On Thu, 25 Jun 2026 10:22:22 GMT, Per Minborg <[email protected]> wrote:

>> ## Summary
>> 
>> This PR proposes to introduce a pooled confined arena as an optimization for 
>> `Arena.ofConfined()`, where small native allocations can be served from a 
>> reusable per-thread/per-slot memory pool instead of calling the regular 
>> native allocator for every short-lived arena. The arena remains confined to 
>> its owner thread and is still closed normally, but its backing storage can 
>> be reset and reused when the arena closes. The feature requires no API 
>> changes.
>> 
>> ### Outline
>> 
>> Platform threads: There are up to four lazily allocated pools per Thread, 
>> encoded in `Thread.confinedMemoryPool`.
>> Virtual threads: fixed shared native pool with CAS-protected slots, because 
>> per-virtual-thread native pools would not scale.
>> 
>> Pooled memory is zeroed out upon _closing_ an Arena to minimize data 
>> visibility between reuse. This means the data is visible only within a TWR 
>> block, and never outside it.
>> 
>> By default, a confined arena has access to four pools, each of size 64 
>> bytes.  The pool sizes are configurable via a system property and can be 8, 
>> 16, 32, or 64 bytes. Pooling can also be turned off completely by setting 
>> the pool power-of-two size to zero. As there can be up to four pools per 
>> thread, nested confined arenas are supported (i.e., up to four nested 
>> arenas).
>> 
>> ## Static Analysis
>> 
>> An extensive static corpus analysis of third-party libraries and the JDK 
>> itself has been conducted with respect to `Area.ofConfined()` usage, 
>> revealing that confined arenas were used _only_ in TWR blocks and _never_ in 
>> an unstructured way. The static analysis further revealed that in most 
>> cases, only a small amount of native memory was ever allocated, usually less 
>> than 32 bytes, and in many cases, 8 bytes or less. This usage pattern lends 
>> itself well to pooling. 
>> 
>> ## Dynamic Analysis
>> 
>> A dynamic statistical analysis of actual runs was also made, where various 
>> properties of confined arenas were recorded and summarized during a complete 
>> tier1 test run. While a tier1 run is not necessarily representative of a 
>> typical application workload, it provided some interesting results:
>> 
>> The run produced 93 per-process histogram blocks and 788,773,092 closed 
>> confined arenas. The result is dominated by arenas with no native allocation 
>> at all: 375,934,768 arenas (47.661%) are in the zero-byte bucket. Counting 
>> arenas up to 63 bytes covers 99.997% of all arena closures.
>> 
>> The largest count bucket is 8-15 bytes per arena with 400,951,293 arenas 
>> (50.832% of all arenas...
>
> Per Minborg has updated the pull request incrementally with two additional 
> commits since the last revision:
> 
>  - Add local pools
>  - Add 4 nested levels

I skimmed through the design and it looks reasonable. The data/analysis to give 
an insight into pool to cache and their size is good analysis. 4 

(Maybe in the future we can look at the NIO thread-local buffer cache to see if 
it could use a confined arena. It differs to what you have here in that it may 
cache large buffers (8k or 16k is typically for networking I/O) and a larger 
number to deal with scatter/gathers ops with I/O with a large number of 
buffers.)

Hanging the cache off of Thread.FieldHolder for platform threads is good. 
Interestingly, and if I read the code correctly, if some accidentally forgets 
to close a confined arena before thread exit then the memory will be released 
if the arena came from the cache.

Using a shared pool for virtual threads make sense, I was a bit concerned with 
the early versions that put the cached pools into every Thread. Allocating a 
pool based on ncores*2 is probably okay, I assume time will tell if any 
contention will be observable.

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

PR Comment: https://git.openjdk.org/jdk/pull/31365#issuecomment-4885614764

Reply via email to