[XFS] Remove the xlog_ticket allocator

[linux-2.6] / fs / xfs / xfs_log_priv.h

diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index e008233ee2492dd4b7c96f76ccaafc372b32201e..c1583960009de8d884725e8a965961ad1775ea42 100644 (file)
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -49,10 +49,10 @@ struct xfs_mount;
 #define XLOG_HEADER_SIZE       512
 
 #define XLOG_REC_SHIFT(log) \
-       BTOBB(1 << (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb) ? \
+       BTOBB(1 << (xfs_sb_version_haslogv2(&log->l_mp->m_sb) ? \
         XLOG_MAX_RECORD_BSHIFT : XLOG_BIG_RECORD_BSHIFT))
 #define XLOG_TOTAL_REC_SHIFT(log) \
-       BTOBB(XLOG_MAX_ICLOGS << (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb) ? \
+       BTOBB(XLOG_MAX_ICLOGS << (xfs_sb_version_haslogv2(&log->l_mp->m_sb) ? \
         XLOG_MAX_RECORD_BSHIFT : XLOG_BIG_RECORD_BSHIFT))
 
 
@@ -242,7 +242,7 @@ typedef struct xlog_res {
 
 typedef struct xlog_ticket {
        sv_t               t_sema;       /* sleep on this semaphore      : 20 */
-       struct xlog_ticket *t_next;      /*                              :4|8 */
+       struct xlog_ticket *t_next;      /*                              :4|8 */
        struct xlog_ticket *t_prev;      /*                              :4|8 */
        xlog_tid_t         t_tid;        /* transaction identifier       : 4  */
        int                t_curr_res;   /* current reservation in bytes : 4  */
@@ -324,6 +324,19 @@ typedef struct xlog_rec_ext_header {
  * - ic_offset is the current number of bytes written to in this iclog.
  * - ic_refcnt is bumped when someone is writing to the log.
  * - ic_state is the state of the iclog.
+ *
+ * Because of cacheline contention on large machines, we need to separate
+ * various resources onto different cachelines. To start with, make the
+ * structure cacheline aligned. The following fields can be contended on
+ * by independent processes:
+ *
+ *     - ic_callback_*
+ *     - ic_refcnt
+ *     - fields protected by the global l_icloglock
+ *
+ * so we need to ensure that these fields are located in separate cachelines.
+ * We'll put all the read-only and l_icloglock fields in the first cacheline,
+ * and move everything else out to subsequent cachelines.
  */
 typedef struct xlog_iclog_fields {
        sv_t                    ic_forcesema;
@@ -332,18 +345,23 @@ typedef struct xlog_iclog_fields {
        struct xlog_in_core     *ic_prev;
        struct xfs_buf          *ic_bp;
        struct log              *ic_log;
-       xfs_log_callback_t      *ic_callback;
-       xfs_log_callback_t      **ic_callback_tail;
-#ifdef XFS_LOG_TRACE
-       struct ktrace           *ic_trace;
-#endif
        int                     ic_size;
        int                     ic_offset;
-       int                     ic_refcnt;
        int                     ic_bwritecnt;
        ushort_t                ic_state;
        char                    *ic_datap;      /* pointer to iclog data */
-} xlog_iclog_fields_t;
+#ifdef XFS_LOG_TRACE
+       struct ktrace           *ic_trace;
+#endif
+
+       /* Callback structures need their own cacheline */
+       spinlock_t              ic_callback_lock ____cacheline_aligned_in_smp;
+       xfs_log_callback_t      *ic_callback;
+       xfs_log_callback_t      **ic_callback_tail;
+
+       /* reference counts need their own cacheline */
+       atomic_t                ic_refcnt ____cacheline_aligned_in_smp;
+} xlog_iclog_fields_t ____cacheline_aligned_in_smp;
 
 typedef union xlog_in_core2 {
        xlog_rec_header_t       hic_header;
@@ -366,6 +384,7 @@ typedef struct xlog_in_core {
 #define        ic_bp           hic_fields.ic_bp
 #define        ic_log          hic_fields.ic_log
 #define        ic_callback     hic_fields.ic_callback
+#define        ic_callback_lock hic_fields.ic_callback_lock
 #define        ic_callback_tail hic_fields.ic_callback_tail
 #define        ic_trace        hic_fields.ic_trace
 #define        ic_size         hic_fields.ic_size
@@ -387,13 +406,8 @@ typedef struct log {
        sema_t                  l_flushsema;    /* iclog flushing semaphore */
        int                     l_flushcnt;     /* # of procs waiting on this
                                                 * sema */
-       int                     l_ticket_cnt;   /* free ticket count */
-       int                     l_ticket_tcnt;  /* total ticket count */
        int                     l_covered_state;/* state of "covering disk
                                                 * log entries" */
-       xlog_ticket_t           *l_freelist;    /* free list of tickets */
-       xlog_ticket_t           *l_unmount_free;/* kmem_free these addresses */
-       xlog_ticket_t           *l_tail;        /* free list of tickets */
        xlog_in_core_t          *l_iclog;       /* head log queue       */
        spinlock_t              l_icloglock;    /* grab to change iclog state */
        xfs_lsn_t               l_tail_lsn;     /* lsn of 1st LR with unflushed
@@ -459,6 +473,8 @@ extern struct xfs_buf *xlog_get_bp(xlog_t *, int);
 extern void     xlog_put_bp(struct xfs_buf *);
 extern int      xlog_bread(xlog_t *, xfs_daddr_t, int, struct xfs_buf *);
 
+extern kmem_zone_t     *xfs_log_ticket_zone;
+
 /* iclog tracing */
 #define XLOG_TRACE_GRAB_FLUSH  1
 #define XLOG_TRACE_REL_FLUSH   2