Re: [PATCH] mm, slab: reschedule cache_reap() on the same CPU

2018-04-11 Thread Pekka Enberg
t;workqueue: schedule WORK_CPU_UNBOUND work on wq_unbound_cpumask CPUs") CC: <sta...@vger.kernel.org> Cc: Joonsoo Kim <iamjoonsoo@lge.com> Cc: David Rientjes <rient...@google.com> Cc: Pekka Enberg <penb...@kernel.org> Cc: Christoph Lameter <c...@linux.com> Cc:

Re: [PATCH 0/4] zswap: Optimize compressed pool memory utilization

2016-08-17 Thread Pekka Enberg
On Wed, Aug 17, 2016 at 1:03 PM, Srividya Desireddy wrote: > This series of patches optimize the memory utilized by zswap for storing > the swapped out pages. > > Zswap is a cache which compresses the pages that are being swapped out > and stores them into a dynamically

Re: [PATCH 3/4] zswap: Zero-filled pages handling

2016-08-17 Thread Pekka Enberg
overhead caused due to zero-filled page check is very minimal >> when compared to the time saved by avoiding compression and allocation in >> case of zero-filled pages. The load time of a zero-filled page is reduced >> by 80% when compared to baseline. On Wed, Aug 17, 2016 at 3:25

Re: [PATCH 3/4] zswap: Zero-filled pages handling

2016-08-17 Thread Pekka Enberg
On Wed, Aug 17, 2016 at 1:18 PM, Srividya Desireddy wrote: > This patch adds a check in zswap_frontswap_store() to identify zero-filled > page before compression of the page. If the page is a zero-filled page, set > zswap_entry.zeroflag and skip the compression of the

Re: [PATCH, REGRESSION v3] mm: make apply_to_page_range more robust

2016-01-21 Thread Pekka Enberg
On 01/22/2016 01:12 AM, David Rientjes wrote: NACK to your patch as it is just covering up buggy code silently. The problem needs to be addressed in change_memory_common() to return if there is no size to change (numpages == 0). It's a two line fix to that function. So add a WARN_ON there

Re: [PATCH] mm: slab: convert slab_is_available to boolean

2015-09-15 Thread Pekka Enberg
On 9/15/15 8:50 PM, Denis Kirjanov wrote: A good one candidate to return a boolean result Signed-off-by: Denis Kirjanov <k...@linux-powerpc.org> Reviewed-by: Pekka Enberg <penb...@kernel.org> -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in

[PATCH 06/14] drm: Use kvfree() in drm_free_large()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: David Airlie airl...@linux.ie Signed-off-by: Pekka Enberg penb...@kernel.org --- include/drm/drm_mem_util.h | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/include/drm/drm_mem_util.h b/include/drm/drm_mem_util.h index 19a2404

[PATCH 12/14] dm: Use kvfree() in dm_kvfree()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: Alasdair Kergon a...@redhat.com Cc: Mike Snitzer snit...@redhat.com Signed-off-by: Pekka Enberg penb...@kernel.org --- drivers/md/dm-stats.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/md/dm-stats.c b/drivers/md/dm

[PATCH 03/14] cxgb3: Use kvfree() in cxgb_free_mem()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: Santosh Raspatur sant...@chelsio.com Signed-off-by: Pekka Enberg penb...@kernel.org --- drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb3

[PATCH 09/14] IB/ehca: Use kvfree() in ipz_queue_{cd}tor()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: Hoang-Nam Nguyen hngu...@de.ibm.com Cc: Christoph Raisch rai...@de.ibm.com Signed-off-by: Pekka Enberg penb...@kernel.org --- drivers/infiniband/hw/ehca/ipz_pt_fn.c | 10 ++ 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers

[PATCH 08/14] drivers/input/evdev.c: Use kvfree() in evdev_release()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: Dmitry Torokhov dmitry.torok...@gmail.com Signed-off-by: Pekka Enberg penb...@kernel.org --- drivers/input/evdev.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index a18f41b

[PATCH 01/14] ipc/util.c: Use kvfree() in ipc_rcu_free()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg penb...@kernel.org --- ipc/util.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/ipc/util.c b/ipc/util.c index ff3323e..537a41c 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -467,10 +467,7 @@ void

[PATCH 02/14] kernel/relay.c: Use kvfree() in relay_free_page_array()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Signed-off-by: Pekka Enberg penb...@kernel.org --- kernel/relay.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/relay.c b/kernel/relay.c index e9dbaeb..0b4570c 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -81,10

[PATCH 05/14] ceph: Use kvfree() in ceph_put_page_vector()

2015-05-15 Thread Pekka Enberg
Use kvfree instead of open-coding it. Cc: Yan, Zheng z...@redhat.com Cc: Sage Weil s...@redhat.com Signed-off-by: Pekka Enberg penb...@kernel.org --- net/ceph/pagevec.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index 096d914

[PATCH 11/14] libcxgbi: Use kvfree() in cxgbi_free_big_mem()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: James E.J. Bottomley jbottom...@odin.com Signed-off-by: Pekka Enberg penb...@kernel.org --- drivers/scsi/cxgbi/libcxgbi.h | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi

[PATCH 13/14] bcache: Use kvfree() in various places

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: Kent Overstreet k...@daterainc.com Signed-off-by: Pekka Enberg penb...@kernel.org --- drivers/md/bcache/super.c | 10 ++ drivers/md/bcache/util.h | 10 ++ 2 files changed, 4 insertions(+), 16 deletions(-) diff --git a/drivers/md

[PATCH 14/14] NTFS: Use kvfree() in ntfs_free()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: Anton Altaparmakov an...@tuxera.com Signed-off-by: Pekka Enberg penb...@kernel.org --- fs/ntfs/malloc.h | 7 +-- 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h index a44b14c..ab172e5 100644 --- a/fs

[PATCH 07/14] drm/nouveau/gem: Use kvfree() in u_free()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: David Airlie airl...@linux.ie Signed-off-by: Pekka Enberg penb...@kernel.org --- drivers/gpu/drm/nouveau/nouveau_gem.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm

[PATCH 04/14] cxgb4: Use kvfree() in t4_free_mem()

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: Hariprasad S haripra...@chelsio.com Signed-off-by: Pekka Enberg penb...@kernel.org --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4

[PATCH 10/14] target: Use kvfree() in session alloc and free

2015-05-15 Thread Pekka Enberg
Use kvfree() instead of open-coding it. Cc: Nicholas A. Bellinger n...@linux-iscsi.org Signed-off-by: Pekka Enberg penb...@kernel.org --- drivers/target/target_core_transport.c | 10 ++ 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/target/target_core_transport.c

Re: [PATCH v2] perf kmem: Show warning when trying to run stat without record

2015-05-05 Thread Pekka Enberg
below to inform user: # perf kmem stat --page --caller Not found page events. Have you run 'perf kmem record --page' before? Acked-by: Pekka Enberg penb...@kernel.org Signed-off-by: Namhyung Kim namhy...@kernel.org Thanks, applied. I just found the messages a bit odd souding, perhaps

Re: [PATCH 0/13] Parallel struct page initialisation v4

2015-04-28 Thread Pekka Enberg
the machine appears to work as normal. Boot times were measured from the time shutdown was called until ssh was available again. In the 64G case, the boot time savings are negligible. On the 1TB machine, the savings were 16 seconds. FWIW, Acked-by: Pekka Enberg penb...@kernel.org for the whole series

Re: [PATCHSET 0/6] perf kmem: Implement page allocation analysis (v7)

2015-04-13 Thread Pekka Enberg
, it does slab allocation analysis for backward compatibility. Nice addition! Acked-by: Pekka Enberg penb...@kernel.org for the whole series. - Pekka -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info

Re: [PATCH v6 2/4] perf tools: add Java demangling support

2015-03-31 Thread Pekka Enberg
Hi Stephane, On Tue, Mar 31, 2015 at 1:19 AM, Stephane Eranian eran...@google.com wrote: +#define BASE_ENT(c, n) [c-'A']=n +static const char *base_types['Z'-'A' + 1]={ + BASE_ENT('B', byte ), + BASE_ENT('C', char ), + BASE_ENT('D', double ), + BASE_ENT('F', float ),

Re: stand-alone kvmtool

2015-03-01 Thread Pekka Enberg
On 2/26/15 1:02 PM, Alex Bennée wrote: If you can have it all it would be nice to preserve buildability all through your history for bisecting (and the moon on a stick please ;-) Is the dependency on the kernel sources something that has been stable over the projects history or something that's

Re: stand-alone kvmtool

2015-02-23 Thread Pekka Enberg
Hi, On 2/18/15 5:50 PM, Will Deacon wrote: Thanks for doing this. Since it looks unlikely that kvmtool will ever be merged back into the kernel tree, it makes sense to cut the dependency in my opinion. I am certainly OK with a standalone repository which preserves the history. Will, would

Re: [PATCH v3 1/5] slab: Correct size_index table before replacing the bootstrap kmem_cache_node.

2015-02-05 Thread Pekka Enberg
...@imgtec.com Cc: Christoph Lameter c...@linux.com Cc: Pekka Enberg penb...@kernel.org Cc: David Rientjes rient...@google.com Cc: Joonsoo Kim iamjoonsoo@lge.com Cc: Andrew Morton a...@linux-foundation.org Cc: linux...@kvack.org Cc: linux-kernel@vger.kernel.org Acked-by: Pekka Enberg penb...@kernel.org

Re: [PATCH 1/5] LLVMLinux: Correct size_index table before replacing the bootstrap kmem_cache_node.

2015-02-04 Thread Pekka Enberg
On 2/3/15 3:37 PM, Daniel Sanders wrote: This patch moves the initialization of the size_index table slightly earlier so that the first few kmem_cache_node's can be safely allocated when KMALLOC_MIN_SIZE is large. The patch looks OK to me but how is this related to LLVM? - Pekka -- To

Re: [PATCH 1/5] LLVMLinux: Correct size_index table before replacing the bootstrap kmem_cache_node.

2015-02-04 Thread Pekka Enberg
On Wed, Feb 4, 2015 at 10:38 PM, Daniel Sanders daniel.sand...@imgtec.com wrote: I don't believe the bug to be LLVM specific but GCC doesn't normally encounter the problem. I haven't been able to identify exactly what GCC is doing better (probably inlining) but it seems that GCC is managing

Re: [PATCH -mm v2 1/3] slub: never fail to shrink cache

2015-01-28 Thread Pekka Enberg
Lameter c...@linux.com Acked-by: Pekka Enberg penb...@kernel.org -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http

Re: [PATCH 1/7] slub: Remove __slab_alloc code duplication

2014-12-10 Thread Pekka Enberg
On Wed, Dec 10, 2014 at 6:30 PM, Christoph Lameter c...@linux.com wrote: Somehow the two branches in __slab_alloc do the same. Unify them. Signed-off-by: Christoph Lameter c...@linux.com Reviewed-by: Pekka Enberg penb...@kernel.org -- To unsubscribe from this list: send the line unsubscribe

Re: [PATCH 2/7] slub: Use page-mapping to store address of page frame like done in SLAB

2014-12-10 Thread Pekka Enberg
of invocations of page_address(). Those are mostly only used for debugging though so this should have no performance benefit. Signed-off-by: Christoph Lameter c...@linux.com Reviewed-by: Pekka Enberg penb...@kernel.org -- To unsubscribe from this list: send the line unsubscribe linux-kernel

Re: [PATCH 3/7] slub: Do not use c-page on free

2014-12-10 Thread Pekka Enberg
On Wed, Dec 10, 2014 at 6:30 PM, Christoph Lameter c...@linux.com wrote: Avoid using the page struct address on free by just doing an address comparison. That is easily doable now that the page address is available in the page struct and we already have the page struct address of the object to

Re: [PATCH 4/7] slub: Avoid using the page struct address in allocation fastpath

2014-12-10 Thread Pekka Enberg
On Wed, Dec 10, 2014 at 6:30 PM, Christoph Lameter c...@linux.com wrote: We can use virt_to_page there and only invoke the costly function if actually a node is specified and we have to check the NUMA locality. Increases the cost of allocating on a specific NUMA node but then that was never

Re: [PATCH 5/7] slub: Use end_token instead of NULL to terminate freelists

2014-12-10 Thread Pekka Enberg
-by: Pekka Enberg penb...@kernel.org -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/

Re: [PATCH 6/7] slub: Drop -page field from kmem_cache_cpu

2014-12-10 Thread Pekka Enberg
the condition that the current cpu has no percpu slab attached to it. Signed-off-by: Christoph Lameter c...@linux.com Reviewed-by: Pekka Enberg penb...@kernel.org -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo

Re: [PATCH 3/7] slub: Do not use c-page on free

2014-12-10 Thread Pekka Enberg
-by: Pekka Enberg penb...@kernel.org - Pekka -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/

Re: [PATCH v2] slab: Fix nodeid bounds check for non-contiguous node IDs

2014-12-01 Thread Pekka Enberg
void *cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, void *obj; int x; - VM_BUG_ON(nodeid num_online_nodes()); + VM_BUG_ON(nodeid 0 || nodeid = MAX_NUMNODES); n = get_node(cachep, nodeid); BUG_ON(!n); Reviewed-by: Pekka Enberg penb

Re: [PATCH] SLAB Maintainer update

2014-06-05 Thread Pekka Enberg
Acked-by: Pekka Enberg penb...@kernel.org -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/

Re: slab_common: fix the check for duplicate slab names

2014-05-23 Thread Pekka Enberg
On 05/23/2014 11:16 PM, Mike Snitzer wrote: On Tue, Mar 25 2014 at 2:07pm -0400, Christoph Lameter c...@linux.com wrote: On Tue, 25 Mar 2014, Mike Snitzer wrote: This patch still isn't upstream. Who should be shepherding it to Linus? Pekka usually does that. Acked-by: Christoph Lameter

Re: randconfig build error with next-20140512, in mm/slub.c

2014-05-12 Thread Pekka Enberg
, feste...@gmail.com, Fabio Estevam fabio.este...@freescale.com,Christoph Lameter c...@linux.com, David Rientjes rient...@google.com, Pekka Enberg penb...@kernel.org Subject: [PATCH] mm: slub: Place count_partial() outside CONFIG_SLUB_DEBUG if block On Mon, 12 May 2014, Jim Davis wrote

Re: [PATCH] slab: Fix off by one in object max number tests.

2014-05-05 Thread Pekka Enberg
On Tue, May 6, 2014 at 6:32 AM, Linus Torvalds torva...@linux-foundation.org wrote: On Mon, May 5, 2014 at 8:25 PM, David Miller da...@davemloft.net wrote: Sam Ravnborg s...@ravnborg.org wrote: There is a related patch in this area which I think is not yet applied. See:

[PROBLEM] perf report --gtk doesn't work

2014-04-25 Thread Pekka Enberg
Hello, I'm seeing the following with v3.15-rc2: $ ~/bin/perf report --gtk GTK browser requested but could not find libperf-gtk.so The library file is in $HOME/lib64 and perf attempts to look it up. However, printing out dlerror() output shows the following: [penberg@localhost hornet]$

Re: [PATCH 4/4] kmemcheck: Switch to using kernel disassembler

2014-04-15 Thread Pekka Enberg
. Signed-off-by: Sasha Levin sasha.le...@oracle.com Vegard probably should take a closer look at this but: Acked-by: Pekka Enberg penb...@kernel.org -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info

[GIT PULL] SLAB changes for v3.15-rc1

2014-04-13 Thread Pekka Enberg
Hi Linus, Please pull the latest SLAB tree from: git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux.git slab/next The biggest change is byte-sized freelist indices which reduces slab freelist memory usage: https://lkml.org/lkml/2013/12/2/64 Pekka

Re: oops in slab/leaks_show

2014-04-11 Thread Pekka Enberg
On 03/11/2014 10:30 AM, Joonsoo Kim wrote: -8- From ff6fe77fb764ca5bf8705bf53d07d38e4111e84c Mon Sep 17 00:00:00 2001 From: Joonsoo Kim iamjoonsoo@lge.com Date: Tue, 11 Mar 2014 14:14:25 +0900 Subject: [PATCH] slab: remove kernel_map_pages() optimization in slab

Re: [PATCH 02/13] perf ui/gtk: Reuse generic __hpp__fmt() code

2014-03-03 Thread Pekka Enberg
On 03/03/2014 03:14 AM, Namhyung Kim wrote: The __hpp__color_fmt used in the gtk code can be replace by the generic code with small change in print_fn callback. This is a preparation to upcoming changes and no functional changes intended. Cc: Jiri Olsa jo...@redhat.com Cc: Pekka Enberg penb

Re: [patch] x86, kmemcheck: Use kstrtoint() instead of sscanf()

2014-03-03 Thread Pekka Enberg
On 02/20/2014 12:14 AM, David Rientjes wrote: Kmemcheck should use the preferred interface for parsing command line arguments, kstrto*(), rather than sscanf() itself. Use it appropriately. Signed-off-by: David Rientjes rient...@google.com Acked-by: Pekka Enberg penb...@kernel.org Andrew

Re: Memory allocator semantics

2014-02-11 Thread Pekka Enberg
Hi Paul, On Sun, Feb 9, 2014 at 4:00 AM, Paul E. McKenney paul...@linux.vnet.ibm.com wrote: From what I can see, (A) works by accident, but is kind of useless because you allocate and free the memory without touching it. (B) and (C) are the lightest touches I could imagine, and as you say,

Re: Memory allocator semantics

2014-02-11 Thread Pekka Enberg
On Tue, Feb 11, 2014 at 2:14 PM, Paul E. McKenney paul...@linux.vnet.ibm.com wrote: In contrast, from kfree() to a kmalloc() returning some of the kfree()ed memory, I believe the kfree()/kmalloc() implementation must do any needed synchronization and ordering. But that is a different set of

Re: [PATCH v3 5/5] slab: make more slab management structure off the slab

2014-02-08 Thread Pekka Enberg
On Fri, Dec 13, 2013 at 9:03 AM, Joonsoo Kim iamjoonsoo@lge.com wrote: Hello, Pekka. Below is updated patch for 5/5 in this series. Now I get acks from Christoph to all patches in this series. So, could you merge this patchset? :) If you want to resend wholeset with proper ack, I will do

Re: Memory allocator semantics

2014-02-08 Thread Pekka Enberg
Hi Paul, On 01/02/2014 10:33 PM, Paul E. McKenney wrote: From what I can see, the Linux-kernel's SLAB, SLOB, and SLUB memory allocators would deal with the following sort of race: A. CPU 0: r1 = kmalloc(...); ACCESS_ONCE(gp) = r1; CPU 1: r2 = ACCESS_ONCE(gp); if (r2) kfree(r2);

[GIT PULL] SLAB changes for v3.14-rc1

2014-02-02 Thread Pekka Enberg
Hi Linus, Please pull the latest SLAB tree from: git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux.git slab/next It contains random bug fixes that have accumulated in my inbox over the past few months. Pekka -- The following changes since

Re: [PATCH] perf tools: Fix JIT profiling on heap

2014-01-31 Thread Pekka Enberg
On 01/31/2014 05:04 PM, Arnaldo Carvalho de Melo wrote: Em Fri, Jan 31, 2014 at 01:50:27PM +0200, Pekka Enberg escreveu: On 01/16/2014 03:49 AM, Namhyung Kim wrote: Gaurav reported that perf cannot profile JIT program if it executes the code on heap. This was because current map__new() only

Re: Warning at mm/slub.c

2014-01-31 Thread Pekka Enberg
On 01/24/2014 04:21 PM, Peter Zijlstra wrote: Dave Hansen already send a fix for that: lkml.kernel.org/r/52d5746f.2040...@intel.com Pekka, any chance to get that merged? Sorry for the delay - I'm way behind my inbox. It's applied now, thanks! Pekka -- To unsubscribe

Re: [PATCH] perf tools: Fix JIT profiling on heap

2014-01-31 Thread Pekka Enberg
On 01/16/2014 03:49 AM, Namhyung Kim wrote: Gaurav reported that perf cannot profile JIT program if it executes the code on heap. This was because current map__new() only handle JIT on anon mappings - extends it to handle no_dso (heap, stack) case too. This patch assumes JIT profiling only

Re: [PATCH] slub: use lockdep_assert_held

2014-01-13 Thread Pekka Enberg
On 01/10/2014 02:23 PM, Peter Zijlstra wrote: Instead of using comments in an attempt at getting the locking right, use proper assertions that actively warn you if you got it wrong. Also add extra braces in a few sites to comply with coding-style. Signed-off-by: Peter Zijlstra

Re: [PATCH 0/9] re-shrink 'struct page' when SLUB is on.

2014-01-11 Thread Pekka Enberg
On Sat, Jan 11, 2014 at 1:42 AM, Dave Hansen d...@sr71.net wrote: On 01/10/2014 03:39 PM, Andrew Morton wrote: I tested 4 cases, all of these on the cache-cold kfree() case. The first 3 are with vanilla upstream kernel source. The 4th is patched with my new slub code (all single-threaded):

Re: [PATCH] fix crash when using XFS on loopback

2014-01-09 Thread Pekka Enberg
On Thu, Jan 9, 2014 at 2:19 AM, Andrew Morton a...@linux-foundation.org wrote: cache-misses are reduced by this patchset, roughly 5%. And elapsed times are also improved by 3.1% to baseline. ah, OK, thanks, useful. A few instructions added to page_mapping() won't have effects like that!

Re: [PATCH] fix crash when using XFS on loopback

2014-01-08 Thread Pekka Enberg
tree. Acked-by: Pekka Enberg penb...@kernel.org -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/

Re: [PATCH] mm/slub: fix accumulate per cpu partial cache objects

2013-12-30 Thread Pekka Enberg
On 12/30/2013 03:08 AM, Wanpeng Li wrote: Zefan's patch is good enough, mine doesn't need any more. OK, thanks guys! Pekka -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at

Re: [PATCH] slub: Fix calculation of cpu slabs

2013-12-29 Thread Pekka Enberg
On Sat, Oct 5, 2013 at 10:48 AM, Wanpeng Li liw...@linux.vnet.ibm.com wrote: On Tue, Sep 10, 2013 at 11:43:37AM +0800, Li Zefan wrote: /sys/kernel/slab/:t-048 # cat cpu_slabs 231 N0=16 N1=215 /sys/kernel/slab/:t-048 # cat slabs 145 N0=36 N1=109 See, the number of slabs is smaller

Re: [PATCH] mm/slub: fix accumulate per cpu partial cache objects

2013-12-29 Thread Pekka Enberg
On Sat, Dec 28, 2013 at 3:50 AM, Li Zefan lize...@huawei.com wrote: On 2013/12/27 17:46, Wanpeng Li wrote: SLUB per cpu partial cache is a list of slab caches to accelerate objects allocation. However, current codes just accumulate the objects number of the first slab cache of per cpu partial

Re: [Devel] [PATCH 1/6] slab: cleanup kmem_cache_create_memcg()

2013-12-19 Thread Pekka Enberg
On 12/19/2013 11:26 AM, Vasily Averin wrote: On 12/19/2013 12:39 PM, Vladimir Davydov wrote: On 12/19/2013 12:17 PM, Vasily Averin wrote: On 12/18/2013 05:16 PM, Vladimir Davydov wrote: --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -176,8 +176,9 @@ kmem_cache_create_memcg(struct mem_cgroup

Re: [RFC][PATCH 0/7] re-shrink 'struct page' when SLUB is on.

2013-12-18 Thread Pekka Enberg
On 12/17/2013 02:45 AM, Dave Hansen wrote: I'll do some testing and see if I can coax out any delta from the optimization myself. Christoph went to a lot of trouble to put this together, so I assumed that he had a really good reason, although the changelogs don't really mention any. IIRC it's

Re: [PATCH 1/6] slab: cleanup kmem_cache_create_memcg()

2013-12-18 Thread Pekka Enberg
On 12/18/2013 03:16 PM, Vladimir Davydov wrote: Signed-off-by: Vladimir Davydov vdavy...@parallels.com Cc: Michal Hocko mho...@suse.cz Cc: Johannes Weiner han...@cmpxchg.org Cc: Glauber Costa glom...@gmail.com Cc: Christoph Lameter c...@linux.com Cc: Pekka Enberg penb...@kernel.org Cc: Andrew

Re: Slab BUG with DEBUG_* options

2013-12-03 Thread Pekka Enberg
On 11/30/2013 01:42 PM, Meelis Roos wrote: I am debugging a reboot problem on Sun Ultra 5 (sparc64) with 512M RAM and turned on DEBUG_PAGEALLOC DEBUG_SLAB and DEBUG_SLAB_LEAK (and most other debug options) and got the following BUG and hang on startup. This happened originally with

Re: Slab BUG with DEBUG_* options

2013-12-03 Thread Pekka Enberg
On 12/03/2013 02:25 PM, Joonsoo Kim wrote: No. He report that BUG() is triggered on v3.11-rc2 and v3.12. And my recent change is merged into v3.13-rc1 as you know. :) Hah, I guess my eyesight isn't what it used to be, I could have sworn it said v3.13-rc2... Thanks anyway, Joonsoo!

Re: [PATCH 1/2] perf sched: Introduce timehist command - v2

2013-12-02 Thread Pekka Enberg
On 12/02/2013 02:23 AM, David Ahern wrote: 'perf sched timehist' provides an analysis of scheduling events. Example usage: perf sched record -- sleep 1 perf sched timehist By default it shows the individual schedule events, including the time between sched-in events for the task, the

Re: [RFC 0/3] perf tools: Show time info (v1)

2013-12-02 Thread Pekka Enberg
] page_fault 2.45%0.002572 sched-messaging [kernel.kallsyms] [k] sock_alloc_send_pskb I put the series on 'perf/time-sample-v1' branch in my tree: git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.git Any comments are welcome, thanks Reviewed-by: Pekka Enberg penb

[tip:perf/core] perf trace: Remove thread summary coloring

2013-11-30 Thread tip-bot for Pekka Enberg
Commit-ID: 15e65c693d7de4c83d1e97fd89f87d47f2219782 Gitweb: http://git.kernel.org/tip/15e65c693d7de4c83d1e97fd89f87d47f2219782 Author: Pekka Enberg penb...@kernel.org AuthorDate: Thu, 14 Nov 2013 18:43:30 +0200 Committer: Arnaldo Carvalho de Melo a...@redhat.com CommitDate: Wed, 27 Nov

Re: [PATCH 0/3] Early use of boot service memory

2013-11-15 Thread Pekka Enberg
On 11/15/13 2:50 AM, jerry.hoem...@hp.com wrote: One already has to specify command line arguments to enable kdump. Yes, so what? The problem with your patch is that now to enable kdump, I have to know that there's a second command line option and if my firmware is broken or not. The

Re: [PATCH 0/3] Early use of boot service memory

2013-11-14 Thread Pekka Enberg
Hi Jerry, On Thu, Nov 14, 2013 at 1:57 AM, jerry.hoem...@hp.com wrote: I will still point out that as currently used, efi_reserve_boot_services is wrong. A work around for firmware bugs on one platform shouldn't be breaking platforms that don't have that bug. Its just much less likely to

[PATCH] perf trace: Remove thread summary coloring

2013-11-14 Thread Pekka Enberg
Thread summary line coloring looks ugly. It doesn't add much value so remove coloring completely. Signed-off-by: Pekka Enberg penb...@kernel.org --- tools/perf/builtin-trace.c | 13 ++--- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools

Re: [PATCH 0/3] Early use of boot service memory

2013-11-14 Thread Pekka Enberg
On Thu, Nov 14, 2013 at 8:04 PM, jerry.hoem...@hp.com wrote: Making this issue a quirk will be a lot more practical. Its a small, focused change whose implications are limited and more easily understood. There's nothing practical with requiring users to pass a kernel option to make kdump

Re: [PATCH] ecryptfs: Fix explicit null dereference

2013-11-14 Thread Pekka Enberg
-by: Pekka Enberg penb...@kernel.org -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/

[tip:perf/urgent] perf trace: Tweak summary output

2013-11-14 Thread tip-bot for Pekka Enberg
Commit-ID: 27a778b512e002d856952b4f01842ba4d34bc3d1 Gitweb: http://git.kernel.org/tip/27a778b512e002d856952b4f01842ba4d34bc3d1 Author: Pekka Enberg penb...@kernel.org AuthorDate: Wed, 13 Nov 2013 14:21:48 +0200 Committer: Arnaldo Carvalho de Melo a...@redhat.com CommitDate: Thu, 14 Nov

[PATCH] perf trace: Tweak summary output

2013-11-13 Thread Pekka Enberg
...@redhat.com Cc: Arnaldo Carvalho de Melo a...@ghostprotocols.net Signed-off-by: Pekka Enberg penb...@kernel.org --- tools/perf/builtin-trace.c | 10 +- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 2a6149e

Re: [PATCH] perf trace: Tweak summary output

2013-11-13 Thread Pekka Enberg
On Wed, Nov 13, 2013 at 2:57 PM, Ingo Molnar mi...@kernel.org wrote: Are you convinced about double-digit precision output for percentages? I think it suggest a false level of accuracy, but YYMV - typographically xx.yy certainly looks nicer than xx.y (it's more symmetric). Yeah, I think it's

Re: [PATCH 0/3] Early use of boot service memory

2013-11-12 Thread Pekka Enberg
On Tue, Nov 12, 2013 at 4:15 AM, Jerry Hoemann jerry.hoem...@hp.com wrote: Some platform have firmware that violates UEFI spec and access boot service code or data segments after the system has called Exit Boot Services. The call to efi_reserve_boot_services in setup_arch is a work around to

Re: [RFC/PATCHSET 00/14] perf report: Add support to accumulate hist periods (v2)

2013-11-12 Thread Pekka Enberg
On 11/06/2013 05:33 PM, David Ahern wrote: On 11/6/13, 4:47 AM, Ingo Molnar wrote: I'm not too worried about call-graph 'legacies': it generates such huge perf.data files which is parsed so slowly at the moment that there's very little user base ... Anyone who absolutely needs call-graph

[PATCH] perf trace: Fix syscall summary duration order

2013-11-12 Thread Pekka Enberg
Switch duration order to minimum, average, maximum for the '--summary' command line option because it's more natural to read. Cc: David Ahern dsah...@gmail.com Cc: Ingo Molnar mi...@redhat.com Cc: Arnaldo Carvalho de Melo a...@ghostprotocols.net Signed-off-by: Pekka Enberg penb...@kernel.org

[PATCH] perf trace: Simplify '--summary' output

2013-11-12 Thread Pekka Enberg
a...@ghostprotocols.net Signed-off-by: Pekka Enberg penb...@kernel.org --- tools/perf/builtin-trace.c | 25 - 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f841d2a..22354c8 100644 --- a/tools/perf

Re: [PATCH] perf trace: Add summary only option

2013-11-12 Thread Pekka Enberg
Ahern dsah...@gmail.com Cc: Pekka Enberg penb...@kernel.org Cc: Ingo Molnar mi...@kernel.org Cc: Jiri Olsa jo...@redhat.com Cc: Namhyung Kim namhy...@kernel.org Cc: Adrian Hunter adrian.hun...@intel.com --- Thanks David! Tested-by: Pekka Enberg penb...@kernel.org -- To unsubscribe from this list

Re: [PATCH 0/3] Early use of boot service memory

2013-11-12 Thread Pekka Enberg
Hi Jerry, On Tue, Nov 12, 2013 at 7:55 PM, jerry.hoem...@hp.com wrote: My change does not address platforms that have misbehaving firmware. It just allows platforms that don't have this issue to avoid issues that the call to efi_reserve_boot_services presents. The problem I have with your

Re: [PATCH] perf trace: Simplify '--summary' output

2013-11-12 Thread Pekka Enberg
On 11/12/13 11:36 PM, David Ahern wrote: On 11/12/13, 2:33 PM, Ingo Molnar wrote: Summary of events: dbus-daemon (555), 10 events, 0.0%, 0.000 msec msec/call syscallcalls min avg max stddev --- --

[tip:perf/urgent] perf trace: Change syscall summary duration order

2013-11-12 Thread tip-bot for Pekka Enberg
Commit-ID: 7f7a4138c66e857cc5bbf6e248a47379765349b5 Gitweb: http://git.kernel.org/tip/7f7a4138c66e857cc5bbf6e248a47379765349b5 Author: Pekka Enberg penb...@kernel.org AuthorDate: Tue, 12 Nov 2013 16:10:10 +0200 Committer: Arnaldo Carvalho de Melo a...@redhat.com CommitDate: Tue, 12 Nov

[tip:perf/urgent] perf trace: Simplify '--summary' output

2013-11-12 Thread tip-bot for Pekka Enberg
Commit-ID: 99ff7150547382ee612c40d8d6a0670ddec7c9fc Gitweb: http://git.kernel.org/tip/99ff7150547382ee612c40d8d6a0670ddec7c9fc Author: Pekka Enberg penb...@kernel.org AuthorDate: Tue, 12 Nov 2013 16:42:14 +0200 Committer: Arnaldo Carvalho de Melo a...@redhat.com CommitDate: Tue, 12 Nov

Re: [PATCH] perf trace: Simplify '--summary' output

2013-11-12 Thread Pekka Enberg
On 11/12/13 11:40 PM, Ingo Molnar wrote: So if you prefer unit-less lines that's defensible, perhaps output the unit somewhere else: syscallcalls min avg max stddev (msec) (msec) (msec)(%) ---

Re: [RFC/PATCHSET 00/14] perf report: Add support to accumulate hist periods (v2)

2013-11-01 Thread Pekka Enberg
On Fri, Nov 1, 2013 at 9:55 AM, Ingo Molnar mi...@kernel.org wrote: Btw., if anyone is interested in improving the GTK front-end, it would be _really_ nice if it had a 'start profiling' button like sysprof has today, with a 'samples' field showing the current number of samples. (We could even

Re: [PATCH v2 13/15] slab: use struct page for slab management

2013-10-30 Thread Pekka Enberg
On 10/30/2013 10:28 AM, Joonsoo Kim wrote: If you want an incremental patch against original patchset, I can do it. Please let me know what you want. Yes, please. Incremental is much easier to deal with if we want this to end up in v3.13. Pekka -- To unsubscribe from

Re: [PATCH v4 2/3] Support for perf to probe into SDT markers:

2013-10-30 Thread Pekka Enberg
On 10/30/13 12:05 PM, Masami Hiramatsu wrote: To find all system libraries, we can use ldconfig. $ ldconfig --print-cache shows what dynamic libraries will be loaded. On my own laptop (running ubuntu13.04) shows ~1000 libs. Good point. That definitely narrows down the scanned set.

Re: [PATCH v4 2/3] Support for perf to probe into SDT markers:

2013-10-29 Thread Pekka Enberg
On 10/29/2013 11:55 AM, Hemant Kumar wrote: 1. Where this cache should be? Keeping it in tracing directory inside the debugfs directory should seem more feasible. And, shall this cache be shareable? You can't share all of the cache because otherwise you'll expose details on binaries that not

Re: Re: [PATCH v4 2/3] Support for perf to probe into SDT markers:

2013-10-29 Thread Pekka Enberg
On Tue, Oct 29, 2013 at 4:51 PM, Mark Wielaard m...@redhat.com wrote: A nice user case to think about when designing this interface might be the java hotspot jvm (libjvm.so). It has SDT markers with the same name that might occur at multiple addresses depending on code path taken or compiler

Re: [PATCH v4 2/3] Support for perf to probe into SDT markers:

2013-10-28 Thread Pekka Enberg
On 10/26/2013 02:16 PM, Frank Ch. Eigler wrote: Pekka Enberg penb...@kernel.org writes: Is there a technical reason why 'perf list' could not show all the available SDT markers on a system and that the 'mark to event' mapping cannot happen automatically? [...] A quick experiment

Re: [PATCH v4 2/3] Support for perf to probe into SDT markers:

2013-10-28 Thread Pekka Enberg
Hi David, On 10/25/2013 06:20 PM, David Ahern wrote: On 10/25/13 8:20 AM, Pekka Enberg wrote: Technically feasible. But then we would have to parse each of the libraries and executables to list them. Right? I am not sure if such a delay is acceptable. You could do it at 'perf list' time

Re: [PATCH v4 2/3] Support for perf to probe into SDT markers:

2013-10-28 Thread Pekka Enberg
On 10/26/2013 12:50 PM, Ingo Molnar wrote: I think in 99% of the usecases people will either use pre-built markers that come with their distro, or will be intimately aware of the markers because they are in the very app they are developing. So I wouldn't worry about 'user has a weird binary'

Re: [PATCH v4 2/3] Support for perf to probe into SDT markers:

2013-10-28 Thread Pekka Enberg
On 10/28/13 1:23 PM, Masami Hiramatsu wrote: By the way, what happens if multiple binaries has same SDT marker? Yeah, perf list shows just one and ignores others. However, if we probe one, and run binary which use the other one, user will never see the marker. So, it still needs a concrete

Re: [PATCH v4 2/3] Support for perf to probe into SDT markers:

2013-10-28 Thread Pekka Enberg
On 10/28/2013 04:11 PM, Srikar Dronamraju wrote: But what if a system has both 32 bit libc and 64 bit libc? Wont we could end up with 2 libc:setjmp? Should we give some more intelligence into perf to choose the 64 bit libc over 32 bit one? You can just trace both of them by default, no?

Re: [PATCH v4 2/3] Support for perf to probe into SDT markers:

2013-10-28 Thread Pekka Enberg
On 10/28/13 7:31 PM, Srikar Dronamraju wrote: But what if a system has both 32 bit libc and 64 bit libc? Wont we could end up with 2 libc:setjmp? Should we give some more intelligence into perf to choose the 64 bit libc over 32 bit one? You can just trace both of them by default, no? There

  1   2   3   4   5   6   7   8   9   >