mirror of
https://github.com/gatieme/LDD-LinuxDeviceDrivers.git
synced 2026-08-20 22:04:56 +08:00
description/memory: page cache
This commit is contained in:
Cheng Jian
@@ -325,7 +325,7 @@ TLB entry shootdown 常常或多或少的带来一些性能问题.
|
||||
| 2020/11/03 | Nianyao Tang <tangnianyao@huawei.com> | [KVM: arm64: Don't force broadcast tlbi when guest is running](https://lists.cs.columbia.edu/pipermail/kvmarm/2020-November/043071.html) | KVM 当 guest 在运行的时候, 避免 tlbi 广播. | RFC v1 ☐ | [Patchwork RTC](https://lore.kernel.org/linux-arm-kernel/1603331829-33879-1-git-send-email-zhangshaokun@hisilicon.com) |
|
||||
| 2019/06/17 | Takao Indoh <indou.takao@jp.fujitsu.com> | [arm64: Introduce boot parameter to disable TLB flush instruction within the same inner shareable domain](hhttps://lists.cs.columbia.edu/pipermail/kvmarm/2020-November/043071.html) | 富士通的开发人员发现 ARM64 TLB.IS 广播在 HPC 上造成了严重的性能下降, 因此新增一个 disable_tlbflush_is 参数来禁用 TLB.IS 广播, 使用原始的 TLB IPI 方式. | RFC v1 ☐ | [Patchwork 0/2](https://patchwork.kernel.org/project/linux-arm-kernel/cover/20190617143255.10462-1-indou.takao@jp.fujitsu.com), [LORE](https://lore.kernel.org/linux-arm-kernel/20190617143255.10462-1-indou.takao@jp.fujitsu.com) |
|
||||
| 2016/10/24 | Marc Zyngier <marc.zyngier@arm.com> | [arm/arm64: KVM: Perform local TLB invalidation when multiplexing vcpus on a single CPU](https://patchwork.kernel.org/project/kvm/patch/1477323088-18768-1-git-send-email-marc.zyngier@arm.com) | KVM 当 guest 在运行的时候, 避免 tlbi 广播. | RFC v1 ☐ | [Patchwork RTC](https://lore.kernel.org/linux-arm-kernel/1603331829-33879-1-git-send-email-zhangshaokun@hisilicon.com) |
|
||||
|
||||
| 2020/02/23 | Andrea Arcangeli <aarcange@redhat.com> | [arm64: tlb: skip tlbi broadcast v2](https://lore.kernel.org/all/20200223192520.20808-1-aarcange@redhat.com) |20200223192520.20808-1-aarcange@redhat.com | v1 ☐ | [LORE](https://lore.kernel.org/all/20200223192520.20808-1-aarcange@redhat.com) |
|
||||
|
||||
> 注: x86 由于没有 tlb IS 方案, 因此只能采用 IPI 的方式来完成 TLB shootdown.
|
||||
|
||||
|
||||
@@ -530,6 +530,16 @@ https://patchwork.kernel.org/project/linux-trace-devel/list/?submitter=200911&st
|
||||
|:----:|:----:|:---:|:----:|:---------:|:----:|
|
||||
| 2021/11/09 | Sai Prakash Ranjan <quic_saipraka@quicinc.com> | [tracing/rwmmio/arm64: Add support to trace register reads/writes](https://patchwork.kernel.org/project/linux-arm-kernel/cover/cover.1636452784.git.quic_saipraka@quicinc.com) | MMIO register read/write tracing. | v3 ☐ | [Patchwork v3,0/3](https://patchwork.kernel.org/project/linux-arm-kernel/cover/cover.1636452784.git.quic_saipraka@quicinc.com) |
|
||||
|
||||
## 14.7 ftrace_direct
|
||||
-------
|
||||
|
||||
| 时间 | 作者 | 特性 | 描述 | 是否合入主线 | 链接 |
|
||||
|:----:|:----:|:---:|:----:|:---------:|:----:|
|
||||
| 2019/11/8 | Steven Rostedt | [ftrace: Add register_ftrace_direct()](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?id=a3ad1a7e39689005cb04a4f2adb82f9d55b4724f) | 1615872606-56087-1-git-send-email-aubrey.li@intel.com | v1 ☑✓ 5.5-rc1 | [LORE 00/10](https://lkml.org/lkml/headers/2019/11/8/1675) |
|
||||
| 2019/08/27 | Peter Zijlstra <peterz@infradead.org> | [Rewrite x86/ftrace to use text_poke()](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?id=768ae4406a5cab7e8702550f2446dbeb377b798d) | 615872606-56087-1-git-send-email-aubrey.li@intel.com | v3 ☑✓ 5.6-rc1 | [LORE v3,0/3](https://lore.kernel.org/all/20190827180622.159326993@infradead.org) |
|
||||
| 2021/06/05 | Jiri Olsa <jolsa@kernel.org> | [x86/ftrace/bpf: Add batch support for direct/tracing attach](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?id=a3ad1a7e39689005cb04a4f2adb82f9d55b4724f) | 1615872606-56087-1-git-send-email-aubrey.li@intel.com | RRC,v3 ☐ | [LORE RRC,v3,00/19](https://lkml.kernel.org/netdev/20210605111034.1810858-1-jolsa@kernel.org) |
|
||||
| 2021/10/8 | Jiri Olsa <jolsa@kernel.org> | [x86/ftrace: Add direct batch interface](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?id=5fae941b9a6f95773df644e7cf304bf199707876) | 1615872606-56087-1-git-send-email-aubrey.li@intel.com | v2 ☑✓ 5.16-rc1 | [LKML v2,0/8](https://lkml.org/lkml/2021/10/8/186), [LORE v2,0/8](https://lore.kernel.org/all/20211008091336.33616-1-jolsa@kernel.org) |
|
||||
|
||||
# 15 kptr_restrict
|
||||
-------
|
||||
|
||||
|
||||
@@ -23,6 +23,7 @@ https://www.infoworld.com/article/2851028/four-ways-linux-is-headed-for-no-downt
|
||||
|
||||
第 1 节内容参照 [History of Linux Kernel Live Patching](https://www.howtoforge.com/history-of-linux-kernel-live-patching)
|
||||
|
||||
Google 设计了一套新的用户空间实时补丁创建工具, [LLpatch](https://github.com/google/LLpatch), 基于 llvm-diff 生成 LLVM-IR 完成 ELF 分析和操作, 因此不需要感知特性架构的二进制差异行为. 参见 [announcing LLpatch: arch-independent live-patch creation](https://lore.kernel.org/live-patching/CABFpvm2o+d0e-dfmCx7H6=8i3QQS_xyGFt4i3zn8G=Myr_miag@mail.gmail.com).
|
||||
|
||||
|
||||
| 时间 | 作者 | 特性 | 描述 | 是否合入主线 | 链接 |
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -1475,6 +1475,8 @@ Oracle 数据库具有类似的虚拟化功能, 称为 Oracle Multitenant, 其
|
||||
|
||||
[Linux 5.18 Scheduler Change To Further Boost AMD EPYC Performance For Some Workloads](https://www.phoronix.com/scan.php?page=news_item&px=AMD-Linux-5.18-Sched-Zen-LLC)
|
||||
|
||||
[Benchmarking The AMD EPYC Speed Boost Coming To Linux 5.18, Thanks To Scheduler/NUMA Improvement](https://www.phoronix.com/scan.php?page=article&item=linux-imbalance-epyc&num=1) 中在 AMD EPYC 上进行了性能测试.
|
||||
|
||||
| 时间 | 作者 | 特性 | 描述 | 是否合入主线 | 链接 |
|
||||
|:----:|:----:|:----:|:---:|:----------:|:---:|
|
||||
| 2021/12/01 | Mel Gorman <mgorman@techsingularity.net> | [Adjust NUMA imbalance for multiple LLCs](https://lore.kernel.org/lkml/20211201151844.20488-1-mgorman@techsingularity.net) | [commit 7d2b5dd0bcc4 ("sched/numa: Allow a floating imbalance between NUMA nodes")](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=7d2b5dd0bcc4) 允许 NUMA 节点之间的不平衡, 这样通信任务不会被 load balance 分开. 当 LLC 和 node 之间有 1:1 的关系时, 这种方法可以很好地工作, 但是对于多个 LLC, 如果独立的任务过早地使用 CPU 共享缓存, 这种方法就不太理想了. 本系列解决了两个问题:<br>1. 调度程序域权重的使用不一致, 以及当每个 NUMA 节点有许多 LLC 时性能不佳. NUMA之间允许的不均衡的进程数目不再是一个固定的值 NUMA_IMBALANCE_MIN(2), 而是在 build_sched_domains() 中实际探测 NUMA 域下辖的 LLC 的数目, 作为 sd->imb_numa_nr. | v4 ☐ | [PatchWork v3,0/2](https://lore.kernel.org/lkml/20211201151844.20488-1-mgorman@techsingularity.net)<br>*-*-*-*-*-*-*-* <br>[LORE v4,0/2](https://lore.kernel.org/lkml/20211210093307.31701-1-mgorman@techsingularity.net)<br>*-*-*-*-*-*-*-* <br>[LORE v6,0/2](https://lore.kernel.org/all/20220208094334.16379-1-mgorman@techsingularity.net) |
|
||||
@@ -1772,6 +1774,12 @@ schedtune 与 uclamp 都是由 ARM 公司的 Patrick Bellasi 主导开发.
|
||||
| 低时延设定 | 通过 prefer-idle 设置 | 通过 latency_sensitive 设定 |
|
||||
| RT TASK | NA | 支持 |
|
||||
|
||||
| 时间 | 作者 | 特性 | 描述 | 是否合入主线 | 链接 |
|
||||
|:-----:|:----:|:----:|:----:|:------------:|:----:|
|
||||
| 2019/06/21 | Patrick Bellasi <patrick.bellasi@arm.com> | [Add utilization clamping support](https://lore.kernel.org/all/20190621084217.8167-1-patrick.bellasi@arm.com) | 20190621084217.8167-1-patrick.bellasi@arm.com | v10 ☐☑✓ | [LORE v10,0/16](https://lore.kernel.org/all/20190621084217.8167-1-patrick.bellasi@arm.com) |
|
||||
| 2019/08/22 | Patrick Bellasi <patrick.bellasi@arm.com> | [Add utilization clamping support (CGroups API)](https://lore.kernel.org/all/20190822132811.31294-1-patrick.bellasi@arm.com) | 20190822132811.31294-1-patrick.bellasi@arm.com | v14 ☐☑✓ | [LORE v14,0/6](https://lore.kernel.org/all/20190822132811.31294-1-patrick.bellasi@arm.com) |
|
||||
|
||||
|
||||
|
||||
## 7.6 freezer 冻结
|
||||
-------
|
||||
|
||||
Reference in New Issue
Block a user