From: Andi Kleen <ak@linux.intel.com> To: Peter Zijlstra <a.p.zijlstra@chello.nl>, linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [PATCH 00/25] mm: Preemptibility -v7 Date: Tue, 25 Jan 2011 12:47:07 -0800 [thread overview] Message-ID: <4D3F36CB.6060505@linux.intel.com> (raw) In-Reply-To: <1295987985.28776.1118.camel@laptop> > Its nesting hundreds of spinlocks (255+) make the preempt debug code > unhappy, it also causes fun latencies when you do start KVM/GRU > Although arguably that's the least convincing reason to do all this its > the one that got me to actually compose this series -- I really should > write a new leader.. Least Convincing is a good description... Tuning operations which only happen once is not very interesting, especially if that affects fast paths. > Making all this preemptible also allows making the whole mmu_gather > thing preemptible, which is something we've wanted to do for a long > while, it also allows XPMEM or whatever that thing was called (Andrea > knows) and of course, it moves a part of -rt upstream. I thought the reason for the preempt off inside the mmu gather region was to stay on the same CPU for local/remote flushes. How would it change that? > If we decide to keep patch 24, it also simplifies the truncate path > quite a bit. That sounds like a good thing. Making truncate simpler is always good. -Andi
WARNING: multiple messages have this Message-ID (diff)
From: Andi Kleen <ak@linux.intel.com> To: Peter Zijlstra <a.p.zijlstra@chello.nl>, linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [PATCH 00/25] mm: Preemptibility -v7 Date: Tue, 25 Jan 2011 12:47:07 -0800 [thread overview] Message-ID: <4D3F36CB.6060505@linux.intel.com> (raw) In-Reply-To: <1295987985.28776.1118.camel@laptop> > Its nesting hundreds of spinlocks (255+) make the preempt debug code > unhappy, it also causes fun latencies when you do start KVM/GRU > Although arguably that's the least convincing reason to do all this its > the one that got me to actually compose this series -- I really should > write a new leader.. Least Convincing is a good description... Tuning operations which only happen once is not very interesting, especially if that affects fast paths. > Making all this preemptible also allows making the whole mmu_gather > thing preemptible, which is something we've wanted to do for a long > while, it also allows XPMEM or whatever that thing was called (Andrea > knows) and of course, it moves a part of -rt upstream. I thought the reason for the preempt off inside the mmu gather region was to stay on the same CPU for local/remote flushes. How would it change that? > If we decide to keep patch 24, it also simplifies the truncate path > quite a bit. That sounds like a good thing. Making truncate simpler is always good. -Andi -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/ Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-01-25 20:47 UTC|newest] Thread overview: 128+ messages / expand[flat|nested] mbox.gz Atom feed top 2011-01-25 17:31 [PATCH 00/25] mm: Preemptibility -v7 Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 01/25] tile: Fix __pte_free_tlb Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-02-04 20:39 ` Chris Metcalf 2011-02-04 20:39 ` Chris Metcalf 2011-02-04 20:39 ` Chris Metcalf 2011-02-07 13:55 ` Peter Zijlstra 2011-02-07 13:55 ` Peter Zijlstra 2011-02-23 20:59 ` Chris Metcalf 2011-02-23 20:59 ` Chris Metcalf 2011-02-23 20:59 ` Chris Metcalf 2011-01-25 17:31 ` [PATCH 02/25] mm: Preemptible mmu_gather Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 03/25] powerpc: " Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 04/25] sparc: " Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 20:30 ` David Miller 2011-01-25 20:30 ` David Miller 2011-01-25 17:31 ` [PATCH 05/25] s390: preemptible mmu_gather Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 06/25] arm: Preemptible mmu_gather Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 07/25] sh: " Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 08/25] um: " Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 09/25] ia64: " Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 20:12 ` Tony Luck 2011-01-25 20:12 ` Tony Luck 2011-01-25 20:22 ` Peter Zijlstra 2011-01-25 20:22 ` Peter Zijlstra 2011-01-25 21:23 ` Tony Luck 2011-01-25 21:23 ` Tony Luck 2011-01-26 11:01 ` Peter Zijlstra 2011-01-26 11:01 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 10/25] mm: Now that all old mmu_gather code is gone, remove the storage Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 11/25] mm, powerpc: Move the RCU page-table freeing into generic code Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 12/25] lockdep, mutex: Provide mutex_lock_nest_lock Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 13/25] mutex: Provide mutex_is_contended Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 14/25] mm: Convert i_mmap_lock to a mutex Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 15/25] mm: Extended batches for generic mmu_gather Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 16/25] mm: Revert page_lock_anon_vma() lock annotation Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 17/25] mm: Improve page_lock_anon_vma() comment Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 18/25] mm: Rename drop_anon_vma to put_anon_vma Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 19/25] mm: Move anon_vma ref out from under CONFIG_KSM Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 20/25] mm: Simplify anon_vma refcounts Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 20:16 ` Linus Torvalds 2011-01-25 20:16 ` Linus Torvalds 2011-01-25 20:31 ` Peter Zijlstra 2011-01-25 20:31 ` Peter Zijlstra 2011-01-25 20:37 ` Linus Torvalds 2011-01-25 20:37 ` Linus Torvalds 2011-01-25 17:31 ` [PATCH 21/25] mm: Use refcounts for page_lock_anon_vma() Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 22/25] mm: Convert anon_vma->lock to a mutex Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-02-03 5:27 ` KOSAKI Motohiro 2011-02-03 5:27 ` KOSAKI Motohiro 2011-02-03 15:04 ` Peter Zijlstra 2011-02-03 15:04 ` Peter Zijlstra 2011-02-04 4:35 ` KOSAKI Motohiro 2011-02-04 4:35 ` KOSAKI Motohiro 2011-01-25 17:31 ` [PATCH 23/25] mm: Optimize page_lock_anon_vma() fast-path Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 24/25] mm: Remove i_mmap_mutex lockbreak Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` [PATCH 25/25] mm, arch: Ensure we never tlb_flush_mmu() from atomic context Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 17:31 ` Peter Zijlstra 2011-01-25 18:32 ` [PATCH 00/25] mm: Preemptibility -v7 Sam Ravnborg 2011-01-25 18:32 ` Sam Ravnborg 2011-01-25 19:28 ` Peter Zijlstra 2011-01-25 19:28 ` Peter Zijlstra 2011-01-25 19:41 ` Sam Ravnborg 2011-01-25 19:41 ` Sam Ravnborg 2011-01-25 19:45 ` Andi Kleen 2011-01-25 19:45 ` Andi Kleen 2011-01-25 19:45 ` Andi Kleen [not found] ` <1295987985.28776.1118.camel@laptop> 2011-01-25 20:47 ` Andi Kleen [this message] 2011-01-25 20:47 ` Andi Kleen 2011-01-25 21:09 ` Peter Zijlstra 2011-01-25 21:09 ` Peter Zijlstra 2011-01-26 13:13 ` [RFC][PATCH 26/25] mm, arch: Convert ia64, arm, sh to generic tlb Peter Zijlstra 2011-01-26 13:13 ` Peter Zijlstra 2011-01-26 19:19 ` Sam Ravnborg 2011-01-26 19:30 ` Peter Zijlstra 2011-01-26 20:03 ` Sam Ravnborg 2011-02-17 12:06 ` [PATCH 00/25] mm: Preemptibility -v7 Peter Zijlstra 2011-02-17 12:06 ` Peter Zijlstra
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=4D3F36CB.6060505@linux.intel.com \ --to=ak@linux.intel.com \ --cc=a.p.zijlstra@chello.nl \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.