Re: [PATCH v9 0/8] mm: optimize zone-device memmap initialization
"Li Zhe" <[email protected]> Wed, 5 Aug 2026 17:49:22 +0800
| Newsgroups | org.kernel.vger.linux-arch,org.kernel.vger.linux-hardening,org.kernel.vger.linux-kernel,org.kvack.linux-mm |
|---|---|
| Message-ID | <[email protected]> |
On 8/4/26 5:40 AM, Andrew Morton wrote: > On Mon, 3 Aug 2026 15:09:21 +0800 "Li Zhe" <[email protected]> wrote: > >> Test procedure: >> Rebind the nd_pmem and dax_pmem drivers 30 times and collect the memmap >> initialization time from the pr_debug() output of >> memmap_init_zone_device(). >> >> Base(v7.2-rc1): >> Average of nd_pmem rebinds: 244.28 ms >> Average of dax_pmem rebinds: 273.31 ms >> >> With this series applied: >> Average of nd_pmem rebinds: 96.79 ms >> Average of dax_pmem rebinds: 119.04 ms >> >> This reduces the average memmap initialization time measured during >> rebind by about 60.4% for nd_pmem and 56.4% for dax_pmem. > Well that's nice. > > Review is partial and it's late in the cycle so I'd prefer to schedule > this for the next -rc cycle. > > AI review might have found a couple of things, please check? > https://sashiko.dev/#/patchset/[email protected] Thanks. I checked the Sashiko comments. The reported items are the same points that were discussed in the previous v7/v8 reviews. v9 already folds the related explanation into patch 7, so I do not plan any additional code change for these items. Thanks, Zhe