Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753290AbbFNPFV (ORCPT ); Sun, 14 Jun 2015 11:05:21 -0400 Received: from mail-wi0-f170.google.com ([209.85.212.170]:33576 "EHLO mail-wi0-f170.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753136AbbFNPFG (ORCPT ); Sun, 14 Jun 2015 11:05:06 -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 2/3] mm: make optimistic check for swapin readahead Date: Sun, 14 Jun 2015 18:04:42 +0300 Message-Id: <1434294283-8699-3-git-send-email-ebru.akagunduz@gmail.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1434294283-8699-1-git-send-email-ebru.akagunduz@gmail.com> References: <1434294283-8699-1-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: 3785 Lines: 112 This patch makes optimistic check for swapin readahead to increase thp collapse rate. Before getting swapped out pages to memory, checks them and allows up to a certain number. It also prints out using tracepoints amount of unmapped ptes. Signed-off-by: Ebru Akagunduz --- include/trace/events/huge_memory.h | 11 +++++++---- mm/huge_memory.c | 13 ++++++++++--- 2 files changed, 17 insertions(+), 7 deletions(-) diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 4b9049b..53c9f2e 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -9,9 +9,9 @@ TRACE_EVENT(mm_khugepaged_scan_pmd, TP_PROTO(struct mm_struct *mm, unsigned long vm_start, bool writable, - bool referenced, int none_or_zero, int collapse), + bool referenced, int none_or_zero, int collapse, int unmapped), - TP_ARGS(mm, vm_start, writable, referenced, none_or_zero, collapse), + TP_ARGS(mm, vm_start, writable, referenced, none_or_zero, collapse, unmapped), TP_STRUCT__entry( __field(struct mm_struct *, mm) @@ -20,6 +20,7 @@ TRACE_EVENT(mm_khugepaged_scan_pmd, __field(bool, referenced) __field(int, none_or_zero) __field(int, collapse) + __field(int, unmapped) ), TP_fast_assign( @@ -29,15 +30,17 @@ TRACE_EVENT(mm_khugepaged_scan_pmd, __entry->referenced = referenced; __entry->none_or_zero = none_or_zero; __entry->collapse = collapse; + __entry->unmapped = unmapped; ), - TP_printk("mm=%p, vm_start=%04lx, writable=%d, referenced=%d, none_or_zero=%d, collapse=%d", + TP_printk("mm=%p, vm_start=%04lx, writable=%d, referenced=%d, none_or_zero=%d, collapse=%d, unmapped=%d", __entry->mm, __entry->vm_start, __entry->writable, __entry->referenced, __entry->none_or_zero, - __entry->collapse) + __entry->collapse, + __entry->unmapped) ); TRACE_EVENT(mm_collapse_huge_page, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9bb97fc..22bc0bf 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -2639,11 +2640,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, { pmd_t *pmd; pte_t *pte, *_pte; - int ret = 0, none_or_zero = 0; + int ret = 0, none_or_zero = 0, unmapped = 0; struct page *page; unsigned long _address; spinlock_t *ptl; - int node = NUMA_NO_NODE; + int node = NUMA_NO_NODE, max_ptes_swap = HPAGE_PMD_NR/8; bool writable = false, referenced = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); @@ -2657,6 +2658,12 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = *_pte; + if (is_swap_pte(pteval)) { + if (++unmapped <= max_ptes_swap) + continue; + else + goto out_unmap; + } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { if (!userfaultfd_armed(vma) && ++none_or_zero <= khugepaged_max_ptes_none) @@ -2701,7 +2708,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, out_unmap: pte_unmap_unlock(pte, ptl); trace_mm_khugepaged_scan_pmd(mm, vma->vm_start, writable, referenced, - none_or_zero, ret); + none_or_zero, ret, unmapped); if (ret) { node = khugepaged_find_target_node(); /* collapse_huge_page will return with the mmap_sem released */ -- 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/