exofs: Multi-device mirror support

This patch changes on-disk format, it is accompanied with a parallel
patch to mkfs.exofs that enables multi-device capabilities.

After this patch, old exofs will refuse to mount a new formatted FS and
new exofs will refuse an old format. This is done by moving the magic
field offset inside the FSCB. A new FSCB *version* field was added. In
the future, exofs will refuse to mount unmatched FSCB version. To
up-grade or down-grade an exofs one must use mkfs.exofs --upgrade option
before mounting.

Introduced, a new object that contains a *device-table*. This object
contains the default *data-map* and a linear array of devices
information, which identifies the devices used in the filesystem. This
object is only written to offline by mkfs.exofs. This is why it is kept
separate from the FSCB, since the later is written to while mounted.

Same partition number, same object number is used on all devices only
the device varies.

* define the new format, then load the device table on mount time make
  sure every thing is supported.

* Change I/O engine to now support Mirror IO, .i.e write same data
  to multiple devices, read from a random device to spread the
  read-load from multiple clients (TODO: stripe read)

Implementation notes:
 A few points introduced in previous patch should be mentioned here:

* Special care was made so absolutlly all operation that have any chance
  of failing are done before any osd-request is executed. This is to
  minimize the need for a data consistency recovery, to only real IO
  errors.

* Each IO state has a kref. It starts at 1, any osd-request executed
  will increment the kref, finally when all are executed the first ref
  is dropped. At IO-done, each request completion decrements the kref,
  the last one to return executes the internal _last_io() routine.
  _last_io() will call the registered io_state_done. On sync mode a
  caller does not supply a done method, indicating a synchronous
  request, the caller is put to sleep and a special io_state_done is
  registered that will awaken the caller. Though also in sync mode all
  operations are executed in parallel.

Signed-off-by: Boaz Harrosh <[email protected]>

fs/exofs/common.h

@@ -49,6 +49,7 @@
 #define EXOFS_MIN_PID   0x10000	/* Smallest partition ID */
 #define EXOFS_OBJ_OFF	0x10000	/* offset for objects */
 #define EXOFS_SUPER_ID	0x10000	/* object ID for on-disk superblock */
+#define EXOFS_DEVTABLE_ID 0x10001 /* object ID for on-disk device table */
 #define EXOFS_ROOT_ID	0x10002	/* object ID for root directory */
 
 /* exofs Application specific page/attribute */
@@ -78,17 +79,67 @@ enum {
 #define EXOFS_SUPER_MAGIC	0x5DF5
 
 /*
- * The file system control block - stored in an object's data (mainly, the one
- * with ID EXOFS_SUPER_ID).  This is where the in-memory superblock is stored
- * on disk.  Right now it just has a magic value, which is basically a sanity
- * check on our ability to communicate with the object store.
+ * The file system control block - stored in object EXOFS_SUPER_ID's data.
+ * This is where the in-memory superblock is stored on disk.
  */
+enum {EXOFS_FSCB_VER = 1, EXOFS_DT_VER = 1};
 struct exofs_fscb {
 	__le64  s_nextid;	/* Highest object ID used */
-	__le32  s_numfiles;	/* Number of files on fs */
+	__le64  s_numfiles;	/* Number of files on fs */
+	__le32	s_version;	/* == EXOFS_FSCB_VER */
 	__le16  s_magic;	/* Magic signature */
 	__le16  s_newfs;	/* Non-zero if this is a new fs */
-};
+
+	/* From here on it's a static part, only written by mkexofs */
+	__le64	s_dev_table_oid;   /* Resurved, not used */
+	__le64	s_dev_table_count; /* == 0 means no dev_table */
+} __packed;
+
+/*
+ * Describes the raid used in the FS. It is part of the device table.
+ * This here is taken from the pNFS-objects definition. In exofs we
+ * use one raid policy through-out the filesystem. (NOTE: the funny
+ * alignment at begining. We take care of it at exofs_device_table.
+ */
+struct exofs_dt_data_map {
+	__le32	cb_num_comps;
+	__le64	cb_stripe_unit;
+	__le32	cb_group_width;
+	__le32	cb_group_depth;
+	__le32	cb_mirror_cnt;
+	__le32	cb_raid_algorithm;
+} __packed;
+
+/*
+ * This is an osd device information descriptor. It is a single entry in
+ * the exofs device table. It describes an osd target lun which
+ * contains data belonging to this FS. (Same partition_id on all devices)
+ */
+struct exofs_dt_device_info {
+	__le32	systemid_len;
+	u8	systemid[OSD_SYSTEMID_LEN];
+	__le64	long_name_offset;	/* If !0 then offset-in-file */
+	__le32	osdname_len;		/* */
+	u8	osdname[44];		/* Embbeded, Ususally an asci uuid */
+} __packed;
+
+/*
+ * The EXOFS device table - stored in object EXOFS_DEVTABLE_ID's data.
+ * It contains the raid used for this multy-device FS and an array of
+ * participating devices.
+ */
+struct exofs_device_table {
+	__le32				dt_version;	/* == EXOFS_DT_VER */
+	struct exofs_dt_data_map	dt_data_map;	/* Raid policy to use */
+
+	/* Resurved space For future use. Total includeing this:
+	 * (8 * sizeof(le64))
+	 */
+	__le64				__Resurved[4];
+
+	__le64				dt_num_devices;	/* Array size */
+	struct exofs_dt_device_info	dt_dev_table[];	/* Array of devices */
+} __packed;
 
 /****************************************************************************
  * inode-related things

fs/exofs/exofs.h

@@ -37,6 +37,11 @@
 #include <linux/time.h>
 #include "common.h"
 
+/* FIXME: Remove once pnfs hits mainline
+ * #include <linux/exportfs/pnfs_osd_xdr.h>
+ */
+#include "pnfs.h"
+
 #define EXOFS_ERR(fmt, a...) printk(KERN_ERR "exofs: " fmt, ##a)
 
 #ifdef CONFIG_EXOFS_DEBUG
@@ -54,7 +59,6 @@
  * our extension to the in-memory superblock
  */
 struct exofs_sb_info {
-	struct osd_dev	*s_dev;			/* returned by get_osd_dev    */
 	struct exofs_fscb s_fscb;		/* Written often, pre-allocate*/
 	osd_id		s_pid;			/* partition ID of file system*/
 	int		s_timeout;		/* timeout for OSD operations */
@@ -63,7 +67,11 @@ struct exofs_sb_info {
 	spinlock_t	s_next_gen_lock;	/* spinlock for gen # update  */
 	u32		s_next_generation;	/* next gen # to use          */
 	atomic_t	s_curr_pending;		/* number of pending commands */
-	uint8_t		s_cred[OSD_CAP_LEN];	/* all-powerful credential    */
+	uint8_t		s_cred[OSD_CAP_LEN];	/* credential for the fscb    */
+
+	struct pnfs_osd_data_map data_map;	/* Default raid to use        */
+	unsigned	s_numdevs;		/* Num of devices in array    */
+	struct osd_dev	*s_ods[1];		/* Variable length, minimum 1 */
 };
 
 /*

fs/exofs/inode.c

@@ -62,7 +62,10 @@ static void _pcol_init(struct page_collect *pcol, unsigned expected_pages,
 	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
 
 	pcol->sbi = sbi;
-	pcol->req_q = osd_request_queue(sbi->s_dev);
+	/* Create master bios on first Q, later on cloning, each clone will be
+	 * allocated on it's destination Q
+	 */
+	pcol->req_q = osd_request_queue(sbi->s_ods[0]);
 	pcol->inode = inode;
 	pcol->expected_pages = expected_pages;
 

fs/exofs/ios.c

@@ -71,7 +71,7 @@ int exofs_get_io_state(struct exofs_sb_info *sbi, struct exofs_io_state** pios)
 	/*TODO: Maybe use kmem_cach per sbi of size
 	 * exofs_io_state_size(sbi->s_numdevs)
 	 */
-	ios = kzalloc(exofs_io_state_size(1), GFP_KERNEL);
+	ios = kzalloc(exofs_io_state_size(sbi->s_numdevs), GFP_KERNEL);
 	if (unlikely(!ios)) {
 		*pios = NULL;
 		return -ENOMEM;
@@ -209,10 +209,10 @@ int exofs_sbi_create(struct exofs_io_state *ios)
 {
 	int i, ret;
 
-	for (i = 0; i < 1; i++) {
+	for (i = 0; i < ios->sbi->s_numdevs; i++) {
 		struct osd_request *or;
 
-		or = osd_start_request(ios->sbi->s_dev, GFP_KERNEL);
+		or = osd_start_request(ios->sbi->s_ods[i], GFP_KERNEL);
 		if (unlikely(!or)) {
 			EXOFS_ERR("%s: osd_start_request failed\n", __func__);
 			ret = -ENOMEM;
@@ -233,10 +233,10 @@ int exofs_sbi_remove(struct exofs_io_state *ios)
 {
 	int i, ret;
 
-	for (i = 0; i < 1; i++) {
+	for (i = 0; i < ios->sbi->s_numdevs; i++) {
 		struct osd_request *or;
 
-		or = osd_start_request(ios->sbi->s_dev, GFP_KERNEL);
+		or = osd_start_request(ios->sbi->s_ods[i], GFP_KERNEL);
 		if (unlikely(!or)) {
 			EXOFS_ERR("%s: osd_start_request failed\n", __func__);
 			ret = -ENOMEM;
@@ -257,10 +257,10 @@ int exofs_sbi_write(struct exofs_io_state *ios)
 {
 	int i, ret;
 
-	for (i = 0; i < 1; i++) {
+	for (i = 0; i < ios->sbi->s_numdevs; i++) {
 		struct osd_request *or;
 
-		or = osd_start_request(ios->sbi->s_dev, GFP_KERNEL);
+		or = osd_start_request(ios->sbi->s_ods[i], GFP_KERNEL);
 		if (unlikely(!or)) {
 			EXOFS_ERR("%s: osd_start_request failed\n", __func__);
 			ret = -ENOMEM;
@@ -272,7 +272,21 @@ int exofs_sbi_write(struct exofs_io_state *ios)
 		if (ios->bio) {
 			struct bio *bio;
 
-			bio = ios->bio;
+			if (i != 0) {
+				bio = bio_kmalloc(GFP_KERNEL,
+						  ios->bio->bi_max_vecs);
+				if (unlikely(!bio)) {
+					ret = -ENOMEM;
+					goto out;
+				}
+
+				__bio_clone(bio, ios->bio);
+				bio->bi_bdev = NULL;
+				bio->bi_next = NULL;
+				ios->per_dev[i].bio =  bio;
+			} else {
+				bio = ios->bio;
+			}
 
 			osd_req_write(or, &ios->obj, ios->offset, bio,
 				      ios->length);
@@ -306,8 +320,10 @@ int exofs_sbi_read(struct exofs_io_state *ios)
 
 	for (i = 0; i < 1; i++) {
 		struct osd_request *or;
+		unsigned first_dev = (unsigned)ios->obj.id;
 
-		or = osd_start_request(ios->sbi->s_dev, GFP_KERNEL);
+		first_dev %= ios->sbi->s_numdevs;
+		or = osd_start_request(ios->sbi->s_ods[first_dev], GFP_KERNEL);
 		if (unlikely(!or)) {
 			EXOFS_ERR("%s: osd_start_request failed\n", __func__);
 			ret = -ENOMEM;
@@ -382,10 +398,10 @@ int exofs_oi_truncate(struct exofs_i_info *oi, u64 size)
 	attr = g_attr_logical_length;
 	attr.val_ptr = &newsize;
 
-	for (i = 0; i < 1; i++) {
+	for (i = 0; i < sbi->s_numdevs; i++) {
 		struct osd_request *or;
 
-		or = osd_start_request(sbi->s_dev, GFP_KERNEL);
+		or = osd_start_request(sbi->s_ods[i], GFP_KERNEL);
 		if (unlikely(!or)) {
 			EXOFS_ERR("%s: osd_start_request failed\n", __func__);
 			ret = -ENOMEM;

fs/exofs/pnfs.h

@@ -0,0 +1,51 @@
+/*
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <[email protected]>
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify it under the
+ * terms of the GNU General Public License  version 2 as published by the Free
+ * Software Foundation.
+ *
+ */
+
+/* FIXME: Remove this file once pnfs hits mainline */
+
+#ifndef __EXOFS_PNFS_H__
+#define __EXOFS_PNFS_H__
+
+#if defined(CONFIG_PNFS)
+
+
+/* FIXME: move this file to: linux/exportfs/pnfs_osd_xdr.h */
+#include "../nfs/objlayout/pnfs_osd_xdr.h"
+
+#else /* defined(CONFIG_PNFS) */
+
+enum pnfs_iomode {
+	IOMODE_READ = 1,
+	IOMODE_RW = 2,
+	IOMODE_ANY = 3,
+};
+
+/* Layout Structure */
+enum pnfs_osd_raid_algorithm4 {
+	PNFS_OSD_RAID_0		= 1,
+	PNFS_OSD_RAID_4		= 2,
+	PNFS_OSD_RAID_5		= 3,
+	PNFS_OSD_RAID_PQ	= 4     /* Reed-Solomon P+Q */
+};
+
+struct pnfs_osd_data_map {
+	u32	odm_num_comps;
+	u64	odm_stripe_unit;
+	u32	odm_group_width;
+	u32	odm_group_depth;
+	u32	odm_mirror_cnt;
+	u32	odm_raid_algorithm;
+};
+
+#endif /* else defined(CONFIG_PNFS) */
+
+#endif /* __EXOFS_PNFS_H__ */