summaryrefslogtreecommitdiffstats
path: root/include/trace/events/iocost.h
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2019-08-29 00:05:58 +0200
committerJens Axboe <axboe@kernel.dk>2019-08-29 05:17:12 +0200
commit7caa47151ab2e644dd221f741ec7578d9532c9a3 (patch)
treef5ffe39d84924c03fb72f927ab420e3ca6a629ec /include/trace/events/iocost.h
parentblk-mq: add optional request->alloc_time_ns (diff)
downloadlinux-7caa47151ab2e644dd221f741ec7578d9532c9a3.tar.xz
linux-7caa47151ab2e644dd221f741ec7578d9532c9a3.zip
blkcg: implement blk-iocost
This patchset implements IO cost model based work-conserving proportional controller. While io.latency provides the capability to comprehensively prioritize and protect IOs depending on the cgroups, its protection is binary - the lowest latency target cgroup which is suffering is protected at the cost of all others. In many use cases including stacking multiple workload containers in a single system, it's necessary to distribute IO capacity with better granularity. One challenge of controlling IO resources is the lack of trivially observable cost metric. The most common metrics - bandwidth and iops - can be off by orders of magnitude depending on the device type and IO pattern. However, the cost isn't a complete mystery. Given several key attributes, we can make fairly reliable predictions on how expensive a given stream of IOs would be, at least compared to other IO patterns. The function which determines the cost of a given IO is the IO cost model for the device. This controller distributes IO capacity based on the costs estimated by such model. The more accurate the cost model the better but the controller adapts based on IO completion latency and as long as the relative costs across differents IO patterns are consistent and sensible, it'll adapt to the actual performance of the device. Currently, the only implemented cost model is a simple linear one with a few sets of default parameters for different classes of device. This covers most common devices reasonably well. All the infrastructure to tune and add different cost models is already in place and a later patch will also allow using bpf progs for cost models. Please see the top comment in blk-iocost.c and documentation for more details. v2: Rebased on top of RQ_ALLOC_TIME changes and folded in Rik's fix for a divide-by-zero bug in current_hweight() triggered by zero inuse_sum. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Andy Newell <newella@fb.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Rik van Riel <riel@surriel.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'include/trace/events/iocost.h')
-rw-r--r--include/trace/events/iocost.h174
1 files changed, 174 insertions, 0 deletions
diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
new file mode 100644
index 000000000000..ec2217dd57ac
--- /dev/null
+++ b/include/trace/events/iocost.h
@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM iocost
+
+#if !defined(_TRACE_BLK_IOCOST_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BLK_IOCOST_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(iocost_iocg_activate,
+
+ TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+ u64 last_period, u64 cur_period, u64 vtime),
+
+ TP_ARGS(iocg, path, now, last_period, cur_period, vtime),
+
+ TP_STRUCT__entry (
+ __string(devname, ioc_name(iocg->ioc))
+ __string(cgroup, path)
+ __field(u64, now)
+ __field(u64, vnow)
+ __field(u64, vrate)
+ __field(u64, last_period)
+ __field(u64, cur_period)
+ __field(u64, last_vtime)
+ __field(u64, vtime)
+ __field(u32, weight)
+ __field(u32, inuse)
+ __field(u64, hweight_active)
+ __field(u64, hweight_inuse)
+ ),
+
+ TP_fast_assign(
+ __assign_str(devname, ioc_name(iocg->ioc));
+ __assign_str(cgroup, path);
+ __entry->now = now->now;
+ __entry->vnow = now->vnow;
+ __entry->vrate = now->vrate;
+ __entry->last_period = last_period;
+ __entry->cur_period = cur_period;
+ __entry->last_vtime = iocg->last_vtime;
+ __entry->vtime = vtime;
+ __entry->weight = iocg->weight;
+ __entry->inuse = iocg->inuse;
+ __entry->hweight_active = iocg->hweight_active;
+ __entry->hweight_inuse = iocg->hweight_inuse;
+ ),
+
+ TP_printk("[%s:%s] now=%llu:%llu vrate=%llu "
+ "period=%llu->%llu vtime=%llu->%llu "
+ "weight=%u/%u hweight=%llu/%llu",
+ __get_str(devname), __get_str(cgroup),
+ __entry->now, __entry->vnow, __entry->vrate,
+ __entry->last_period, __entry->cur_period,
+ __entry->last_vtime, __entry->vtime,
+ __entry->inuse, __entry->weight,
+ __entry->hweight_inuse, __entry->hweight_active
+ )
+);
+
+DECLARE_EVENT_CLASS(iocg_inuse_update,
+
+ TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+ u32 old_inuse, u32 new_inuse,
+ u64 old_hw_inuse, u64 new_hw_inuse),
+
+ TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+ old_hw_inuse, new_hw_inuse),
+
+ TP_STRUCT__entry (
+ __string(devname, ioc_name(iocg->ioc))
+ __string(cgroup, path)
+ __field(u64, now)
+ __field(u32, old_inuse)
+ __field(u32, new_inuse)
+ __field(u64, old_hweight_inuse)
+ __field(u64, new_hweight_inuse)
+ ),
+
+ TP_fast_assign(
+ __assign_str(devname, ioc_name(iocg->ioc));
+ __assign_str(cgroup, path);
+ __entry->now = now->now;
+ __entry->old_inuse = old_inuse;
+ __entry->new_inuse = new_inuse;
+ __entry->old_hweight_inuse = old_hw_inuse;
+ __entry->new_hweight_inuse = new_hw_inuse;
+ ),
+
+ TP_printk("[%s:%s] now=%llu inuse=%u->%u hw_inuse=%llu->%llu",
+ __get_str(devname), __get_str(cgroup), __entry->now,
+ __entry->old_inuse, __entry->new_inuse,
+ __entry->old_hweight_inuse, __entry->new_hweight_inuse
+ )
+);
+
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_takeback,
+
+ TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+ u32 old_inuse, u32 new_inuse,
+ u64 old_hw_inuse, u64 new_hw_inuse),
+
+ TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+ old_hw_inuse, new_hw_inuse)
+);
+
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_giveaway,
+
+ TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+ u32 old_inuse, u32 new_inuse,
+ u64 old_hw_inuse, u64 new_hw_inuse),
+
+ TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+ old_hw_inuse, new_hw_inuse)
+);
+
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset,
+
+ TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+ u32 old_inuse, u32 new_inuse,
+ u64 old_hw_inuse, u64 new_hw_inuse),
+
+ TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+ old_hw_inuse, new_hw_inuse)
+);
+
+TRACE_EVENT(iocost_ioc_vrate_adj,
+
+ TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 (*missed_ppm)[2],
+ u32 rq_wait_pct, int nr_lagging, int nr_shortages,
+ int nr_surpluses),
+
+ TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages,
+ nr_surpluses),
+
+ TP_STRUCT__entry (
+ __string(devname, ioc_name(ioc))
+ __field(u64, old_vrate)
+ __field(u64, new_vrate)
+ __field(int, busy_level)
+ __field(u32, read_missed_ppm)
+ __field(u32, write_missed_ppm)
+ __field(u32, rq_wait_pct)
+ __field(int, nr_lagging)
+ __field(int, nr_shortages)
+ __field(int, nr_surpluses)
+ ),
+
+ TP_fast_assign(
+ __assign_str(devname, ioc_name(ioc));
+ __entry->old_vrate = atomic64_read(&ioc->vtime_rate);;
+ __entry->new_vrate = new_vrate;
+ __entry->busy_level = ioc->busy_level;
+ __entry->read_missed_ppm = (*missed_ppm)[READ];
+ __entry->write_missed_ppm = (*missed_ppm)[WRITE];
+ __entry->rq_wait_pct = rq_wait_pct;
+ __entry->nr_lagging = nr_lagging;
+ __entry->nr_shortages = nr_shortages;
+ __entry->nr_surpluses = nr_surpluses;
+ ),
+
+ TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d surpluses=%d",
+ __get_str(devname), __entry->old_vrate, __entry->new_vrate,
+ __entry->busy_level,
+ __entry->read_missed_ppm, __entry->write_missed_ppm,
+ __entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages,
+ __entry->nr_surpluses
+ )
+);
+
+#endif /* _TRACE_BLK_IOCOST_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>