diff options
| -rw-r--r-- | block/blk-core.c | 14 | ||||
| -rw-r--r-- | include/linux/blkdev.h | 24 |
2 files changed, 29 insertions, 9 deletions
diff --git a/block/blk-core.c b/block/blk-core.c index 684d7eb33d4..97e9e5405b8 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2595,6 +2595,20 @@ EXPORT_SYMBOL(kblockd_schedule_delayed_work); #define PLUG_MAGIC 0x91827364 +/** + * blk_start_plug - initialize blk_plug and track it inside the task_struct + * @plug: The &struct blk_plug that needs to be initialized + * + * Description: + * Tracking blk_plug inside the task_struct will help with auto-flushing the + * pending I/O should the task end up blocking between blk_start_plug() and + * blk_finish_plug(). This is important from a performance perspective, but + * also ensures that we don't deadlock. For instance, if the task is blocking + * for a memory allocation, memory reclaim could end up wanting to free a + * page belonging to that request that is currently residing in our private + * plug. By flushing the pending I/O when the process goes to sleep, we avoid + * this kind of deadlock. + */ void blk_start_plug(struct blk_plug *plug) { struct task_struct *tsk = current; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c712efdafc3..1978655faa3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -860,17 +860,23 @@ struct request_queue *blk_alloc_queue_node(gfp_t, int); extern void blk_put_queue(struct request_queue *); /* - * Note: Code in between changing the blk_plug list/cb_list or element of such - * lists is preemptable, but such code can't do sleep (or be very careful), - * otherwise data is corrupted. For details, please check schedule() where - * blk_schedule_flush_plug() is called. + * blk_plug permits building a queue of related requests by holding the I/O + * fragments for a short period. This allows merging of sequential requests + * into single larger request. As the requests are moved from a per-task list to + * the device's request_queue in a batch, this results in improved scalability + * as the lock contention for request_queue lock is reduced. + * + * It is ok not to disable preemption when adding the request to the plug list + * or when attempting a merge, because blk_schedule_flush_list() will only flush + * the plug list when the task sleeps by itself. For details, please see + * schedule() where blk_schedule_flush_plug() is called. */ struct blk_plug { - unsigned long magic; - struct list_head list; - struct list_head cb_list; - unsigned int should_sort; - unsigned int count; + unsigned long magic; /* detect uninitialized use-cases */ + struct list_head list; /* requests */ + struct list_head cb_list; /* md requires an unplug callback */ + unsigned int should_sort; /* list to be sorted before flushing? */ + unsigned int count; /* number of queued requests */ }; #define BLK_MAX_REQUEST_COUNT 16 |