ore: RAID5 Support

index 69dc236..0c522c6 100644
@@ -295,7 +295,7 @@ static int _maybe_not_all_in_one_io(struct ore_io_state *ios,
 		for (i = 0; i < pages_less; ++i)
 			pcol->pages[i] = *src_page++;
 
-		EXOFS_DBGMSG("Length was adjusted nr_pages=0x%x pages_less=%d "
+		EXOFS_DBGMSG("Length was adjusted nr_pages=0x%x pages_less=0x%x "
 			"expected_pages=0x%x next_offset=0x%llx "
 			"next_len=0x%lx\n",
 			pcol_src->nr_pages, pages_less, pcol->expected_pages,

@@ -758,14 +758,19 @@ static int exofs_writepages(struct address_space *mapping,
 
 	if (wbc->sync_mode == WB_SYNC_ALL) {
 		return write_exec(&pcol); /* pump the last reminder */
-	} else {/* not SYNC let the reminder join the next writeout */
+	} else if (pcol.nr_pages) {
+		/* not SYNC let the reminder join the next writeout */
 		unsigned i;
 
-		for (i = 0; i < pcol.nr_pages; i++)
-			unlock_page(pcol.pages[i]);
+		for (i = 0; i < pcol.nr_pages; i++) {
+			struct page *page = pcol.pages[i];
 
-		return 0;
+			end_page_writeback(page);
+			set_page_dirty(page);
+			unlock_page(page);
+		}
 	}
+	return 0;
 }
 
 static int exofs_writepage(struct page *page, struct writeback_control *wbc)

index 0dafd50..3b1cc3a 100644
@@ -506,7 +506,6 @@ static int _prepare_for_striping(struct ore_io_state *ios)
 	unsigned devs_in_group = ios->layout->group_width * mirrors_p1;
 	unsigned dev = si->dev;
 	unsigned first_dev = dev - (dev % devs_in_group);
-	unsigned max_comp = ios->numdevs ? ios->numdevs - mirrors_p1 : 0;
 	unsigned cur_pg = ios->pages_consumed;
 	u64 length = ios->length;
 	int ret = 0;

@@ -538,9 +537,6 @@ static int _prepare_for_striping(struct ore_io_state *ios)
 				per_dev->offset = si->obj_offset - si->unit_off;
 				cur_len = stripe_unit;
 			}
-
-			if (max_comp < comp)
-				max_comp = comp;
 		} else {
 			cur_len = stripe_unit;
 		}

@@ -558,7 +554,7 @@ static int _prepare_for_striping(struct ore_io_state *ios)
 		length -= cur_len;
 	}
 out:
-	ios->numdevs = max_comp + mirrors_p1;
+	ios->numdevs = devs_in_group;
 	ios->pages_consumed = cur_pg;
 	if (unlikely(ret)) {
 		if (length == ios->length)

487 lines not on this page · raw message

140 lines not on this page · raw message

64 lines not on this page · raw message

index a8e39d1..43821c1 100644
@@ -40,6 +40,7 @@ struct ore_layout {
 	unsigned mirrors_p1;
 
 	unsigned group_width;
+	unsigned parity;
 	u64	 group_depth;
 	unsigned group_count;
 

@@ -89,11 +90,16 @@ static inline void ore_comp_set_dev(
 }
 
 struct ore_striping_info {
+	u64 offset;
 	u64 obj_offset;
-	u64 group_length;
+	u64 length;
+	u64 first_stripe_start; /* only used in raid writes */
 	u64 M; /* for truncate */
+	unsigned bytes_in_stripe;
 	unsigned dev;
+	unsigned par_dev;
 	unsigned unit_off;
+	unsigned cur_comp;
 };
 
 struct ore_io_state;

@@ -127,6 +133,13 @@ struct ore_io_state {
 
 	bool			reading;
 
+	/* House keeping of Parity pages */
+	bool			extra_part_alloc;
+	struct page		**parity_pages;
+	unsigned		max_par_pages;
+	unsigned		cur_par_page;
+	unsigned		sgs_per_dev;
+
 	/* Variable array of size numdevs */
 	unsigned numdevs;
 	struct ore_per_dev_state {

@@ -134,7 +147,10 @@ struct ore_io_state {
 		struct bio *bio;
 		loff_t offset;
 		unsigned length;
+		unsigned last_sgs_total;
 		unsigned dev;
+		struct osd_sg_entry *sglist;
+		unsigned cur_sg;
 	} per_dev[];
 };
 

@@ -147,8 +163,7 @@ static inline unsigned ore_io_state_size(unsigned numdevs)
 /* ore.c */
 int ore_verify_layout(unsigned total_comps, struct ore_layout *layout);
 void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
-			  struct ore_striping_info *si);
-
+			  u64 length, struct ore_striping_info *si);
 int ore_get_rw_state(struct ore_layout *layout, struct ore_components *comps,
 		     bool is_reading, u64 offset, u64 length,
 		     struct ore_io_state **ios);

index fd6090d..08ee454 100644
@@ -95,6 +95,14 @@ int ore_verify_layout(unsigned total_comps, struct ore_layout *layout)
 	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 @@ static struct osd_dev *_ios_od(struct ore_io_state *ios, unsigned index)
 	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 @@ static void _done_io(struct osd_request *or, void *p)
 	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 @@ int _ore_add_stripe_unit(struct ore_io_state *ios,  unsigned *cur_pg,
 			ret = -ENOMEM;
 			goto out;
 		}
+		_add_stripe_page(ios->sp2d, &ios->si, pages[pg]);
+
 		pgbase = 0;
 		++pg;
 	}

@@ -636,6 +646,7 @@ static int _prepare_for_striping(struct ore_io_state *ios)
 
 	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 @@ static int _prepare_for_striping(struct ore_io_state *ios)
 		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 @@ static int _prepare_for_striping(struct ore_io_state *ios)
 				      devs_in_group + first_dev;
 			/* Next stripe, start fresh */
 			si->cur_comp = 0;
+			si->cur_pg = 0;
 		}
 	}
 out:

@@ -873,6 +885,14 @@ int ore_write(struct ore_io_state *ios)
 	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 @@ int ore_write(struct ore_io_state *ios)
 }
 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 @@ int ore_read(struct ore_io_state *ios)
 		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;
 	}

599 lines not on this page · raw message

index c21080b..2ffd2c3 100644
@@ -57,8 +57,23 @@ void _ore_add_sg_seg(struct ore_per_dev_state *per_dev, unsigned cur_len,
 		 bool not_last);
 int _ore_add_parity_unit(struct ore_io_state *ios, struct ore_striping_info *si,
 		     struct ore_per_dev_state *per_dev, unsigned cur_len);
+void _ore_add_stripe_page(struct __stripe_pages_2d *sp2d,
+		       struct ore_striping_info *si, struct page *page);
+static inline void _add_stripe_page(struct __stripe_pages_2d *sp2d,
+				struct ore_striping_info *si, struct page *page)
+{
+	if (!sp2d) /* Inline the fast path */
+		return; /* Hay no raid stuff */
+	_ore_add_stripe_page(sp2d, si, page);
+}
 
 /* ios.c stuff needed by ios_raid.c */
+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);
 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);
+int _ore_read_mirror(struct ore_io_state *ios, unsigned cur_comp);
+int ore_io_execute(struct ore_io_state *ios);

index 43821c1..f05fa82 100644
@@ -99,11 +99,17 @@ struct ore_striping_info {
 	unsigned dev;
 	unsigned par_dev;
 	unsigned unit_off;
+	unsigned cur_pg;
 	unsigned cur_comp;
 };
 
 struct ore_io_state;
 typedef void (*ore_io_done_fn)(struct ore_io_state *ios, void *private);
+struct _ore_r4w_op {
+	/* @Priv given here is passed ios->private */
+	struct page * (*get_page)(void *priv, u64 page_index, bool *uptodate);
+	void (*put_page)(void *priv, struct page *page);
+};
 
 struct ore_io_state {
 	struct kref		kref;

@@ -139,6 +145,9 @@ struct ore_io_state {
 	unsigned		max_par_pages;
 	unsigned		cur_par_page;
 	unsigned		sgs_per_dev;
+	struct __stripe_pages_2d *sp2d;
+	struct ore_io_state	 *ios_read_4_write;
+	const struct _ore_r4w_op *r4w;
 
 	/* Variable array of size numdevs */
 	unsigned numdevs;

index 3161da6..c807ab9 100644
@@ -459,6 +459,43 @@ static void _write_done(struct ore_io_state *ios, void *private)
 	objlayout_write_done(&objios->oir, status, objios->sync);
 }
 
+static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
+{
+	struct objio_state *objios = priv;
+	struct nfs_write_data *wdata = objios->oir.rpcdata;
+	pgoff_t index = offset / PAGE_SIZE;
+	struct page *page = find_get_page(wdata->inode->i_mapping, index);
+
+	if (!page) {
+		page = find_or_create_page(wdata->inode->i_mapping,
+						index, GFP_NOFS);
+		if (unlikely(!page)) {
+			dprintk("%s: grab_cache_page Failed index=0x%lx\n",
+				__func__, index);
+			return NULL;
+		}
+		unlock_page(page);
+	}
+	if (PageDirty(page) || PageWriteback(page))
+		*uptodate = true;
+	else
+		*uptodate = PageUptodate(page);
+	dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate);
+	return page;
+}
+
+static void __r4w_put_page(void *priv, struct page *page)
+{
+	dprintk("%s: index=0x%lx\n", __func__, page->index);
+	page_cache_release(page);
+	return;
+}
+
+static const struct _ore_r4w_op _r4w_op = {
+	.get_page = &__r4w_get_page,
+	.put_page = &__r4w_put_page,
+};
+
 int objio_write_pagelist(struct nfs_write_data *wdata, int how)
 {
 	struct objio_state *objios;

@@ -472,6 +509,7 @@ int objio_write_pagelist(struct nfs_write_data *wdata, int how)
 		return ret;
 
 	objios->sync = 0 != (how & FLUSH_SYNC);
+	objios->ios->r4w = &_r4w_op;
 
 	if (!objios->sync)
 		objios->ios->done = _write_done;

index 08ee454..fcfa86a 100644
@@ -49,9 +49,17 @@ int ore_verify_layout(unsigned total_comps, struct ore_layout *layout)
 {
 	u64 stripe_length;
 
-/* FIXME: Only raid0 is supported for now. */
-	if (layout->raid_algorithm != PNFS_OSD_RAID_0) {
-		ORE_ERR("Only RAID_0 for now\n");
+	switch (layout->raid_algorithm) {
+	case PNFS_OSD_RAID_0:
+		layout->parity = 0;
+		break;
+	case PNFS_OSD_RAID_5:
+		layout->parity = 1;
+		break;
+	case PNFS_OSD_RAID_PQ:
+	case PNFS_OSD_RAID_4:
+	default:
+		ORE_ERR("Only RAID_0/5 for now\n");
 		return -EINVAL;
 	}
 	if (0 != (layout->stripe_unit & ~PAGE_MASK)) {

index 3b1cc3a..d92998d 100644
@@ -57,9 +57,6 @@ MODULE_LICENSE("GPL");
  * 3. Cache some havily used calculations that will be needed by users.
  */
 
-static void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
-				 struct ore_striping_info *si);
-
 enum { BIO_MAX_PAGES_KMALLOC =
 		(PAGE_SIZE - sizeof(struct bio)) / sizeof(struct bio_vec),};
 

@@ -409,8 +406,8 @@ EXPORT_SYMBOL(ore_check_io);
  *
  *	O = L % stripe_unit + N * stripe_unit + M * group_depth * stripe_unit
  */
-static void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
-				 struct ore_striping_info *si)
+void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
+			  struct ore_striping_info *si)
 {
 	u32	stripe_unit = layout->stripe_unit;
 	u32	group_width = layout->group_width;

@@ -443,6 +440,7 @@ static void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
 	si->group_length = T - H;
 	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,

index af2231a..a8e39d1 100644
@@ -146,6 +146,9 @@ static inline unsigned ore_io_state_size(unsigned numdevs)
 
 /* ore.c */
 int ore_verify_layout(unsigned total_comps, struct ore_layout *layout);
+void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
+			  struct ore_striping_info *si);
+
 int ore_get_rw_state(struct ore_layout *layout, struct ore_components *comps,
 		     bool is_reading, u64 offset, u64 length,
 		     struct ore_io_state **ios);

index 86c0ac8..3e5f3a6 100644
@@ -63,6 +63,7 @@ struct page_collect {
 	bool read_4_write; /* This means two things: that the read is sync
 			    * And the pages should not be unlocked.
 			    */
+	struct page *that_locked_page;
 };
 
 static void _pcol_init(struct page_collect *pcol, unsigned expected_pages,

@@ -81,6 +82,7 @@ static void _pcol_init(struct page_collect *pcol, unsigned expected_pages,
 	pcol->length = 0;
 	pcol->pg_first = -1;
 	pcol->read_4_write = false;
+	pcol->that_locked_page = NULL;
 }
 
 static void _pcol_reset(struct page_collect *pcol)

@@ -93,6 +95,7 @@ static void _pcol_reset(struct page_collect *pcol)
 	pcol->length = 0;
 	pcol->pg_first = -1;
 	pcol->ios = NULL;
+	pcol->that_locked_page = NULL;
 
 	/* this is probably the end of the loop but in writes
 	 * it might not end here. don't be left with nothing

@@ -391,6 +394,8 @@ static int readpage_strip(void *data, struct page *page)
 		EXOFS_ERR("PageUptodate(0x%lx, 0x%lx)\n", pcol->inode->i_ino,
 			  page->index);
 
+	pcol->that_locked_page = page;
+
 	if (page->index < end_index)
 		len = PAGE_CACHE_SIZE;
 	else if (page->index == end_index)

@@ -560,6 +565,56 @@ static void writepages_done(struct ore_io_state *ios, void *p)
 	EXOFS_DBGMSG2("writepages_done END\n");
 }
 
+static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
+{
+	struct page_collect *pcol = priv;
+	pgoff_t index = offset / PAGE_SIZE;
+
+	if (!pcol->that_locked_page ||
+	    (pcol->that_locked_page->index != index)) {
+		struct page *page = find_get_page(pcol->inode->i_mapping, index);
+
+		if (!page) {
+			page = find_or_create_page(pcol->inode->i_mapping,
+						   index, GFP_NOFS);
+			if (unlikely(!page)) {
+				EXOFS_DBGMSG("grab_cache_page Failed "
+					"index=0x%llx\n", _LLU(index));
+				return NULL;
+			}
+			unlock_page(page);
+		}
+		if (PageDirty(page) || PageWriteback(page))
+			*uptodate = true;
+		else
+			*uptodate = PageUptodate(page);
+		EXOFS_DBGMSG("index=0x%lx uptodate=%d\n", index, *uptodate);
+		return page;
+	} else {
+		EXOFS_DBGMSG("YES that_locked_page index=0x%lx\n",
+			     pcol->that_locked_page->index);
+		*uptodate = true;
+		return pcol->that_locked_page;
+	}
+}
+
+static void __r4w_put_page(void *priv, struct page *page)
+{
+	struct page_collect *pcol = priv;
+
+	if (pcol->that_locked_page != page) {
+		EXOFS_DBGMSG("index=0x%lx\n", page->index);
+		page_cache_release(page);
+		return;
+	}
+	EXOFS_DBGMSG("that_locked_page index=0x%lx\n", page->index);
+}
+
+static const struct _ore_r4w_op _r4w_op = {
+	.get_page = &__r4w_get_page,
+	.put_page = &__r4w_put_page,
+};
+
 static int write_exec(struct page_collect *pcol)
 {
 	struct exofs_i_info *oi = exofs_i(pcol->inode);

@@ -589,6 +644,7 @@ static int write_exec(struct page_collect *pcol)
 	ios = pcol->ios;
 	ios->pages = pcol_copy->pages;
 	ios->done = writepages_done;
+	ios->r4w = &_r4w_op;
 	ios->private = pcol_copy;
 
 	/* pages ownership was passed to pcol_copy */

@@ -773,6 +829,7 @@ static int exofs_writepages(struct address_space *mapping,
 	return 0;
 }
 
+/*
 static int exofs_writepage(struct page *page, struct writeback_control *wbc)
 {
 	struct page_collect pcol;

@@ -788,7 +845,7 @@ static int exofs_writepage(struct page *page, struct writeback_control *wbc)
 
 	return write_exec(&pcol);
 }
-
+*/
 /* i_mutex held using inode->i_size directly */
 static void _write_failed(struct inode *inode, loff_t to)
 {

@@ -894,7 +951,7 @@ static void exofs_invalidatepage(struct page *page, unsigned long offset)
 const struct address_space_operations exofs_aops = {
 	.readpage	= exofs_readpage,
 	.readpages	= exofs_readpages,
-	.writepage	= exofs_writepage,
+	.writepage	= NULL,
 	.writepages	= exofs_writepages,
 	.write_begin	= exofs_write_begin_export,
 	.write_end	= exofs_write_end,