Date:   Tue, 15 Mar 2022 20:46:56 -0600
From:   Yu Zhao <yuzhao@...gle.com>
To:     Barry Song <21cnbao@...il.com>
Cc:     Konstantin Kharlamov <Hi-Angel@...dex.ru>,
        Michael Larabel <Michael@...haellarabel.com>,
        Andi Kleen <ak@...ux.intel.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        "Aneesh Kumar K . V" <aneesh.kumar@...ux.ibm.com>,
        Jens Axboe <axboe@...nel.dk>,
        Brian Geffon <bgeffon@...gle.com>,
        Catalin Marinas <catalin.marinas@....com>,
        Jonathan Corbet <corbet@....net>,
        Donald Carr <d@...os-reins.com>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        Daniel Byrne <djbyrne@....edu>,
        Johannes Weiner <hannes@...xchg.org>,
        Hillf Danton <hdanton@...a.com>,
        Jan Alexander Steffens <heftig@...hlinux.org>,
        Holger Hoffstätte <holger@...lied-asynchrony.com>,
        Jesse Barnes <jsbarnes@...gle.com>,
        Linux ARM <linux-arm-kernel@...ts.infradead.org>,
        "open list:DOCUMENTATION" <linux-doc@...r.kernel.org>,
        linux-kernel <linux-kernel@...r.kernel.org>,
        Linux-MM <linux-mm@...ck.org>, Mel Gorman <mgorman@...e.de>,
        Michal Hocko <mhocko@...nel.org>,
        Oleksandr Natalenko <oleksandr@...alenko.name>,
        Kernel Page Reclaim v2 <page-reclaim@...gle.com>,
        Rik van Riel <riel@...riel.com>,
        Mike Rapoport <rppt@...nel.org>,
        Sofia Trinh <sofia.trinh@....works>,
        Steven Barrett <steven@...uorix.net>,
        Suleiman Souhlal <suleiman@...gle.com>,
        Shuang Zhai <szhai2@...rochester.edu>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Vlastimil Babka <vbabka@...e.cz>,
        Will Deacon <will@...nel.org>,
        Matthew Wilcox <willy@...radead.org>,
        "the arch/x86 maintainers" <x86@...nel.org>,
        Huang Ying <ying.huang@...el.com>
Subject: Re: [PATCH v7 04/12] mm: multigenerational LRU: groundwork

On Tue, Mar 15, 2022 at 4:29 AM Barry Song <21cnbao@...il.com> wrote:

<snipped>

> > I guess the main cause of the regression for the previous sequence
> > with 16 entries is that the ebizzy has a new allocated copy in
> > search_mem(), which is mapped and used only once in each loop.
> > and the temp copy can push out those hot chunks.
> >
> > Anyway, I understand it is a trade-off between warmly embracing new
> > pages and holding old pages tightly. Real user cases from phone, server,
> > desktop will be judging this better.

Thanks for all the details. I looked into them today and found no
regressions when running with your original program.

After I explain why, I hope you'd be convinced that using programs
like this one is not a good way to measure things :)

Problems:
1) Given the 2.5GB configuration and a sequence of cold/hot chunks, I
assume your program tries to simulate a handful of apps running on a
phone.  A short repeating sequence is closer to sequential access than
to real user behaviors, as I suggested last time. You could check out
how something similar is done here [1].
2) Under the same assumption (phone), C programs are very different
from Android apps in terms of runtime memory behaviors, e.g., JVM GC
[2].
3) Assuming you are interested in the runtime memory behavior of C/C++
programs, your program is still not very representative. All C/C++
programs I'm familiar with choose to link against TCmalloc, jemalloc
or implement their own allocators. GNU libc, IMO, has a small market
share nowadays.
4) TCmalloc/jemalloc are not only optimized for multithreading, they
are also THP aware. THP is very important when benchmarking page
reclaim, e.g., two similarly warm THPs can comprise 511+1 or 1+511 of
warm+cold 4K pages. The LRU algorithm that chooses more of the former
is at the disadvantage. Unless it's recommended by the applications
you are trying to benchmark, THP should be disabled. (Android
generally doesn't use THP.)
5) Swap devices are also important. Zram should NOT be used unless you
know your benchmark doesn't generate incompressible data. The LRU
algorithm that chooses more incompressible pages is at disadvantage.

Here is my result: on the same Snapdragon 7c + 2.5GB RAM + 1.5GB
ramdisk swap, with your original program compiled against libc malloc
and TCMalloc, to 32-bit and 64-bit binaries:

# cat /sys/kernel/mm/lru_gen/enabled
0x0003
# cat /sys/kernel/mm/transparent_hugepage/enabled
always madvise [never]

# modprobe brd rd_nr=1 rd_size=1572864
# if=/dev/zero of=/dev/ram0 bs=1M
# mkswap /dev/ram0
# swapoff -a
# swapon /dev/ram0

# ldd test_absl_32
        linux-vdso.so.1 (0xf6e7f000)
        libabsl_malloc.so.2103.0.1 =>
/usr/lib/libabsl_malloc.so.2103.0.1 (0xf6e23000)
        libpthread.so.0 => /lib/libpthread.so.0 (0xf6dff000)
        libc.so.6 => /lib/libc.so.6 (0xf6d07000)
        /lib/ld-linux-armhf.so.3 (0x09df0000)
        libabsl_base.so.2103.0.1 => /usr/lib/libabsl_base.so.2103.0.1
(0xf6ce5000)
        libabsl_raw_logging.so.2103.0.1 =>
/usr/lib/libabsl_raw_logging.so.2103.0.1 (0xf6cc4000)
        libabsl_spinlock_wait.so.2103.0.1 =>
/usr/lib/libabsl_spinlock_wait.so.2103.0.1 (0xf6ca3000)
        libc++.so.1 => /usr/lib/libc++.so.1 (0xf6c04000)
        libc++abi.so.1 => /usr/lib/libc++abi.so.1 (0xf6bcd000)
# file test_absl_64
test_absl_64: ELF 64-bit LSB executable, ARM aarch64, version 1
(SYSV), statically linked
# ldd test_gnu_32
        linux-vdso.so.1 (0xeabef000)
        libpthread.so.0 => /lib/libpthread.so.0 (0xeab92000)
        libc.so.6 => /lib/libc.so.6 (0xeaa9a000)
        /lib/ld-linux-armhf.so.3 (0x05690000)
# file test_gnu_64
test_gnu_64: ELF 64-bit LSB executable, ARM aarch64, version 1 (SYSV),
statically linked

### baseline 5.17-rc8

# perf record ./test_gnu_64 -t 4 -s $((200*1024*1024)) -S 6000000
10 records/s
real 59.00 s
user 39.83 s
sys  174.18 s

    18.51%  [.] memcpy
    15.98%  [k] __pi_clear_page
     5.59%  [k] rmqueue_pcplist
     5.19%  [k] do_raw_spin_lock
     5.09%  [k] memmove
     4.60%  [k] _raw_spin_unlock_irq
     3.62%  [k] _raw_spin_unlock_irqrestore
     3.61%  [k] free_unref_page_list
     3.29%  [k] zap_pte_range
     2.53%  [k] local_daif_restore
     2.50%  [k] down_read_trylock
     1.41%  [k] handle_mm_fault
     1.32%  [k] do_anonymous_page
     1.31%  [k] up_read
     1.03%  [k] free_swap_cache

### MGLRU v9

# perf record ./test_gnu_64 -t 4 -s $((200*1024*1024)) -S 6000000
11 records/s
real 57.00 s
user 39.39 s

    19.36%  [.] memcpy
    16.50%  [k] __pi_clear_page
     6.21%  [k] memmove
     5.57%  [k] rmqueue_pcplist
     5.07%  [k] do_raw_spin_lock
     4.96%  [k] _raw_spin_unlock_irqrestore
     4.25%  [k] free_unref_page_list
     3.80%  [k] zap_pte_range
     3.69%  [k] _raw_spin_unlock_irq
     2.71%  [k] local_daif_restore
     2.10%  [k] down_read_trylock
     1.50%  [k] handle_mm_fault
     1.29%  [k] do_anonymous_page
     1.17%  [k] free_swap_cache
     1.08%  [k] up_read

[1] https://chromium.googlesource.com/chromiumos/platform/tast-tests/+/refs/heads/main/src/chromiumos/tast/local/memory/mempressure/mempressure.go
[2] https://developer.android.com/topic/performance/memory-overview

Powered by blists - more mailing lists