:00:0f.0: DCA is disabled in BIOS
>>>
>>> hm, I think this note above is critical that it is missing from the
>>> below.
>>>
>>>> I have just updated to 2.6.35.7 stable and with ioatdma loaded, samba RX
>>>> performance drops from normal levels, to about 500kB/s with the smbd
>>>> process at 100% CPU.
>>>
>>> does netstat -s show it all to be from retransmits or SACKs?
>>
>> I assume smbd normally does not consume 100% cpu. Can you send the
>> output of:
>>
>> perf record -a sleep 5; perf report
>>
>> ...while the bad performance is occurring. That might give a clue as to
>> what is tanking the performance.
>
> Not sure if the 300k file will make it as an attachment, so here are the
> first entries in the report. Let me know if you'd still like the file:
>
>
>    perf report --sort comm,dso,symbol | head -50
> # Events: 7K cycles
> #
> # Overhead          Command         Shared Object  Symbol
> # ........  ...............  ....................  ......
> #
>       58.34%             smbd  [ioatdma]             [k] ioat_tx_status
>       39.19%             smbd  [kernel.kallsyms]     [k] tcp_service_net_dma

Ok, this looks like we are spending a lot of time waiting for the dma 
engine... but it's not immediately clear why.

It looks like I can reproduce this with a simple iperf test.  I'll see 
if I can bisect when this was introduced.

witout ioatdma:
# iperf -c <test system> -l 256k -w 256k -P 16 -t 7200
[..]
[SUM]  0.0-31.7 sec  3.45 GBytes   934 Mbits/sec

with ioatdma:
# iperf -c <test system> -l 256k -w 256k -P 16 -t 7200
[..]
[SUM]  0.0-41.3 sec   364 MBytes  73.9 Mbits/sec

--
Dan

------------------------------------------------------------------------------
Beautiful is writing same markup. Internet Explorer 9 supports
standards for HTML5, CSS3, SVG 1.1,  ECMAScript5, and DOM L2 & L3.
Spend less time writing and  rewriting code and more time creating great
experiences on the web. Be a part of the beta today.
http://p.sf.net/sfu/beautyoftheweb
_______________________________________________
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