On 2014-09-29 15:12:58 +0200, Loic Dachary wrote:
>
>
> On 29/09/2014 14:34, Janne Grunau wrote:
> > SIMD optimized erasure code computation needs aligned memory. Buffers
> > aligned to a page boundary are not needed though. The buffers used
> > for the erasure code computation are typical smaller than a page.
> >
> > The typical alignment requirements SIMD operations are 16 bytes for
> > SSE2 and NEON and 32 bytes for AVX/AVX2.
> >
> > Signed-off-by: Janne Grunau <j...@jannau.net>
> > ---
> > configure.ac | 9 +++++
> > src/common/buffer.cc | 106
> > +++++++++++++++++++++++++++++++++++++++++++++++++++
> > src/include/buffer.h | 15 ++++++++
> > 3 files changed, 130 insertions(+)
> >
> > diff --git a/configure.ac b/configure.ac
> > index cccf2d9..1bb27c4 100644
> > --- a/configure.ac
> > +++ b/configure.ac
> > @@ -793,6 +793,15 @@ AC_MSG_RESULT([no])
> > ])
> >
> > #
> > +# Check for functions to provide aligned memory
> > +#
> > +AC_CHECK_HEADERS([malloc.h])
> > +AC_CHECK_FUNCS([posix_memalign _aligned_malloc memalign aligned_malloc],
> > + [found_memalign=yes; break])
> > +
> > +AS_IF([test "x$found_memalign" != "xyes"], [AC_MSG_WARN([No function for
> > aligned memory allocation found])])
> > +
> > +#
> > # Check for pthread spinlock (depends on ACX_PTHREAD)
> > #
> > saved_LIBS="$LIBS"
> > diff --git a/src/common/buffer.cc b/src/common/buffer.cc
> > index af298ac..dfe887e 100644
> > --- a/src/common/buffer.cc
> > +++ b/src/common/buffer.cc
> > @@ -30,6 +30,10 @@
> > #include <sys/uio.h>
> > #include <limits.h>
> >
> > +#ifdef HAVE_MALLOC_H
> > +#include <malloc.h>
> > +#endif
> > +
> > namespace ceph {
> >
> > #ifdef BUFFER_DEBUG
> > @@ -155,9 +159,17 @@ static simple_spinlock_t buffer_debug_lock =
> > SIMPLE_SPINLOCK_INITIALIZER;
> > virtual int zero_copy_to_fd(int fd, loff_t *offset) {
> > return -ENOTSUP;
> > }
> > + virtual bool is_aligned(unsigned align) {
> > + assert((align >= sizeof(void *)) && (align & (align - 1)) == 0);
> > + return ((intptr_t)data & (align - 1)) == 0;
> > + }
> > virtual bool is_page_aligned() {
> > return ((long)data & ~CEPH_PAGE_MASK) == 0;
> > }
> > + bool is_n_align_sized(unsigned align) {
> > + assert((align >= sizeof(void *)) && (align & (align - 1)) == 0);
>
> This does not seem necessary in this context ?
it is not strictly necessary but I would still consider it a bug if
is_n_align_sized() is called with an align parameter that is not
supported for allocating buffers.
Janne
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
