jbd2: refine waiting for shadow buffers

Currently when we add a buffer to a transaction, we wait until the
buffer is removed from BJ_Shadow list (so that we prevent any changes
to the buffer that is just written to the journal).  This can take
unnecessarily long as a lot happens between the time the buffer is
submitted to the journal and the time when we remove the buffer from
BJ_Shadow list.  (e.g.  We wait for all data buffers in the
transaction, we issue a cache flush, etc.)  Also this creates a
dependency of do_get_write_access() on transaction commit (namely
waiting for data IO to complete) which we want to avoid when
implementing transaction reservation.

So we modify commit code to set new BH_Shadow flag when temporary
shadowing buffer is created and we clear that flag once IO on that
buffer is complete.  This allows do_get_write_access() to wait only
for BH_Shadow bit and thus removes the dependency on data IO
completion.

Reviewed-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

3 files changed, 53 insertions, 26 deletions

diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 9c505f1aa1fd..2439054a6c9a 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -244,6 +244,31 @@ typedef struct journal_superblock_s
 
 #include <linux/fs.h>
 #include <linux/sched.h>
+
+enum jbd_state_bits {
+        BH_JBD                  /* Has an attached ext3 journal_head */
+          = BH_PrivateStart,
+        BH_JWrite,              /* Being written to log (@@@ DEBUGGING) */
+        BH_Freed,               /* Has been freed (truncated) */
+        BH_Revoked,             /* Has been revoked from the log */
+        BH_RevokeValid,         /* Revoked flag is valid */
+        BH_JBDDirty,            /* Is dirty but journaled */
+        BH_State,               /* Pins most journal_head state */
+        BH_JournalHead,         /* Pins bh->b_private and jh->b_bh */
+        BH_Unshadow,            /* Dummy bit, for BJ_Shadow wakeup filtering */
+        BH_JBDPrivateStart,     /* First bit available for private use by FS */
+};
+
+BUFFER_FNS(JBD, jbd)
+BUFFER_FNS(JWrite, jwrite)
+BUFFER_FNS(JBDDirty, jbddirty)
+TAS_BUFFER_FNS(JBDDirty, jbddirty)
+BUFFER_FNS(Revoked, revoked)
+TAS_BUFFER_FNS(Revoked, revoked)
+BUFFER_FNS(RevokeValid, revokevalid)
+TAS_BUFFER_FNS(RevokeValid, revokevalid)
+BUFFER_FNS(Freed, freed)
+
 #include <linux/jbd_common.h>
 
 #define J_ASSERT(assert)        BUG_ON(!(assert))
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index b7dc40da99e0..e33e84b3d5c8 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -302,6 +302,34 @@ typedef struct journal_superblock_s
 
 #include <linux/fs.h>
 #include <linux/sched.h>
+
+enum jbd_state_bits {
+        BH_JBD                  /* Has an attached ext3 journal_head */
+          = BH_PrivateStart,
+        BH_JWrite,              /* Being written to log (@@@ DEBUGGING) */
+        BH_Freed,               /* Has been freed (truncated) */
+        BH_Revoked,             /* Has been revoked from the log */
+        BH_RevokeValid,         /* Revoked flag is valid */
+        BH_JBDDirty,            /* Is dirty but journaled */
+        BH_State,               /* Pins most journal_head state */
+        BH_JournalHead,         /* Pins bh->b_private and jh->b_bh */
+        BH_Shadow,              /* IO on shadow buffer is running */
+        BH_Verified,            /* Metadata block has been verified ok */
+        BH_JBDPrivateStart,     /* First bit available for private use by FS */
+};
+
+BUFFER_FNS(JBD, jbd)
+BUFFER_FNS(JWrite, jwrite)
+BUFFER_FNS(JBDDirty, jbddirty)
+TAS_BUFFER_FNS(JBDDirty, jbddirty)
+BUFFER_FNS(Revoked, revoked)
+TAS_BUFFER_FNS(Revoked, revoked)
+BUFFER_FNS(RevokeValid, revokevalid)
+TAS_BUFFER_FNS(RevokeValid, revokevalid)
+BUFFER_FNS(Freed, freed)
+BUFFER_FNS(Shadow, shadow)
+BUFFER_FNS(Verified, verified)
+
 #include <linux/jbd_common.h>
 
 #define J_ASSERT(assert)        BUG_ON(!(assert))
diff --git a/include/linux/jbd_common.h b/include/linux/jbd_common.h
index 6133679bc4c0..b1f708976ffd 100644
--- a/include/linux/jbd_common.h
+++ b/include/linux/jbd_common.h
@@ -1,32 +1,6 @@
 #ifndef _LINUX_JBD_STATE_H
 #define _LINUX_JBD_STATE_H
 
-enum jbd_state_bits {
-        BH_JBD                  /* Has an attached ext3 journal_head */
-          = BH_PrivateStart,
-        BH_JWrite,              /* Being written to log (@@@ DEBUGGING) */
-        BH_Freed,               /* Has been freed (truncated) */
-        BH_Revoked,             /* Has been revoked from the log */
-        BH_RevokeValid,         /* Revoked flag is valid */
-        BH_JBDDirty,            /* Is dirty but journaled */
-        BH_State,               /* Pins most journal_head state */
-        BH_JournalHead,         /* Pins bh->b_private and jh->b_bh */
-        BH_Unshadow,            /* Dummy bit, for BJ_Shadow wakeup filtering */
-        BH_Verified,            /* Metadata block has been verified ok */
-        BH_JBDPrivateStart,     /* First bit available for private use by FS */
-};
-
-BUFFER_FNS(JBD, jbd)
-BUFFER_FNS(JWrite, jwrite)
-BUFFER_FNS(JBDDirty, jbddirty)
-TAS_BUFFER_FNS(JBDDirty, jbddirty)
-BUFFER_FNS(Revoked, revoked)
-TAS_BUFFER_FNS(Revoked, revoked)
-BUFFER_FNS(RevokeValid, revokevalid)
-TAS_BUFFER_FNS(RevokeValid, revokevalid)
-BUFFER_FNS(Freed, freed)
-BUFFER_FNS(Verified, verified)
-
 static inline struct buffer_head *jh2bh(struct journal_head *jh)
 {
         return jh->b_bh;