From: Mateusz Guzik <mjguzik@gmail.com>
To: linux-kernel@vger.kernel.org
Cc: dennis@kernel.org, tj@kernel.org, cl@linux.com,
akpm@linux-foundation.org, shakeelb@google.com,
linux-mm@kvack.org, Mateusz Guzik <mjguzik@gmail.com>
Subject: Re: [PATCH v2 1/2] pcpcntr: add group allocation/free
Date: Wed, 23 Aug 2023 03:14:35 +0200 [thread overview]
Message-ID: <CAGudoHE5iCbMzZ-N65RhQvdVygP7rcHKEqn90pif0M9DCZUm7g@mail.gmail.com> (raw)
In-Reply-To: <20230822184152.2194558-2-mjguzik@gmail.com>
On 8/22/23, Mateusz Guzik <mjguzik@gmail.com> wrote:
> Allocations and frees are globally serialized on the pcpu lock (and the
> CPU hotplug lock if enabled, which is the case on Debian).
>
> At least one frequent consumer allocates 4 back-to-back counters (and
> frees them in the same manner), exacerbating the problem.
>
> While this does not fully remedy scalability issues, it is a step
> towards that goal and provides immediate relief.
>
I just found I'm going to have to send a v3 to handle !CONFIG_SMP.
Temporarily I can't even compile-test that, so for now I'm just asking
if this v2 looks fine (modulo the !smp problem).
Sorry for the spam.
> Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
> ---
> include/linux/percpu_counter.h | 20 ++++++++---
> lib/percpu_counter.c | 61 +++++++++++++++++++++++-----------
> 2 files changed, 57 insertions(+), 24 deletions(-)
>
> diff --git a/include/linux/percpu_counter.h
> b/include/linux/percpu_counter.h
> index 75b73c83bc9d..518a4088b964 100644
> --- a/include/linux/percpu_counter.h
> +++ b/include/linux/percpu_counter.h
> @@ -30,17 +30,27 @@ struct percpu_counter {
>
> extern int percpu_counter_batch;
>
> -int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t
> gfp,
> - struct lock_class_key *key);
> +int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount,
> gfp_t gfp,
> + u32 nr_counters, struct lock_class_key *key);
>
> -#define percpu_counter_init(fbc, value, gfp) \
> +#define percpu_counter_init_many(fbc, value, gfp, nr_counters) \
> ({ \
> static struct lock_class_key __key; \
> \
> - __percpu_counter_init(fbc, value, gfp, &__key); \
> + __percpu_counter_init_many(fbc, value, gfp, nr_counters,\
> + &__key); \
> })
>
> -void percpu_counter_destroy(struct percpu_counter *fbc);
> +
> +#define percpu_counter_init(fbc, value, gfp) \
> + percpu_counter_init_many(fbc, value, gfp, 1)
> +
> +void percpu_counter_destroy_many(struct percpu_counter *fbc, u32
> nr_counters);
> +static inline void percpu_counter_destroy(struct percpu_counter *fbc)
> +{
> + percpu_counter_destroy_many(fbc, 1);
> +}
> +
> void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
> void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount,
> s32 batch);
> diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
> index 5004463c4f9f..9338b27f1cdd 100644
> --- a/lib/percpu_counter.c
> +++ b/lib/percpu_counter.c
> @@ -151,48 +151,71 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
> }
> EXPORT_SYMBOL(__percpu_counter_sum);
>
> -int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t
> gfp,
> - struct lock_class_key *key)
> +int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount,
> gfp_t gfp,
> + u32 nr_counters, struct lock_class_key *key)
> {
> unsigned long flags __maybe_unused;
> -
> - raw_spin_lock_init(&fbc->lock);
> - lockdep_set_class(&fbc->lock, key);
> - fbc->count = amount;
> - fbc->counters = alloc_percpu_gfp(s32, gfp);
> - if (!fbc->counters)
> + size_t counter_size;
> + s32 __percpu *counters;
> + u32 i;
> +
> + counter_size = ALIGN(sizeof(*counters), __alignof__(*counters));
> + counters = __alloc_percpu_gfp(nr_counters * counter_size,
> + __alignof__(*counters), gfp);
> + if (!counters) {
> + fbc[0].counters = NULL;
> return -ENOMEM;
> + }
>
> - debug_percpu_counter_activate(fbc);
> + for (i = 0; i < nr_counters; i++) {
> + raw_spin_lock_init(&fbc[i].lock);
> + lockdep_set_class(&fbc[i].lock, key);
> +#ifdef CONFIG_HOTPLUG_CPU
> + INIT_LIST_HEAD(&fbc[i].list);
> +#endif
> + fbc[i].count = amount;
> + fbc[i].counters = (void *)counters + (i * counter_size);
> +
> + debug_percpu_counter_activate(&fbc[i]);
> + }
>
> #ifdef CONFIG_HOTPLUG_CPU
> - INIT_LIST_HEAD(&fbc->list);
> spin_lock_irqsave(&percpu_counters_lock, flags);
> - list_add(&fbc->list, &percpu_counters);
> + for (i = 0; i < nr_counters; i++)
> + list_add(&fbc[i].list, &percpu_counters);
> spin_unlock_irqrestore(&percpu_counters_lock, flags);
> #endif
> return 0;
> }
> -EXPORT_SYMBOL(__percpu_counter_init);
> +EXPORT_SYMBOL(__percpu_counter_init_many);
>
> -void percpu_counter_destroy(struct percpu_counter *fbc)
> +void percpu_counter_destroy_many(struct percpu_counter *fbc, u32
> nr_counters)
> {
> unsigned long flags __maybe_unused;
> + u32 i;
> +
> + if (WARN_ON_ONCE(!fbc))
> + return;
>
> - if (!fbc->counters)
> + if (!fbc[0].counters)
> return;
>
> - debug_percpu_counter_deactivate(fbc);
> + for (i = 0; i < nr_counters; i++)
> + debug_percpu_counter_deactivate(&fbc[i]);
>
> #ifdef CONFIG_HOTPLUG_CPU
> spin_lock_irqsave(&percpu_counters_lock, flags);
> - list_del(&fbc->list);
> + for (i = 0; i < nr_counters; i++)
> + list_del(&fbc[i].list);
> spin_unlock_irqrestore(&percpu_counters_lock, flags);
> #endif
> - free_percpu(fbc->counters);
> - fbc->counters = NULL;
> +
> + free_percpu(fbc[0].counters);
> +
> + for (i = 0; i < nr_counters; i++)
> + fbc[i].counters = NULL;
> }
> -EXPORT_SYMBOL(percpu_counter_destroy);
> +EXPORT_SYMBOL(percpu_counter_destroy_many);
>
> int percpu_counter_batch __read_mostly = 32;
> EXPORT_SYMBOL(percpu_counter_batch);
> --
> 2.39.2
>
>
--
Mateusz Guzik <mjguzik gmail.com>
next prev parent reply other threads:[~2023-08-23 1:14 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-22 18:41 [PATCH v2 0/2] execve scalability issues, part 1 Mateusz Guzik
2023-08-22 18:41 ` [PATCH v2 1/2] pcpcntr: add group allocation/free Mateusz Guzik
2023-08-23 1:14 ` Mateusz Guzik [this message]
2023-08-22 18:41 ` [PATCH v2 2/2] fork: group allocation of per-cpu counters for mm struct Mateusz Guzik
2023-08-23 2:22 ` kernel test robot
2023-08-23 4:05 ` kernel test robot
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAGudoHE5iCbMzZ-N65RhQvdVygP7rcHKEqn90pif0M9DCZUm7g@mail.gmail.com \
--to=mjguzik@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=dennis@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=shakeelb@google.com \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox