From: Yang Xu <xuyang2018.jy@cn.fujitsu.com>
To: ltp@lists.linux.it
Subject: [LTP] [PATCH v1 2/3] syscalls/mallinfo02: Add a basic test to check use mmap or sbrk
Date: Wed, 3 Feb 2021 18:46:15 +0800 [thread overview]
Message-ID: <601A7EF7.2070603@cn.fujitsu.com> (raw)
In-Reply-To: <601A713F.7020301@cn.fujitsu.com>
Hi Cyril
> Hi Cyril
>> Hi!
>>> "The number of bytes in blocks currently allocated using mmap(2).".
>>> For allocations greater than or equal to 128K and that can't be
>>> satisfied from
>>> the free list, the memory-allocation functions employ mmap(2) instead
>>> of increasing
>>> the program break using sbrk(2).
>>>
>>> In this case, we test 20k size to use sbrk and 128k size to use mmap.
>>
>> The size when glibc uses mmap() instead of heap is libc implementation
>> detail. I'm not sure that we want to have that value hardcoded in a
>> LTP test.
> Here has some wrong description, I use "MAX(info.fordblks, 131072) +
> reuse_size" size to test instead of 128K.
>>
>> Also glibc documentation says:
>>
>> The default value is set to `131072' bytes and the threshold is adjusted
>> dynamically to suit the allocation patterns of the program.
>
> IMO, the threshold is adjusted dynamically because of two things if we
> don't use mallopt with M_MMAP_THRESHOLD
> 1) fordblks; /* Total free space (bytes) */
> 2) the previous mmap regin space
>
>
> From mallopt man-page for M_MMAP_THRESHOLD option, it said
> " For allocations greater than or equal to the limit specified (in
> bytes) by M_MMAP_THRESHOLD that can't be satisfied from the free list,
> the memory-allocation functions employ mmap(2) instead of increasing the
> program break using sbrk(2)."
>
> So I use this code "MAX(info.fordblks, 131072)" to get the right value
> to trigger mmap.
>
> mallopt man-page for M_MMAP_THRESHOLD option also said "On the
> other hand, there are some disadvantages to the use of mmap(2):
> deallocated space is not placed on the free list for reuse by later
> allocations; " .
>
> I guess it means mmap area is not counted int info.fordblks(free list )
> and can be used for the next sbrk(increase the heap). That is why I add
> reuse_size when I get the corrcet mmap size. Or, I miss something?
>
> If we can't ensure it , I will remove this patch. Or, other advise?
For glibc malloc mmap dynamic threshhold , here[1] has a detailed
description.
[1]https://sourceware.org/git/?p=glibc.git;a=blob;f=malloc/malloc.c;h=1f4bbd8edf8b97701b779f183475565c7d0a6762;hb=d5c8f98c5e6de207790d3e9edadf5bda4aa2521f#l1043
>
>
> Best Regards
> Yang Xu
>
>>
>
>
>
>
next prev parent reply other threads:[~2021-02-03 10:46 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-26 9:55 [LTP] [PATCH v1 1/3] syscalls/mallinfo01: Add a basic test for mallinfo Yang Xu
2021-01-26 9:55 ` [LTP] [PATCH v1 2/3] syscalls/mallinfo02: Add a basic test to check use mmap or sbrk Yang Xu
2021-01-28 15:37 ` Cyril Hrubis
2021-02-03 9:47 ` Yang Xu
2021-02-03 10:46 ` Yang Xu [this message]
2021-02-04 6:08 ` Li Wang
2021-02-04 9:53 ` Yang Xu
2021-01-26 9:55 ` [LTP] [PATCH v1 3/3] syscalls/mallinfo03: Add an overflow test when setting 2G size Yang Xu
2021-01-28 15:42 ` Cyril Hrubis
2021-02-03 9:49 ` Yang Xu
2021-02-04 8:54 ` Li Wang
2021-02-04 10:01 ` Yang Xu
2021-02-04 13:56 ` Li Wang
2021-02-04 12:12 ` [LTP] [PATCH v2 1/5] tst_mallinfo.c: Add a common print helper for mallinfo Yang Xu
2021-02-04 12:12 ` [LTP] [PATCH v2 2/5] syscalls/mallopt01: Use tst_print_mallinfo api Yang Xu
2021-02-04 12:12 ` [LTP] [PATCH v2 3/5] syscalls/mallinfo01: Add a basic test for mallinfo Yang Xu
2021-02-04 12:12 ` [LTP] [PATCH v2 4/5] syscalls/mallinfo02: Add a basic test to check use mmap or sbrk Yang Xu
2021-02-04 13:51 ` Li Wang
2021-02-05 7:51 ` Yang Xu
2021-02-05 8:15 ` Yang Xu
2021-02-05 9:00 ` Yang Xu
2021-02-05 9:20 ` Li Wang
2021-02-04 12:12 ` [LTP] [PATCH v2 5/5] syscalls/mallinfo03: Add an overflow test when setting 2G size Yang Xu
2021-02-04 13:29 ` [LTP] [PATCH v2 1/5] tst_mallinfo.c: Add a common print helper for mallinfo Li Wang
2021-02-05 7:44 ` Yang Xu
2021-02-05 8:00 ` Li Wang
2021-02-05 11:21 ` Petr Vorel
2021-02-08 15:30 ` Cyril Hrubis
2021-02-18 5:52 ` [LTP] [PATCH v3 1/4] syscalls/mallinfo01: Add a basic test " Yang Xu
2021-02-18 5:52 ` [LTP] [PATCH v3 2/4] syscalls/mallopt01: Use unified print_mallinfo api Yang Xu
2021-02-18 5:52 ` [LTP] [PATCH v3 3/4] syscalls/mallinfo02: Add a basic test to check use mmap or sbrk Yang Xu
2021-02-22 6:32 ` Li Wang
2021-02-22 6:40 ` Yang Xu
2021-02-23 1:45 ` Yang Xu
2021-02-18 5:52 ` [LTP] [PATCH v3 4/4] syscalls/mallinfo03: Add an overflow test when setting 2G size Yang Xu
2021-01-28 15:50 ` [LTP] [PATCH v1 1/3] syscalls/mallinfo01: Add a basic test for mallinfo Cyril Hrubis
2021-02-03 6:03 ` Yang Xu
2021-02-04 6:42 ` Li Wang
2021-02-04 9:54 ` Yang Xu
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=601A7EF7.2070603@cn.fujitsu.com \
--to=xuyang2018.jy@cn.fujitsu.com \
--cc=ltp@lists.linux.it \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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.