On Thu, Sep 24, 2015 at 12:33 PM, Wido den Hollander <wido@xxxxxxxx> wrote:
>
>
> On 24-09-15 11:06, Ilya Dryomov wrote:
>> On Thu, Sep 24, 2015 at 7:05 AM, Robert LeBlanc <robert@xxxxxxxxxxxxx> wrote:
>>> -----BEGIN PGP SIGNED MESSAGE-----
>>> Hash: SHA256
>>>
>>> If you use RADOS gateway, RBD or CephFS, then you don't need to worry
>>> about striping. If you write your own application that uses librados,
>>> then you have to worry about it. I understand that there is a
>>> radosstriper library that should help with that. There is also a limit
>>> to the size of an object that can be stored. I think I've seen the
>>> number of 100GB thrown around.
>>
>> Just for the sake of archives, it's 90M by default.
>>
>
> Are you sure?
>
> osd_max_write_size is set to 90 by default. That means that the OSD will
> accept a single write of 90MB at max. However, you can create an object
> and keep appending to the Object and have it grow to over 90MB.
>
> e.g.:
> - Call rados_write() and write 50MB
> - Call rados_append() 100 times and append 50MB in each call
>
> The total object size will be: 50 + (100 * 50) = 5050MB
Oh sure. The general topic of the thread was writing a 1G file and as
a single write, while Robert was talking about how large an object can
be. Sorry!
Thanks,
Ilya
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
