[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <5d1631e0-22a7-a310-8078-75b9088164ce@intel.com>
Date: Thu, 15 Jun 2023 16:33:09 +0800
From: "Yin, Fengwei" <fengwei.yin@...el.com>
To: "Liam R. Howlett" <Liam.Howlett@...cle.com>,
Andrew Morton <akpm@...ux-foundation.org>
CC: <maple-tree@...ts.infradead.org>, <linux-mm@...ck.org>,
<linux-kernel@...r.kernel.org>,
Peng Zhang <zhangpeng.00@...edance.com>
Subject: Re: [PATCH v2 00/16] Reduce preallocations for maple tree
Hi Liam,
On 6/13/2023 4:39 AM, Liam R. Howlett wrote:
> Initial work on preallocations showed no regression in performance
> during testing, but recently some users (both on [1] and off [android]
> list) have reported that preallocating the worst-case number of nodes
> has caused some slow down. This patch set addresses the number of
> allocations in a few ways.
>
> During munmap() most munmap() operations will remove a single VMA, so
> leverage the fact that the maple tree can place a single pointer at
> range 0 - 0 without allocating. This is done by changing the index in
> the 'sidetree'.
>
> Re-introduce the entry argument to mas_preallocate() so that a more
> intelligent guess of the node count can be made.
>
> During development of v2 of this patch set, I also noticed that the
> number of nodes being allocated for a rebalance was beyond what could
> possibly be needed. This is addressed in patch 0008.
>
> Patches are in the following order:
> 0001-0002: Testing framework for benchmarking some operations
> 0003-0004: Reduction of maple node allocation in sidetree
> 0005: Small cleanup of do_vmi_align_munmap()
> 0006-0015: mas_preallocate() calculation change
> 0016: Change the vma iterator order
>
> Changes since v1:
> - Reduced preallocations for append and slot store - Thanks Peng Zhang
> - Added patch to reduce node allocations for mas_rebalance() (patch 0008)
> - Reduced resets during store setup to avoid duplicate walking (patch 0015)
AIM9.page_test in my local env:
before-preallocation: 763812
preallocation: 676600
preallocation fixup v2 (this patchset: 734060
For this specific test, the v2 patch works perfectly. Thanks.
Regards
Yin, Fengwei
>
> v1: https://lore.kernel.org/lkml/20230601021605.2823123-1-Liam.Howlett@oracle.com/
>
> [1] https://lore.kernel.org/linux-mm/202305061457.ac15990c-yujie.liu@intel.com/
>
> Liam R. Howlett (16):
> maple_tree: Add benchmarking for mas_for_each
> maple_tree: Add benchmarking for mas_prev()
> mm: Move unmap_vmas() declaration to internal header
> mm: Change do_vmi_align_munmap() side tree index
> mm: Remove prev check from do_vmi_align_munmap()
> maple_tree: Introduce __mas_set_range()
> mm: Remove re-walk from mmap_region()
> maple_tree: Adjust node allocation on mas_rebalance()
> maple_tree: Re-introduce entry to mas_preallocate() arguments
> mm: Use vma_iter_clear_gfp() in nommu
> mm: Set up vma iterator for vma_iter_prealloc() calls
> maple_tree: Move mas_wr_end_piv() below mas_wr_extend_null()
> maple_tree: Update mas_preallocate() testing
> maple_tree: Refine mas_preallocate() node calculations
> maple_tree: Reduce resets during store setup
> mm/mmap: Change vma iteration order in do_vmi_align_munmap()
>
> fs/exec.c | 1 +
> include/linux/maple_tree.h | 23 ++++-
> include/linux/mm.h | 4 -
> lib/maple_tree.c | 121 ++++++++++++++++------
> lib/test_maple_tree.c | 74 +++++++++++++
> mm/internal.h | 40 ++++++--
> mm/memory.c | 19 ++--
> mm/mmap.c | 171 ++++++++++++++++---------------
> mm/nommu.c | 45 ++++----
> tools/testing/radix-tree/maple.c | 59 ++++++-----
> 10 files changed, 364 insertions(+), 193 deletions(-)
>
Powered by blists - more mailing lists