Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753215AbbGMU2b (ORCPT ); Mon, 13 Jul 2015 16:28:31 -0400 Received: from mail-wg0-f45.google.com ([74.125.82.45]:36265 "EHLO mail-wg0-f45.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753040AbbGMU23 (ORCPT ); Mon, 13 Jul 2015 16:28:29 -0400 From: Ebru Akagunduz To: linux-mm@kvack.org Cc: akpm@linux-foundation.org, kirill.shutemov@linux.intel.com, n-horiguchi@ah.jp.nec.com, aarcange@redhat.com, riel@redhat.com, iamjoonsoo.kim@lge.com, xiexiuqi@huawei.com, gorcunov@openvz.org, linux-kernel@vger.kernel.org, mgorman@suse.de, rientjes@google.com, vbabka@suse.cz, aneesh.kumar@linux.vnet.ibm.com, hughd@google.com, hannes@cmpxchg.org, mhocko@suse.cz, boaz@plexistor.com, raindel@mellanox.com, Ebru Akagunduz Subject: [RFC v3 3/3] mm: make swapin readahead to improve thp collapse rate Date: Mon, 13 Jul 2015 23:28:04 +0300 Message-Id: <1436819284-3964-4-git-send-email-ebru.akagunduz@gmail.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1436819284-3964-1-git-send-email-ebru.akagunduz@gmail.com> References: <1436819284-3964-1-git-send-email-ebru.akagunduz@gmail.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6248 Lines: 188 This patch makes swapin readahead to improve thp collapse rate. When khugepaged scanned pages, there can be a few of the pages in swap area. With the patch THP can collapse 4kB pages into a THP when there are up to max_ptes_swap swap ptes in a 2MB range. The patch was tested with a test program that allocates 800MB of memory, writes to it, and then sleeps. I force the system to swap out all. Afterwards, the test program touches the area by writing, it skips a page in each 20 pages of the area. Without the patch, system did not swap in readahead. THP rate was %47 of the program of the memory, it did not change over time. With this patch, after 10 minutes of waiting khugepaged had collapsed %99 of the program's memory. Signed-off-by: Ebru Akagunduz Acked-by: Rik van Riel --- Changes in v2: - Use FAULT_FLAG_ALLOW_RETRY|FAULT_FLAG_RETRY_NOWAIT flag instead of 0x0 when called do_swap_page from __collapse_huge_page_swapin (Rik van Riel) Changes in v3: - Catch VM_FAULT_HWPOISON and VM_FAULT_OOM return cases in __collapse_huge_page_swapin (Kirill A. Shutemov) Test results: After swapped out ------------------------------------------------------------------- | Anonymous | AnonHugePages | Swap | Fraction | ------------------------------------------------------------------- With patch | 267128 kB | 266240 kB | 532876 kB | %99 | ------------------------------------------------------------------- Without patch | 238160 kB | 235520 kB | 561844 kB | %98 | ------------------------------------------------------------------- After swapped in ------------------------------------------------------------------- | Anonymous | AnonHugePages | Swap | Fraction | ------------------------------------------------------------------- With patch | 533876 kB | 530432 kB | 266128 kB | %99 | ------------------------------------------------------------------- Without patch | 499956 kB | 235520 kB | 300048 kB | %47 | ------------------------------------------------------------------- include/linux/mm.h | 4 ++++ include/trace/events/huge_memory.h | 24 ++++++++++++++++++++++ mm/huge_memory.c | 41 ++++++++++++++++++++++++++++++++++++++ mm/memory.c | 2 +- 4 files changed, 70 insertions(+), 1 deletion(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index eacf348..603f3ba 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -40,6 +40,10 @@ #define MM_COLLAPSE_ISOLATE_FAIL 5 #define MM_EXCEED_SWAP_PTE 2 +extern int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + unsigned int flags, pte_t orig_pte); + struct mempolicy; struct anon_vma; struct anon_vma_chain; diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index b6bdcc4..8d34086 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -98,6 +98,30 @@ TRACE_EVENT(mm_collapse_huge_page_isolate, __entry->ret) ); +TRACE_EVENT(mm_collapse_huge_page_swapin, + + TP_PROTO(struct mm_struct *mm, int swap_pte, int ret), + + TP_ARGS(mm, swap_pte, ret), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __field(int, swap_pte) + __field(int, ret) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->swap_pte = swap_pte; + __entry->ret = ret; + ), + + TP_printk("mm=%p, swap_pte=%d, ret=%d", + __entry->mm, + __entry->swap_pte, + __entry->ret) +); + #endif /* __HUGE_MEMORY_H */ #include diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b4cef9d..b372b40 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2511,6 +2511,45 @@ static bool hugepage_vma_check(struct vm_area_struct *vma) return true; } +/* + * Bring missing pages in from swap, to complete THP collapse. + * Only done if khugepaged_scan_pmd believes it is worthwhile. + * + * Called and returns without pte mapped or spinlocks held, + * but with mmap_sem held to protect against vma changes. + */ + +static void __collapse_huge_page_swapin(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pte_t *pte) +{ + unsigned long _address; + pte_t pteval = *pte; + int swap_pte = 0, ret = 0; + + pte = pte_offset_map(pmd, address); + for (_address = address; _address < address + HPAGE_PMD_NR*PAGE_SIZE; + pte++, _address += PAGE_SIZE) { + pteval = *pte; + if (is_swap_pte(pteval)) { + swap_pte++; + ret = do_swap_page(mm, vma, _address, pte, pmd, + FAULT_FLAG_ALLOW_RETRY|FAULT_FLAG_RETRY_NOWAIT, + pteval); + if (ret == VM_FAULT_HWPOISON || ret == VM_FAULT_OOM) { + trace_mm_collapse_huge_page_swapin(mm, vma->vm_start, swap_pte, 0); + return; + } + /* pte is unmapped now, we need to map it */ + pte = pte_offset_map(pmd, _address); + } + } + pte--; + pte_unmap(pte); + trace_mm_collapse_huge_page_swapin(mm, swap_pte, 1); +} + static void collapse_huge_page(struct mm_struct *mm, unsigned long address, struct page **hpage, @@ -2584,6 +2623,8 @@ static void collapse_huge_page(struct mm_struct *mm, anon_vma_lock_write(vma->anon_vma); + __collapse_huge_page_swapin(mm, vma, address, pmd, pte); + pte = pte_offset_map(pmd, address); pte_ptl = pte_lockptr(mm, pmd); diff --git a/mm/memory.c b/mm/memory.c index 67afe75..eec23a2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2443,7 +2443,7 @@ EXPORT_SYMBOL(unmap_mapping_range); * We return with the mmap_sem locked or unlocked in the same cases * as does filemap_fault(). */ -static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, +int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, unsigned int flags, pte_t orig_pte) { -- 1.9.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/