diff options
| -rw-r--r-- | fs/xfs/xfs_log.c | 38 | ||||
| -rw-r--r-- | fs/xfs/xfs_log.h | 1 | ||||
| -rw-r--r-- | fs/xfs/xfs_log_cil.c | 62 | ||||
| -rw-r--r-- | fs/xfs/xfs_log_priv.h | 4 | ||||
| -rw-r--r-- | fs/xfs/xfs_sysfs.c | 1 | ||||
| -rw-r--r-- | fs/xfs/xfs_trace.c | 1 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans.c | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans_ail.c | 11 |
8 files changed, 91 insertions, 29 deletions
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 098f5c8ceb29..c738e8c79efa 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -52,11 +52,6 @@ xlog_state_get_iclog_space( int *continued_write, int *logoffsetp); STATIC void -xlog_state_switch_iclogs( - struct xlog *log, - struct xlog_in_core *iclog, - int eventual_size); -STATIC void xlog_grant_push_ail( struct xlog *log, int need_bytes); @@ -3174,7 +3169,7 @@ xfs_log_ticket_ungrant( * This routine will mark the current iclog in the ring as WANT_SYNC and move * the current iclog pointer to the next iclog in the ring. */ -STATIC void +void xlog_state_switch_iclogs( struct xlog *log, struct xlog_in_core *iclog, @@ -3346,6 +3341,20 @@ out_error: return -EIO; } +/* + * Force the log to a specific LSN. + * + * If an iclog with that lsn can be found: + * If it is in the DIRTY state, just return. + * If it is in the ACTIVE state, move the in-core log into the WANT_SYNC + * state and go to sleep or return. + * If it is in any other state, go to sleep or return. + * + * Synchronous forces are implemented with a wait queue. All callers trying + * to force a given lsn to disk must wait on the queue attached to the + * specific in-core log. When given in-core log finally completes its write + * to disk, that thread will wake up all threads waiting on the queue. + */ static int xlog_force_lsn( struct xlog *log, @@ -3431,18 +3440,13 @@ out_error: } /* - * Force the in-core log to disk for a specific LSN. + * Force the log to a specific checkpoint sequence. * - * Find in-core log with lsn. - * If it is in the DIRTY state, just return. - * If it is in the ACTIVE state, move the in-core log into the WANT_SYNC - * state and go to sleep or return. - * If it is in any other state, go to sleep or return. - * - * Synchronous forces are implemented with a wait queue. All callers trying - * to force a given lsn to disk must wait on the queue attached to the - * specific in-core log. When given in-core log finally completes its write - * to disk, that thread will wake up all threads waiting on the queue. + * First force the CIL so that all the required changes have been flushed to the + * iclogs. If the CIL force completed it will return a commit LSN that indicates + * the iclog that needs to be flushed to stable storage. If the caller needs + * a synchronous log force, we will wait on the iclog with the LSN returned by + * xlog_cil_force_seq() to be completed. */ int xfs_log_force_seq( diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index 8431a2f4bd13..dc1b77b92fc1 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -104,6 +104,7 @@ struct xlog_ticket; struct xfs_log_item; struct xfs_item_ops; struct xfs_trans; +struct xlog; int xfs_log_force(struct xfs_mount *mp, uint flags); int xfs_log_force_seq(struct xfs_mount *mp, xfs_csn_t seq, uint flags, diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index f6c4e4e8f112..59d3bd45543b 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -840,6 +840,7 @@ xlog_cil_push_work( xfs_csn_t push_seq; struct bio bio; DECLARE_COMPLETION_ONSTACK(bdev_flush); + bool push_commit_stable; new_ctx = kmem_zalloc(sizeof(*new_ctx), KM_NOFS); new_ctx->ticket = xlog_cil_ticket_alloc(log); @@ -850,6 +851,8 @@ xlog_cil_push_work( spin_lock(&cil->xc_push_lock); push_seq = cil->xc_push_seq; ASSERT(push_seq <= ctx->sequence); + push_commit_stable = cil->xc_push_commit_stable; + cil->xc_push_commit_stable = false; /* * As we are about to switch to a new, empty CIL context, we no longer @@ -1066,8 +1069,16 @@ xlog_cil_push_work( * The commit iclog must be written to stable storage to guarantee * journal IO vs metadata writeback IO is correctly ordered on stable * storage. + * + * If the push caller needs the commit to be immediately stable and the + * commit_iclog is not yet marked as XLOG_STATE_WANT_SYNC to indicate it + * will be written when released, switch it's state to WANT_SYNC right + * now. */ ctx->commit_iclog->ic_flags |= XLOG_ICL_NEED_FUA; + if (push_commit_stable && + ctx->commit_iclog->ic_state == XLOG_STATE_ACTIVE) + xlog_state_switch_iclogs(log, ctx->commit_iclog, 0); xlog_state_release_iclog(log, ctx->commit_iclog, preflush_tail_lsn); /* Not safe to reference ctx now! */ @@ -1161,13 +1172,26 @@ xlog_cil_push_background( /* * xlog_cil_push_now() is used to trigger an immediate CIL push to the sequence * number that is passed. When it returns, the work will be queued for - * @push_seq, but it won't be completed. The caller is expected to do any - * waiting for push_seq to complete if it is required. + * @push_seq, but it won't be completed. + * + * If the caller is performing a synchronous force, we will flush the workqueue + * to get previously queued work moving to minimise the wait time they will + * undergo waiting for all outstanding pushes to complete. The caller is + * expected to do the required waiting for push_seq to complete. + * + * If the caller is performing an async push, we need to ensure that the + * checkpoint is fully flushed out of the iclogs when we finish the push. If we + * don't do this, then the commit record may remain sitting in memory in an + * ACTIVE iclog. This then requires another full log force to push to disk, + * which defeats the purpose of having an async, non-blocking CIL force + * mechanism. Hence in this case we need to pass a flag to the push work to + * indicate it needs to flush the commit record itself. */ static void xlog_cil_push_now( struct xlog *log, - xfs_lsn_t push_seq) + xfs_lsn_t push_seq, + bool async) { struct xfs_cil *cil = log->l_cilp; @@ -1177,7 +1201,8 @@ xlog_cil_push_now( ASSERT(push_seq && push_seq <= cil->xc_current_sequence); /* start on any pending background push to minimise wait time on it */ - flush_work(&cil->xc_push_work); + if (!async) + flush_work(&cil->xc_push_work); /* * If the CIL is empty or we've already pushed the sequence then @@ -1190,6 +1215,7 @@ xlog_cil_push_now( } cil->xc_push_seq = push_seq; + cil->xc_push_commit_stable = async; queue_work(log->l_mp->m_cil_workqueue, &cil->xc_push_work); spin_unlock(&cil->xc_push_lock); } @@ -1275,11 +1301,26 @@ xlog_cil_commit( } /* + * Flush the CIL to stable storage but don't wait for it to complete. This + * requires the CIL push to ensure the commit record for the push hits the disk, + * but otherwise is no different to a push done from a log force. + */ +void +xlog_cil_flush( + struct xlog *log) +{ + xfs_csn_t seq = log->l_cilp->xc_current_sequence; + + trace_xfs_log_force(log->l_mp, seq, _RET_IP_); + xlog_cil_push_now(log, seq, true); +} + +/* * Conditionally push the CIL based on the sequence passed in. * - * We only need to push if we haven't already pushed the sequence - * number given. Hence the only time we will trigger a push here is - * if the push sequence is the same as the current context. + * We only need to push if we haven't already pushed the sequence number given. + * Hence the only time we will trigger a push here is if the push sequence is + * the same as the current context. * * We return the current commit lsn to allow the callers to determine if a * iclog flush is necessary following this call. @@ -1295,13 +1336,17 @@ xlog_cil_force_seq( ASSERT(sequence <= cil->xc_current_sequence); + if (!sequence) + sequence = cil->xc_current_sequence; + trace_xfs_log_force(log->l_mp, sequence, _RET_IP_); + /* * check to see if we need to force out the current context. * xlog_cil_push() handles racing pushes for the same sequence, * so no need to deal with it here. */ restart: - xlog_cil_push_now(log, sequence); + xlog_cil_push_now(log, sequence, false); /* * See if we can find a previous sequence still committing. @@ -1325,6 +1370,7 @@ restart: * It is still being pushed! Wait for the push to * complete, then start again from the beginning. */ + XFS_STATS_INC(log->l_mp, xs_log_force_sleep); xlog_wait(&cil->xc_commit_wait, &cil->xc_push_lock); goto restart; } diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 1ed299803904..014e0dc0ba97 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -277,6 +277,7 @@ struct xfs_cil { spinlock_t xc_push_lock ____cacheline_aligned_in_smp; xfs_csn_t xc_push_seq; + bool xc_push_commit_stable; struct list_head xc_committing; wait_queue_head_t xc_commit_wait; wait_queue_head_t xc_start_wait; @@ -520,6 +521,8 @@ int xlog_write(struct xlog *log, struct xfs_cil_ctx *ctx, void xfs_log_ticket_ungrant(struct xlog *log, struct xlog_ticket *ticket); void xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket); +void xlog_state_switch_iclogs(struct xlog *log, struct xlog_in_core *iclog, + int eventual_size); int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog, xfs_lsn_t log_tail_lsn); @@ -594,6 +597,7 @@ void xlog_cil_set_ctx_write_state(struct xfs_cil_ctx *ctx, /* * CIL force routines */ +void xlog_cil_flush(struct xlog *log); xfs_lsn_t xlog_cil_force_seq(struct xlog *log, xfs_csn_t sequence); static inline void diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index f1bc88f4367c..18dc5eca6c04 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -10,6 +10,7 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_sysfs.h" +#include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_mount.h" diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c index 7e01e00550ac..4c86afad1617 100644 --- a/fs/xfs/xfs_trace.c +++ b/fs/xfs/xfs_trace.c @@ -20,6 +20,7 @@ #include "xfs_bmap.h" #include "xfs_attr.h" #include "xfs_trans.h" +#include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_buf_item.h" #include "xfs_quota.h" diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index b52394b0e1f4..70868f8b5911 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -9,7 +9,6 @@ #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" -#include "xfs_log_priv.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_extent_busy.h" @@ -17,6 +16,7 @@ #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_log.h" +#include "xfs_log_priv.h" #include "xfs_trace.h" #include "xfs_error.h" #include "xfs_defer.h" diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index dbb69b4bf3ed..69aac416e2ce 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -17,6 +17,7 @@ #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_log.h" +#include "xfs_log_priv.h" #ifdef DEBUG /* @@ -429,8 +430,12 @@ xfsaild_push( /* * If we encountered pinned items or did not finish writing out all - * buffers the last time we ran, force the log first and wait for it - * before pushing again. + * buffers the last time we ran, force a background CIL push to get the + * items unpinned in the near future. We do not wait on the CIL push as + * that could stall us for seconds if there is enough background IO + * load. Stalling for that long when the tail of the log is pinned and + * needs flushing will hard stop the transaction subsystem when log + * space runs out. */ if (ailp->ail_log_flush && ailp->ail_last_pushed_lsn == 0 && (!list_empty_careful(&ailp->ail_buf_list) || @@ -438,7 +443,7 @@ xfsaild_push( ailp->ail_log_flush = 0; XFS_STATS_INC(mp, xs_push_ail_flush); - xfs_log_force(mp, XFS_LOG_SYNC); + xlog_cil_flush(mp->m_log); } spin_lock(&ailp->ail_lock); |