mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-25 05:34:00 +08:00
b8bea09a45
Add tracepoint for better insight to how the RAID56 data are submitted. The output looks like this: (trace event header and UUID skipped) raid56_read_partial: full_stripe=389152768 devid=3 type=DATA1 offset=32768 opf=0x0 physical=323059712 len=32768 raid56_read_partial: full_stripe=389152768 devid=1 type=DATA2 offset=0 opf=0x0 physical=67174400 len=65536 raid56_write_stripe: full_stripe=389152768 devid=3 type=DATA1 offset=0 opf=0x1 physical=323026944 len=32768 raid56_write_stripe: full_stripe=389152768 devid=2 type=PQ1 offset=0 opf=0x1 physical=323026944 len=32768 The above debug output is from a 32K data write into an empty RAID56 data chunk. Some explanation on the event output: full_stripe: the logical bytenr of the full stripe devid: btrfs devid type: raid stripe type. DATA1: the first data stripe DATA2: the second data stripe PQ1: the P stripe PQ2: the Q stripe offset: the offset inside the stripe. opf: the bio op type physical: the physical offset the bio is for len: the length of the bio The first two lines are from partial RMW read, which is reading the remaining data stripes from disks. The last two lines are for full stripe RMW write, which is writing the involved two 16K stripes (one for DATA1 stripe, one for P stripe). The stripe for DATA2 doesn't need to be written. There are 5 types of trace events: - raid56_read_partial Read remaining data for regular read/write path. - raid56_write_stripe Write the modified stripes for regular read/write path. - raid56_scrub_read_recover Read remaining data for scrub recovery path. - raid56_scrub_write_stripe Write the modified stripes for scrub path. - raid56_scrub_read Read remaining data for scrub path. Also, since the trace events are included at super.c, we have to export needed structure definitions to 'raid56.h' and include the header in super.c, or we're unable to access those members. Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> [ reformat comments ] Signed-off-by: David Sterba <dsterba@suse.com>
201 lines
5.0 KiB
C
201 lines
5.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (C) 2012 Fusion-io All rights reserved.
|
|
* Copyright (C) 2012 Intel Corp. All rights reserved.
|
|
*/
|
|
|
|
#ifndef BTRFS_RAID56_H
|
|
#define BTRFS_RAID56_H
|
|
|
|
#include <linux/workqueue.h>
|
|
#include "volumes.h"
|
|
|
|
enum btrfs_rbio_ops {
|
|
BTRFS_RBIO_WRITE,
|
|
BTRFS_RBIO_READ_REBUILD,
|
|
BTRFS_RBIO_PARITY_SCRUB,
|
|
BTRFS_RBIO_REBUILD_MISSING,
|
|
};
|
|
|
|
struct btrfs_raid_bio {
|
|
struct btrfs_io_context *bioc;
|
|
|
|
/*
|
|
* While we're doing RMW on a stripe we put it into a hash table so we
|
|
* can lock the stripe and merge more rbios into it.
|
|
*/
|
|
struct list_head hash_list;
|
|
|
|
/* LRU list for the stripe cache */
|
|
struct list_head stripe_cache;
|
|
|
|
/* For scheduling work in the helper threads */
|
|
struct work_struct work;
|
|
|
|
/*
|
|
* bio_list and bio_list_lock are used to add more bios into the stripe
|
|
* in hopes of avoiding the full RMW
|
|
*/
|
|
struct bio_list bio_list;
|
|
spinlock_t bio_list_lock;
|
|
|
|
/*
|
|
* Also protected by the bio_list_lock, the plug list is used by the
|
|
* plugging code to collect partial bios while plugged. The stripe
|
|
* locking code also uses it to hand off the stripe lock to the next
|
|
* pending IO.
|
|
*/
|
|
struct list_head plug_list;
|
|
|
|
/* Flags that tell us if it is safe to merge with this bio. */
|
|
unsigned long flags;
|
|
|
|
/*
|
|
* Set if we're doing a parity rebuild for a read from higher up, which
|
|
* is handled differently from a parity rebuild as part of RMW.
|
|
*/
|
|
enum btrfs_rbio_ops operation;
|
|
|
|
/* Size of each individual stripe on disk */
|
|
u32 stripe_len;
|
|
|
|
/* How many pages there are for the full stripe including P/Q */
|
|
u16 nr_pages;
|
|
|
|
/* How many sectors there are for the full stripe including P/Q */
|
|
u16 nr_sectors;
|
|
|
|
/* Number of data stripes (no p/q) */
|
|
u8 nr_data;
|
|
|
|
/* Numer of all stripes (including P/Q) */
|
|
u8 real_stripes;
|
|
|
|
/* How many pages there are for each stripe */
|
|
u8 stripe_npages;
|
|
|
|
/* How many sectors there are for each stripe */
|
|
u8 stripe_nsectors;
|
|
|
|
/* First bad stripe, -1 means no corruption */
|
|
s8 faila;
|
|
|
|
/* Second bad stripe (for RAID6 use) */
|
|
s8 failb;
|
|
|
|
/* Stripe number that we're scrubbing */
|
|
u8 scrubp;
|
|
|
|
/*
|
|
* Size of all the bios in the bio_list. This helps us decide if the
|
|
* rbio maps to a full stripe or not.
|
|
*/
|
|
int bio_list_bytes;
|
|
|
|
int generic_bio_cnt;
|
|
|
|
refcount_t refs;
|
|
|
|
atomic_t stripes_pending;
|
|
|
|
atomic_t error;
|
|
|
|
/* Bitmap to record which horizontal stripe has data */
|
|
unsigned long dbitmap;
|
|
|
|
/* Allocated with stripe_nsectors-many bits for finish_*() calls */
|
|
unsigned long finish_pbitmap;
|
|
|
|
/*
|
|
* These are two arrays of pointers. We allocate the rbio big enough
|
|
* to hold them both and setup their locations when the rbio is
|
|
* allocated.
|
|
*/
|
|
|
|
/*
|
|
* Pointers to pages that we allocated for reading/writing stripes
|
|
* directly from the disk (including P/Q).
|
|
*/
|
|
struct page **stripe_pages;
|
|
|
|
/* Pointers to the sectors in the bio_list, for faster lookup */
|
|
struct sector_ptr *bio_sectors;
|
|
|
|
/*
|
|
* For subpage support, we need to map each sector to above
|
|
* stripe_pages.
|
|
*/
|
|
struct sector_ptr *stripe_sectors;
|
|
|
|
/* Allocated with real_stripes-many pointers for finish_*() calls */
|
|
void **finish_pointers;
|
|
};
|
|
|
|
/*
|
|
* For trace event usage only. Records useful debug info for each bio submitted
|
|
* by RAID56 to each physical device.
|
|
*
|
|
* No matter signed or not, (-1) is always the one indicating we can not grab
|
|
* the proper stripe number.
|
|
*/
|
|
struct raid56_bio_trace_info {
|
|
u64 devid;
|
|
|
|
/* The offset inside the stripe. (<= STRIPE_LEN) */
|
|
u32 offset;
|
|
|
|
/*
|
|
* Stripe number.
|
|
* 0 is the first data stripe, and nr_data for P stripe,
|
|
* nr_data + 1 for Q stripe.
|
|
* >= real_stripes for
|
|
*/
|
|
u8 stripe_nr;
|
|
};
|
|
|
|
static inline int nr_parity_stripes(const struct map_lookup *map)
|
|
{
|
|
if (map->type & BTRFS_BLOCK_GROUP_RAID5)
|
|
return 1;
|
|
else if (map->type & BTRFS_BLOCK_GROUP_RAID6)
|
|
return 2;
|
|
else
|
|
return 0;
|
|
}
|
|
|
|
static inline int nr_data_stripes(const struct map_lookup *map)
|
|
{
|
|
return map->num_stripes - nr_parity_stripes(map);
|
|
}
|
|
|
|
#define RAID5_P_STRIPE ((u64)-2)
|
|
#define RAID6_Q_STRIPE ((u64)-1)
|
|
|
|
#define is_parity_stripe(x) (((x) == RAID5_P_STRIPE) || \
|
|
((x) == RAID6_Q_STRIPE))
|
|
|
|
struct btrfs_device;
|
|
|
|
int raid56_parity_recover(struct bio *bio, struct btrfs_io_context *bioc,
|
|
u32 stripe_len, int mirror_num, int generic_io);
|
|
int raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc, u32 stripe_len);
|
|
|
|
void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page,
|
|
unsigned int pgoff, u64 logical);
|
|
|
|
struct btrfs_raid_bio *raid56_parity_alloc_scrub_rbio(struct bio *bio,
|
|
struct btrfs_io_context *bioc, u32 stripe_len,
|
|
struct btrfs_device *scrub_dev,
|
|
unsigned long *dbitmap, int stripe_nsectors);
|
|
void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio);
|
|
|
|
struct btrfs_raid_bio *
|
|
raid56_alloc_missing_rbio(struct bio *bio, struct btrfs_io_context *bioc,
|
|
u64 length);
|
|
void raid56_submit_missing_rbio(struct btrfs_raid_bio *rbio);
|
|
|
|
int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info);
|
|
void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info);
|
|
|
|
#endif
|