sched/numa: Skip VMA scanning on memory pinned
v3 cover sched/numa: Skip VMA scanning on memory pinned
v1->v2:
1. add perf improvment numbers in commit log. Yet to find perf diff on will-it-scale, so not included here. Plan to run more workloads.
2. add tracepoint.
3. To peterz's comment, this will make it impossible to attract tasks to those memory just like other VMA skippings. This is the current implementation, I think we can improve that in the future, but at the moment it's probabaly better to keep it consistent.
v2->v3:
1. add enable_cpuset() based on Mel's suggestion but again I think it's redundant
2. print out nodemask with %*p.. format in the tracepoint
Libo Chen (2):
sched/numa: Skip VMA scanning on memory pinned to one NUMA node via
cpuset.mems
sched/numa: Add tracepoint that tracks the skipping of numa balancing
due to cpuset memory pinning
include/trace/events/sched.h | 30 ++++++++++++++++++++++++++++++ kernel/sched/fair.c | 9 +++++++++ 2 files changed, 39 insertions(+)
Signature · 1 line
2.43.5
PATCH v3 1/2 sched/numa: Skip VMA scanning on memory pinned to one NUMA node via cpuset.mems
When the memory of the current task is pinned to one NUMA node by cgroup, there is no point in continuing the rest of VMA scanning and hinting page faults as they will just be overhead. With this change, there will be no more unnecessary PTE updates or page faults in this scenario.
We have seen up to a 6x improvement on a typical java workload running on VMs with memory and CPU pinned to one NUMA node via cpuset in a two-socket AARCH64 system. With the same pinning, on a 18-cores-per-socket Intel platform, we have seen 20% improvment in a microbench that creates a 30-vCPU selftest KVM guest with 4GB memory, where each vCPU reads 4KB pages in a fixed number of loops.
--- kernel/sched/fair.c | 7 +++++++ 1 file changed, 7 insertions(+)
kernel/sched/fair.c +7 -0
@@ -3329,6 +3329,13 @@ static void task_numa_work(struct callback_head *work)if (p->flags &PF_EXITING )return ; +/* +* Memory is pinned to only one NUMA node via cpuset.mems, naturally +* no page can be migrated. +*/ +if (cpusets_enabled () &&nodes_weight (cpuset_current_mems_allowed) ==1 ) +return ; +if (!mm->numa_next_scan) { mm->numa_next_scan = now +msecs_to_jiffies (sysctl_numa_balancing_scan_delay);
Signature · 1 line
2.43.5
Re: [PATCH v3 1/2] sched/numa: Skip VMA scanning on memory pinned to one NUMA node via cpuset.mems
Hi Libo,
Quoted 5 lines · Libo Chen
When the memory of the current task is pinned to one NUMA node by cgroup, there is no point in continuing the rest of VMA scanning and hinting page faults as they will just be overhead. With this change, there will be no more unnecessary PTE updates or page faults in this scenario.
Quoted 8 lines
We have seen up to a 6x improvement on a typical java workload running on VMs with memory and CPU pinned to one NUMA node via cpuset in a two-socket AARCH64 system. With the same pinning, on a 18-cores-per-socket Intel platform, we have seen 20% improvment in a microbench that creates a 30-vCPU selftest KVM guest with 4GB memory, where each vCPU reads 4KB pages in a fixed number of loops.
Signed-off-by Libo Chen <[email protected]>
I think this is a promising change that we can perform fine-grain NUMA balance control on a per-cgroup basis rather than system-wide NUMA balance for every task, which is costly.
Quoted 9 lines
--- kernel/sched/fair.c | 7 +++++++ 1 file changed, 7 insertions(+)kernel/sched/fair.c +0
-0
kernel/sched/fair.c static void task_numa_work(struct callback_head *work) · line 3338
Quoted 10 lines
kernel/sched/fair.c +7
-0@@ -3329,6 +3329,13 @@ static void task_numa_work(struct callback_head *work)if (p->flags &PF_EXITING )return ; +/* +* Memory is pinned to only one NUMA node via cpuset.mems, naturally +* no page can be migrated. +*/ +if (cpusets_enabled () &&nodes_weight (cpuset_current_mems_allowed) ==1 ) +return ; +
I found that you had a proposal in V1 to address Peter's concern[1]:
Allow the task to be migrated to its preferred Node, even if the task's
memory policy is restricted to 1 Node. In your previous proposal, only if the task's cpumask is bound to the same Node as its memory policy node, the NUMA balance scanning is skipped, because a cgroup usually binds its tasks and memory allocation policy to the same node. Not sure if that could be turned into:
If the task's memory policy node's CPU mask is a subset of the task's cpumask, the NUMA balance scan is allowed.
For example,
Suppose p's memory is only allocated on node0, which contains CPU2, CPU3.
1. If p's CPU affinity is CPU0, CPU1, there is no need to do NUMA balancing scanning, because CPU0,1 are not in p's legitimate cpumask.
2. If p's CPU affinity is CPU3, there is no need to do NUMA balancing scanning. p is already on its preferred node.
3. But if p's CPU affinity is CPU2, CPU3, CPU6, the NUMA balancing scan should be allowed. Because it is possible to migrate p from CPU6 to either CPU2 or CPU3.
What I'm thinking of is something as follows(untested):
if (cpusets_enabled() &&
nodes_weight(cpuset_current_mems_allowed) == 1 &&
!cpumask_subset(cpumask_of_node(cpuset_current_mems_allowed),
p->cpus_ptr))
return;I tested your patch on top of the latest sched/core,
binding task CPU affinity to Node1 and memory allocation node on Node1:
echo "8-15" > /sys/fs/cgroup/mytest/cpuset.cpus
echo "1" > /sys/fs/cgroup/mytest/cpuset.mems
cgexec -g cpuset:mytest ./run-mmtests.sh --no-monitor --config config-numa skip_scan
And it works as expected:
# bpftrace numa_trace.bt
@sched_skip_cpuset_numa: 133
thanks,
Chenyu
Quoted 3 lines
kernel/sched/fair.c +0
-0if (!mm->numa_next_scan) { mm->numa_next_scan = now +msecs_to_jiffies (sysctl_numa_balancing_scan_delay);
Re: [PATCH v3 1/2] sched/numa: Skip VMA scanning on memory pinned to one NUMA node via cpuset.mems
Hi Yu
Quoted 15 lines · Yu C
Hi Libo,
Quoted 12 lines · Libo Chen
When the memory of the current task is pinned to one NUMA node by cgroup, there is no point in continuing the rest of VMA scanning and hinting page faults as they will just be overhead. With this change, there will be no more unnecessary PTE updates or page faults in this scenario.
We have seen up to a 6x improvement on a typical java workload running on VMs with memory and CPU pinned to one NUMA node via cpuset in a two-socket AARCH64 system. With the same pinning, on a 18-cores-per-socket Intel platform, we have seen 20% improvment in a microbench that creates a 30-vCPU selftest KVM guest with 4GB memory, where each vCPU reads 4KB pages in a fixed number of loops.
Quoted 6 lines
Quoted 1 line
Signed-off-by Libo Chen <[email protected]>I think this is a promising change that we can perform fine-grain NUMA balance control on a per-cgroup basis rather than system-wide NUMA balance for every task, which is costly.
Yes indeed, the cost, from we have seen, can be quite astonishing
Quoted 23 lines
Quoted 11 lines
---
kernel/sched/fair.c| 7 +++++++1 file changed, 7 insertions(+)kernel/sched/fair.c +0
-0@@ -3329,6 +3329,13 @@ static void task_numa_work(struct callback_head *work) if (p->flags & PF_EXITING) return;Quoted 7 lines
+ /*
+ * Memory is pinned to only one NUMA node via cpuset.mems, naturally + * no page can be migrated.
+ */
+ if (cpusets_enabled()&&nodes_weight(cpuset_current_mems_allowed)== 1) + return;
+I found that you had a proposal in V1 to address Peter's concern[1]:
Allow the task to be migrated to its preferred Node, even if the task's
memory policy is restricted to 1 Node. In your previous proposal, only if the task's cpumask is bound to the same Node as its memory policy node, the NUMA balance scanning is skipped, because a cgroup usually binds its tasks and memory allocation policy to the same node. Not sure if that could be turned into:
Quoted 2 lines
If the task's memory policy node's CPU mask is a subset of the task's cpumask, the NUMA balance scan is allowed.
I guess fundamentally is this really worth it? Do the benefits of NUMA task migrations only outweigh the overheads of VMA scanning, PTE updates and page faults etc? I suppose this is workload-dependent, but what about the best-case scenario? I think we probably need more data. Also if we do that, we also need to do the same for other VMA skipping scenarios.
Thanks,
Libo
Quoted 35 lines
For example,
Suppose p's memory is only allocated on node0, which contains CPU2, CPU3.
1. If p's CPU affinity is CPU0, CPU1, there is no need to do NUMA balancing scanning, because CPU0,1 are not in p's legitimate cpumask.
2. If p's CPU affinity is CPU3, there is no need to do NUMA balancing scanning. p is already on its preferred node.
3. But if p's CPU affinity is CPU2, CPU3, CPU6, the NUMA balancing scan should be allowed. Because it is possible to migrate p from CPU6 to either CPU2 or CPU3.What I'm thinking of is something as follows(untested):
if (cpusets_enabled()&&nodes_weight(cpuset_current_mems_allowed)== 1 && !cpumask_subset(cpumask_of_node(cpuset_current_mems_allowed),p->cpus_ptr))
return;I tested your patch on top of the latest sched/core,
binding task CPU affinity to Node1 and memory allocation node on Node1:
echo "8-15" >/sys/fs/cgroup/mytest/cpuset.cpus
echo "1" >/sys/fs/cgroup/mytest/cpuset.mems
cgexec -g cpuset:mytest ./run-mmtests.sh --no-monitor --config config-numaskip_scanAnd it works as expected:
# bpftrace numa_trace.bt@sched_skip_cpuset_numa: 133
thanks,
ChenyuQuoted 3 lines
if (!mm->numa_next_scan) {
mm->numa_next_scan= now +msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
Chen, Yu C
Tested-byRe: [PATCH v3 1/2] sched/numa: Skip VMA scanning on memory pinned to one NUMA node via cpuset.mems
Quoted 50 lines · Libo Chen
Hi Yu
Quoted 15 lines · Yu C
Hi Libo,
Quoted 12 lines · Libo Chen
When the memory of the current task is pinned to one NUMA node by cgroup, there is no point in continuing the rest of VMA scanning and hinting page faults as they will just be overhead. With this change, there will be no more unnecessary PTE updates or page faults in this scenario.
We have seen up to a 6x improvement on a typical java workload running on VMs with memory and CPU pinned to one NUMA node via cpuset in a two-socket AARCH64 system. With the same pinning, on a 18-cores-per-socket Intel platform, we have seen 20% improvment in a microbench that creates a 30-vCPU selftest KVM guest with 4GB memory, where each vCPU reads 4KB pages in a fixed number of loops.
Quoted 6 lines
Quoted 1 line
Signed-off-by Libo Chen <[email protected]>I think this is a promising change that we can perform fine-grain NUMA balance control on a per-cgroup basis rather than system-wide NUMA balance for every task, which is costly.
Yes indeed, the cost, from we have seen, can be quite astonishing
Quoted 23 lines
Quoted 9 lines
--- kernel/sched/fair.c | 7 +++++++ 1 file changed, 7 insertions(+)kernel/sched/fair.c +0
-0kernel/sched/fair.c static void task_numa_work(struct callback_head *work) · line 3337
Quoted 9 lines
kernel/sched/fair.c +6
-0@@ -3329,6 +3329,13 @@ static void task_numa_work(struct callback_head *work) if (p->flags & PF_EXITING) return; + /* + * Memory is pinned to only one NUMA node via cpuset.mems, naturally + * no page can be migrated. + */ + if (cpusets_enabled() && nodes_weight(cpuset_current_mems_allowed) == 1) + return; +I found that you had a proposal in V1 to address Peter's concern[1]:
Allow the task to be migrated to its preferred Node, even if the task's
memory policy is restricted to 1 Node. In your previous proposal, only if the task's cpumask is bound to the same Node as its memory policy node, the NUMA balance scanning is skipped, because a cgroup usually binds its tasks and memory allocation policy to the same node. Not sure if that could be turned into:
Quoted 5 lines
Quoted 2 lines
If the task's memory policy node's CPU mask is a subset of the task's cpumask, the NUMA balance scan is allowed.
I guess fundamentally is this really worth it? Do the benefits of NUMA task migrations only outweigh the overheads of VMA scanning, PTE updates and page faults etc? I suppose this is workload-dependent, but what about the best-case scenario? I think we probably need more data. Also if we do that, we also need to do the same for other VMA skipping scenarios.
Overall that can be a future work and I agree for now this patch is simple enough and feel free to add:
thanks,
Chenyu
PATCH v3 2/2 sched/numa: Add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning
In reply to Libo ChenUnlike sched_skip_vma_numa tracepoint which tracks skipped VMAs, this tracks the task subjected to cpuset.mems pinning and prints out its allowed memory node mask.
--- include/trace/events/sched.h | 30 ++++++++++++++++++++++++++++++ kernel/sched/fair.c | 4 +++- 2 files changed, 33 insertions(+), 1 deletion(-)
include/trace/events/sched.h +30 -0
@@ -745,6 +745,36 @@ TRACE_EVENT(sched_skip_vma_numa, __entry->vm_end, __print_symbolic(__entry->reason, NUMAB_SKIP_REASON)) ); + +TRACE_EVENT (sched_skip_cpuset_numa, + + TP_PROTO(struct task_struct *tsk, nodemask_t *mem_allowed_ptr), + +TP_ARGS (tsk, mem_allowed_ptr), + +TP_STRUCT__entry ( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( pid_t, tgid ) + __field( pid_t, ngid ) + __field( nodemask_t *, mem_allowed_ptr ) + ), + +TP_fast_assign ( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = task_pid_nr(tsk); + __entry->tgid = task_tgid_nr(tsk); + __entry->ngid = task_numa_group_id(tsk); + __entry->mem_allowed_ptr = mem_allowed_ptr; + ), + +TP_printk ("comm=%s pid=%d tgid=%d ngid=%d mem_nodes_allowed=%*pbl" , + __entry->comm, + __entry->pid, + __entry->tgid, + __entry->ngid, +nodemask_pr_args (__entry->mem_allowed_ptr)) +);#endif /* CONFIG_NUMA_BALANCING */ /*
kernel/sched/fair.c +3 -1
@@ -3333,8 +3333,10 @@ static void task_numa_work(struct callback_head *work)* Memory is pinned to only one NUMA node via cpuset.mems, naturally * no page can be migrated. */ -if (cpusets_enabled () &&nodes_weight (cpuset_current_mems_allowed) ==1 ) +if (cpusets_enabled () &&nodes_weight (cpuset_current_mems_allowed) ==1 ) { +trace_sched_skip_cpuset_numa (current, &cpuset_current_mems_allowed);return ; + }if (!mm->numa_next_scan) { mm->numa_next_scan = now +
Signature · 1 line
2.43.5
Steven Rostedt
maintainerRe: [PATCH v3 2/2] sched/numa: Add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning
Quoted 19 lines · On Thu, 17 Apr 2025 12:15:43 -0700 Libo Chen <[email protected]> wrote:
include/trace/events/sched.h +11
-0@@ -745,6 +745,36 @@ TRACE_EVENT(sched_skip_vma_numa, __entry->vm_end, __print_symbolic(__entry->reason, NUMAB_SKIP_REASON)) ); + +TRACE_EVENT(sched_skip_cpuset_numa, + + TP_PROTO(struct task_struct *tsk, nodemask_t *mem_allowed_ptr), + + TP_ARGS(tsk, mem_allowed_ptr), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( pid_t, tgid )
include/trace/events/sched.h TRACE_EVENT(sched_skip_vma_numa, · line 768
Quoted 10 lines
include/trace/events/sched.h +10
-0+ __field( pid_t, ngid ) + __field( nodemask_t *, mem_allowed_ptr ) + ), + +TP_fast_assign ( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid =task_pid_nr (tsk); + __entry->tgid =task_tgid_nr (tsk); + __entry->ngid =task_numa_group_id (tsk); + __entry->mem_allowed_ptr = mem_allowed_ptr;
This is a bug. You can't save random pointers in the TP_fast_assign() and reference it later in the TP_printk().
The TP_fast_assign() is executed during the normal kernel workflow when the tracepoint is triggered. The pointer is saved into the ring buffer.
include/trace/events/sched.h TRACE_EVENT(sched_skip_vma_numa, · line 776
Quoted 8 lines
include/trace/events/sched.h +8
-0+ ), + +TP_printk ("comm=%s pid=%d tgid=%d ngid=%d mem_nodes_allowed=%*pbl" , + __entry->comm, + __entry->pid, + __entry->tgid, + __entry->ngid, +nodemask_pr_args (__entry->mem_allowed_ptr))
The TP_printk() is executed when a user reads the /sys/kernel/tracing/trace file. Which could be literally months later.
The nodemask_pr_args() will dereference the __entry->mem_allowed_ptr from what was saved in the ring buffer, which the content it points to could have been freed days ago.
If that happens, then BOOM! Kernel goes bye-bye!
The trace event verifier is made to find bugs like his. And with the recent update to handle "%*p" it found this bug. ;-)
-- Steve
Quoted 2 lines
include/trace/events/sched.h +1
-0+);#endif /* CONFIG_NUMA_BALANCING */
Re: [PATCH v3 2/2] sched/numa: Add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning
Quoted 31 lines · Steven Rostedt
Quoted 24 lines · On Thu, 17 Apr 2025 12:15:43 -0700 Libo Chen <[email protected]> wrote:
include/trace/events/sched.h +16
-0@@ -745,6 +745,36 @@ TRACE_EVENT(sched_skip_vma_numa, __entry->vm_end, __print_symbolic(__entry->reason, NUMAB_SKIP_REASON)) ); + +TRACE_EVENT(sched_skip_cpuset_numa, + + TP_PROTO(struct task_struct *tsk, nodemask_t *mem_allowed_ptr), + + TP_ARGS(tsk, mem_allowed_ptr), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( pid_t, tgid ) + __field( pid_t, ngid ) + __field( nodemask_t *, mem_allowed_ptr ) + ), + + TP_fast_assign(
Quoted 9 lines
include/trace/events/sched.h TRACE_EVENT(sched_skip_vma_numa, · line 768
Quoted 5 lines
include/trace/events/sched.h +5
-0+memcpy (__entry->comm, tsk->comm,TASK_COMM_LEN ); + __entry->pid =task_pid_nr (tsk); + __entry->tgid =task_tgid_nr (tsk); + __entry->ngid =task_numa_group_id (tsk); + __entry->mem_allowed_ptr = mem_allowed_ptr;This is a bug. You can't save random pointers in the
TP_fast_assign()and reference it later in theTP_printk().
Admittedly I was a bit nervous about dereferencing this pointer at TP_printk() time. Will fix it!
Also wondering if we can fail the build in this scenario so it will be easier to catch this bug at the build time.
Thanks
Libo
Quoted 29 lines
The
TP_fast_assign()is executed during the normal kernel workflow when the tracepoint is triggered. The pointer is saved into the ring buffer.include/trace/events/sched.h TRACE_EVENT(sched_skip_vma_numa, · line 776
Quoted 8 lines
include/trace/events/sched.h +8
-0+ ), + +TP_printk ("comm=%s pid=%d tgid=%d ngid=%d mem_nodes_allowed=%*pbl" , + __entry->comm, + __entry->pid, + __entry->tgid, + __entry->ngid, +nodemask_pr_args (__entry->mem_allowed_ptr))The
TP_printk()is executed when a user reads the/sys/kernel/tracing/tracefile. Which could be literally months later.The
nodemask_pr_args()will dereference the__entry->mem_allowed_ptrfrom what was saved in the ring buffer, which the content it points to could have been freed days ago.If that happens, then BOOM! Kernel goes bye-bye!
The trace event verifier is made to find bugs like his. And with the recent update to handle "%*p" it found this bug. ;-)
-- Steve
Quoted 2 lines
include/trace/events/sched.h +1
-0+);#endif /* CONFIG_NUMA_BALANCING */
Steven Rostedt
maintainerRe: [PATCH v3 2/2] sched/numa: Add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning
Quoted 2 lines · On Wed, 23 Apr 2025 16:05:44 +0000 Libo Chen <[email protected]> wrote:
Also wondering if we can fail the build in this scenario so it will be easier to catch this bug at the build time.
return -EPONYS ;-)
I wish. It's hard enough to catch this at runtime.
-- Steve
Re: [PATCH v3 2/2] sched/numa: Add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning
Quoted 7 lines · Steven Rostedt
On Wed, 23 Apr 2025 16:05:44 +0000
Libo Chen <[email protected]> wrote:
Quoted 7 lines
Quoted 2 lines
Also wondering if we can fail the build in this scenario so it will be easier to catch this bug at the build time.
return
-EPONYS;-)I wish. It's hard enough to catch this at runtime.
Correct me if I'm wrong but can you disallow any passed-in pointers to be dereferenced when TP_printk() is executed? This is something you can check at the build time, right?
Libo
Quoted 1 line
-- Steve
Steven Rostedt
maintainerRe: [PATCH v3 2/2] sched/numa: Add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning
Quoted 3 lines · On Wed, 23 Apr 2025 16:50:15 +0000 Libo Chen <[email protected]> wrote:
Correct me if I'm wrong but can you disallow any passed-in pointers to be dereferenced when
TP_printk()is executed? This is something you can check at the build time, right?
You can dereference if the pointer is to the content on the ring buffer. For instance, you can have:
"%p*h", &__entry->val
It dereferences to the content stored on the ring buffer.
What we can't have is:
"%p*h", __entry->val
-- Steve
Steven Rostedt
maintainerRe: [PATCH v3 2/2] sched/numa: Add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning
Quoted 3 lines · On Wed, 23 Apr 2025 12:56:59 -0400 Steven Rostedt <[email protected]> wrote:
For instance, you can have:
"%p*h",
&__entry->val
That should have been:
"%p*h", __entry->size, &__entry->val
-- Steve
Re: [PATCH v3 2/2] sched/numa: Add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning
In reply to Steven RostedtQuoted 14 lines · Steven Rostedt
Quoted 3 lines · On Wed, 23 Apr 2025 16:50:15 +0000 Libo Chen <[email protected]> wrote:
Correct me if I'm wrong but can you disallow any passed-in pointers to be dereferenced when
TP_printk()is executed? This is something you can check at the build time, right?You can dereference if the pointer is to the content on the ring buffer. For instance, you can have:
Quoted 7 lines
"%p*h",
&__entry->valIt dereferences to the content stored on the ring buffer.
What we can't have is:
"%p*h",
__entry->val
Right, I was thinking something stricter such as disallowing point-type field in TP_STRUCT__entry {} to avoid direct assignment to point-type field so there will be no chance to have unsafe dereference but then I realize C doesn’t have built-in mechanism to detect various types of pointers at the compile time, maybe rust can do that. Anyway I give up.
Thanks,
Libo
Quoted 2 lines
-- Steve
Quoted 9 lines · On Thu, 17 Apr 2025 12:15:41 -0700 Libo Chen <[email protected]> wrote:
v1->v2:
1. add perf improvment numbers in commit log. Yet to find perf diff on will-it-scale, so not included here. Plan to run more workloads.
2. add tracepoint.
3. To peterz's comment, this will make it impossible to attract tasks to those memory just like other VMA skippings. This is the current implementation, I think we can improve that in the future, but at the moment it's probabaly better to keep it consistent.
Quoted 4 lines
v2->v3:
1. addenable_cpuset()based on Mel's suggestion but again I think it's redundant
2. print out nodemask with %*p.. format in the tracepoint
I do agree with Mel - bitmap_weight() is somewhat expensive and cpusets_enabled() is super fast. So the benefit to cpusets_enabled()=false kernels will exceed to cost to cpusets_enabled()=true kernels.
This isn't traditionally mm.git material, but it's close. I'll grab the patchset for some testing. and shall drop it again if it turns up via another tree.
Quoted 16 lines · Andrew Morton
Quoted 9 lines · On Thu, 17 Apr 2025 12:15:41 -0700 Libo Chen <[email protected]> wrote:
v1->v2:
1. add perf improvment numbers in commit log. Yet to find perf diff on will-it-scale, so not included here. Plan to run more workloads.
2. add tracepoint.
3. To peterz's comment, this will make it impossible to attract tasks to those memory just like other VMA skippings. This is the current implementation, I think we can improve that in the future, but at the moment it's probabaly better to keep it consistent.Quoted 4 lines
v2->v3:
1. addenable_cpuset()based on Mel's suggestion but again I think it's redundant
2. print out nodemask with %*p.. format in the tracepoint
Quoted 5 lines
I do agree with Mel -
bitmap_weight()is somewhat expensive andcpusets_enabled()is super fast. So the benefit to cpusets_enabled()=false kernels will exceed to cost to cpusets_enabled()=true kernels.
Ah yes, that's right. Thanks for grabbing it~
Libo
Quoted 4 lines
This isn't traditionally mm.git material, but it's close. I'll grab the patchset for some testing. and shall drop it again if it turns up via another tree.