When tmpfs has the memory policy interleaved it always starts allocating at 
each file at node 0.
When there are many small files the lower nodes fill up disproportionately.
My proposed solution is to start a file at a randomly chosen node.

Cc: Christoph Lameter <[email protected]>
Cc: Nick Piggin <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Lee Schermerhorn <[email protected]>
Cc: [email protected]
Signed-off-by: Nathan T Zimmer <[email protected]>


diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 
79ab255..38eda26 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -17,6 +17,7 @@ struct shmem_inode_info {
                char            *symlink;       /* unswappable short symlink */
        };
        struct shared_policy    policy;         /* NUMA memory alloc policy */
+       int                     node_offset;    /* bias for interleaved nodes */
        struct list_head        swaplist;       /* chain of maybes on swap */
        struct list_head        xattr_list;     /* list of shmem_xattr */
        struct inode            vfs_inode;
diff --git a/mm/shmem.c b/mm/shmem.c
index f99ff3e..58ef512 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -819,7 +819,7 @@ static struct page *shmem_alloc_page(gfp_t gfp,
 
        /* Create a pseudo vma that just contains the policy */
        pvma.vm_start = 0;
-       pvma.vm_pgoff = index;
+       pvma.vm_pgoff = index + info->node_offset;
        pvma.vm_ops = NULL;
        pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);
 
@@ -1153,6 +1153,7 @@ static struct inode *shmem_get_inode(struct super_block 
*sb, const struct inode
                        inode->i_fop = &shmem_file_operations;
                        mpol_shared_policy_init(&info->policy,
                                                 shmem_get_sbmpol(sbinfo));
+                       info->node_offset = node_random(&node_online_map);
                        break;
                case S_IFDIR:
                        inc_nlink(inode);


--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to