Hi Yan Zheng,
I can not add the stripe parameters when try to use the qemu-image CLI like that
qemu-img create -f raw rbd:rbd/qumeimage 1G
and show the image properties
rbd image 'qumeimage':
size 1024 MB in 256 objects
order 22 (4096 kB objects)
block_name_prefix: rb.0.10d5.238e1f29
format: 1
so how to create a striped qeum image?
thanks very much!
JIan Li
At 2014-05-13 06:30:18,"Yan, Zheng" <[email protected]> wrote:
>the kernel rdb does not support it, you need to use qemu.
>
>On Mon, May 12, 2014 at 8:00 PM, lijian <[email protected]> wrote:
>> Hi,
>>
>> I want to create a block image using the rbd cli and followng the rule:
>> stripe-unit * stripe-count = 2^order,
>> Take for example:
>> rbd create --pool rbd --size 20480 --order 21 --image-format 2 --stripe-unit
>> 1048576 --stripe-count 2 image1
>>
>> But when I try to map to a block device then raise a message: rbd: add
>> failed: (22) Invalid argument
>> check the linux kernel(Linux nodeclient 3.11.0-12-generic #19-Ubuntu SMP Wed
>> Oct 9 16:20:46 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux) log
>> dmesg | grep rbd
>> rbd: image image1: unsupported stripe unit (got 1048576 want 2097152)
>> I guess the rbd kernel does not support the 'fancy striping', after I read
>> the kernel code rbd.c
>> ----------------------------------------------------------------------------------------------------------------------
>> if (stripe_unit != obj_size) {
>> rbd_warn(rbd_dev, "unsupported stripe unit "
>> "(got %llu want %llu)",
>> stripe_unit, obj_size);
>> return -EINVAL;
>> }
>> stripe_count = ceph_decode_64(&p);
>> if (stripe_count != 1) {
>> rbd_warn(rbd_dev, "unsupported stripe count "
>> "(got %llu want 1)", stripe_count);
>> return -EINVAL;
>> }
>> -----------------------------------------------------------------------------------------------------------------
>>
>> So how to enable/test the 'fancy striping' features, please help!
>>
>> Best Regards,
>> Jian LI
>>
>>
>>
>>
>> _______________________________________________
>> ceph-users mailing list
>> [email protected]
>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>>
_______________________________________________
ceph-users mailing list
[email protected]
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
