Linux kernel regression status

[next] [mainline] [stable/longterm] • [new] • [all] • [resolved] [inconclusive] 

  • 223baf9d17f
    (v6.4-rc1)
  • sched: performance regression in hackbench (partly solved in -next by c1753fd02a00, partially caused by df323337e50) by Aaron Lu
    [1]: [RFC PATCH] sched: Introduce per-mm/cpu concurrency id state
    , by Mathieu Desnoyers (monitored)
    [2]: [RFC PATCH] sched: Fix performance regression introduced by mm_cid
    , by Mathieu Desnoyers (monitored)
    [3]: [RFC PATCH] sched: Fix performance regression introduced by mm_cid (v2)
    , by Mathieu Desnoyers (monitored)
    [4]: [RFC PATCH v3] sched: Fix performance regression introduced by mm_cid
    , by Mathieu Desnoyers (monitored)
    [5]: [RFC PATCH v4] sched: Fix performance regression introduced by mm_cid
    , by Mathieu Desnoyers (monitored)
    [6]: [RFC PATCH] sched: Rate limit migrations
    , by Mathieu Desnoyers (monitored)
    [7]: [RFC PATCH v5] sched: Fix performance regression introduced by mm_cid
    , by Mathieu Desnoyers (monitored)
    [8]: [RFC PATCH v6] sched: Fix performance regression introduced by mm_cid
    , by Mathieu Desnoyers (monitored)
    [9]: [RFC PATCH v7] sched: Fix performance regression introduced by mm_cid
    , by Mathieu Desnoyers (monitored)
    [10]: [RFC PATCH v8] sched: Fix performance regression introduced by mm_cid
    , by Mathieu Desnoyers (monitored)
    [11]: [RFC PATCH v9 2/2] sched: Fix performance regression introduced by mm_cid
    , by Mathieu Desnoyers (monitored)
    [12]: [PATCH v10] sched: Fix performance regression introduced by mm_cid
    , by Mathieu Desnoyers (monitored)
    [13]: [tip: sched/core] sched: Fix performance regression introduced by mm_cid
    , by tip-bot2 for Mathieu Desnoyers (monitored)
    [14]: [PATCH 6.4 182/800] mm: move mm_count into its own cache line
    , by Greg Kroah-Hartman (monitored)
    [15]: [RFC PATCH 1/1] sched: Extend cpu idle state for 1ms
    , by Mathieu Desnoyers (monitored)
    [16]: [RFC PATCH 1/1] sched: Favor almost idle previously used CPUs for wake affine
    , by Mathieu Desnoyers (monitored)
    [17]: [RFC PATCH 1/1] sched: ttwu_queue_cond: perform queued wakeups across different L2 caches
    , by Mathieu Desnoyers (monitored)
    [18]: [RFC PATCH 3/3] sched: ttwu_queue_cond: skip queued wakeups across different l2 caches
    , by Mathieu Desnoyers (monitored)
    [19]: [RFC PATCH v3 3/3] sched: ttwu_queue_cond: skip queued wakeups across different l2 caches
    , by Mathieu Desnoyers (monitored)
    [20]: [RFC PATCH 1/2] sched: Rate limit migrations to 1 per 2ms per task
    , by Mathieu Desnoyers (monitored)
    [21]: [RFC PATCH 0/2] Makes it easier for the wakee to choose previous CPU
    , by Chen Yu (monitored)
    [22]: [PATCH 0/2] Introduce SIS_CACHE to choose previous CPU during task wakeup
    , by Chen Yu (monitored)
    [23]: [RFC PATCH] sched/fair: Bias runqueue selection towards almost idle prev CPU
    , by Mathieu Desnoyers (monitored)
    [24]: [RFC PATCH] sched/fair: Introduce WAKEUP_BIAS_PREV_IDLE to reduce migrations
    , by Mathieu Desnoyers (monitored)
    [25]: [RFC PATCH] sched/fair: Introduce WAKEUP_BIAS_PREV to reduce migrations
    , by Mathieu Desnoyers (monitored)
    [26]: [RFC PATCH 1/2] sched/fair: Introduce UTIL_FITS_CAPACITY feature
    , by Mathieu Desnoyers (monitored)
    [27]: [RFC PATCH 2/2] sched/fair: Introduce SELECT_BIAS_PREV to reduce migrations
    , by Mathieu Desnoyers (monitored)
    [28]: [RFC PATCH v2 1/2] sched/fair: Introduce UTIL_FITS_CAPACITY feature (v2)
    , by Mathieu Desnoyers (monitored)
    [29]: [RFC PATCH v2 2/2] sched/fair: Introduce SELECT_BIAS_PREV to reduce migrations
    , by Mathieu Desnoyers (monitored)
    [30]: [PATCH v2 0/3] Introduce SIS_CACHE to choose previous CPU during task wakeup
    , by Chen Yu (monitored)
    Resolution: 223baf9d17f2 ("sched: Fix performance regression introduced by mm_cid")
    in v6.4-rc1

    Latest five known activities:

    Regzbot command history:

    mainline

    [compiled by regzbot on 2024-12-05 20:38:07 (UTC). Wanna know more about regzbot? Then check out its getting started guide or its reference documentation.]

    [recently 63 events occurred that regzbot was unable to handle]