2017-04-19 22:48:24 +08:00
|
|
|
/*
|
|
|
|
* Header file for the BFQ I/O scheduler: data structures and
|
|
|
|
* prototypes of interface functions among BFQ components.
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License as
|
|
|
|
* published by the Free Software Foundation; either version 2 of the
|
|
|
|
* License, or (at your option) any later version.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
* General Public License for more details.
|
|
|
|
*/
|
|
|
|
#ifndef _BFQ_H
|
|
|
|
#define _BFQ_H
|
|
|
|
|
|
|
|
#include <linux/blktrace_api.h>
|
|
|
|
#include <linux/hrtimer.h>
|
|
|
|
#include <linux/blk-cgroup.h>
|
|
|
|
|
|
|
|
#define BFQ_IOPRIO_CLASSES 3
|
|
|
|
#define BFQ_CL_IDLE_TIMEOUT (HZ/5)
|
|
|
|
|
|
|
|
#define BFQ_MIN_WEIGHT 1
|
|
|
|
#define BFQ_MAX_WEIGHT 1000
|
|
|
|
#define BFQ_WEIGHT_CONVERSION_COEFF 10
|
|
|
|
|
|
|
|
#define BFQ_DEFAULT_QUEUE_IOPRIO 4
|
|
|
|
|
|
|
|
#define BFQ_WEIGHT_LEGACY_DFL 100
|
|
|
|
#define BFQ_DEFAULT_GRP_IOPRIO 0
|
|
|
|
#define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Soft real-time applications are extremely more latency sensitive
|
|
|
|
* than interactive ones. Over-raise the weight of the former to
|
|
|
|
* privilege them against the latter.
|
|
|
|
*/
|
|
|
|
#define BFQ_SOFTRT_WEIGHT_FACTOR 100
|
|
|
|
|
|
|
|
struct bfq_entity;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* struct bfq_service_tree - per ioprio_class service tree.
|
|
|
|
*
|
|
|
|
* Each service tree represents a B-WF2Q+ scheduler on its own. Each
|
|
|
|
* ioprio_class has its own independent scheduler, and so its own
|
|
|
|
* bfq_service_tree. All the fields are protected by the queue lock
|
|
|
|
* of the containing bfqd.
|
|
|
|
*/
|
|
|
|
struct bfq_service_tree {
|
|
|
|
/* tree for active entities (i.e., those backlogged) */
|
|
|
|
struct rb_root active;
|
2017-07-12 15:25:01 +08:00
|
|
|
/* tree for idle entities (i.e., not backlogged, with V < F_i)*/
|
2017-04-19 22:48:24 +08:00
|
|
|
struct rb_root idle;
|
|
|
|
|
|
|
|
/* idle entity with minimum F_i */
|
|
|
|
struct bfq_entity *first_idle;
|
|
|
|
/* idle entity with maximum F_i */
|
|
|
|
struct bfq_entity *last_idle;
|
|
|
|
|
|
|
|
/* scheduler virtual time */
|
|
|
|
u64 vtime;
|
|
|
|
/* scheduler weight sum; active and idle entities contribute to it */
|
|
|
|
unsigned long wsum;
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* struct bfq_sched_data - multi-class scheduler.
|
|
|
|
*
|
|
|
|
* bfq_sched_data is the basic scheduler queue. It supports three
|
|
|
|
* ioprio_classes, and can be used either as a toplevel queue or as an
|
block, bfq: consider also in_service_entity to state whether an entity is active
Groups of BFQ queues are represented by generic entities in BFQ. When
a queue belonging to a parent entity is deactivated, the parent entity
may need to be deactivated too, in case the deactivated queue was the
only active queue for the parent entity. This deactivation may need to
be propagated upwards if the entity belongs, in its turn, to a further
higher-level entity, and so on. In particular, the upward propagation
of deactivation stops at the first parent entity that remains active
even if one of its child entities has been deactivated.
To decide whether the last non-deactivation condition holds for a
parent entity, BFQ checks whether the field next_in_service is still
not NULL for the parent entity, after the deactivation of one of its
child entity. If it is not NULL, then there are certainly other active
entities in the parent entity, and deactivations can stop.
Unfortunately, this check misses a corner case: if in_service_entity
is not NULL, then next_in_service may happen to be NULL, although the
parent entity is evidently active. This happens if: 1) the entity
pointed by in_service_entity is the only active entity in the parent
entity, and 2) according to the definition of next_in_service, the
in_service_entity cannot be considered as next_in_service. See the
comments on the definition of next_in_service for details on this
second point.
Hitting the above corner case causes crashes.
To address this issue, this commit:
1) Extends the above check on only next_in_service to controlling both
next_in_service and in_service_entity (if any of them is not NULL,
then no further deactivation is performed)
2) Improves the (important) comments on how next_in_service is defined
and updated; in particular it fixes a few rather obscure paragraphs
Reported-by: Eric Wheeler <bfq-sched@lists.ewheeler.net>
Reported-by: Rick Yiu <rick_yiu@htc.com>
Reported-by: Tom X Nguyen <tom81094@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Eric Wheeler <bfq-sched@lists.ewheeler.net>
Tested-by: Rick Yiu <rick_yiu@htc.com>
Tested-by: Laurentiu Nicola <lnicola@dend.ro>
Tested-by: Tom X Nguyen <tom81094@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-07-29 18:42:56 +08:00
|
|
|
* intermediate queue in a hierarchical setup.
|
2017-04-19 22:48:24 +08:00
|
|
|
*
|
|
|
|
* The supported ioprio_classes are the same as in CFQ, in descending
|
|
|
|
* priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
|
|
|
|
* Requests from higher priority queues are served before all the
|
|
|
|
* requests from lower priority queues; among requests of the same
|
|
|
|
* queue requests are served according to B-WF2Q+.
|
block, bfq: consider also in_service_entity to state whether an entity is active
Groups of BFQ queues are represented by generic entities in BFQ. When
a queue belonging to a parent entity is deactivated, the parent entity
may need to be deactivated too, in case the deactivated queue was the
only active queue for the parent entity. This deactivation may need to
be propagated upwards if the entity belongs, in its turn, to a further
higher-level entity, and so on. In particular, the upward propagation
of deactivation stops at the first parent entity that remains active
even if one of its child entities has been deactivated.
To decide whether the last non-deactivation condition holds for a
parent entity, BFQ checks whether the field next_in_service is still
not NULL for the parent entity, after the deactivation of one of its
child entity. If it is not NULL, then there are certainly other active
entities in the parent entity, and deactivations can stop.
Unfortunately, this check misses a corner case: if in_service_entity
is not NULL, then next_in_service may happen to be NULL, although the
parent entity is evidently active. This happens if: 1) the entity
pointed by in_service_entity is the only active entity in the parent
entity, and 2) according to the definition of next_in_service, the
in_service_entity cannot be considered as next_in_service. See the
comments on the definition of next_in_service for details on this
second point.
Hitting the above corner case causes crashes.
To address this issue, this commit:
1) Extends the above check on only next_in_service to controlling both
next_in_service and in_service_entity (if any of them is not NULL,
then no further deactivation is performed)
2) Improves the (important) comments on how next_in_service is defined
and updated; in particular it fixes a few rather obscure paragraphs
Reported-by: Eric Wheeler <bfq-sched@lists.ewheeler.net>
Reported-by: Rick Yiu <rick_yiu@htc.com>
Reported-by: Tom X Nguyen <tom81094@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Eric Wheeler <bfq-sched@lists.ewheeler.net>
Tested-by: Rick Yiu <rick_yiu@htc.com>
Tested-by: Laurentiu Nicola <lnicola@dend.ro>
Tested-by: Tom X Nguyen <tom81094@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-07-29 18:42:56 +08:00
|
|
|
*
|
|
|
|
* The schedule is implemented by the service trees, plus the field
|
|
|
|
* @next_in_service, which points to the entity on the active trees
|
|
|
|
* that will be served next, if 1) no changes in the schedule occurs
|
|
|
|
* before the current in-service entity is expired, 2) the in-service
|
|
|
|
* queue becomes idle when it expires, and 3) if the entity pointed by
|
|
|
|
* in_service_entity is not a queue, then the in-service child entity
|
|
|
|
* of the entity pointed by in_service_entity becomes idle on
|
|
|
|
* expiration. This peculiar definition allows for the following
|
|
|
|
* optimization, not yet exploited: while a given entity is still in
|
|
|
|
* service, we already know which is the best candidate for next
|
|
|
|
* service among the other active entitities in the same parent
|
|
|
|
* entity. We can then quickly compare the timestamps of the
|
|
|
|
* in-service entity with those of such best candidate.
|
|
|
|
*
|
|
|
|
* All fields are protected by the lock of the containing bfqd.
|
2017-04-19 22:48:24 +08:00
|
|
|
*/
|
|
|
|
struct bfq_sched_data {
|
|
|
|
/* entity in service */
|
|
|
|
struct bfq_entity *in_service_entity;
|
|
|
|
/* head-of-line entity (see comments above) */
|
|
|
|
struct bfq_entity *next_in_service;
|
|
|
|
/* array of service trees, one per ioprio_class */
|
|
|
|
struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
|
|
|
|
/* last time CLASS_IDLE was served */
|
|
|
|
unsigned long bfq_class_idle_last_service;
|
|
|
|
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* struct bfq_weight_counter - counter of the number of all active entities
|
|
|
|
* with a given weight.
|
|
|
|
*/
|
|
|
|
struct bfq_weight_counter {
|
|
|
|
unsigned int weight; /* weight of the entities this counter refers to */
|
|
|
|
unsigned int num_active; /* nr of active entities with this weight */
|
|
|
|
/*
|
|
|
|
* Weights tree member (see bfq_data's @queue_weights_tree and
|
|
|
|
* @group_weights_tree)
|
|
|
|
*/
|
|
|
|
struct rb_node weights_node;
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* struct bfq_entity - schedulable entity.
|
|
|
|
*
|
|
|
|
* A bfq_entity is used to represent either a bfq_queue (leaf node in the
|
|
|
|
* cgroup hierarchy) or a bfq_group into the upper level scheduler. Each
|
|
|
|
* entity belongs to the sched_data of the parent group in the cgroup
|
|
|
|
* hierarchy. Non-leaf entities have also their own sched_data, stored
|
|
|
|
* in @my_sched_data.
|
|
|
|
*
|
|
|
|
* Each entity stores independently its priority values; this would
|
|
|
|
* allow different weights on different devices, but this
|
|
|
|
* functionality is not exported to userspace by now. Priorities and
|
|
|
|
* weights are updated lazily, first storing the new values into the
|
|
|
|
* new_* fields, then setting the @prio_changed flag. As soon as
|
|
|
|
* there is a transition in the entity state that allows the priority
|
|
|
|
* update to take place the effective and the requested priority
|
|
|
|
* values are synchronized.
|
|
|
|
*
|
|
|
|
* Unless cgroups are used, the weight value is calculated from the
|
|
|
|
* ioprio to export the same interface as CFQ. When dealing with
|
|
|
|
* ``well-behaved'' queues (i.e., queues that do not spend too much
|
|
|
|
* time to consume their budget and have true sequential behavior, and
|
|
|
|
* when there are no external factors breaking anticipation) the
|
|
|
|
* relative weights at each level of the cgroups hierarchy should be
|
|
|
|
* guaranteed. All the fields are protected by the queue lock of the
|
|
|
|
* containing bfqd.
|
|
|
|
*/
|
|
|
|
struct bfq_entity {
|
|
|
|
/* service_tree member */
|
|
|
|
struct rb_node rb_node;
|
|
|
|
/* pointer to the weight counter associated with this entity */
|
|
|
|
struct bfq_weight_counter *weight_counter;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Flag, true if the entity is on a tree (either the active or
|
|
|
|
* the idle one of its service_tree) or is in service.
|
|
|
|
*/
|
|
|
|
bool on_st;
|
|
|
|
|
|
|
|
/* B-WF2Q+ start and finish timestamps [sectors/weight] */
|
|
|
|
u64 start, finish;
|
|
|
|
|
|
|
|
/* tree the entity is enqueued into; %NULL if not on a tree */
|
|
|
|
struct rb_root *tree;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* minimum start time of the (active) subtree rooted at this
|
|
|
|
* entity; used for O(log N) lookups into active trees
|
|
|
|
*/
|
|
|
|
u64 min_start;
|
|
|
|
|
|
|
|
/* amount of service received during the last service slot */
|
|
|
|
int service;
|
|
|
|
|
|
|
|
/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
|
|
|
|
int budget;
|
|
|
|
|
|
|
|
/* weight of the queue */
|
|
|
|
int weight;
|
|
|
|
/* next weight if a change is in progress */
|
|
|
|
int new_weight;
|
|
|
|
|
|
|
|
/* original weight, used to implement weight boosting */
|
|
|
|
int orig_weight;
|
|
|
|
|
|
|
|
/* parent entity, for hierarchical scheduling */
|
|
|
|
struct bfq_entity *parent;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* For non-leaf nodes in the hierarchy, the associated
|
|
|
|
* scheduler queue, %NULL on leaf nodes.
|
|
|
|
*/
|
|
|
|
struct bfq_sched_data *my_sched_data;
|
|
|
|
/* the scheduler queue this entity belongs to */
|
|
|
|
struct bfq_sched_data *sched_data;
|
|
|
|
|
|
|
|
/* flag, set to request a weight, ioprio or ioprio_class change */
|
|
|
|
int prio_changed;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct bfq_group;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* struct bfq_ttime - per process thinktime stats.
|
|
|
|
*/
|
|
|
|
struct bfq_ttime {
|
|
|
|
/* completion time of the last request */
|
|
|
|
u64 last_end_request;
|
|
|
|
|
|
|
|
/* total process thinktime */
|
|
|
|
u64 ttime_total;
|
|
|
|
/* number of thinktime samples */
|
|
|
|
unsigned long ttime_samples;
|
|
|
|
/* average process thinktime */
|
|
|
|
u64 ttime_mean;
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* struct bfq_queue - leaf schedulable entity.
|
|
|
|
*
|
|
|
|
* A bfq_queue is a leaf request queue; it can be associated with an
|
|
|
|
* io_context or more, if it is async or shared between cooperating
|
|
|
|
* processes. @cgroup holds a reference to the cgroup, to be sure that it
|
|
|
|
* does not disappear while a bfqq still references it (mostly to avoid
|
|
|
|
* races between request issuing and task migration followed by cgroup
|
|
|
|
* destruction).
|
|
|
|
* All the fields are protected by the queue lock of the containing bfqd.
|
|
|
|
*/
|
|
|
|
struct bfq_queue {
|
|
|
|
/* reference counter */
|
|
|
|
int ref;
|
|
|
|
/* parent bfq_data */
|
|
|
|
struct bfq_data *bfqd;
|
|
|
|
|
|
|
|
/* current ioprio and ioprio class */
|
|
|
|
unsigned short ioprio, ioprio_class;
|
|
|
|
/* next ioprio and ioprio class if a change is in progress */
|
|
|
|
unsigned short new_ioprio, new_ioprio_class;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Shared bfq_queue if queue is cooperating with one or more
|
|
|
|
* other queues.
|
|
|
|
*/
|
|
|
|
struct bfq_queue *new_bfqq;
|
|
|
|
/* request-position tree member (see bfq_group's @rq_pos_tree) */
|
|
|
|
struct rb_node pos_node;
|
|
|
|
/* request-position tree root (see bfq_group's @rq_pos_tree) */
|
|
|
|
struct rb_root *pos_root;
|
|
|
|
|
|
|
|
/* sorted list of pending requests */
|
|
|
|
struct rb_root sort_list;
|
|
|
|
/* if fifo isn't expired, next request to serve */
|
|
|
|
struct request *next_rq;
|
|
|
|
/* number of sync and async requests queued */
|
|
|
|
int queued[2];
|
|
|
|
/* number of requests currently allocated */
|
|
|
|
int allocated;
|
|
|
|
/* number of pending metadata requests */
|
|
|
|
int meta_pending;
|
|
|
|
/* fifo list of requests in sort_list */
|
|
|
|
struct list_head fifo;
|
|
|
|
|
|
|
|
/* entity representing this queue in the scheduler */
|
|
|
|
struct bfq_entity entity;
|
|
|
|
|
|
|
|
/* maximum budget allowed from the feedback mechanism */
|
|
|
|
int max_budget;
|
|
|
|
/* budget expiration (in jiffies) */
|
|
|
|
unsigned long budget_timeout;
|
|
|
|
|
|
|
|
/* number of requests on the dispatch list or inside driver */
|
|
|
|
int dispatched;
|
|
|
|
|
|
|
|
/* status flags */
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
/* node for active/idle bfqq list inside parent bfqd */
|
|
|
|
struct list_head bfqq_list;
|
|
|
|
|
|
|
|
/* associated @bfq_ttime struct */
|
|
|
|
struct bfq_ttime ttime;
|
|
|
|
|
|
|
|
/* bit vector: a 1 for each seeky requests in history */
|
|
|
|
u32 seek_history;
|
|
|
|
|
|
|
|
/* node for the device's burst list */
|
|
|
|
struct hlist_node burst_list_node;
|
|
|
|
|
|
|
|
/* position of the last request enqueued */
|
|
|
|
sector_t last_request_pos;
|
|
|
|
|
|
|
|
/* Number of consecutive pairs of request completion and
|
|
|
|
* arrival, such that the queue becomes idle after the
|
|
|
|
* completion, but the next request arrives within an idle
|
|
|
|
* time slice; used only if the queue's IO_bound flag has been
|
|
|
|
* cleared.
|
|
|
|
*/
|
|
|
|
unsigned int requests_within_timer;
|
|
|
|
|
|
|
|
/* pid of the process owning the queue, used for logging purposes */
|
|
|
|
pid_t pid;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Pointer to the bfq_io_cq owning the bfq_queue, set to %NULL
|
|
|
|
* if the queue is shared.
|
|
|
|
*/
|
|
|
|
struct bfq_io_cq *bic;
|
|
|
|
|
|
|
|
/* current maximum weight-raising time for this queue */
|
|
|
|
unsigned long wr_cur_max_time;
|
|
|
|
/*
|
|
|
|
* Minimum time instant such that, only if a new request is
|
|
|
|
* enqueued after this time instant in an idle @bfq_queue with
|
|
|
|
* no outstanding requests, then the task associated with the
|
|
|
|
* queue it is deemed as soft real-time (see the comments on
|
|
|
|
* the function bfq_bfqq_softrt_next_start())
|
|
|
|
*/
|
|
|
|
unsigned long soft_rt_next_start;
|
|
|
|
/*
|
|
|
|
* Start time of the current weight-raising period if
|
|
|
|
* the @bfq-queue is being weight-raised, otherwise
|
|
|
|
* finish time of the last weight-raising period.
|
|
|
|
*/
|
|
|
|
unsigned long last_wr_start_finish;
|
|
|
|
/* factor by which the weight of this queue is multiplied */
|
|
|
|
unsigned int wr_coeff;
|
|
|
|
/*
|
|
|
|
* Time of the last transition of the @bfq_queue from idle to
|
|
|
|
* backlogged.
|
|
|
|
*/
|
|
|
|
unsigned long last_idle_bklogged;
|
|
|
|
/*
|
|
|
|
* Cumulative service received from the @bfq_queue since the
|
|
|
|
* last transition from idle to backlogged.
|
|
|
|
*/
|
|
|
|
unsigned long service_from_backlogged;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Value of wr start time when switching to soft rt
|
|
|
|
*/
|
|
|
|
unsigned long wr_start_at_switch_to_srt;
|
|
|
|
|
|
|
|
unsigned long split_time; /* time of last split */
|
block, bfq: let a queue be merged only shortly after starting I/O
In BFQ and CFQ, two processes are said to be cooperating if they do
I/O in such a way that the union of their I/O requests yields a
sequential I/O pattern. To get such a sequential I/O pattern out of
the non-sequential pattern of each cooperating process, BFQ and CFQ
merge the queues associated with these processes. In more detail,
cooperating processes, and thus their associated queues, usually
start, or restart, to do I/O shortly after each other. This is the
case, e.g., for the I/O threads of KVM/QEMU and of the dump
utility. Basing on this assumption, this commit allows a bfq_queue to
be merged only during a short time interval (100ms) after it starts,
or re-starts, to do I/O. This filtering provides two important
benefits.
First, it greatly reduces the probability that two non-cooperating
processes have their queues merged by mistake, if they just happen to
do I/O close to each other for a short time interval. These spurious
merges cause loss of service guarantees. A low-weight bfq_queue may
unjustly get more than its expected share of the throughput: if such a
low-weight queue is merged with a high-weight queue, then the I/O for
the low-weight queue is served as if the queue had a high weight. This
may damage other high-weight queues unexpectedly. For instance,
because of this issue, lxterminal occasionally took 7.5 seconds to
start, instead of 6.5 seconds, when some sequential readers and
writers did I/O in the background on a FUJITSU MHX2300BT HDD. The
reason is that the bfq_queues associated with some of the readers or
the writers were merged with the high-weight queues of some processes
that had to do some urgent but little I/O. The readers then exploited
the inherited high weight for all or most of their I/O, during the
start-up of terminal. The filtering introduced by this commit
eliminated any outlier caused by spurious queue merges in our start-up
time tests.
This filtering also provides a little boost of the throughput
sustainable by BFQ: 3-4%, depending on the CPU. The reason is that,
once a bfq_queue cannot be merged any longer, this commit makes BFQ
stop updating the data needed to handle merging for the queue.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Angelo Ruocco <angeloruocco90@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-12-20 19:38:33 +08:00
|
|
|
|
|
|
|
unsigned long first_IO_time; /* time of first I/O for this queue */
|
2017-04-19 22:48:24 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* struct bfq_io_cq - per (request_queue, io_context) structure.
|
|
|
|
*/
|
|
|
|
struct bfq_io_cq {
|
|
|
|
/* associated io_cq structure */
|
|
|
|
struct io_cq icq; /* must be the first member */
|
|
|
|
/* array of two process queues, the sync and the async */
|
|
|
|
struct bfq_queue *bfqq[2];
|
|
|
|
/* per (request_queue, blkcg) ioprio */
|
|
|
|
int ioprio;
|
|
|
|
#ifdef CONFIG_BFQ_GROUP_IOSCHED
|
|
|
|
uint64_t blkcg_serial_nr; /* the current blkcg serial */
|
|
|
|
#endif
|
|
|
|
/*
|
2017-08-04 13:35:10 +08:00
|
|
|
* Snapshot of the has_short_time flag before merging; taken
|
|
|
|
* to remember its value while the queue is merged, so as to
|
|
|
|
* be able to restore it in case of split.
|
2017-04-19 22:48:24 +08:00
|
|
|
*/
|
2017-08-04 13:35:10 +08:00
|
|
|
bool saved_has_short_ttime;
|
2017-04-19 22:48:24 +08:00
|
|
|
/*
|
|
|
|
* Same purpose as the previous two fields for the I/O bound
|
|
|
|
* classification of a queue.
|
|
|
|
*/
|
|
|
|
bool saved_IO_bound;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Same purpose as the previous fields for the value of the
|
|
|
|
* field keeping the queue's belonging to a large burst
|
|
|
|
*/
|
|
|
|
bool saved_in_large_burst;
|
|
|
|
/*
|
|
|
|
* True if the queue belonged to a burst list before its merge
|
|
|
|
* with another cooperating queue.
|
|
|
|
*/
|
|
|
|
bool was_in_burst_list;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Similar to previous fields: save wr information.
|
|
|
|
*/
|
|
|
|
unsigned long saved_wr_coeff;
|
|
|
|
unsigned long saved_last_wr_start_finish;
|
|
|
|
unsigned long saved_wr_start_at_switch_to_srt;
|
|
|
|
unsigned int saved_wr_cur_max_time;
|
|
|
|
struct bfq_ttime saved_ttime;
|
|
|
|
};
|
|
|
|
|
|
|
|
enum bfq_device_speed {
|
|
|
|
BFQ_BFQD_FAST,
|
|
|
|
BFQ_BFQD_SLOW,
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* struct bfq_data - per-device data structure.
|
|
|
|
*
|
|
|
|
* All the fields are protected by @lock.
|
|
|
|
*/
|
|
|
|
struct bfq_data {
|
|
|
|
/* device request queue */
|
|
|
|
struct request_queue *queue;
|
|
|
|
/* dispatch queue */
|
|
|
|
struct list_head dispatch;
|
|
|
|
|
|
|
|
/* root bfq_group for the device */
|
|
|
|
struct bfq_group *root_group;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* rbtree of weight counters of @bfq_queues, sorted by
|
|
|
|
* weight. Used to keep track of whether all @bfq_queues have
|
|
|
|
* the same weight. The tree contains one counter for each
|
|
|
|
* distinct weight associated to some active and not
|
|
|
|
* weight-raised @bfq_queue (see the comments to the functions
|
|
|
|
* bfq_weights_tree_[add|remove] for further details).
|
|
|
|
*/
|
|
|
|
struct rb_root queue_weights_tree;
|
|
|
|
/*
|
|
|
|
* rbtree of non-queue @bfq_entity weight counters, sorted by
|
|
|
|
* weight. Used to keep track of whether all @bfq_groups have
|
|
|
|
* the same weight. The tree contains one counter for each
|
|
|
|
* distinct weight associated to some active @bfq_group (see
|
|
|
|
* the comments to the functions bfq_weights_tree_[add|remove]
|
|
|
|
* for further details).
|
|
|
|
*/
|
|
|
|
struct rb_root group_weights_tree;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Number of bfq_queues containing requests (including the
|
|
|
|
* queue in service, even if it is idling).
|
|
|
|
*/
|
|
|
|
int busy_queues;
|
|
|
|
/* number of weight-raised busy @bfq_queues */
|
|
|
|
int wr_busy_queues;
|
|
|
|
/* number of queued requests */
|
|
|
|
int queued;
|
|
|
|
/* number of requests dispatched and waiting for completion */
|
|
|
|
int rq_in_driver;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Maximum number of requests in driver in the last
|
|
|
|
* @hw_tag_samples completed requests.
|
|
|
|
*/
|
|
|
|
int max_rq_in_driver;
|
|
|
|
/* number of samples used to calculate hw_tag */
|
|
|
|
int hw_tag_samples;
|
|
|
|
/* flag set to one if the driver is showing a queueing behavior */
|
|
|
|
int hw_tag;
|
|
|
|
|
|
|
|
/* number of budgets assigned */
|
|
|
|
int budgets_assigned;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Timer set when idling (waiting) for the next request from
|
|
|
|
* the queue in service.
|
|
|
|
*/
|
|
|
|
struct hrtimer idle_slice_timer;
|
|
|
|
|
|
|
|
/* bfq_queue in service */
|
|
|
|
struct bfq_queue *in_service_queue;
|
|
|
|
|
|
|
|
/* on-disk position of the last served request */
|
|
|
|
sector_t last_position;
|
|
|
|
|
|
|
|
/* time of last request completion (ns) */
|
|
|
|
u64 last_completion;
|
|
|
|
|
|
|
|
/* time of first rq dispatch in current observation interval (ns) */
|
|
|
|
u64 first_dispatch;
|
|
|
|
/* time of last rq dispatch in current observation interval (ns) */
|
|
|
|
u64 last_dispatch;
|
|
|
|
|
|
|
|
/* beginning of the last budget */
|
|
|
|
ktime_t last_budget_start;
|
|
|
|
/* beginning of the last idle slice */
|
|
|
|
ktime_t last_idling_start;
|
|
|
|
|
|
|
|
/* number of samples in current observation interval */
|
|
|
|
int peak_rate_samples;
|
|
|
|
/* num of samples of seq dispatches in current observation interval */
|
|
|
|
u32 sequential_samples;
|
|
|
|
/* total num of sectors transferred in current observation interval */
|
|
|
|
u64 tot_sectors_dispatched;
|
|
|
|
/* max rq size seen during current observation interval (sectors) */
|
|
|
|
u32 last_rq_max_size;
|
|
|
|
/* time elapsed from first dispatch in current observ. interval (us) */
|
|
|
|
u64 delta_from_first;
|
|
|
|
/*
|
|
|
|
* Current estimate of the device peak rate, measured in
|
|
|
|
* [BFQ_RATE_SHIFT * sectors/usec]. The left-shift by
|
|
|
|
* BFQ_RATE_SHIFT is performed to increase precision in
|
|
|
|
* fixed-point calculations.
|
|
|
|
*/
|
|
|
|
u32 peak_rate;
|
|
|
|
|
|
|
|
/* maximum budget allotted to a bfq_queue before rescheduling */
|
|
|
|
int bfq_max_budget;
|
|
|
|
|
|
|
|
/* list of all the bfq_queues active on the device */
|
|
|
|
struct list_head active_list;
|
|
|
|
/* list of all the bfq_queues idle on the device */
|
|
|
|
struct list_head idle_list;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Timeout for async/sync requests; when it fires, requests
|
|
|
|
* are served in fifo order.
|
|
|
|
*/
|
|
|
|
u64 bfq_fifo_expire[2];
|
|
|
|
/* weight of backward seeks wrt forward ones */
|
|
|
|
unsigned int bfq_back_penalty;
|
|
|
|
/* maximum allowed backward seek */
|
|
|
|
unsigned int bfq_back_max;
|
|
|
|
/* maximum idling time */
|
|
|
|
u32 bfq_slice_idle;
|
|
|
|
|
|
|
|
/* user-configured max budget value (0 for auto-tuning) */
|
|
|
|
int bfq_user_max_budget;
|
|
|
|
/*
|
|
|
|
* Timeout for bfq_queues to consume their budget; used to
|
|
|
|
* prevent seeky queues from imposing long latencies to
|
|
|
|
* sequential or quasi-sequential ones (this also implies that
|
|
|
|
* seeky queues cannot receive guarantees in the service
|
|
|
|
* domain; after a timeout they are charged for the time they
|
|
|
|
* have been in service, to preserve fairness among them, but
|
|
|
|
* without service-domain guarantees).
|
|
|
|
*/
|
|
|
|
unsigned int bfq_timeout;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Number of consecutive requests that must be issued within
|
|
|
|
* the idle time slice to set again idling to a queue which
|
|
|
|
* was marked as non-I/O-bound (see the definition of the
|
|
|
|
* IO_bound flag for further details).
|
|
|
|
*/
|
|
|
|
unsigned int bfq_requests_within_timer;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Force device idling whenever needed to provide accurate
|
|
|
|
* service guarantees, without caring about throughput
|
|
|
|
* issues. CAVEAT: this may even increase latencies, in case
|
|
|
|
* of useless idling for processes that did stop doing I/O.
|
|
|
|
*/
|
|
|
|
bool strict_guarantees;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Last time at which a queue entered the current burst of
|
|
|
|
* queues being activated shortly after each other; for more
|
|
|
|
* details about this and the following parameters related to
|
|
|
|
* a burst of activations, see the comments on the function
|
|
|
|
* bfq_handle_burst.
|
|
|
|
*/
|
|
|
|
unsigned long last_ins_in_burst;
|
|
|
|
/*
|
|
|
|
* Reference time interval used to decide whether a queue has
|
|
|
|
* been activated shortly after @last_ins_in_burst.
|
|
|
|
*/
|
|
|
|
unsigned long bfq_burst_interval;
|
|
|
|
/* number of queues in the current burst of queue activations */
|
|
|
|
int burst_size;
|
|
|
|
|
|
|
|
/* common parent entity for the queues in the burst */
|
|
|
|
struct bfq_entity *burst_parent_entity;
|
|
|
|
/* Maximum burst size above which the current queue-activation
|
|
|
|
* burst is deemed as 'large'.
|
|
|
|
*/
|
|
|
|
unsigned long bfq_large_burst_thresh;
|
|
|
|
/* true if a large queue-activation burst is in progress */
|
|
|
|
bool large_burst;
|
|
|
|
/*
|
|
|
|
* Head of the burst list (as for the above fields, more
|
|
|
|
* details in the comments on the function bfq_handle_burst).
|
|
|
|
*/
|
|
|
|
struct hlist_head burst_list;
|
|
|
|
|
|
|
|
/* if set to true, low-latency heuristics are enabled */
|
|
|
|
bool low_latency;
|
|
|
|
/*
|
|
|
|
* Maximum factor by which the weight of a weight-raised queue
|
|
|
|
* is multiplied.
|
|
|
|
*/
|
|
|
|
unsigned int bfq_wr_coeff;
|
|
|
|
/* maximum duration of a weight-raising period (jiffies) */
|
|
|
|
unsigned int bfq_wr_max_time;
|
|
|
|
|
|
|
|
/* Maximum weight-raising duration for soft real-time processes */
|
|
|
|
unsigned int bfq_wr_rt_max_time;
|
|
|
|
/*
|
|
|
|
* Minimum idle period after which weight-raising may be
|
|
|
|
* reactivated for a queue (in jiffies).
|
|
|
|
*/
|
|
|
|
unsigned int bfq_wr_min_idle_time;
|
|
|
|
/*
|
|
|
|
* Minimum period between request arrivals after which
|
|
|
|
* weight-raising may be reactivated for an already busy async
|
|
|
|
* queue (in jiffies).
|
|
|
|
*/
|
|
|
|
unsigned long bfq_wr_min_inter_arr_async;
|
|
|
|
|
|
|
|
/* Max service-rate for a soft real-time queue, in sectors/sec */
|
|
|
|
unsigned int bfq_wr_max_softrt_rate;
|
|
|
|
/*
|
|
|
|
* Cached value of the product R*T, used for computing the
|
|
|
|
* maximum duration of weight raising automatically.
|
|
|
|
*/
|
|
|
|
u64 RT_prod;
|
|
|
|
/* device-speed class for the low-latency heuristic */
|
|
|
|
enum bfq_device_speed device_speed;
|
|
|
|
|
|
|
|
/* fallback dummy bfqq for extreme OOM conditions */
|
|
|
|
struct bfq_queue oom_bfqq;
|
|
|
|
|
|
|
|
spinlock_t lock;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* bic associated with the task issuing current bio for
|
|
|
|
* merging. This and the next field are used as a support to
|
|
|
|
* be able to perform the bic lookup, needed by bio-merge
|
|
|
|
* functions, before the scheduler lock is taken, and thus
|
|
|
|
* avoid taking the request-queue lock while the scheduler
|
|
|
|
* lock is being held.
|
|
|
|
*/
|
|
|
|
struct bfq_io_cq *bio_bic;
|
|
|
|
/* bfqq associated with the task issuing current bio for merging */
|
|
|
|
struct bfq_queue *bio_bfqq;
|
block, bfq: limit tags for writes and async I/O
Asynchronous I/O can easily starve synchronous I/O (both sync reads
and sync writes), by consuming all request tags. Similarly, storms of
synchronous writes, such as those that sync(2) may trigger, can starve
synchronous reads. In their turn, these two problems may also cause
BFQ to loose control on latency for interactive and soft real-time
applications. For example, on a PLEXTOR PX-256M5S SSD, LibreOffice
Writer takes 0.6 seconds to start if the device is idle, but it takes
more than 45 seconds (!) if there are sequential writes in the
background.
This commit addresses this issue by limiting the maximum percentage of
tags that asynchronous I/O requests and synchronous write requests can
consume. In particular, this commit grants a higher threshold to
synchronous writes, to prevent the latter from being starved by
asynchronous I/O.
According to the above test, LibreOffice Writer now starts in about
1.2 seconds on average, regardless of the background workload, and
apart from some rare outlier. To check this improvement, run, e.g.,
sudo ./comm_startup_lat.sh bfq 5 5 seq 10 "lowriter --terminate_after_init"
for the comm_startup_lat benchmark in the S suite [1].
[1] https://github.com/Algodev-github/S
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-13 19:05:17 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Cached sbitmap shift, used to compute depth limits in
|
|
|
|
* bfq_update_depths.
|
|
|
|
*/
|
|
|
|
unsigned int sb_shift;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Depth limits used in bfq_limit_depth (see comments on the
|
|
|
|
* function)
|
|
|
|
*/
|
|
|
|
unsigned int word_depths[2][2];
|
2017-04-19 22:48:24 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
enum bfqq_state_flags {
|
|
|
|
BFQQF_just_created = 0, /* queue just allocated */
|
|
|
|
BFQQF_busy, /* has requests or is in service */
|
|
|
|
BFQQF_wait_request, /* waiting for a request */
|
|
|
|
BFQQF_non_blocking_wait_rq, /*
|
|
|
|
* waiting for a request
|
|
|
|
* without idling the device
|
|
|
|
*/
|
|
|
|
BFQQF_fifo_expire, /* FIFO checked in this slice */
|
2017-08-04 13:35:10 +08:00
|
|
|
BFQQF_has_short_ttime, /* queue has a short think time */
|
2017-04-19 22:48:24 +08:00
|
|
|
BFQQF_sync, /* synchronous queue */
|
|
|
|
BFQQF_IO_bound, /*
|
|
|
|
* bfqq has timed-out at least once
|
|
|
|
* having consumed at most 2/10 of
|
|
|
|
* its budget
|
|
|
|
*/
|
|
|
|
BFQQF_in_large_burst, /*
|
|
|
|
* bfqq activated in a large burst,
|
|
|
|
* see comments to bfq_handle_burst.
|
|
|
|
*/
|
|
|
|
BFQQF_softrt_update, /*
|
|
|
|
* may need softrt-next-start
|
|
|
|
* update
|
|
|
|
*/
|
|
|
|
BFQQF_coop, /* bfqq is shared */
|
|
|
|
BFQQF_split_coop /* shared bfqq will be split */
|
|
|
|
};
|
|
|
|
|
|
|
|
#define BFQ_BFQQ_FNS(name) \
|
|
|
|
void bfq_mark_bfqq_##name(struct bfq_queue *bfqq); \
|
|
|
|
void bfq_clear_bfqq_##name(struct bfq_queue *bfqq); \
|
|
|
|
int bfq_bfqq_##name(const struct bfq_queue *bfqq);
|
|
|
|
|
|
|
|
BFQ_BFQQ_FNS(just_created);
|
|
|
|
BFQ_BFQQ_FNS(busy);
|
|
|
|
BFQ_BFQQ_FNS(wait_request);
|
|
|
|
BFQ_BFQQ_FNS(non_blocking_wait_rq);
|
|
|
|
BFQ_BFQQ_FNS(fifo_expire);
|
2017-08-04 13:35:10 +08:00
|
|
|
BFQ_BFQQ_FNS(has_short_ttime);
|
2017-04-19 22:48:24 +08:00
|
|
|
BFQ_BFQQ_FNS(sync);
|
|
|
|
BFQ_BFQQ_FNS(IO_bound);
|
|
|
|
BFQ_BFQQ_FNS(in_large_burst);
|
|
|
|
BFQ_BFQQ_FNS(coop);
|
|
|
|
BFQ_BFQQ_FNS(split_coop);
|
|
|
|
BFQ_BFQQ_FNS(softrt_update);
|
|
|
|
#undef BFQ_BFQQ_FNS
|
|
|
|
|
|
|
|
/* Expiration reasons. */
|
|
|
|
enum bfqq_expiration {
|
|
|
|
BFQQE_TOO_IDLE = 0, /*
|
|
|
|
* queue has been idling for
|
|
|
|
* too long
|
|
|
|
*/
|
|
|
|
BFQQE_BUDGET_TIMEOUT, /* budget took too long to be used */
|
|
|
|
BFQQE_BUDGET_EXHAUSTED, /* budget consumed */
|
|
|
|
BFQQE_NO_MORE_REQUESTS, /* the queue has no more requests */
|
|
|
|
BFQQE_PREEMPTED /* preemption in progress */
|
|
|
|
};
|
|
|
|
|
|
|
|
struct bfqg_stats {
|
block, bfq: move debug blkio stats behind CONFIG_DEBUG_BLK_CGROUP
BFQ currently creates, and updates, its own instance of the whole
set of blkio statistics that cfq creates. Yet, from the comments
of Tejun Heo in [1], it turned out that most of these statistics
are meant/useful only for debugging. This commit makes BFQ create
the latter, debugging statistics only if the option
CONFIG_DEBUG_BLK_CGROUP is set.
By doing so, this commit also enables BFQ to enjoy a high perfomance
boost. The reason is that, if CONFIG_DEBUG_BLK_CGROUP is not set, then
BFQ has to update far fewer statistics, and, in particular, not the
heaviest to update. To give an idea of the benefits, if
CONFIG_DEBUG_BLK_CGROUP is not set, then, on an Intel i7-4850HQ, and
with 8 threads doing random I/O in parallel on null_blk (configured
with 0 latency), the throughput of BFQ grows from 310 to 400 KIOPS
(+30%). We have measured similar or even much higher boosts with other
CPUs: e.g., +45% with an ARM CortexTM-A53 Octa-core. Our results have
been obtained and can be reproduced very easily with the script in [1].
[1] https://www.spinics.net/lists/linux-block/msg18943.html
Suggested-by: Tejun Heo <tj@kernel.org>
Suggested-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Luca Miccio <lucmiccio@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-13 14:34:10 +08:00
|
|
|
#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
|
2017-04-19 22:48:24 +08:00
|
|
|
/* number of ios merged */
|
|
|
|
struct blkg_rwstat merged;
|
|
|
|
/* total time spent on device in ns, may not be accurate w/ queueing */
|
|
|
|
struct blkg_rwstat service_time;
|
|
|
|
/* total time spent waiting in scheduler queue in ns */
|
|
|
|
struct blkg_rwstat wait_time;
|
|
|
|
/* number of IOs queued up */
|
|
|
|
struct blkg_rwstat queued;
|
|
|
|
/* total disk time and nr sectors dispatched by this group */
|
|
|
|
struct blkg_stat time;
|
|
|
|
/* sum of number of ios queued across all samples */
|
|
|
|
struct blkg_stat avg_queue_size_sum;
|
|
|
|
/* count of samples taken for average */
|
|
|
|
struct blkg_stat avg_queue_size_samples;
|
|
|
|
/* how many times this group has been removed from service tree */
|
|
|
|
struct blkg_stat dequeue;
|
|
|
|
/* total time spent waiting for it to be assigned a timeslice. */
|
|
|
|
struct blkg_stat group_wait_time;
|
|
|
|
/* time spent idling for this blkcg_gq */
|
|
|
|
struct blkg_stat idle_time;
|
|
|
|
/* total time with empty current active q with other requests queued */
|
|
|
|
struct blkg_stat empty_time;
|
|
|
|
/* fields after this shouldn't be cleared on stat reset */
|
|
|
|
uint64_t start_group_wait_time;
|
|
|
|
uint64_t start_idle_time;
|
|
|
|
uint64_t start_empty_time;
|
|
|
|
uint16_t flags;
|
block, bfq: move debug blkio stats behind CONFIG_DEBUG_BLK_CGROUP
BFQ currently creates, and updates, its own instance of the whole
set of blkio statistics that cfq creates. Yet, from the comments
of Tejun Heo in [1], it turned out that most of these statistics
are meant/useful only for debugging. This commit makes BFQ create
the latter, debugging statistics only if the option
CONFIG_DEBUG_BLK_CGROUP is set.
By doing so, this commit also enables BFQ to enjoy a high perfomance
boost. The reason is that, if CONFIG_DEBUG_BLK_CGROUP is not set, then
BFQ has to update far fewer statistics, and, in particular, not the
heaviest to update. To give an idea of the benefits, if
CONFIG_DEBUG_BLK_CGROUP is not set, then, on an Intel i7-4850HQ, and
with 8 threads doing random I/O in parallel on null_blk (configured
with 0 latency), the throughput of BFQ grows from 310 to 400 KIOPS
(+30%). We have measured similar or even much higher boosts with other
CPUs: e.g., +45% with an ARM CortexTM-A53 Octa-core. Our results have
been obtained and can be reproduced very easily with the script in [1].
[1] https://www.spinics.net/lists/linux-block/msg18943.html
Suggested-by: Tejun Heo <tj@kernel.org>
Suggested-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Luca Miccio <lucmiccio@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-13 14:34:10 +08:00
|
|
|
#endif /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
|
2017-04-19 22:48:24 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
#ifdef CONFIG_BFQ_GROUP_IOSCHED
|
|
|
|
|
|
|
|
/*
|
|
|
|
* struct bfq_group_data - per-blkcg storage for the blkio subsystem.
|
|
|
|
*
|
|
|
|
* @ps: @blkcg_policy_storage that this structure inherits
|
|
|
|
* @weight: weight of the bfq_group
|
|
|
|
*/
|
|
|
|
struct bfq_group_data {
|
|
|
|
/* must be the first member */
|
|
|
|
struct blkcg_policy_data pd;
|
|
|
|
|
|
|
|
unsigned int weight;
|
|
|
|
};
|
|
|
|
|
|
|
|
/**
|
|
|
|
* struct bfq_group - per (device, cgroup) data structure.
|
|
|
|
* @entity: schedulable entity to insert into the parent group sched_data.
|
|
|
|
* @sched_data: own sched_data, to contain child entities (they may be
|
|
|
|
* both bfq_queues and bfq_groups).
|
|
|
|
* @bfqd: the bfq_data for the device this group acts upon.
|
|
|
|
* @async_bfqq: array of async queues for all the tasks belonging to
|
|
|
|
* the group, one queue per ioprio value per ioprio_class,
|
|
|
|
* except for the idle class that has only one queue.
|
|
|
|
* @async_idle_bfqq: async queue for the idle class (ioprio is ignored).
|
|
|
|
* @my_entity: pointer to @entity, %NULL for the toplevel group; used
|
|
|
|
* to avoid too many special cases during group creation/
|
|
|
|
* migration.
|
|
|
|
* @stats: stats for this bfqg.
|
|
|
|
* @active_entities: number of active entities belonging to the group;
|
|
|
|
* unused for the root group. Used to know whether there
|
|
|
|
* are groups with more than one active @bfq_entity
|
|
|
|
* (see the comments to the function
|
|
|
|
* bfq_bfqq_may_idle()).
|
|
|
|
* @rq_pos_tree: rbtree sorted by next_request position, used when
|
|
|
|
* determining if two or more queues have interleaving
|
|
|
|
* requests (see bfq_find_close_cooperator()).
|
|
|
|
*
|
|
|
|
* Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup
|
|
|
|
* there is a set of bfq_groups, each one collecting the lower-level
|
|
|
|
* entities belonging to the group that are acting on the same device.
|
|
|
|
*
|
|
|
|
* Locking works as follows:
|
|
|
|
* o @bfqd is protected by the queue lock, RCU is used to access it
|
|
|
|
* from the readers.
|
|
|
|
* o All the other fields are protected by the @bfqd queue lock.
|
|
|
|
*/
|
|
|
|
struct bfq_group {
|
|
|
|
/* must be the first member */
|
|
|
|
struct blkg_policy_data pd;
|
|
|
|
|
block, bfq: access and cache blkg data only when safe
In blk-cgroup, operations on blkg objects are protected with the
request_queue lock. This is no more the lock that protects
I/O-scheduler operations in blk-mq. In fact, the latter are now
protected with a finer-grained per-scheduler-instance lock. As a
consequence, although blkg lookups are also rcu-protected, blk-mq I/O
schedulers may see inconsistent data when they access blkg and
blkg-related objects. BFQ does access these objects, and does incur
this problem, in the following case.
The blkg_lookup performed in bfq_get_queue, being protected (only)
through rcu, may happen to return the address of a copy of the
original blkg. If this is the case, then the blkg_get performed in
bfq_get_queue, to pin down the blkg, is useless: it does not prevent
blk-cgroup code from destroying both the original blkg and all objects
directly or indirectly referred by the copy of the blkg. BFQ accesses
these objects, which typically causes a crash for NULL-pointer
dereference of memory-protection violation.
Some additional protection mechanism should be added to blk-cgroup to
address this issue. In the meantime, this commit provides a quick
temporary fix for BFQ: cache (when safe) blkg data that might
disappear right after a blkg_lookup.
In particular, this commit exploits the following facts to achieve its
goal without introducing further locks. Destroy operations on a blkg
invoke, as a first step, hooks of the scheduler associated with the
blkg. And these hooks are executed with bfqd->lock held for BFQ. As a
consequence, for any blkg associated with the request queue an
instance of BFQ is attached to, we are guaranteed that such a blkg is
not destroyed, and that all the pointers it contains are consistent,
while that instance is holding its bfqd->lock. A blkg_lookup performed
with bfqd->lock held then returns a fully consistent blkg, which
remains consistent until this lock is held. In more detail, this holds
even if the returned blkg is a copy of the original one.
Finally, also the object describing a group inside BFQ needs to be
protected from destruction on the blkg_free of the original blkg
(which invokes bfq_pd_free). This commit adds private refcounting for
this object, to let it disappear only after no bfq_queue refers to it
any longer.
This commit also removes or updates some stale comments on locking
issues related to blk-cgroup operations.
Reported-by: Tomas Konir <tomas.konir@gmail.com>
Reported-by: Lee Tibbert <lee.tibbert@gmail.com>
Reported-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Tomas Konir <tomas.konir@gmail.com>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-06-05 16:11:15 +08:00
|
|
|
/* cached path for this blkg (see comments in bfq_bic_update_cgroup) */
|
|
|
|
char blkg_path[128];
|
|
|
|
|
|
|
|
/* reference counter (see comments in bfq_bic_update_cgroup) */
|
|
|
|
int ref;
|
|
|
|
|
2017-04-19 22:48:24 +08:00
|
|
|
struct bfq_entity entity;
|
|
|
|
struct bfq_sched_data sched_data;
|
|
|
|
|
|
|
|
void *bfqd;
|
|
|
|
|
|
|
|
struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
|
|
|
|
struct bfq_queue *async_idle_bfqq;
|
|
|
|
|
|
|
|
struct bfq_entity *my_entity;
|
|
|
|
|
|
|
|
int active_entities;
|
|
|
|
|
|
|
|
struct rb_root rq_pos_tree;
|
|
|
|
|
|
|
|
struct bfqg_stats stats;
|
|
|
|
};
|
|
|
|
|
|
|
|
#else
|
|
|
|
struct bfq_group {
|
|
|
|
struct bfq_sched_data sched_data;
|
|
|
|
|
|
|
|
struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
|
|
|
|
struct bfq_queue *async_idle_bfqq;
|
|
|
|
|
|
|
|
struct rb_root rq_pos_tree;
|
|
|
|
};
|
|
|
|
#endif
|
|
|
|
|
|
|
|
struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
|
|
|
|
|
|
|
|
/* --------------- main algorithm interface ----------------- */
|
|
|
|
|
|
|
|
#define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \
|
|
|
|
{ RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })
|
|
|
|
|
|
|
|
extern const int bfq_timeout;
|
|
|
|
|
|
|
|
struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync);
|
|
|
|
void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync);
|
|
|
|
struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
|
|
|
|
void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
|
|
|
|
void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
|
|
|
|
struct rb_root *root);
|
|
|
|
void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
|
|
|
|
struct rb_root *root);
|
|
|
|
void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
|
|
|
|
bool compensate, enum bfqq_expiration reason);
|
|
|
|
void bfq_put_queue(struct bfq_queue *bfqq);
|
|
|
|
void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
|
|
|
|
void bfq_schedule_dispatch(struct bfq_data *bfqd);
|
|
|
|
void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
|
|
|
|
|
|
|
|
/* ------------ end of main algorithm interface -------------- */
|
|
|
|
|
|
|
|
/* ---------------- cgroups-support interface ---------------- */
|
|
|
|
|
|
|
|
void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
|
|
|
|
unsigned int op);
|
|
|
|
void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
|
|
|
|
void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op);
|
|
|
|
void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
|
|
|
|
uint64_t io_start_time, unsigned int op);
|
|
|
|
void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
|
|
|
|
void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
|
|
|
|
void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
|
|
|
|
void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg);
|
|
|
|
void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg);
|
|
|
|
void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
|
|
|
|
struct bfq_group *bfqg);
|
|
|
|
|
|
|
|
void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg);
|
|
|
|
void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio);
|
|
|
|
void bfq_end_wr_async(struct bfq_data *bfqd);
|
|
|
|
struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
|
|
|
|
struct blkcg *blkcg);
|
|
|
|
struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
|
|
|
|
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
|
|
|
|
struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
|
block, bfq: access and cache blkg data only when safe
In blk-cgroup, operations on blkg objects are protected with the
request_queue lock. This is no more the lock that protects
I/O-scheduler operations in blk-mq. In fact, the latter are now
protected with a finer-grained per-scheduler-instance lock. As a
consequence, although blkg lookups are also rcu-protected, blk-mq I/O
schedulers may see inconsistent data when they access blkg and
blkg-related objects. BFQ does access these objects, and does incur
this problem, in the following case.
The blkg_lookup performed in bfq_get_queue, being protected (only)
through rcu, may happen to return the address of a copy of the
original blkg. If this is the case, then the blkg_get performed in
bfq_get_queue, to pin down the blkg, is useless: it does not prevent
blk-cgroup code from destroying both the original blkg and all objects
directly or indirectly referred by the copy of the blkg. BFQ accesses
these objects, which typically causes a crash for NULL-pointer
dereference of memory-protection violation.
Some additional protection mechanism should be added to blk-cgroup to
address this issue. In the meantime, this commit provides a quick
temporary fix for BFQ: cache (when safe) blkg data that might
disappear right after a blkg_lookup.
In particular, this commit exploits the following facts to achieve its
goal without introducing further locks. Destroy operations on a blkg
invoke, as a first step, hooks of the scheduler associated with the
blkg. And these hooks are executed with bfqd->lock held for BFQ. As a
consequence, for any blkg associated with the request queue an
instance of BFQ is attached to, we are guaranteed that such a blkg is
not destroyed, and that all the pointers it contains are consistent,
while that instance is holding its bfqd->lock. A blkg_lookup performed
with bfqd->lock held then returns a fully consistent blkg, which
remains consistent until this lock is held. In more detail, this holds
even if the returned blkg is a copy of the original one.
Finally, also the object describing a group inside BFQ needs to be
protected from destruction on the blkg_free of the original blkg
(which invokes bfq_pd_free). This commit adds private refcounting for
this object, to let it disappear only after no bfq_queue refers to it
any longer.
This commit also removes or updates some stale comments on locking
issues related to blk-cgroup operations.
Reported-by: Tomas Konir <tomas.konir@gmail.com>
Reported-by: Lee Tibbert <lee.tibbert@gmail.com>
Reported-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Tomas Konir <tomas.konir@gmail.com>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-06-05 16:11:15 +08:00
|
|
|
void bfqg_and_blkg_put(struct bfq_group *bfqg);
|
2017-04-19 22:48:24 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_BFQ_GROUP_IOSCHED
|
2017-04-20 23:37:05 +08:00
|
|
|
extern struct cftype bfq_blkcg_legacy_files[];
|
|
|
|
extern struct cftype bfq_blkg_files[];
|
2017-04-19 22:48:24 +08:00
|
|
|
extern struct blkcg_policy blkcg_policy_bfq;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* ------------- end of cgroups-support interface ------------- */
|
|
|
|
|
|
|
|
/* - interface of the internal hierarchical B-WF2Q+ scheduler - */
|
|
|
|
|
|
|
|
#ifdef CONFIG_BFQ_GROUP_IOSCHED
|
|
|
|
/* both next loops stop at one of the child entities of the root group */
|
|
|
|
#define for_each_entity(entity) \
|
|
|
|
for (; entity ; entity = entity->parent)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* For each iteration, compute parent in advance, so as to be safe if
|
|
|
|
* entity is deallocated during the iteration. Such a deallocation may
|
|
|
|
* happen as a consequence of a bfq_put_queue that frees the bfq_queue
|
|
|
|
* containing entity.
|
|
|
|
*/
|
|
|
|
#define for_each_entity_safe(entity, parent) \
|
|
|
|
for (; entity && ({ parent = entity->parent; 1; }); entity = parent)
|
|
|
|
|
|
|
|
#else /* CONFIG_BFQ_GROUP_IOSCHED */
|
|
|
|
/*
|
|
|
|
* Next two macros are fake loops when cgroups support is not
|
|
|
|
* enabled. I fact, in such a case, there is only one level to go up
|
|
|
|
* (to reach the root group).
|
|
|
|
*/
|
|
|
|
#define for_each_entity(entity) \
|
|
|
|
for (; entity ; entity = NULL)
|
|
|
|
|
|
|
|
#define for_each_entity_safe(entity, parent) \
|
|
|
|
for (parent = NULL; entity ; entity = parent)
|
|
|
|
#endif /* CONFIG_BFQ_GROUP_IOSCHED */
|
|
|
|
|
|
|
|
struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq);
|
|
|
|
struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
|
|
|
|
struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity);
|
|
|
|
struct bfq_entity *bfq_entity_of(struct rb_node *node);
|
|
|
|
unsigned short bfq_ioprio_to_weight(int ioprio);
|
|
|
|
void bfq_put_idle_entity(struct bfq_service_tree *st,
|
|
|
|
struct bfq_entity *entity);
|
|
|
|
struct bfq_service_tree *
|
|
|
|
__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
|
block, bfq: don't change ioprio class for a bfq_queue on a service tree
On each deactivation or re-scheduling (after being served) of a
bfq_queue, BFQ invokes the function __bfq_entity_update_weight_prio(),
to perform pending updates of ioprio, weight and ioprio class for the
bfq_queue. BFQ also invokes this function on I/O-request dispatches,
to raise or lower weights more quickly when needed, thereby improving
latency. However, the entity representing the bfq_queue may be on the
active (sub)tree of a service tree when this happens, and, although
with a very low probability, the bfq_queue may happen to also have a
pending change of its ioprio class. If both conditions hold when
__bfq_entity_update_weight_prio() is invoked, then the entity moves to
a sort of hybrid state: the new service tree for the entity, as
returned by bfq_entity_service_tree(), differs from service tree on
which the entity still is. The functions that handle activations and
deactivations of entities do not cope with such a hybrid state (and
would need to become more complex to cope).
This commit addresses this issue by just making
__bfq_entity_update_weight_prio() not perform also a possible pending
change of ioprio class, when invoked on an I/O-request dispatch for a
bfq_queue. Such a change is thus postponed to when
__bfq_entity_update_weight_prio() is invoked on deactivation or
re-scheduling of the bfq_queue.
Reported-by: Marco Piazza <mpiazza@gmail.com>
Reported-by: Laurentiu Nicola <lnicola@dend.ro>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-07-03 16:00:10 +08:00
|
|
|
struct bfq_entity *entity,
|
|
|
|
bool update_class_too);
|
2017-04-19 22:48:24 +08:00
|
|
|
void bfq_bfqq_served(struct bfq_queue *bfqq, int served);
|
|
|
|
void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
|
|
|
|
unsigned long time_ms);
|
|
|
|
bool __bfq_deactivate_entity(struct bfq_entity *entity,
|
|
|
|
bool ins_into_idle_tree);
|
|
|
|
bool next_queue_may_preempt(struct bfq_data *bfqd);
|
|
|
|
struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd);
|
|
|
|
void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
|
|
|
|
void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
|
|
|
|
bool ins_into_idle_tree, bool expiration);
|
|
|
|
void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
|
block, bfq: make lookup_next_entity push up vtime on expirations
To provide a very smooth service, bfq starts to serve a bfq_queue
only if the queue is 'eligible', i.e., if the same queue would
have started to be served in the ideal, perfectly fair system that
bfq simulates internally. This is obtained by associating each
queue with a virtual start time, and by computing a special system
virtual time quantity: a queue is eligible only if the system
virtual time has reached the virtual start time of the
queue. Finally, bfq guarantees that, when a new queue must be set
in service, there is always at least one eligible entity for each
active parent entity in the scheduler. To provide this guarantee,
the function __bfq_lookup_next_entity pushes up, for each parent
entity on which it is invoked, the system virtual time to the
minimum among the virtual start times of the entities in the
active tree for the parent entity (more precisely, the push up
occurs if the system virtual time happens to be lower than all
such virtual start times).
There is however a circumstance in which __bfq_lookup_next_entity
cannot push up the system virtual time for a parent entity, even
if the system virtual time is lower than the virtual start times
of all the child entities in the active tree. It happens if one of
the child entities is in service. In fact, in such a case, there
is already an eligible entity, the in-service one, even if it may
not be not present in the active tree (because in-service entities
may be removed from the active tree).
Unfortunately, in the last re-design of the
hierarchical-scheduling engine, the reset of the pointer to the
in-service entity for a given parent entity--reset to be done as a
consequence of the expiration of the in-service entity--always
happens after the function __bfq_lookup_next_entity has been
invoked. This causes the function to think that there is still an
entity in service for the parent entity, and then that the system
virtual time cannot be pushed up, even if actually such a
no-more-in-service entity has already been properly reinserted
into the active tree (or in some other tree if no more
active). Yet, the system virtual time *had* to be pushed up, to be
ready to correctly choose the next queue to serve. Because of the
lack of this push up, bfq may wrongly set in service a queue that
had been speculatively pre-computed as the possible
next-in-service queue, but that would no more be the one to serve
after the expiration and the reinsertion into the active trees of
the previously in-service entities.
This commit addresses this issue by making
__bfq_lookup_next_entity properly push up the system virtual time
if an expiration is occurring.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-08-31 14:46:29 +08:00
|
|
|
void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
|
|
|
|
bool expiration);
|
2017-04-19 22:48:24 +08:00
|
|
|
void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
|
|
|
|
bool expiration);
|
|
|
|
void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
|
|
|
|
|
|
|
|
/* --------------- end of interface of B-WF2Q+ ---------------- */
|
|
|
|
|
|
|
|
/* Logging facilities. */
|
|
|
|
#ifdef CONFIG_BFQ_GROUP_IOSCHED
|
|
|
|
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
|
|
|
|
|
|
|
|
#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \
|
2017-07-13 02:49:56 +08:00
|
|
|
blk_add_cgroup_trace_msg((bfqd)->queue, \
|
|
|
|
bfqg_to_blkg(bfqq_group(bfqq))->blkcg, \
|
|
|
|
"bfq%d%c " fmt, (bfqq)->pid, \
|
|
|
|
bfq_bfqq_sync((bfqq)) ? 'S' : 'A', ##args); \
|
2017-04-19 22:48:24 +08:00
|
|
|
} while (0)
|
|
|
|
|
2017-07-13 02:49:56 +08:00
|
|
|
#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \
|
|
|
|
blk_add_cgroup_trace_msg((bfqd)->queue, \
|
|
|
|
bfqg_to_blkg(bfqg)->blkcg, fmt, ##args); \
|
|
|
|
} while (0)
|
2017-04-19 22:48:24 +08:00
|
|
|
|
|
|
|
#else /* CONFIG_BFQ_GROUP_IOSCHED */
|
|
|
|
|
|
|
|
#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \
|
|
|
|
blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid, \
|
|
|
|
bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
|
|
|
|
##args)
|
|
|
|
#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0)
|
|
|
|
|
|
|
|
#endif /* CONFIG_BFQ_GROUP_IOSCHED */
|
|
|
|
|
|
|
|
#define bfq_log(bfqd, fmt, args...) \
|
|
|
|
blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
|
|
|
|
|
|
|
|
#endif /* _BFQ_H */
|