/*
* sa_entry is not refcounted: statahead thread allocates it and do async stat,
- * and in async stat callback ll_statahead_interpret() will prepare the inode
- * and set lock data in the ptlrpcd context. Then the scanner process will be
- * woken up if this entry is the waiting one, can access and free it.
+ * and in async stat callback ll_statahead_interpret() will add it into
+ * sai_interim_entries, later statahead thread will call sa_handle_callback() to
+ * instantiate entry and move it into sai_entries, and then only scanner process
+ * can access and free it.
*/
struct sa_entry {
- /* link into sai_entries */
+ /* link into sai_interim_entries or sai_entries */
struct list_head se_list;
/* link into sai hash table locally */
struct list_head se_hash;
se_state_t se_state;
/* entry size, contains name */
int se_size;
+ /* pointer to async getattr enqueue info */
+ struct md_enqueue_info *se_minfo;
+ /* pointer to the async getattr request */
+ struct ptlrpc_request *se_req;
/* pointer to the target inode */
struct inode *se_inode;
/* entry name */
return atomic_read(&sai->sai_cache_count) >= sai->sai_max;
}
+/* got async stat replies */
+static inline int sa_has_callback(struct ll_statahead_info *sai)
+{
+ return !list_empty(&sai->sai_interim_entries);
+}
+
static inline int agl_list_empty(struct ll_statahead_info *sai)
{
return list_empty(&sai->sai_agls);
}
/* finish async stat RPC arguments */
-static void sa_fini_data(struct md_op_item *item)
+static void sa_fini_data(struct md_enqueue_info *minfo)
{
- ll_unlock_md_op_lsm(&item->mop_data);
- iput(item->mop_dir);
- OBD_FREE_PTR(item);
+ ll_unlock_md_op_lsm(&minfo->mi_data);
+ iput(minfo->mi_dir);
+ OBD_FREE_PTR(minfo);
}
-static int ll_statahead_interpret(struct req_capsule *pill,
- struct md_op_item *item, int rc);
+static int ll_statahead_interpret(struct ptlrpc_request *req,
+ struct md_enqueue_info *minfo, int rc);
/*
* prepare arguments for async stat RPC.
*/
-static struct md_op_item *
+static struct md_enqueue_info *
sa_prep_data(struct inode *dir, struct inode *child, struct sa_entry *entry)
{
- struct md_op_item *item;
+ struct md_enqueue_info *minfo;
struct ldlm_enqueue_info *einfo;
- struct md_op_data *op_data;
+ struct md_op_data *op_data;
- OBD_ALLOC_PTR(item);
- if (!item)
+ OBD_ALLOC_PTR(minfo);
+ if (!minfo)
return ERR_PTR(-ENOMEM);
- op_data = ll_prep_md_op_data(&item->mop_data, dir, child,
+ op_data = ll_prep_md_op_data(&minfo->mi_data, dir, child,
entry->se_qstr.name, entry->se_qstr.len, 0,
LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data)) {
- OBD_FREE_PTR(item);
- return (struct md_op_item *)op_data;
+ OBD_FREE_PTR(minfo);
+ return (struct md_enqueue_info *)op_data;
}
if (!child)
op_data->op_fid2 = entry->se_fid;
- item->mop_it.it_op = IT_GETATTR;
- item->mop_dir = igrab(dir);
- item->mop_cb = ll_statahead_interpret;
- item->mop_cbdata = entry;
-
- einfo = &item->mop_einfo;
- einfo->ei_type = LDLM_IBITS;
- einfo->ei_mode = it_to_lock_mode(&item->mop_it);
- einfo->ei_cb_bl = ll_md_blocking_ast;
- einfo->ei_cb_cp = ldlm_completion_ast;
- einfo->ei_cb_gl = NULL;
+ minfo->mi_it.it_op = IT_GETATTR;
+ minfo->mi_dir = igrab(dir);
+ minfo->mi_cb = ll_statahead_interpret;
+ minfo->mi_cbdata = entry;
+
+ einfo = &minfo->mi_einfo;
+ einfo->ei_type = LDLM_IBITS;
+ einfo->ei_mode = it_to_lock_mode(&minfo->mi_it);
+ einfo->ei_cb_bl = ll_md_blocking_ast;
+ einfo->ei_cb_cp = ldlm_completion_ast;
+ einfo->ei_cb_gl = NULL;
einfo->ei_cbdata = NULL;
- return item;
+ return minfo;
}
/*
sa_make_ready(struct ll_statahead_info *sai, struct sa_entry *entry, int ret)
{
struct ll_inode_info *lli = ll_i2info(sai->sai_dentry->d_inode);
+ struct md_enqueue_info *minfo = entry->se_minfo;
+ struct ptlrpc_request *req = entry->se_req;
bool wakeup;
+ /* release resources used in RPC */
+ if (minfo) {
+ entry->se_minfo = NULL;
+ ll_intent_release(&minfo->mi_it);
+ sa_fini_data(minfo);
+ }
+
+ if (req) {
+ entry->se_req = NULL;
+ ptlrpc_req_finished(req);
+ }
+
spin_lock(&lli->lli_sa_lock);
wakeup = __sa_make_ready(sai, entry, ret);
spin_unlock(&lli->lli_sa_lock);
sai->sai_index = 1;
init_waitqueue_head(&sai->sai_waitq);
+ INIT_LIST_HEAD(&sai->sai_interim_entries);
INIT_LIST_HEAD(&sai->sai_entries);
INIT_LIST_HEAD(&sai->sai_agls);
LASSERT(!sai->sai_task);
LASSERT(!sai->sai_agl_task);
LASSERT(sai->sai_sent == sai->sai_replied);
+ LASSERT(!sa_has_callback(sai));
list_for_each_entry_safe(entry, next, &sai->sai_entries,
se_list)
}
/*
- * Callback for async stat RPC, this is called in ptlrpcd context. It prepares
- * the inode and set lock data directly in the ptlrpcd context. It will wake up
- * the directory listing process if the dentry is the waiting one.
+ * prepare inode for sa entry, add it into agl list, now sa_entry is ready
+ * to be used by scanner process.
*/
-static int ll_statahead_interpret(struct req_capsule *pill,
- struct md_op_item *item, int rc)
+static void sa_instantiate(struct ll_statahead_info *sai,
+ struct sa_entry *entry)
{
- struct lookup_intent *it = &item->mop_it;
- struct inode *dir = item->mop_dir;
- struct ll_inode_info *lli = ll_i2info(dir);
- struct ll_statahead_info *sai = lli->lli_sai;
- struct sa_entry *entry = (struct sa_entry *)item->mop_cbdata;
- struct mdt_body *body;
+ struct inode *dir = sai->sai_dentry->d_inode;
struct inode *child;
- __u64 handle = 0;
+ struct md_enqueue_info *minfo;
+ struct lookup_intent *it;
+ struct ptlrpc_request *req;
+ struct mdt_body *body;
+ int rc = 0;
ENTRY;
- if (it_disposition(it, DISP_LOOKUP_NEG))
- rc = -ENOENT;
-
- /*
- * because statahead thread will wait for all inflight RPC to finish,
- * sai should be always valid, no need to refcount
- */
- LASSERT(sai != NULL);
- LASSERT(entry != NULL);
-
- CDEBUG(D_READA, "sa_entry %.*s rc %d\n",
- entry->se_qstr.len, entry->se_qstr.name, rc);
-
- if (rc != 0) {
- ll_intent_release(it);
- sa_fini_data(item);
- } else {
- /*
- * release ibits lock ASAP to avoid deadlock when statahead
- * thread enqueues lock on parent in readdir and another
- * process enqueues lock on child with parent lock held, eg.
- * unlink.
- */
- handle = it->it_lock_handle;
- ll_intent_drop_lock(it);
- ll_unlock_md_op_lsm(&item->mop_data);
- }
-
- if (rc != 0) {
- spin_lock(&lli->lli_sa_lock);
- if (__sa_make_ready(sai, entry, rc))
- wake_up(&sai->sai_waitq);
-
- sai->sai_replied++;
- spin_unlock(&lli->lli_sa_lock);
-
- RETURN(rc);
- }
+ LASSERT(entry->se_handle != 0);
- entry->se_handle = handle;
- body = req_capsule_server_get(pill, &RMF_MDT_BODY);
+ minfo = entry->se_minfo;
+ it = &minfo->mi_it;
+ req = entry->se_req;
+ body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
if (!body)
GOTO(out, rc = -EFAULT);
child = entry->se_inode;
/* revalidate; unlinked and re-created with the same name */
- if (unlikely(!lu_fid_eq(&item->mop_data.op_fid2, &body->mbo_fid1))) {
+ if (unlikely(!lu_fid_eq(&minfo->mi_data.op_fid2, &body->mbo_fid1))) {
if (child) {
entry->se_inode = NULL;
iput(child);
if (rc != 1)
GOTO(out, rc = -EAGAIN);
- rc = ll_prep_inode(&child, pill, dir->i_sb, it);
+ rc = ll_prep_inode(&child, &req->rq_pill, dir->i_sb, it);
if (rc)
GOTO(out, rc);
if (agl_should_run(sai, child))
ll_agl_add(sai, child, entry->se_index);
+ EXIT;
+
out:
/*
- * First it will drop ldlm ibits lock refcount by calling
+ * sa_make_ready() will drop ldlm ibits lock refcount by calling
* ll_intent_drop_lock() in spite of failures. Do not worry about
* calling ll_intent_drop_lock() more than once.
*/
- ll_intent_release(&item->mop_it);
- sa_fini_data(item);
sa_make_ready(sai, entry, rc);
+}
+
+/* once there are async stat replies, instantiate sa_entry from replies */
+static void sa_handle_callback(struct ll_statahead_info *sai)
+{
+ struct ll_inode_info *lli;
+
+ lli = ll_i2info(sai->sai_dentry->d_inode);
+
+ spin_lock(&lli->lli_sa_lock);
+ while (sa_has_callback(sai)) {
+ struct sa_entry *entry;
+
+ entry = list_entry(sai->sai_interim_entries.next,
+ struct sa_entry, se_list);
+ list_del_init(&entry->se_list);
+ spin_unlock(&lli->lli_sa_lock);
+
+ sa_instantiate(sai, entry);
+ spin_lock(&lli->lli_sa_lock);
+ }
+ spin_unlock(&lli->lli_sa_lock);
+}
+
+/*
+ * callback for async stat RPC, because this is called in ptlrpcd context, we
+ * only put sa_entry in sai_interim_entries, and wake up statahead thread to
+ * really prepare inode and instantiate sa_entry later.
+ */
+static int ll_statahead_interpret(struct ptlrpc_request *req,
+ struct md_enqueue_info *minfo, int rc)
+{
+ struct lookup_intent *it = &minfo->mi_it;
+ struct inode *dir = minfo->mi_dir;
+ struct ll_inode_info *lli = ll_i2info(dir);
+ struct ll_statahead_info *sai = lli->lli_sai;
+ struct sa_entry *entry = (struct sa_entry *)minfo->mi_cbdata;
+ __u64 handle = 0;
+
+ ENTRY;
+
+ if (it_disposition(it, DISP_LOOKUP_NEG))
+ rc = -ENOENT;
+
+ /*
+ * because statahead thread will wait for all inflight RPC to finish,
+ * sai should be always valid, no need to refcount
+ */
+ LASSERT(sai != NULL);
+ LASSERT(entry != NULL);
+
+ CDEBUG(D_READA, "sa_entry %.*s rc %d\n",
+ entry->se_qstr.len, entry->se_qstr.name, rc);
+
+ if (rc != 0) {
+ ll_intent_release(it);
+ sa_fini_data(minfo);
+ } else {
+ /*
+ * release ibits lock ASAP to avoid deadlock when statahead
+ * thread enqueues lock on parent in readdir and another
+ * process enqueues lock on child with parent lock held, eg.
+ * unlink.
+ */
+ handle = it->it_lock_handle;
+ ll_intent_drop_lock(it);
+ ll_unlock_md_op_lsm(&minfo->mi_data);
+ }
spin_lock(&lli->lli_sa_lock);
+ if (rc != 0) {
+ if (__sa_make_ready(sai, entry, rc))
+ wake_up(&sai->sai_waitq);
+ } else {
+ int first = 0;
+
+ entry->se_minfo = minfo;
+ entry->se_req = ptlrpc_request_addref(req);
+ /*
+ * Release the async ibits lock ASAP to avoid deadlock
+ * when statahead thread tries to enqueue lock on parent
+ * for readpage and other tries to enqueue lock on child
+ * with parent's lock held, for example: unlink.
+ */
+ entry->se_handle = handle;
+ if (!sa_has_callback(sai))
+ first = 1;
+
+ list_add_tail(&entry->se_list, &sai->sai_interim_entries);
+ if (first && sai->sai_task)
+ wake_up_process(sai->sai_task);
+ }
sai->sai_replied++;
+
spin_unlock(&lli->lli_sa_lock);
RETURN(rc);
/* async stat for file not found in dcache */
static int sa_lookup(struct inode *dir, struct sa_entry *entry)
{
- struct md_op_item *item;
- int rc;
+ struct md_enqueue_info *minfo;
+ int rc;
ENTRY;
- item = sa_prep_data(dir, NULL, entry);
- if (IS_ERR(item))
- RETURN(PTR_ERR(item));
+ minfo = sa_prep_data(dir, NULL, entry);
+ if (IS_ERR(minfo))
+ RETURN(PTR_ERR(minfo));
- rc = md_intent_getattr_async(ll_i2mdexp(dir), item);
+ rc = md_intent_getattr_async(ll_i2mdexp(dir), minfo);
if (rc < 0)
- sa_fini_data(item);
+ sa_fini_data(minfo);
RETURN(rc);
}
struct inode *inode = dentry->d_inode;
struct lookup_intent it = { .it_op = IT_GETATTR,
.it_lock_handle = 0 };
- struct md_op_item *item;
+ struct md_enqueue_info *minfo;
int rc;
ENTRY;
if (d_mountpoint(dentry))
RETURN(1);
- item = sa_prep_data(dir, inode, entry);
- if (IS_ERR(item))
- RETURN(PTR_ERR(item));
+ minfo = sa_prep_data(dir, inode, entry);
+ if (IS_ERR(minfo))
+ RETURN(PTR_ERR(minfo));
entry->se_inode = igrab(inode);
rc = md_revalidate_lock(ll_i2mdexp(dir), &it, ll_inode2fid(inode),
if (rc == 1) {
entry->se_handle = it.it_lock_handle;
ll_intent_release(&it);
- sa_fini_data(item);
+ sa_fini_data(minfo);
RETURN(1);
}
- rc = md_intent_getattr_async(ll_i2mdexp(dir), item);
+ rc = md_intent_getattr_async(ll_i2mdexp(dir), minfo);
if (rc < 0) {
entry->se_inode = NULL;
iput(inode);
- sa_fini_data(item);
+ sa_fini_data(minfo);
}
RETURN(rc);
break;
}
+ sai->sai_in_readpage = 1;
page = ll_get_dir_page(dir, op_data, pos);
ll_unlock_md_op_lsm(op_data);
+ sai->sai_in_readpage = 0;
if (IS_ERR(page)) {
rc = PTR_ERR(page);
CDEBUG(D_READA,
while (({set_current_state(TASK_IDLE);
sai->sai_task; })) {
+ if (sa_has_callback(sai)) {
+ __set_current_state(TASK_RUNNING);
+ sa_handle_callback(sai);
+ }
+
spin_lock(&lli->lli_agl_lock);
while (sa_sent_full(sai) &&
!agl_list_empty(sai)) {
/*
* statahead is finished, but statahead entries need to be cached, wait
- * for file release closedir() call to stop me.
+ * for file release to stop me.
*/
while (({set_current_state(TASK_IDLE);
sai->sai_task; })) {
- schedule();
+ if (sa_has_callback(sai)) {
+ __set_current_state(TASK_RUNNING);
+ sa_handle_callback(sai);
+ } else {
+ schedule();
+ }
}
__set_current_state(TASK_RUNNING);
/* in case we're not woken up, timeout wait */
msleep(125);
+ /* release resources held by statahead RPCs */
+ sa_handle_callback(sai);
+
CDEBUG(D_READA, "%s: statahead thread stopped: sai %p, parent %pd\n",
sbi->ll_fsname, sai, parent);
if (!entry)
GOTO(out, rc = -EAGAIN);
+ /* if statahead is busy in readdir, help it do post-work */
+ if (!sa_ready(entry) && sai->sai_in_readpage)
+ sa_handle_callback(sai);
+
if (!sa_ready(entry)) {
spin_lock(&lli->lli_sa_lock);
sai->sai_index_wait = entry->se_index;
git://git.whamcloud.com / fs / lustre-release.git / blobdiff