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".
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
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)
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
}
}
+ dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
ret = 1;
out_release_op:
op_release(new_op);
{
int ret;
+ if (time_before(jiffies, dentry->d_time))
+ return 1;
+
if (flags & LOOKUP_RCU)
return -ECHILD;
"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);
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);
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;
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",
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,
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",
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",
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",
"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;
* with this object
*/
unsigned long pinode_flags;
+
+ unsigned long getattr_time;
};
#define P_ATIME_FLAG 0
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);
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;
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");
* 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.
*
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 {
"%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;
}
} 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;
}
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,
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,
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;
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));
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;
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);
ClearMtimeFlag(orangefs_inode);
ClearCtimeFlag(orangefs_inode);
ClearModeFlag(orangefs_inode);
+ orangefs_inode->getattr_time = jiffies - 1;
}
return ret;
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