4ac845a2e9
The io context sharing introduced a per-ioc spinlock, that would protect the cfq io context lookup. That is a regression from the original, since we never needed any locking there because the ioc/cic were process private. The cic lookup is changed from an rbtree construct to a radix tree, which we can then use RCU to make the reader side lockless. That is the performance critical path, modifying the radix tree is only done on process creation (when that process first does IO, actually) and on process exit (if that process has done IO). As it so happens, radix trees are also much faster for this type of lookup where the key is a pointer. It's a very sparse tree. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
95 lines
2 KiB
C
95 lines
2 KiB
C
#ifndef IOCONTEXT_H
|
|
#define IOCONTEXT_H
|
|
|
|
#include <linux/radix-tree.h>
|
|
|
|
/*
|
|
* This is the per-process anticipatory I/O scheduler state.
|
|
*/
|
|
struct as_io_context {
|
|
spinlock_t lock;
|
|
|
|
void (*dtor)(struct as_io_context *aic); /* destructor */
|
|
void (*exit)(struct as_io_context *aic); /* called on task exit */
|
|
|
|
unsigned long state;
|
|
atomic_t nr_queued; /* queued reads & sync writes */
|
|
atomic_t nr_dispatched; /* number of requests gone to the drivers */
|
|
|
|
/* IO History tracking */
|
|
/* Thinktime */
|
|
unsigned long last_end_request;
|
|
unsigned long ttime_total;
|
|
unsigned long ttime_samples;
|
|
unsigned long ttime_mean;
|
|
/* Layout pattern */
|
|
unsigned int seek_samples;
|
|
sector_t last_request_pos;
|
|
u64 seek_total;
|
|
sector_t seek_mean;
|
|
};
|
|
|
|
struct cfq_queue;
|
|
struct cfq_io_context {
|
|
void *key;
|
|
unsigned long dead_key;
|
|
|
|
struct cfq_queue *cfqq[2];
|
|
|
|
struct io_context *ioc;
|
|
|
|
unsigned long last_end_request;
|
|
sector_t last_request_pos;
|
|
|
|
unsigned long ttime_total;
|
|
unsigned long ttime_samples;
|
|
unsigned long ttime_mean;
|
|
|
|
unsigned int seek_samples;
|
|
u64 seek_total;
|
|
sector_t seek_mean;
|
|
|
|
struct list_head queue_list;
|
|
|
|
void (*dtor)(struct io_context *); /* destructor */
|
|
void (*exit)(struct io_context *); /* called on task exit */
|
|
};
|
|
|
|
/*
|
|
* I/O subsystem state of the associated processes. It is refcounted
|
|
* and kmalloc'ed. These could be shared between processes.
|
|
*/
|
|
struct io_context {
|
|
atomic_t refcount;
|
|
atomic_t nr_tasks;
|
|
|
|
/* all the fields below are protected by this lock */
|
|
spinlock_t lock;
|
|
|
|
unsigned short ioprio;
|
|
unsigned short ioprio_changed;
|
|
|
|
/*
|
|
* For request batching
|
|
*/
|
|
unsigned long last_waited; /* Time last woken after wait for request */
|
|
int nr_batch_requests; /* Number of requests left in the batch */
|
|
|
|
struct as_io_context *aic;
|
|
struct radix_tree_root radix_root;
|
|
void *ioc_data;
|
|
};
|
|
|
|
static inline struct io_context *ioc_task_link(struct io_context *ioc)
|
|
{
|
|
/*
|
|
* if ref count is zero, don't allow sharing (ioc is going away, it's
|
|
* a race).
|
|
*/
|
|
if (ioc && atomic_inc_not_zero(&ioc->refcount))
|
|
return ioc;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
#endif
|