From nobody Fri Oct 3 12:14:51 2025 Received: from baidu.com (mx24.baidu.com [111.206.215.185]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id E65042F0C41 for ; Mon, 1 Sep 2025 08:21:46 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=111.206.215.185 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1756714910; cv=none; b=LgWEcjAtQjM2SYdLwuL3QxuAwI6suijQ4sxp+qXNHEtNMW4mcMpOpmabAbcODk0b+FXIihTnP80pH1JR4+1hMOAS5/WrOT7SNnNBKs93XYOccngX3SfMl/okuAxeIH4pVZHKJQthGM337Rmyh4xNxJrCpe7CDb0aGFl9dEhqjl4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1756714910; c=relaxed/simple; bh=CZOS5QghR7MNWOh6P8RwRJdeHu9mu31HNR7Pe+f02Cw=; h=From:To:CC:Subject:Date:Message-ID:MIME-Version:Content-Type; b=A+zYoFDr5hSYIjE16G+FgKSEEBmRAqjS3PXunygyah1GeXiQ+AFj2sUfwarzYKegP0WjgB1sBdYxoMdR753H9gIOR3YTC8GW1XLDJqoV38J0h+gCsWG2a6ccUXeUvd5mpPqGnv5IhP2JadWS6HROdwHkPxCEVQE5kfNMzeiqdXU= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=baidu.com; spf=pass smtp.mailfrom=baidu.com; arc=none smtp.client-ip=111.206.215.185 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=baidu.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=baidu.com From: lirongqing To: , , , , , , CC: Li RongQing Subject: [PATCH][v4] mm/hugetlb: retry to allocate for early boot hugepage allocation Date: Mon, 1 Sep 2025 16:20:52 +0800 Message-ID: <20250901082052.3247-1-lirongqing@baidu.com> X-Mailer: git-send-email 2.17.1 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-ClientProxiedBy: bjkjy-exc4.internal.baidu.com (172.31.50.48) To bjkjy-exc3.internal.baidu.com (172.31.50.47) X-FEAS-Client-IP: 172.31.50.47 X-FE-Policy-ID: 52:10:53:SYSTEM Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Li RongQing In cloud environments with massive hugepage reservations (95%+ of system RAM), single-attempt allocation during early boot often fails due to memory pressure. Commit 91f386bf0772 ("hugetlb: batch freeing of vmemmap pages") intensified this by deferring page frees, increase peak memory usage during allocation. Introduce a retry mechanism that leverages vmemmap optimization reclaim (~1.6% memory) when available. Upon initial allocation failure, the system retries until successful or no further progress is made, ensuring reliable hugepage allocation while preserving batched vmemmap freeing benefits. Testing on a 256G machine allocating 252G of hugepages: Before: 128056/129024 hugepages allocated After: Successfully allocated all 129024 hugepages Suggested-by: David Hildenbrand Signed-off-by: Li RongQing Acked-by: David Hildenbrand --- Diff with v3: rewrite comment Diff with v2: auto retry mechanism Diff with v1: add log if two-phase hugepage allocation is triggered add the knod to control split ratio mm/hugetlb.c | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 753f99b..af7c36f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3589,10 +3589,9 @@ static unsigned long __init hugetlb_pages_alloc_boot= (struct hstate *h) =20 unsigned long jiffies_start; unsigned long jiffies_end; + unsigned long remaining; =20 job.thread_fn =3D hugetlb_pages_alloc_boot_node; - job.start =3D 0; - job.size =3D h->max_huge_pages; =20 /* * job.max_threads is 25% of the available cpu threads by default. @@ -3616,10 +3615,29 @@ static unsigned long __init hugetlb_pages_alloc_boo= t(struct hstate *h) } =20 job.max_threads =3D hugepage_allocation_threads; - job.min_chunk =3D h->max_huge_pages / hugepage_allocation_threads; =20 jiffies_start =3D jiffies; - padata_do_multithreaded(&job); + do { + remaining =3D h->max_huge_pages - h->nr_huge_pages; + + job.start =3D h->nr_huge_pages; + job.size =3D remaining; + job.min_chunk =3D remaining / hugepage_allocation_threads; + padata_do_multithreaded(&job); + + if (h->nr_huge_pages =3D=3D h->max_huge_pages) + break; + + /* + * Retry only if the vmemmap optimization might have been able to free + * some memory back to the system. + */ + if (!hugetlb_vmemmap_optimizable(h)) + break; + + /* Continue if progress was made in last iteration */ + } while (remaining !=3D (h->max_huge_pages - h->nr_huge_pages)); + jiffies_end =3D jiffies; =20 pr_info("HugeTLB: allocation took %dms with hugepage_allocation_threads= =3D%ld\n", --=20 2.9.4