Files
lkl_linux/block/blk-timeout.c
Jens Axboe 320ae51fee blk-mq: new multi-queue block IO queueing mechanism
Linux currently has two models for block devices:

- The classic request_fn based approach, where drivers use struct
  request units for IO. The block layer provides various helper
  functionalities to let drivers share code, things like tag
  management, timeout handling, queueing, etc.

- The "stacked" approach, where a driver squeezes in between the
  block layer and IO submitter. Since this bypasses the IO stack,
  driver generally have to manage everything themselves.

With drivers being written for new high IOPS devices, the classic
request_fn based driver doesn't work well enough. The design dates
back to when both SMP and high IOPS was rare. It has problems with
scaling to bigger machines, and runs into scaling issues even on
smaller machines when you have IOPS in the hundreds of thousands
per device.

The stacked approach is then most often selected as the model
for the driver. But this means that everybody has to re-invent
everything, and along with that we get all the problems again
that the shared approach solved.

This commit introduces blk-mq, block multi queue support. The
design is centered around per-cpu queues for queueing IO, which
then funnel down into x number of hardware submission queues.
We might have a 1:1 mapping between the two, or it might be
an N:M mapping. That all depends on what the hardware supports.

blk-mq provides various helper functions, which include:

- Scalable support for request tagging. Most devices need to
  be able to uniquely identify a request both in the driver and
  to the hardware. The tagging uses per-cpu caches for freed
  tags, to enable cache hot reuse.

- Timeout handling without tracking request on a per-device
  basis. Basically the driver should be able to get a notification,
  if a request happens to fail.

- Optional support for non 1:1 mappings between issue and
  submission queues. blk-mq can redirect IO completions to the
  desired location.

- Support for per-request payloads. Drivers almost always need
  to associate a request structure with some driver private
  command structure. Drivers can tell blk-mq this at init time,
  and then any request handed to the driver will have the
  required size of memory associated with it.

- Support for merging of IO, and plugging. The stacked model
  gets neither of these. Even for high IOPS devices, merging
  sequential IO reduces per-command overhead and thus
  increases bandwidth.

For now, this is provided as a potential 3rd queueing model, with
the hope being that, as it matures, it can replace both the classic
and stacked model. That would get us back to having just 1 real
model for block devices, leaving the stacked approach to dm/md
devices (as it was originally intended).

Contributions in this patch from the following people:

Shaohua Li <shli@fusionio.com>
Alexander Gordeev <agordeev@redhat.com>
Christoph Hellwig <hch@infradead.org>
Mike Christie <michaelc@cs.wisc.edu>
Matias Bjorling <m@bjorling.me>
Jeff Moyer <jmoyer@redhat.com>

Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-25 11:56:00 +01:00

220 lines
5.2 KiB
C

/*
* Functions related to generic timeout handling of requests.
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/fault-inject.h>
#include "blk.h"
#include "blk-mq.h"
#ifdef CONFIG_FAIL_IO_TIMEOUT
static DECLARE_FAULT_ATTR(fail_io_timeout);
static int __init setup_fail_io_timeout(char *str)
{
return setup_fault_attr(&fail_io_timeout, str);
}
__setup("fail_io_timeout=", setup_fail_io_timeout);
int blk_should_fake_timeout(struct request_queue *q)
{
if (!test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
return 0;
return should_fail(&fail_io_timeout, 1);
}
static int __init fail_io_timeout_debugfs(void)
{
struct dentry *dir = fault_create_debugfs_attr("fail_io_timeout",
NULL, &fail_io_timeout);
return IS_ERR(dir) ? PTR_ERR(dir) : 0;
}
late_initcall(fail_io_timeout_debugfs);
ssize_t part_timeout_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct gendisk *disk = dev_to_disk(dev);
int set = test_bit(QUEUE_FLAG_FAIL_IO, &disk->queue->queue_flags);
return sprintf(buf, "%d\n", set != 0);
}
ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct gendisk *disk = dev_to_disk(dev);
int val;
if (count) {
struct request_queue *q = disk->queue;
char *p = (char *) buf;
val = simple_strtoul(p, &p, 10);
spin_lock_irq(q->queue_lock);
if (val)
queue_flag_set(QUEUE_FLAG_FAIL_IO, q);
else
queue_flag_clear(QUEUE_FLAG_FAIL_IO, q);
spin_unlock_irq(q->queue_lock);
}
return count;
}
#endif /* CONFIG_FAIL_IO_TIMEOUT */
/*
* blk_delete_timer - Delete/cancel timer for a given function.
* @req: request that we are canceling timer for
*
*/
void blk_delete_timer(struct request *req)
{
list_del_init(&req->timeout_list);
}
static void blk_rq_timed_out(struct request *req)
{
struct request_queue *q = req->q;
enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
if (q->rq_timed_out_fn)
ret = q->rq_timed_out_fn(req);
switch (ret) {
case BLK_EH_HANDLED:
/* Can we use req->errors here? */
if (q->mq_ops)
blk_mq_complete_request(req, req->errors);
else
__blk_complete_request(req);
break;
case BLK_EH_RESET_TIMER:
blk_clear_rq_complete(req);
if (q->mq_ops)
blk_mq_add_timer(req);
else
blk_add_timer(req);
break;
case BLK_EH_NOT_HANDLED:
/*
* LLD handles this for now but in the future
* we can send a request msg to abort the command
* and we can move more of the generic scsi eh code to
* the blk layer.
*/
break;
default:
printk(KERN_ERR "block: bad eh return: %d\n", ret);
break;
}
}
void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
unsigned int *next_set)
{
if (time_after_eq(jiffies, rq->deadline)) {
list_del_init(&rq->timeout_list);
/*
* Check if we raced with end io completion
*/
if (!blk_mark_rq_complete(rq))
blk_rq_timed_out(rq);
} else if (!*next_set || time_after(*next_timeout, rq->deadline)) {
*next_timeout = rq->deadline;
*next_set = 1;
}
}
void blk_rq_timed_out_timer(unsigned long data)
{
struct request_queue *q = (struct request_queue *) data;
unsigned long flags, next = 0;
struct request *rq, *tmp;
int next_set = 0;
spin_lock_irqsave(q->queue_lock, flags);
list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
blk_rq_check_expired(rq, &next, &next_set);
if (next_set)
mod_timer(&q->timeout, round_jiffies_up(next));
spin_unlock_irqrestore(q->queue_lock, flags);
}
/**
* blk_abort_request -- Request request recovery for the specified command
* @req: pointer to the request of interest
*
* This function requests that the block layer start recovery for the
* request by deleting the timer and calling the q's timeout function.
* LLDDs who implement their own error recovery MAY ignore the timeout
* event if they generated blk_abort_req. Must hold queue lock.
*/
void blk_abort_request(struct request *req)
{
if (blk_mark_rq_complete(req))
return;
blk_delete_timer(req);
blk_rq_timed_out(req);
}
EXPORT_SYMBOL_GPL(blk_abort_request);
void __blk_add_timer(struct request *req, struct list_head *timeout_list)
{
struct request_queue *q = req->q;
unsigned long expiry;
if (!q->rq_timed_out_fn)
return;
BUG_ON(!list_empty(&req->timeout_list));
BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
/*
* Some LLDs, like scsi, peek at the timeout to prevent a
* command from being retried forever.
*/
if (!req->timeout)
req->timeout = q->rq_timeout;
req->deadline = jiffies + req->timeout;
if (timeout_list)
list_add_tail(&req->timeout_list, timeout_list);
/*
* If the timer isn't already pending or this timeout is earlier
* than an existing one, modify the timer. Round up to next nearest
* second.
*/
expiry = round_jiffies_up(req->deadline);
if (!timer_pending(&q->timeout) ||
time_before(expiry, q->timeout.expires))
mod_timer(&q->timeout, expiry);
}
/**
* blk_add_timer - Start timeout timer for a single request
* @req: request that is about to start running.
*
* Notes:
* Each request has its own timer, and as it is added to the queue, we
* set up the timer. When the request completes, we cancel the timer.
*/
void blk_add_timer(struct request *req)
{
__blk_add_timer(req, &req->q->timeout_list);
}