ore: RAID5 read
This patch introduces the first stage of RAID5 support
mainly the skip-over-raid-units when reading. For
writes it inserts BLANK units, into where XOR blocks
should be calculated and written to.
It introduces the new "general raid maths", and the main
additional parameters and components needed for raid5.
Since at this stage it could corrupt future version that
actually do support raid5. The enablement of raid5
mounting and setting of parity-count > 0 is disabled. So
the raid5 code will never be used. Mounting of raid5 is
only enabled later once the basic XOR write is also in.
But if the patch "enable RAID5" is applied this code has
been tested to be able to properly read raid5 volumes
and is according to standard.
Also it has been tested that the new maths still properly
supports RAID0 and grouping code just as before.
(BTW: I have found more bugs in the pnfs-obj RAID math
fixed here)
The ore.c file is getting too big, so new ore_raid.[hc]
files are added that will include the special raid stuff
that are not used in striping and mirrors. In future write
support these will get bigger.
When adding the ore_raid.c to Kbuild file I was forced to
rename ore.ko to libore.ko. Is it possible to keep source
file, say ore.c and module file ore.ko the same even if there
are multiple files inside ore.ko?
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index d92998d..fd6090d 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -24,24 +24,9 @@
#include <linux/slab.h>
#include <asm/div64.h>
+#include <linux/lcm.h>
-#include <scsi/osd_ore.h>
-
-#define ORE_ERR(fmt, a...) printk(KERN_ERR "ore: " fmt, ##a)
-
-#ifdef CONFIG_EXOFS_DEBUG
-#define ORE_DBGMSG(fmt, a...) \
- printk(KERN_NOTICE "ore @%s:%d: " fmt, __func__, __LINE__, ##a)
-#else
-#define ORE_DBGMSG(fmt, a...) \
- do { if (0) printk(fmt, ##a); } while (0)
-#endif
-
-/* u64 has problems with printk this will cast it to unsigned long long */
-#define _LLU(x) (unsigned long long)(x)
-
-#define ORE_DBGMSG2(M...) do {} while (0)
-/* #define ORE_DBGMSG2 ORE_DBGMSG */
+#include "ore_raid.h"
MODULE_AUTHOR("Boaz Harrosh <bharrosh@panasas.com>");
MODULE_DESCRIPTION("Objects Raid Engine ore.ko");
@@ -133,21 +118,81 @@
return ore_comp_dev(ios->oc, index);
}
-static int _get_io_state(struct ore_layout *layout,
- struct ore_components *oc, unsigned numdevs,
- struct ore_io_state **pios)
+static 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)
{
struct ore_io_state *ios;
+ struct page **pages;
+ struct osd_sg_entry *sgilist;
+ struct __alloc_all_io_state {
+ struct ore_io_state ios;
+ struct ore_per_dev_state per_dev[numdevs];
+ union {
+ struct osd_sg_entry sglist[sgs_per_dev * numdevs];
+ struct page *pages[num_par_pages];
+ };
+ } *_aios;
- /*TODO: Maybe use kmem_cach per sbi of size
- * exofs_io_state_size(layout->s_numdevs)
- */
- ios = kzalloc(ore_io_state_size(numdevs), GFP_KERNEL);
- if (unlikely(!ios)) {
- ORE_DBGMSG("Failed kzalloc bytes=%d\n",
- ore_io_state_size(numdevs));
- *pios = NULL;
- return -ENOMEM;
+ if (likely(sizeof(*_aios) <= PAGE_SIZE)) {
+ _aios = kzalloc(sizeof(*_aios), GFP_KERNEL);
+ if (unlikely(!_aios)) {
+ ORE_DBGMSG("Failed kzalloc bytes=%zd\n",
+ sizeof(*_aios));
+ *pios = NULL;
+ return -ENOMEM;
+ }
+ pages = num_par_pages ? _aios->pages : NULL;
+ sgilist = sgs_per_dev ? _aios->sglist : NULL;
+ ios = &_aios->ios;
+ } else {
+ struct __alloc_small_io_state {
+ struct ore_io_state ios;
+ struct ore_per_dev_state per_dev[numdevs];
+ } *_aio_small;
+ union __extra_part {
+ struct osd_sg_entry sglist[sgs_per_dev * numdevs];
+ struct page *pages[num_par_pages];
+ } *extra_part;
+
+ _aio_small = kzalloc(sizeof(*_aio_small), GFP_KERNEL);
+ if (unlikely(!_aio_small)) {
+ ORE_DBGMSG("Failed alloc first part bytes=%zd\n",
+ sizeof(*_aio_small));
+ *pios = NULL;
+ return -ENOMEM;
+ }
+ extra_part = kzalloc(sizeof(*extra_part), GFP_KERNEL);
+ if (unlikely(!extra_part)) {
+ ORE_DBGMSG("Failed alloc second part bytes=%zd\n",
+ sizeof(*extra_part));
+ kfree(_aio_small);
+ *pios = NULL;
+ return -ENOMEM;
+ }
+
+ pages = num_par_pages ? extra_part->pages : NULL;
+ sgilist = sgs_per_dev ? extra_part->sglist : NULL;
+ /* In this case the per_dev[0].sgilist holds the pointer to
+ * be freed
+ */
+ ios = &_aio_small->ios;
+ ios->extra_part_alloc = true;
+ }
+
+ if (pages) {
+ ios->parity_pages = pages;
+ ios->max_par_pages = num_par_pages;
+ }
+ if (sgilist) {
+ unsigned d;
+
+ for (d = 0; d < numdevs; ++d) {
+ ios->per_dev[d].sglist = sgilist;
+ sgilist += sgs_per_dev;
+ }
+ ios->sgs_per_dev = sgs_per_dev;
}
ios->layout = layout;
@@ -178,9 +223,42 @@
{
struct ore_io_state *ios;
unsigned numdevs = layout->group_width * layout->mirrors_p1;
+ unsigned sgs_per_dev = 0, max_par_pages = 0;
int ret;
- ret = _get_io_state(layout, oc, numdevs, pios);
+ if (layout->parity && length) {
+ unsigned data_devs = layout->group_width - layout->parity;
+ unsigned stripe_size = layout->stripe_unit * data_devs;
+ unsigned pages_in_unit = layout->stripe_unit / PAGE_SIZE;
+ u32 remainder;
+ u64 num_stripes;
+ u64 num_raid_units;
+
+ num_stripes = div_u64_rem(length, stripe_size, &remainder);
+ if (remainder)
+ ++num_stripes;
+
+ num_raid_units = num_stripes * layout->parity;
+
+ if (is_reading) {
+ /* For reads add per_dev sglist array */
+ /* TODO: Raid 6 we need twice more. Actually:
+ * num_stripes / LCMdP(W,P);
+ * if (W%P != 0) num_stripes *= parity;
+ */
+
+ /* first/last seg is split */
+ num_raid_units += layout->group_width;
+ sgs_per_dev = div_u64(num_raid_units, data_devs);
+ } else {
+ /* For Writes add parity pages array. */
+ max_par_pages = num_raid_units * pages_in_unit *
+ sizeof(struct page *);
+ }
+ }
+
+ ret = _ore_get_io_state(layout, oc, numdevs, sgs_per_dev, max_par_pages,
+ pios);
if (unlikely(ret))
return ret;
@@ -189,10 +267,11 @@
ios->offset = offset;
if (length) {
- ore_calc_stripe_info(layout, offset, &ios->si);
- ios->length = (length <= ios->si.group_length) ? length :
- ios->si.group_length;
+ ore_calc_stripe_info(layout, offset, length, &ios->si);
+ ios->length = ios->si.length;
ios->nr_pages = (ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
+ if (layout->parity)
+ _ore_post_alloc_raid_stuff(ios);
}
return 0;
@@ -209,7 +288,7 @@
int ore_get_io_state(struct ore_layout *layout, struct ore_components *oc,
struct ore_io_state **pios)
{
- return _get_io_state(layout, oc, oc->numdevs, pios);
+ return _ore_get_io_state(layout, oc, oc->numdevs, 0, 0, pios);
}
EXPORT_SYMBOL(ore_get_io_state);
@@ -227,6 +306,7 @@
bio_put(per_dev->bio);
}
+ _ore_free_raid_stuff(ios);
kfree(ios);
}
}
@@ -367,53 +447,65 @@
/*
* L - logical offset into the file
*
- * U - The number of bytes in a stripe within a group
+ * D - number of Data devices
+ * D = group_width - parity
*
- * U = stripe_unit * group_width
+ * U - The number of bytes in a stripe within a group
+ * U = stripe_unit * D
*
* T - The number of bytes striped within a group of component objects
* (before advancing to the next group)
- *
- * T = stripe_unit * group_width * group_depth
+ * T = U * group_depth
*
* S - The number of bytes striped across all component objects
* before the pattern repeats
+ * S = T * group_count
*
- * S = stripe_unit * group_width * group_depth * group_count
- *
- * M - The "major" (i.e., across all components) stripe number
- *
+ * M - The "major" (i.e., across all components) cycle number
* M = L / S
*
- * G - Counts the groups from the beginning of the major stripe
- *
+ * G - Counts the groups from the beginning of the major cycle
* G = (L - (M * S)) / T [or (L % S) / T]
*
* H - The byte offset within the group
- *
* H = (L - (M * S)) % T [or (L % S) % T]
*
* N - The "minor" (i.e., across the group) stripe number
- *
* N = H / U
*
* C - The component index coresponding to L
*
- * C = (H - (N * U)) / stripe_unit + G * group_width
- * [or (L % U) / stripe_unit + G * group_width]
+ * C = (H - (N * U)) / stripe_unit + G * D
+ * [or (L % U) / stripe_unit + G * D]
*
* O - The component offset coresponding to L
- *
* O = L % stripe_unit + N * stripe_unit + M * group_depth * stripe_unit
+ *
+ * LCMdP – Parity cycle: Lowest Common Multiple of group_width, parity
+ * divide by parity
+ * LCMdP = lcm(group_width, parity) / parity
+ *
+ * R - The parity Rotation stripe
+ * (Note parity cycle always starts at a group's boundary)
+ * R = N % LCMdP
+ *
+ * I = the first parity device index
+ * I = (group_width + group_width - R*parity - parity) % group_width
+ *
+ * Craid - The component index Rotated
+ * Craid = (group_width + C - R*parity) % group_width
+ * (We add the group_width to avoid negative numbers modulo math)
*/
void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
- struct ore_striping_info *si)
+ u64 length, struct ore_striping_info *si)
{
u32 stripe_unit = layout->stripe_unit;
u32 group_width = layout->group_width;
u64 group_depth = layout->group_depth;
+ u32 parity = layout->parity;
- u32 U = stripe_unit * group_width;
+ u32 D = group_width - parity;
+ u32 U = D * stripe_unit;
u64 T = U * group_depth;
u64 S = T * layout->group_count;
u64 M = div64_u64(file_offset, S);
@@ -429,22 +521,43 @@
u32 N = div_u64(H, U);
/* "H - (N * U)" is just "H % U" so it's bound to u32 */
- si->dev = (u32)(H - (N * U)) / stripe_unit + G * group_width;
- si->dev *= layout->mirrors_p1;
+ u32 C = (u32)(H - (N * U)) / stripe_unit + G * group_width;
div_u64_rem(file_offset, stripe_unit, &si->unit_off);
si->obj_offset = si->unit_off + (N * stripe_unit) +
(M * group_depth * stripe_unit);
- si->group_length = T - H;
+ if (parity) {
+ u32 LCMdP = lcm(group_width, parity) / parity;
+ /* R = N % LCMdP; */
+ u32 RxP = (N % LCMdP) * parity;
+ u32 first_dev = C - C % group_width;
+
+ si->par_dev = (group_width + group_width - parity - RxP) %
+ group_width + first_dev;
+ si->dev = (group_width + C - RxP) % group_width + first_dev;
+ si->bytes_in_stripe = U;
+ si->first_stripe_start = M * S + G * T + N * U;
+ } else {
+ /* Make the math correct see _prepare_one_group */
+ si->par_dev = group_width;
+ si->dev = C;
+ }
+
+ si->dev *= layout->mirrors_p1;
+ si->par_dev *= layout->mirrors_p1;
+ si->offset = file_offset;
+ si->length = T - H;
+ if (si->length > length)
+ si->length = length;
si->M = M;
}
EXPORT_SYMBOL(ore_calc_stripe_info);
-static int _add_stripe_unit(struct ore_io_state *ios, unsigned *cur_pg,
- unsigned pgbase, struct ore_per_dev_state *per_dev,
- int cur_len)
+int _ore_add_stripe_unit(struct ore_io_state *ios, unsigned *cur_pg,
+ unsigned pgbase, struct page **pages,
+ struct ore_per_dev_state *per_dev, int cur_len)
{
unsigned pg = *cur_pg;
struct request_queue *q =
@@ -455,8 +568,11 @@
if (per_dev->bio == NULL) {
unsigned pages_in_stripe = ios->layout->group_width *
(ios->layout->stripe_unit / PAGE_SIZE);
- unsigned bio_size = (ios->nr_pages + pages_in_stripe) /
- ios->layout->group_width;
+ unsigned nr_pages = ios->nr_pages * ios->layout->group_width /
+ (ios->layout->group_width -
+ ios->layout->parity);
+ unsigned bio_size = (nr_pages + pages_in_stripe) /
+ ios->layout->group_width;
per_dev->bio = bio_kmalloc(GFP_KERNEL, bio_size);
if (unlikely(!per_dev->bio)) {
@@ -471,12 +587,13 @@
unsigned pglen = min_t(unsigned, PAGE_SIZE - pgbase, cur_len);
unsigned added_len;
- BUG_ON(ios->nr_pages <= pg);
cur_len -= pglen;
- added_len = bio_add_pc_page(q, per_dev->bio, ios->pages[pg],
+ added_len = bio_add_pc_page(q, per_dev->bio, pages[pg],
pglen, pgbase);
if (unlikely(pglen != added_len)) {
+ ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=%u\n",
+ per_dev->bio->bi_vcnt);
ret = -ENOMEM;
goto out;
}
@@ -501,9 +618,11 @@
struct ore_striping_info *si = &ios->si;
unsigned stripe_unit = ios->layout->stripe_unit;
unsigned mirrors_p1 = ios->layout->mirrors_p1;
- unsigned devs_in_group = ios->layout->group_width * mirrors_p1;
+ unsigned group_width = ios->layout->group_width;
+ unsigned devs_in_group = group_width * mirrors_p1;
unsigned dev = si->dev;
unsigned first_dev = dev - (dev % devs_in_group);
+ unsigned dev_order;
unsigned cur_pg = ios->pages_consumed;
u64 length = ios->length;
int ret = 0;
@@ -513,7 +632,10 @@
return 0;
}
- BUG_ON(length > si->group_length);
+ BUG_ON(length > si->length);
+
+ dev_order = _dev_order(devs_in_group, mirrors_p1, si->par_dev, dev);
+ si->cur_comp = dev_order;
while (length) {
unsigned comp = dev - first_dev;
@@ -522,17 +644,20 @@
if (!per_dev->length) {
per_dev->dev = dev;
- if (dev < si->dev) {
- per_dev->offset = si->obj_offset + stripe_unit -
- si->unit_off;
- cur_len = stripe_unit;
- } else if (dev == si->dev) {
+ if (dev == si->dev) {
+ WARN_ON(dev == si->par_dev);
per_dev->offset = si->obj_offset;
cur_len = stripe_unit - si->unit_off;
page_off = si->unit_off & ~PAGE_MASK;
BUG_ON(page_off && (page_off != ios->pgbase));
- } else { /* dev > si->dev */
- per_dev->offset = si->obj_offset - si->unit_off;
+ } else {
+ if (si->cur_comp > dev_order)
+ per_dev->offset =
+ si->obj_offset - si->unit_off;
+ else /* si->cur_comp < dev_order */
+ per_dev->offset =
+ si->obj_offset + stripe_unit -
+ si->unit_off;
cur_len = stripe_unit;
}
} else {
@@ -541,8 +666,8 @@
if (cur_len >= length)
cur_len = length;
- ret = _add_stripe_unit(ios, &cur_pg, page_off , per_dev,
- cur_len);
+ ret = _ore_add_stripe_unit(ios, &cur_pg, page_off, ios->pages,
+ per_dev, cur_len);
if (unlikely(ret))
goto out;
@@ -550,6 +675,41 @@
dev = (dev % devs_in_group) + first_dev;
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 we are writing and this is the very last
+ * stripe. then operate on parity dev.
+ */
+ dev = si->par_dev;
+ if (ios->reading)
+ /* In writes cur_len just means if it's the
+ * last one. See _ore_add_parity_unit.
+ */
+ cur_len = length;
+ per_dev = &ios->per_dev[dev - first_dev];
+ if (!per_dev->length) {
+ /* Only/always the parity unit of the first
+ * stripe will be empty. So this is a chance to
+ * initialize the per_dev info.
+ */
+ per_dev->dev = dev;
+ per_dev->offset = si->obj_offset - si->unit_off;
+ }
+
+ ret = _ore_add_parity_unit(ios, si, per_dev, cur_len);
+ if (unlikely(ret))
+ goto out;
+
+ /* Rotate next par_dev backwards with wraping */
+ si->par_dev = (devs_in_group + si->par_dev -
+ ios->layout->parity * mirrors_p1) %
+ devs_in_group + first_dev;
+ /* Next stripe, start fresh */
+ si->cur_comp = 0;
+ }
}
out:
ios->numdevs = devs_in_group;
@@ -747,12 +907,24 @@
per_dev->or = or;
if (ios->pages) {
- osd_req_read(or, obj, per_dev->offset,
- per_dev->bio, per_dev->length);
+ if (per_dev->cur_sg) {
+ /* finalize the last sg_entry */
+ _ore_add_sg_seg(per_dev, 0, false);
+ if (unlikely(!per_dev->cur_sg))
+ return 0; /* Skip parity only device */
+
+ osd_req_read_sg(or, obj, per_dev->bio,
+ per_dev->sglist, per_dev->cur_sg);
+ } else {
+ /* The no raid case */
+ osd_req_read(or, obj, per_dev->offset,
+ per_dev->bio, per_dev->length);
+ }
+
ORE_DBGMSG("read(0x%llx) offset=0x%llx length=0x%llx"
- " dev=%d\n", _LLU(obj->id),
+ " dev=%d sg_len=%d\n", _LLU(obj->id),
_LLU(per_dev->offset), _LLU(per_dev->length),
- first_dev);
+ first_dev, per_dev->cur_sg);
} else {
BUG_ON(ios->kern_buff);
@@ -849,7 +1021,7 @@
{
unsigned stripe_unit = layout->stripe_unit;
- ore_calc_stripe_info(layout, file_offset, &ti->si);
+ ore_calc_stripe_info(layout, file_offset, 0, &ti->si);
ti->prev_group_obj_off = ti->si.M * stripe_unit;
ti->next_group_obj_off = ti->si.M ? (ti->si.M - 1) * stripe_unit : 0;
