Update HOWTO with RADOS information

Signed-off-by: Igor Fedotov <ifedotov@suse.com>

diff --git a/HOWTO b/HOWTO
index 307b50d47c85762f07d82e2e8e332cf5c77f1fb6..f91a22eb10acc72aa2246f2ebd50e06c1e1b0ad8 100644 (file)
--- a/HOWTO
+++ b/HOWTO
@@ -1810,6 +1810,11 @@ I/O engine
                        I/O engine that does regular EXT4_IOC_MOVE_EXT ioctls to simulate
                        defragment activity in request to DDIR_WRITE event.
 
+               **rados**
+                       I/O engine supporting direct access to Ceph Reliable Autonomic
+                       Distributed Object Store (RADOS) via librados. This ioengine
+                       defines engine specific options.
+
                **rbd**
                        I/O engine supporting direct access to Ceph Rados Block Devices
                        (RBD) via librbd without the need to use the kernel rbd driver. This
@@ -2011,7 +2016,7 @@ with the caveat that when used on the command line, they must come after the
                Allocate space immediately inside defragment event, and free right
                after event.
 
-.. option:: clustername=str : [rbd]
+.. option:: clustername=str : [rbd,rados]
 
        Specifies the name of the Ceph cluster.
 
@@ -2019,17 +2024,22 @@ with the caveat that when used on the command line, they must come after the
 
        Specifies the name of the RBD.
 
-.. option:: pool=str : [rbd]
+.. option:: pool=str : [rbd,rados]
 
-       Specifies the name of the Ceph pool containing RBD.
+       Specifies the name of the Ceph pool containing RBD or RADOS data.
 
-.. option:: clientname=str : [rbd]
+.. option:: clientname=str : [rbd,rados]
 
        Specifies the username (without the 'client.' prefix) used to access the
        Ceph cluster. If the *clustername* is specified, the *clientname* shall be
        the full *type.id* string. If no type. prefix is given, fio will add
        'client.' by default.
 
+.. option:: busy_poll=bool : [rbd,rados]
+
+        Poll store instead of waiting for completion. Usually this provides better
+        throughput at cost of higher(up to 100%) CPU utilization.
+
 .. option:: skip_bad=bool : [mtd]
 
        Skip operations against known bad blocks.