RAID-6 polynomial

RAID-6 polynomial

[Tirumala Reddy Marri]

What is the default polynomial to calculate RAID-6 syndrome in
async_pq.c? Is it 0x11d ?
Thanks in Advance,
Marri

Re: RAID-6 polynomial

[Michael Evans]

On Mon, Apr 19, 2010 at 4:44 PM, Tirumala Reddy Marri <tmarri@amcc.com> wrote:
> What is the default polynomial to calculate RAID-6 syndrome in
> async_pq.c? Is it 0x11d ?
> Thanks in Advance,
> Marri
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>

If you google "raid6 math" you'll get a result like this as the first result:

http://kernel.org/pub/linux/kernel/people/hpa/raid6.pdf The
Mathematics of Raid 6
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

RE: RAID-6 polynomial

[Tirumala Reddy Marri]

I understand the RAID-6 or GF(2) math. There is a test code crypto/async_tx/raid6test.c which make calls to async_gen_syncdrome() in turn calls raid6_int4_gen_syndrome(). I could not find which polynomial this code is using.
-Marri


-----Original Message-----
From: Michael Evans [mailto:mjevans1983@gmail.com] 
Sent: Monday, April 19, 2010 6:55 PM
To: Tirumala Reddy Marri
Cc: linux-raid@vger.kernel.org
Subject: Re: RAID-6 polynomial

On Mon, Apr 19, 2010 at 4:44 PM, Tirumala Reddy Marri <tmarri@amcc.com> wrote:
> What is the default polynomial to calculate RAID-6 syndrome in
> async_pq.c? Is it 0x11d ?
> Thanks in Advance,
> Marri
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>

If you google "raid6 math" you'll get a result like this as the first result:

http://kernel.org/pub/linux/kernel/people/hpa/raid6.pdf The
Mathematics of Raid 6
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: RAID-6 polynomial

[Michael Evans]

On Mon, Apr 19, 2010 at 8:14 PM, Tirumala Reddy Marri <tmarri@amcc.com> wrote:
> I understand the RAID-6 or GF(2) math. There is a test code crypto/async_tx/raid6test.c which make calls to async_gen_syncdrome() in turn calls raid6_int4_gen_syndrome(). I could not find which polynomial this code is using.
> -Marri
>
>
> -----Original Message-----
> From: Michael Evans [mailto:mjevans1983@gmail.com]
> Sent: Monday, April 19, 2010 6:55 PM
> To: Tirumala Reddy Marri
> Cc: linux-raid@vger.kernel.org
> Subject: Re: RAID-6 polynomial
>
> On Mon, Apr 19, 2010 at 4:44 PM, Tirumala Reddy Marri <tmarri@amcc.com> wrote:
>> What is the default polynomial to calculate RAID-6 syndrome in
>> async_pq.c? Is it 0x11d ?
>> Thanks in Advance,
>> Marri
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>>
>
> If you google "raid6 math" you'll get a result like this as the first result:
>
> http://kernel.org/pub/linux/kernel/people/hpa/raid6.pdf The
> Mathematics of Raid 6
>

Please bottom-reply for kernel.org lists.

Would the hex you stated match the polynomial described in the 12 page
(IIRC) PDF I linked?
0x11d would be, in binary, (h)100011101(l); I'm not sure if it
presumes the 0th power being set or not.
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: RAID-6 polynomial

[H. Peter Anvin]

On 04/19/2010 04:44 PM, Tirumala Reddy Marri wrote:
> What is the default polynomial to calculate RAID-6 syndrome in
> async_pq.c? Is it 0x11d ?

Yes.

	-hpa

RE: RAID-6 polynomial

[Tirumala Reddy Marri]

-----Original Message-----
From: H. Peter Anvin [mailto:hpa@zytor.com] 
Sent: Wednesday, April 21, 2010 6:01 PM
To: Tirumala Reddy Marri
Cc: linux-raid@vger.kernel.org
Subject: Re: RAID-6 polynomial

On 04/19/2010 04:44 PM, Tirumala Reddy Marri wrote:
> What is the default polynomial to calculate RAID-6 syndrome in
> async_pq.c? Is it 0x11d ?
>
>Yes.
>
>	-hpa
>
----

Is there a reason for hard coding 0x11d as polynomial ? The problem I
ran into was when  I was trying disk fail test there was issue in
recovering the data. Then it turned out to be ADMA was using polynomial
0x14d and SW algorithm was using 0x11d. This was because syndrome
calculated using DMA engine and recovery done using SW api.

Re: RAID-6 polynomial

[H. Peter Anvin]

On 04/22/2010 09:14 PM, Tirumala Reddy Marri wrote:
> 
> Is there a reason for hard coding 0x11d as polynomial ? The problem I
> ran into was when  I was trying disk fail test there was issue in
> recovering the data. Then it turned out to be ADMA was using polynomial
> 0x14d and SW algorithm was using 0x11d. This was because syndrome
> calculated using DMA engine and recovery done using SW api.
> 

Yes, it would mean the on-disk format would be incompatible otherwise.
Everyone needs to use the same polynomial.

	-hpa

-- 
H. Peter Anvin, Intel Open Source Technology Center
I work for Intel.  I don't speak on their behalf.