mirror of
https://github.com/ceph/ceph
synced 2024-12-22 03:22:00 +00:00
c186c5ec6c
This PR improves the English in the "CephFS Delayed Deletion" chapter of the Ceph Internals Guide (which is stored in the doc/dev/ directory). There was no pressing need to rewrite this. I just saw that it could be tightened up, and I had the fifteen minutes I needed to do it. Co-author: Anthony D'Atri <anthony.datri@gmail.com> Signed-off-by: Zac Dover <zac.dover@gmail.com>
14 lines
606 B
ReStructuredText
14 lines
606 B
ReStructuredText
=========================
|
|
CephFS delayed deletion
|
|
=========================
|
|
|
|
The deletion of a file does not immediately remove its data. Each of the file's
|
|
underlying objects must be removed independently. If these objects were removed
|
|
immediately, the client would have to send ``size_of_file / stripe_size *
|
|
replication_count`` messages. This would consume significant bandwith and would
|
|
slow the client unacceptably. If snapshots exist, their existence can prevent
|
|
the deletion of objects associated with them.
|
|
|
|
In these cases, such files are (1) marked as deleted on the MDS and (2) deleted
|
|
lazily.
|