All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mike Galbraith <efault@gmx.de>
To: Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Vlastimil Babka <vbabka@suse.cz>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	Christoph Lameter <cl@linux.com>,
	David Rientjes <rientjes@google.com>,
	Pekka Enberg <penberg@kernel.org>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Mel Gorman <mgorman@techsingularity.net>,
	Jesper Dangaard Brouer <brouer@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Jann Horn <jannh@google.com>
Subject: Re: [RFC v2 00/34] SLUB: reduce irq disabled scope and make it RT compatible
Date: Sat, 03 Jul 2021 17:47:01 +0200	[thread overview]
Message-ID: <ca0474137c1e5a16a1215693298c9cd93218e24c.camel@gmx.de> (raw)
In-Reply-To: <891dc24e38106f8542f4c72831d52dc1a1863ae8.camel@gmx.de>

On Sat, 2021-07-03 at 09:24 +0200, Mike Galbraith wrote:
>
> It also appears to be saying that there's something RT specific to
> stare at in addition to the list_lock business.

The what is ___slab_alloc() consuming 3.9% CPU in tip-rt-slub whereas
it consumes < 1% in both tip-rt (sans slub patches) and tip-slub.

The why remains to ponder.

            5.13.0.g60ab3ed-tip-rt           5.13.0.g60ab3ed-tip-rt-slub      5.13.0.g60ab3ed-tip-slub
    25.18%  copy_user_enhanced_fast_string   copy_user_enhanced_fast_string   copy_user_enhanced_fast_string
     5.08%  unix_stream_read_generic         unix_stream_read_generic         unix_stream_read_generic
     3.39%  rt_spin_lock                 *** ___slab_alloc ***                __skb_datagram_iter
     2.80%  __skb_datagram_iter              rt_spin_lock                     _raw_spin_lock
     2.11%  get_page_from_freelist           __skb_datagram_iter              __alloc_skb
     2.01%  skb_release_data                 rt_spin_unlock                   skb_release_data
     1.94%  rt_spin_unlock                   get_page_from_freelist           __alloc_pages
     1.85%  __alloc_skb                      migrate_enable                   unix_stream_sendmsg
     1.68%  __schedule                       skb_release_data                 _raw_spin_lock_irqsave
     1.67%  unix_stream_sendmsg              __schedule                       free_pcppages_bulk
     1.50%  free_pcppages_bulk               unix_stream_sendmsg              __slab_free
     1.38%  migrate_enable                   free_pcppages_bulk               __fget_light
     1.24%  __fget_light                     __alloc_pages                    vfs_write
     1.16%  __slab_free                      migrate_disable                  __schedule
     1.14%  __alloc_pages                    __fget_light                     get_page_from_freelist
     1.10%  fsnotify                         __slab_free                      new_sync_write
     1.07%  kfree                            fsnotify                         fsnotify

5.13.0.g60ab3ed-tip-rt-slub ___slab_alloc() consumes 3.90%
  0.40 │       mov    0x28(%r13),%edx
  0.42 │       add    %r15,%rdx
       │     __swab():
       │     #endif
       │
       │     static __always_inline unsigned long __swab(const unsigned long y)
       │     {
       │     #if __BITS_PER_LONG == 64
       │     return __swab64(y);
  0.05 │       mov    %rdx,%rax
  1.14 │       bswap  %rax
       │     freelist_ptr():
       │     return (void *)((unsigned long)ptr ^ s->random ^  <== CONFIG_SLAB_FREELIST_HARDENED
  0.72 │       xor    0xb0(%r13),%rax
 65.41 │       xor    (%rdx),%rax                              <== huh? miss = 65% of that 3.9% kernel util?
       │     next_tid():
       │     return tid + TID_STEP;
  0.09 │       addq   $0x200,0x48(%r12)
       │     ___slab_alloc():
       │     * freelist is pointing to the list of objects to be used.
       │     * page is pointing to the page from which the objects are obtained.
       │     * That page must be frozen for per cpu allocations to work.
       │     */
       │     VM_BUG_ON(!c->page->frozen);
       │     c->freelist = get_freepointer(s, freelist);
  0.05 │       mov    %rax,0x40(%r12)
       │     c->tid = next_tid(c->tid);
       │     local_unlock_irqrestore(&s->cpu_slab->lock, flags);

5.13.0.g60ab3ed-tip-rt ___slab_alloc() consumes < 1%
Percent│     }
       │
       │     /* must check again c->freelist in case of cpu migration or IRQ */
       │     freelist = c->freelist;
  0.02 │ a1:   mov    (%r14),%r13
       │     if (freelist)
       │       test   %r13,%r13
  0.02 │     ↓ je     460
       │     get_freepointer():
       │     return freelist_dereference(s, object + s->offset);
  0.23 │ ad:   mov    0x28(%r12),%edx
  0.18 │       add    %r13,%rdx
       │     __swab():
       │     #endif
       │
       │     static __always_inline unsigned long __swab(const unsigned long y)
       │     {
       │     #if __BITS_PER_LONG == 64
       │     return __swab64(y);
  0.06 │       mov    %rdx,%rax
  1.16 │       bswap  %rax
       │     freelist_ptr():
       │     return (void *)((unsigned long)ptr ^ s->random ^
  0.23 │       xor    0xb0(%r12),%rax
 35.25 │       xor    (%rdx),%rax              <== 35% of < 1% kernel util
       │     next_tid():
       │     return tid + TID_STEP;
  0.28 │       addq   $0x200,0x8(%r14)
       │     ___slab_alloc():
       │     * freelist is pointing to the list of objects to be used.
       │     * page is pointing to the page from which the objects are obtained.
       │     * That page must be frozen for per cpu allocations to work.
       │     */
       │     VM_BUG_ON(!c->page->frozen);
       │     c->freelist = get_freepointer(s, freelist);

5.13.0.g60ab3ed-tip-slub ___slab_alloc() also consumes < 1%
Percent│     load_freelist:
       │
       │     lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock));
  0.28 │ 84:   add    this_cpu_off,%rax
       │     get_freepointer():
       │     return freelist_dereference(s, object + s->offset);
  0.14 │       mov    0x28(%r14),%eax
       │     ___slab_alloc():
       │     * freelist is pointing to the list of objects to be used.
       │     * page is pointing to the page from which the objects are obtained.
       │     * That page must be frozen for per cpu allocations to work.
       │     */
       │     VM_BUG_ON(!c->page->frozen);
       │     c->freelist = get_freepointer(s, freelist);
 34.36 │       mov    0x0(%r13,%rax,1),%rax
       │     next_tid():
       │     return tid + TID_STEP;
  0.10 │       addq   $0x1,0x8(%r12)
       │     ___slab_alloc():
       │     c->freelist = get_freepointer(s, freelist);
  0.04 │       mov    %rax,(%r12)
       │     c->tid = next_tid(c->tid);
       │     local_unlock_irqrestore(&s->cpu_slab->lock, flags);
  0.12 │       mov    (%r14),%rax
  0.03 │       add    this_cpu_off,%rax
       │     arch_local_irq_restore():
       │     return arch_irqs_disabled_flags(flags);
       │     }



  reply	other threads:[~2021-07-03 15:47 UTC|newest]

Thread overview: 65+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-09 11:38 Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 01/34] mm, slub: don't call flush_all() from list_locations() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 02/34] mm, slub: allocate private object map for sysfs listings Vlastimil Babka
2021-06-09 13:29   ` Christoph Lameter
2021-06-09 13:29     ` Christoph Lameter
2021-06-09 11:38 ` [RFC v2 03/34] mm, slub: allocate private object map for validate_slab_cache() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 04/34] mm, slub: don't disable irq for debug_check_no_locks_freed() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 05/34] mm, slub: remove redundant unfreeze_partials() from put_cpu_partial() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 06/34] mm, slub: unify cmpxchg_double_slab() and __cmpxchg_double_slab() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 07/34] mm, slub: extract get_partial() from new_slab_objects() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 08/34] mm, slub: dissolve new_slab_objects() into ___slab_alloc() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 09/34] mm, slub: return slab page from get_partial() and set c->page afterwards Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 10/34] mm, slub: restructure new page checks in ___slab_alloc() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 11/34] mm, slub: simplify kmem_cache_cpu and tid setup Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 12/34] mm, slub: move disabling/enabling irqs to ___slab_alloc() Vlastimil Babka
2021-07-06  4:38   ` Mike Galbraith
2021-07-06  4:38     ` Mike Galbraith
2021-06-09 11:38 ` [RFC v2 13/34] mm, slub: do initial checks in ___slab_alloc() with irqs enabled Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 14/34] mm, slub: move disabling irqs closer to get_partial() in ___slab_alloc() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 15/34] mm, slub: restore irqs around calling new_slab() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 16/34] mm, slub: validate slab from partial list or page allocator before making it cpu slab Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 17/34] mm, slub: check new pages with restored irqs Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 18/34] mm, slub: stop disabling irqs around get_partial() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 19/34] mm, slub: move reset of c->page and freelist out of deactivate_slab() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 20/34] mm, slub: make locking in deactivate_slab() irq-safe Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 21/34] mm, slub: call deactivate_slab() without disabling irqs Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 22/34] mm, slub: move irq control into unfreeze_partials() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 23/34] mm, slub: discard slabs in unfreeze_partials() without irqs disabled Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 24/34] mm, slub: detach whole partial list at once in unfreeze_partials() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 25/34] mm, slub: detach percpu partial list in unfreeze_partials() using this_cpu_cmpxchg() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 26/34] mm, slub: only disable irq with spin_lock in __unfreeze_partials() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 27/34] mm, slub: don't disable irqs in slub_cpu_dead() Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 28/34] mm, slab: make flush_slab() possible to call with irqs enabled Vlastimil Babka
2021-06-09 11:38 ` [RFC v2 29/34] mm: slub: Move flush_cpu_slab() invocations __free_slab() invocations out of IRQ context Vlastimil Babka
2021-06-09 22:29   ` Cyrill Gorcunov
2021-06-10  8:32     ` Vlastimil Babka
2021-06-10  8:36       ` Cyrill Gorcunov
2021-07-07  6:33   ` Hillf Danton
2021-06-09 11:38 ` [RFC v2 30/34] mm: slub: Make object_map_lock a raw_spinlock_t Vlastimil Babka
2021-06-09 11:39 ` [RFC v2 31/34] mm, slub: optionally save/restore irqs in slab_[un]lock()/ Vlastimil Babka
2021-07-02 12:17   ` Sebastian Andrzej Siewior
2021-06-09 11:39 ` [RFC v2 32/34] mm, slub: make slab_lock() disable irqs with PREEMPT_RT Vlastimil Babka
2021-06-09 11:39 ` [RFC v2 33/34] mm, slub: use migrate_disable() on PREEMPT_RT Vlastimil Babka
2021-06-14 11:07   ` Vlastimil Babka
2021-06-14 11:16     ` Sebastian Andrzej Siewior
2021-06-14 11:33       ` Vlastimil Babka
2021-06-14 12:54         ` Vlastimil Babka
2021-06-14 14:01         ` Sebastian Andrzej Siewior
2021-06-09 11:39 ` [RFC v2 34/34] mm, slub: convert kmem_cpu_slab protection to local_lock Vlastimil Babka
2021-06-14  9:49 ` [RFC v2 00/34] SLUB: reduce irq disabled scope and make it RT compatible Mel Gorman
2021-06-14 11:31   ` Mel Gorman
2021-06-14 11:10 ` Vlastimil Babka
2021-07-02 18:29 ` Sebastian Andrzej Siewior
2021-07-02 20:25   ` Vlastimil Babka
2021-07-29 13:49     ` Sebastian Andrzej Siewior
2021-07-29 14:17       ` Vlastimil Babka
2021-07-29 14:37         ` Sebastian Andrzej Siewior
2021-07-03  7:24   ` Mike Galbraith
2021-07-03 15:47     ` Mike Galbraith [this message]
2021-07-04  5:37       ` Mike Galbraith
2021-07-18  7:41     ` Vlastimil Babka
2021-07-18  8:29       ` Mike Galbraith
2021-07-18 12:09         ` Mike Galbraith
2021-07-05 16:00   ` Mike Galbraith
2021-07-06 17:56     ` Mike Galbraith

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=ca0474137c1e5a16a1215693298c9cd93218e24c.camel@gmx.de \
    --to=efault@gmx.de \
    --cc=bigeasy@linutronix.de \
    --cc=brouer@redhat.com \
    --cc=cl@linux.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=jannh@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=penberg@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rientjes@google.com \
    --cc=tglx@linutronix.de \
    --cc=vbabka@suse.cz \
    --subject='Re: [RFC v2 00/34] SLUB: reduce irq disabled scope and make it RT compatible' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.