linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: James Simmons <jsimmons@infradead.org>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	devel@driverdev.osuosl.org,
	Andreas Dilger <andreas.dilger@intel.com>,
	Oleg Drokin <oleg.drokin@intel.com>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Lustre Development List <lustre-devel@lists.lustre.org>,
	Alex Zhuravlev <alexey.zhuravlev@intel.com>,
	James Simmons <jsimmons@infradead.org>
Subject: [PATCH 17/60] staging: lustre: obdclass: do not call lu_site_purge() for single object exceed
Date: Sat, 28 Jan 2017 19:04:45 -0500	[thread overview]
Message-ID: <1485648328-2141-18-git-send-email-jsimmons@infradead.org> (raw)
In-Reply-To: <1485648328-2141-1-git-send-email-jsimmons@infradead.org>

From: Alex Zhuravlev <alexey.zhuravlev@intel.com>

First of all, this is expensive procedure including a global
mutex and per-bucket spinlocks. also, all the threads observed
exceed will be calling lu_site_purge() and essentially serialized
on that. instead we can let other threads to skip the whole
procedure.

Signed-off-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-7896
Reviewed-on: http://review.whamcloud.com/19082
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Mike Pershin <mike.pershin@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
---
 drivers/staging/lustre/lustre/include/lu_object.h  |  8 ++++++-
 drivers/staging/lustre/lustre/obdclass/lu_object.c | 26 +++++++++++++++-------
 2 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/drivers/staging/lustre/lustre/include/lu_object.h b/drivers/staging/lustre/lustre/include/lu_object.h
index f442a96..c7dee1d 100644
--- a/drivers/staging/lustre/lustre/include/lu_object.h
+++ b/drivers/staging/lustre/lustre/include/lu_object.h
@@ -712,8 +712,14 @@ static inline int lu_object_is_dying(const struct lu_object_header *h)
 
 void lu_object_put(const struct lu_env *env, struct lu_object *o);
 void lu_object_unhash(const struct lu_env *env, struct lu_object *o);
+int lu_site_purge_objects(const struct lu_env *env, struct lu_site *s, int nr,
+			  bool canblock);
 
-int lu_site_purge(const struct lu_env *env, struct lu_site *s, int nr);
+static inline int lu_site_purge(const struct lu_env *env, struct lu_site *s,
+				int nr)
+{
+	return lu_site_purge_objects(env, s, nr, true);
+}
 
 void lu_site_print(const struct lu_env *env, struct lu_site *s, void *cookie,
 		   lu_printer_t printer);
diff --git a/drivers/staging/lustre/lustre/obdclass/lu_object.c b/drivers/staging/lustre/lustre/obdclass/lu_object.c
index 1805861..abcf951 100644
--- a/drivers/staging/lustre/lustre/obdclass/lu_object.c
+++ b/drivers/staging/lustre/lustre/obdclass/lu_object.c
@@ -60,7 +60,7 @@ enum {
 	LU_CACHE_PERCENT_DEFAULT = 20
 };
 
-#define LU_CACHE_NR_MAX_ADJUST		128
+#define LU_CACHE_NR_MAX_ADJUST		512
 #define LU_CACHE_NR_UNLIMITED		-1
 #define LU_CACHE_NR_DEFAULT		LU_CACHE_NR_UNLIMITED
 #define LU_CACHE_NR_LDISKFS_LIMIT	LU_CACHE_NR_UNLIMITED
@@ -329,8 +329,11 @@ static void lu_object_free(const struct lu_env *env, struct lu_object *o)
 
 /**
  * Free \a nr objects from the cold end of the site LRU list.
+ * if canblock is false, then don't block awaiting for another
+ * instance of lu_site_purge() to complete
  */
-int lu_site_purge(const struct lu_env *env, struct lu_site *s, int nr)
+int lu_site_purge_objects(const struct lu_env *env, struct lu_site *s,
+			  int nr, bool canblock)
 {
 	struct lu_object_header *h;
 	struct lu_object_header *temp;
@@ -360,7 +363,11 @@ int lu_site_purge(const struct lu_env *env, struct lu_site *s, int nr)
 	 * It doesn't make any sense to make purge threads parallel, that can
 	 * only bring troubles to us. See LU-5331.
 	 */
-	mutex_lock(&s->ls_purge_mutex);
+	if (canblock)
+		mutex_lock(&s->ls_purge_mutex);
+	else if (!mutex_trylock(&s->ls_purge_mutex))
+		goto out;
+
 	did_sth = 0;
 	cfs_hash_for_each_bucket(s->ls_obj_hash, &bd, i) {
 		if (i < start)
@@ -414,10 +421,10 @@ int lu_site_purge(const struct lu_env *env, struct lu_site *s, int nr)
 	}
 	/* race on s->ls_purge_start, but nobody cares */
 	s->ls_purge_start = i % CFS_HASH_NBKT(s->ls_obj_hash);
-
+out:
 	return nr;
 }
-EXPORT_SYMBOL(lu_site_purge);
+EXPORT_SYMBOL(lu_site_purge_objects);
 
 /*
  * Object printing.
@@ -625,9 +632,12 @@ static void lu_object_limit(const struct lu_env *env, struct lu_device *dev)
 
 	size = cfs_hash_size_get(dev->ld_site->ls_obj_hash);
 	nr = (__u64)lu_cache_nr;
-	if (size > nr)
-		lu_site_purge(env, dev->ld_site,
-			      min_t(__u64, size - nr, LU_CACHE_NR_MAX_ADJUST));
+	if (size <= nr)
+		return;
+
+	lu_site_purge_objects(env, dev->ld_site,
+			      min_t(__u64, size - nr, LU_CACHE_NR_MAX_ADJUST),
+			      false);
 }
 
 static struct lu_object *lu_object_new(const struct lu_env *env,
-- 
1.8.3.1

  parent reply	other threads:[~2017-01-29  0:11 UTC|newest]

Thread overview: 79+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-29  0:04 [PATCH 00/60] staging: lustre: batches of fixes for lustre client James Simmons
2017-01-29  0:04 ` [PATCH 01/60] staging: lustre: llite: Remove access of stripe in ll_setattr_raw James Simmons
2017-01-29  0:04 ` [PATCH 02/60] staging: lustre: statahead: drop support for remote entry James Simmons
2017-01-29  0:04 ` [PATCH 03/60] staging: lustre: clio: add cl_page LRU shrinker James Simmons
2017-01-29  0:04 ` [PATCH 04/60] staging: lustre: mdc: quiet console message for known -EINTR James Simmons
2017-01-29  0:04 ` [PATCH 05/60] staging: lustre: llite: check request != NULL in ll_migrate James Simmons
2017-01-30 11:34   ` Dan Carpenter
2017-02-11 17:12     ` James Simmons
2017-01-29  0:04 ` [PATCH 06/60] staging: lustre: clio: revise readahead to support 16MB IO James Simmons
2017-01-29  0:04 ` [PATCH 07/60] staging: lustre: ptlrpc: set proper mbits for EINPROGRESS resend James Simmons
2017-01-29  0:04 ` [PATCH 08/60] staging: lustre: ldlm: Restore connect flags on failure James Simmons
2017-01-29  0:04 ` [PATCH 09/60] staging: lustre: lmv: Correctly generate target_obd James Simmons
2017-01-29  0:04 ` [PATCH 10/60] staging: lustre: obdclass: add more info to sysfs version string James Simmons
2017-02-03 10:33   ` Greg Kroah-Hartman
2017-02-08  1:04     ` [lustre-devel] " Dilger, Andreas
2017-02-08  6:27       ` Greg Kroah-Hartman
2017-01-29  0:04 ` [PATCH 11/60] staging: lustre: obd: RCU stalls in lu_cache_shrink_count() James Simmons
2017-01-29  0:04 ` [PATCH 12/60] staging: lustre: lmv: Error not handled for lmv_find_target James Simmons
2017-01-29  0:04 ` [PATCH 13/60] staging: lustre: obdclass: health_check to report unhealthy upon LBUG James Simmons
2017-01-30 12:03   ` Dan Carpenter
2017-01-31  1:00     ` James Simmons
2017-01-29  0:04 ` [PATCH 14/60] staging: lustre: lov: Ensure correct operation for large object sizes James Simmons
2017-01-31  8:53   ` Dan Carpenter
2017-01-29  0:04 ` [PATCH 15/60] staging: lustre: hsm: stack overrun in hai_dump_data_field James Simmons
2017-01-29  0:04 ` [PATCH 16/60] staging: lustre: llite: don't ignore layout for group lock request James Simmons
2017-01-29  0:04 ` James Simmons [this message]
2017-01-29  0:04 ` [PATCH 18/60] staging: lustre: ptlrpc: skip lock if export failed James Simmons
2017-01-29  0:04 ` [PATCH 19/60] staging: lustre: llite: handle inactive OSTs better in statfs James Simmons
2017-01-29  0:04 ` [PATCH 20/60] staging: lustre: llite: remove obsolete comment for ll_unlink() James Simmons
2017-01-29  0:04 ` [PATCH 21/60] staging: lustre: ptlrpc: correct use of list_add_tail() James Simmons
2017-01-31  8:54   ` Dan Carpenter
2017-01-29  0:04 ` [PATCH 22/60] staging: lustre: fid: fix race in fid allocation James Simmons
2017-01-31  8:55   ` Dan Carpenter
2017-01-29  0:04 ` [PATCH 23/60] staging: lustre: lmv: remove unused placement parameter James Simmons
2017-01-29  0:04 ` [PATCH 24/60] staging: lustre: lustre: Remove old commented out code James Simmons
2017-01-29  0:04 ` [PATCH 25/60] staging: lustre: llite: normal user can't set FS default stripe James Simmons
2017-01-29  0:04 ` [PATCH 26/60] staging: lustre: llite: Trust creates in revalidate too James Simmons
2017-01-29  0:04 ` [PATCH 27/60] staging: lustre: mgc: handle config_llog_data::cld_refcount properly James Simmons
2017-01-29  0:04 ` [PATCH 28/60] staging: lustre: ldlm: ASSERTION(flock->blocking_export!=0) failed James Simmons
2017-01-29  0:04 ` [PATCH 29/60] staging: lustre: llite: Setting xattr are properly checked with and without ACLs James Simmons
2017-01-29  0:04 ` [PATCH 30/60] staging: lustre: ptlrpc: comment for FLD_QUERY RPC reply swab James Simmons
2017-01-29  0:04 ` [PATCH 31/60] staging: lustre: clio: sync write should update mtime James Simmons
2017-01-29  0:05 ` [PATCH 32/60] staging: lustre: osc: limits the number of chunks in write RPC James Simmons
2017-01-29  0:05 ` [PATCH 33/60] staging: lustre: libcfs: avoid stomping on module param cpu_pattern James Simmons
2017-01-29  0:05 ` [PATCH 34/60] staging: lustre: libcfs: default CPT matches NUMA topology James Simmons
2017-01-29  0:05 ` [PATCH 35/60] staging: lustre: lov: ld_target could be NULL James Simmons
2017-01-29  0:05 ` [PATCH 36/60] staging: lustre: header: remove assert from interval_set() James Simmons
2017-01-29  0:05 ` [PATCH 37/60] staging: lustre: llite: specify READA debug mask for ras_update James Simmons
2017-01-29  0:05 ` [PATCH 38/60] staging: lustre: llite: Adding timed wait in ll_umount_begin James Simmons
2017-01-29  0:05 ` [PATCH 39/60] staging: libcfs: remove integer types abstraction from libcfs James Simmons
2017-01-29  0:05 ` [PATCH 40/60] staging: ptlrpc: leaked rs on difficult reply James Simmons
2017-01-29  0:05 ` [PATCH 41/60] staging: lustre: osc: osc_match_base prototype differs from declaration James Simmons
2017-01-29  0:05 ` [PATCH 42/60] staging: lustre: ptlrpc: allow blocking asts to be delayed James Simmons
2017-01-29  0:05 ` [PATCH 43/60] staging: lustre: obd: remove OBD_NOTIFY_CREATE James Simmons
2017-01-29  0:05 ` [PATCH 44/60] staging: lustre: libcfs: fix error messages James Simmons
2017-01-29  0:05 ` [PATCH 45/60] staging: lustre: libcfs: Change positional struct initializers to C99 James Simmons
2017-01-29  0:05 ` [PATCH 46/60] staging: lustre: mdc: Make IT_OPEN take lookup bits lock James Simmons
2017-01-29  0:05 ` [PATCH 47/60] staging: lustre: mdc: avoid returning freed request James Simmons
2017-01-29  0:05 ` [PATCH 48/60] staging: lustre: ksocklnd: ignore timedout TX on closing connection James Simmons
2017-01-29  0:05 ` [PATCH 49/60] staging: lustre: socklnd: remove socklnd_init_msg James Simmons
2017-01-29  0:05 ` [PATCH 50/60] staging: lustre: ptlrpc: remove unused pc->pc_env James Simmons
2017-01-29  0:05 ` [PATCH 51/60] staging: lustre: ptlrpc: update MODULE_PARAM_DESC in ptlrpcd.c James Simmons
2017-01-29  0:05 ` [PATCH 52/60] staging: lustre: linkea: linkEA size limitation James Simmons
2017-01-29  0:05 ` [PATCH 53/60] staging: lustre: ptlrpc: update replay cursor when close during replay James Simmons
2017-01-29  0:05 ` [PATCH 54/60] staging: lustre: fid: Change positional struct initializers to C99 James Simmons
2017-01-29  0:05 ` [PATCH 55/60] staging: lustre: obd: move s3 in lmd_parse to inner loop James Simmons
2017-01-29  0:05 ` [PATCH 56/60] staging: lustre: llite: don't invoke direct_IO for the EOF case James Simmons
2017-01-29  0:05 ` [PATCH 57/60] staging: lustre: lmv: remove nlink check in lmv_revalidate_slaves James Simmons
2017-01-29  0:05 ` [PATCH 58/60] staging: lustre: osc: avoid 64 divide in osc_cache_too_much James Simmons
2017-01-29  0:05 ` [PATCH 59/60] staging: lustre: ptlrpc : remove userland usage from ptlrpc James Simmons
2017-01-29  0:05 ` [PATCH 60/60] staging: lustre: libcfs: fix minimum size check for libcfs ioctl James Simmons
2017-01-30 10:51   ` Dan Carpenter
2017-01-30 10:54     ` Dan Carpenter
2017-01-31  0:48       ` James Simmons
2017-01-31  2:25     ` James Simmons
2017-01-31  8:13       ` Dan Carpenter
2017-02-01 13:32       ` [lustre-devel] " Olaf Weber
2017-02-01 16:39         ` Greg Kroah-Hartman
2017-02-03 10:46 ` [PATCH 00/60] staging: lustre: batches of fixes for lustre client Greg Kroah-Hartman

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=1485648328-2141-18-git-send-email-jsimmons@infradead.org \
    --to=jsimmons@infradead.org \
    --cc=alexey.zhuravlev@intel.com \
    --cc=andreas.dilger@intel.com \
    --cc=devel@driverdev.osuosl.org \
    --cc=gregkh@linuxfoundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lustre-devel@lists.lustre.org \
    --cc=oleg.drokin@intel.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).