Memtest-SDRAM

Memtest-SDRAM

[srideep.devireddy]

[-- Attachment #1: Type: text/plain, Size: 753 bytes --]


Hi all ,



  Can I comprehensively test and conform that my SDRAM is creating
problem other than mtest at u-boot( which I already implemented the
mtest with the help of mailing list , where my memory failed . ) , if is
there is a way please do let me know .



Thanks in advance,



Best Regards\

Srideep











Confidentiality Notice

The information contained in this electronic message and any attachments to this message are intended
for the exclusive use of the addressee(s) and may contain confidential or privileged information. If
you are not the intended recipient, please notify the sender at Wipro or Mailadmin@wipro.com immediately
and destroy all copies of this message and any attachments.

[-- Attachment #2: Type: text/html, Size: 3371 bytes --]

Re: Memtest-SDRAM

[Wolfgang Denk]

In message <6AD9F6A5F6E096408F0B703773355A0765E931@CHN-SNR-MBX01.wipro.com> you wrote:
> 
>   Can I comprehensively test and conform that my SDRAM is creating
> problem other than mtest at u-boot( which I already implemented the
> mtest with the help of mailing list , where my memory failed . ) , if is
> there is a way please do let me know .

A simple test is: if Linux is running  without  problems  under  load
than there are no problems with your SDRAM.

See also the U-Boot FAQ.

Best regards,

Wolfgang Denk

-- 
Software Engineering:  Embedded and Realtime Systems,  Embedded Linux
Phone: (+49)-8142-66989-10 Fax: (+49)-8142-66989-80 Email: wd@denx.de
I have a very small mind and must live with it.    -- Edsger Dijkstra

Re: Memtest-SDRAM

[Kylo Ginsberg]

On 11/19/05, Wolfgang Denk <wd@denx.de> wrote:
> In message <6AD9F6A5F6E096408F0B703773355A0765E931@CHN-SNR-MBX01.wipro.co=
m> you wrote:
> >
> >   Can I comprehensively test and conform that my SDRAM is creating
> > problem other than mtest at u-boot( which I already implemented the
> > mtest with the help of mailing list , where my memory failed . ) , if i=
s
> > there is a way please do let me know .
>
> A simple test is: if Linux is running  without  problems  under  load
> than there are no problems with your SDRAM.

Yes, but determining the proper load to test with can be tricky.=20
E.g., I had a subtle memory timing issue that only turned up under
very peculiar circumstances under linux; this was very difficult to
reproduce until I started using a simple user-space memory tester
application, which could very reliably produce failures.  Fwiw, I
started with this:

http://pyropus.ca/software/memtester/

Cheers,
Kylo

Re: Memtest-SDRAM

[Wolfgang Denk]

In message <61cc712d0511201058p367df361i7e46591336918712@mail.gmail.com> you wrote:
>
> > A simple test is: if Linux is running  without  problems  under  load
> > than there are no problems with your SDRAM.
> 
> Yes, but determining the proper load to test with can be tricky. 

Ummm.. I disagree. Avtually it's pretty simple. Boot the system  with
root  file  system  mounted  over  NFS.  The  compile  a Linux kernel
natively on the board. This is doing all you want: stressing  network
(lots  of  DMA),  stressing  the memory (lots of context switches and
heavy RAM use), etc. If your system survives this,  you  can  be  98%
sure that it will pass any other test as well.

> E.g., I had a subtle memory timing issue that only turned up under
> very peculiar circumstances under linux; this was very difficult to

Of course there are really weird cases,  but  fortunaltey  these  are
rare exceptions.

Best regards,

Wolfgang Denk

-- 
Software Engineering:  Embedded and Realtime Systems,  Embedded Linux
Phone: (+49)-8142-66989-10 Fax: (+49)-8142-66989-80 Email: wd@denx.de
Committee, n.:  A group of men who individually can do nothing but as
a group decide that nothing can be done.                 - Fred Allen