* David Goulet (david.gou...@polymtl.ca) wrote:
Hi,
I have some doubt about the value of #define CACHE_LINE_SIZE
(urcu/arch_x86.h) that is set to 128.
After some research and looking on my computer, the x86 architecture
seems to have most of the time 64 bytes size. On my i7 920, here's
* David Goulet (david.gou...@polymtl.ca) wrote:
Signed-off-by: David Goulet david.gou...@polymtl.ca
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
---
ChangeLog | 11 +++
1 files changed, 11 insertions(+), 0 deletions(-)
diff --git a/ChangeLog b/ChangeLog
* David Goulet (david.gou...@polymtl.ca) wrote:
On 10-08-17 02:51 PM, Mathieu Desnoyers wrote:
* David Goulet (david.gou...@polymtl.ca) wrote:
Hi,
I have some doubt about the value of #define CACHE_LINE_SIZE
(urcu/arch_x86.h) that is set to 128.
After some research and looking on my
* David Goulet (david.gou...@polymtl.ca) wrote:
Signed-off-by: David Goulet david.gou...@polymtl.ca
---
libust/buffers.c|4 ++--
libust/marker.c |6 +++---
libust/tracectl.c |4 ++--
libust/tracepoint.c |8
4 files changed, 11 insertions(+), 11
On 10-08-17 03:45 PM, Mathieu Desnoyers wrote:
* David Goulet (david.gou...@polymtl.ca) wrote:
On 10-08-17 02:51 PM, Mathieu Desnoyers wrote:
* David Goulet (david.gou...@polymtl.ca) wrote:
Hi,
I have some doubt about the value of #define CACHE_LINE_SIZE
(urcu/arch_x86.h) that is set to
On 10-08-17 03:54 PM, Mathieu Desnoyers wrote:
* Mathieu Desnoyers (comp...@krystal.dyndns.org) wrote:
* David Goulet (david.gou...@polymtl.ca) wrote:
On 10-08-17 02:51 PM, Mathieu Desnoyers wrote:
* David Goulet (david.gou...@polymtl.ca) wrote:
Hi,
I have some
* David Goulet (david.gou...@polymtl.ca) wrote:
On 10-08-17 03:45 PM, Mathieu Desnoyers wrote:
[...]
Yes. The performance degradation caused by cache-line bouncing is _way_
worse than extra cache pressure.
There is something I don't understand here. Correct me if (most likely)
I am wrong.
* Alexandre Montplaisir (alexandre.montplai...@polymtl.ca) wrote:
On 10-08-17 03:54 PM, Mathieu Desnoyers wrote:
[...]
Oh, and by the way, given that these are arrays made of one variable per
cpu, the extra space allocated will not consume extra cache lines in any
of the CPU. We're just
On 10-08-17 04:24 PM, Mathieu Desnoyers wrote:
* David Goulet (david.gou...@polymtl.ca) wrote:
On 10-08-17 03:45 PM, Mathieu Desnoyers wrote:
[...]
Yes. The performance degradation caused by cache-line bouncing is _way_
worse than extra cache pressure.
There is something I don't
For libustcomm, libustd, ustctl and ustd.
Signed-off-by: David Goulet david.gou...@polymtl.ca
---
libustcomm/multipoll.c |4 ++--
libustcomm/ustcomm.c | 22 +++---
libustd/libustd.c |6 +++---
ustctl/ustctl.c|2 +-
ustd/ustd.c|7
* David Goulet (david.gou...@polymtl.ca) wrote:
On 10-08-17 04:24 PM, Mathieu Desnoyers wrote:
* David Goulet (david.gou...@polymtl.ca) wrote:
On 10-08-17 03:45 PM, Mathieu Desnoyers wrote:
[...]
Yes. The performance degradation caused by cache-line bouncing is _way_
worse than extra cache
* Alexandre Montplaisir (alexandre.montplai...@polymtl.ca) wrote:
On 10-08-17 04:27 PM, Mathieu Desnoyers wrote:
* Alexandre Montplaisir (alexandre.montplai...@polymtl.ca) wrote:
On 10-08-17 03:54 PM, Mathieu Desnoyers wrote:
[...]
Oh, and by the way, given that these are
* David Goulet (david.gou...@polymtl.ca) wrote:
For libustcomm, libustd, ustctl and ustd.
Signed-off-by: David Goulet david.gou...@polymtl.ca
---
libustcomm/multipoll.c |4 ++--
libustcomm/ustcomm.c | 22 +++---
libustd/libustd.c |6 +++---
Hi Mathieu,
I have a quite big problem since the new patch with strncpy for UST.
With a high number of events (10 +), I got this :
buffers.h:525: ust_buffers_write: Assertion `buf_offset + len
buf-chan-subbuf_size*buf-chan-subbuf_cnt' failed.
At that line in (libust/buffers.h) you have
* David Goulet (david.gou...@polymtl.ca) wrote:
Hi Mathieu,
I have a quite big problem since the new patch with strncpy for UST.
With a high number of events (10 +), I got this :
buffers.h:525: ust_buffers_write: Assertion `buf_offset + len
buf-chan-subbuf_size*buf-chan-subbuf_cnt'
fix off by one in strncpy and write asserts(). Shows only when the event
reserved fits the exact end of buffer.
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
---
libust/buffers.h |6 --
1 file changed, 4 insertions(+), 2 deletions(-)
Index: ust/libust/buffers.h
Support __HAVE_ARCH_INLINE_MEMCPY. Start with a fall-back to memcpy().
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
---
include/linux/string.h |3 +++
1 file changed, 3 insertions(+)
Index: linux.trees.git/include/linux/string.h
Move idle notifiers into arch-agnostic code. Adapt x86 64 accordingly to call
the new architecture-agnostic notifiers rather than its own. Other architectures
are still todo.
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
---
arch/x86/include/asm/idle.h |7 ---
This patchset implements a generic ring buffer library, which provides a very
efficient, yet flexible, API to both tracers and drivers to move large amounts
of data within and outside of kernel-space.
It comes as a response to Linus mandate from the 2008 Kernel Summit. In May
2010, Steven
Implements per-cpu-local iterator and channel-wide iterator. Implements a read()
file operation based on these iterators. These iterators or the read() file
operation can be used by ring buffer clients.
The channel-wide iterator implements timestamp-ordered fusion merge of per-cpu
channels using
Changelog since v1:
* Use basic api configuration structure to specify the ring buffer behavior
rather than duplicating API members needlessly.
Offer basic APIs for pre-built ring buffer clients:
- Global Overwrite
- Global Discard
- Per-cpu Overwrite with channel-wide iterator
- Per-cpu
Being able to use the atomic notifier from cpu idle entry to ensure the tracer
flush the last events in the current subbuffer requires the rcu read-side to be
marked notrace.
Also apply to the the die notifier.
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
Reviewed-by: Paul E.
Building the trace clock without CONFIG_TRACING enabled is useful for the ring
buffer library sample client.
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
---
kernel/Makefile|1 +
kernel/trace/Kconfig |3 +++
kernel/trace/trace_clock.c |3 +++
3
Changelog since v1:
* Adapt to Basic API v2.
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
---
kernel/trace/Makefile |8
kernel/trace/lib_global_discard_ring_buffer_benchmark.c | 14
Ring buffer backend, with page allocation, data read/write API, cpu hotplug
management.
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
---
include/linux/ringbuffer/backend.h | 141 +
include/linux/ringbuffer/backend_internal.h | 418 +++
Executive summary:
poll_wait_set_exclusive : set poll wait queue to exclusive
Sets up a poll wait queue to use exclusive wakeups. This is useful to
wake up only one waiter at each wakeup. Used to work-around thundering herd
problem.
Detail:
* Problem description :
In the ring buffer poll()
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
---
kernel/trace/Kconfig |1
kernel/trace/Makefile|1
kernel/trace/lib_ring_buffer_benchmark.c | 659 +++
3 files changed, 661 insertions(+)
Index:
Changelog since v1:
* Update documentation matching new basic API.
Signed-off-by: Mathieu Desnoyers mathieu.desnoy...@efficios.com
---
Documentation/ring-buffer/ring-buffer-design.txt | 78 +++
Documentation/ring-buffer/ring-buffer-usage.txt | 254 +++
2 files
* Kirill A. Shutemov (kir...@shutemov.name) wrote:
Index: linux.trees.git/include/linux/align.h
===
--- /dev/null 1970-01-01 00:00:00.0 +
+++ linux.trees.git/include/linux/align.h 2010-08-17
29 matches
Mail list logo