mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-28 20:02:17 +00:00
![majianpeng](/assets/img/avatar_default.png)
There is an iobarrier in raid1 because of contention between normal IO and resync IO. It suspends all normal IO when resync/recovery happens. However if normal IO is out side the resync window, there is no contention. So this patch changes the barrier mechanism to only block IO that could contend with the resync that is currently happening. We partition the whole space into five parts. |---------|-----------|------------|----------------|-------| start next_resync start_next_window end_window start + RESYNC_WINDOW = next_resync next_resync + NEXT_NORMALIO_DISTANCE = start_next_window start_next_window + NEXT_NORMALIO_DISTANCE = end_window Firstly we introduce some concepts: 1 - RESYNC_WINDOW: For resync, there are 32 resync requests at most at the same time. A sync request is RESYNC_BLOCK_SIZE(64*1024). So the RESYNC_WINDOW is 32 * RESYNC_BLOCK_SIZE, that is 2MB. 2 - NEXT_NORMALIO_DISTANCE: the distance between next_resync and start_next_window. It also indicates the distance between start_next_window and end_window. It is currently 3 * RESYNC_WINDOW_SIZE but could be tuned if this turned out not to be optimal. 3 - next_resync: the next sector at which we will do sync IO. 4 - start: a position which is at most RESYNC_WINDOW before next_resync. 5 - start_next_window: a position which is NEXT_NORMALIO_DISTANCE beyond next_resync. Normal-io after this position doesn't need to wait for resync-io to complete. 6 - end_window: a position which is 2 * NEXT_NORMALIO_DISTANCE beyond next_resync. This also doesn't need to wait, but is counted differently. 7 - current_window_requests: the count of normalIO between start_next_window and end_window. 8 - next_window_requests: the count of normalIO after end_window. NormalIO will be partitioned into four types: NormIO1: the end sector of bio is smaller or equal the start NormIO2: the start sector of bio larger or equal to end_window NormIO3: the start sector of bio larger or equal to start_next_window. NormIO4: the location between start_next_window and end_window |--------|-----------|--------------------|----------------|-------------| | start | next_resync | start_next_window | end_window | NormIO1 NormIO4 NormIO4 NormIO3 NormIO2 For NormIO1, we don't need any io barrier. For NormIO4, we used a similar approach to the original iobarrier mechanism. The normalIO and resyncIO must be kept separate. For NormIO2/3, we add two fields to struct r1conf: "current_window_requests" and "next_window_requests". They indicate the count of active requests in the two window. For these, we don't wait for resync io to complete. For resync action, if there are NormIO4s, we must wait for it. If not, we can proceed. But if resync action reaches start_next_window and current_window_requests > 0 (that is there are NormIO3s), we must wait until the current_window_requests becomes zero. When current_window_requests becomes zero, start_next_window also moves forward. Then current_window_requests will replaced by next_window_requests. There is a problem which when and how to change from NormIO2 to NormIO3. Only then can sync action progress. We add a field in struct r1conf "start_next_window". A: if start_next_window == MaxSector, it means there are no NormIO2/3. So start_next_window = next_resync + NEXT_NORMALIO_DISTANCE B: if current_window_requests == 0 && next_window_requests != 0, it means start_next_window move to end_window There is another problem which how to differentiate between old NormIO2(now it is NormIO3) and NormIO2. For example, there are many bios which are NormIO2 and a bio which is NormIO3. NormIO3 firstly completed, so the bios of NormIO2 became NormIO3. We add a field in struct r1bio "start_next_window". This is used to record the position conf->start_next_window when the call to wait_barrier() is made in make_request(). In allow_barrier(), we check the conf->start_next_window. If r1bio->stat_next_window == conf->start_next_window, it means there is no transition between NormIO2 and NormIO3. If r1bio->start_next_window != conf->start_next_window, it mean there was a transition between NormIO2 and NormIO3. There can only have been one transition. So it only means the bio is old NormIO2. For one bio, there may be many r1bio's. So we make sure all the r1bio->start_next_window are the same value. If we met blocked_dev in make_request(), it must call allow_barrier and wait_barrier. So the former and the later value of conf->start_next_window will be change. If there are many r1bio's with differnet start_next_window, for the relevant bio, it depend on the last value of r1bio. It will cause error. To avoid this, we must wait for previous r1bios to complete. Signed-off-by: Jianpeng Ma <majianpeng@gmail.com> Signed-off-by: NeilBrown <neilb@suse.de>
178 lines
5.1 KiB
C
178 lines
5.1 KiB
C
#ifndef _RAID1_H
|
|
#define _RAID1_H
|
|
|
|
struct raid1_info {
|
|
struct md_rdev *rdev;
|
|
sector_t head_position;
|
|
|
|
/* When choose the best device for a read (read_balance())
|
|
* we try to keep sequential reads one the same device
|
|
*/
|
|
sector_t next_seq_sect;
|
|
sector_t seq_start;
|
|
};
|
|
|
|
/*
|
|
* memory pools need a pointer to the mddev, so they can force an unplug
|
|
* when memory is tight, and a count of the number of drives that the
|
|
* pool was allocated for, so they know how much to allocate and free.
|
|
* mddev->raid_disks cannot be used, as it can change while a pool is active
|
|
* These two datums are stored in a kmalloced struct.
|
|
* The 'raid_disks' here is twice the raid_disks in r1conf.
|
|
* This allows space for each 'real' device can have a replacement in the
|
|
* second half of the array.
|
|
*/
|
|
|
|
struct pool_info {
|
|
struct mddev *mddev;
|
|
int raid_disks;
|
|
};
|
|
|
|
struct r1conf {
|
|
struct mddev *mddev;
|
|
struct raid1_info *mirrors; /* twice 'raid_disks' to
|
|
* allow for replacements.
|
|
*/
|
|
int raid_disks;
|
|
|
|
/* During resync, read_balancing is only allowed on the part
|
|
* of the array that has been resynced. 'next_resync' tells us
|
|
* where that is.
|
|
*/
|
|
sector_t next_resync;
|
|
|
|
/* When raid1 starts resync, we divide array into four partitions
|
|
* |---------|--------------|---------------------|-------------|
|
|
* next_resync start_next_window end_window
|
|
* start_next_window = next_resync + NEXT_NORMALIO_DISTANCE
|
|
* end_window = start_next_window + NEXT_NORMALIO_DISTANCE
|
|
* current_window_requests means the count of normalIO between
|
|
* start_next_window and end_window.
|
|
* next_window_requests means the count of normalIO after end_window.
|
|
* */
|
|
sector_t start_next_window;
|
|
int current_window_requests;
|
|
int next_window_requests;
|
|
|
|
spinlock_t device_lock;
|
|
|
|
/* list of 'struct r1bio' that need to be processed by raid1d,
|
|
* whether to retry a read, writeout a resync or recovery
|
|
* block, or anything else.
|
|
*/
|
|
struct list_head retry_list;
|
|
|
|
/* queue pending writes to be submitted on unplug */
|
|
struct bio_list pending_bio_list;
|
|
int pending_count;
|
|
|
|
/* for use when syncing mirrors:
|
|
* We don't allow both normal IO and resync/recovery IO at
|
|
* the same time - resync/recovery can only happen when there
|
|
* is no other IO. So when either is active, the other has to wait.
|
|
* See more details description in raid1.c near raise_barrier().
|
|
*/
|
|
wait_queue_head_t wait_barrier;
|
|
spinlock_t resync_lock;
|
|
int nr_pending;
|
|
int nr_waiting;
|
|
int nr_queued;
|
|
int barrier;
|
|
int array_frozen;
|
|
|
|
/* Set to 1 if a full sync is needed, (fresh device added).
|
|
* Cleared when a sync completes.
|
|
*/
|
|
int fullsync;
|
|
|
|
/* When the same as mddev->recovery_disabled we don't allow
|
|
* recovery to be attempted as we expect a read error.
|
|
*/
|
|
int recovery_disabled;
|
|
|
|
|
|
/* poolinfo contains information about the content of the
|
|
* mempools - it changes when the array grows or shrinks
|
|
*/
|
|
struct pool_info *poolinfo;
|
|
mempool_t *r1bio_pool;
|
|
mempool_t *r1buf_pool;
|
|
|
|
/* temporary buffer to synchronous IO when attempting to repair
|
|
* a read error.
|
|
*/
|
|
struct page *tmppage;
|
|
|
|
|
|
/* When taking over an array from a different personality, we store
|
|
* the new thread here until we fully activate the array.
|
|
*/
|
|
struct md_thread *thread;
|
|
};
|
|
|
|
/*
|
|
* this is our 'private' RAID1 bio.
|
|
*
|
|
* it contains information about what kind of IO operations were started
|
|
* for this RAID1 operation, and about their status:
|
|
*/
|
|
|
|
struct r1bio {
|
|
atomic_t remaining; /* 'have we finished' count,
|
|
* used from IRQ handlers
|
|
*/
|
|
atomic_t behind_remaining; /* number of write-behind ios remaining
|
|
* in this BehindIO request
|
|
*/
|
|
sector_t sector;
|
|
sector_t start_next_window;
|
|
int sectors;
|
|
unsigned long state;
|
|
struct mddev *mddev;
|
|
/*
|
|
* original bio going to /dev/mdx
|
|
*/
|
|
struct bio *master_bio;
|
|
/*
|
|
* if the IO is in READ direction, then this is where we read
|
|
*/
|
|
int read_disk;
|
|
|
|
struct list_head retry_list;
|
|
/* Next two are only valid when R1BIO_BehindIO is set */
|
|
struct bio_vec *behind_bvecs;
|
|
int behind_page_count;
|
|
/*
|
|
* if the IO is in WRITE direction, then multiple bios are used.
|
|
* We choose the number when they are allocated.
|
|
*/
|
|
struct bio *bios[0];
|
|
/* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/
|
|
};
|
|
|
|
/* bits for r1bio.state */
|
|
#define R1BIO_Uptodate 0
|
|
#define R1BIO_IsSync 1
|
|
#define R1BIO_Degraded 2
|
|
#define R1BIO_BehindIO 3
|
|
/* Set ReadError on bios that experience a readerror so that
|
|
* raid1d knows what to do with them.
|
|
*/
|
|
#define R1BIO_ReadError 4
|
|
/* For write-behind requests, we call bi_end_io when
|
|
* the last non-write-behind device completes, providing
|
|
* any write was successful. Otherwise we call when
|
|
* any write-behind write succeeds, otherwise we call
|
|
* with failure when last write completes (and all failed).
|
|
* Record that bi_end_io was called with this flag...
|
|
*/
|
|
#define R1BIO_Returned 6
|
|
/* If a write for this request means we can clear some
|
|
* known-bad-block records, we set this flag
|
|
*/
|
|
#define R1BIO_MadeGood 7
|
|
#define R1BIO_WriteError 8
|
|
|
|
extern int md_raid1_congested(struct mddev *mddev, int bits);
|
|
|
|
#endif
|