Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <20190716152656.12255-1-lpf.vector@gmail.com> <20190716152656.12255-2-lpf.vector@gmail.com>
 <20190724193637.44ced3b82dd76649df28ecf5@linux-foundation.org>
In-Reply-To: <20190724193637.44ced3b82dd76649df28ecf5@linux-foundation.org>
From:   Pengfei Li <lpf.vector@gmail.com>
Date:   Thu, 25 Jul 2019 22:21:34 +0800
Message-ID: <CAD7_sbEGno-o=zh=VJQOXPZ=ppcTF3h_UWAXo6dXFnBJcTNTrA@mail.gmail.com>
Subject: Re: [PATCH v6 1/2] mm/vmalloc: do not keep unpurged areas in the busy tree
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Matthew Wilcox <willy@infradead.org>,
        Uladzislau Rezki <urezki@gmail.com>, rpenyaev@suse.de,
        peterz@infradead.org, guro@fb.com, rick.p.edgecombe@intel.com,
        rppt@linux.ibm.com, aryabinin@virtuozzo.com, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Thanks.

Signed-off-by: Pengfei Li <lpf.vector@gmail.com>

On Thu, Jul 25, 2019 at 10:36 AM Andrew Morton
<akpm@linux-foundation.org> wrote:
>
> On Tue, 16 Jul 2019 23:26:55 +0800 Pengfei Li <lpf.vector@gmail.com> wrote:
>
> > From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
> >
> > The busy tree can be quite big, even though the area is freed
> > or unmapped it still stays there until "purge" logic removes
> > it.
> >
> > 1) Optimize and reduce the size of "busy" tree by removing a
> > node from it right away as soon as user triggers free paths.
> > It is possible to do so, because the allocation is done using
> > another augmented tree.
> >
> > The vmalloc test driver shows the difference, for example the
> > "fix_size_alloc_test" is ~11% better comparing with default
> > configuration:
> >
> > sudo ./test_vmalloc.sh performance
> >
> > <default>
> > Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec
> > Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec
> > Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec
> > <default>
> >
> > <this patch>
> > Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec
> > Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec
> > Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec
> > <this patch>
> >
> > 2) Since the busy tree now contains allocated areas only and does
> > not interfere with lazily free nodes, introduce the new function
> > show_purge_info() that dumps "unpurged" areas that is propagated
> > through "/proc/vmallocinfo".
> >
> > 3) Eliminate VM_LAZY_FREE flag.
> >
> > Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
>
> This should have included your signed-off-by, since you were on the
> patch delivery path.  (Documentation/process/submitting-patches.rst,
> section 11).
>
> Please send along your signed-off-by?