All of lore.kernel.org
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: Ingo Molnar <mingo@elte.hu>
Cc: "Stephen C. Tweedie" <sct@redhat.com>,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [patch] Real-Time Preemption, -RT-2.6.13-rc4-V0.7.52-01
Date: Fri, 26 Aug 2005 07:20:49 -0400	[thread overview]
Message-ID: <1125055250.5365.33.camel@localhost.localdomain> (raw)
In-Reply-To: <20050826060815.GB17783@elte.hu>

On Fri, 2005-08-26 at 08:08 +0200, Ingo Molnar wrote:
> * Steven Rostedt <rostedt@goodmis.org> wrote:
> 
> > So, the only other solutions that I can think of is:
> > 
> > a) add yet another (bloat) lock to the buffer head.
> > 
> > b) Still use your b_update_lock for the jbd_lock_bh_journal_head and 
> > change the jbd_lock_bh_state to what I discussed earlier, and that 
> > being the hash wait_on_bit code.
> 
> could you try a), how clean does it get? Personally i'm much more in 
> favor of cleanliness. On the vanilla kernel a spinlock is zero bytes on 
> UP [the most RAM-sensitive platform], and it's a word on typical SMP.

Not only the cleanest, but also the simplest :-)

-- Steve

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

Index: linux_realtime_ernie/fs/buffer.c
===================================================================
--- linux_realtime_ernie/fs/buffer.c	(revision 303)
+++ linux_realtime_ernie/fs/buffer.c	(working copy)
@@ -3053,6 +3053,7 @@
 {
 	BUG_ON(!list_empty(&bh->b_assoc_buffers));
 	BUG_ON(spin_is_locked(&bh->b_uptodate_lock));
+	BUG_ON(spin_is_locked(&bh->b_state_lock));
 	kmem_cache_free(bh_cachep, bh);
 	preempt_disable();
 	__get_cpu_var(bh_accounting).nr--;
@@ -3071,6 +3072,7 @@
 		memset(bh, 0, sizeof(*bh));
 		INIT_LIST_HEAD(&bh->b_assoc_buffers);
 		spin_lock_init(&bh->b_uptodate_lock);
+		spin_lock_init(&bh->b_state_lock);
 	}
 }
 
Index: linux_realtime_ernie/include/linux/buffer_head.h
===================================================================
--- linux_realtime_ernie/include/linux/buffer_head.h	(revision 303)
+++ linux_realtime_ernie/include/linux/buffer_head.h	(working copy)
@@ -62,6 +62,7 @@
  	void *b_private;		/* reserved for b_end_io */
 	struct list_head b_assoc_buffers; /* associated with another mapping */
 	spinlock_t b_uptodate_lock;
+	spinlock_t b_state_lock;
 };
 
 /*
Index: linux_realtime_ernie/include/linux/jbd.h
===================================================================
--- linux_realtime_ernie/include/linux/jbd.h	(revision 303)
+++ linux_realtime_ernie/include/linux/jbd.h	(working copy)
@@ -326,32 +326,32 @@
 
 static inline void jbd_lock_bh_state(struct buffer_head *bh)
 {
-	bit_spin_lock(BH_State, &bh->b_state);
+	spin_lock(&bh->b_state_lock);
 }
 
 static inline int jbd_trylock_bh_state(struct buffer_head *bh)
 {
-	return bit_spin_trylock(BH_State, &bh->b_state);
+	return spin_trylock(&bh->b_state_lock);
 }
 
 static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
 {
-	return bit_spin_is_locked(BH_State, &bh->b_state);
+	return spin_is_locked(&bh->b_state_lock);
 }
 
 static inline void jbd_unlock_bh_state(struct buffer_head *bh)
 {
-	bit_spin_unlock(BH_State, &bh->b_state);
+	spin_unlock(&bh->b_state_lock);
 }
 
 static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
 {
-	bit_spin_lock(BH_JournalHead, &bh->b_state);
+	spin_lock(&bh->b_uptodate_lock);
 }
 
 static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
 {
-	bit_spin_unlock(BH_JournalHead, &bh->b_state);
+	spin_unlock(&bh->b_uptodate_lock);
 }
 
 struct jbd_revoke_table_s;



  reply	other threads:[~2005-08-26 11:21 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-07-30 16:03 [patch] Real-Time Preemption, -RT-2.6.13-rc4-V0.7.52-01 Ingo Molnar
2005-07-30 20:47 ` Peter Zijlstra
2005-07-30 20:52   ` Ingo Molnar
2005-07-31  4:47     ` Lee Revell
2005-07-31  6:38       ` Ingo Molnar
2005-08-01  4:45         ` Lee Revell
2005-08-01 21:08           ` Ingo Molnar
2005-08-01 21:12             ` Ingo Molnar
2005-08-02 13:56           ` Steven Rostedt
2005-08-02 14:05             ` Lee Revell
2005-08-02 14:20               ` Steven Rostedt
2005-08-02 15:37                 ` 2.6.13-rc3 -> sluggish PS2 keyboard (was Re: [patch] Real-Time Preemption, -RT-2.6.13-rc4-V0.7.52-01) Lee Revell
2005-08-02 15:44                   ` Vojtech Pavlik
2005-08-02 15:46                     ` Lee Revell
2005-08-02 15:47                     ` Lee Revell
2005-08-02 15:53                       ` Steven Rostedt
2005-08-02 15:55                       ` Vojtech Pavlik
2005-08-02 15:55                   ` Dmitry Torokhov
2005-08-02 15:38                 ` [patch] Real-Time Preemption, -RT-2.6.13-rc4-V0.7.52-01 Lee Revell
2005-07-31  8:03     ` Peter Zijlstra
2005-07-31 10:44       ` Ingo Molnar
2005-07-31 15:56         ` [patch] Real-Time Preemption, -RT-2.6.13-rc4-V0.7.52-05 Gene Heskett
2005-08-01 18:22 ` [patch] Real-Time Preemption, -RT-2.6.13-rc4-V0.7.52-01 Steven Rostedt
2005-08-01 19:49   ` Steven Rostedt
2005-08-01 20:52   ` Ingo Molnar
2005-08-01 21:09     ` Daniel Walker
2005-08-01 21:15       ` Ingo Molnar
2005-08-02  0:43       ` Steven Rostedt
2005-08-01 21:15     ` Steven Rostedt
2005-08-01 21:23       ` Ingo Molnar
2005-08-01 21:20   ` Daniel Walker
2005-08-02  0:53     ` Steven Rostedt
2005-08-02 10:19       ` Ingo Molnar
2005-08-02 19:45         ` Steven Rostedt
2005-08-02 19:56           ` Steven Rostedt
2005-08-02 23:38           ` Daniel Walker
2005-08-03  0:00             ` Steven Rostedt
2005-08-03  1:12               ` George Anzinger
2005-08-03  1:48                 ` Keith Owens
2005-08-03  2:12                   ` George Anzinger
2005-08-03  2:25               ` Daniel Walker
2005-08-03  2:42                 ` Steven Rostedt
2005-08-03  2:58                   ` Daniel Walker
2005-08-03 10:30                     ` Steven Rostedt
2005-08-03 15:10                       ` Daniel Walker
2005-08-03 10:37                     ` [Question] arch-independent way to differentiate between user and kernel Steven Rostedt
2005-08-03 10:48                       ` Ingo Molnar
2005-08-03 12:18                         ` Steven Rostedt
2005-08-03 10:56                       ` [Question] arch-independent way to differentiate between user andkernel linux-os (Dick Johnson)
2005-08-03 11:44                         ` Steven Rostedt
2005-08-03 12:04                           ` Ingo Molnar
2005-08-03 12:30                             ` Steven Rostedt
2005-08-03 14:50                     ` [patch] Real-Time Preemption, -RT-2.6.13-rc4-V0.7.52-01 Steven Rostedt
2005-08-03 15:15                       ` Steven Rostedt
2005-08-03 15:57                         ` Steven Rostedt
2005-08-03 16:44                       ` Steven Rostedt
     [not found]                         ` <20050812125844.GA13357@elte.hu>
2005-08-26  4:24                           ` Steven Rostedt
2005-08-26  6:08                             ` Ingo Molnar
2005-08-26 11:20                               ` Steven Rostedt [this message]
2005-08-30 10:58                                 ` Stephen C. Tweedie
2005-08-30 11:14                                   ` Ingo Molnar
2005-08-30 11:00                             ` Stephen C. Tweedie
2005-08-02  3:55     ` Steven Rostedt
2005-08-02  4:07       ` Daniel Walker
2005-08-02 14:53 ` Steven Rostedt
2005-08-04 12:20 ` Andrzej Nowak

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=1125055250.5365.33.camel@localhost.localdomain \
    --to=rostedt@goodmis.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=sct@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.