linux-block.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Hyeonggon Yoo <42.hyeyoo@gmail.com>
To: Matthew Wilcox <willy@infradead.org>
Cc: linux-mm@kvack.org, Christoph Lameter <cl@linux.com>,
	Pekka Enberg <penberg@kernel.org>,
	David Rientjes <rientjes@google.com>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Vlastimil Babka <vbabka@suse.cz>,
	linux-kernel@vger.kernel.org, Jens Axboe <axboe@kernel.dk>,
	John Garry <john.garry@huawei.com>,
	linux-block@vger.kernel.org, netdev@vger.kernel.org
Subject: Re: [RFC v2 PATCH] mm, sl[au]b: Introduce lockless cache
Date: Wed, 22 Sep 2021 08:32:28 +0000	[thread overview]
Message-ID: <20210922083228.GA79355@kvm.asia-northeast3-a.c.our-ratio-313919.internal> (raw)
In-Reply-To: <YUoFfrQBmOdPEKpJ@casper.infradead.org>

Hello Matthew.
There's good news.

in v3 (work in progress now), I fixed some bugs (I hate kernel panics!)
And for test, made NAPI use it. it works pretty well.

On Tue, Sep 21, 2021 at 05:17:02PM +0100, Matthew Wilcox wrote:
> On Tue, Sep 21, 2021 at 03:42:39PM +0000, Hyeonggon Yoo wrote:
> > > > +	/* slowpath */
> > > > +	cache->size = kmem_cache_alloc_bulk(s, gfpflags,
> > > > +			KMEM_LOCKLESS_CACHE_QUEUE_SIZE, cache->queue);
> > > 
> > > Go back to the Bonwick paper and look at the magazine section again.
> > > You have to allocate _half_ the size of the queue, otherwise you get
> > > into pathological situations where you start to free and allocate
> > > every time.
> > 
> > I want to ask you where idea of allocating 'half' the size of queue came from.
> > the paper you sent does not work with single queue(magazine). Instead,
> > it manages pool of magazines.
> > 
> > And after reading the paper, I see managing pool of magazine (where M is
> > an boot parameter) is valid approach to reduce hitting slowpath.
> 
> Bonwick uses two magazines per cpu; if both are empty, one is replaced
> with a full one.  If both are full, one is replaced with an empty one.
> Our slab implementation doesn't provide magazine allocation, but it does
> provide bulk allocation.
> So translating the Bonwick implementation to
> our implementation, we need to bulk-allocate or bulk-free half of the
> array at any time.

Is there a reason that the number should be 'half'?

what about something like this:

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 884d3311cd8e..f32736302d53 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -455,12 +455,13 @@ void *kmem_cache_alloc_cached(struct kmem_cache *s, gfp_t gfpflags)
        }

        cache = get_cpu_ptr(s->cache);
-       if (cache->size) /* fastpath without lock */
+       if (cache->size) /* fastpath without lock */
                p = cache->queue[--cache->size];
        else {
                /* slowpath */
-               cache->size = kmem_cache_alloc_bulk(s, gfpflags,
-                               KMEM_LOCKLESS_CACHE_QUEUE_SIZE, cache->queue);
+               cache->size += kmem_cache_alloc_bulk(s, gfpflags,
+                               KMEM_LOCKLESS_CACHE_BATCHCOUNT,
+                               cache->queue);
                if (cache->size)
                        p = cache->queue[--cache->size];
                else
@@ -491,13 +492,13 @@ void kmem_cache_free_cached(struct kmem_cache *s, void *p)
        cache = get_cpu_ptr(s->cache);
        if (cache->size < KMEM_LOCKLESS_CACHE_QUEUE_SIZE) {
                cache->queue[cache->size++] = p;
-               put_cpu_ptr(s->cache);
-               return ;
+       } else {
+               kmem_cache_free_bulk(s,
+                               KMEM_LOCKLESS_CACHE_BATCHCOUNT,
+                               cache->queue - KMEM_LOCKLESS_CACHE_BATCHCOUNT);
+               cache->size -= KMEM_LOCKLESS_CACHE_BATCHCOUNT;
        }
        put_cpu_ptr(s->cache);
-
-       /* Is there better way to do this? */
-       kmem_cache_free(s, p);
 }
 EXPORT_SYMBOL(kmem_cache_free_cached);

  reply	other threads:[~2021-09-22  8:32 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-20 15:48 Hyeonggon Yoo
2021-09-20 22:01 ` Matthew Wilcox
2021-09-21 10:56   ` Hyeonggon Yoo
2021-09-21 15:42   ` Hyeonggon Yoo
2021-09-21 16:17     ` Matthew Wilcox
2021-09-22  8:32       ` Hyeonggon Yoo [this message]
2021-09-22  9:11         ` Hyeonggon Yoo
2021-09-21 15:37 ` Jens Axboe
2021-09-22  8:19   ` Hyeonggon Yoo
2021-09-22 12:58     ` Jens Axboe
2021-09-23  3:34       ` Hyeonggon Yoo
2021-09-23 13:28       ` Jakub Kicinski
2021-09-23  3:55 ` Github link here Hyeonggon Yoo

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=20210922083228.GA79355@kvm.asia-northeast3-a.c.our-ratio-313919.internal \
    --to=42.hyeyoo@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=cl@linux.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=john.garry@huawei.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=netdev@vger.kernel.org \
    --cc=penberg@kernel.org \
    --cc=rientjes@google.com \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    --subject='Re: [RFC v2 PATCH] mm, sl[au]b: Introduce lockless cache' \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).