Kernel parameter of `isolcpus=` or 'nohz_full=' are used to isolate CPUs
for specific task, and it isn't expected to let block IO disturb these CPUs.
blk-mq kworker shouldn't be scheduled on isolated CPUs. Also if isolated
CPUs is run for blk-mq kworker, long block IO latency can be caused.
Kernel workqueue only respects CPU isolation for WQ_UNBOUND, for bound
WQ, the responsibility is on user because CPU is specified as WQ API
parameter, such as mod_delayed_work_on(cpu), queue_delayed_work_on(cpu)
and queue_work_on(cpu).
So not run blk-mq kworker on isolated CPUs by removing isolated CPUs
from hctx->cpumask. Meantime use queue map to check if all CPUs in this
hw queue are offline instead of hctx->cpumask, this way can avoid any
cost in fast IO code path, and is safe since hctx->cpumask are only
used in the two cases.
Cc: Tim Chen <[email protected]>
Cc: Juri Lelli <[email protected]>
Cc: Andrew Theurer <[email protected]>
Cc: Joe Mario <[email protected]>
Cc: Sebastian Jug <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Bart Van Assche <[email protected]>
Cc: Tejun Heo <[email protected]>
Tesed-by: Joe Mario <[email protected]>
Signed-off-by: Ming Lei <[email protected]>
---
V5:
- fix comment
- add one helper for document benefit
- all are suggested by Jens
V4:
- improve comment & commit log as suggested by Tim
V3:
- avoid to check invalid cpu as reported by Bart
- take current cpu(to be offline, not done yet) into account
- simplify blk_mq_hctx_has_online_cpu()
V2:
- remove module parameter, meantime use queue map to check if
all cpus in one hctx are offline
block/blk-mq.c | 57 +++++++++++++++++++++++++++++++++++++++++---------
1 file changed, 47 insertions(+), 10 deletions(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 555ada922cf0..06cd9c8068fc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -28,6 +28,7 @@
#include <linux/prefetch.h>
#include <linux/blk-crypto.h>
#include <linux/part_stat.h>
+#include <linux/sched/isolation.h>
#include <trace/events/block.h>
@@ -2168,6 +2169,15 @@ static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
return cpu;
}
+/*
+ * ->next_cpu is always calculated from hctx->cpumask, so simply use
+ * it for speeding up the check
+ */
+static bool blk_mq_hctx_empty_cpumask(struct blk_mq_hw_ctx *hctx)
+{
+ return hctx->next_cpu >= nr_cpu_ids;
+}
+
/*
* It'd be great if the workqueue API had a way to pass
* in a mask and had some smarts for more clever placement.
@@ -2179,7 +2189,8 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
bool tried = false;
int next_cpu = hctx->next_cpu;
- if (hctx->queue->nr_hw_queues == 1)
+ /* Switch to unbound if no allowable CPUs in this hctx */
+ if (hctx->queue->nr_hw_queues == 1 || blk_mq_hctx_empty_cpumask(hctx))
return WORK_CPU_UNBOUND;
if (--hctx->next_cpu_batch <= 0) {
@@ -3488,14 +3499,30 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
return data.has_rq;
}
-static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu,
- struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
+ unsigned int this_cpu)
{
- if (cpumask_first_and(hctx->cpumask, cpu_online_mask) != cpu)
- return false;
- if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids)
- return false;
- return true;
+ enum hctx_type type = hctx->type;
+ int cpu;
+
+ /*
+ * hctx->cpumask has to rule out isolated CPUs, but userspace still
+ * might submit IOs on these isolated CPUs, so use the queue map to
+ * check if all CPUs mapped to this hctx are offline
+ */
+ for_each_online_cpu(cpu) {
+ struct blk_mq_hw_ctx *h = blk_mq_map_queue_type(hctx->queue,
+ type, cpu);
+
+ if (h != hctx)
+ continue;
+
+ /* this hctx has at least one online CPU */
+ if (this_cpu != cpu)
+ return true;
+ }
+
+ return false;
}
static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
@@ -3503,8 +3530,7 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
struct blk_mq_hw_ctx, cpuhp_online);
- if (!cpumask_test_cpu(cpu, hctx->cpumask) ||
- !blk_mq_last_cpu_in_hctx(cpu, hctx))
+ if (blk_mq_hctx_has_online_cpu(hctx, cpu))
return 0;
/*
@@ -3912,6 +3938,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
}
queue_for_each_hw_ctx(q, hctx, i) {
+ int cpu;
+
/*
* If no software queues are mapped to this hardware queue,
* disable it and free the request entries.
@@ -3938,6 +3966,15 @@ static void blk_mq_map_swqueue(struct request_queue *q)
*/
sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx);
+ /*
+ * Rule out isolated CPUs from hctx->cpumask to avoid
+ * running block kworker on isolated CPUs
+ */
+ for_each_cpu(cpu, hctx->cpumask) {
+ if (cpu_is_isolated(cpu))
+ cpumask_clear_cpu(cpu, hctx->cpumask);
+ }
+
/*
* Initialize batch roundrobin counts
*/
--
2.41.0
On Thu, Mar 21, 2024 at 10:13 PM Ming Lei <[email protected]> wrote:
>
> Kernel parameter of `isolcpus=` or 'nohz_full=' are used to isolate CPUs
> for specific task, and it isn't expected to let block IO disturb these CPUs.
> blk-mq kworker shouldn't be scheduled on isolated CPUs. Also if isolated
> CPUs is run for blk-mq kworker, long block IO latency can be caused.
>
> Kernel workqueue only respects CPU isolation for WQ_UNBOUND, for bound
> WQ, the responsibility is on user because CPU is specified as WQ API
> parameter, such as mod_delayed_work_on(cpu), queue_delayed_work_on(cpu)
> and queue_work_on(cpu).
>
> So not run blk-mq kworker on isolated CPUs by removing isolated CPUs
> from hctx->cpumask. Meantime use queue map to check if all CPUs in this
> hw queue are offline instead of hctx->cpumask, this way can avoid any
> cost in fast IO code path, and is safe since hctx->cpumask are only
> used in the two cases.
>
> Cc: Tim Chen <[email protected]>
> Cc: Juri Lelli <[email protected]>
> Cc: Andrew Theurer <[email protected]>
> Cc: Joe Mario <[email protected]>
> Cc: Sebastian Jug <[email protected]>
> Cc: Frederic Weisbecker <[email protected]>
> Cc: Bart Van Assche <[email protected]>
> Cc: Tejun Heo <[email protected]>
> Tesed-by: Joe Mario <[email protected]>
> Signed-off-by: Ming Lei <[email protected]>
> ---
> V5:
> - fix comment
> - add one helper for document benefit
> - all are suggested by Jens
> V4:
> - improve comment & commit log as suggested by Tim
> V3:
> - avoid to check invalid cpu as reported by Bart
> - take current cpu(to be offline, not done yet) into account
> - simplify blk_mq_hctx_has_online_cpu()
>
> V2:
> - remove module parameter, meantime use queue map to check if
> all cpus in one hctx are offline
>
>
> block/blk-mq.c | 57 +++++++++++++++++++++++++++++++++++++++++---------
> 1 file changed, 47 insertions(+), 10 deletions(-)
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index 555ada922cf0..06cd9c8068fc 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -28,6 +28,7 @@
> #include <linux/prefetch.h>
> #include <linux/blk-crypto.h>
> #include <linux/part_stat.h>
> +#include <linux/sched/isolation.h>
>
> #include <trace/events/block.h>
>
> @@ -2168,6 +2169,15 @@ static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
> return cpu;
> }
>
> +/*
> + * ->next_cpu is always calculated from hctx->cpumask, so simply use
> + * it for speeding up the check
> + */
> +static bool blk_mq_hctx_empty_cpumask(struct blk_mq_hw_ctx *hctx)
> +{
> + return hctx->next_cpu >= nr_cpu_ids;
> +}
> +
> /*
> * It'd be great if the workqueue API had a way to pass
> * in a mask and had some smarts for more clever placement.
> @@ -2179,7 +2189,8 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
> bool tried = false;
> int next_cpu = hctx->next_cpu;
>
> - if (hctx->queue->nr_hw_queues == 1)
> + /* Switch to unbound if no allowable CPUs in this hctx */
> + if (hctx->queue->nr_hw_queues == 1 || blk_mq_hctx_empty_cpumask(hctx))
> return WORK_CPU_UNBOUND;
>
> if (--hctx->next_cpu_batch <= 0) {
> @@ -3488,14 +3499,30 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
> return data.has_rq;
> }
>
> -static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu,
> - struct blk_mq_hw_ctx *hctx)
> +static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
> + unsigned int this_cpu)
> {
> - if (cpumask_first_and(hctx->cpumask, cpu_online_mask) != cpu)
> - return false;
> - if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids)
> - return false;
> - return true;
> + enum hctx_type type = hctx->type;
> + int cpu;
> +
> + /*
> + * hctx->cpumask has to rule out isolated CPUs, but userspace still
> + * might submit IOs on these isolated CPUs, so use the queue map to
> + * check if all CPUs mapped to this hctx are offline
> + */
> + for_each_online_cpu(cpu) {
> + struct blk_mq_hw_ctx *h = blk_mq_map_queue_type(hctx->queue,
> + type, cpu);
> +
> + if (h != hctx)
> + continue;
> +
> + /* this hctx has at least one online CPU */
> + if (this_cpu != cpu)
> + return true;
> + }
> +
> + return false;
> }
>
> static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
> @@ -3503,8 +3530,7 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
> struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
> struct blk_mq_hw_ctx, cpuhp_online);
>
> - if (!cpumask_test_cpu(cpu, hctx->cpumask) ||
> - !blk_mq_last_cpu_in_hctx(cpu, hctx))
> + if (blk_mq_hctx_has_online_cpu(hctx, cpu))
> return 0;
>
> /*
> @@ -3912,6 +3938,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
> }
>
> queue_for_each_hw_ctx(q, hctx, i) {
> + int cpu;
> +
> /*
> * If no software queues are mapped to this hardware queue,
> * disable it and free the request entries.
> @@ -3938,6 +3966,15 @@ static void blk_mq_map_swqueue(struct request_queue *q)
> */
> sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx);
>
> + /*
> + * Rule out isolated CPUs from hctx->cpumask to avoid
> + * running block kworker on isolated CPUs
> + */
> + for_each_cpu(cpu, hctx->cpumask) {
> + if (cpu_is_isolated(cpu))
> + cpumask_clear_cpu(cpu, hctx->cpumask);
> + }
> +
> /*
> * Initialize batch roundrobin counts
> */
> --
> 2.41.0
>
>
Reviewed-by: Ewan D. Milne <[email protected]>
On Fri, 22 Mar 2024 10:12:44 +0800, Ming Lei wrote:
> Kernel parameter of `isolcpus=` or 'nohz_full=' are used to isolate CPUs
> for specific task, and it isn't expected to let block IO disturb these CPUs.
> blk-mq kworker shouldn't be scheduled on isolated CPUs. Also if isolated
> CPUs is run for blk-mq kworker, long block IO latency can be caused.
>
> Kernel workqueue only respects CPU isolation for WQ_UNBOUND, for bound
> WQ, the responsibility is on user because CPU is specified as WQ API
> parameter, such as mod_delayed_work_on(cpu), queue_delayed_work_on(cpu)
> and queue_work_on(cpu).
>
> [...]
Applied, thanks!
[1/1] blk-mq: don't schedule block kworker on isolated CPUs
commit: 5f27f3d892743312fce237958a4194859ef93d69
Best regards,
--
Jens Axboe