9 Sep
2020
9 Sep
'20
9:06 a.m.
Hi *,
I'm wondering about what actually happens in the ceph cluster if I
copy/sync the content of one bucket into a different bucket. I'll just
describe what I saw and maybe someone could clarify what is happening.
I have a RGW in a small test cluster (15.2.2) and created a bucket
(bucket1) with s3cmd, then put a large file into bucket1. This takes
some time, of course, I see the network utilization on the client and
also the OSD load on the cluster during the upload (expected).
Then I create bucket2 and run 's3cmd cp s3://bucket1/file
s3://bucket2' which takes only a couple of seconds. I only see some
OSD load for a short period of time during the copy process, but
that's it. The copied file is available almost immediately.
How does this work? It seems as if there's (almost) no client traffic
(except for the cp command, of course) to recreate the file in the
second bucket, as if the OSDs are directly instructed to create copies
of the objects.
I would highly appreciate it if anyone could clarify this for me.
Thanks!
Eugen
9 Sep
9 Sep
9:21 a.m.
Den ons 9 sep. 2020 kl 10:06 skrev Eugen Block <eblock(a)nde.ag>ag>:
Hi *,
I'm wondering about what actually happens in the ceph cluster if I
copy/sync the content of one bucket into a different bucket.
How does this work? It seems as if there's (almost) no client traffic
(except for the cp command, of course) to recreate the file in the
second bucket, as if the OSDs are directly instructed to create copies
of the objects.
I think rgw will make a header that points to the original data only, so
you are right in that there is no huge data copy operation.
--
May the most significant bit of your life be positive.
9:55 a.m.
I think rgw will make a header that points to the
original data only, so
you are right in that there is no huge data copy operation.
Alright, that would explain it. But what happens when I overwrite the
object in bucket1 with different content? Because I'm still able to
get the original content from bucket2/file although it's overwritten
in bucket1.
Zitat von Janne Johansson <icepic.dz(a)gmail.com>om>:
> Den ons 9 sep. 2020 kl 10:06 skrev Eugen Block <eblock(a)nde.ag>ag>:
>
>> Hi *,
>>
>> I'm wondering about what actually happens in the ceph cluster if I
>> copy/sync the content of one bucket into a different bucket.
>>
>> How does this work? It seems as if there's (almost) no client traffic
>> (except for the cp command, of course) to recreate the file in the
>> second bucket, as if the OSDs are directly instructed to create copies
>> of the objects.
>>
>
I think rgw will make a header that points to the
original data only, so
you are right in that there is no huge data copy operation.
>
> --
> May the most significant bit of your life be positive.
1:02 p.m.
Basically same thing that happens when you overwrite any object. New
data is sent from the client, and a new Head is created pointing at it.
The old head is removed, and the data marked for garbage collection if
it's unused (which it won't be, in this case, since another Head points
at it).
Daniel
On 9/9/20 4:55 AM, Eugen Block wrote:
I think rgw
will make a header that points to the original data only, so
you are right in that there is no huge data copy operation.
Alright, that would explain it. But what happens when I overwrite the
object in bucket1 with different content? Because I'm still able to get
the original content from bucket2/file although it's overwritten in
bucket1.
Zitat von Janne Johansson <icepic.dz(a)gmail.com>om>:
> Den ons 9 sep. 2020 kl 10:06 skrev Eugen Block <eblock(a)nde.ag>ag>:
>
>> Hi *,
>>
>> I'm wondering about what actually happens in the ceph cluster if I
>> copy/sync the content of one bucket into a different bucket.
>>
>> How does this work? It seems as if there's (almost) no client traffic
>> (except for the cp command, of course) to recreate the file in the
>> second bucket, as if the OSDs are directly instructed to create copies
>> of the objects.
>>
>
I think rgw will make a header that points to the
original data only, so
you are right in that there is no huge data copy operation.
>
> --
> May the most significant bit of your life be positive.
_______________________________________________
ceph-users mailing list -- ceph-users(a)ceph.io
To unsubscribe send an email to ceph-users-leave(a)ceph.io
1:04 p.m.
Thank you, that's very helpful, I appreciate it!
Zitat von Daniel Gryniewicz <dang(a)redhat.com>om>:
Basically same thing that happens when you overwrite
any object.
New data is sent from the client, and a new Head is created pointing
at it. The old head is removed, and the data marked for garbage
collection if it's unused (which it won't be, in this case, since
another Head points at it).
Daniel
On 9/9/20 4:55 AM, Eugen Block wrote:
>> I think rgw will make a header that points to the original data only, so
>> you are right in that there is no huge data copy operation.
>
> Alright, that would explain it. But what happens when I overwrite
> the object in bucket1 with different content? Because I'm still
> able to get the original content from bucket2/file although it's
> overwritten in bucket1.
>
>
> Zitat von Janne Johansson <icepic.dz(a)gmail.com>om>:
>
>> Den ons 9 sep. 2020 kl 10:06 skrev Eugen Block <eblock(a)nde.ag>ag>:
>>
>>> Hi *,
>>>
>>> I'm wondering about what actually happens in the ceph cluster if I
>>> copy/sync the content of one bucket into a different bucket.
>>>
>>> How does this work? It seems as if there's (almost) no client traffic
>>> (except for the cp command, of course) to recreate the file in the
>>> second bucket, as if the OSDs are directly instructed to create copies
>>> of the objects.
>>>
>>
>> I think rgw will make a header that points to the original data only, so
>> you are right in that there is no huge data copy operation.
>>
>> --
>> May the most significant bit of your life be positive.
>
>
> _______________________________________________
> ceph-users mailing list -- ceph-users(a)ceph.io
> To unsubscribe send an email to ceph-users-leave(a)ceph.io
>
1347
days inactive
1347
days old
4 comments
3 participants
participants (3)
-
Daniel Gryniewicz -
Eugen Block -
Janne Johansson