xfs: add the xlog_grant_head structure

Add a new data structure to allow sharing code between the log grant and
regrant code.

Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
This commit is contained in:
Christoph Hellwig 2012-02-20 02:31:25 +00:00 committed by Ben Myers
parent 14a7235fba
commit 28496968a6
4 changed files with 74 additions and 73 deletions

View File

@ -158,7 +158,7 @@ xlog_reserveq_wake(
struct xlog_ticket *tic; struct xlog_ticket *tic;
int need_bytes; int need_bytes;
list_for_each_entry(tic, &log->l_reserveq, t_queue) { list_for_each_entry(tic, &log->l_reserve_head.waiters, t_queue) {
if (tic->t_flags & XLOG_TIC_PERM_RESERV) if (tic->t_flags & XLOG_TIC_PERM_RESERV)
need_bytes = tic->t_unit_res * tic->t_cnt; need_bytes = tic->t_unit_res * tic->t_cnt;
else else
@ -183,7 +183,7 @@ xlog_writeq_wake(
struct xlog_ticket *tic; struct xlog_ticket *tic;
int need_bytes; int need_bytes;
list_for_each_entry(tic, &log->l_writeq, t_queue) { list_for_each_entry(tic, &log->l_write_head.waiters, t_queue) {
ASSERT(tic->t_flags & XLOG_TIC_PERM_RESERV); ASSERT(tic->t_flags & XLOG_TIC_PERM_RESERV);
need_bytes = tic->t_unit_res; need_bytes = tic->t_unit_res;
@ -205,7 +205,7 @@ xlog_reserveq_wait(
struct xlog_ticket *tic, struct xlog_ticket *tic,
int need_bytes) int need_bytes)
{ {
list_add_tail(&tic->t_queue, &log->l_reserveq); list_add_tail(&tic->t_queue, &log->l_reserve_head.waiters);
do { do {
if (XLOG_FORCED_SHUTDOWN(log)) if (XLOG_FORCED_SHUTDOWN(log))
@ -213,7 +213,7 @@ xlog_reserveq_wait(
xlog_grant_push_ail(log, need_bytes); xlog_grant_push_ail(log, need_bytes);
__set_current_state(TASK_UNINTERRUPTIBLE); __set_current_state(TASK_UNINTERRUPTIBLE);
spin_unlock(&log->l_grant_reserve_lock); spin_unlock(&log->l_reserve_head.lock);
XFS_STATS_INC(xs_sleep_logspace); XFS_STATS_INC(xs_sleep_logspace);
@ -221,10 +221,10 @@ xlog_reserveq_wait(
schedule(); schedule();
trace_xfs_log_grant_wake(log, tic); trace_xfs_log_grant_wake(log, tic);
spin_lock(&log->l_grant_reserve_lock); spin_lock(&log->l_reserve_head.lock);
if (XLOG_FORCED_SHUTDOWN(log)) if (XLOG_FORCED_SHUTDOWN(log))
goto shutdown; goto shutdown;
} while (xlog_space_left(log, &log->l_grant_reserve_head) < need_bytes); } while (xlog_space_left(log, &log->l_reserve_head.grant) < need_bytes);
list_del_init(&tic->t_queue); list_del_init(&tic->t_queue);
return 0; return 0;
@ -239,7 +239,7 @@ xlog_writeq_wait(
struct xlog_ticket *tic, struct xlog_ticket *tic,
int need_bytes) int need_bytes)
{ {
list_add_tail(&tic->t_queue, &log->l_writeq); list_add_tail(&tic->t_queue, &log->l_write_head.waiters);
do { do {
if (XLOG_FORCED_SHUTDOWN(log)) if (XLOG_FORCED_SHUTDOWN(log))
@ -247,7 +247,7 @@ xlog_writeq_wait(
xlog_grant_push_ail(log, need_bytes); xlog_grant_push_ail(log, need_bytes);
__set_current_state(TASK_UNINTERRUPTIBLE); __set_current_state(TASK_UNINTERRUPTIBLE);
spin_unlock(&log->l_grant_write_lock); spin_unlock(&log->l_write_head.lock);
XFS_STATS_INC(xs_sleep_logspace); XFS_STATS_INC(xs_sleep_logspace);
@ -255,10 +255,10 @@ xlog_writeq_wait(
schedule(); schedule();
trace_xfs_log_regrant_write_wake(log, tic); trace_xfs_log_regrant_write_wake(log, tic);
spin_lock(&log->l_grant_write_lock); spin_lock(&log->l_write_head.lock);
if (XLOG_FORCED_SHUTDOWN(log)) if (XLOG_FORCED_SHUTDOWN(log))
goto shutdown; goto shutdown;
} while (xlog_space_left(log, &log->l_grant_write_head) < need_bytes); } while (xlog_space_left(log, &log->l_write_head.grant) < need_bytes);
list_del_init(&tic->t_queue); list_del_init(&tic->t_queue);
return 0; return 0;
@ -779,22 +779,22 @@ xfs_log_space_wake(
if (XLOG_FORCED_SHUTDOWN(log)) if (XLOG_FORCED_SHUTDOWN(log))
return; return;
if (!list_empty_careful(&log->l_writeq)) { if (!list_empty_careful(&log->l_write_head.waiters)) {
ASSERT(!(log->l_flags & XLOG_ACTIVE_RECOVERY)); ASSERT(!(log->l_flags & XLOG_ACTIVE_RECOVERY));
spin_lock(&log->l_grant_write_lock); spin_lock(&log->l_write_head.lock);
free_bytes = xlog_space_left(log, &log->l_grant_write_head); free_bytes = xlog_space_left(log, &log->l_write_head.grant);
xlog_writeq_wake(log, &free_bytes); xlog_writeq_wake(log, &free_bytes);
spin_unlock(&log->l_grant_write_lock); spin_unlock(&log->l_write_head.lock);
} }
if (!list_empty_careful(&log->l_reserveq)) { if (!list_empty_careful(&log->l_reserve_head.waiters)) {
ASSERT(!(log->l_flags & XLOG_ACTIVE_RECOVERY)); ASSERT(!(log->l_flags & XLOG_ACTIVE_RECOVERY));
spin_lock(&log->l_grant_reserve_lock); spin_lock(&log->l_reserve_head.lock);
free_bytes = xlog_space_left(log, &log->l_grant_reserve_head); free_bytes = xlog_space_left(log, &log->l_reserve_head.grant);
xlog_reserveq_wake(log, &free_bytes); xlog_reserveq_wake(log, &free_bytes);
spin_unlock(&log->l_grant_reserve_lock); spin_unlock(&log->l_reserve_head.lock);
} }
} }
@ -1070,12 +1070,12 @@ xlog_alloc_log(xfs_mount_t *mp,
xlog_assign_atomic_lsn(&log->l_tail_lsn, 1, 0); xlog_assign_atomic_lsn(&log->l_tail_lsn, 1, 0);
xlog_assign_atomic_lsn(&log->l_last_sync_lsn, 1, 0); xlog_assign_atomic_lsn(&log->l_last_sync_lsn, 1, 0);
log->l_curr_cycle = 1; /* 0 is bad since this is initial value */ log->l_curr_cycle = 1; /* 0 is bad since this is initial value */
xlog_assign_grant_head(&log->l_grant_reserve_head, 1, 0); xlog_assign_grant_head(&log->l_reserve_head.grant, 1, 0);
xlog_assign_grant_head(&log->l_grant_write_head, 1, 0); xlog_assign_grant_head(&log->l_write_head.grant, 1, 0);
INIT_LIST_HEAD(&log->l_reserveq); INIT_LIST_HEAD(&log->l_reserve_head.waiters);
INIT_LIST_HEAD(&log->l_writeq); INIT_LIST_HEAD(&log->l_write_head.waiters);
spin_lock_init(&log->l_grant_reserve_lock); spin_lock_init(&log->l_reserve_head.lock);
spin_lock_init(&log->l_grant_write_lock); spin_lock_init(&log->l_write_head.lock);
error = EFSCORRUPTED; error = EFSCORRUPTED;
if (xfs_sb_version_hassector(&mp->m_sb)) { if (xfs_sb_version_hassector(&mp->m_sb)) {
@ -1250,7 +1250,7 @@ xlog_grant_push_ail(
ASSERT(BTOBB(need_bytes) < log->l_logBBsize); ASSERT(BTOBB(need_bytes) < log->l_logBBsize);
free_bytes = xlog_space_left(log, &log->l_grant_reserve_head); free_bytes = xlog_space_left(log, &log->l_reserve_head.grant);
free_blocks = BTOBBT(free_bytes); free_blocks = BTOBBT(free_bytes);
/* /*
@ -1382,8 +1382,8 @@ xlog_sync(xlog_t *log,
roundoff < BBTOB(1))); roundoff < BBTOB(1)));
/* move grant heads by roundoff in sync */ /* move grant heads by roundoff in sync */
xlog_grant_add_space(log, &log->l_grant_reserve_head, roundoff); xlog_grant_add_space(log, &log->l_reserve_head.grant, roundoff);
xlog_grant_add_space(log, &log->l_grant_write_head, roundoff); xlog_grant_add_space(log, &log->l_write_head.grant, roundoff);
/* put cycle number in every block */ /* put cycle number in every block */
xlog_pack_data(log, iclog, roundoff); xlog_pack_data(log, iclog, roundoff);
@ -2547,8 +2547,8 @@ restart:
* path. Hence any lock will be globally hot if we take it unconditionally on * path. Hence any lock will be globally hot if we take it unconditionally on
* every pass. * every pass.
* *
* As tickets are only ever moved on and off the reserveq under the * As tickets are only ever moved on and off the l_reserve.waiters under the
* l_grant_reserve_lock, we only need to take that lock if we are going to add * l_reserve.lock, we only need to take that lock if we are going to add
* the ticket to the queue and sleep. We can avoid taking the lock if the ticket * the ticket to the queue and sleep. We can avoid taking the lock if the ticket
* was never added to the reserveq because the t_queue list head will be empty * was never added to the reserveq because the t_queue list head will be empty
* and we hold the only reference to it so it can safely be checked unlocked. * and we hold the only reference to it so it can safely be checked unlocked.
@ -2574,23 +2574,23 @@ xlog_grant_log_space(
need_bytes = tic->t_unit_res; need_bytes = tic->t_unit_res;
if (tic->t_flags & XFS_LOG_PERM_RESERV) if (tic->t_flags & XFS_LOG_PERM_RESERV)
need_bytes *= tic->t_ocnt; need_bytes *= tic->t_ocnt;
free_bytes = xlog_space_left(log, &log->l_grant_reserve_head); free_bytes = xlog_space_left(log, &log->l_reserve_head.grant);
if (!list_empty_careful(&log->l_reserveq)) { if (!list_empty_careful(&log->l_reserve_head.waiters)) {
spin_lock(&log->l_grant_reserve_lock); spin_lock(&log->l_reserve_head.lock);
if (!xlog_reserveq_wake(log, &free_bytes) || if (!xlog_reserveq_wake(log, &free_bytes) ||
free_bytes < need_bytes) free_bytes < need_bytes)
error = xlog_reserveq_wait(log, tic, need_bytes); error = xlog_reserveq_wait(log, tic, need_bytes);
spin_unlock(&log->l_grant_reserve_lock); spin_unlock(&log->l_reserve_head.lock);
} else if (free_bytes < need_bytes) { } else if (free_bytes < need_bytes) {
spin_lock(&log->l_grant_reserve_lock); spin_lock(&log->l_reserve_head.lock);
error = xlog_reserveq_wait(log, tic, need_bytes); error = xlog_reserveq_wait(log, tic, need_bytes);
spin_unlock(&log->l_grant_reserve_lock); spin_unlock(&log->l_reserve_head.lock);
} }
if (error) if (error)
return error; return error;
xlog_grant_add_space(log, &log->l_grant_reserve_head, need_bytes); xlog_grant_add_space(log, &log->l_reserve_head.grant, need_bytes);
xlog_grant_add_space(log, &log->l_grant_write_head, need_bytes); xlog_grant_add_space(log, &log->l_write_head.grant, need_bytes);
trace_xfs_log_grant_exit(log, tic); trace_xfs_log_grant_exit(log, tic);
xlog_verify_grant_tail(log); xlog_verify_grant_tail(log);
return 0; return 0;
@ -2627,23 +2627,23 @@ xlog_regrant_write_log_space(
* otherwise try to get some space for this transaction. * otherwise try to get some space for this transaction.
*/ */
need_bytes = tic->t_unit_res; need_bytes = tic->t_unit_res;
free_bytes = xlog_space_left(log, &log->l_grant_write_head); free_bytes = xlog_space_left(log, &log->l_write_head.grant);
if (!list_empty_careful(&log->l_writeq)) { if (!list_empty_careful(&log->l_write_head.waiters)) {
spin_lock(&log->l_grant_write_lock); spin_lock(&log->l_write_head.lock);
if (!xlog_writeq_wake(log, &free_bytes) || if (!xlog_writeq_wake(log, &free_bytes) ||
free_bytes < need_bytes) free_bytes < need_bytes)
error = xlog_writeq_wait(log, tic, need_bytes); error = xlog_writeq_wait(log, tic, need_bytes);
spin_unlock(&log->l_grant_write_lock); spin_unlock(&log->l_write_head.lock);
} else if (free_bytes < need_bytes) { } else if (free_bytes < need_bytes) {
spin_lock(&log->l_grant_write_lock); spin_lock(&log->l_write_head.lock);
error = xlog_writeq_wait(log, tic, need_bytes); error = xlog_writeq_wait(log, tic, need_bytes);
spin_unlock(&log->l_grant_write_lock); spin_unlock(&log->l_write_head.lock);
} }
if (error) if (error)
return error; return error;
xlog_grant_add_space(log, &log->l_grant_write_head, need_bytes); xlog_grant_add_space(log, &log->l_write_head.grant, need_bytes);
trace_xfs_log_regrant_write_exit(log, tic); trace_xfs_log_regrant_write_exit(log, tic);
xlog_verify_grant_tail(log); xlog_verify_grant_tail(log);
return 0; return 0;
@ -2665,9 +2665,9 @@ xlog_regrant_reserve_log_space(xlog_t *log,
if (ticket->t_cnt > 0) if (ticket->t_cnt > 0)
ticket->t_cnt--; ticket->t_cnt--;
xlog_grant_sub_space(log, &log->l_grant_reserve_head, xlog_grant_sub_space(log, &log->l_reserve_head.grant,
ticket->t_curr_res); ticket->t_curr_res);
xlog_grant_sub_space(log, &log->l_grant_write_head, xlog_grant_sub_space(log, &log->l_write_head.grant,
ticket->t_curr_res); ticket->t_curr_res);
ticket->t_curr_res = ticket->t_unit_res; ticket->t_curr_res = ticket->t_unit_res;
xlog_tic_reset_res(ticket); xlog_tic_reset_res(ticket);
@ -2678,7 +2678,7 @@ xlog_regrant_reserve_log_space(xlog_t *log,
if (ticket->t_cnt > 0) if (ticket->t_cnt > 0)
return; return;
xlog_grant_add_space(log, &log->l_grant_reserve_head, xlog_grant_add_space(log, &log->l_reserve_head.grant,
ticket->t_unit_res); ticket->t_unit_res);
trace_xfs_log_regrant_reserve_exit(log, ticket); trace_xfs_log_regrant_reserve_exit(log, ticket);
@ -2724,8 +2724,8 @@ xlog_ungrant_log_space(xlog_t *log,
bytes += ticket->t_unit_res*ticket->t_cnt; bytes += ticket->t_unit_res*ticket->t_cnt;
} }
xlog_grant_sub_space(log, &log->l_grant_reserve_head, bytes); xlog_grant_sub_space(log, &log->l_reserve_head.grant, bytes);
xlog_grant_sub_space(log, &log->l_grant_write_head, bytes); xlog_grant_sub_space(log, &log->l_write_head.grant, bytes);
trace_xfs_log_ungrant_exit(log, ticket); trace_xfs_log_ungrant_exit(log, ticket);
@ -3349,7 +3349,7 @@ xlog_verify_grant_tail(
int tail_cycle, tail_blocks; int tail_cycle, tail_blocks;
int cycle, space; int cycle, space;
xlog_crack_grant_head(&log->l_grant_write_head, &cycle, &space); xlog_crack_grant_head(&log->l_write_head.grant, &cycle, &space);
xlog_crack_atomic_lsn(&log->l_tail_lsn, &tail_cycle, &tail_blocks); xlog_crack_atomic_lsn(&log->l_tail_lsn, &tail_cycle, &tail_blocks);
if (tail_cycle != cycle) { if (tail_cycle != cycle) {
if (cycle - 1 != tail_cycle && if (cycle - 1 != tail_cycle &&
@ -3619,15 +3619,15 @@ xfs_log_force_umount(
* we don't enqueue anything once the SHUTDOWN flag is set, and this * we don't enqueue anything once the SHUTDOWN flag is set, and this
* action is protected by the grant locks. * action is protected by the grant locks.
*/ */
spin_lock(&log->l_grant_reserve_lock); spin_lock(&log->l_reserve_head.lock);
list_for_each_entry(tic, &log->l_reserveq, t_queue) list_for_each_entry(tic, &log->l_reserve_head.waiters, t_queue)
wake_up_process(tic->t_task); wake_up_process(tic->t_task);
spin_unlock(&log->l_grant_reserve_lock); spin_unlock(&log->l_reserve_head.lock);
spin_lock(&log->l_grant_write_lock); spin_lock(&log->l_write_head.lock);
list_for_each_entry(tic, &log->l_writeq, t_queue) list_for_each_entry(tic, &log->l_write_head.waiters, t_queue)
wake_up_process(tic->t_task); wake_up_process(tic->t_task);
spin_unlock(&log->l_grant_write_lock); spin_unlock(&log->l_write_head.lock);
if (!(log->l_iclog->ic_state & XLOG_STATE_IOERROR)) { if (!(log->l_iclog->ic_state & XLOG_STATE_IOERROR)) {
ASSERT(!logerror); ASSERT(!logerror);

View File

@ -469,6 +469,16 @@ struct xfs_cil {
#define XLOG_CIL_SPACE_LIMIT(log) (log->l_logsize >> 3) #define XLOG_CIL_SPACE_LIMIT(log) (log->l_logsize >> 3)
#define XLOG_CIL_HARD_SPACE_LIMIT(log) (3 * (log->l_logsize >> 4)) #define XLOG_CIL_HARD_SPACE_LIMIT(log) (3 * (log->l_logsize >> 4))
/*
* ticket grant locks, queues and accounting have their own cachlines
* as these are quite hot and can be operated on concurrently.
*/
struct xlog_grant_head {
spinlock_t lock ____cacheline_aligned_in_smp;
struct list_head waiters;
atomic64_t grant;
};
/* /*
* The reservation head lsn is not made up of a cycle number and block number. * The reservation head lsn is not made up of a cycle number and block number.
* Instead, it uses a cycle number and byte number. Logs don't expect to * Instead, it uses a cycle number and byte number. Logs don't expect to
@ -520,17 +530,8 @@ typedef struct log {
/* lsn of 1st LR with unflushed * buffers */ /* lsn of 1st LR with unflushed * buffers */
atomic64_t l_tail_lsn ____cacheline_aligned_in_smp; atomic64_t l_tail_lsn ____cacheline_aligned_in_smp;
/* struct xlog_grant_head l_reserve_head;
* ticket grant locks, queues and accounting have their own cachlines struct xlog_grant_head l_write_head;
* as these are quite hot and can be operated on concurrently.
*/
spinlock_t l_grant_reserve_lock ____cacheline_aligned_in_smp;
struct list_head l_reserveq;
atomic64_t l_grant_reserve_head;
spinlock_t l_grant_write_lock ____cacheline_aligned_in_smp;
struct list_head l_writeq;
atomic64_t l_grant_write_head;
/* The following field are used for debugging; need to hold icloglock */ /* The following field are used for debugging; need to hold icloglock */
#ifdef DEBUG #ifdef DEBUG

View File

@ -965,9 +965,9 @@ xlog_find_tail(
log->l_curr_cycle++; log->l_curr_cycle++;
atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn)); atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn));
atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn)); atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn));
xlog_assign_grant_head(&log->l_grant_reserve_head, log->l_curr_cycle, xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle,
BBTOB(log->l_curr_block)); BBTOB(log->l_curr_block));
xlog_assign_grant_head(&log->l_grant_write_head, log->l_curr_cycle, xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle,
BBTOB(log->l_curr_block)); BBTOB(log->l_curr_block));
/* /*

View File

@ -782,12 +782,12 @@ DECLARE_EVENT_CLASS(xfs_loggrant_class,
__entry->curr_res = tic->t_curr_res; __entry->curr_res = tic->t_curr_res;
__entry->unit_res = tic->t_unit_res; __entry->unit_res = tic->t_unit_res;
__entry->flags = tic->t_flags; __entry->flags = tic->t_flags;
__entry->reserveq = list_empty(&log->l_reserveq); __entry->reserveq = list_empty(&log->l_reserve_head.waiters);
__entry->writeq = list_empty(&log->l_writeq); __entry->writeq = list_empty(&log->l_write_head.waiters);
xlog_crack_grant_head(&log->l_grant_reserve_head, xlog_crack_grant_head(&log->l_reserve_head.grant,
&__entry->grant_reserve_cycle, &__entry->grant_reserve_cycle,
&__entry->grant_reserve_bytes); &__entry->grant_reserve_bytes);
xlog_crack_grant_head(&log->l_grant_write_head, xlog_crack_grant_head(&log->l_write_head.grant,
&__entry->grant_write_cycle, &__entry->grant_write_cycle,
&__entry->grant_write_bytes); &__entry->grant_write_bytes);
__entry->curr_cycle = log->l_curr_cycle; __entry->curr_cycle = log->l_curr_cycle;