Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 | #ifndef _BLK_CGROUP_H #define _BLK_CGROUP_H /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> */ #include <linux/cgroup.h> enum blkio_policy_id { BLKIO_POLICY_PROP = 0, /* Proportional Bandwidth division */ BLKIO_POLICY_THROTL, /* Throttling */ }; /* Max limits for throttle policy */ #define THROTL_IOPS_MAX UINT_MAX #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) #ifndef CONFIG_BLK_CGROUP /* When blk-cgroup is a module, its subsys_id isn't a compile-time constant */ extern struct cgroup_subsys blkio_subsys; #define blkio_subsys_id blkio_subsys.subsys_id #endif enum stat_type { /* Total time spent (in ns) between request dispatch to the driver and * request completion for IOs doen by this cgroup. This may not be * accurate when NCQ is turned on. */ BLKIO_STAT_SERVICE_TIME = 0, /* Total bytes transferred */ BLKIO_STAT_SERVICE_BYTES, /* Total IOs serviced, post merge */ BLKIO_STAT_SERVICED, /* Total time spent waiting in scheduler queue in ns */ BLKIO_STAT_WAIT_TIME, /* Number of IOs merged */ BLKIO_STAT_MERGED, /* Number of IOs queued up */ BLKIO_STAT_QUEUED, /* All the single valued stats go below this */ BLKIO_STAT_TIME, BLKIO_STAT_SECTORS, /* Time not charged to this cgroup */ BLKIO_STAT_UNACCOUNTED_TIME, #ifdef CONFIG_DEBUG_BLK_CGROUP BLKIO_STAT_AVG_QUEUE_SIZE, BLKIO_STAT_IDLE_TIME, BLKIO_STAT_EMPTY_TIME, BLKIO_STAT_GROUP_WAIT_TIME, BLKIO_STAT_DEQUEUE #endif }; enum stat_sub_type { BLKIO_STAT_READ = 0, BLKIO_STAT_WRITE, BLKIO_STAT_SYNC, BLKIO_STAT_ASYNC, BLKIO_STAT_TOTAL }; /* blkg state flags */ enum blkg_state_flags { BLKG_waiting = 0, BLKG_idling, BLKG_empty, }; /* cgroup files owned by proportional weight policy */ enum blkcg_file_name_prop { BLKIO_PROP_weight = 1, BLKIO_PROP_weight_device, BLKIO_PROP_io_service_bytes, BLKIO_PROP_io_serviced, BLKIO_PROP_time, BLKIO_PROP_sectors, BLKIO_PROP_unaccounted_time, BLKIO_PROP_io_service_time, BLKIO_PROP_io_wait_time, BLKIO_PROP_io_merged, BLKIO_PROP_io_queued, BLKIO_PROP_avg_queue_size, BLKIO_PROP_group_wait_time, BLKIO_PROP_idle_time, BLKIO_PROP_empty_time, BLKIO_PROP_dequeue, }; /* cgroup files owned by throttle policy */ enum blkcg_file_name_throtl { BLKIO_THROTL_read_bps_device, BLKIO_THROTL_write_bps_device, BLKIO_THROTL_read_iops_device, BLKIO_THROTL_write_iops_device, BLKIO_THROTL_io_service_bytes, BLKIO_THROTL_io_serviced, }; struct blkio_cgroup { struct cgroup_subsys_state css; unsigned int weight; spinlock_t lock; struct hlist_head blkg_list; struct list_head policy_list; /* list of blkio_policy_node */ }; struct blkio_group_stats { /* total disk time and nr sectors dispatched by this group */ uint64_t time; uint64_t sectors; /* Time not charged to this cgroup */ uint64_t unaccounted_time; uint64_t stat_arr[BLKIO_STAT_QUEUED + 1][BLKIO_STAT_TOTAL]; #ifdef CONFIG_DEBUG_BLK_CGROUP /* Sum of number of IOs queued across all samples */ uint64_t avg_queue_size_sum; /* Count of samples taken for average */ uint64_t avg_queue_size_samples; /* How many times this group has been removed from service tree */ unsigned long dequeue; /* Total time spent waiting for it to be assigned a timeslice. */ uint64_t group_wait_time; uint64_t start_group_wait_time; /* Time spent idling for this blkio_group */ uint64_t idle_time; uint64_t start_idle_time; /* * Total time when we have requests queued and do not contain the * current active queue. */ uint64_t empty_time; uint64_t start_empty_time; uint16_t flags; #endif }; struct blkio_group { /* An rcu protected unique identifier for the group */ void *key; struct hlist_node blkcg_node; unsigned short blkcg_id; /* Store cgroup path */ char path[128]; /* The device MKDEV(major, minor), this group has been created for */ dev_t dev; /* policy which owns this blk group */ enum blkio_policy_id plid; /* Need to serialize the stats in the case of reset/update */ spinlock_t stats_lock; struct blkio_group_stats stats; }; struct blkio_policy_node { struct list_head node; dev_t dev; /* This node belongs to max bw policy or porportional weight policy */ enum blkio_policy_id plid; /* cgroup file to which this rule belongs to */ int fileid; union { unsigned int weight; /* * Rate read/write in terms of byptes per second * Whether this rate represents read or write is determined * by file type "fileid". */ u64 bps; unsigned int iops; } val; }; extern unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg, dev_t dev); extern uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg, dev_t dev); extern uint64_t blkcg_get_write_bps(struct blkio_cgroup *blkcg, dev_t dev); extern unsigned int blkcg_get_read_iops(struct blkio_cgroup *blkcg, dev_t dev); extern unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg, dev_t dev); typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg); typedef void (blkio_update_group_weight_fn) (void *key, struct blkio_group *blkg, unsigned int weight); typedef void (blkio_update_group_read_bps_fn) (void * key, struct blkio_group *blkg, u64 read_bps); typedef void (blkio_update_group_write_bps_fn) (void *key, struct blkio_group *blkg, u64 write_bps); typedef void (blkio_update_group_read_iops_fn) (void *key, struct blkio_group *blkg, unsigned int read_iops); typedef void (blkio_update_group_write_iops_fn) (void *key, struct blkio_group *blkg, unsigned int write_iops); struct blkio_policy_ops { blkio_unlink_group_fn *blkio_unlink_group_fn; blkio_update_group_weight_fn *blkio_update_group_weight_fn; blkio_update_group_read_bps_fn *blkio_update_group_read_bps_fn; blkio_update_group_write_bps_fn *blkio_update_group_write_bps_fn; blkio_update_group_read_iops_fn *blkio_update_group_read_iops_fn; blkio_update_group_write_iops_fn *blkio_update_group_write_iops_fn; }; struct blkio_policy_type { struct list_head list; struct blkio_policy_ops ops; enum blkio_policy_id plid; }; /* Blkio controller policy registration */ extern void blkio_policy_register(struct blkio_policy_type *); extern void blkio_policy_unregister(struct blkio_policy_type *); static inline char *blkg_path(struct blkio_group *blkg) { return blkg->path; } #else struct blkio_group { }; struct blkio_policy_type { }; static inline void blkio_policy_register(struct blkio_policy_type *blkiop) { } static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { } static inline char *blkg_path(struct blkio_group *blkg) { return NULL; } #endif #define BLKIO_WEIGHT_MIN 10 #define BLKIO_WEIGHT_MAX 1000 #define BLKIO_WEIGHT_DEFAULT 500 #ifdef CONFIG_DEBUG_BLK_CGROUP void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg); void blkiocg_update_dequeue_stats(struct blkio_group *blkg, unsigned long dequeue); void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg); void blkiocg_update_idle_time_stats(struct blkio_group *blkg); void blkiocg_set_start_empty_time(struct blkio_group *blkg); #define BLKG_FLAG_FNS(name) \ static inline void blkio_mark_blkg_##name( \ struct blkio_group_stats *stats) \ { \ stats->flags |= (1 << BLKG_##name); \ } \ static inline void blkio_clear_blkg_##name( \ struct blkio_group_stats *stats) \ { \ stats->flags &= ~(1 << BLKG_##name); \ } \ static inline int blkio_blkg_##name(struct blkio_group_stats *stats) \ { \ return (stats->flags & (1 << BLKG_##name)) != 0; \ } \ BLKG_FLAG_FNS(waiting) BLKG_FLAG_FNS(idling) BLKG_FLAG_FNS(empty) #undef BLKG_FLAG_FNS #else static inline void blkiocg_update_avg_queue_size_stats( struct blkio_group *blkg) {} static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg, unsigned long dequeue) {} static inline void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg) {} static inline void blkiocg_update_idle_time_stats(struct blkio_group *blkg) {} static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {} #endif #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) extern struct blkio_cgroup blkio_root_cgroup; extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup); extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, struct blkio_group *blkg, void *key, dev_t dev, enum blkio_policy_id plid); extern int blkiocg_del_blkio_group(struct blkio_group *blkg); extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key); void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time, unsigned long unaccounted_time); void blkiocg_update_dispatch_stats(struct blkio_group *blkg, uint64_t bytes, bool direction, bool sync); void blkiocg_update_completion_stats(struct blkio_group *blkg, uint64_t start_time, uint64_t io_start_time, bool direction, bool sync); void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction, bool sync); void blkiocg_update_io_add_stats(struct blkio_group *blkg, struct blkio_group *curr_blkg, bool direction, bool sync); void blkiocg_update_io_remove_stats(struct blkio_group *blkg, bool direction, bool sync); #else struct cgroup; static inline struct blkio_cgroup * cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; } static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, struct blkio_group *blkg, void *key, dev_t dev, enum blkio_policy_id plid) {} static inline int blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; } static inline struct blkio_group * blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; } static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time, unsigned long unaccounted_time) {} static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg, uint64_t bytes, bool direction, bool sync) {} static inline void blkiocg_update_completion_stats(struct blkio_group *blkg, uint64_t start_time, uint64_t io_start_time, bool direction, bool sync) {} static inline void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction, bool sync) {} static inline void blkiocg_update_io_add_stats(struct blkio_group *blkg, struct blkio_group *curr_blkg, bool direction, bool sync) {} static inline void blkiocg_update_io_remove_stats(struct blkio_group *blkg, bool direction, bool sync) {} #endif #endif /* _BLK_CGROUP_H */ |