mirror of
https://github.com/gatieme/LDD-LinuxDeviceDrivers.git
synced 2026-09-21 03:43:38 +08:00
description/memory: get_scan_count()
This commit is contained in:
Cheng Jian
File diff suppressed because one or more lines are too long
@@ -62,7 +62,9 @@ git log --oneline v5.15...v5.16 | grep -E "Merge tag | Linux " | grep -E "sched
|
||||
| 5.14 | 2021/08/29 | [Merge tag 'sched-core-2021-06-28', 5.14-rc1](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=54a728dc5e4feb0a9278ad62b19f34ad21ed0ee4)<br>[Merge tag 'sched-urgent-2021-06-30', 5.14-rc1](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=a6eaf3850cb171c328a8b0db6d3c79286a1eba9d)<br>[Merge tag 'sched-urgent-2021-07-11', 5.14-rc1](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=877029d9216dcc842f50d37571f318cd17a30a2d)<br>[Merge tag 'sched-urgent-2021-08-08', 5.14-rc5](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=713f0f37e8128e8a0190a98f5a4be71fb32a671a)<br>[Merge tag 'sched_urgent_for_v5.14', 5.14](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=537b57bd5a202af145c266d4773971c2c9f90cd9) |
|
||||
| 5.15 | 2021/11/1 | NA | [Merge tag 'sched-core-2021-08-30'](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=5d3c0db4598c5de511824649df2aa976259cf10a)<br>[Merge remote-tracking branch 'tip/sched/arm64'](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=65266a7c6abf)<br>[Merge tag 'sched_urgent_for_v5.15_rc1'](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=56c244382fdb)<br>[Merge tag 'sched_urgent_for_v5.15_rc4'](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=777feabaea77)<br>[Merge tag 'sched_urgent_for_v5.15_rc7'](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=6c62666d8879)
|
||||
| 5.16 | 2022/01/09 | [Merge tag 'sched-core-2021-11-01', 5.16-rc1](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=9a7e0a90a454a7826ecbca055a6ec9271b70c686)<br>[Merge tag 'sched_urgent_for_v5.16_rc1', 5.16-rc3](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=fc661f2dcb7e)<br>[Merge tag 'sched-urgent-2021-11-28', 5.16-rc3](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=97891bbf38f7)<br>[Merge tag 'sched_urgent_for_v5.16_rc4', 5.16-rc4](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=1d213767dc6f)<br>[Merge tag 'sched-urgent-2021-12-12', 5.16-rc5](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=773602256a2ca73455b0baeae5737c4a9ed6ef49) |
|
||||
| 5.17 | 2022/03/20 | [sched-core-2021-11-01, 5.16-rc1](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=9a7e0a90a454a7826ecbca055a6ec9271b70c686)<br>[sched_urgent_for_v5.16_rc1, 5.16-rc1](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=fc661f2dcb7e41dcda9ae862efb822bb2f461646)<br>[sched-urgent-2021-11-28, 5.16-rc3](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=97891bbf38f71ec97199d2459368b5b4b700706e)<br>[sched_urgent_for_v5.16_rc4, 5.16-rc4](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=1d213767dc6f594022e43b6b59c45e7e3c84c4de)<br>[sched-urgent-2021-12-1, 5.16-rc5](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=773602256a2ca73455b0baeae5737c4a9ed6ef49) |
|
||||
| 5.17 | 2022/03/20 | [sched_core_for_v5.17_rc1, 5.17-rc1](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=6ae71436cda7)<br>[sched_urgent_for_v5.17_rc2, 5.17-rc2](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=10c64a0f2806)<br>[sched_urgent_for_v5.17_rc2_p2, 5.17-rc2](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=24f4db1f3a27)<br>[sched_urgent_for_v5.17_rc4, 5.17-rc4](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=6f3573672324)<br>[sched_urgent_for_v5.17_rc5, 5.17-rc5](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=0b0894ff78cc) |
|
||||
| 5.18 | NA | [sched-core-2022-03-22, 5.18-rc1](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=3fe2f7446f1e029b220f7f650df6d138f91651f2), [scheduler updates for v5.18](https://lore.kernel.org/lkml/YjhZUezhnamHAl0H@gmail.com) |
|
||||
|
||||
|
||||
cgit 上查看 sched 所有的 log 信息 :
|
||||
|
||||
@@ -1505,7 +1507,7 @@ Oracle 数据库具有类似的虚拟化功能, 称为 Oracle Multitenant, 其
|
||||
|
||||
| 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) |
|
||||
| 2021/12/01 | Mel Gorman <mgorman@techsingularity.net> | [Adjust NUMA imbalance for multiple LLCs](https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?id=e496132ebedd870b67f1f6d2428f9bb9d7ae27fd) | [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 ☑✓ 5.18-rc1 | [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) |
|
||||
| 2022/02/17 | K Prateek Nayak <kprateek.nayak@amd.com> | [sched/fair: Consider cpu affinity when allowing NUMA imbalance in find_idlest_group](https://lore.kernel.org/all/20220217055408.28151-1-kprateek.nayak@amd.com) | 当前的调度程序代码只是检查本地组中的任务数是否小于允许的 NUMA 不平衡阈值. 该阈值以前是 NUMA 域跨度的 25%）, 但在 Mel 补丁集 "Adjust NUMA imbalance for multiple LLCs" 中 commit e496132ebedd ("sched/fair: Adjust the allowed NUMA imbalance when SD_NUMA spans multiple LLCs" 现在等于 NUMA 域中的 LLC 数目, 通常情况下这种机制运行良好.<br>但是对于进程都通过 numactl/taskset PIN 到一组分散的 CPU 上的情况(比如每个 LLC 域中选一个 CPU), 任务的数量将始终在阈值内, 因此所有 8 个流线程将在第一个 SOCKET 上唤醒, 从而导致次优性能. 在最初的少量 CPU 上堆积之后, 虽然负载平衡器可以工作, 但是稳定的均衡状态, 并且需要频繁的迁移 PING PONG.<br>我们可以通过检查本地组中允许的 CPU 数量是否少于本地组中运行的任务数量来检测并避免这种堆积, 并使用此信息将本来会堆积的县城分散到下一个 SOCKET 中(毕竟, 这个慢路径的目标是在初始放置期间找到最空闲的组和最空闲的 CPU). | v4 ☐☑✓ | [LORE](https://lore.kernel.org/all/20220217055408.28151-1-kprateek.nayak@amd.com) |
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user