mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: Steven Whitehouse <swhiteho@redhat.com>
Cc: torvalds@linux-foundation.org, mingo@elte.hu,
	peterz@infradead.org, awalls@radix.net,
	linux-kernel@vger.kernel.org, jeff@garzik.org,
	akpm@linux-foundation.org, jens.axboe@oracle.com,
	rusty@rustcorp.com.au, cl@linux-foundation.org,
	dhowells@redhat.com, arjan@linux.intel.com, avi@redhat.com,
	johannes@sipsolutions.net, andi@firstfloor.org
Subject: [PATCH UPDATED 39/40] gfs2: use workqueue instead of slow-work
Date: Tue, 19 Jan 2010 17:46:19 +0900	[thread overview]
Message-ID: <4B55715B.8070702@kernel.org> (raw)
In-Reply-To: <4B550440.4040800@kernel.org>

Workqueue can now handle high concurrency.  Convert gfs to use
workqueue instead of slow-work.

* Steven pointed out that recovery path might be run from allocation
  path and thus requires forward progress guarantee without memory
  allocation.  Create and use gfs_recovery_wq with rescuer.  Please
  note that forward progress wasn't guaranteed with slow-work.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Steven Whitehouse <swhiteho@redhat.com>
---
So, here's the updated version.  Only compile tested.

Thanks.

 fs/gfs2/Kconfig      |    1 
 fs/gfs2/incore.h     |    3 --
 fs/gfs2/main.c       |   14 +++++++------
 fs/gfs2/ops_fstype.c |    8 +++----
 fs/gfs2/recovery.c   |   54 +++++++++++++++++++--------------------------------
 fs/gfs2/recovery.h   |    6 +++--
 fs/gfs2/sys.c        |    3 +-
 7 files changed, 40 insertions(+), 49 deletions(-)

Index: work/fs/gfs2/incore.h
===================================================================
--- work.orig/fs/gfs2/incore.h
+++ work/fs/gfs2/incore.h
@@ -12,7 +12,6 @@
 
 #include <linux/fs.h>
 #include <linux/workqueue.h>
-#include <linux/slow-work.h>
 #include <linux/dlm.h>
 #include <linux/buffer_head.h>
 
@@ -383,7 +382,7 @@ struct gfs2_journal_extent {
 struct gfs2_jdesc {
 	struct list_head jd_list;
 	struct list_head extent_list;
-	struct slow_work jd_work;
+	struct work_struct jd_work;
 	struct inode *jd_inode;
 	unsigned long jd_flags;
 #define JDF_RECOVERY 1
Index: work/fs/gfs2/main.c
===================================================================
--- work.orig/fs/gfs2/main.c
+++ work/fs/gfs2/main.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 #include <linux/gfs2_ondisk.h>
 #include <asm/atomic.h>
-#include <linux/slow-work.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -24,6 +23,7 @@
 #include "util.h"
 #include "glock.h"
 #include "quota.h"
+#include "recovery.h"
 
 static struct shrinker qd_shrinker = {
 	.shrink = gfs2_shrink_qd_memory,
@@ -114,9 +114,11 @@ static int __init init_gfs2_fs(void)
 	if (error)
 		goto fail_unregister;
 
-	error = slow_work_register_user(THIS_MODULE);
-	if (error)
-		goto fail_slow;
+	error = -ENOMEM;
+	gfs_recovery_wq = __create_workqueue("gfs_recovery", WQ_RESCUER,
+					     WQ_MAX_ACTIVE);
+	if (!gfs_recovery_wq)
+		goto fail_wq;
 
 	gfs2_register_debugfs();
 
@@ -124,7 +126,7 @@ static int __init init_gfs2_fs(void)
 
 	return 0;
 
-fail_slow:
+fail_wq:
 	unregister_filesystem(&gfs2meta_fs_type);
 fail_unregister:
 	unregister_filesystem(&gfs2_fs_type);
@@ -163,7 +165,7 @@ static void __exit exit_gfs2_fs(void)
 	gfs2_unregister_debugfs();
 	unregister_filesystem(&gfs2_fs_type);
 	unregister_filesystem(&gfs2meta_fs_type);
-	slow_work_unregister_user(THIS_MODULE);
+	destroy_workqueue(gfs_recovery_wq);
 
 	kmem_cache_destroy(gfs2_quotad_cachep);
 	kmem_cache_destroy(gfs2_rgrpd_cachep);
Index: work/fs/gfs2/ops_fstype.c
===================================================================
--- work.orig/fs/gfs2/ops_fstype.c
+++ work/fs/gfs2/ops_fstype.c
@@ -17,7 +17,6 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/gfs2_ondisk.h>
-#include <linux/slow-work.h>
 #include <linux/quotaops.h>
 
 #include "gfs2.h"
@@ -673,7 +672,7 @@ static int gfs2_jindex_hold(struct gfs2_
 			break;
 
 		INIT_LIST_HEAD(&jd->extent_list);
-		slow_work_init(&jd->jd_work, &gfs2_recover_ops);
+		INIT_WORK(&jd->jd_work, gfs2_recover_func);
 		jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1);
 		if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
 			if (!jd->jd_inode)
@@ -778,7 +777,8 @@ static int init_journal(struct gfs2_sbd
 	if (sdp->sd_lockstruct.ls_first) {
 		unsigned int x;
 		for (x = 0; x < sdp->sd_journals; x++) {
-			error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x));
+			error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x),
+						     true);
 			if (error) {
 				fs_err(sdp, "error recovering journal %u: %d\n",
 				       x, error);
@@ -788,7 +788,7 @@ static int init_journal(struct gfs2_sbd
 
 		gfs2_others_may_mount(sdp);
 	} else if (!sdp->sd_args.ar_spectator) {
-		error = gfs2_recover_journal(sdp->sd_jdesc);
+		error = gfs2_recover_journal(sdp->sd_jdesc, true);
 		if (error) {
 			fs_err(sdp, "error recovering my journal: %d\n", error);
 			goto fail_jinode_gh;
Index: work/fs/gfs2/recovery.c
===================================================================
--- work.orig/fs/gfs2/recovery.c
+++ work/fs/gfs2/recovery.c
@@ -14,7 +14,6 @@
 #include <linux/buffer_head.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
-#include <linux/slow-work.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -28,6 +27,8 @@
 #include "util.h"
 #include "dir.h"
 
+struct workqueue_struct *gfs_recovery_wq;
+
 int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
 			   struct buffer_head **bh)
 {
@@ -443,23 +444,7 @@ static void gfs2_recovery_done(struct gf
         kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp);
 }
 
-static int gfs2_recover_get_ref(struct slow_work *work)
-{
-	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
-	if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags))
-		return -EBUSY;
-	return 0;
-}
-
-static void gfs2_recover_put_ref(struct slow_work *work)
-{
-	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
-	clear_bit(JDF_RECOVERY, &jd->jd_flags);
-	smp_mb__after_clear_bit();
-	wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
-}
-
-static void gfs2_recover_work(struct slow_work *work)
+void gfs2_recover_func(struct work_struct *work)
 {
 	struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
 	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
@@ -578,7 +563,7 @@ static void gfs2_recover_work(struct slo
 		gfs2_glock_dq_uninit(&j_gh);
 
 	fs_info(sdp, "jid=%u: Done\n", jd->jd_jid);
-	return;
+	goto done;
 
 fail_gunlock_tr:
 	gfs2_glock_dq_uninit(&t_gh);
@@ -590,32 +575,35 @@ fail_gunlock_j:
 	}
 
 	fs_info(sdp, "jid=%u: %s\n", jd->jd_jid, (error) ? "Failed" : "Done");
-
 fail:
 	gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP);
+done:
+	clear_bit(JDF_RECOVERY, &jd->jd_flags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
 }
 
-struct slow_work_ops gfs2_recover_ops = {
-	.owner	 = THIS_MODULE,
-	.get_ref = gfs2_recover_get_ref,
-	.put_ref = gfs2_recover_put_ref,
-	.execute = gfs2_recover_work,
-};
-
-
 static int gfs2_recovery_wait(void *word)
 {
 	schedule();
 	return 0;
 }
 
-int gfs2_recover_journal(struct gfs2_jdesc *jd)
+int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait)
 {
 	int rv;
-	rv = slow_work_enqueue(&jd->jd_work);
-	if (rv)
-		return rv;
-	wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait, TASK_UNINTERRUPTIBLE);
+
+	if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags))
+		return -EBUSY;
+
+	/* we have JDF_RECOVERY, queue should always succeed */
+	rv = queue_work(gfs_recovery_wq, &jd->jd_work);
+	BUG_ON(!rv);
+
+	if (wait)
+		wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait,
+			    TASK_UNINTERRUPTIBLE);
+
 	return 0;
 }
 
Index: work/fs/gfs2/recovery.h
===================================================================
--- work.orig/fs/gfs2/recovery.h
+++ work/fs/gfs2/recovery.h
@@ -12,6 +12,8 @@
 
 #include "incore.h"
 
+extern struct workqueue_struct *gfs_recovery_wq;
+
 static inline void gfs2_replay_incr_blk(struct gfs2_sbd *sdp, unsigned int *blk)
 {
 	if (++*blk == sdp->sd_jdesc->jd_blocks)
@@ -27,8 +29,8 @@ extern void gfs2_revoke_clean(struct gfs
 
 extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
 		    struct gfs2_log_header_host *head);
-extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd);
-extern struct slow_work_ops gfs2_recover_ops;
+extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait);
+extern void gfs2_recover_func(struct work_struct *work);
 
 #endif /* __RECOVERY_DOT_H__ */
 
Index: work/fs/gfs2/sys.c
===================================================================
--- work.orig/fs/gfs2/sys.c
+++ work/fs/gfs2/sys.c
@@ -26,6 +26,7 @@
 #include "quota.h"
 #include "util.h"
 #include "glops.h"
+#include "recovery.h"
 
 struct gfs2_attr {
 	struct attribute attr;
@@ -351,7 +352,7 @@ static ssize_t recover_store(struct gfs2
 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
 		if (jd->jd_jid != jid)
 			continue;
-		rv = slow_work_enqueue(&jd->jd_work);
+		rv = gfs2_recover_journal(jd, false);
 		break;
 	}
 out:
Index: work/fs/gfs2/Kconfig
===================================================================
--- work.orig/fs/gfs2/Kconfig
+++ work/fs/gfs2/Kconfig
@@ -7,7 +7,6 @@ config GFS2_FS
 	select IP_SCTP if DLM_SCTP
 	select FS_POSIX_ACL
 	select CRC32
-	select SLOW_WORK
 	select QUOTA
 	select QUOTACTL
 	help

  reply	other threads:[~2010-01-19  8:47 UTC|newest]

Thread overview: 102+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-01-18  0:57 [PATCHSET] concurrency managed workqueue, take#3 Tejun Heo
2010-01-18  0:57 ` [PATCH 01/40] sched: consult online mask instead of active in select_fallback_rq() Tejun Heo
2010-01-18 10:13   ` Peter Zijlstra
2010-01-18 11:26     ` Tejun Heo
2010-01-18  0:57 ` [PATCH 02/40] sched: rename preempt_notifiers to sched_notifiers and refactor implementation Tejun Heo
2010-01-18  0:57 ` [PATCH 03/40] sched: refactor try_to_wake_up() Tejun Heo
2010-01-18  0:57 ` [PATCH 04/40] sched: implement __set_cpus_allowed() Tejun Heo
2010-01-18  9:56   ` Peter Zijlstra
2010-01-18 11:22     ` Tejun Heo
2010-01-18 11:41       ` Peter Zijlstra
2010-01-19  1:07         ` Tejun Heo
2010-01-19  8:37           ` Peter Zijlstra
2010-01-20  8:35             ` Tejun Heo
2010-01-20  8:50               ` Peter Zijlstra
2010-01-20  9:00                 ` Tejun Heo
2010-01-20  8:59                   ` Peter Zijlstra
2010-01-24  8:18               ` Tejun Heo
2010-01-18  0:57 ` [PATCH 05/40] sched: make sched_notifiers unconditional Tejun Heo
2010-01-18  0:57 ` [PATCH 06/40] sched: add wakeup/sleep sched_notifiers and allow NULL notifier ops Tejun Heo
2010-01-18  9:57   ` Peter Zijlstra
2010-01-18 11:31     ` Tejun Heo
2010-01-18 12:49       ` Peter Zijlstra
2010-01-19  1:04         ` Tejun Heo
2010-01-19  8:28           ` Tejun Heo
2010-01-19  8:55             ` Peter Zijlstra
2010-01-20  8:47               ` Tejun Heo
2010-01-18  0:57 ` [PATCH 07/40] sched: implement try_to_wake_up_local() Tejun Heo
2010-01-18  0:57 ` [PATCH 08/40] acpi: use queue_work_on() instead of binding workqueue worker to cpu0 Tejun Heo
2010-01-18  0:57 ` [PATCH 09/40] stop_machine: reimplement without using workqueue Tejun Heo
2010-01-18  0:57 ` [PATCH 10/40] workqueue: misc/cosmetic updates Tejun Heo
2010-01-18  0:57 ` [PATCH 11/40] workqueue: merge feature parameters into flags Tejun Heo
2010-01-18  0:57 ` [PATCH 12/40] workqueue: define both bit position and mask for work flags Tejun Heo
2010-01-18  0:57 ` [PATCH 13/40] workqueue: separate out process_one_work() Tejun Heo
2010-01-18  0:57 ` [PATCH 14/40] workqueue: temporarily disable workqueue tracing Tejun Heo
2010-01-18  0:57 ` [PATCH 15/40] workqueue: kill cpu_populated_map Tejun Heo
2010-01-18  0:57 ` [PATCH 16/40] workqueue: update cwq alignement Tejun Heo
2010-01-18  0:57 ` [PATCH 17/40] workqueue: reimplement workqueue flushing using color coded works Tejun Heo
2010-01-18  0:57 ` [PATCH 18/40] workqueue: introduce worker Tejun Heo
2010-01-18  0:57 ` [PATCH 19/40] workqueue: reimplement work flushing using linked works Tejun Heo
2010-01-18  0:57 ` [PATCH 20/40] workqueue: implement per-cwq active work limit Tejun Heo
2010-01-18  0:57 ` [PATCH 21/40] workqueue: reimplement workqueue freeze using max_active Tejun Heo
2010-01-18  0:57 ` [PATCH 22/40] workqueue: introduce global cwq and unify cwq locks Tejun Heo
2010-01-18  0:57 ` [PATCH 23/40] workqueue: implement worker states Tejun Heo
2010-01-18  0:57 ` [PATCH 24/40] workqueue: reimplement CPU hotplugging support using trustee Tejun Heo
2010-01-18  0:57 ` [PATCH 25/40] workqueue: make single thread workqueue shared worker pool friendly Tejun Heo
2010-01-18  0:57 ` [PATCH 26/40] workqueue: use shared worklist and pool all workers per cpu Tejun Heo
2010-01-18  0:57 ` [PATCH 27/40] workqueue: implement concurrency managed dynamic worker pool Tejun Heo
2010-01-18  0:57 ` [PATCH 28/40] workqueue: increase max_active of keventd and kill current_is_keventd() Tejun Heo
2010-01-18  0:57 ` [PATCH 29/40] workqueue: add system_wq and system_single_wq Tejun Heo
2010-01-18  0:57 ` [PATCH 30/40] workqueue: implement work_busy() Tejun Heo
2010-01-18  2:52   ` Andy Walls
2010-01-18  5:41     ` Tejun Heo
2010-01-18  0:57 ` [PATCH 31/40] libata: take advantage of cmwq and remove concurrency limitations Tejun Heo
2010-01-18 15:48   ` Stefan Richter
2010-01-19  0:49     ` Tejun Heo
2010-01-18  0:57 ` [PATCH 32/40] async: introduce workqueue based alternative implementation Tejun Heo
2010-01-18  6:01   ` Arjan van de Ven
2010-01-18  8:49     ` Tejun Heo
2010-01-18 15:25       ` Arjan van de Ven
2010-01-19  0:57         ` Tejun Heo
2010-01-19  0:57           ` Arjan van de Ven
2010-01-19  7:56             ` Tejun Heo
2010-01-19 14:37               ` Arjan van de Ven
2010-01-20  0:19                 ` Tejun Heo
2010-01-20  0:31                   ` Arjan van de Ven
2010-01-20  2:08                     ` Tejun Heo
2010-01-20  6:03                       ` Arjan van de Ven
2010-01-20  8:24                         ` Tejun Heo
2010-01-22 10:59                           ` [PATCH] async: use workqueue for worker pool Tejun Heo
2010-01-18  0:57 ` [PATCH 33/40] async: convert async users to use the new implementation Tejun Heo
2010-01-18  0:57 ` [PATCH 34/40] async: kill original implementation Tejun Heo
2010-01-18  0:57 ` [PATCH 35/40] fscache: convert object to use workqueue instead of slow-work Tejun Heo
2010-01-18  0:57 ` [PATCH 36/40] fscache: convert operation " Tejun Heo
2010-01-18  0:57 ` [PATCH 37/40] fscache: drop references to slow-work Tejun Heo
2010-01-18  0:57 ` [PATCH 38/40] cifs: use workqueue instead of slow-work Tejun Heo
2010-01-19 12:20   ` Jeff Layton
2010-01-20  0:15     ` Tejun Heo
2010-01-20  0:56       ` Jeff Layton
2010-01-20  1:23         ` Tejun Heo
2010-01-22 11:14           ` [PATCH UPDATED " Tejun Heo
2010-01-22 11:45             ` Jeff Layton
2010-01-24  8:25               ` Tejun Heo
2010-01-24 12:13                 ` Jeff Layton
2010-01-25 15:25                   ` Tejun Heo
2010-01-18  0:57 ` [PATCH 39/40] gfs2: " Tejun Heo
2010-01-18  9:45   ` Steven Whitehouse
2010-01-18 11:24     ` Tejun Heo
2010-01-18 12:07       ` Steven Whitehouse
2010-01-19  1:00         ` Tejun Heo
2010-01-19  8:46           ` Tejun Heo [this message]
2010-01-18  0:57 ` [PATCH 40/40] slow-work: kill it Tejun Heo
2010-01-18  1:03 ` perf-wq.c used to generate synthetic workload Tejun Heo
2010-01-18 16:13 ` [PATCHSET] concurrency managed workqueue, take#3 Stefan Richter
2010-02-12 18:03 ` [PATCH 35/40] fscache: convert object to use workqueue instead of slow-work David Howells
2010-02-13  5:43   ` Tejun Heo
2010-02-15 15:04   ` David Howells
2010-02-16  3:40     ` Tejun Heo
2010-02-16  3:59       ` Tejun Heo
2010-02-16 18:05     ` David Howells
2010-02-16 23:50       ` Tejun Heo
2010-02-18 11:50       ` David Howells
2010-02-18 12:33         ` Tejun Heo

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=4B55715B.8070702@kernel.org \
    --to=tj@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=arjan@linux.intel.com \
    --cc=avi@redhat.com \
    --cc=awalls@radix.net \
    --cc=cl@linux-foundation.org \
    --cc=dhowells@redhat.com \
    --cc=jeff@garzik.org \
    --cc=jens.axboe@oracle.com \
    --cc=johannes@sipsolutions.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=peterz@infradead.org \
    --cc=rusty@rustcorp.com.au \
    --cc=swhiteho@redhat.com \
    --cc=torvalds@linux-foundation.org \
    /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

Powered by JetHome