When bfq was merged into mainline, there were two I/O schedulers that implemented the proportional-share policy: bfq for blk-mq and cfq for legacy blk. bfq's interface files in the blkio/io controller have the same names as cfq. But the cgroups interface doesn't allow two entities to use the same name for their files, so for bfq we had to prepend the "bfq" prefix to each of its files. However no legacy code uses these modified file names. This naming also causes confusion, as, e.g., in [1]. Now cfq has gone with legacy blk, so there is no need any longer for these prefixes in (the never used) bfq names. Yet some people may have started to use the current bfq interface. So, as suggested by Tejun Heo [2], make bfq present a double interface, one with the file names prepended with the "bfq" prefix, and the other one with no prefix. [1] https://github.com/systemd/systemd/issues/7057 [2] https://lkml.org/lkml/2019/9/18/736 Suggested-by: Tejun Heo <tj@xxxxxxxxxx> Signed-off-by: Paolo Valente <paolo.valente@xxxxxxxxxx> --- Documentation/block/bfq-iosched.rst | 40 +++-- block/bfq-cgroup.c | 258 ++++++++++++++-------------- 2 files changed, 153 insertions(+), 145 deletions(-) diff --git a/Documentation/block/bfq-iosched.rst b/Documentation/block/bfq-iosched.rst index 0d237d402860..8ecd37903391 100644 --- a/Documentation/block/bfq-iosched.rst +++ b/Documentation/block/bfq-iosched.rst @@ -536,12 +536,14 @@ process. To get proportional sharing of bandwidth with BFQ for a given device, BFQ must of course be the active scheduler for that device. -Within each group directory, the names of the files associated with -BFQ-specific cgroup parameters and stats begin with the "bfq." -prefix. So, with cgroups-v1 or cgroups-v2, the full prefix for -BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group -parameter to set the weight of a group with BFQ is blkio.bfq.weight -or io.bfq.weight. +The interface of the proportional-share policy implemented by BFQ +consists of a series of cgroup parameters. For legacy issues, each +parameter can be read or written, equivalently, through one of two +files: the first file has the same name as the parameter to +read/write, while the second file has that same name prepended by the +prefix "bfq.". For example, the two files by which to set/show the +weight of a group are blkio.weight and blkio.bfq.weight with +cgroups-v1, or io.weight and io.bfq.weight with cgroups-v2. As for cgroups-v1 (blkio controller), the exact set of stat files created, and kept up-to-date by bfq, depends on whether @@ -550,14 +552,15 @@ the stat files documented in Documentation/admin-guide/cgroup-v1/blkio-controller.rst. If, instead, CONFIG_BFQ_CGROUP_DEBUG is not set, then bfq creates only the files:: - blkio.bfq.io_service_bytes - blkio.bfq.io_service_bytes_recursive - blkio.bfq.io_serviced - blkio.bfq.io_serviced_recursive + blkio.io_service_bytes + blkio.io_service_bytes_recursive + blkio.io_serviced + blkio.io_serviced_recursive -The value of CONFIG_BFQ_CGROUP_DEBUG greatly influences the maximum -throughput sustainable with bfq, because updating the blkio.bfq.* -stats is rather costly, especially for some of the stats enabled by +(plus their counterparts with also the bfq prefix). The value of +CONFIG_BFQ_CGROUP_DEBUG greatly influences the maximum throughput +sustainable with BFQ, because updating the blkio.* stats is rather +costly, especially for some of the stats enabled by CONFIG_BFQ_CGROUP_DEBUG. Parameters to set @@ -565,11 +568,12 @@ Parameters to set For each group, there is only the following parameter to set. -weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the -group inside its parent. Available values: 1..10000 (default 100). The -linear mapping between ioprio and weights, described at the beginning -of the tunable section, is still valid, but all weights higher than -IOPRIO_BE_NR*10 are mapped to ioprio 0. +weight (namely blkio.weight/blkio.bfq.weight or +io.weight/io.bfq.weight): the weight of the group inside its +parent. Available values: 1..10000 (default 100). The linear mapping +between ioprio and weights, described at the beginning of the tunable +section, is still valid, but all weights higher than IOPRIO_BE_NR*10 +are mapped to ioprio 0. Recall that, if low-latency is set, then BFQ automatically raises the weight of the queues associated with interactive and soft real-time diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index decda96770f4..d3b59b731992 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -1211,139 +1211,143 @@ struct blkcg_policy blkcg_policy_bfq = { .pd_reset_stats_fn = bfq_pd_reset_stats, }; -struct cftype bfq_blkcg_legacy_files[] = { - { - .name = "bfq.weight", - .flags = CFTYPE_NOT_ON_ROOT, - .seq_show = bfq_io_show_weight_legacy, - .write_u64 = bfq_io_set_weight_legacy, - }, - { - .name = "bfq.weight_device", - .flags = CFTYPE_NOT_ON_ROOT, - .seq_show = bfq_io_show_weight, - .write = bfq_io_set_weight, - }, - - /* statistics, covers only the tasks in the bfqg */ - { - .name = "bfq.io_service_bytes", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_bytes, - }, - { - .name = "bfq.io_serviced", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_ios, - }, -#ifdef CONFIG_BFQ_CGROUP_DEBUG - { - .name = "bfq.time", - .private = offsetof(struct bfq_group, stats.time), - .seq_show = bfqg_print_stat, - }, - { - .name = "bfq.sectors", - .seq_show = bfqg_print_stat_sectors, - }, - { - .name = "bfq.io_service_time", - .private = offsetof(struct bfq_group, stats.service_time), - .seq_show = bfqg_print_rwstat, - }, - { - .name = "bfq.io_wait_time", - .private = offsetof(struct bfq_group, stats.wait_time), - .seq_show = bfqg_print_rwstat, - }, - { - .name = "bfq.io_merged", - .private = offsetof(struct bfq_group, stats.merged), - .seq_show = bfqg_print_rwstat, - }, - { - .name = "bfq.io_queued", - .private = offsetof(struct bfq_group, stats.queued), - .seq_show = bfqg_print_rwstat, - }, -#endif /* CONFIG_BFQ_CGROUP_DEBUG */ +#define bfq_make_blkcg_legacy_files(prefix) \ + { \ + .name = #prefix "weight", \ + .flags = CFTYPE_NOT_ON_ROOT, \ + .seq_show = bfq_io_show_weight, \ + .write_u64 = bfq_io_set_weight_legacy, \ + }, \ + \ + /* statistics, covers only the tasks in the bfqg */ \ + { \ + .name = #prefix "io_service_bytes", \ + .private = (unsigned long)&blkcg_policy_bfq, \ + .seq_show = blkg_print_stat_bytes, \ + }, \ + { \ + .name = #prefix "io_serviced", \ + .private = (unsigned long)&blkcg_policy_bfq, \ + .seq_show = blkg_print_stat_ios, \ + }, \ + \ + /* the same statistics which cover the bfqg and its descendants */ \ + { \ + .name = #prefix "io_service_bytes_recursive", \ + .private = (unsigned long)&blkcg_policy_bfq, \ + .seq_show = blkg_print_stat_bytes_recursive, \ + }, \ + { \ + .name = #prefix "io_serviced_recursive", \ + .private = (unsigned long)&blkcg_policy_bfq, \ + .seq_show = blkg_print_stat_ios_recursive, \ + } + +#define bfq_make_blkcg_legacy_debug_files(prefix) \ + { \ + .name = #prefix "time", \ + .private = offsetof(struct bfq_group, stats.time), \ + .seq_show = bfqg_print_stat, \ + }, \ + { \ + .name = #prefix "sectors", \ + .seq_show = bfqg_print_stat_sectors, \ + }, \ + { \ + .name = #prefix "io_service_time", \ + .private = offsetof(struct bfq_group, stats.service_time), \ + .seq_show = bfqg_print_rwstat, \ + }, \ + { \ + .name = #prefix "io_wait_time", \ + .private = offsetof(struct bfq_group, stats.wait_time), \ + .seq_show = bfqg_print_rwstat, \ + }, \ + { \ + .name = #prefix "io_merged", \ + .private = offsetof(struct bfq_group, stats.merged), \ + .seq_show = bfqg_print_rwstat, \ + }, \ + { \ + .name = #prefix "io_queued", \ + .private = offsetof(struct bfq_group, stats.queued), \ + .seq_show = bfqg_print_rwstat, \ + }, \ + { \ + .name = #prefix "time_recursive", \ + .private = offsetof(struct bfq_group, stats.time), \ + .seq_show = bfqg_print_stat_recursive, \ + }, \ + { \ + .name = #prefix "sectors_recursive", \ + .seq_show = bfqg_print_stat_sectors_recursive, \ + }, \ + { \ + .name = #prefix "io_service_time_recursive", \ + .private = offsetof(struct bfq_group, stats.service_time), \ + .seq_show = bfqg_print_rwstat_recursive, \ + }, \ + { \ + .name = #prefix "io_wait_time_recursive", \ + .private = offsetof(struct bfq_group, stats.wait_time), \ + .seq_show = bfqg_print_rwstat_recursive, \ + }, \ + { \ + .name = #prefix "io_merged_recursive", \ + .private = offsetof(struct bfq_group, stats.merged), \ + .seq_show = bfqg_print_rwstat_recursive, \ + }, \ + { \ + .name = #prefix "io_queued_recursive", \ + .private = offsetof(struct bfq_group, stats.queued), \ + .seq_show = bfqg_print_rwstat_recursive, \ + }, \ + { \ + .name = #prefix "avg_queue_size", \ + .seq_show = bfqg_print_avg_queue_size, \ + }, \ + { \ + .name = #prefix "group_wait_time", \ + .private = offsetof(struct bfq_group, stats.group_wait_time), \ + .seq_show = bfqg_print_stat, \ + }, \ + { \ + .name = #prefix "idle_time", \ + .private = offsetof(struct bfq_group, stats.idle_time), \ + .seq_show = bfqg_print_stat, \ + }, \ + { \ + .name = #prefix "empty_time", \ + .private = offsetof(struct bfq_group, stats.empty_time), \ + .seq_show = bfqg_print_stat, \ + }, \ + { \ + .name = #prefix "dequeue", \ + .private = offsetof(struct bfq_group, stats.dequeue), \ + .seq_show = bfqg_print_stat, \ + } - /* the same statistics which cover the bfqg and its descendants */ - { - .name = "bfq.io_service_bytes_recursive", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_bytes_recursive, - }, - { - .name = "bfq.io_serviced_recursive", - .private = (unsigned long)&blkcg_policy_bfq, - .seq_show = blkg_print_stat_ios_recursive, - }, +struct cftype bfq_blkcg_legacy_files[] = { + bfq_make_blkcg_legacy_files(bfq.), + bfq_make_blkcg_legacy_files(), #ifdef CONFIG_BFQ_CGROUP_DEBUG - { - .name = "bfq.time_recursive", - .private = offsetof(struct bfq_group, stats.time), - .seq_show = bfqg_print_stat_recursive, - }, - { - .name = "bfq.sectors_recursive", - .seq_show = bfqg_print_stat_sectors_recursive, - }, - { - .name = "bfq.io_service_time_recursive", - .private = offsetof(struct bfq_group, stats.service_time), - .seq_show = bfqg_print_rwstat_recursive, - }, - { - .name = "bfq.io_wait_time_recursive", - .private = offsetof(struct bfq_group, stats.wait_time), - .seq_show = bfqg_print_rwstat_recursive, - }, - { - .name = "bfq.io_merged_recursive", - .private = offsetof(struct bfq_group, stats.merged), - .seq_show = bfqg_print_rwstat_recursive, - }, - { - .name = "bfq.io_queued_recursive", - .private = offsetof(struct bfq_group, stats.queued), - .seq_show = bfqg_print_rwstat_recursive, - }, - { - .name = "bfq.avg_queue_size", - .seq_show = bfqg_print_avg_queue_size, - }, - { - .name = "bfq.group_wait_time", - .private = offsetof(struct bfq_group, stats.group_wait_time), - .seq_show = bfqg_print_stat, - }, - { - .name = "bfq.idle_time", - .private = offsetof(struct bfq_group, stats.idle_time), - .seq_show = bfqg_print_stat, - }, - { - .name = "bfq.empty_time", - .private = offsetof(struct bfq_group, stats.empty_time), - .seq_show = bfqg_print_stat, - }, - { - .name = "bfq.dequeue", - .private = offsetof(struct bfq_group, stats.dequeue), - .seq_show = bfqg_print_stat, - }, -#endif /* CONFIG_BFQ_CGROUP_DEBUG */ + bfq_make_blkcg_legacy_debug_files(bfq.), + bfq_make_blkcg_legacy_debug_files(), +#endif { } /* terminate */ }; +#define bfq_make_blkg_files(prefix) \ + { \ + .name = #prefix "weight", \ + .flags = CFTYPE_NOT_ON_ROOT, \ + .seq_show = bfq_io_show_weight, \ + .write = bfq_io_set_weight, \ + } + struct cftype bfq_blkg_files[] = { - { - .name = "bfq.weight", - .flags = CFTYPE_NOT_ON_ROOT, - .seq_show = bfq_io_show_weight, - .write = bfq_io_set_weight, - }, + bfq_make_blkg_files(bfq.), + bfq_make_blkg_files(), {} /* terminate */ }; -- 2.20.1
