[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZSic8JsHGIlfuwhp@probook>
Date: Fri, 13 Oct 2023 03:27:12 +0200
From: J. Neuschäfer <j.neuschaefer@....net>
To: Nick Terrell <terrelln@...a.com>
Cc: Jonathan Neuschäfer <j.neuschaefer@....net>,
Arnd Bergmann <arnd@...db.de>,
Linux ARM <linux-arm-kernel@...ts.infradead.org>,
Russell King <linux@...linux.org.uk>,
Tony Lindgren <tony@...mide.com>,
Geert Uytterhoeven <geert+renesas@...der.be>,
Linus Walleij <linus.walleij@...aro.org>,
Sebastian Reichel <sebastian.reichel@...labora.com>,
"Hawkins, Nick" <nick.hawkins@....com>,
Christophe Leroy <christophe.leroy@...roup.eu>,
Florian Fainelli <f.fainelli@...il.com>,
Nick Desaulniers <ndesaulniers@...gle.com>,
Xin Li <xin3.li@...el.com>,
Seung-Woo Kim <sw0312.kim@...sung.com>,
Paul Bolle <pebolle@...cali.nl>,
Bart Van Assche <bvanassche@....org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 0/3] ARM ZSTD boot compression
On Thu, Oct 12, 2023 at 10:33:23PM +0000, Nick Terrell wrote:
> > On Apr 14, 2023, at 10:00 PM, Jonathan Neuschäfer <j.neuschaefer@....net> wrote:
> > On Thu, Apr 13, 2023 at 01:13:21PM +0200, Arnd Bergmann wrote:
> >> On Wed, Apr 12, 2023, at 23:33, Arnd Bergmann wrote:
> >>> On Wed, Apr 12, 2023, at 23:21, Jonathan Neuschäfer wrote:
> >>>> This patchset enables ZSTD kernel (de)compression on 32-bit ARM.
> >>>> Unfortunately, it is much slower than I hoped (tested on ARM926EJ-S):
> >>>>
> >>>> - LZO: 7.2 MiB, 6 seconds
> >>>> - ZSTD: 5.6 MiB, 60 seconds
[...]
> > For ZSTD as used in kernel decompression (the zstd22 configuration), the
> > window is even bigger, 128 MiB. (AFAIU)
>
> Sorry, I’m a bit late to the party, I wasn’t getting LKML email for some time...
>
> But this is totally configurable. You can switch compression configurations
> at any time. If you believe that the window size is the issue causing speed
> regressions, you could use a zstd compression to use a e.g. 256KB window
> size like this:
>
> zstd -19 --zstd=wlog=18
>
> This will keep the same algorithm search strength, but limit the decoder memory
> usage.
Noted.
> I will also try to get this patchset working on my machine, and try to debug.
> The 10x slower speed difference is not expected, and we see much better speed
> in userspace ARM. I suspect it has something to do with the preboot environment.
> E.g. when implementing x86-64 zstd kernel decompression, I noticed that
> memcpy(dst, src, 16) wasn’t getting inlined properly, causing a massive performance
> penalty.
In the meantime I've seen 8s for ZSTD vs. 2s for other algorithms, on
only mildly less ancient hardware (Hi3518A, another ARM9 SoC), so I
think the main culprit here was particularly bad luck in my choice of
test hardware.
The inlining issues are a good point, noted for the next time I work on this.
Thanks,
Jonathan
Download attachment "signature.asc" of type "application/pgp-signature" (834 bytes)
Powered by blists - more mailing lists