LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: NeilBrown <neilb@suse.com>
To: Oleg Drokin <oleg.drokin@intel.com>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	James Simmons <jsimmons@infradead.org>,
	Andreas Dilger <andreas.dilger@intel.com>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Lustre Development List <lustre-devel@lists.lustre.org>
Subject: [PATCH 04/10] staging: lustre: lu_object: move retry logic inside htable_lookup
Date: Tue, 01 May 2018 13:52:39 +1000	[thread overview]
Message-ID: <152514675897.17843.15112214060540196720.stgit@noble> (raw)
In-Reply-To: <152514658325.17843.11455067361317157487.stgit@noble>

The current retry logic, to wait when a 'dying' object is found,
spans multiple functions.  The process is attached to a waitqueue
and set TASK_UNINTERRUPTIBLE in htable_lookup, and this status
is passed back through lu_object_find_try() to lu_object_find_at()
where schedule() is called and the process is removed from the queue.

This can be simplified by moving all the logic (including
hashtable locking) inside htable_lookup(), which now never returns
EAGAIN.

Note that htable_lookup() is called with the hash bucket lock
held, and will drop and retake it if it needs to schedule.

I made this a 'goto' loop rather than a 'while(1)' loop as the
diff is easier to read.

Signed-off-by: NeilBrown <neilb@suse.com>
---
 drivers/staging/lustre/lustre/obdclass/lu_object.c |   73 +++++++-------------
 1 file changed, 27 insertions(+), 46 deletions(-)

diff --git a/drivers/staging/lustre/lustre/obdclass/lu_object.c b/drivers/staging/lustre/lustre/obdclass/lu_object.c
index 2bf089817157..93daa52e2535 100644
--- a/drivers/staging/lustre/lustre/obdclass/lu_object.c
+++ b/drivers/staging/lustre/lustre/obdclass/lu_object.c
@@ -586,16 +586,21 @@ EXPORT_SYMBOL(lu_object_print);
 static struct lu_object *htable_lookup(struct lu_site *s,
 				       struct cfs_hash_bd *bd,
 				       const struct lu_fid *f,
-				       wait_queue_entry_t *waiter,
 				       __u64 *version)
 {
+	struct cfs_hash		*hs = s->ls_obj_hash;
 	struct lu_site_bkt_data *bkt;
 	struct lu_object_header *h;
 	struct hlist_node	*hnode;
-	__u64  ver = cfs_hash_bd_version_get(bd);
+	__u64 ver;
+	wait_queue_entry_t waiter;
 
-	if (*version == ver)
+retry:
+	ver = cfs_hash_bd_version_get(bd);
+
+	if (*version == ver) {
 		return ERR_PTR(-ENOENT);
+	}
 
 	*version = ver;
 	bkt = cfs_hash_bd_extra_get(s->ls_obj_hash, bd);
@@ -625,11 +630,15 @@ static struct lu_object *htable_lookup(struct lu_site *s,
 	 * drained), and moreover, lookup has to wait until object is freed.
 	 */
 
-	init_waitqueue_entry(waiter, current);
-	add_wait_queue(&bkt->lsb_marche_funebre, waiter);
+	init_waitqueue_entry(&waiter, current);
+	add_wait_queue(&bkt->lsb_marche_funebre, &waiter);
 	set_current_state(TASK_UNINTERRUPTIBLE);
 	lprocfs_counter_incr(s->ls_stats, LU_SS_CACHE_DEATH_RACE);
-	return ERR_PTR(-EAGAIN);
+	cfs_hash_bd_unlock(hs, bd, 1);
+	schedule();
+	remove_wait_queue(&bkt->lsb_marche_funebre, &waiter);
+	cfs_hash_bd_lock(hs, bd, 1);
+	goto retry;
 }
 
 /**
@@ -693,13 +702,14 @@ static struct lu_object *lu_object_new(const struct lu_env *env,
 }
 
 /**
- * Core logic of lu_object_find*() functions.
+ * Much like lu_object_find(), but top level device of object is specifically
+ * \a dev rather than top level device of the site. This interface allows
+ * objects of different "stacking" to be created within the same site.
  */
-static struct lu_object *lu_object_find_try(const struct lu_env *env,
-					    struct lu_device *dev,
-					    const struct lu_fid *f,
-					    const struct lu_object_conf *conf,
-					    wait_queue_entry_t *waiter)
+struct lu_object *lu_object_find_at(const struct lu_env *env,
+				    struct lu_device *dev,
+				    const struct lu_fid *f,
+				    const struct lu_object_conf *conf)
 {
 	struct lu_object      *o;
 	struct lu_object      *shadow;
@@ -725,17 +735,16 @@ static struct lu_object *lu_object_find_try(const struct lu_env *env,
 	 * It is unnecessary to perform lookup-alloc-lookup-insert, instead,
 	 * just alloc and insert directly.
 	 *
-	 * If dying object is found during index search, add @waiter to the
-	 * site wait-queue and return ERR_PTR(-EAGAIN).
 	 */
 	if (conf && conf->loc_flags & LOC_F_NEW)
 		return lu_object_new(env, dev, f, conf);
 
 	s  = dev->ld_site;
 	hs = s->ls_obj_hash;
-	cfs_hash_bd_get_and_lock(hs, (void *)f, &bd, 1);
-	o = htable_lookup(s, &bd, f, waiter, &version);
-	cfs_hash_bd_unlock(hs, &bd, 1);
+	cfs_hash_bd_get_and_lock(hs, (void *)f, &bd, 0);
+	o = htable_lookup(s, &bd, f, &version);
+	cfs_hash_bd_unlock(hs, &bd, 0);
+
 	if (!IS_ERR(o) || PTR_ERR(o) != -ENOENT)
 		return o;
 
@@ -751,7 +760,7 @@ static struct lu_object *lu_object_find_try(const struct lu_env *env,
 
 	cfs_hash_bd_lock(hs, &bd, 1);
 
-	shadow = htable_lookup(s, &bd, f, waiter, &version);
+	shadow = htable_lookup(s, &bd, f, &version);
 	if (likely(PTR_ERR(shadow) == -ENOENT)) {
 		cfs_hash_bd_add_locked(hs, &bd, &o->lo_header->loh_hash);
 		cfs_hash_bd_unlock(hs, &bd, 1);
@@ -766,34 +775,6 @@ static struct lu_object *lu_object_find_try(const struct lu_env *env,
 	lu_object_free(env, o);
 	return shadow;
 }
-
-/**
- * Much like lu_object_find(), but top level device of object is specifically
- * \a dev rather than top level device of the site. This interface allows
- * objects of different "stacking" to be created within the same site.
- */
-struct lu_object *lu_object_find_at(const struct lu_env *env,
-				    struct lu_device *dev,
-				    const struct lu_fid *f,
-				    const struct lu_object_conf *conf)
-{
-	wait_queue_head_t	*wq;
-	struct lu_object	*obj;
-	wait_queue_entry_t	   wait;
-
-	while (1) {
-		obj = lu_object_find_try(env, dev, f, conf, &wait);
-		if (obj != ERR_PTR(-EAGAIN))
-			return obj;
-		/*
-		 * lu_object_find_try() already added waiter into the
-		 * wait queue.
-		 */
-		schedule();
-		wq = lu_site_wq_from_fid(dev->ld_site, (void *)f);
-		remove_wait_queue(wq, &wait);
-	}
-}
 EXPORT_SYMBOL(lu_object_find_at);
 
 /**

  parent reply	other threads:[~2018-05-01  3:52 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-01  3:52 [PATCH 00/10] staging: lustre: assorted improvements NeilBrown
2018-05-01  3:52 ` [PATCH 02/10] staging: lustre: make struct lu_site_bkt_data private NeilBrown
2018-05-01  4:10   ` [lustre-devel] " Dilger, Andreas
2018-05-02  3:02   ` James Simmons
2018-05-03 23:39     ` NeilBrown
2018-05-07  1:42       ` Greg Kroah-Hartman
2018-05-01  3:52 ` [PATCH 01/10] staging: lustre: ldlm: store name directly in namespace NeilBrown
2018-05-01  4:04   ` Dilger, Andreas
2018-05-02 18:11   ` James Simmons
2018-05-01  3:52 ` [PATCH 03/10] staging: lustre: lu_object: discard extra lru count NeilBrown
2018-05-01  4:19   ` Dilger, Andreas
2018-05-04  0:08     ` NeilBrown
2018-05-01  3:52 ` [PATCH 07/10] staging: lustre: llite: remove redundant lookup in dump_pgcache NeilBrown
2018-05-01  3:52 ` [PATCH 08/10] staging: lustre: move misc-device registration closer to related code NeilBrown
2018-05-02 18:12   ` James Simmons
2018-05-01  3:52 ` NeilBrown [this message]
2018-05-01  8:22   ` [lustre-devel] [PATCH 04/10] staging: lustre: lu_object: move retry logic inside htable_lookup Dilger, Andreas
2018-05-02 18:21     ` James Simmons
2018-05-04  0:30       ` NeilBrown
2018-05-04  1:30     ` NeilBrown
2018-05-01  3:52 ` [PATCH 05/10] staging: lustre: fold lu_object_new() into lu_object_find_at() NeilBrown
2018-05-01  3:52 ` [PATCH 10/10] staging: lustre: fix error deref in ll_splice_alias() NeilBrown
2018-05-02  3:05   ` James Simmons
2018-05-04  0:34     ` NeilBrown
2018-05-01  3:52 ` [PATCH 06/10] staging: lustre: llite: use more private data in dump_pgcache NeilBrown
2018-05-01  3:52 ` [PATCH 09/10] staging: lustre: move remaining code from linux-module.c to module.c NeilBrown
2018-05-02 18:13   ` James Simmons
2018-05-07  0:54 [PATCH 00/10 - v2] staging: lustre: assorted improvements NeilBrown
2018-05-07  0:54 ` [PATCH 04/10] staging: lustre: lu_object: move retry logic inside htable_lookup NeilBrown

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=152514675897.17843.15112214060540196720.stgit@noble \
    --to=neilb@suse.com \
    --cc=andreas.dilger@intel.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=jsimmons@infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lustre-devel@lists.lustre.org \
    --cc=oleg.drokin@intel.com \
    --subject='Re: [PATCH 04/10] staging: lustre: lu_object: move retry logic inside htable_lookup' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).