scst README: add section about VMware and Ceph RBD space reclaim

Reported-by: Alex Gorbachev <ag@iss-integration.com>



git-svn-id: http://svn.code.sf.net/p/scst/svn/trunk@6961 d57e44dd-8a1f-0410-8b47-8ef2f437770f
This commit is contained in:
Vladislav Bolkhovitin
2016-08-20 01:33:47 +00:00
parent 68fc4a14b1
commit 610325e5c2
2 changed files with 28 additions and 0 deletions
+14
View File
@@ -1952,6 +1952,20 @@ context switch is natural for such potentially long operation as
EXTENDED COPY.
VMware and Ceph RBD space reclaim
---------------------------------
VMware with VMFS5 filesystem ignores UNMAP alignment, so if you use 4MB
Ceph RBD objects and VMFS5, only some discards will reclaim RBD space
due to 1MB discard not often hitting the tail of objects.
Thus, to have efficient ESXi space reclamation with RBD and VMFS5, you are
recommended to use 1 MB object size in Ceph.
See https://sourceforge.net/p/scst/mailman/message/35287598 thread for
details.
Caching
-------
+14
View File
@@ -1805,6 +1805,20 @@ context switch is natural for such potentially long operation as
EXTENDED COPY.
VMware and Ceph RBD space reclaim
---------------------------------
VMware with VMFS5 filesystem ignores UNMAP alignment, so if you use 4MB
Ceph RBD objects and VMFS5, only some discards will reclaim RBD space
due to 1MB discard not often hitting the tail of objects.
Thus, to have efficient ESXi space reclamation with RBD and VMFS5, you are
recommended to use 1 MB object size in Ceph.
See https://sourceforge.net/p/scst/mailman/message/35287598 thread for
details.
Caching
-------