path: root/block/blk-throttle.c

/*
 * Interface for controlling IO bandwidth on a request queue
 *
 * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com>
 */

#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/blktrace_api.h>
#include <linux/blk-cgroup.h>
#include "blk.h"

/* Max dispatch from a group in 1 round */
static int throtl_grp_quantum = 8;

/* Total max dispatch from all groups in one round */
static int throtl_quantum = 32;

/* Throttling is performed over 100ms slice and after that slice is renewed */
static unsigned long throtl_slice = HZ/10;	/* 100 ms */

static struct blkcg_policy blkcg_policy_throtl;

/* A workqueue to queue throttle related work */
static struct workqueue_struct *kthrotld_workqueue;

/*
 * To implement hierarchical throttling, throtl_grps form a tree and bios
 * are dispatched upwards level by level until they reach the top and get
 * issued.  When dispatching bios from the children and local group at each
 * level, if the bios are dispatched into a single bio_list, there's a risk
 * of a local or child group which can queue many bios at once filling up
 * the list starving others.
 *
 * To avoid such starvation, dispatched bios are queued separately
 * according to where they came from.  When they are again dispatched to
 * the parent, they're popped in round-robin order so that no single source
 * hogs the dispatch window.
 *
 * throtl_qnode is used to keep the queued bios separated by their sources.
 * Bios are queued to throtl_qnode which in turn is queued to
 * throtl_service_queue and then dispatched in round-robin order.
 *
 * It's also used to track the reference counts on blkg's.  A qnode always
 * belongs to a throtl_grp and gets queued on itself or the parent, so
 * incrementing the reference of the associated throtl_grp when a qnode is
 * queued and decrementing when dequeued is enough to keep the whole blkg
 * tree pinned while bios are in flight.
 */
struct throtl_qnode {
	struct list_head	node;		/* service_queue->queued[] */
	struct bio_list		bios;		/* queued bios */
	struct throtl_grp	*tg;		/* tg this qnode belongs to */
};

struct throtl_service_queue {
	struct throtl_service_queue *parent_sq;	/* the parent service_queue */

	/*
	 * Bios queued directly to this service_queue or dispatched from
	 * children throtl_grp's.
	 */
	struct list_head	queued[2];	/* throtl_qnode [READ/WRITE] */
	unsigned int		nr_queued[2];	/* number of queued bios */

	/*
	 * RB tree of active children throtl_grp's, which are sorted by
	 * their ->disptime.
	 */
	struct rb_root		pending_tree;	/* RB tree of active tgs */
	struct rb_node		*first_pending;	/* first node in the tree */
	unsigned int		nr_pending;	/* # queued in the tree */
	unsigned long		first_pending_disptime;	/* disptime of the first tg */
	struct timer_list	pending_timer;	/* fires on first_pending_disptime */
};

enum tg_state_flags {
	THROTL_TG_PENDING	= 1 << 0,	/* on parent's pending tree */
	THROTL_TG_WAS_EMPTY	= 1 << 1,	/* bio_lists[] became non-empty */
};

#define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)

struct throtl_grp {
	/* must be the first member */
	struct blkg_policy_data pd;

	/* active throtl group service_queue member */
	struct rb_node rb_node;

	/* throtl_data this group belongs to */
	struct throtl_data *td;

	/* this group's service queue */
	struct throtl_service_queue service_queue;

	/*
	 * qnode_on_self is used when bios are directly queued to this
	 * throtl_grp so that local bios compete fairly with bios
	 * dispatched from children.  qnode_on_parent is used when bios are
	 * dispatched from this throtl_grp into its parent and will compete
	 * with the sibling qnode_on_parents and the parent's
	 * qnode_on_self.
	 */
	struct throtl_qnode qnode_on_self[2];
	struct throtl_qnode qnode_on_parent[2];

	/*
	 * Dispatch time in jiffies. This is the estimated time when group
	 * will unthrottle and is ready to dispatch more bio. It is used as
	 * key to sort active groups in service tree.
	 */
	unsigned long disptime;

	unsigned int flags;

	/* are there any throtl rules between this group and td? */
	bool has_rules[2];

	/* bytes per second rate limits */
	uint64_t bps[2];

	/* IOPS limits */
	unsigned int iops[2];

	/* Number of bytes disptached in current slice */
	uint64_t bytes_disp[2];
	/* Number of bio's dispatched in current slice */
	unsigned int io_disp[2];

	/* When did we start a new slice */
	unsigned long slice_start[2];
	unsigned long slice_end[2];
};

struct throtl_data
{
	/* service tree for active throtl groups */
	struct throtl_service_queue service_queue;

	struct request_queue *queue;

	/* Total Number of queued bios on READ and WRITE lists */
	unsigned int nr_queued[2];

	/* Work for dispatching throttled bios */
	struct work_struct dispatch_work;
};

static void throtl_pending_timer_fn(unsigned long arg);

static inline struct throtl_grp *pd_to_tg(struct blkg_policy_data *pd)
{
	return pd ? container_of(pd, struct throtl_grp, pd) : NULL;
}

static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg)
{
	return pd_to_tg(blkg_to_pd(blkg, &blkcg_policy_throtl));
}

static inline struct blkcg_gq *tg_to_blkg(struct throtl_grp *tg)
{
	return pd_to_blkg(&tg->pd);
}

/**
 * sq_to_tg - return the throl_grp the specified service queue belongs to
 * @sq: the throtl_service_queue of interest
 *
 * Return the throtl_grp @sq belongs to.  If @sq is the top-level one
 * embedded in throtl_data, %NULL is returned.
 */
static struct throtl_grp *sq_to_tg(struct