ocfs2: allocation reservations
This patch improves Ocfs2 allocation policy by allowing an inode to
reserve a portion of the local alloc bitmap for itself. The reserved
portion (allocation window) is advisory in that other allocation
windows might steal it if the local alloc bitmap becomes
full. Otherwise, the reservations are honored and guaranteed to be
free. When the local alloc window is moved to a different portion of
the bitmap, existing reservations are discarded.
Reservation windows are represented internally by a red-black
tree. Within that tree, each node represents the reservation window of
one inode. An LRU of active reservations is also maintained. When new
data is written, we allocate it from the inodes window. When all bits
in a window are exhausted, we allocate a new one as close to the
previous one as possible. Should we not find free space, an existing
reservation is pulled off the LRU and cannibalized.
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index dee0319..cfe672e 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -95,6 +95,7 @@
unsigned int atime_quantum;
signed short slot;
unsigned int localalloc_opt;
+ unsigned int resv_level;
char cluster_stack[OCFS2_STACK_LABEL_LEN + 1];
};
@@ -176,6 +177,7 @@
Opt_noacl,
Opt_usrquota,
Opt_grpquota,
+ Opt_resv_level,
Opt_err,
};
@@ -202,6 +204,7 @@
{Opt_noacl, "noacl"},
{Opt_usrquota, "usrquota"},
{Opt_grpquota, "grpquota"},
+ {Opt_resv_level, "resv_level=%u"},
{Opt_err, NULL}
};
@@ -1030,6 +1033,7 @@
osb->osb_commit_interval = parsed_options.commit_interval;
osb->local_alloc_default_bits = ocfs2_megabytes_to_clusters(sb, parsed_options.localalloc_opt);
osb->local_alloc_bits = osb->local_alloc_default_bits;
+ osb->osb_resv_level = parsed_options.resv_level;
status = ocfs2_verify_userspace_stack(osb, &parsed_options);
if (status)
@@ -1290,6 +1294,7 @@
mopt->slot = OCFS2_INVALID_SLOT;
mopt->localalloc_opt = OCFS2_DEFAULT_LOCAL_ALLOC_SIZE;
mopt->cluster_stack[0] = '\0';
+ mopt->resv_level = OCFS2_DEFAULT_RESV_LEVEL;
if (!options) {
status = 1;
@@ -1433,6 +1438,17 @@
mopt->mount_opt |= OCFS2_MOUNT_NO_POSIX_ACL;
mopt->mount_opt &= ~OCFS2_MOUNT_POSIX_ACL;
break;
+ case Opt_resv_level:
+ if (is_remount)
+ break;
+ if (match_int(&args[0], &option)) {
+ status = 0;
+ goto bail;
+ }
+ if (option >= OCFS2_MIN_RESV_LEVEL &&
+ option < OCFS2_MAX_RESV_LEVEL)
+ mopt->resv_level = option;
+ break;
default:
mlog(ML_ERROR,
"Unrecognized mount option \"%s\" "
@@ -1514,6 +1530,9 @@
else
seq_printf(s, ",noacl");
+ if (osb->osb_resv_level != OCFS2_DEFAULT_RESV_LEVEL)
+ seq_printf(s, ",resv_level=%d", osb->osb_resv_level);
+
return 0;
}
@@ -2042,6 +2061,12 @@
init_waitqueue_head(&osb->osb_mount_event);
+ status = ocfs2_resmap_init(osb, &osb->osb_la_resmap);
+ if (status) {
+ mlog_errno(status);
+ goto bail;
+ }
+
osb->vol_label = kmalloc(OCFS2_MAX_VOL_LABEL_LEN, GFP_KERNEL);
if (!osb->vol_label) {
mlog(ML_ERROR, "unable to alloc vol label\n");