From dd291d77cc90eb6a86e9860ba8e6e38eebd57d12 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 8 Apr 2024 10:41:07 +0900 Subject: block: Introduce zone write plugging Zone write plugging implements a per-zone "plug" for write operations to control the submission and execution order of write operations to sequential write required zones of a zoned block device. Per-zone plugging guarantees that at any time there is at most only one write request per zone being executed. This mechanism is intended to replace zone write locking which implements a similar per-zone write throttling at the scheduler level, but is implemented only by mq-deadline. Unlike zone write locking which operates on requests, zone write plugging operates on BIOs. A zone write plug is simply a BIO list that is atomically manipulated using a spinlock and a kblockd submission work. A write BIO to a zone is "plugged" to delay its execution if a write BIO for the same zone was already issued, that is, if a write request for the same zone is being executed. The next plugged BIO is unplugged and issued once the write request completes. This mechanism allows to: - Untangle zone write ordering from block IO schedulers. This allows removing the restriction on using mq-deadline for writing to zoned block devices. Any block IO scheduler, including "none" can be used. - Zone write plugging operates on BIOs instead of requests. Plugged BIOs waiting for execution thus do not hold scheduling tags and thus are not preventing other BIOs from executing (reads or writes to other zones). Depending on the workload, this can significantly improve the device use (higher queue depth operation) and performance. - Both blk-mq (request based) zoned devices and BIO-based zoned devices (e.g. device mapper) can use zone write plugging. It is mandatory for the former but optional for the latter. BIO-based drivers can use zone write plugging to implement write ordering guarantees, or the drivers can implement their own if needed. - The code is less invasive in the block layer and is mostly limited to blk-zoned.c with some small changes in blk-mq.c, blk-merge.c and bio.c. Zone write plugging is implemented using struct blk_zone_wplug. This structure includes a spinlock, a BIO list and a work structure to handle the submission of plugged BIOs. Zone write plugs structures are managed using a per-disk hash table. Plugging of zone write BIOs is done using the function blk_zone_write_plug_bio() which returns false if a BIO execution does not need to be delayed and true otherwise. This function is called from blk_mq_submit_bio() after a BIO is split to avoid large BIOs spanning multiple zones which would cause mishandling of zone write plugs. This ichange enables by default zone write plugging for any mq request-based block device. BIO-based device drivers can also use zone write plugging by expliclty calling blk_zone_write_plug_bio() in their ->submit_bio method. For such devices, the driver must ensure that a BIO passed to blk_zone_write_plug_bio() is already split and not straddling zone boundaries. Only write and write zeroes BIOs are plugged. Zone write plugging does not introduce any significant overhead for other operations. A BIO that is being handled through zone write plugging is flagged using the new BIO flag BIO_ZONE_WRITE_PLUGGING. A request handling a BIO flagged with this new flag is flagged with the new RQF_ZONE_WRITE_PLUGGING flag. The completion of BIOs and requests flagged trigger respectively calls to the functions blk_zone_write_bio_endio() and blk_zone_write_complete_request(). The latter function is used to trigger submission of the next plugged BIO using the zone plug work. blk_zone_write_bio_endio() does the same for BIO-based devices. This ensures that at any time, at most one request (blk-mq devices) or one BIO (BIO-based devices) is being executed for any zone. The handling of zone write plugs using a per-zone plug spinlock maximizes parallelism and device usage by allowing multiple zones to be writen simultaneously without lock contention. Zone write plugging ignores flush BIOs without data. Hovever, any flush BIO that has data is always plugged so that the write part of the flush sequence is serialized with other regular writes. Given that any BIO handled through zone write plugging will be the only BIO in flight for the target zone when it is executed, the unplugging and submission of a BIO will have no chance of successfully merging with plugged requests or requests in the scheduler. To overcome this potential performance degradation, blk_mq_submit_bio() calls the function blk_zone_write_plug_attempt_merge() to try to merge other plugged BIOs with the one just unplugged and submitted. Successful merging is signaled using blk_zone_write_plug_bio_merged(), called from bio_attempt_back_merge(). Furthermore, to avoid recalculating the number of segments of plugged BIOs to attempt merging, the number of segments of a plugged BIO is saved using the new struct bio field __bi_nr_segments. To avoid growing the size of struct bio, this field is added as a union with the bio_cookie field. This is safe to do as polling is always disabled for plugged BIOs. When BIOs are plugged in a zone write plug, the device request queue usage counter is always incremented. This reference is kept and reused for blk-mq devices when the plugged BIO is unplugged and submitted again using submit_bio_noacct_nocheck(). For this case, the unplugged BIO is already flagged with BIO_ZONE_WRITE_PLUGGING and blk_mq_submit_bio() proceeds directly to allocating a new request for the BIO, re-using the usage reference count taken when the BIO was plugged. This extra reference count is dropped in blk_zone_write_plug_attempt_merge() for any plugged BIO that is successfully merged. Given that BIO-based devices will not take this path, the extra reference is dropped after a plugged BIO is unplugged and submitted. Zone write plugs are dynamically allocated and managed using a hash table (an array of struct hlist_head) with RCU protection. A zone write plug is allocated when a write BIO is received for the zone and not freed until the zone is fully written, reset or finished. To detect when a zone write plug can be freed, the write state of each zone is tracked using a write pointer offset which corresponds to the offset of a zone write pointer relative to the zone start. Write operations always increment this write pointer offset. Zone reset operations set it to 0 and zone finish operations set it to the zone size. If a write error happens, the wp_offset value of a zone write plug may become incorrect and out of sync with the device managed write pointer. This is handled using the zone write plug flag BLK_ZONE_WPLUG_ERROR. The function blk_zone_wplug_handle_error() is called from the new disk zone write plug work when this flag is set. This function executes a report zone to update the zone write pointer offset to the current value as indicated by the device. The disk zone write plug work is scheduled whenever a BIO flagged with BIO_ZONE_WRITE_PLUGGING completes with an error or when bio_zone_wplug_prepare_bio() detects an unaligned write. Once scheduled, the disk zone write plugs work keeps running until all zone errors are handled. To match the new data structures used for zoned disks, the function disk_free_zone_bitmaps() is renamed to the more generic disk_free_zone_resources(). The function disk_init_zone_resources() is also introduced to initialize zone write plugs resources when a gendisk is allocated. In order to guarantee that the user can simultaneously write up to a number of zones equal to a device max active zone limit or max open zone limit, zone write plugs are allocated using a mempool sized to the maximum of these 2 device limits. For a device that does not have active and open zone limits, 128 is used as the default mempool size. If a change to the device active and open zone limits is detected, the disk mempool is resized when blk_revalidate_disk_zones() is executed. This commit contains contributions from Christoph Hellwig . Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Tested-by: Hans Holmberg Tested-by: Dennis Maisenbacher Reviewed-by: Martin K. Petersen Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20240408014128.205141-8-dlemoal@kernel.org Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/blk-mq.h') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d3d8fd8e229b..60090c8366fb 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -56,6 +56,8 @@ typedef __u32 __bitwise req_flags_t; #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) /* The per-zone write lock is held for this request */ #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) +/* The request completion needs to be signaled to zone write pluging. */ +#define RQF_ZONE_WRITE_PLUGGING ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) #define RQF_RESV ((__force req_flags_t)(1 << 23)) -- cgit v1.2.3 From 02ccd7c360b1692da164842f211d41fab7d83adc Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 8 Apr 2024 10:41:26 +0900 Subject: block: Remove zone write locking Zone write locking is now unused and replaced with zone write plugging. Remove all code that was implementing zone write locking, that is, the various helper functions controlling request zone write locking and the gendisk attached zone bitmaps. Signed-off-by: Damien Le Moal Reviewed-by: Bart Van Assche Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Tested-by: Hans Holmberg Tested-by: Dennis Maisenbacher Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20240408014128.205141-27-dlemoal@kernel.org Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 83 -------------------------------------------------- 1 file changed, 83 deletions(-) (limited to 'include/linux/blk-mq.h') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 60090c8366fb..89ba6b16fe8b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -54,8 +54,6 @@ typedef __u32 __bitwise req_flags_t; /* Look at ->special_vec for the actual data payload instead of the bio chain. */ #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) -/* The per-zone write lock is held for this request */ -#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) /* The request completion needs to be signaled to zone write pluging. */ #define RQF_ZONE_WRITE_PLUGGING ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ @@ -1152,85 +1150,4 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, } void blk_dump_rq_flags(struct request *, char *); -#ifdef CONFIG_BLK_DEV_ZONED -static inline unsigned int blk_rq_zone_no(struct request *rq) -{ - return disk_zone_no(rq->q->disk, blk_rq_pos(rq)); -} - -static inline unsigned int blk_rq_zone_is_seq(struct request *rq) -{ - return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq)); -} - -/** - * blk_rq_is_seq_zoned_write() - Check if @rq requires write serialization. - * @rq: Request to examine. - * - * Note: REQ_OP_ZONE_APPEND requests do not require serialization. - */ -static inline bool blk_rq_is_seq_zoned_write(struct request *rq) -{ - return op_needs_zoned_write_locking(req_op(rq)) && - blk_rq_zone_is_seq(rq); -} - -bool blk_req_needs_zone_write_lock(struct request *rq); -bool blk_req_zone_write_trylock(struct request *rq); -void __blk_req_zone_write_lock(struct request *rq); -void __blk_req_zone_write_unlock(struct request *rq); - -static inline void blk_req_zone_write_lock(struct request *rq) -{ - if (blk_req_needs_zone_write_lock(rq)) - __blk_req_zone_write_lock(rq); -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ - if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) - __blk_req_zone_write_unlock(rq); -} - -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return rq->q->disk->seq_zones_wlock && - test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock); -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - if (!blk_req_needs_zone_write_lock(rq)) - return true; - return !blk_req_zone_is_write_locked(rq); -} -#else /* CONFIG_BLK_DEV_ZONED */ -static inline bool blk_rq_is_seq_zoned_write(struct request *rq) -{ - return false; -} - -static inline bool blk_req_needs_zone_write_lock(struct request *rq) -{ - return false; -} - -static inline void blk_req_zone_write_lock(struct request *rq) -{ -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ -} -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return false; -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - return true; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - #endif /* BLK_MQ_H */ -- cgit v1.2.3