[PATCH v6 00/33] SLUB: reduce irq disabled scope and make it RT compatible · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 01/33] mm, slub: don't call flush_all() from slab_debug_trace_open() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 03/33] mm, slub: allocate private object map for validate_slab_cache() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 02/33] mm, slub: allocate private object map for debugfs listings · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 04/33] mm, slub: don't disable irq for debug_check_no_locks_freed() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 05/33] mm, slub: remove redundant unfreeze_partials() from put_cpu_partial() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 07/33] mm, slub: dissolve new_slab_objects() into ___slab_alloc() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 06/33] mm, slub: extract get_partial() from new_slab_objects() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 09/33] mm, slub: restructure new page checks in ___slab_alloc() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 10/33] mm, slub: simplify kmem_cache_cpu and tid setup · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 11/33] mm, slub: move disabling/enabling irqs to ___slab_alloc() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 14/33] mm, slub: restore irqs around calling new_slab() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 08/33] mm, slub: return slab page from get_partial() and set c->page afterwards · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 13/33] mm, slub: move disabling irqs closer to get_partial() in ___slab_alloc() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 15/33] mm, slub: validate slab from partial list or page allocator before making it cpu slab · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 16/33] mm, slub: check new pages with restored irqs · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 12/33] mm, slub: do initial checks in ___slab_alloc() with irqs enabled · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 18/33] mm, slub: move reset of c->page and freelist out of deactivate_slab() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 19/33] mm, slub: make locking in deactivate_slab() irq-safe · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 17/33] mm, slub: stop disabling irqs around get_partial() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 24/33] mm, slub: separate detaching of partial list in unfreeze_partials() from unfreezing · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 22/33] mm, slub: discard slabs in unfreeze_partials() without irqs disabled · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 20/33] mm, slub: call deactivate_slab() without disabling irqs · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 28/33] mm: slub: move flush_cpu_slab() invocations __free_slab() invocations out of IRQ context · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 27/33] mm, slab: split out the cpu offline variant of flush_slab() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 25/33] mm, slub: only disable irq with spin_lock in __unfreeze_partials() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 26/33] mm, slub: don't disable irqs in slub_cpu_dead() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 31/33] mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 30/33] mm, slub: make slab_lock() disable irqs with PREEMPT_RT · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 29/33] mm: slub: make object_map_lock a raw_spinlock_t · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 33/33] mm, slub: convert kmem_cpu_slab protection to local_lock · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 21/33] mm, slub: move irq control into unfreeze_partials() · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 32/33] mm, slub: use migrate_disable() on PREEMPT_RT · Vlastimil Babka <hidden> · 2021-09-04
[PATCH v6 23/33] mm, slub: detach whole partial list at once in unfreeze_partials() · Vlastimil Babka <hidden> · 2021-09-04
Re: [PATCH v6 00/33] SLUB: reduce irq disabled scope and make it RT compatible · Mike Galbraith <hidden> · 2021-09-05
Re: [PATCH v6 00/33] SLUB: reduce irq disabled scope and make it RT compatible · Mel Gorman <hidden> · 2021-09-07

Re: [PATCH v6 00/33] SLUB: reduce irq disabled scope and make it RT compatible

From: Mel Gorman <hidden>
Date: 2021-09-07 08:20:20
Also in: lkml

On Sat, Sep 04, 2021 at 12:49:30PM +0200, Vlastimil Babka wrote:

The RFC/v1 version also got basic performance screening by Mel that didn't show
major regressions. Mike's testing with hackbench of v2 on !RT reported
negligible differences [6]:

FWIW, this version didn't show any major differences in terms of
performance and it didn't functionally fail either.

-- 
Mel Gorman
SUSE Labs

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help