mirror of
				https://git.proxmox.com/git/mirror_zfs
				synced 2025-11-04 14:26:57 +00:00 
			
		
		
		
	zvol_write() assumes that the write request must be written to stable storage
if rq_is_sync() is true. Unfortunately, this assumption is incorrect. Indeed,
"sync" does *not* mean what we think it means in the context of the Linux
block layer. This is well explained in linux/fs.h:
    WRITE:       A normal async write. Device will be plugged.
    WRITE_SYNC:  Synchronous write. Identical to WRITE, but passes down
                 the hint that someone will be waiting on this IO
                 shortly.
    WRITE_FLUSH: Like WRITE_SYNC but with preceding cache flush.
    WRITE_FUA:   Like WRITE_SYNC but data is guaranteed to be on
                 non-volatile media on completion.
In other words, SYNC does not *mean* that the write must be on stable storage
on completion. It just means that someone is waiting on us to complete the
write request. Thus triggering a ZIL commit for each SYNC write request on a
ZVOL is unnecessary and harmful for performance. To make matters worse, ZVOL
users have no way to express that they actually want data to be written to
stable storage, which means the ZIL is broken for ZVOLs.
The request for stable storage is expressed by the FUA flag, so we must
commit the ZIL after the write if the FUA flag is set. In addition, we must
commit the ZIL before the write if the FLUSH flag is set.
Also, we must inform the block layer that we actually support FLUSH and FUA.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
		
	
			
		
			
				
	
	
		
			47 lines
		
	
	
		
			1.4 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
			
		
		
	
	
			47 lines
		
	
	
		
			1.4 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
dnl #
 | 
						|
dnl # 2.6.36 API change
 | 
						|
dnl # In 2.6.36 kernels the blk_queue_ordered() interface has been
 | 
						|
dnl # replaced by the simpler blk_queue_flush().  However, while the
 | 
						|
dnl # old interface was available to all the new one is GPL-only.
 | 
						|
dnl # Thus in addition to detecting if this function is available
 | 
						|
dnl # we determine if it is GPL-only.  If the GPL-only interface is
 | 
						|
dnl # there we implement our own compatibility function, otherwise
 | 
						|
dnl # we use the function.  The hope is that long term this function
 | 
						|
dnl # will be opened up.
 | 
						|
dnl #
 | 
						|
AC_DEFUN([ZFS_AC_KERNEL_BLK_QUEUE_FLUSH], [
 | 
						|
	AC_MSG_CHECKING([whether blk_queue_flush() is available])
 | 
						|
	tmp_flags="$EXTRA_KCFLAGS"
 | 
						|
	EXTRA_KCFLAGS="-Wno-unused-but-set-variable"
 | 
						|
	ZFS_LINUX_TRY_COMPILE([
 | 
						|
		#include <linux/blkdev.h>
 | 
						|
	],[
 | 
						|
		struct request_queue *q = NULL;
 | 
						|
		(void) blk_queue_flush(q, REQ_FLUSH);
 | 
						|
	],[
 | 
						|
		AC_MSG_RESULT(yes)
 | 
						|
		AC_DEFINE(HAVE_BLK_QUEUE_FLUSH, 1,
 | 
						|
		          [blk_queue_flush() is available])
 | 
						|
	],[
 | 
						|
		AC_MSG_RESULT(no)
 | 
						|
	])
 | 
						|
 | 
						|
	AC_MSG_CHECKING([whether blk_queue_flush() is GPL-only])
 | 
						|
	ZFS_LINUX_TRY_COMPILE([
 | 
						|
		#include <linux/module.h>
 | 
						|
		#include <linux/blkdev.h>
 | 
						|
 | 
						|
		MODULE_LICENSE("CDDL");
 | 
						|
	],[
 | 
						|
		struct request_queue *q = NULL;
 | 
						|
		(void) blk_queue_flush(q, REQ_FLUSH);
 | 
						|
	],[
 | 
						|
		AC_MSG_RESULT(no)
 | 
						|
	],[
 | 
						|
		AC_MSG_RESULT(yes)
 | 
						|
		AC_DEFINE(HAVE_BLK_QUEUE_FLUSH_GPL_ONLY, 1,
 | 
						|
		          [blk_queue_flush() is GPL-only])
 | 
						|
	])
 | 
						|
	EXTRA_KCFLAGS="$tmp_flags"
 | 
						|
])
 |