Message ID | 20200325014205.11843-5-david@fromorbit.com (mailing list archive) |
---|---|
State | Accepted |
Headers | show |
Series | xfs: various fixes and cleanups | expand |
On 3/24/20 6:42 PM, Dave Chinner wrote: > From: Dave Chinner <dchinner@redhat.com> > > The buffer cache shrinker frees more than just the xfs_buf slab > objects - it also frees the pages attached to the buffers. Make sure > the memory reclaim code accounts for this memory being freed > correctly, similar to how the inode shrinker accounts for pages > freed from the page cache due to mapping invalidation. > > We also need to make sure that the mm subsystem knows these are > reclaimable objects. We provide the memory reclaim subsystem with a > a shrinker to reclaim xfs_bufs, so we should really mark the slab > that way. > > We also have a lot of xfs_bufs in a busy system, spread them around > like we do inodes. > > Signed-off-by: Dave Chinner <dchinner@redhat.com> Ok, makes sense Reviewed-by: Allison Collins <allison.henderson@oracle.com> > --- > fs/xfs/xfs_buf.c | 11 ++++++++--- > 1 file changed, 8 insertions(+), 3 deletions(-) > > diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c > index f880141a22681..9ec3eaf1c618f 100644 > --- a/fs/xfs/xfs_buf.c > +++ b/fs/xfs/xfs_buf.c > @@ -327,6 +327,9 @@ xfs_buf_free( > > __free_page(page); > } > + if (current->reclaim_state) > + current->reclaim_state->reclaimed_slab += > + bp->b_page_count; > } else if (bp->b_flags & _XBF_KMEM) > kmem_free(bp->b_addr); > _xfs_buf_free_pages(bp); > @@ -2114,9 +2117,11 @@ xfs_buf_delwri_pushbuf( > int __init > xfs_buf_init(void) > { > - xfs_buf_zone = kmem_cache_create("xfs_buf", > - sizeof(struct xfs_buf), 0, > - SLAB_HWCACHE_ALIGN, NULL); > + xfs_buf_zone = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, > + SLAB_HWCACHE_ALIGN | > + SLAB_RECLAIM_ACCOUNT | > + SLAB_MEM_SPREAD, > + NULL); > if (!xfs_buf_zone) > goto out; > >
On Wed, Mar 25, 2020 at 12:42:01PM +1100, Dave Chinner wrote: > From: Dave Chinner <dchinner@redhat.com> > > The buffer cache shrinker frees more than just the xfs_buf slab > objects - it also frees the pages attached to the buffers. Make sure > the memory reclaim code accounts for this memory being freed > correctly, similar to how the inode shrinker accounts for pages > freed from the page cache due to mapping invalidation. > > We also need to make sure that the mm subsystem knows these are > reclaimable objects. We provide the memory reclaim subsystem with a > a shrinker to reclaim xfs_bufs, so we should really mark the slab > that way. > > We also have a lot of xfs_bufs in a busy system, spread them around > like we do inodes. > > Signed-off-by: Dave Chinner <dchinner@redhat.com> > --- https://lore.kernel.org/linux-xfs/20191101120513.GD59146@bfoster/ > fs/xfs/xfs_buf.c | 11 ++++++++--- > 1 file changed, 8 insertions(+), 3 deletions(-) > > diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c > index f880141a22681..9ec3eaf1c618f 100644 > --- a/fs/xfs/xfs_buf.c > +++ b/fs/xfs/xfs_buf.c > @@ -327,6 +327,9 @@ xfs_buf_free( > > __free_page(page); > } > + if (current->reclaim_state) > + current->reclaim_state->reclaimed_slab += > + bp->b_page_count; > } else if (bp->b_flags & _XBF_KMEM) > kmem_free(bp->b_addr); > _xfs_buf_free_pages(bp); > @@ -2114,9 +2117,11 @@ xfs_buf_delwri_pushbuf( > int __init > xfs_buf_init(void) > { > - xfs_buf_zone = kmem_cache_create("xfs_buf", > - sizeof(struct xfs_buf), 0, > - SLAB_HWCACHE_ALIGN, NULL); > + xfs_buf_zone = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, > + SLAB_HWCACHE_ALIGN | > + SLAB_RECLAIM_ACCOUNT | > + SLAB_MEM_SPREAD, > + NULL); > if (!xfs_buf_zone) > goto out; > > -- > 2.26.0.rc2 >
On Wed, Mar 25, 2020 at 12:42:01PM +1100, Dave Chinner wrote: > From: Dave Chinner <dchinner@redhat.com> > > The buffer cache shrinker frees more than just the xfs_buf slab > objects - it also frees the pages attached to the buffers. Make sure > the memory reclaim code accounts for this memory being freed > correctly, similar to how the inode shrinker accounts for pages > freed from the page cache due to mapping invalidation. > > We also need to make sure that the mm subsystem knows these are > reclaimable objects. We provide the memory reclaim subsystem with a > a shrinker to reclaim xfs_bufs, so we should really mark the slab > that way. > > We also have a lot of xfs_bufs in a busy system, spread them around > like we do inodes. > > Signed-off-by: Dave Chinner <dchinner@redhat.com> Looks decent, Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> --D > --- > fs/xfs/xfs_buf.c | 11 ++++++++--- > 1 file changed, 8 insertions(+), 3 deletions(-) > > diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c > index f880141a22681..9ec3eaf1c618f 100644 > --- a/fs/xfs/xfs_buf.c > +++ b/fs/xfs/xfs_buf.c > @@ -327,6 +327,9 @@ xfs_buf_free( > > __free_page(page); > } > + if (current->reclaim_state) > + current->reclaim_state->reclaimed_slab += > + bp->b_page_count; > } else if (bp->b_flags & _XBF_KMEM) > kmem_free(bp->b_addr); > _xfs_buf_free_pages(bp); > @@ -2114,9 +2117,11 @@ xfs_buf_delwri_pushbuf( > int __init > xfs_buf_init(void) > { > - xfs_buf_zone = kmem_cache_create("xfs_buf", > - sizeof(struct xfs_buf), 0, > - SLAB_HWCACHE_ALIGN, NULL); > + xfs_buf_zone = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, > + SLAB_HWCACHE_ALIGN | > + SLAB_RECLAIM_ACCOUNT | > + SLAB_MEM_SPREAD, > + NULL); > if (!xfs_buf_zone) > goto out; > > -- > 2.26.0.rc2 >
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index f880141a22681..9ec3eaf1c618f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -327,6 +327,9 @@ xfs_buf_free( __free_page(page); } + if (current->reclaim_state) + current->reclaim_state->reclaimed_slab += + bp->b_page_count; } else if (bp->b_flags & _XBF_KMEM) kmem_free(bp->b_addr); _xfs_buf_free_pages(bp); @@ -2114,9 +2117,11 @@ xfs_buf_delwri_pushbuf( int __init xfs_buf_init(void) { - xfs_buf_zone = kmem_cache_create("xfs_buf", - sizeof(struct xfs_buf), 0, - SLAB_HWCACHE_ALIGN, NULL); + xfs_buf_zone = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0, + SLAB_HWCACHE_ALIGN | + SLAB_RECLAIM_ACCOUNT | + SLAB_MEM_SPREAD, + NULL); if (!xfs_buf_zone) goto out;