Messages in this thread | | | Subject | Re: [RESEND PATCH v4 00/10] Rework REFCOUNT_FULL using atomic_fetch_* operations | From | Hanjun Guo <> | Date | Fri, 22 Nov 2019 11:44:55 +0800 |
| |
On 2019/11/21 19:58, Will Deacon wrote: > Hi everybody, > > This is a resend of version four of the patches I posted here: > > v4: https://lore.kernel.org/lkml/20191030143035.19440-1-will@kernel.org > > Previous versions can be found at: > > v1: https://lkml.kernel.org/r/20190802101000.12958-1-will@kernel.org > v2: https://lkml.kernel.org/r/20190827163204.29903-1-will@kernel.org > v3: https://lkml.kernel.org/r/20191007154703.5574-1-will@kernel.org > > I didn't receive any feedback last time around, other than some positive > noises from Kees, so please consider this for inclusion in mainline.
This time I tested this patch set on both ARM64 and x86 server, against 5.4-rc8.
On ARM64, similar test case and the similar performance improvement.
On X86, I tested on a 24 cores Xeon(R) CPU E5-2620, with kernel compile (make -j) for test case, and no issue was found.
Tested-by: Hanjun Guo <guohanjun@huawei.com>
Thanks Hanjun
| |