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. A second
POSIX_FADV_FILE_STREAMID sets only the stream ID on the file,
not the inode.
Signed-off-by: Jens Axboe <axboe@xxxxxx>
---
fs/inode.c | 1 +
fs/open.c | 1 +
include/linux/fs.h | 22 ++++++++++++++++++++++
include/uapi/linux/fadvise.h | 3 +++
mm/fadvise.c | 25 +++++++++++++++++++++++++
5 files changed, 52 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 6796f04d6032..979f34ff165b 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 c7496f263860..f43b866c3639 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -648,6 +648,7 @@ struct inode {
#ifdef CONFIG_IMA
atomic_t i_readcount; /* struct files open RO */
#endif
+ unsigned int i_streamid;
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
struct file_lock_context *i_flctx;
struct address_space i_data;
@@ -668,6 +669,14 @@ 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);
@@ -839,6 +848,7 @@ struct file {
* Must not be taken from IRQ context.
*/
spinlock_t f_lock;
+ unsigned int f_streamid;
atomic_long_t f_count;
unsigned int f_flags;
fmode_t f_mode;
@@ -870,6 +880,18 @@ struct file_handle {
unsigned char f_handle[0];
};
+/*
+ * If the file doesn't have a stream ID set, return the inode stream ID
+ * in case that has been set.
+ */
+static inline unsigned int file_streamid(struct file *f)
+{
+ if (f->f_streamid)
+ return f->f_streamid;
+
+ return inode_streamid(f->f_inode);
+}
+
static inline struct file *get_file(struct file *f)
{
atomic_long_inc(&f->f_count);
diff --git a/include/uapi/linux/fadvise.h b/include/uapi/linux/fadvise.h
index e8e747139b9a..e6e561db7f88 100644
--- a/include/uapi/linux/fadvise.h
+++ b/include/uapi/linux/fadvise.h
@@ -18,4 +18,7 @@
#define POSIX_FADV_NOREUSE 5 /* Data will be accessed once. */
#endif
+#define POSIX_FADV_STREAMID 8 /* associate stream ID with file+inode */
+#define POSIX_FADV_FILE_STREAMID 9 /* associate stream ID with file */
+
#endif /* FADVISE_H_INCLUDED */
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 4a3907cf79f8..a56e81840040 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -60,6 +60,8 @@ 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:
+ case POSIX_FADV_FILE_STREAMID:
/* no bad return value, but ignore advice */
break;
default:
@@ -144,6 +146,29 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
}
}
break;
+ case POSIX_FADV_STREAMID:
+ case POSIX_FADV_FILE_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;
+ break;
+ }
+ /*
+ * FILE_STREAMID stores only in the file, STREAMID stores
+ * the stream hint in both the file and the inode.
+ */
+ f.file->f_streamid = offset;
+ if (advice == POSIX_FADV_STREAMID) {
+ spin_lock(&inode->i_lock);
+ inode->i_streamid = offset;
+ spin_unlock(&inode->i_lock);
+ }
+ break;
default:
ret = -EINVAL;
}
--
2.4.0.rc2.1.g3d6bc9a
--
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
