copy_file_range support in GlusterFS

    * libglusterfs changes to add new fop

    * Fuse changes:
      - Changes in fuse bridge xlator to receive and send responses

    * posix changes to perform the op on the backend filesystem

    * protocol and rpc changes for sending and receiving the fop

    * gfapi changes for performing the fop

    * tools: glfs-copy-file-range tool for testing copy_file_range fop

      - Although, copy_file_range support has been added to the upstream
	    fuse kernel module, no release has been made yet of a kernel
        which contains the support. It is expected to come in the
        upcoming release of linux-4.20

        So, as of now, executing copy_file_range fop on a fused based
        filesystem results in fuse kernel module sending read on the
	    source fd and write on the destination fd.

	    Therefore a small gfapi based tool has been written to be able
        test the copy_file_range fop. This tool is similar (in functionality)
	    to the example program given in copy_file_range man page.

	    So, running regular copy_file_range on a fuse mount point and
	    running gfapi based glfs-copy-file-range tool gives some idea about
	    how fast, the copy_file_range (or reflink) can be.

	    On the local machine this was the result obtained.

	    mount -t glusterfs workstation:new /mnt/glusterfs
	    [root@workstation ~]# cd /mnt/glusterfs/
	    [root@workstation glusterfs]# ls
	    file
	    [root@workstation glusterfs]# cd
	    [root@workstation ~]# time /tmp/a.out /mnt/glusterfs/file /mnt/glusterfs/new
	    real  0m6.495s
	    user  0m0.000s
	    sys   0m1.439s
	    [root@workstation ~]# time glfs-copy-file-range $(hostname) new /tmp/glfs.log /file /rrr
	    OPEN_SRC: opening /file is success
	    OPEN_DST: opening /rrr is success
	    FSTAT_SRC: fstat on /rrr is success
	    copy_file_range successful

        real  0m0.309s
        user  0m0.039s
        sys   0m0.017s

        This tool needs following arguments
         1) hostname
         2) volume name
         3) log file path
         4) source file path (relative to the gluster volume root)
         5) destination file path (relative to the gluster volume root)

        "glfs-copy-file-range <hostname> <volume> <log file path> <source> <destination>"

      - Added a testcase as well to run glfs-copy-file-range tool

    * io-stats changes to capture the fop for profiling

    * NOTE:

      - Added conditional check to see whether the copy_file_range syscall
        is available or not. If not, then return ENOSYS.

      - Added conditional check for kernel minor version in fuse_kernel.h
        and fuse-bridge while referring to copy_file_range. And the kernel
        minor version is kept as it is. i.e. 24. Increment it in future
        when there is a kernel release which contains the support for
        copy_file_range fop in fuse kernel module.

    * The document which contains a writeup on this enhancement can be found at
      https://docs.google.com/document/d/1BSILbXr_knynNwxSyyu503JoTz5QFM_4suNIh2WwrSc/edit

Change-Id: I280069c814dd21ce6ec3be00a884fc24ab692367
updates: #536
Signed-off-by: Raghavendra Bhat <raghavendra@redhat.com>

1 files changed, 13 insertions, 0 deletions

diff --git a/libglusterfs/src/glusterfs/xlator.h b/libglusterfs/src/glusterfs/xlator.h
index 4137d12eb27..12d507bc021 100644
--- a/libglusterfs/src/glusterfs/xlator.h
+++ b/libglusterfs/src/glusterfs/xlator.h
@@ -23,6 +23,7 @@
 #include "glusterfs/list.h"
 #include "glusterfs/latency.h"
 #include "glusterfs/compat-uuid.h"
+#include "glusterfs/syscall.h"
 
 #define FIRST_CHILD(xl) (xl->children->xlator)
 #define SECOND_CHILD(xl) (xl->children->next->xlator)
@@ -354,6 +355,11 @@ typedef int32_t (*fop_namelink_cbk_t)(call_frame_t *frame, void *cookie,
                                       int32_t op_errno, struct iatt *prebuf,
                                       struct iatt *postbuf, dict_t *xdata);
 
+typedef int32_t (*fop_copy_file_range_cbk_t)(
+    call_frame_t *frame, void *cookie, xlator_t *this, int32_t op_ret,
+    int32_t op_errno, struct iatt *stbuf, struct iatt *prebuf_dst,
+    struct iatt *postbuf_dst, dict_t *xdata);
+
 typedef int32_t (*fop_lookup_t)(call_frame_t *frame, xlator_t *this, loc_t *loc,
                                 dict_t *xdata);
 
@@ -544,6 +550,11 @@ typedef int32_t (*fop_icreate_t)(call_frame_t *frame, xlator_t *this,
 
 typedef int32_t (*fop_namelink_t)(call_frame_t *frame, xlator_t *this,
                                   loc_t *loc, dict_t *xdata);
+typedef int32_t (*fop_copy_file_range_t)(call_frame_t *frame, xlator_t *this,
+                                         fd_t *fd_in, off64_t off_in,
+                                         fd_t *fd_out, off64_t off_out,
+                                         size_t len, uint32_t flags,
+                                         dict_t *xdata);
 
 /* WARNING: make sure the list is in order with FOP definition in
    `rpc/xdr/src/glusterfs-fops.x`.
@@ -609,6 +620,7 @@ struct xlator_fops {
     fop_put_t put;
     fop_icreate_t icreate;
     fop_namelink_t namelink;
+    fop_copy_file_range_t copy_file_range;
 
     /* these entries are used for a typechecking hack in STACK_WIND _only_ */
     /* make sure to add _cbk variables only after defining regular fops as
@@ -673,6 +685,7 @@ struct xlator_fops {
     fop_put_cbk_t put_cbk;
     fop_icreate_cbk_t icreate_cbk;
     fop_namelink_cbk_t namelink_cbk;
+    fop_copy_file_range_cbk_t copy_file_range_cbk;
 };
 
 typedef int32_t (*cbk_forget_t)(xlator_t *this, inode_t *inode);