RFR: 8303215: Make thread stacks not use huge pages [v2]

[Thomas Stuefe]

On Thu, 25 May 2023 16:26:00 GMT, Poonam Bajaj <poonam at openjdk.org> wrote:

>> When a system has Transparent Huge Pages (THP) enabled (/sys/kernel/mm/transparent_hugepage/enabled is set to 'always'), thread stacks can have significantly more resident set size (RSS) than they actually require. This occurs when the stack size is 2MB or larger, which makes the memory range of the stack more likely to be aligned on a Large Page Size boundary (2MB on most systems). This in turn makes the stack eligible to be backed by transparent huge pages resulting in more memory consumption than it would otherwise when standard small pages are used. This issue is more apparent on AArch64 platforms where the default stack size is 2MB. 
>> 
>> 
>> Example mapping from smaps illustrating this issue:
>> fffced200000-fffced204000 ---p 00000000 00:00 0 
>> Size:                16 kB     # guard pages
>> KernelPageSize:       4 kB
>> MMUPageSize:          4 kB
>> ...
>> fffced204000-fffced400000 rw-p 00000000 00:00 0 
>> Size:              2032 kB    # stack space
>> KernelPageSize:       4 kB
>> MMUPageSize:          4 kB
>> Rss:               2032 kB    # entire stack resident in memory
>> 
>> 
>> This fix addresses this issue with the following two main changes:
>> 
>> 1. Change the default stack size to 2040KB, which is 2 pages less than 2MB. This ensures that stacks don't get 2MB aligned. And why 2 pages less than 2MB, because for non-JavaThreads, glibc adds an additional guard page to the total stack size. To keep it simple and to keep the default stack size value for  all options - ThreadStackSize, CompilerThreadStackSize, and VMThreadStackSize same, we use the default value as 2040K.
>> 
>> Example mapping for a JavaThread:
>> 
>> ffff6e913000-ffff6e917000 ---p 00000000 00:00 0 
>> Size:                 16 kB
>> KernelPageSize:        4 kB
>> MMUPageSize:           4 kB
>> ...
>> ffff6e917000-ffff6eb11000 rw-p 00000000 00:00 0 
>> Size:               2024 kB
>> KernelPageSize:        4 kB
>> MMUPageSize:           4 kB
>> Rss:                  92 kB
>> 
>> Example Mapping for a non-JavaThread (WatcherThread):
>> 
>> ffff6eb11000-ffff6eb12000 ---p 00000000 00:00 0 
>> Size:                  4 kB
>> KernelPageSize:        4 kB
>> MMUPageSize:           4 kB
>> ...
>> ffff6eb12000-ffff6ed10000 rw-p 00000000 00:00 0 
>> Size:               2040 kB
>> KernelPageSize:        4 kB
>> MMUPageSize:           4 kB
>> Rss:                  12 kB
>> 
>> 
>> 2. If the requested stack size is greater than or equal to the default large page size (2MB on most systems) and can be large-page aligned, then add an ...
>
> Poonam Bajaj has updated the pull request incrementally with one additional commit since the last revision:
> 
>   call scan_default_large_page_size() in the beginning of large_page_init()

Some small nits remain.

src/hotspot/os/linux/os_linux.cpp line 932:

> 930:   // Add an additional page to the stack size to reduce its chances of getting large page aligned
> 931:   // so that the stack does not get backed by a transparent huge page.
> 932:   if (stack_size >= os::Linux::_default_large_page_size && is_aligned(stack_size, os::Linux::_default_large_page_size)) {

Could you use `os::Linux::default_large_page_size()` instead of accessing the private member directly?

src/hotspot/os/linux/os_linux.cpp line 3628:

> 3626: static size_t _large_page_size = 0;
> 3627: 
> 3628: size_t os::Linux::scan_default_large_page_size() {

I think this is not needed anymore, or? You can revert this back to a local static function, and call that in `os::large_page_init()`

src/hotspot/os_cpu/linux_aarch64/globals_linux_aarch64.hpp line 33:

> 31: 
> 32: define_pd_global(bool, DontYieldALot,            false);
> 33: define_pd_global(intx, ThreadStackSize,          2040); // 0 => use system default

A comment would be good here to explain the odd size

-------------

Changes requested by stuefe (Reviewer).

PR Review: https://git.openjdk.org/jdk/pull/14105#pullrequestreview-1444429076
PR Review Comment: https://git.openjdk.org/jdk/pull/14105#discussion_r1205865548
PR Review Comment: https://git.openjdk.org/jdk/pull/14105#discussion_r1205867752
PR Review Comment: https://git.openjdk.org/jdk/pull/14105#discussion_r1205869074