exofs: Override read-ahead to align on stripe_size
* Set all inode->i_mapping->backing_dev_info to point to
the per super-block sb->s_bdi.
* Calculating a read_ahead that is:
- preferable 2 stripes long
(Future patch will add a mount option to override this)
- Minimum 128K aligned up to stripe-size
- Caped to maximum-IO-sizes round down to stripe_size.
(Max sizes are governed by max bio-size that fits in a page
times number-of-devices)
CC: Marc Dionne <marc.c.dionne@gmail.com>
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
index 2dc925f..99fcb91 100644
--- a/fs/exofs/exofs.h
+++ b/fs/exofs/exofs.h
@@ -256,6 +256,8 @@
}
/* inode.c */
+unsigned exofs_max_io_pages(struct exofs_layout *layout,
+ unsigned expected_pages);
int exofs_setattr(struct dentry *, struct iattr *);
int exofs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index fb9d380..681b3cb 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -43,6 +43,17 @@
PAGE_SIZE / sizeof(struct page *),
};
+unsigned exofs_max_io_pages(struct exofs_layout *layout,
+ unsigned expected_pages)
+{
+ unsigned pages = min_t(unsigned, expected_pages, MAX_PAGES_KMALLOC);
+
+ /* TODO: easily support bio chaining */
+ pages = min_t(unsigned, pages,
+ layout->group_width * BIO_MAX_PAGES_KMALLOC);
+ return pages;
+}
+
struct page_collect {
struct exofs_sb_info *sbi;
struct inode *inode;
@@ -97,8 +108,7 @@
static int pcol_try_alloc(struct page_collect *pcol)
{
- unsigned pages = min_t(unsigned, pcol->expected_pages,
- MAX_PAGES_KMALLOC);
+ unsigned pages;
if (!pcol->ios) { /* First time allocate io_state */
int ret = exofs_get_io_state(&pcol->sbi->layout, &pcol->ios);
@@ -108,8 +118,7 @@
}
/* TODO: easily support bio chaining */
- pages = min_t(unsigned, pages,
- pcol->sbi->layout.group_width * BIO_MAX_PAGES_KMALLOC);
+ pages = exofs_max_io_pages(&pcol->sbi->layout, pcol->expected_pages);
for (; pages; pages >>= 1) {
pcol->pages = kmalloc(pages * sizeof(struct page *),
@@ -1049,6 +1058,7 @@
memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
}
+ inode->i_mapping->backing_dev_info = sb->s_bdi;
if (S_ISREG(inode->i_mode)) {
inode->i_op = &exofs_file_inode_operations;
inode->i_fop = &exofs_file_operations;
@@ -1149,6 +1159,7 @@
sbi = sb->s_fs_info;
+ inode->i_mapping->backing_dev_info = sb->s_bdi;
sb->s_dirt = 1;
inode_init_owner(inode, dir, mode);
inode->i_ino = sbi->s_nextid++;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 78f5ad6..e87510f 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -390,6 +390,23 @@
return 0;
}
+static unsigned __ra_pages(struct exofs_layout *layout)
+{
+ const unsigned _MIN_RA = 32; /* min 128K read-ahead */
+ unsigned ra_pages = layout->group_width * layout->stripe_unit /
+ PAGE_SIZE;
+ unsigned max_io_pages = exofs_max_io_pages(layout, ~0);
+
+ ra_pages *= 2; /* two stripes */
+ if (ra_pages < _MIN_RA)
+ ra_pages = roundup(_MIN_RA, ra_pages / 2);
+
+ if (ra_pages > max_io_pages)
+ ra_pages = max_io_pages;
+
+ return ra_pages;
+}
+
/* @odi is valid only as long as @fscb_dev is valid */
static int exofs_devs_2_odi(struct exofs_dt_device_info *dt_dev,
struct osd_dev_info *odi)
@@ -623,6 +640,7 @@
}
/* set up operation vectors */
+ sbi->bdi.ra_pages = __ra_pages(&sbi->layout);
sb->s_bdi = &sbi->bdi;
sb->s_fs_info = sbi;
sb->s_op = &exofs_sops;