niansa-misc/linux
1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
Code Issues Projects Releases Packages Wiki Activity

sched: Compact RSEQ concurrency IDs with reduced threads and affinity

Browse source 
When a process reduces its number of threads or clears bits in its CPU
affinity mask, the mm_cid allocation should eventually converge towards
smaller values.

However, the change introduced by:

commit 7e019dcc47 ("sched: Improve cache locality of RSEQ concurrency
IDs for intermittent workloads")

adds a per-mm/CPU recent_cid which is never unset unless a thread
migrates.

This is a tradeoff between:

A) Preserving cache locality after a transition from many threads to few
   threads, or after reducing the hamming weight of the allowed CPU mask.

B) Making the mm_cid upper bounds wrt nr threads and allowed CPU mask
   easy to document and understand.

C) Allowing applications to eventually react to mm_cid compaction after
   reduction of the nr threads or allowed CPU mask, making the tracking
   of mm_cid compaction easier by shrinking it back towards 0 or not.

D) Making sure applications that periodically reduce and then increase
   again the nr threads or allowed CPU mask still benefit from good
   cache locality with mm_cid.

Introduce the following changes:

* After shrinking the number of threads or reducing the number of
  allowed CPUs, reduce the value of max_nr_cid so expansion of CID
  allocation will preserve cache locality if the number of threads or
  allowed CPUs increase again.

* Only re-use a recent_cid if it is within the max_nr_cid upper bound,
  else find the first available CID.

Fixes: 7e019dcc47 ("sched: Improve cache locality of RSEQ concurrency IDs for intermittent workloads")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Gabriele Monaco <gmonaco@redhat.com>
Link: https://lkml.kernel.org/r/20250210153253.460471-2-gmonaco@redhat.com
This commit is contained in:
Mathieu Desnoyers 2025-02-10 16:32:50 +01:00 • committed by Peter Zijlstra
parent 0ad2507d5d
commit 02d954c0fd
2 changed files with 26 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
include/linux/mm_types.h
View file

@ -875,10 +875,11 @@ struct mm_struct {
*/ */
unsigned int nr_cpus_allowed; unsigned int nr_cpus_allowed;
/** /**
* @max_nr_cid: Maximum number of concurrency IDs allocated. * @max_nr_cid: Maximum number of allowed concurrency
* IDs allocated.
* *
* Track the highest number of concurrency IDs allocated for the * Track the highest number of allowed concurrency IDs
* mm. * allocated for the mm.
*/ */
atomic_t max_nr_cid; atomic_t max_nr_cid;
/** /**

25
kernel/sched/sched.h
View file

@ -3698,10 +3698,28 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm)
{ {
struct cpumask *cidmask = mm_cidmask(mm); struct cpumask *cidmask = mm_cidmask(mm);
struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid; struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
int cid = __this_cpu_read(pcpu_cid->recent_cid); int cid, max_nr_cid, allowed_max_nr_cid;
/*
* After shrinking the number of threads or reducing the number
* of allowed cpus, reduce the value of max_nr_cid so expansion
* of cid allocation will preserve cache locality if the number
* of threads or allowed cpus increase again.
*/
max_nr_cid = atomic_read(&mm->max_nr_cid);
while ((allowed_max_nr_cid = min_t(int, READ_ONCE(mm->nr_cpus_allowed),
atomic_read(&mm->mm_users))),
max_nr_cid > allowed_max_nr_cid) {
/* atomic_try_cmpxchg loads previous mm->max_nr_cid into max_nr_cid. */
if (atomic_try_cmpxchg(&mm->max_nr_cid, &max_nr_cid, allowed_max_nr_cid)) {
max_nr_cid = allowed_max_nr_cid;
break;
}
}
/* Try to re-use recent cid. This improves cache locality. */ /* Try to re-use recent cid. This improves cache locality. */
if (!mm_cid_is_unset(cid) && !cpumask_test_and_set_cpu(cid, cidmask)) cid = __this_cpu_read(pcpu_cid->recent_cid);
if (!mm_cid_is_unset(cid) && cid < max_nr_cid &&
!cpumask_test_and_set_cpu(cid, cidmask))
return cid; return cid;
/* /*
* Expand cid allocation if the maximum number of concurrency * Expand cid allocation if the maximum number of concurrency
@ -3709,8 +3727,9 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm)
* and number of threads. Expanding cid allocation as much as * and number of threads. Expanding cid allocation as much as
* possible improves cache locality. * possible improves cache locality.
*/ */
cid = atomic_read(&mm->max_nr_cid); cid = max_nr_cid;
while (cid < READ_ONCE(mm->nr_cpus_allowed) && cid < atomic_read(&mm->mm_users)) { while (cid < READ_ONCE(mm->nr_cpus_allowed) && cid < atomic_read(&mm->mm_users)) {
/* atomic_try_cmpxchg loads previous mm->max_nr_cid into cid. */
if (!atomic_try_cmpxchg(&mm->max_nr_cid, &cid, cid + 1)) if (!atomic_try_cmpxchg(&mm->max_nr_cid, &cid, cid + 1))
continue; continue;
if (!cpumask_test_and_set_cpu(cid, cidmask)) if (!cpumask_test_and_set_cpu(cid, cidmask))