ore: RAID5 Write
This is finally the RAID5 Write support.
The bigger part of this patch is not the XOR engine itself, But the
read4write logic, which is a complete mini prepare_for_striping
reading engine that can read scattered pages of a stripe into cache
so it can be used for XOR calculation. That is, if the write was not
stripe aligned.
The main algorithm behind the XOR engine is the 2 dimensional array:
struct __stripe_pages_2d.
A drawing might save 1000 words
---
__stripe_pages_2d
|
n = pages_in_stripe_unit;
w = group_width - parity;
| pages array presented to the XOR lib
| |
V |
__1_page_stripe[0].pages --> [c0][c1]..[cw][c_par] <---|
| |
__1_page_stripe[1].pages --> [c0][c1]..[cw][c_par] <---
|
... | ...
|
__1_page_stripe[n].pages --> [c0][c1]..[cw][c_par]
^
|
data added columns first then row
---
The pages are put on this array columns first. .i.e:
p0-of-c0, p1-of-c0, ... pn-of-c0, p0-of-c1, ...
So we are doing a corner turn of the pages.
Note that pages will zigzag down and left. but are put sequentially
in growing order. So when the time comes to XOR the stripe, only the
beginning and end of the array need be checked. We scan the array
and any NULL spot will be field by pages-to-be-read.
The FS that wants to support RAID5 needs to supply an
operations-vector that searches a given page in cache, and specifies
if the page is uptodate or need reading. All these pages to be read
are put on a slave ore_io_state and synchronously read. All the pages
of a stripe are read in one IO, using the scatter gather mechanism.
In write we constrain our IO to only be incomplete on a single
stripe. Meaning either the complete IO is within a single stripe so
we might have pages to read from both beginning or end of the
strip. Or we have some reading to do at beginning but end at strip
boundary. The left over pages are pushed to the next IO by the API
already established by previous work, where an IO offset/length
combination presented to the ORE might get the length truncated and
the user must re-submit the leftover pages. (Both exofs and NFS
support this)
But any ORE user should make it's best effort to align it's IO
before hand and avoid complications. A cached ore_layout->stripe_size
member can be used for that calculation. (NOTE: that ORE demands
that stripe_size may not be bigger then 32bit)
What else? Well read it and tell me.
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index fd6090d..08ee454 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -95,6 +95,14 @@
layout->max_io_length =
(BIO_MAX_PAGES_KMALLOC * PAGE_SIZE - layout->stripe_unit) *
layout->group_width;
+ if (layout->parity) {
+ unsigned stripe_length =
+ (layout->group_width - layout->parity) *
+ layout->stripe_unit;
+
+ layout->max_io_length /= stripe_length;
+ layout->max_io_length *= stripe_length;
+ }
return 0;
}
EXPORT_SYMBOL(ore_verify_layout);
@@ -118,7 +126,7 @@
return ore_comp_dev(ios->oc, index);
}
-static int _ore_get_io_state(struct ore_layout *layout,
+int _ore_get_io_state(struct ore_layout *layout,
struct ore_components *oc, unsigned numdevs,
unsigned sgs_per_dev, unsigned num_par_pages,
struct ore_io_state **pios)
@@ -334,7 +342,7 @@
kref_put(&ios->kref, _last_io);
}
-static int ore_io_execute(struct ore_io_state *ios)
+int ore_io_execute(struct ore_io_state *ios)
{
DECLARE_COMPLETION_ONSTACK(wait);
bool sync = (ios->done == NULL);
@@ -597,6 +605,8 @@
ret = -ENOMEM;
goto out;
}
+ _add_stripe_page(ios->sp2d, &ios->si, pages[pg]);
+
pgbase = 0;
++pg;
}
@@ -636,6 +646,7 @@
dev_order = _dev_order(devs_in_group, mirrors_p1, si->par_dev, dev);
si->cur_comp = dev_order;
+ si->cur_pg = si->unit_off / PAGE_SIZE;
while (length) {
unsigned comp = dev - first_dev;
@@ -677,14 +688,14 @@
length -= cur_len;
si->cur_comp = (si->cur_comp + 1) % group_width;
- if (unlikely((dev == si->par_dev) ||
- (!length && ios->parity_pages))) {
- if (!length)
+ if (unlikely((dev == si->par_dev) || (!length && ios->sp2d))) {
+ if (!length && ios->sp2d) {
/* If we are writing and this is the very last
* stripe. then operate on parity dev.
*/
dev = si->par_dev;
- if (ios->reading)
+ }
+ if (ios->sp2d)
/* In writes cur_len just means if it's the
* last one. See _ore_add_parity_unit.
*/
@@ -709,6 +720,7 @@
devs_in_group + first_dev;
/* Next stripe, start fresh */
si->cur_comp = 0;
+ si->cur_pg = 0;
}
}
out:
@@ -873,6 +885,14 @@
int i;
int ret;
+ if (unlikely(ios->sp2d && !ios->r4w)) {
+ /* A library is attempting a RAID-write without providing
+ * a pages lock interface.
+ */
+ WARN_ON_ONCE(1);
+ return -ENOTSUPP;
+ }
+
ret = _prepare_for_striping(ios);
if (unlikely(ret))
return ret;
@@ -888,7 +908,7 @@
}
EXPORT_SYMBOL(ore_write);
-static int _read_mirror(struct ore_io_state *ios, unsigned cur_comp)
+int _ore_read_mirror(struct ore_io_state *ios, unsigned cur_comp)
{
struct osd_request *or;
struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp];
@@ -952,7 +972,7 @@
return ret;
for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
- ret = _read_mirror(ios, i);
+ ret = _ore_read_mirror(ios, i);
if (unlikely(ret))
return ret;
}