[PATCH 2/6] Add support for per-file stream ID

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Writing on flash devices can be much more efficient, if we can
inform the device what kind of data can be grouped together. If
the device is able to group data together with similar lifetimes,
then it can be more efficient in garbage collection. This, in turn,
leads to lower write amplification, which is a win on both device
wear and performance.

Add a new fadvise hint, POSIX_FADV_STREAMID, which sets the file
and inode streamid. The file streamid is used if we have the file
available at the time of the write (O_DIRECT), we use the inode
streamid if not (buffered writeback). The fadvise hint uses the
'offset' field to specify a stream ID.

Signed-off-by: Jens Axboe <axboe@xxxxxx>
---
 fs/inode.c                   |  1 +
 fs/open.c                    |  1 +
 include/linux/fs.h           | 11 +++++++++++
 include/uapi/linux/fadvise.h |  2 ++
 mm/fadvise.c                 | 17 +++++++++++++++++
 5 files changed, 32 insertions(+)

diff --git a/fs/inode.c b/fs/inode.c
index f00b16f45507..41885322ba64 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -149,6 +149,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_blocks = 0;
 	inode->i_bytes = 0;
 	inode->i_generation = 0;
+	inode->i_streamid = 0;
 	inode->i_pipe = NULL;
 	inode->i_bdev = NULL;
 	inode->i_cdev = NULL;
diff --git a/fs/open.c b/fs/open.c
index 33f9cbf2610b..4a9b2be1a674 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -743,6 +743,7 @@ static int do_dentry_open(struct file *f,
 	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
+	f->f_streamid = 0;
 
 	return 0;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b4d71b5e1ff2..6288d9680af6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -631,6 +631,7 @@ struct inode {
 	};
 
 	__u32			i_generation;
+	unsigned int		i_streamid;
 
 #ifdef CONFIG_FSNOTIFY
 	__u32			i_fsnotify_mask; /* all events this inode cares about */
@@ -640,6 +641,14 @@ struct inode {
 	void			*i_private; /* fs or device private pointer */
 };
 
+static inline unsigned int inode_streamid(struct inode *inode)
+{
+	if (inode)
+		return inode->i_streamid;
+
+	return 0;
+}
+
 static inline int inode_unhashed(struct inode *inode)
 {
 	return hlist_unhashed(&inode->i_hash);
@@ -820,6 +829,8 @@ struct file {
 	const struct cred	*f_cred;
 	struct file_ra_state	f_ra;
 
+	unsigned int		f_streamid;
+
 	u64			f_version;
 #ifdef CONFIG_SECURITY
 	void			*f_security;
diff --git a/include/uapi/linux/fadvise.h b/include/uapi/linux/fadvise.h
index e8e747139b9a..3dc8a1ff1422 100644
--- a/include/uapi/linux/fadvise.h
+++ b/include/uapi/linux/fadvise.h
@@ -18,4 +18,6 @@
 #define POSIX_FADV_NOREUSE	5 /* Data will be accessed once.  */
 #endif
 
+#define POSIX_FADV_STREAMID	8 /* associate stream ID with file */
+
 #endif	/* FADVISE_H_INCLUDED */
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 4a3907cf79f8..b111a8899fb7 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -60,6 +60,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 		case POSIX_FADV_WILLNEED:
 		case POSIX_FADV_NOREUSE:
 		case POSIX_FADV_DONTNEED:
+		case POSIX_FADV_STREAMID:
 			/* no bad return value, but ignore advice */
 			break;
 		default:
@@ -144,6 +145,22 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 			}
 		}
 		break;
+	case POSIX_FADV_STREAMID:
+		/*
+		 * streamid is stored in offset... we don't limit or check
+		 * if the device supports streams, or if it does, if the
+		 * stream nr is within the limits. 1 is the lowest valid
+		 * stream id, 0 is "don't care/know".
+		 */
+		if (offset != (unsigned int) offset)
+			ret = EINVAL;
+		else {
+			f.file->f_streamid = offset;
+			spin_lock(&inode->i_lock);
+			inode->i_streamid = offset;
+			spin_unlock(&inode->i_lock);
+		}
+		break;
 	default:
 		ret = -EINVAL;
 	}
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html




[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [Samba]     [Device Mapper]     [CEPH Development]
  Powered by Linux