Re: filesystem for solid state drives in linux

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

 



On Fri, Jan 16, 2009 at 7:06 AM, andi <andi.platschek@xxxxxxxxx> wrote:
> Peter Teoh wrote:
>>
>> Any filesystem can be used for SSD, but some are better suited due to
>> SSD's hardware characteristic, among which is a lack of a moving
>> read/write head.   so which are the FS specially written to take
>> advantage of this feature?
>>
>
> I think this more about the I/O scheduler than the filesystem. When you use
> a harddisk you don't want the
> read/write head move more than necessary, and you want to get out as much as
> possible of every move of the head.
>
> The I/O scheduler plans the sequence in which the I/O requests are performed
> which can save you a lot of time on harddisks.
> This is not necessary for memory without any mechanical parts like SSD's,
> flash cards etc.
> The linux kernel is using the Noop I/O scheduler for these devices, which
> does no reordering, because it is not necessary for them.
>
> did I get this right? I am not sure, but I think is really more about the
> I/O scheduler and less about the filesystem itself...
>
> andi
>>

YES, u do have a point there....so i am not sure as well....but after
some googling....THANKS FOR YOUR INTUITION....

http://blogs.zdnet.com/perlow/?p=9190

YES, in the article above.....i/o scheduler=noop is recommended,
together with the reasoning.....and more ... in the article were also
mentioned not to have journalling ......etc. etc....worthwhile to
read.


-- 
Regards,
Peter Teoh

--
To unsubscribe from this list: send an email with
"unsubscribe kernelnewbies" to ecartis@xxxxxxxxxxxx
Please read the FAQ at http://kernelnewbies.org/FAQ


[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