summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/filesystems/orangefs.txt50
-rw-r--r--fs/orangefs/dcache.c4
-rw-r--r--fs/orangefs/inode.c6
-rw-r--r--fs/orangefs/namei.c12
-rw-r--r--fs/orangefs/orangefs-kernel.h6
-rw-r--r--fs/orangefs/orangefs-mod.c2
-rw-r--r--fs/orangefs/orangefs-sysfs.c43
-rw-r--r--fs/orangefs/orangefs-utils.c38
-rw-r--r--fs/orangefs/protocol.h8
9 files changed, 135 insertions, 34 deletions
diff --git a/Documentation/filesystems/orangefs.txt b/Documentation/filesystems/orangefs.txt
index e1a0056a365f..1dfdec790946 100644
--- a/Documentation/filesystems/orangefs.txt
+++ b/Documentation/filesystems/orangefs.txt
@@ -281,7 +281,7 @@ on the wait queue and one attempt is made to recycle them. Obviously,
if the client-core stays dead too long, the arbitrary userspace processes
trying to use Orangefs will be negatively affected. Waiting ops
that can't be serviced will be removed from the request list and
-have their states set to "given up". In-progress ops that can't
+have their states set to "given up". In-progress ops that can't
be serviced will be removed from the in_progress hash table and
have their states set to "given up".
@@ -338,7 +338,7 @@ particular response.
PVFS2_VFS_OP_STATFS
fill a pvfs2_statfs_response_t with useless info <g>. It is hard for
us to know, in a timely fashion, these statistics about our
- distributed network filesystem.
+ distributed network filesystem.
PVFS2_VFS_OP_FS_MOUNT
fill a pvfs2_fs_mount_response_t which is just like a PVFS_object_kref
@@ -386,7 +386,7 @@ responses:
io_array[1].iov_base = address of global variable "pdev_magic" (int32_t)
io_array[1].iov_len = sizeof(int32_t)
-
+
io_array[2].iov_base = address of parameter "tag" (PVFS_id_gen_t)
io_array[2].iov_len = sizeof(int64_t)
@@ -402,5 +402,47 @@ Readdir responses initialize the fifth element io_array like this:
io_array[4].iov_len = contents of member trailer_size (PVFS_size)
from out_downcall member of global variable
vfs_request
-
+
+Orangefs exploits the dcache in order to avoid sending redundant
+requests to userspace. We keep object inode attributes up-to-date with
+orangefs_inode_getattr. Orangefs_inode_getattr uses two arguments to
+help it decide whether or not to update an inode: "new" and "bypass".
+Orangefs keeps private data in an object's inode that includes a short
+timeout value, getattr_time, which allows any iteration of
+orangefs_inode_getattr to know how long it has been since the inode was
+updated. When the object is not new (new == 0) and the bypass flag is not
+set (bypass == 0) orangefs_inode_getattr returns without updating the inode
+if getattr_time has not timed out. Getattr_time is updated each time the
+inode is updated.
+
+Creation of a new object (file, dir, sym-link) includes the evaluation of
+its pathname, resulting in a negative directory entry for the object.
+A new inode is allocated and associated with the dentry, turning it from
+a negative dentry into a "productive full member of society". Orangefs
+obtains the new inode from Linux with new_inode() and associates
+the inode with the dentry by sending the pair back to Linux with
+d_instantiate().
+
+The evaluation of a pathname for an object resolves to its corresponding
+dentry. If there is no corresponding dentry, one is created for it in
+the dcache. Whenever a dentry is modified or verified Orangefs stores a
+short timeout value in the dentry's d_time, and the dentry will be trusted
+for that amount of time. Orangefs is a network filesystem, and objects
+can potentially change out-of-band with any particular Orangefs kernel module
+instance, so trusting a dentry is risky. The alternative to trusting
+dentries is to always obtain the needed information from userspace - at
+least a trip to the client-core, maybe to the servers. Obtaining information
+from a dentry is cheap, obtaining it from userspace is relatively expensive,
+hence the motivation to use the dentry when possible.
+
+The timeout values d_time and getattr_time are jiffy based, and the
+code is designed to avoid the jiffy-wrap problem:
+
+"In general, if the clock may have wrapped around more than once, there
+is no way to tell how much time has elapsed. However, if the times t1
+and t2 are known to be fairly close, we can reliably compute the
+difference in a way that takes into account the possibility that the
+clock may have wrapped between times."
+
+ from course notes by instructor Andy Wang
diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c
index 5dfc4f3cfe68..00235bf644dc 100644
--- a/fs/orangefs/dcache.c
+++ b/fs/orangefs/dcache.c
@@ -73,6 +73,7 @@ static int orangefs_revalidate_lookup(struct dentry *dentry)
}
}
+ dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
ret = 1;
out_release_op:
op_release(new_op);
@@ -94,6 +95,9 @@ static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
int ret;
+ if (time_before(jiffies, dentry->d_time))
+ return 1;
+
if (flags & LOOKUP_RCU)
return -ECHILD;
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 2e63e6d0a68e..28a0557a69be 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -262,7 +262,7 @@ int orangefs_getattr(struct vfsmount *mnt,
"orangefs_getattr: called on %s\n",
dentry->d_name.name);
- ret = orangefs_inode_getattr(inode, 0, 1);
+ ret = orangefs_inode_getattr(inode, 0, 0);
if (ret == 0) {
generic_fillattr(inode, kstat);
@@ -384,7 +384,7 @@ struct inode *orangefs_iget(struct super_block *sb, struct orangefs_object_kref
if (!inode || !(inode->i_state & I_NEW))
return inode;
- error = orangefs_inode_getattr(inode, 1, 0);
+ error = orangefs_inode_getattr(inode, 1, 1);
if (error) {
iget_failed(inode);
return ERR_PTR(error);
@@ -429,7 +429,7 @@ struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir,
orangefs_set_inode(inode, ref);
inode->i_ino = hash; /* needed for stat etc */
- error = orangefs_inode_getattr(inode, 1, 0);
+ error = orangefs_inode_getattr(inode, 1, 1);
if (error)
goto out_iput;
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
index 7e8dfa97c44a..62c525936ee8 100644
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -72,6 +72,8 @@ static int orangefs_create(struct inode *dir,
d_instantiate(dentry, inode);
unlock_new_inode(inode);
+ dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: dentry instantiated for %s\n",
@@ -181,6 +183,8 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
+ dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+
inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
if (IS_ERR(inode)) {
gossip_debug(GOSSIP_NAME_DEBUG,
@@ -189,6 +193,8 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
+ ORANGEFS_I(inode)->getattr_time = jiffies - 1;
+
gossip_debug(GOSSIP_NAME_DEBUG,
"%s:%s:%d "
"Found good inode [%lu] with count [%d]\n",
@@ -316,6 +322,8 @@ static int orangefs_symlink(struct inode *dir,
d_instantiate(dentry, inode);
unlock_new_inode(inode);
+ dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
"Inode (Symlink) %pU -> %s\n",
@@ -378,6 +386,8 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
d_instantiate(dentry, inode);
unlock_new_inode(inode);
+ dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
"Inode (Directory) %pU -> %s\n",
@@ -408,6 +418,8 @@ static int orangefs_rename(struct inode *old_dir,
"orangefs_rename: called (%pd2 => %pd2) ct=%d\n",
old_dentry, new_dentry, d_count(new_dentry));
+ ORANGEFS_I(new_dentry->d_parent->d_inode)->getattr_time = jiffies - 1;
+
new_op = op_alloc(ORANGEFS_VFS_OP_RENAME);
if (!new_op)
return -EINVAL;
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 4b6e132d5a0f..633c07a6e3d8 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -246,6 +246,8 @@ struct orangefs_inode_s {
* with this object
*/
unsigned long pinode_flags;
+
+ unsigned long getattr_time;
};
#define P_ATIME_FLAG 0
@@ -527,7 +529,7 @@ int orangefs_inode_setxattr(struct inode *inode,
size_t size,
int flags);
-int orangefs_inode_getattr(struct inode *inode, int new, int size);
+int orangefs_inode_getattr(struct inode *inode, int new, int bypass);
int orangefs_inode_check_changed(struct inode *inode);
@@ -546,6 +548,8 @@ extern struct mutex request_mutex;
extern int debug;
extern int op_timeout_secs;
extern int slot_timeout_secs;
+extern int dcache_timeout_msecs;
+extern int getattr_timeout_msecs;
extern struct list_head orangefs_superblocks;
extern spinlock_t orangefs_superblocks_lock;
extern struct list_head orangefs_request_list;
diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c
index 6f072a8c0de1..e9fd5755c05f 100644
--- a/fs/orangefs/orangefs-mod.c
+++ b/fs/orangefs/orangefs-mod.c
@@ -47,6 +47,8 @@ struct client_debug_mask client_debug_mask = { NULL, 0, 0 };
unsigned int kernel_mask_set_mod_init; /* implicitly false */
int op_timeout_secs = ORANGEFS_DEFAULT_OP_TIMEOUT_SECS;
int slot_timeout_secs = ORANGEFS_DEFAULT_SLOT_TIMEOUT_SECS;
+int dcache_timeout_msecs = 50;
+int getattr_timeout_msecs = 50;
MODULE_LICENSE("GPL");
MODULE_AUTHOR("ORANGEFS Development Team");
diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c
index 5c03113e3ad2..375708c2db87 100644
--- a/fs/orangefs/orangefs-sysfs.c
+++ b/fs/orangefs/orangefs-sysfs.c
@@ -61,10 +61,21 @@
* Slots are requested and waited for,
* the wait times out after slot_timeout_secs.
*
+ * What: /sys/fs/orangefs/dcache_timeout_msecs
+ * Date: Jul 2016
+ * Contact: Martin Brandenburg <martin@omnibond.com>
+ * Description:
+ * Time lookup is valid in milliseconds.
+ *
+ * What: /sys/fs/orangefs/getattr_timeout_msecs
+ * Date: Jul 2016
+ * Contact: Martin Brandenburg <martin@omnibond.com>
+ * Description:
+ * Time getattr is valid in milliseconds.
*
* What: /sys/fs/orangefs/acache/...
* Date: Jun 2015
- * Contact: Mike Marshall <hubcap@omnibond.com>
+ * Contact: Martin Brandenburg <martin@omnibond.com>
* Description:
* Attribute cache configurable settings.
*
@@ -117,6 +128,8 @@ struct orangefs_obj {
int perf_history_size;
int perf_time_interval_secs;
int slot_timeout_secs;
+ int dcache_timeout_msecs;
+ int getattr_timeout_msecs;
};
struct acache_orangefs_obj {
@@ -658,6 +671,20 @@ static ssize_t sysfs_int_show(char *kobj_id, char *buf, void *attr)
"%d\n",
slot_timeout_secs);
goto out;
+ } else if (!strcmp(orangefs_attr->attr.name,
+ "dcache_timeout_msecs")) {
+ rc = scnprintf(buf,
+ PAGE_SIZE,
+ "%d\n",
+ dcache_timeout_msecs);
+ goto out;
+ } else if (!strcmp(orangefs_attr->attr.name,
+ "getattr_timeout_msecs")) {
+ rc = scnprintf(buf,
+ PAGE_SIZE,
+ "%d\n",
+ getattr_timeout_msecs);
+ goto out;
} else {
goto out;
}
@@ -734,6 +761,12 @@ static ssize_t int_store(struct orangefs_obj *orangefs_obj,
} else if (!strcmp(attr->attr.name, "slot_timeout_secs")) {
rc = kstrtoint(buf, 0, &slot_timeout_secs);
goto out;
+ } else if (!strcmp(attr->attr.name, "dcache_timeout_msecs")) {
+ rc = kstrtoint(buf, 0, &dcache_timeout_msecs);
+ goto out;
+ } else if (!strcmp(attr->attr.name, "getattr_timeout_msecs")) {
+ rc = kstrtoint(buf, 0, &getattr_timeout_msecs);
+ goto out;
} else {
goto out;
}
@@ -1361,6 +1394,12 @@ static struct orangefs_attribute op_timeout_secs_attribute =
static struct orangefs_attribute slot_timeout_secs_attribute =
__ATTR(slot_timeout_secs, 0664, int_orangefs_show, int_store);
+static struct orangefs_attribute dcache_timeout_msecs_attribute =
+ __ATTR(dcache_timeout_msecs, 0664, int_orangefs_show, int_store);
+
+static struct orangefs_attribute getattr_timeout_msecs_attribute =
+ __ATTR(getattr_timeout_msecs, 0664, int_orangefs_show, int_store);
+
static struct orangefs_attribute perf_counter_reset_attribute =
__ATTR(perf_counter_reset,
0664,
@@ -1382,6 +1421,8 @@ static struct orangefs_attribute perf_time_interval_secs_attribute =
static struct attribute *orangefs_default_attrs[] = {
&op_timeout_secs_attribute.attr,
&slot_timeout_secs_attribute.attr,
+ &dcache_timeout_msecs_attribute.attr,
+ &getattr_timeout_msecs_attribute.attr,
&perf_counter_reset_attribute.attr,
&perf_history_size_attribute.attr,
&perf_time_interval_secs_attribute.attr,
diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c
index c5fbc62357c6..d13c7291fd05 100644
--- a/fs/orangefs/orangefs-utils.c
+++ b/fs/orangefs/orangefs-utils.c
@@ -251,7 +251,7 @@ static int orangefs_inode_is_stale(struct inode *inode, int new,
return 0;
}
-int orangefs_inode_getattr(struct inode *inode, int new, int size)
+int orangefs_inode_getattr(struct inode *inode, int new, int bypass)
{
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
struct orangefs_kernel_op_s *new_op;
@@ -261,12 +261,16 @@ int orangefs_inode_getattr(struct inode *inode, int new, int size)
gossip_debug(GOSSIP_UTILS_DEBUG, "%s: called on inode %pU\n", __func__,
get_khandle_from_ino(inode));
+ if (!new && !bypass) {
+ if (time_before(jiffies, orangefs_inode->getattr_time))
+ return 0;
+ }
+
new_op = op_alloc(ORANGEFS_VFS_OP_GETATTR);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.getattr.refn = orangefs_inode->refn;
- new_op->upcall.req.getattr.mask = size ?
- ORANGEFS_ATTR_SYS_ALL_NOHINT : ORANGEFS_ATTR_SYS_ALL_NOHINT_NOSIZE;
+ new_op->upcall.req.getattr.mask = ORANGEFS_ATTR_SYS_ALL_NOHINT;
ret = service_operation(new_op, __func__,
get_interruptible_flag(inode));
@@ -287,20 +291,18 @@ int orangefs_inode_getattr(struct inode *inode, int new, int size)
case S_IFREG:
inode->i_flags = orangefs_inode_flags(&new_op->
downcall.resp.getattr.attributes);
- if (size) {
- inode_size = (loff_t)new_op->
- downcall.resp.getattr.attributes.size;
- rounded_up_size =
- (inode_size + (4096 - (inode_size % 4096)));
- inode->i_size = inode_size;
- orangefs_inode->blksize =
- new_op->downcall.resp.getattr.attributes.blksize;
- spin_lock(&inode->i_lock);
- inode->i_bytes = inode_size;
- inode->i_blocks =
- (unsigned long)(rounded_up_size / 512);
- spin_unlock(&inode->i_lock);
- }
+ inode_size = (loff_t)new_op->
+ downcall.resp.getattr.attributes.size;
+ rounded_up_size =
+ (inode_size + (4096 - (inode_size % 4096)));
+ inode->i_size = inode_size;
+ orangefs_inode->blksize =
+ new_op->downcall.resp.getattr.attributes.blksize;
+ spin_lock(&inode->i_lock);
+ inode->i_bytes = inode_size;
+ inode->i_blocks =
+ (unsigned long)(rounded_up_size / 512);
+ spin_unlock(&inode->i_lock);
break;
case S_IFDIR:
inode->i_size = PAGE_SIZE;
@@ -345,6 +347,7 @@ int orangefs_inode_getattr(struct inode *inode, int new, int size)
inode->i_mode = type | (is_root_handle(inode) ? S_ISVTX : 0) |
orangefs_inode_perms(&new_op->downcall.resp.getattr.attributes);
+ orangefs_inode->getattr_time = jiffies + getattr_timeout_msecs*HZ/1000;
ret = 0;
out:
op_release(new_op);
@@ -418,6 +421,7 @@ int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr)
ClearMtimeFlag(orangefs_inode);
ClearCtimeFlag(orangefs_inode);
ClearModeFlag(orangefs_inode);
+ orangefs_inode->getattr_time = jiffies - 1;
}
return ret;
diff --git a/fs/orangefs/protocol.h b/fs/orangefs/protocol.h
index 1efc6f8a5224..3d7418c728f5 100644
--- a/fs/orangefs/protocol.h
+++ b/fs/orangefs/protocol.h
@@ -207,14 +207,6 @@ typedef __s64 ORANGEFS_offset;
ORANGEFS_ATTR_SYS_DIRENT_COUNT | \
ORANGEFS_ATTR_SYS_BLKSIZE)
-#define ORANGEFS_ATTR_SYS_ALL_NOHINT_NOSIZE \
- (ORANGEFS_ATTR_SYS_COMMON_ALL | \
- ORANGEFS_ATTR_SYS_LNK_TARGET | \
- ORANGEFS_ATTR_SYS_DFILE_COUNT | \
- ORANGEFS_ATTR_SYS_MIRROR_COPIES_COUNT | \
- ORANGEFS_ATTR_SYS_DIRENT_COUNT | \
- ORANGEFS_ATTR_SYS_BLKSIZE)
-
#define ORANGEFS_XATTR_REPLACE 0x2
#define ORANGEFS_XATTR_CREATE 0x1
#define ORANGEFS_MAX_SERVER_ADDR_LEN 256