Re: How to measure the RAM read/write performance

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



>Another easy way to make memory(ie..pages) non cacheble is use the
>below function,
>dma_alloc_coherent(NULL, size, &p, GFP_KERNEL);

I did like what you said. With the timings,i can see it is reading directly from RAM. I have some doubts..
--> What exactly happend here? Here read/write are done by CPU or DMA controller?

I am new to DMA kind of operations, i have one doubt in how to do DMA?
Can you give me some example driver code, for this following case....

--> I want to do a DMA from a mem mapped I/O (lets say physical 0x40000000) to RAM location @ 0x80000000. 
    How do you do this?

Thanks
Sandeep


On Fri, Mar 1, 2013 at 10:45 AM, Arun KS <getarunks@xxxxxxxxx> wrote:
On Thu, Feb 28, 2013 at 3:54 PM, sandeep kumar
<coolsandyforyou@xxxxxxxxx> wrote:
>>1. use early_param to get the physical start address and size of
>> test_region, or you can just ignore this step and hard code to 510M and 2M
>> for test purpose only.
>
>>2. use ioremap_nocache() to map this region to a virtual region. note that
>> this funtion may fail if you are asking a very large vitual memroy region.
> I did the following things,
>
> Thank you so much...It worked. With this i am able to measure RAM
> performance.

Another easy way to make memory(ie..pages) non cacheble is use the
below function,
dma_alloc_coherent(NULL, size, &p, GFP_KERNEL);

This will set the page tables attributes for this page no-cachable.
All reads & writes will always happen from main memory because MMU see
the memory attribute for this page as non cacheble.

Thanks,
Arun
>
>
> On Thu, Feb 28, 2013 at 11:39 AM, sandeep kumar <coolsandyforyou@xxxxxxxxx>
> wrote:
>>
>> >1. use early_param to get the physical start address and size of
>> > test_region, or you can just ignore this step and hard code to 510M and 2M
>> > for test purpose only.
>>
>> >2. use ioremap_nocache() to map this region to a virtual region. note
>> > that this funtion may fail if you are asking a very large vitual memroy
>> > region.
>> I did the following things,
>> 1) Reserved 3MB memory through ATAGS
>> 2) Wrote small driver to ioremap that memory in following way,
>>
>>  void *tcpm_base = ioremap_nocache(0x03B00000, SZ_3MB);
>>  27             if(tcpm_base!=NULL)
>>  28             {
>>  29             printk("Jiffies %x %ld\n\n\n\n", jiffies, jiffies);
>>  30             for(i=0;i<SZ_4KB;i++)
>>  31             src = ""> >>  32             printk("Jiffies %x %ld\n\n\n\n", jiffies, jiffies);
>>  33             }
>>  34             else
>>  35                 printk("unable to map 3MB\n");
>>
>> 3) I am getting the following error,
>>
>> [    1.876647] Unable to handle kernel paging request at virtual address
>> ea82c000
>> [    1.880950] pgd = c0004000
>> [    1.883636] [ea82c000] *pgd=49818811, *pte=00000000, *ppte=00000000
>> [    1.889892] Internal error: Oops: 7 [#1] PREEMPT
>> [    1.894500] Modules linked in:
>> [    1.897521] CPU: 0    Not tainted  (3.0.31-g1080f34-dirty #106)
>> [    1.903442] PC is at sand_misc_init+0x4c/0xac
>> [    1.907775] LR is at sand_misc_init+0x3c/0xac
>> [    1.912109] pc : [<c0022ee0>]    lr : [<c0022ed0>]    psr: 80000013
>> [    1.912139] sp : e982bf98  ip : 00000000  fp : 00000000
>> [    1.923553] r10: 00000000  r9 : 00000000  r8 : 00000000
>> [    1.928771] r7 : 00000000  r6 : c00461b4  r5 : ea828000  r4 : 00000000
>> [    1.935272] r3 : 00003fff  r2 : 00003ffd  r1 : c07ea2cf  r0 : 00000063
>> [    1.941802] Flags: Nzcv  IRQs on  FIQs on  Mode SVC_32  ISA ARM
>> Segment kernel
>> [    1.949096] Control: 10c57c7d  Table: 00404059  DAC: 00000015
>> [    1.954803]
>> [    1.954833] PC: 0xc0022e60:
>> [    1.959075] 2e60  c09105f0 c0366554 c07ea27e c07ea296 e3a01000 e92d4010
>> e1a02001 eb0a9acd
>> [    1.967224] 2e80  e59f3008 e5830008 e3a00001 e8bd8010 c0dd8380 e92d4037
>> e3a04000 e3a0063b
>> [    1.975402] 2ea0  e3a01901 e1a02004 e5cd4007 e5cd4006 eb00b9aa e2505000
>> 0a000019 e59f3070
>> [    1.983551] 2ec0  e59f0070 e5931000 e5932000 eb18a072 e58d4000 e3033fff
>> ea000007 e59d2000
>> [    1.991699] 2ee0  e7952002 f57ff04f e6ef2072 e5cd2007 e59d2000 e2822001
>> e58d2000 e59d2000
>> [    1.999877] 2f00  e1520003 dafffff4 e59f3024 e59f0024 e5931000 e5932000
>> e28dd00c e8bd4030
>> [    2.008026] 2f20  ea18a05d e59f0010 e28dd00c e8bd4030 ea18a059 c08ea600
>> c07ea2cf c07ea2e2
>> [    2.016174] 2f40  e59f3040 e3a01000 e92d4010 e59f0038 e5932000 eb0a845a
>> e59f3030 e3500000
>> [    2.024353]
>> [    2.024353] LR: 0xc0022e50:
>> [    2.028594] 2e50  e3e00015 e8bd81fc c0dd8380 c07ea279 c09105f0 c0366554
>> c07ea27e c07ea296
>> [    2.036773] 2e70  e3a01000 e92d4010 e1a02001 eb0a9acd e59f3008 e5830008
>> e3a00001 e8bd8010
>> [    2.044921] 2e90  c0dd8380 e92d4037 e3a04000 e3a0063b e3a01901 e1a02004
>> e5cd4007 e5cd4006
>> [    2.053070] 2eb0  eb00b9aa e2505000 0a000019 e59f3070 e59f0070 e5931000
>> e5932000 eb18a072
>> [    2.061248] 2ed0  e58d4000 e3033fff ea000007 e59d2000 e7952002 f57ff04f
>> e6ef2072 e5cd2007
>> [    2.069396] 2ef0  e59d2000 e2822001 e58d2000 e59d2000 e1520003 dafffff4
>> e59f3024 e59f0024
>> [    2.077575] 2f10  e5931000 e5932000 e28dd00c e8bd4030 ea18a05d e59f0010
>> e28dd00c e8bd4030
>> [    2.085723] 2f30  ea18a059 c08ea600 c07ea2cf c07ea2e2 e59f3040 e3a01000
>> e92d4010 e59f0038
>> [    2.093872]
>> [    2.093902] SP: 0xe982bf18:
>> [    2.098144] bf18  382e3120 30393536 00205d35 000000d0 00004fff 00003b00
>> 192d8000 ea82bfff
>> [    2.106292] bf38  03b00000 ffffffff e982bf84 c00461b4 00000000 c0044dac
>> 00000063 c07ea2cf
>> [    2.114440] bf58  00003ffd 00003fff 00000000 ea828000 c00461b4 00000000
>> 00000000 00000000
>> [    2.122619] bf78  00000000 00000000 00000000 e982bf98 c0022ed0 c0022ee0
>> 80000013 ffffffff
>> [    2.130767] bf98  00003ffd 0000a27e 00000000 c0037b4c c0022e94 c003f3fc
>> e9814a80 00373231
>> [    2.138946] bfb8  00000000 00000000 00000000 00000236 c0037b4c c003818c
>> c00461b4 00000013
>> [    2.147094] bfd8  00000000 00000000 00000000 c0008374 00000000 c0008300
>> c00461b4 c00461b4
>> [    2.155242] bff8  00000000 00000000 00000000 00000001 00000000 e9817940
>> c08e8ef4 00000000
>> [    2.163421]
>> [    2.163421] R1: 0xc07ea24f:
>> [    2.167663] a24c  65207265 726f7272 6f6c6220 25206b63 000a646c 706f6f6c
>> 26006425 3e2d6f6c
>> [    2.175842] a26c  635f6f6c 6d5f6c74 78657475 6f6f6c00 363c0070 6f6f6c3e
>> 6d203a70 6c75646f
>> [    2.183990] a28c  6f6c2065 64656461 363c000a 6f6f6c3e 6f203a70 6f207475
>> 656d2066 79726f6d
>> [    2.192138] a2ac  6162000a 6e696b63 69665f67 7300656c 6c657a69 74696d69
>> 74756100 656c636f
>> [    2.200317] a2cc  4a007261 69666669 25207365 6c252078 0a0a0a64 6e75000a
>> 656c6261 206f7420
>> [    2.208465] a2ec  2070616d 0a424d33 656d7000 65725f6d 6e6f6967 333c0073
>> 656d703e 7325286d
>> [    2.216613] a30c  736b3a29 635f7465 74616572 6e615f65 64615f64 61662064
>> 000a6c69 703e343c
>> [    2.224792] a32c  3a6d656d 6d6f7320 69687465 6920676e 65762073 77207972
>> 676e6f72 6f79202c
>> [    2.232940] a34c  72612075 6c632065 6e69736f 20612067 62206d76 696b6361
>> 6120676e 6c61206e
>> [    2.241119]
>> [    2.241119] R5: 0xea827f80:
>> [    2.245361] 7f80  ******** ******** ******** ******** ******** ********
>> ******** ********
>> [    2.253509] 7fa0  ******** ******** ******** ******** ******** ********
>> ******** ********
>> [    2.261688] 7fc0  ******** ******** ******** ******** ******** ********
>> ******** ********
>> [    2.269836] 7fe0  ******** ******** ******** ******** ******** ********
>> ******** ********
>> [    2.278015] 8000  00000000 00000000 00000000 00000000 00000000 00000000
>> 00000000 00000000
>> [    2.286163] 8020  00000000 00000000 00000000 00000000 00000000 00000000
>> 00000000 00000000
>> [    2.294311] 8040  00000000 00000000 00000000 00000000 00000000 00000000
>> 00000000 00000000
>> [    2.302490] 8060  00000000 00000000 00000000 00000000 00000000 00000000
>> 00000000 00000000
>> [    2.310638]
>> [    2.310638] R6: 0xc0046134:
>> [    2.314880] 6134  eb038dff eb02a1f9 e1a03007 e1a00005 e1a02006 eb025566
>> e59f3008 e5834000
>> [    2.323059] 6154  e8bd41f0 ea0259b3 c09059d4 c08fbcd4 c064e808 c0791c0d
>> c0958220 e59fc020
>> [    2.331207] 6174  e92d4007 e59f301c e59cc000 e1a02001 e59f1014 e58dc000
>> eb055aab e3a00000
>> [    2.339385] 6194  e8bd800e c0958220 c0791c27 c0791c1b e121f007 e1a00004
>> e1a0e006 e1a0f005
>> [    2.347534] 61b4  eb02959a e320f000 e59f300c e5932000 e2822001 e5832000
>> e12fff1e c0958224
>> [    2.355682] 61d4  e59f300c e5932000 e2422001 e5832000 e12fff1e c0958224
>> e12fff1e e12fff1e
>> [    2.363861] 61f4  e12fff1e e12fff1e eafffffe e59f3014 e92d4010 e5933004
>> e3530000 08bd8010
>> [    2.372009] 6214  e12fff33 e8bd8010 c0958224 e59f3014 e1a01000 e92d4010
>> e5d30000 e1a0e00f
>> [    2.380187] Process swapper (pid: 1, stack limit = 0xe982a2e8)
>> [    2.385986] Stack: (0xe982bf98 to 0xe982c000)
>> [    2.390319] bf80:
>> 00003ffd 0000a27e
>> [    2.398498] bfa0: 00000000 c0037b4c c0022e94 c003f3fc e9814a80 00373231
>> 00000000 00000000
>> [    2.406646] bfc0: 00000000 00000236 c0037b4c c003818c c00461b4 00000013
>> 00000000 00000000
>> [    2.414825] bfe0: 00000000 c0008374 00000000 c0008300 c00461b4 c00461b4
>> 00000000 00000000
>> [    2.423004] [<c0022ee0>] (sand_misc_init+0x4c/0xac) from [<c003f3fc>]
>> (do_one_initcall+0xd0/0x1a4)
>> [    2.431915] [<c003f3fc>] (do_one_initcall+0xd0/0x1a4) from [<c0008374>]
>> (kernel_init+0x74/0x118)
>> [    2.440673] [<c0008374>] (kernel_init+0x74/0x118) from [<c00461b4>]
>> (kernel_thread_exit+0x0/0x8)
>> [    2.449462] Code: e58d4000 e3033fff ea000007 e59d2000 (e7952002)
>> [    2.455566] ---[ end trace f76f3c76dcb9b9ef ]---
>> [    2.460144] Kernel panic - not syncing: Attempted to kill init!
>> [    2.466064] [<c004ad10>] (unwind_backtrace+0x0/0x12c) from [<c064af70>]
>> (panic+0x90/0x1bc)
>> [    2.474304] [<c064af70>] (panic+0x90/0x1bc) from [<c00eb8dc>]
>> (do_exit+0xb8/0x734)
>> [    2.481842] [<c00eb8dc>] (do_exit+0xb8/0x734) from [<c0048f8c>]
>> (die+0x208/0x23c)
>> [    2.489318] [<c0048f8c>] (die+0x208/0x23c) from [<c004e158>]
>> (__do_kernel_fault+0x64/0x84)
>> [    2.497558] [<c004e158>] (__do_kernel_fault+0x64/0x84) from
>> [<c004e3e0>] (do_page_fault+0x268/0x288)
>> [    2.506683] [<c004e3e0>] (do_page_fault+0x268/0x288) from [<c003f270>]
>> (do_DataAbort+0x34/0x94)
>> [    2.515350] [<c003f270>] (do_DataAbort+0x34/0x94) from [<c0044dac>]
>> (__dabt_svc+0x4c/0x60)
>> [    2.523590] Exception stack(0xe982bf50 to 0xe982bf98)
>> [    2.528625] bf40:                                     00000063 c07ea2cf
>> 00003ffd 00003fff
>> [    2.536804] bf60: 00000000 ea828000 c00461b4 00000000 00000000 00000000
>> 00000000 00000000
>> [    2.544952] bf80: 00000000 e982bf98 c0022ed0 c0022ee0 80000013 ffffffff
>> [    2.551544] [<c0044dac>] (__dabt_svc+0x4c/0x60) from [<c0022ee0>]
>> (sand_misc_init+0x4c/0xac)
>> [    2.559967] [<c0022ee0>] (sand_misc_init+0x4c/0xac) from [<c003f3fc>]
>> (do_one_initcall+0xd0/0x1a4)
>> [    2.568908] [<c003f3fc>] (do_one_initcall+0xd0/0x1a4) from [<c0008374>]
>> (kernel_init+0x74/0x118)
>> [    2.577667] [<c0008374>] (kernel_init+0x74/0x118) from [<c00461b4>]
>> (kernel_thread_exit+0x0/0x8)
>>
>>
>> Any idea what went wrong.
>> I am sure about the ioremap() start address, thats what i reserved in
>> ATAGS.
>>
>> Thanks
>> Sandeep
>>
>>
>> On Thu, Feb 28, 2013 at 10:30 AM, sandeep kumar
>> <coolsandyforyou@xxxxxxxxx> wrote:
>>>
>>> >1. use early_param to get the physical start address and size of
>>> > test_region, or you can just ignore this step and hard code to 510M and 2M
>>> > for test purpose only.
>>>
>>> >2. use ioremap_nocache() to map this region to a virtual region. note
>>> > that this funtion may fail if you are asking a very large vitual memroy
>>> > region.
>>>
>>> Sounds good, i am gonna try this and let you know.. :)
>>>
>>>
>>> On Wed, Feb 27, 2013 at 8:19 PM, buyitian <buyit@xxxxxxx> wrote:
>>>>
>>>> ----------------------------------------
>>>> > From: buyit@xxxxxxx
>>>> > To: coolsandyforyou@xxxxxxxxx; kernelnewbies@xxxxxxxxxxxxxxxxx
>>>> > Subject: RE: How to measure the RAM read/write performance
>>>> > Date: Wed, 27 Feb 2013 22:33:15 +0800
>>>> > CC: dhylands@xxxxxxxxx
>>>> >
>>>> > ________________________________
>>>> > > From: coolsandyforyou@xxxxxxxxx
>>>> > > Date: Tue, 26 Feb 2013 17:01:54 +0530
>>>> > > Subject: How to measure the RAM read/write performance
>>>> > > To: kernelnewbies@xxxxxxxxxxxxxxxxx
>>>> > > CC: dhylands@xxxxxxxxx
>>>> > >
>>>> > > Hi All
>>>> > > In performance benchmark tools, When we profile read/write timings
>>>> > > mostly, those read/writes are done to cache only.
>>>> > >
>>>> > > I want to measure my DDR(RAM chip) performance.
>>>> > > So i want to make sure, every read/write should happen to DDR RAM
>>>> > > chip only.
>>>> > >
>>>> > > How can i achieve this...Any ideas/suggestions...?
>>>> >
>>>> > try to reserve a large region from bootloader(L4 in Qualcomm
>>>> > platform), let's say it is 10MB continuous physical memory.
>>>>
>>>> sorry, to be accurate, reserve physical memory is done by kernel
>>>> cmdline, this cmdline parameter can be passed from L4 to kernel, or configed
>>>> by kernel itself.
>>>> the cmdline will be like below:
>>>> mem=510M@0 test_region=2M@510M
>>>>
>>>> above example tells kernel you have totally 512MB physical memory, but
>>>> kernel will only use the first 510MB, the latter 2MB memory is used by you.
>>>> how to map and use this region depends on you.
>>>>
>>>> > in kernel, map this region to an continuous virtual region, note that
>>>> > the pgprot should be uncachable since you want to test without cache.
>>>>
>>>> 1. use early_param to get the physical start address and size of
>>>> test_region, or you can just ignore this step and hard code to 510M and 2M
>>>> for test purpose only.
>>>>
>>>> 2. use ioremap_nocache() to map this region to a virtual region. note
>>>> that this funtion may fail if you are asking a very large vitual memroy
>>>> region.
>>>>
>>>> > once you configed like this, you can read/write to this vitual region
>>>> > without data cache invovled.
>>>> >
>>>> > >
>>>> > > --
>>>> > > With regards,
>>>> > > Sandeep Kumar Anantapalli,
>>>> > >
>>>> > > _______________________________________________ Kernelnewbies
>>>> > > mailing
>>>> > > list Kernelnewbies@xxxxxxxxxxxxxxxxx
>>>> > > http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
>>>> > _______________________________________________
>>>> > Kernelnewbies mailing list
>>>> > Kernelnewbies@xxxxxxxxxxxxxxxxx
>>>> > http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
>>>
>>>
>>>
>>>
>>> --
>>> With regards,
>>> Sandeep Kumar Anantapalli,
>>
>>
>>
>>
>> --
>> With regards,
>> Sandeep Kumar Anantapalli,
>
>
>
>
> --
> With regards,
> Sandeep Kumar Anantapalli,
>
> _______________________________________________
> Kernelnewbies mailing list
> Kernelnewbies@xxxxxxxxxxxxxxxxx
> http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
>



--
With regards,
Sandeep Kumar Anantapalli,
_______________________________________________
Kernelnewbies mailing list
Kernelnewbies@xxxxxxxxxxxxxxxxx
http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies

[Index of Archives]     [Newbies FAQ]     [Linux Kernel Mentors]     [Linux Kernel Development]     [IETF Annouce]     [Git]     [Networking]     [Security]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux RAID]     [Linux SCSI]     [Linux ACPI]
  Powered by Linux