summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--include/sys/Makefile.am1
-rw-r--r--include/sys/arc.h12
-rw-r--r--include/sys/dbuf.h5
-rw-r--r--include/sys/dmu.h1
-rw-r--r--include/sys/dmu_tx.h23
-rw-r--r--include/sys/dsl_dir.h2
-rw-r--r--include/sys/dsl_pool.h31
-rw-r--r--include/sys/sa_impl.h4
-rw-r--r--include/sys/spa_impl.h4
-rw-r--r--include/sys/txg.h3
-rw-r--r--include/sys/txg_impl.h4
-rw-r--r--include/sys/vdev_impl.h20
-rw-r--r--include/sys/zfs_context.h14
-rw-r--r--include/sys/zfs_delay.h41
-rw-r--r--include/sys/zio.h68
-rw-r--r--man/man5/zfs-module-parameters.5597
-rw-r--r--module/zfs/arc.c166
-rw-r--r--module/zfs/dbuf.c68
-rw-r--r--module/zfs/dmu.c37
-rw-r--r--module/zfs/dmu_objset.c2
-rw-r--r--module/zfs/dmu_tx.c207
-rw-r--r--module/zfs/dmu_zfetch.c6
-rw-r--r--module/zfs/dnode.c17
-rw-r--r--module/zfs/dsl_dir.c50
-rw-r--r--module/zfs/dsl_pool.c360
-rw-r--r--module/zfs/dsl_scan.c5
-rw-r--r--module/zfs/spa.c92
-rw-r--r--module/zfs/spa_misc.c46
-rw-r--r--module/zfs/txg.c33
-rw-r--r--module/zfs/vdev.c4
-rw-r--r--module/zfs/vdev_cache.c2
-rw-r--r--module/zfs/vdev_mirror.c4
-rw-r--r--module/zfs/vdev_queue.c734
-rw-r--r--module/zfs/vdev_raidz.c2
-rw-r--r--module/zfs/zfs_fm.c2
-rw-r--r--module/zfs/zfs_vnops.c37
-rw-r--r--module/zfs/zil.c2
-rw-r--r--module/zfs/zio.c83
38 files changed, 1943 insertions, 846 deletions
diff --git a/include/sys/Makefile.am b/include/sys/Makefile.am
index 34c715101..9d7756627 100644
--- a/include/sys/Makefile.am
+++ b/include/sys/Makefile.am
@@ -62,6 +62,7 @@ COMMON_H = \
$(top_srcdir)/include/sys/zfs_context.h \
$(top_srcdir)/include/sys/zfs_ctldir.h \
$(top_srcdir)/include/sys/zfs_debug.h \
+ $(top_srcdir)/include/sys/zfs_delay.h \
$(top_srcdir)/include/sys/zfs_dir.h \
$(top_srcdir)/include/sys/zfs_fuid.h \
$(top_srcdir)/include/sys/zfs_rlock.h \
diff --git a/include/sys/arc.h b/include/sys/arc.h
index 221946da3..9d68d3b43 100644
--- a/include/sys/arc.h
+++ b/include/sys/arc.h
@@ -145,12 +145,13 @@ int arc_referenced(arc_buf_t *buf);
#endif
int arc_read(zio_t *pio, spa_t *spa, const blkptr_t *bp,
- arc_done_func_t *done, void *private, int priority, int flags,
+ arc_done_func_t *done, void *private, zio_priority_t priority, int flags,
uint32_t *arc_flags, const zbookmark_t *zb);
zio_t *arc_write(zio_t *pio, spa_t *spa, uint64_t txg,
blkptr_t *bp, arc_buf_t *buf, boolean_t l2arc, boolean_t l2arc_compress,
- const zio_prop_t *zp, arc_done_func_t *ready, arc_done_func_t *done,
- void *private, int priority, int zio_flags, const zbookmark_t *zb);
+ const zio_prop_t *zp, arc_done_func_t *ready, arc_done_func_t *physdone,
+ arc_done_func_t *done, void *private, zio_priority_t priority,
+ int zio_flags, const zbookmark_t *zb);
arc_prune_t *arc_add_prune_callback(arc_prune_func_t *func, void *private);
void arc_remove_prune_callback(arc_prune_t *p);
@@ -179,11 +180,6 @@ void l2arc_fini(void);
void l2arc_start(void);
void l2arc_stop(void);
-/* Global tunings */
-extern int zfs_write_limit_shift;
-extern unsigned long zfs_write_limit_max;
-extern kmutex_t zfs_write_limit_lock;
-
#ifndef _KERNEL
extern boolean_t arc_watch;
#endif
diff --git a/include/sys/dbuf.h b/include/sys/dbuf.h
index 3140665ab..23b919bf7 100644
--- a/include/sys/dbuf.h
+++ b/include/sys/dbuf.h
@@ -112,6 +112,9 @@ typedef struct dbuf_dirty_record {
/* pointer to parent dirty record */
struct dbuf_dirty_record *dr_parent;
+ /* How much space was changed to dsl_pool_dirty_space() for this? */
+ unsigned int dr_accounted;
+
union dirty_types {
struct dirty_indirect {
@@ -252,7 +255,7 @@ dmu_buf_impl_t *dbuf_hold_level(struct dnode *dn, int level, uint64_t blkid,
int dbuf_hold_impl(struct dnode *dn, uint8_t level, uint64_t blkid, int create,
void *tag, dmu_buf_impl_t **dbp);
-void dbuf_prefetch(struct dnode *dn, uint64_t blkid);
+void dbuf_prefetch(struct dnode *dn, uint64_t blkid, zio_priority_t prio);
void dbuf_add_ref(dmu_buf_impl_t *db, void *tag);
uint64_t dbuf_refcount(dmu_buf_impl_t *db);
diff --git a/include/sys/dmu.h b/include/sys/dmu.h
index 5485131df..1314c1eed 100644
--- a/include/sys/dmu.h
+++ b/include/sys/dmu.h
@@ -218,6 +218,7 @@ typedef enum dmu_object_type {
typedef enum txg_how {
TXG_WAIT = 1,
TXG_NOWAIT,
+ TXG_WAITED,
} txg_how_t;
void byteswap_uint64_array(void *buf, size_t size);
diff --git a/include/sys/dmu_tx.h b/include/sys/dmu_tx.h
index 48a507e34..f6a62af4b 100644
--- a/include/sys/dmu_tx.h
+++ b/include/sys/dmu_tx.h
@@ -23,7 +23,7 @@
* Use is subject to license terms.
*/
/*
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2013 by Delphix. All rights reserved.
*/
#ifndef _SYS_DMU_TX_H
@@ -60,8 +60,22 @@ struct dmu_tx {
txg_handle_t tx_txgh;
void *tx_tempreserve_cookie;
struct dmu_tx_hold *tx_needassign_txh;
- list_t tx_callbacks; /* list of dmu_tx_callback_t on this dmu_tx */
- uint8_t tx_anyobj;
+
+ /* list of dmu_tx_callback_t on this dmu_tx */
+ list_t tx_callbacks;
+
+ /* placeholder for syncing context, doesn't need specific holds */
+ boolean_t tx_anyobj;
+
+ /* has this transaction already been delayed? */
+ boolean_t tx_waited;
+
+ /* time this transaction was created */
+ hrtime_t tx_start;
+
+ /* need to wait for sufficient dirty space */
+ boolean_t tx_wait_dirty;
+
int tx_err;
#ifdef DEBUG_DMU_TX
uint64_t tx_space_towrite;
@@ -121,7 +135,8 @@ typedef struct dmu_tx_stats {
kstat_named_t dmu_tx_memory_reclaim;
kstat_named_t dmu_tx_memory_inflight;
kstat_named_t dmu_tx_dirty_throttle;
- kstat_named_t dmu_tx_write_limit;
+ kstat_named_t dmu_tx_dirty_delay;
+ kstat_named_t dmu_tx_dirty_over_max;
kstat_named_t dmu_tx_quota;
} dmu_tx_stats_t;
diff --git a/include/sys/dsl_dir.h b/include/sys/dsl_dir.h
index 2477e89af..d69d47696 100644
--- a/include/sys/dsl_dir.h
+++ b/include/sys/dsl_dir.h
@@ -20,7 +20,7 @@
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2013 by Delphix. All rights reserved.
*/
#ifndef _SYS_DSL_DIR_H
diff --git a/include/sys/dsl_pool.h b/include/sys/dsl_pool.h
index 0f9471486..d5bad8dc1 100644
--- a/include/sys/dsl_pool.h
+++ b/include/sys/dsl_pool.h
@@ -20,7 +20,7 @@
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2013 by Delphix. All rights reserved.
*/
#ifndef _SYS_DSL_POOL_H
@@ -51,6 +51,14 @@ struct dsl_pool;
struct dmu_tx;
struct dsl_scan;
+extern unsigned long zfs_dirty_data_max;
+extern unsigned long zfs_dirty_data_max_max;
+extern unsigned long zfs_dirty_data_sync;
+extern int zfs_dirty_data_max_percent;
+extern int zfs_dirty_data_max_max_percent;
+extern int zfs_delay_min_dirty_percent;
+extern unsigned long zfs_delay_scale;
+
/* These macros are for indexing into the zfs_all_blkstats_t. */
#define DMU_OT_DEFERRED DMU_OT_NONE
#define DMU_OT_OTHER DMU_OT_NUMTYPES /* place holder for DMU_OT() types */
@@ -85,9 +93,6 @@ typedef struct dsl_pool {
/* No lock needed - sync context only */
blkptr_t dp_meta_rootbp;
- hrtime_t dp_read_overhead;
- uint64_t dp_throughput; /* bytes per millisec */
- uint64_t dp_write_limit;
uint64_t dp_tmp_userrefs_obj;
bpobj_t dp_free_bpobj;
uint64_t dp_bptree_obj;
@@ -97,12 +102,19 @@ typedef struct dsl_pool {
/* Uses dp_lock */
kmutex_t dp_lock;
- uint64_t dp_space_towrite[TXG_SIZE];
- uint64_t dp_tempreserved[TXG_SIZE];
+ kcondvar_t dp_spaceavail_cv;
+ uint64_t dp_dirty_pertxg[TXG_SIZE];
+ uint64_t dp_dirty_total;
uint64_t dp_mos_used_delta;
uint64_t dp_mos_compressed_delta;
uint64_t dp_mos_uncompressed_delta;
+ /*
+ * Time of most recently scheduled (furthest in the future)
+ * wakeup for delayed transactions.
+ */
+ hrtime_t dp_last_wakeup;
+
/* Has its own locking */
tx_state_t dp_tx;
txg_list_t dp_dirty_datasets;
@@ -131,10 +143,8 @@ void dsl_pool_sync_done(dsl_pool_t *dp, uint64_t txg);
int dsl_pool_sync_context(dsl_pool_t *dp);
uint64_t dsl_pool_adjustedsize(dsl_pool_t *dp, boolean_t netfree);
uint64_t dsl_pool_adjustedfree(dsl_pool_t *dp, boolean_t netfree);
-int dsl_pool_tempreserve_space(dsl_pool_t *dp, uint64_t space, dmu_tx_t *tx);
-void dsl_pool_tempreserve_clear(dsl_pool_t *dp, int64_t space, dmu_tx_t *tx);
-void dsl_pool_memory_pressure(dsl_pool_t *dp);
-void dsl_pool_willuse_space(dsl_pool_t *dp, int64_t space, dmu_tx_t *tx);
+void dsl_pool_dirty_space(dsl_pool_t *dp, int64_t space, dmu_tx_t *tx);
+void dsl_pool_undirty_space(dsl_pool_t *dp, int64_t space, uint64_t txg);
void dsl_free(dsl_pool_t *dp, uint64_t txg, const blkptr_t *bpp);
void dsl_free_sync(zio_t *pio, dsl_pool_t *dp, uint64_t txg,
const blkptr_t *bpp);
@@ -143,6 +153,7 @@ void dsl_pool_upgrade_clones(dsl_pool_t *dp, dmu_tx_t *tx);
void dsl_pool_upgrade_dir_clones(dsl_pool_t *dp, dmu_tx_t *tx);
void dsl_pool_mos_diduse_space(dsl_pool_t *dp,
int64_t used, int64_t comp, int64_t uncomp);
+boolean_t dsl_pool_need_dirty_delay(dsl_pool_t *dp);
void dsl_pool_config_enter(dsl_pool_t *dp, void *tag);
void dsl_pool_config_exit(dsl_pool_t *dp, void *tag);
boolean_t dsl_pool_config_held(dsl_pool_t *dp);
diff --git a/include/sys/sa_impl.h b/include/sys/sa_impl.h
index 582bd76f0..fcbd8eb34 100644
--- a/include/sys/sa_impl.h
+++ b/include/sys/sa_impl.h
@@ -20,7 +20,7 @@
*/
/*
* Copyright (c) 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2013 by Delphix. All rights reserved.
*/
#ifndef _SYS_SA_IMPL_H
@@ -153,7 +153,7 @@ struct sa_os {
*
* The header has a fixed portion with a variable number
* of "lengths" depending on the number of variable sized
- * attribues which are determined by the "layout number"
+ * attributes which are determined by the "layout number"
*/
#define SA_MAGIC 0x2F505A /* ZFS SA */
diff --git a/include/sys/spa_impl.h b/include/sys/spa_impl.h
index 2e65ce845..55515c1fc 100644
--- a/include/sys/spa_impl.h
+++ b/include/sys/spa_impl.h
@@ -20,7 +20,7 @@
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2013 by Delphix. All rights reserved.
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
*/
@@ -234,7 +234,7 @@ struct spa {
uint64_t spa_feat_desc_obj; /* Feature descriptions */
taskqid_t spa_deadman_tqid; /* Task id */
uint64_t spa_deadman_calls; /* number of deadman calls */
- uint64_t spa_sync_starttime; /* starting time fo spa_sync */
+ hrtime_t spa_sync_starttime; /* starting time of spa_sync */
uint64_t spa_deadman_synctime; /* deadman expiration timer */
spa_stats_t spa_stats; /* assorted spa statistics */
diff --git a/include/sys/txg.h b/include/sys/txg.h
index 9e547819b..1bb6bac91 100644
--- a/include/sys/txg.h
+++ b/include/sys/txg.h
@@ -23,7 +23,7 @@
* Use is subject to license terms.
*/
/*
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2013 by Delphix. All rights reserved.
*/
#ifndef _SYS_TXG_H
@@ -76,6 +76,7 @@ extern void txg_register_callbacks(txg_handle_t *txghp, list_t *tx_callbacks);
extern void txg_delay(struct dsl_pool *dp, uint64_t txg, hrtime_t delta,
hrtime_t resolution);
+extern void txg_kick(struct dsl_pool *dp);
/*
* Wait until the given transaction group has finished syncing.
diff --git a/include/sys/txg_impl.h b/include/sys/txg_impl.h
index 8a0977f1f..e583d61ea 100644
--- a/include/sys/txg_impl.h
+++ b/include/sys/txg_impl.h
@@ -18,6 +18,7 @@
*
* CDDL HEADER END
*/
+
/*
* Copyright 2009 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
@@ -89,11 +90,14 @@ struct tx_cpu {
typedef struct tx_state {
tx_cpu_t *tx_cpu; /* protects access to tx_open_txg */
kmutex_t tx_sync_lock; /* protects the rest of this struct */
+
uint64_t tx_open_txg; /* currently open txg id */
uint64_t tx_quiesced_txg; /* quiesced txg waiting for sync */
uint64_t tx_syncing_txg; /* currently syncing txg id */
uint64_t tx_synced_txg; /* last synced txg id */
+ hrtime_t tx_open_time; /* start time of tx_open_txg */
+
uint64_t tx_sync_txg_waiting; /* txg we're waiting to sync */
uint64_t tx_quiesce_txg_waiting; /* txg we're waiting to open */
diff --git a/include/sys/vdev_impl.h b/include/sys/vdev_impl.h
index 45a2b5e48..4b465d295 100644
--- a/include/sys/vdev_impl.h
+++ b/include/sys/vdev_impl.h
@@ -100,12 +100,22 @@ struct vdev_cache {
kmutex_t vc_lock;
};
+typedef struct vdev_queue_class {
+ uint32_t vqc_active;
+
+ /*
+ * Sorted by offset or timestamp, depending on if the queue is
+ * LBA-ordered vs FIFO.
+ */
+ avl_tree_t vqc_queued_tree;
+} vdev_queue_class_t;
+
struct vdev_queue {
- avl_tree_t vq_deadline_tree;
- avl_tree_t vq_read_tree;
- avl_tree_t vq_write_tree;
- avl_tree_t vq_pending_tree;
- hrtime_t vq_io_complete_ts;
+ vdev_t *vq_vdev;
+ vdev_queue_class_t vq_class[ZIO_PRIORITY_NUM_QUEUEABLE];
+ avl_tree_t vq_active_tree;
+ uint64_t vq_last_offset;
+ hrtime_t vq_io_complete_ts; /* time last i/o completed */
hrtime_t vq_io_delta_ts;
list_t vq_io_list;
kmutex_t vq_lock;
diff --git a/include/sys/zfs_context.h b/include/sys/zfs_context.h
index 28a1306aa..3fd9e1be0 100644
--- a/include/sys/zfs_context.h
+++ b/include/sys/zfs_context.h
@@ -25,7 +25,7 @@
/*
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
* Copyright (c) 2012, Joyent, Inc. All rights reserved.
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2013 by Delphix. All rights reserved.
*/
#ifndef _SYS_ZFS_CONTEXT_H
@@ -61,6 +61,7 @@
#include <sys/zone.h>
#include <sys/sdt.h>
#include <sys/zfs_debug.h>
+#include <sys/zfs_delay.h>
#include <sys/fm/fs/zfs.h>
#include <sys/sunddi.h>
#include <sys/ctype.h>
@@ -224,6 +225,8 @@ typedef void (*thread_func_t)(void *);
typedef void (*thread_func_arg_t)(void *);
typedef pthread_t kt_did_t;
+#define kpreempt(x) ((void)0)
+
typedef struct kthread {
kt_did_t t_tid;
thread_func_t t_func;
@@ -708,6 +711,15 @@ void ksiddomain_rele(ksiddomain_t *);
#define ddi_log_sysevent(_a, _b, _c, _d, _e, _f, _g) \
sysevent_post_event(_c, _d, _b, "libzpool", _e, _f)
+#define zfs_sleep_until(wakeup) \
+ do { \
+ hrtime_t delta = wakeup - gethrtime(); \
+ struct timespec ts; \
+ ts.tv_sec = delta / NANOSEC; \
+ ts.tv_nsec = delta % NANOSEC; \
+ (void) nanosleep(&ts, NULL); \
+ } while (0)
+
#endif /* _KERNEL */
#endif /* _SYS_ZFS_CONTEXT_H */
diff --git a/include/sys/zfs_delay.h b/include/sys/zfs_delay.h
new file mode 100644
index 000000000..4c7663117
--- /dev/null
+++ b/include/sys/zfs_delay.h
@@ -0,0 +1,41 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+ * or http://www.opensolaris.org/os/licensing.
+ * See the License for the specific language governing permissions
+ * and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+
+#ifndef _SYS_FS_ZFS_DELAY_H
+#define _SYS_FS_ZFS_DELAY_H
+
+#include <linux/delay_compat.h>
+
+/*
+ * Generic wrapper to sleep until a given time.
+ */
+#define zfs_sleep_until(wakeup) \
+ do { \
+ hrtime_t delta = wakeup - gethrtime(); \
+ \
+ if (delta > 0) { \
+ unsigned long delta_us; \
+ delta_us = delta / (NANOSEC / MICROSEC); \
+ usleep_range(delta_us, delta_us + 100); \
+ } \
+ } while (0)
+
+#endif /* _SYS_FS_ZFS_DELAY_H */
diff --git a/include/sys/zio.h b/include/sys/zio.h
index b505ca1e6..cfb256f0f 100644
--- a/include/sys/zio.h
+++ b/include/sys/zio.h
@@ -22,7 +22,7 @@
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2013 by Delphix. All rights reserved.
* Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
*/
@@ -130,19 +130,16 @@ enum zio_compress {
#define ZIO_FAILURE_MODE_CONTINUE 1
#define ZIO_FAILURE_MODE_PANIC 2
-#define ZIO_PRIORITY_NOW (zio_priority_table[0])
-#define ZIO_PRIORITY_SYNC_READ (zio_priority_table[1])
-#define ZIO_PRIORITY_SYNC_WRITE (zio_priority_table[2])
-#define ZIO_PRIORITY_LOG_WRITE (zio_priority_table[3])
-#define ZIO_PRIORITY_CACHE_FILL (zio_priority_table[4])
-#define ZIO_PRIORITY_AGG (zio_priority_table[5])
-#define ZIO_PRIORITY_FREE (zio_priority_table[6])
-#define ZIO_PRIORITY_ASYNC_WRITE (zio_priority_table[7])
-#define ZIO_PRIORITY_ASYNC_READ (zio_priority_table[8])
-#define ZIO_PRIORITY_RESILVER (zio_priority_table[9])
-#define ZIO_PRIORITY_SCRUB (zio_priority_table[10])
-#define ZIO_PRIORITY_DDT_PREFETCH (zio_priority_table[11])
-#define ZIO_PRIORITY_TABLE_SIZE 12
+typedef enum zio_priority {
+ ZIO_PRIORITY_SYNC_READ,
+ ZIO_PRIORITY_SYNC_WRITE, /* ZIL */
+ ZIO_PRIORITY_ASYNC_READ, /* prefetch */
+ ZIO_PRIORITY_ASYNC_WRITE, /* spa_sync() */
+ ZIO_PRIORITY_SCRUB, /* asynchronous scrub/resilver reads */
+ ZIO_PRIORITY_NUM_QUEUEABLE,
+
+ ZIO_PRIORITY_NOW /* non-queued i/os (e.g. free) */
+} zio_priority_t;
#define ZIO_PIPELINE_CONTINUE 0x100
#define ZIO_PIPELINE_STOP 0x101
@@ -198,7 +195,8 @@ enum zio_flag {
ZIO_FLAG_GODFATHER = 1 << 24,
ZIO_FLAG_NOPWRITE = 1 << 25,
ZIO_FLAG_REEXECUTED = 1 << 26,
- ZIO_FLAG_FASTWRITE = 1 << 27
+ ZIO_FLAG_DELEGATED = 1 << 27,
+ ZIO_FLAG_FASTWRITE = 1 << 28
};
#define ZIO_FLAG_MUSTSUCCEED 0
@@ -238,8 +236,7 @@ enum zio_wait_type {
typedef void zio_done_func_t(zio_t *zio);
-extern uint8_t zio_priority_table[ZIO_PRIORITY_TABLE_SIZE];
-extern char *zio_type_name[ZIO_TYPES];
+extern const char *zio_type_name[ZIO_TYPES];
/*
* A bookmark is a four-tuple <objset, object, level, blkid> that uniquely
@@ -381,7 +378,7 @@ struct zio {
zio_type_t io_type;
enum zio_child io_child_type;
int io_cmd;
- uint8_t io_priority;
+ zio_priority_t io_priority;
uint8_t io_reexecute;
uint8_t io_state[ZIO_WAIT_TYPES];
uint64_t io_txg;
@@ -396,7 +393,8 @@ struct zio {
zio_transform_t *io_transform_stack;
/* Callback info */
- zio_done_func_t *io_ready;
+ zio_done_func_t *io_ready;
+ zio_done_func_t *io_physdone;
zio_done_func_t *io_done;
void *io_private;
int64_t io_prev_space_delta; /* DMU private */
@@ -414,13 +412,10 @@ struct zio {
const zio_vsd_ops_t *io_vsd_ops;
uint64_t io_offset;
- uint64_t io_deadline; /* expires at timestamp + deadline */
hrtime_t io_timestamp; /* submitted at */
hrtime_t io_delta; /* vdev queue service delta */
uint64_t io_delay; /* vdev disk service delta (ticks) */
- avl_node_t io_offset_node;
- avl_node_t io_deadline_node;
- avl_tree_t *io_vdev_tree;
+ avl_node_t io_queue_node;
/* Internal pipeline state */
enum zio_flag io_flags;
@@ -433,6 +428,7 @@ struct zio {
int io_child_error[ZIO_CHILD_TYPES];
uint64_t io_children[ZIO_CHILD_TYPES][ZIO_WAIT_TYPES];
uint64_t io_child_count;
+ uint64_t io_phys_children;
uint64_t io_parent_count;
uint64_t *io_stall;
zio_t *io_gang_leader;
@@ -458,16 +454,17 @@ extern zio_t *zio_root(spa_t *spa,
extern zio_t *zio_read(zio_t *pio, spa_t *spa, const blkptr_t *bp, void *data,
uint64_t size, zio_done_func_t *done, void *private,
- int priority, enum zio_flag flags, const zbookmark_t *zb);
+ zio_priority_t priority, enum zio_flag flags, const zbookmark_t *zb);
extern zio_t *zio_write(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp,
void *data, uint64_t size, const zio_prop_t *zp,
- zio_done_func_t *ready, zio_done_func_t *done, void *private,
- int priority, enum zio_flag flags, const zbookmark_t *zb);
+ zio_done_func_t *ready, zio_done_func_t *physdone, zio_done_func_t *done,
+ void *private,
+ zio_priority_t priority, enum zio_flag flags, const zbookmark_t *zb);
extern zio_t *zio_rewrite(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp,
void *data, uint64_t size, zio_done_func_t *done, void *private,
- int priority, enum zio_flag flags, zbookmark_t *zb);
+ zio_priority_t priority, enum zio_flag flags, zbookmark_t *zb);
extern void zio_write_override(zio_t *zio, blkptr_t *bp, int copies,
boolean_t nopwrite);
@@ -479,17 +476,17 @@ extern zio_t *zio_claim(zio_t *pio, spa_t *spa, uint64_t txg,
zio_done_func_t *done, void *private, enum zio_flag flags);
extern zio_t *zio_ioctl(zio_t *pio, spa_t *spa, vdev_t *vd, int cmd,
- zio_done_func_t *done, void *private, int priority, enum zio_flag flags);
+ zio_done_func_t *done, void *private, enum zio_flag flags);
extern zio_t *zio_read_phys(zio_t *pio, vdev_t *vd, uint64_t offset,
uint64_t size, void *data, int checksum,
- zio_done_func_t *done, void *private, int priority, enum zio_flag flags,
- boolean_t labels);
+ zio_done_func_t *done, void *private, zio_priority_t priority,
+ enum zio_flag flags, boolean_t labels);
extern zio_t *zio_write_phys(zio_t *pio, vdev_t *vd, uint64_t offset,
uint64_t size, void *data, int checksum,
- zio_done_func_t *done, void *private, int priority, enum zio_flag flags,
- boolean_t labels);
+ zio_done_func_t *done, void *private, zio_priority_t priority,
+ enum zio_flag flags, boolean_t labels);
extern zio_t *zio_free_sync(zio_t *pio, spa_t *spa, uint64_t txg,
const blkptr_t *bp, enum zio_flag flags);
@@ -520,11 +517,12 @@ extern void zio_vdev_free(void *buf);
extern void zio_resubmit_stage_async(void *);
extern zio_t *zio_vdev_child_io(zio_t *zio, blkptr_t *bp, vdev_t *vd,
- uint64_t offset, void *data, uint64_t size, int type, int priority,
- enum zio_flag flags, zio_done_func_t *done, void *private);
+ uint64_t offset, void *data, uint64_t size, int type,
+ zio_priority_t priority, enum zio_flag flags,
+ zio_done_func_t *done, void *private);
extern zio_t *zio_vdev_delegated_io(vdev_t *vd, uint64_t offset,
- void *data, uint64_t size, int type, int priority,
+ void *data, uint64_t size, int type, zio_priority_t priority,
enum zio_flag flags, zio_done_func_t *done, void *private);
extern void zio_vdev_io_bypass(zio_t *zio);
diff --git a/man/man5/zfs-module-parameters.5 b/man/man5/zfs-module-parameters.5
index a54e31f8b..00d12b087 100644
--- a/man/man5/zfs-module-parameters.5
+++ b/man/man5/zfs-module-parameters.5
@@ -159,6 +159,22 @@ Default value: \fB/etc/zfs/zpool.cache\fR.
.sp
.ne 2
.na
+\fBspa_asize_inflation\fR (int)
+.ad
+.RS 12n
+Multiplication factor used to estimate actual disk consumption from the
+size of data being written. The default value is a worst case estimate,
+but lower values may be valid for a given pool depending on its
+configuration. Pool administrators who understand the factors involved
+may wish to specify a more realistic inflation factor, particularly if
+they operate close to quota or capacity limits.
+.sp
+Default value: 24
+.RE
+
+.sp
+.ne 2
+.na
\fBzfetch_array_rd_sz\fR (ulong)
.ad
.RS 12n
@@ -335,12 +351,17 @@ Use \fB1\fR for yes (default) and \fB0\fR to disable.
.sp
.ne 2
.na
-\fBzfs_deadman_synctime\fR (ulong)
+\fBzfs_deadman_synctime_ms\fR (ulong)
.ad
.RS 12n
-Expire in units of zfs_txg_synctime_ms
+Expiration time in milliseconds. This value has two meanings. First it is
+used to determine when the spa_deadman() logic should fire. By default the
+spa_deadman() will fire if spa_sync() has not completed in 1000 seconds.
+Secondly, the value determines if an I/O is considered "hung". Any I/O that
+has not completed in zfs_deadman_synctime_ms is considered "hung" resulting
+in a zevent being logged.
.sp
-Default value: \fB1,000\fR.
+Default value: \fB1,000,000\fR.
.RE
.sp
@@ -357,6 +378,272 @@ Use \fB1\fR for yes (default) and \fB0\fR to disable.
.sp
.ne 2
.na
+\fBzfs_delay_min_dirty_percent\fR (int)
+.ad
+.RS 12n
+Start to delay each transaction once there is this amount of dirty data,
+expressed as a percentage of \fBzfs_dirty_data_max\fR.
+This value should be >= zfs_vdev_async_write_active_max_dirty_percent.
+See the section "ZFS TRANSACTION DELAY".
+.sp
+Default value: \fB60\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_delay_scale\fR (int)
+.ad
+.RS 12n
+This controls how quickly the transaction delay approaches infinity.
+Larger values cause longer delays for a given amount of dirty data.
+.sp
+For the smoothest delay, this value should be about 1 billion divided
+by the maximum number of operations per second. This will smoothly
+handle between 10x and 1/10th this number.
+.sp
+See the section "ZFS TRANSACTION DELAY".
+.sp
+Note: \fBzfs_delay_scale\fR * \fBzfs_dirty_data_max\fR must be < 2^64.
+.sp
+Default value: \fB500,000\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_dirty_data_max\fR (int)
+.ad
+.RS 12n
+Determines the dirty space limit in bytes. Once this limit is exceeded, new
+writes are halted until space frees up. This parameter takes precedence
+over \fBzfs_dirty_data_max_percent\fR.
+See the section "ZFS TRANSACTION DELAY".
+.sp
+Default value: 10 percent of all memory, capped at \fBzfs_dirty_data_max_max\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_dirty_data_max_max\fR (int)
+.ad
+.RS 12n
+Maximum allowable value of \fBzfs_dirty_data_max\fR, expressed in bytes.
+This limit is only enforced at module load time, and will be ignored if
+\fBzfs_dirty_data_max\fR is later changed. This parameter takes
+precedence over \fBzfs_dirty_data_max_max_percent\fR. See the section
+"ZFS TRANSACTION DELAY".
+.sp
+Default value: 25% of physical RAM.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_dirty_data_max_max_percent\fR (int)
+.ad
+.RS 12n
+Maximum allowable value of \fBzfs_dirty_data_max\fR, expressed as a
+percentage of physical RAM. This limit is only enforced at module load
+time, and will be ignored if \fBzfs_dirty_data_max\fR is later changed.
+The parameter \fBzfs_dirty_data_max_max\fR takes precedence over this
+one. See the section "ZFS TRANSACTION DELAY".
+.sp
+Default value: 25
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_dirty_data_max_percent\fR (int)
+.ad
+.RS 12n
+Determines the dirty space limit, expressed as a percentage of all
+memory. Once this limit is exceeded, new writes are halted until space frees
+up. The parameter \fBzfs_dirty_data_max\fR takes precedence over this
+one. See the section "ZFS TRANSACTION DELAY".
+.sp
+Default value: 10%, subject to \fBzfs_dirty_data_max_max\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_dirty_data_sync\fR (int)
+.ad
+.RS 12n
+Start syncing out a transaction group if there is at least this much dirty data.
+.sp
+Default value: \fB67,108,864\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_async_read_max_active\fR (int)
+.ad
+.RS 12n
+Maxium asynchronous read I/Os active to each device.
+See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB3\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_async_read_min_active\fR (int)
+.ad
+.RS 12n
+Minimum asynchronous read I/Os active to each device.
+See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB1\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_async_write_active_max_dirty_percent\fR (int)
+.ad
+.RS 12n
+When the pool has more than
+\fBzfs_vdev_async_write_active_max_dirty_percent\fR dirty data, use
+\fBzfs_vdev_async_write_max_active\fR to limit active async writes. If
+the dirty data is between min and max, the active I/O limit is linearly
+interpolated. See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB60\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_async_write_active_min_dirty_percent\fR (int)
+.ad
+.RS 12n
+When the pool has less than
+\fBzfs_vdev_async_write_active_min_dirty_percent\fR dirty data, use
+\fBzfs_vdev_async_write_min_active\fR to limit active async writes. If
+the dirty data is between min and max, the active I/O limit is linearly
+interpolated. See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB30\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_async_write_max_active\fR (int)
+.ad
+.RS 12n
+Maxium asynchronous write I/Os active to each device.
+See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB10\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_async_write_min_active\fR (int)
+.ad
+.RS 12n
+Minimum asynchronous write I/Os active to each device.
+See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB1\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_max_active\fR (int)
+.ad
+.RS 12n
+The maximum number of I/Os active to each device. Ideally, this will be >=
+the sum of each queue's max_active. It must be at least the sum of each
+queue's min_active. See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB1,000\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_scrub_max_active\fR (int)
+.ad
+.RS 12n
+Maxium scrub I/Os active to each device.
+See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB2\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_scrub_min_active\fR (int)
+.ad
+.RS 12n
+Minimum scrub I/Os active to each device.
+See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB1\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_sync_read_max_active\fR (int)
+.ad
+.RS 12n
+Maxium synchronous read I/Os active to each device.
+See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB10\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_sync_read_min_active\fR (int)
+.ad
+.RS 12n
+Minimum synchronous read I/Os active to each device.
+See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB10\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_sync_write_max_active\fR (int)
+.ad
+.RS 12n
+Maxium synchronous write I/Os active to each device.
+See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB10\fR.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzfs_vdev_sync_write_min_active\fR (int)
+.ad
+.RS 12n
+Minimum synchronous write I/Os active to each device.
+See the section "ZFS I/O SCHEDULER".
+.sp
+Default value: \fB10\fR.
+.RE
+
+.sp
+.ne 2
+.na
\fBzfs_disable_dup_eviction\fR (int)
.ad
.RS 12n
@@ -445,17 +732,6 @@ Use \fB1\fR for yes and \fB0\fR for no (default).
.sp
.ne 2
.na
-\fBzfs_no_write_throttle\fR (int)
-.ad
-.RS 12n
-Disable write throttling
-.sp
-Use \fB1\fR for yes and \fB0\fR for no (default).
-.RE
-
-.sp
-.ne 2
-.na
\fBzfs_nocacheflush\fR (int)
.ad
.RS 12n
@@ -655,17 +931,6 @@ Default value: \fB0\fR.
.sp
.ne 2
.na
-\fBzfs_txg_synctime_ms\fR (int)
-.ad
-.RS 12n
-Target milliseconds between txg sync
-.sp
-Default value: \fB1,000\fR.
-.RE
-
-.sp
-.ne 2
-.na
\fBzfs_txg_timeout\fR (int)
.ad
.RS 12n
@@ -719,28 +984,6 @@ Default value: \fB0\fR.
.sp
.ne 2
.na
-\fBzfs_vdev_max_pending\fR (int)
-.ad
-.RS 12n
-Max pending per-vdev I/Os
-.sp
-Default value: \fB10\fR.
-.RE
-
-.sp
-.ne 2
-.na
-\fBzfs_vdev_min_pending\fR (int)
-.ad
-.RS 12n
-Min pending per-vdev I/Os
-.sp
-Default value: \fB4\fR.
-.RE
-
-.sp
-.ne 2
-.na
\fBzfs_vdev_mirror_switch_us\fR (int)
.ad
.RS 12n
@@ -752,17 +995,6 @@ Default value: \fB10,000\fR.
.sp
.ne 2
.na
-\fBzfs_vdev_ramp_rate\fR (int)
-.ad
-.RS 12n
-Exponential I/O issue ramp-up rate
-.sp
-Default value: \fB2\fR.
-.RE
-
-.sp
-.ne 2
-.na
\fBzfs_vdev_read_gap_limit\fR (int)
.ad
.RS 12n
@@ -785,17 +1017,6 @@ Default value: \fBnoop\fR.
.sp
.ne 2
.na
-\fBzfs_vdev_time_shift\fR (int)
-.ad
-.RS 12n
-Deadline time shift for vdev I/O
-.sp
-Default value: \fB29\fR (each bucket is 0.537 seconds).
-.RE
-
-.sp
-.ne 2
-.na
\fBzfs_vdev_write_gap_limit\fR (int)
.ad
.RS 12n
@@ -807,61 +1028,6 @@ Default value: \fB4,096\fR.
.sp
.ne 2
.na
-\fBzfs_write_limit_inflated\fR (ulong)
-.ad
-.RS 12n
-Inflated txg write limit
-.sp
-Default value: \fB0\fR.
-.RE
-
-.sp
-.ne 2
-.na
-\fBzfs_write_limit_max\fR (ulong)
-.ad
-.RS 12n
-Max txg write limit
-.sp
-Default value: \fB0\fR.
-.RE
-
-.sp
-.ne 2
-.na
-\fBzfs_write_limit_min\fR (ulong)
-.ad
-.RS 12n
-Min txg write limit
-.sp
-Default value: \fB33,554,432\fR.
-.RE
-
-.sp
-.ne 2
-.na
-\fBzfs_write_limit_override\fR (ulong)
-.ad
-.RS 12n
-Override txg write limit
-.sp
-Default value: \fB0\fR.
-.RE
-
-.sp
-.ne 2
-.na
-\fBzfs_write_limit_shift\fR (int)
-.ad
-.RS 12n
-log2(fraction of memory) per txg
-.sp
-Default value: \fB3\fR.
-.RE
-
-.sp
-.ne 2
-.na
\fBzfs_zevent_cols\fR (int)
.ad
.RS 12n
@@ -1002,3 +1168,186 @@ Number of threads for zvol device
Default value: \fB32\fR.
.RE
+.SH ZFS I/O SCHEDULER
+ZFS issues I/O operations to leaf vdevs to satisfy and complete I/Os.
+The I/O scheduler determines when and in what order those operations are
+issued. The I/O scheduler divides operations into five I/O classes
+prioritized in the following order: sync read, sync write, async read,
+async write, and scrub/resilver. Each queue defines the minimum and
+maximum number of concurrent operations that may be issued to the
+device. In addition, the device has an aggregate maximum,
+\fBzfs_vdev_max_active\fR. Note that the sum of the per-queue minimums
+must not exceed the aggregate maximum. If the sum of the per-queue
+maximums exceeds the aggregate maximum, then the number of active I/Os
+may reach \fBzfs_vdev_max_active\fR, in which case no further I/Os will
+be issued regardless of whether all per-queue minimums have been met.
+.sp
+For many physical devices, throughput increases with the number of
+concurrent operations, but latency typically suffers. Further, physical
+devices typically have a limit at which more concurrent operations have no
+effect on throughput or can actually cause it to decrease.
+.sp
+The scheduler selects the next operation to issue by first looking for an
+I/O class whose minimum has not been satisfied. Once all are satisfied and
+the aggregate maximum has not been hit, the scheduler looks for classes
+whose maximum has not been satisfied. Iteration through the I/O classes is
+done in the order specified above. No further operations are issued if the
+aggregate maximum number of concurrent operations has been hit or if there
+are no operations queued for an I/O class that has not hit its maximum.
+Every time an I/O is queued or an operation completes, the I/O scheduler
+looks for new operations to issue.
+.sp
+In general, smaller max_active's will lead to lower latency of synchronous
+operations. Larger max_active's may lead to higher overall throughput,
+depending on underlying storage.
+.sp
+The ratio of the queues' max_actives determines the balance of performance
+between reads, writes, and scrubs. E.g., increasing
+\fBzfs_vdev_scrub_max_active\fR will cause the scrub or resilver to complete
+more quickly, but reads and writes to have higher latency and lower throughput.
+.sp
+All I/O classes have a fixed maximum number of outstanding operations
+except for the async write class. Asynchronous writes represent the data
+that is committed to stable storage during the syncing stage for
+transaction groups. Transaction groups enter the syncing state
+periodically so the number of queued async writes will quickly burst up
+and then bleed down to zero. Rather than servicing them as quickly as
+possible, the I/O scheduler changes the maximum number of active async
+write I/Os according to the amount of dirty data in the pool. Since
+both throughput and latency typically increase with the number of
+concurrent operations issued to physical devices, reducing the
+burstiness in the number of concurrent operations also stabilizes the
+response time of operations from other -- and in particular synchronous
+-- queues. In broad strokes, the I/O scheduler will issue more
+concurrent operations from the async write queue as there's more dirty
+data in the pool.
+.sp
+Async Writes
+.sp
+The number of concurrent operations issued for the async write I/O class
+follows a piece-wise linear function defined by a few adjustable points.
+.nf
+
+ | o---------| <-- zfs_vdev_async_write_max_active
+ ^ | /^ |
+ | | / | |
+active | / | |
+ I/O | / | |
+count | / | |
+ | / | |
+ |-------o | | <-- zfs_vdev_async_write_min_active
+ 0|_______^______|_________|
+ 0% | | 100% of zfs_dirty_data_max
+ | |
+ | `-- zfs_vdev_async_write_active_max_dirty_percent
+ `--------- zfs_vdev_async_write_active_min_dirty_percent
+
+.fi
+Until the amount of dirty data exceeds a minimum percentage of the dirty
+data allowed in the pool, the I/O scheduler will limit the number of
+concurrent operations to the minimum. As that threshold is crossed, the
+number of concurrent operations issued increases linearly to the maximum at
+the specified maximum percentage of the dirty data allowed in the pool.
+.sp
+Ideally, the amount of dirty data on a busy pool will stay in the sloped
+part of the function between \fBzfs_vdev_async_write_active_min_dirty_percent\fR
+and \fBzfs_vdev_async_write_active_max_dirty_percent\fR. If it exceeds the
+maximum percentage, this indicates that the rate of incoming data is
+greater than the rate that the backend storage can handle. In this case, we
+must further throttle incoming writes, as described in the next section.
+
+.SH ZFS TRANSACTION DELAY
+We delay transactions when we've determined that the backend storage
+isn't able to accommodate the rate of incoming writes.
+.sp
+If there is already a transaction waiting, we delay relative to when
+that transaction will finish waiting. This way the calculated delay time
+is independent of the number of threads concurrently executing
+transactions.
+.sp
+If we are the only waiter, wait relative to when the transaction
+started, rather than the current time. This credits the transaction for
+"time already served", e.g. reading indirect blocks.
+.sp
+The minimum time for a transaction to take is calculated as:
+.nf
+ min_time = zfs_delay_scale * (dirty - min) / (max - dirty)
+ min_time is then capped at 100 milliseconds.
+.fi
+.sp
+The delay has two degrees of freedom that can be adjusted via tunables. The
+percentage of dirty data at which we start to delay is defined by
+\fBzfs_delay_min_dirty_percent\fR. This should typically be at or above
+\fBzfs_vdev_async_write_active_max_dirty_percent\fR so that we only start to
+delay after writing at full speed has failed to keep up with the incoming write
+rate. The scale of the curve is defined by \fBzfs_delay_scale\fR. Roughly speaking,
+this variable determines the amount of delay at the midpoint of the curve.
+.sp
+.nf
+delay
+ 10ms +-------------------------------------------------------------*+
+ | *|
+ 9ms + *+
+ | *|
+ 8ms + *+
+ | * |
+ 7ms + * +
+ | * |
+ 6ms + * +
+ | * |
+ 5ms + * +
+ | * |
+ 4ms + * +
+ | * |
+ 3ms + * +
+ | * |
+ 2ms + (midpoint) * +
+ | | ** |
+ 1ms + v *** +
+ | zfs_delay_scale ----------> ******** |
+ 0 +-------------------------------------*********----------------+
+ 0% <- zfs_dirty_data_max -> 100%
+.fi
+.sp
+Note that since the delay is added to the outstanding time remaining on the
+most recent transaction, the delay is effectively the inverse of IOPS.
+Here the midpoint of 500us translates to 2000 IOPS. The shape of the curve
+was chosen such that small changes in the amount of accumulated dirty data
+in the first 3/4 of the curve yield relatively small differences in the
+amount of delay.
+.sp
+The effects can be easier to understand when the amount of delay is
+represented on a log scale:
+.sp
+.nf
+delay
+100ms +-------------------------------------------------------------++
+ + +
+ | |
+ + *+
+ 10ms + *+
+ + ** +
+ | (midpoint) ** |
+ + | ** +
+ 1ms + v **** +
+ + zfs_delay_scale ----------> ***** +
+ | **** |
+ + **** +
+100us + ** +
+ + * +
+ | * |
+ + * +
+ 10us + * +
+ + +
+ | |
+ + +
+ +--------------------------------------------------------------+
+ 0% <- zfs_dirty_data_max -> 100%
+.fi
+.sp
+Note here that only as the amount of dirty data approaches its limit does
+the delay start to increase rapidly. The goal of a properly tuned system
+should be to keep the amount of dirty data out of that range by first
+ensuring that the appropriate limits are set for the I/O scheduler to reach
+optimal throughput on the backend storage, and then by changing the value
+of \fBzfs_delay_scale\fR to increase the steepness of the curve.
diff --git a/module/zfs/arc.c b/module/zfs/arc.c
index 6aa7d37c7..9cdb52011 100644
--- a/module/zfs/arc.c
+++ b/module/zfs/arc.c
@@ -134,6 +134,7 @@
#include <sys/arc.h>
#include <sys/vdev.h>
#include <sys/vdev_impl.h>
+#include <sys/dsl_pool.h>
#ifdef _KERNEL
#include <sys/vmsystm.h>
#include <vm/anon.h>
@@ -162,6 +163,12 @@ typedef enum arc_reclaim_strategy {
ARC_RECLAIM_CONS /* Conservative reclaim strategy */
} arc_reclaim_strategy_t;
+/*
+ * The number of iterations through arc_evict_*() before we
+ * drop & reacquire the lock.
+ */
+int arc_evict_iterations = 100;
+
/* number of seconds before growing cache again */
int zfs_arc_grow_retry = 5;
@@ -183,6 +190,11 @@ int zfs_arc_memory_throttle_disable = 1;
/* disable duplicate buffer eviction */
int zfs_disable_dup_eviction = 0;
+/*
+ * If this percent of memory is free, don't throttle.
+ */
+int arc_lotsfree_percent = 10;
+
static int arc_dead;
/* expiration time for arc_no_grow */
@@ -519,6 +531,7 @@ typedef struct arc_write_callback arc_write_callback_t;
struct arc_write_callback {
void *awcb_private;
arc_done_func_t *awcb_ready;
+ arc_done_func_t *awcb_physdone;
arc_done_func_t *awcb_done;
arc_buf_t *awcb_buf;
};
@@ -1253,7 +1266,7 @@ arc_change_state(arc_state_t *new_state, arc_buf_hdr_t *ab, kmutex_t *hash_lock)
uint64_t from_delta, to_delta;
ASSERT(MUTEX_HELD(hash_lock));
- ASSERT(new_state != old_state);
+ ASSERT3P(new_state, !=, old_state);
ASSERT(refcnt == 0 || ab->b_datacnt > 0);
ASSERT(ab->b_datacnt == 0 || !GHOST_STATE(new_state));
ASSERT(ab->b_datacnt <= 1 || old_state != arc_anon);
@@ -1859,6 +1872,8 @@ arc_evict(arc_state_t *state, uint64_t spa, int64_t bytes, boolean_t recycle,
kmutex_t *hash_lock;
boolean_t have_lock;
void *stolen = NULL;
+ arc_buf_hdr_t marker = {{{ 0 }}};
+ int count = 0;
ASSERT(state == arc_mru || state == arc_mfu);
@@ -1882,6 +1897,33 @@ arc_evict(arc_state_t *state, uint64_t spa, int64_t bytes, boolean_t recycle,
if (recycle && ab->b_size != bytes &&
ab_prev && ab_prev->b_size == bytes)
continue;
+
+ /* ignore markers */
+ if (ab->b_spa == 0)
+ continue;
+
+ /*
+ * It may take a long time to evict all the bufs requested.
+ * To avoid blocking all arc activity, periodically drop
+ * the arcs_mtx and give other threads a chance to run
+ * before reacquiring the lock.
+ *
+ * If we are looking for a buffer to recycle, we are in
+ * the hot code path, so don't sleep.
+ */
+ if (!recycle && count++ > arc_evict_iterations) {
+ list_insert_after(list, ab, &marker);
+ mutex_exit(&evicted_state->arcs_mtx);
+ mutex_exit(&state->arcs_mtx);
+ kpreempt(KPREEMPT_SYNC);
+ mutex_enter(&state->arcs_mtx);
+ mutex_enter(&evicted_state->arcs_mtx);
+ ab_prev = list_prev(list, &marker);
+ list_remove(list, &marker);
+ count = 0;
+ continue;
+ }
+
hash_lock = HDR_LOCK(ab);
have_lock = MUTEX_HELD(hash_lock);
if (have_lock || mutex_tryenter(hash_lock)) {
@@ -1963,27 +2005,11 @@ arc_evict(arc_state_t *state, uint64_t spa, int64_t bytes, boolean_t recycle,
ARCSTAT_INCR(arcstat_mutex_miss, missed);
/*
- * We have just evicted some data into the ghost state, make
- * sure we also adjust the ghost state size if necessary.
+ * Note: we have just evicted some data into the ghost state,
+ * potentially putting the ghost size over the desired size. Rather
+ * that evicting from the ghost list in this hot code path, leave
+ * this chore to the arc_reclaim_thread().
*/
- if (arc_no_grow &&
- arc_mru_ghost->arcs_size + arc_mfu_ghost->arcs_size > arc_c) {
- int64_t mru_over = arc_anon->arcs_size + arc_mru->arcs_size +
- arc_mru_ghost->arcs_size - arc_c;
-
- if (mru_over > 0 && arc_mru_ghost->arcs_lsize[type] > 0) {
- int64_t todelete =
- MIN(arc_mru_ghost->arcs_lsize[type], mru_over);
- arc_evict_ghost(arc_mru_ghost, 0, todelete,
- ARC_BUFC_DATA);
- } else if (arc_mfu_ghost->arcs_lsize[type] > 0) {
- int64_t todelete = MIN(arc_mfu_ghost->arcs_lsize[type],
- arc_mru_ghost->arcs_size +
- arc_mfu_ghost->arcs_size - arc_c);
- arc_evict_ghost(arc_mfu_ghost, 0, todelete,
- ARC_BUFC_DATA);
- }
- }
return (stolen);
}
@@ -2002,6 +2028,7 @@ arc_evict_ghost(arc_state_t *state, uint64_t spa, int64_t bytes,
kmutex_t *hash_lock;
uint64_t bytes_deleted = 0;
uint64_t bufs_skipped = 0;
+ int count = 0;
ASSERT(GHOST_STATE(state));
bzero(&marker, sizeof(marker));
@@ -2009,6 +2036,8 @@ top:
mutex_enter(&state->arcs_mtx);
for (ab = list_tail(list); ab; ab = ab_prev) {
ab_prev = list_prev(list, ab);
+ if (ab->b_type > ARC_BUFC_NUMTYPES)
+ panic("invalid ab=%p", (void *)ab);
if (spa && ab->b_spa != spa)
continue;
@@ -2020,6 +2049,23 @@ top:
/* caller may be trying to modify this buffer, skip it */
if (MUTEX_HELD(hash_lock))
continue;
+
+ /*
+ * It may take a long time to evict all the bufs requested.
+ * To avoid blocking all arc activity, periodically drop
+ * the arcs_mtx and give other threads a chance to run
+ * before reacquiring the lock.
+ */
+ if (count++ > arc_evict_iterations) {
+ list_insert_after(list, ab, &marker);
+ mutex_exit(&state->arcs_mtx);
+ kpreempt(KPREEMPT_SYNC);
+ mutex_enter(&state->arcs_mtx);
+ ab_prev = list_prev(list, &marker);
+ list_remove(list, &marker);
+ count = 0;
+ continue;
+ }
if (mutex_tryenter(hash_lock)) {
ASSERT(!HDR_IO_IN_PROGRESS(ab));
ASSERT(ab->b_buf == NULL);
@@ -2055,8 +2101,9 @@ top:
mutex_enter(&state->arcs_mtx);
ab_prev = list_prev(list, &marker);
list_remove(list, &marker);
- } else
+ } else {
bufs_skipped += 1;
+ }
}
mutex_exit(&state->arcs_mtx);
@@ -3050,7 +3097,7 @@ arc_read_done(zio_t *zio)
*/
int
arc_read(zio_t *pio, spa_t *spa, const blkptr_t *bp, arc_done_func_t *done,
- void *private, int priority, int zio_flags, uint32_t *arc_flags,
+ void *private, zio_priority_t priority, int zio_flags, uint32_t *arc_flags,
const zbookmark_t *zb)
{
arc_buf_hdr_t *hdr;
@@ -3702,6 +3749,18 @@ arc_write_ready(zio_t *zio)
hdr->b_flags |= ARC_IO_IN_PROGRESS;
}
+/*
+ * The SPA calls this callback for each physical write that happens on behalf
+ * of a logical write. See the comment in dbuf_write_physdone() for details.
+ */
+static void
+arc_write_physdone(zio_t *zio)
+{
+ arc_write_callback_t *cb = zio->io_private;
+ if (cb->awcb_physdone != NULL)
+ cb->awcb_physdone(zio, cb->awcb_buf, cb->awcb_private);
+}
+
static void
arc_write_done(zio_t *zio)
{
@@ -3782,8 +3841,9 @@ arc_write_done(zio_t *zio)
zio_t *
arc_write(zio_t *pio, spa_t *spa, uint64_t txg,
blkptr_t *bp, arc_buf_t *buf, boolean_t l2arc, boolean_t l2arc_compress,
- const zio_prop_t *zp, arc_done_func_t *ready, arc_done_func_t *done,
- void *private, int priority, int zio_flags, const zbookmark_t *zb)
+ const zio_prop_t *zp, arc_done_func_t *ready, arc_done_func_t *physdone,
+ arc_done_func_t *done, void *private, zio_priority_t priority,
+ int zio_flags, const zbookmark_t *zb)
{
arc_buf_hdr_t *hdr = buf->b_hdr;
arc_write_callback_t *callback;
@@ -3800,39 +3860,30 @@ arc_write(zio_t *pio, spa_t *spa, uint64_t txg,
hdr->b_flags |= ARC_L2COMPRESS;
callback = kmem_zalloc(sizeof (arc_write_callback_t), KM_PUSHPAGE);
callback->awcb_ready = ready;
+ callback->awcb_physdone = physdone;
callback->awcb_done = done;
callback->awcb_private = private;
callback->awcb_buf = buf;
zio = zio_write(pio, spa, txg, bp, buf->b_data, hdr->b_size, zp,
- arc_write_ready, arc_write_done, callback, priority, zio_flags, zb);
+ arc_write_ready, arc_write_physdone, arc_write_done, callback,
+ priority, zio_flags, zb);
return (zio);
}
static int
-arc_memory_throttle(uint64_t reserve, uint64_t inflight_data, uint64_t txg)
+arc_memory_throttle(uint64_t reserve, uint64_t txg)
{
#ifdef _KERNEL
- uint64_t available_memory;
-
if (zfs_arc_memory_throttle_disable)
return (0);
- /* Easily reclaimable memory (free + inactive + arc-evictable) */
- available_memory = ptob(spl_kmem_availrmem()) + arc_evictable_memory();
-
- if (available_memory <= zfs_write_limit_max) {
+ if (freemem <= physmem * arc_lotsfree_percent / 100) {
ARCSTAT_INCR(arcstat_memory_throttle_count, 1);
DMU_TX_STAT_BUMP(dmu_tx_memory_reclaim);
return (SET_ERROR(EAGAIN));
}
-
- if (inflight_data > available_memory / 4) {
- ARCSTAT_INCR(arcstat_memory_throttle_count, 1);
- DMU_TX_STAT_BUMP(dmu_tx_memory_inflight);
- return (ERESTART);
- }
#endif
return (0);
}
@@ -3850,15 +3901,6 @@ arc_tempreserve_space(uint64_t reserve, uint64_t txg)
int error;
uint64_t anon_size;
-#ifdef ZFS_DEBUG
- /*
- * Once in a while, fail for no reason. Everything should cope.
- */
- if (spa_get_random(10000) == 0) {
- dprintf("forcing random failure\n");
- return (ERESTART);
- }
-#endif
if (reserve > arc_c/4 && !arc_no_grow)
arc_c = MIN(arc_c_max, reserve * 4);
if (reserve > arc_c) {
@@ -3878,7 +3920,8 @@ arc_tempreserve_space(uint64_t reserve, uint64_t txg)
* in order to compress/encrypt/etc the data. We therefore need to
* make sure that there is sufficient available memory for this.
*/
- if ((error = arc_memory_throttle(reserve, anon_size, txg)))
+ error = arc_memory_throttle(reserve, txg);
+ if (error != 0)
return (error);
/*
@@ -4075,11 +4118,24 @@ arc_init(void)
arc_dead = FALSE;
arc_warm = B_FALSE;
- if (zfs_write_limit_max == 0)
- zfs_write_limit_max = ptob(physmem) >> zfs_write_limit_shift;
- else
- zfs_write_limit_shift = 0;
- mutex_init(&zfs_write_limit_lock, NULL, MUTEX_DEFAULT, NULL);
+ /*
+ * Calculate maximum amount of dirty data per pool.
+ *
+ * If it has been set by a module parameter, take that.
+ * Otherwise, use a percentage of physical memory defined by
+ * zfs_dirty_data_max_percent (default 10%) with a cap at
+ * zfs_dirty_data_max_max (default 25% of physical memory).
+ */
+ if (zfs_dirty_data_max_max == 0)
+ zfs_dirty_data_max_max = physmem * PAGESIZE *
+ zfs_dirty_data_max_max_percent / 100;
+
+ if (zfs_dirty_data_max == 0) {
+ zfs_dirty_data_max = physmem * PAGESIZE *
+ zfs_dirty_data_max_percent / 100;
+ zfs_dirty_data_max = MIN(zfs_dirty_data_max,
+ zfs_dirty_data_max_max);
+ }
}
void
@@ -4137,8 +4193,6 @@ arc_fini(void)
mutex_destroy(&arc_mfu_ghost->arcs_mtx);
mutex_destroy(&arc_l2c_only->arcs_mtx);
- mutex_destroy(&zfs_write_limit_lock);
-
buf_fini();
ASSERT(arc_loaned_bytes == 0);
diff --git a/module/zfs/dbuf.c b/module/zfs/dbuf.c
index 9ad3d1d30..01352a91c 100644
--- a/module/zfs/dbuf.c
+++ b/module/zfs/dbuf.c
@@ -891,7 +891,7 @@ dbuf_free_range(dnode_t *dn, uint64_t start, uint64_t end, dmu_tx_t *tx)
atomic_inc_64(&zfs_free_range_recv_miss);
}
- for (db = list_head(&dn->dn_dbufs); db; db = db_next) {
+ for (db = list_head(&dn->dn_dbufs); db != NULL; db = db_next) {
db_next = list_next(&dn->dn_dbufs, db);
ASSERT(db->db_blkid != DMU_BONUS_BLKID);
@@ -1238,6 +1238,8 @@ dbuf_dirty(dmu_buf_impl_t *db, dmu_tx_t *tx)
sizeof (dbuf_dirty_record_t),
offsetof(dbuf_dirty_record_t, dr_dirty_node));
}
+ if (db->db_blkid != DMU_BONUS_BLKID && os->os_dsl_dataset != NULL)
+ dr->dr_accounted = db->db.db_size;
dr->dr_dbuf = db;
dr->dr_txg = tx->tx_txg;
dr->dr_next = *drp;
@@ -1321,7 +1323,10 @@ dbuf_dirty(dmu_buf_impl_t *db, dmu_tx_t *tx)
dbuf_rele(parent, FTAG);
mutex_enter(&db->db_mtx);
- /* possible race with dbuf_undirty() */
+ /*
+ * Since we've dropped the mutex, it's possible that
+ * dbuf_undirty() might have changed this out from under us.
+ */
if (db->db_last_dirty == dr ||
dn->dn_object == DMU_META_DNODE_OBJECT) {
mutex_enter(&di->dt.di.dr_mtx);
@@ -1391,7 +1396,11 @@ dbuf_undirty(dmu_buf_impl_t *db, dmu_tx_t *tx)
ASSERT(db->db.db_size != 0);
- /* XXX would be nice to fix up dn_towrite_space[] */
+ /*
+ * Any space we accounted for in dp_dirty_* will be cleaned up by
+ * dsl_pool_sync(). This is relatively rare so the discrepancy
+ * is not a big deal.
+ */
*drp = dr->dr_next;
@@ -1571,7 +1580,7 @@ dbuf_assign_arcbuf(dmu_buf_impl_t *db, arc_buf_t *buf, dmu_tx_t *tx)
/*
* "Clear" the contents of this dbuf. This will mark the dbuf
- * EVICTING and clear *most* of its references. Unfortunetely,
+ * EVICTING and clear *most* of its references. Unfortunately,
* when we are not holding the dn_dbufs_mtx, we can't clear the
* entry in the dn_dbufs list. We have to wait until dbuf_destroy()
* in this case. For callers from the DMU we will usually see:
@@ -1768,7 +1777,7 @@ dbuf_create(dnode_t *dn, uint8_t level, uint64_t blkid,
db->db.db_offset = 0;
} else {
int blocksize =
- db->db_level ? 1<<dn->dn_indblkshift : dn->dn_datablksz;
+ db->db_level ? 1 << dn->dn_indblkshift : dn->dn_datablksz;
db->db.db_size = blocksize;
db->db.db_offset = db->db_blkid * blocksize;
}
@@ -1877,7 +1886,7 @@ dbuf_destroy(dmu_buf_impl_t *db)
}
void
-dbuf_prefetch(dnode_t *dn, uint64_t blkid)
+dbuf_prefetch(dnode_t *dn, uint64_t blkid, zio_priority_t prio)
{
dmu_buf_impl_t *db = NULL;
blkptr_t *bp = NULL;
@@ -1901,8 +1910,6 @@ dbuf_prefetch(dnode_t *dn, uint64_t blkid)
if (dbuf_findbp(dn, 0, blkid, TRUE, &db, &bp, NULL) == 0) {
if (bp && !BP_IS_HOLE(bp)) {
- int priority = dn->dn_type == DMU_OT_DDT_ZAP ?
- ZIO_PRIORITY_DDT_PREFETCH : ZIO_PRIORITY_ASYNC_READ;
dsl_dataset_t *ds = dn->dn_objset->os_dsl_dataset;
uint32_t aflags = ARC_NOWAIT | ARC_PREFETCH;
zbookmark_t zb;
@@ -1911,7 +1918,7 @@ dbuf_prefetch(dnode_t *dn, uint64_t blkid)
dn->dn_object, 0, blkid);
(void) arc_read(NULL, dn->dn_objset->os_spa,
- bp, NULL, NULL, priority,
+ bp, NULL, NULL, prio,
ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE,
&aflags, &zb);
}
@@ -2647,6 +2654,38 @@ dbuf_write_ready(zio_t *zio, arc_buf_t *buf, void *vdb)
mutex_exit(&db->db_mtx);
}
+/*
+ * The SPA will call this callback several times for each zio - once
+ * for every physical child i/o (zio->io_phys_children times). This
+ * allows the DMU to monitor the progress of each logical i/o. For example,
+ * there may be 2 copies of an indirect block, or many fragments of a RAID-Z
+ * block. There may be a long delay before all copies/fragments are completed,
+ * so this callback allows us to retire dirty space gradually, as the physical
+ * i/os complete.
+ */
+/* ARGSUSED */
+static void
+dbuf_write_physdone(zio_t *zio, arc_buf_t *buf, void *arg)
+{
+ dmu_buf_impl_t *db = arg;
+ objset_t *os = db->db_objset;
+ dsl_pool_t *dp = dmu_objset_pool(os);
+ dbuf_dirty_record_t *dr;
+ int delta = 0;
+
+ dr = db->db_data_pending;
+ ASSERT3U(dr->dr_txg, ==, zio->io_txg);
+
+ /*
+ * The callback will be called io_phys_children times. Retire one
+ * portion of our dirty space each time we are called. Any rounding
+ * error will be cleaned up by dsl_pool_sync()'s call to
+ * dsl_pool_undirty_space().
+ */
+ delta = dr->dr_accounted / zio->io_phys_children;
+ dsl_pool_undirty_space(dp, delta, zio->io_txg);
+}
+
/* ARGSUSED */
static void
dbuf_write_done(zio_t *zio, arc_buf_t *buf, void *vdb)
@@ -2741,6 +2780,7 @@ dbuf_write_done(zio_t *zio, arc_buf_t *buf, void *vdb)
ASSERT(db->db_dirtycnt > 0);
db->db_dirtycnt -= 1;
db->db_data_pending = NULL;
+
dbuf_rele_and_unlock(db, (void *)(uintptr_t)txg);
}
@@ -2859,8 +2899,8 @@ dbuf_write(dbuf_dirty_record_t *dr, arc_buf_t *data, dmu_tx_t *tx)
ASSERT(db->db_state != DB_NOFILL);
dr->dr_zio = zio_write(zio, os->os_spa, txg,
db->db_blkptr, data->b_data, arc_buf_size(data), &zp,
- dbuf_write_override_ready, dbuf_write_override_done, dr,
- ZIO_PRIORITY_ASYNC_WRITE, ZIO_FLAG_MUSTSUCCEED, &zb);
+ dbuf_write_override_ready, NULL, dbuf_write_override_done,
+ dr, ZIO_PRIORITY_ASYNC_WRITE, ZIO_FLAG_MUSTSUCCEED, &zb);
mutex_enter(&db->db_mtx);
dr->dt.dl.dr_override_state = DR_NOT_OVERRIDDEN;
zio_write_override(dr->dr_zio, &dr->dt.dl.dr_overridden_by,
@@ -2870,7 +2910,7 @@ dbuf_write(dbuf_dirty_record_t *dr, arc_buf_t *data, dmu_tx_t *tx)
ASSERT(zp.zp_checksum == ZIO_CHECKSUM_OFF);
dr->dr_zio = zio_write(zio, os->os_spa, txg,
db->db_blkptr, NULL, db->db.db_size, &zp,
- dbuf_write_nofill_ready, dbuf_write_nofill_done, db,
+ dbuf_write_nofill_ready, NULL, dbuf_write_nofill_done, db,
ZIO_PRIORITY_ASYNC_WRITE,
ZIO_FLAG_MUSTSUCCEED | ZIO_FLAG_NODATA, &zb);
} else {
@@ -2878,8 +2918,8 @@ dbuf_write(dbuf_dirty_record_t *dr, arc_buf_t *data, dmu_tx_t *tx)
dr->dr_zio = arc_write(zio, os->os_spa, txg,
db->db_blkptr, data, DBUF_IS_L2CACHEABLE(db),
DBUF_IS_L2COMPRESSIBLE(db), &zp, dbuf_write_ready,
- dbuf_write_done, db, ZIO_PRIORITY_ASYNC_WRITE,
- ZIO_FLAG_MUSTSUCCEED, &zb);
+ dbuf_write_physdone, dbuf_write_done, db,
+ ZIO_PRIORITY_ASYNC_WRITE, ZIO_FLAG_MUSTSUCCEED, &zb);
}
}
diff --git a/module/zfs/dmu.c b/module/zfs/dmu.c
index 72fce35c5..ade13b9f0 100644
--- a/module/zfs/dmu.c
+++ b/module/zfs/dmu.c
@@ -370,13 +370,11 @@ static int
dmu_buf_hold_array_by_dnode(dnode_t *dn, uint64_t offset, uint64_t length,
int read, void *tag, int *numbufsp, dmu_buf_t ***dbpp, uint32_t flags)
{
- dsl_pool_t *dp = NULL;
dmu_buf_t **dbp;
uint64_t blkid, nblks, i;
uint32_t dbuf_flags;
int err;
zio_t *zio;
- hrtime_t start = 0;
ASSERT(length <= DMU_MAX_ACCESS);
@@ -404,9 +402,6 @@ dmu_buf_hold_array_by_dnode(dnode_t *dn, uint64_t offset, uint64_t length,
}
dbp = kmem_zalloc(sizeof (dmu_buf_t *) * nblks, KM_PUSHPAGE | KM_NODEBUG);
- if (dn->dn_objset->os_dsl_dataset)
- dp = dn->dn_objset->os_dsl_dataset->ds_dir->dd_pool;
- start = gethrtime();
zio = zio_root(dn->dn_objset->os_spa, NULL, NULL, ZIO_FLAG_CANFAIL);
blkid = dbuf_whichblock(dn, offset);
for (i = 0; i < nblks; i++) {
@@ -427,9 +422,6 @@ dmu_buf_hold_array_by_dnode(dnode_t *dn, uint64_t offset, uint64_t length,
/* wait for async i/o */
err = zio_wait(zio);
- /* track read overhead when we are in sync context */
- if (dp && dsl_pool_sync_context(dp))
- dp->dp_read_overhead += gethrtime() - start;
if (err) {
dmu_buf_rele_array(dbp, nblks, tag);
return (err);
@@ -511,12 +503,22 @@ dmu_buf_rele_array(dmu_buf_t **dbp_fake, int numbufs, void *tag)
kmem_free(dbp, sizeof (dmu_buf_t *) * numbufs);
}
+/*
+ * Issue prefetch i/os for the given blocks.
+ *
+ * Note: The assumption is that we *know* these blocks will be needed
+ * almost immediately. Therefore, the prefetch i/os will be issued at
+ * ZIO_PRIORITY_SYNC_READ
+ *
+ * Note: indirect blocks and other metadata will be read synchronously,
+ * causing this function to block if they are not already cached.
+ */
void
dmu_prefetch(objset_t *os, uint64_t object, uint64_t offset, uint64_t len)
{
dnode_t *dn;
uint64_t blkid;
- int nblks, i, err;
+ int nblks, err;
if (zfs_prefetch_disable)
return;
@@ -529,7 +531,7 @@ dmu_prefetch(objset_t *os, uint64_t object, uint64_t offset, uint64_t len)
rw_enter(&dn->dn_struct_rwlock, RW_READER);
blkid = dbuf_whichblock(dn, object * sizeof (dnode_phys_t));
- dbuf_prefetch(dn, blkid);
+ dbuf_prefetch(dn, blkid, ZIO_PRIORITY_SYNC_READ);
rw_exit(&dn->dn_struct_rwlock);
return;
}
@@ -546,16 +548,18 @@ dmu_prefetch(objset_t *os, uint64_t object, uint64_t offset, uint64_t len)
rw_enter(&dn->dn_struct_rwlock, RW_READER);
if (dn->dn_datablkshift) {
int blkshift = dn->dn_datablkshift;
- nblks = (P2ROUNDUP(offset+len, 1<<blkshift) -
- P2ALIGN(offset, 1<<blkshift)) >> blkshift;
+ nblks = (P2ROUNDUP(offset + len, 1 << blkshift) -
+ P2ALIGN(offset, 1 << blkshift)) >> blkshift;
} else {
nblks = (offset < dn->dn_datablksz);
}
if (nblks != 0) {
+ int i;
+
blkid = dbuf_whichblock(dn, offset);
for (i = 0; i < nblks; i++)
- dbuf_prefetch(dn, blkid+i);
+ dbuf_prefetch(dn, blkid + i, ZIO_PRIORITY_SYNC_READ);
}
rw_exit(&dn->dn_struct_rwlock);
@@ -1559,7 +1563,7 @@ dmu_sync_late_arrival(zio_t *pio, objset_t *os, dmu_sync_cb_t *done, zgd_t *zgd,
zio_nowait(zio_write(pio, os->os_spa, dmu_tx_get_txg(tx), zgd->zgd_bp,
zgd->zgd_db->db_data, zgd->zgd_db->db_size, zp,
- dmu_sync_late_arrival_ready, dmu_sync_late_arrival_done, dsa,
+ dmu_sync_late_arrival_ready, NULL, dmu_sync_late_arrival_done, dsa,
ZIO_PRIORITY_SYNC_WRITE, ZIO_FLAG_CANFAIL | ZIO_FLAG_FASTWRITE, zb));
return (0);
@@ -1699,8 +1703,9 @@ dmu_sync(zio_t *pio, uint64_t txg, dmu_sync_cb_t *done, zgd_t *zgd)
zio_nowait(arc_write(pio, os->os_spa, txg,
bp, dr->dt.dl.dr_data, DBUF_IS_L2CACHEABLE(db),
- DBUF_IS_L2COMPRESSIBLE(db), &zp, dmu_sync_ready, dmu_sync_done,
- dsa, ZIO_PRIORITY_SYNC_WRITE, ZIO_FLAG_CANFAIL | ZIO_FLAG_FASTWRITE, &zb));
+ DBUF_IS_L2COMPRESSIBLE(db), &zp, dmu_sync_ready,
+ NULL, dmu_sync_done, dsa, ZIO_PRIORITY_SYNC_WRITE,
+ ZIO_FLAG_CANFAIL, &zb));
return (0);
}
diff --git a/module/zfs/dmu_objset.c b/module/zfs/dmu_objset.c
index 6a3b5f05e..07e00c307 100644
--- a/module/zfs/dmu_objset.c
+++ b/module/zfs/dmu_objset.c
@@ -1032,7 +1032,7 @@ dmu_objset_sync(objset_t *os, zio_t *pio, dmu_tx_t *tx)
zio = arc_write(pio, os->os_spa, tx->tx_txg,
os->os_rootbp, os->os_phys_buf, DMU_OS_IS_L2CACHEABLE(os),
DMU_OS_IS_L2COMPRESSIBLE(os), &zp, dmu_objset_write_ready,
- dmu_objset_write_done, os, ZIO_PRIORITY_ASYNC_WRITE,
+ NULL, dmu_objset_write_done, os, ZIO_PRIORITY_ASYNC_WRITE,
ZIO_FLAG_MUSTSUCCEED, &zb);
/*
diff --git a/module/zfs/dmu_tx.c b/module/zfs/dmu_tx.c
index ece6b14b3..47cb86b08 100644
--- a/module/zfs/dmu_tx.c
+++ b/module/zfs/dmu_tx.c
@@ -53,7 +53,8 @@ dmu_tx_stats_t dmu_tx_stats = {
{ "dmu_tx_memory_reclaim", KSTAT_DATA_UINT64 },
{ "dmu_tx_memory_inflight", KSTAT_DATA_UINT64 },
{ "dmu_tx_dirty_throttle", KSTAT_DATA_UINT64 },
- { "dmu_tx_write_limit", KSTAT_DATA_UINT64 },
+ { "dmu_tx_dirty_delay", KSTAT_DATA_UINT64 },
+ { "dmu_tx_dirty_over_max", KSTAT_DATA_UINT64 },
{ "dmu_tx_quota", KSTAT_DATA_UINT64 },
};
@@ -70,6 +71,7 @@ dmu_tx_create_dd(dsl_dir_t *dd)
offsetof(dmu_tx_hold_t, txh_node));
list_create(&tx->tx_callbacks, sizeof (dmu_tx_callback_t),
offsetof(dmu_tx_callback_t, dcb_node));
+ tx->tx_start = gethrtime();
#ifdef DEBUG_DMU_TX
refcount_create(&tx->tx_space_written);
refcount_create(&tx->tx_space_freed);
@@ -614,6 +616,7 @@ dmu_tx_hold_free(dmu_tx_t *tx, uint64_t object, uint64_t off, uint64_t len)
if (txh == NULL)
return;
dn = txh->txh_dnode;
+ dmu_tx_count_dnode(txh);
if (off >= (dn->dn_maxblkid+1) * dn->dn_datablksz)
return;
@@ -931,6 +934,142 @@ dmu_tx_dirty_buf(dmu_tx_t *tx, dmu_buf_impl_t *db)
}
#endif
+/*
+ * If we can't do 10 iops, something is wrong. Let us go ahead
+ * and hit zfs_dirty_data_max.
+ */
+hrtime_t zfs_delay_max_ns = 100 * MICROSEC; /* 100 milliseconds */
+int zfs_delay_resolution_ns = 100 * 1000; /* 100 microseconds */
+
+/*
+ * We delay transactions when we've determined that the backend storage
+ * isn't able to accommodate the rate of incoming writes.
+ *
+ * If there is already a transaction waiting, we delay relative to when
+ * that transaction finishes waiting. This way the calculated min_time
+ * is independent of the number of threads concurrently executing
+ * transactions.
+ *
+ * If we are the only waiter, wait relative to when the transaction
+ * started, rather than the current time. This credits the transaction for
+ * "time already served", e.g. reading indirect blocks.
+ *
+ * The minimum time for a transaction to take is calculated as:
+ * min_time = scale * (dirty - min) / (max - dirty)
+ * min_time is then capped at zfs_delay_max_ns.
+ *
+ * The delay has two degrees of freedom that can be adjusted via tunables.
+ * The percentage of dirty data at which we start to delay is defined by
+ * zfs_delay_min_dirty_percent. This should typically be at or above
+ * zfs_vdev_async_write_active_max_dirty_percent so that we only start to
+ * delay after writing at full speed has failed to keep up with the incoming
+ * write rate. The scale of the curve is defined by zfs_delay_scale. Roughly
+ * speaking, this variable determines the amount of delay at the midpoint of
+ * the curve.
+ *
+ * delay
+ * 10ms +-------------------------------------------------------------*+
+ * | *|
+ * 9ms + *+
+ * | *|
+ * 8ms + *+
+ * | * |
+ * 7ms + * +
+ * | * |
+ * 6ms + * +
+ * | * |
+ * 5ms + * +
+ * | * |
+ * 4ms + * +
+ * | * |
+ * 3ms + * +
+ * | * |
+ * 2ms + (midpoint) * +
+ * | | ** |
+ * 1ms + v *** +
+ * | zfs_delay_scale ----------> ******** |
+ * 0 +-------------------------------------*********----------------+
+ * 0% <- zfs_dirty_data_max -> 100%
+ *
+ * Note that since the delay is added to the outstanding time remaining on the
+ * most recent transaction, the delay is effectively the inverse of IOPS.
+ * Here the midpoint of 500us translates to 2000 IOPS. The shape of the curve
+ * was chosen such that small changes in the amount of accumulated dirty data
+ * in the first 3/4 of the curve yield relatively small differences in the
+ * amount of delay.
+ *
+ * The effects can be easier to understand when the amount of delay is
+ * represented on a log scale:
+ *
+ * delay
+ * 100ms +-------------------------------------------------------------++
+ * + +
+ * | |
+ * + *+
+ * 10ms + *+
+ * + ** +
+ * | (midpoint) ** |
+ * + | ** +
+ * 1ms + v **** +
+ * + zfs_delay_scale ----------> ***** +
+ * | **** |
+ * + **** +
+ * 100us + ** +
+ * + * +
+ * | * |
+ * + * +
+ * 10us + * +
+ * + +
+ * | |
+ * + +
+ * +--------------------------------------------------------------+
+ * 0% <- zfs_dirty_data_max -> 100%
+ *
+ * Note here that only as the amount of dirty data approaches its limit does
+ * the delay start to increase rapidly. The goal of a properly tuned system
+ * should be to keep the amount of dirty data out of that range by first
+ * ensuring that the appropriate limits are set for the I/O scheduler to reach
+ * optimal throughput on the backend storage, and then by changing the value
+ * of zfs_delay_scale to increase the steepness of the curve.
+ */
+static void
+dmu_tx_delay(dmu_tx_t *tx, uint64_t dirty)
+{
+ dsl_pool_t *dp = tx->tx_pool;
+ uint64_t delay_min_bytes =
+ zfs_dirty_data_max * zfs_delay_min_dirty_percent / 100;
+ hrtime_t wakeup, min_tx_time, now;
+
+ if (dirty <= delay_min_bytes)
+ return;
+
+ /*
+ * The caller has already waited until we are under the max.
+ * We make them pass us the amount of dirty data so we don't
+ * have to handle the case of it being >= the max, which could
+ * cause a divide-by-zero if it's == the max.
+ */
+ ASSERT3U(dirty, <, zfs_dirty_data_max);
+
+ now = gethrtime();
+ min_tx_time = zfs_delay_scale *
+ (dirty - delay_min_bytes) / (zfs_dirty_data_max - dirty);
+ min_tx_time = MIN(min_tx_time, zfs_delay_max_ns);
+ if (now > tx->tx_start + min_tx_time)
+ return;
+
+ DTRACE_PROBE3(delay__mintime, dmu_tx_t *, tx, uint64_t, dirty,
+ uint64_t, min_tx_time);
+
+ mutex_enter(&dp->dp_lock);
+ wakeup = MAX(tx->tx_start + min_tx_time,
+ dp->dp_last_wakeup + min_tx_time);
+ dp->dp_last_wakeup = wakeup;
+ mutex_exit(&dp->dp_lock);
+
+ zfs_sleep_until(wakeup);
+}
+
static int
dmu_tx_try_assign(dmu_tx_t *tx, txg_how_t txg_how)
{
@@ -965,6 +1104,13 @@ dmu_tx_try_assign(dmu_tx_t *tx, txg_how_t txg_how)
return (SET_ERROR(ERESTART));
}
+ if (!tx->tx_waited &&
+ dsl_pool_need_dirty_delay(tx->tx_pool)) {
+ tx->tx_wait_dirty = B_TRUE;
+ DMU_TX_STAT_BUMP(dmu_tx_dirty_delay);
+ return (ERESTART);
+ }
+
tx->tx_txg = txg_hold_open(tx->tx_pool, &tx->tx_txgh);
tx->tx_needassign_txh = NULL;
@@ -1092,6 +1238,10 @@ dmu_tx_unassign(dmu_tx_t *tx)
* blocking, returns immediately with ERESTART. This should be used
* whenever you're holding locks. On an ERESTART error, the caller
* should drop locks, do a dmu_tx_wait(tx), and try again.
+ *
+ * (3) TXG_WAITED. Like TXG_NOWAIT, but indicates that dmu_tx_wait()
+ * has already been called on behalf of this operation (though
+ * most likely on a different tx).
*/
int
dmu_tx_assign(dmu_tx_t *tx, txg_how_t txg_how)
@@ -1100,11 +1250,15 @@ dmu_tx_assign(dmu_tx_t *tx, txg_how_t txg_how)
int err;
ASSERT(tx->tx_txg == 0);
- ASSERT(txg_how == TXG_WAIT || txg_how == TXG_NOWAIT);
+ ASSERT(txg_how == TXG_WAIT || txg_how == TXG_NOWAIT ||
+ txg_how == TXG_WAITED);
ASSERT(!dsl_pool_sync_context(tx->tx_pool));
before = gethrtime();
+ if (txg_how == TXG_WAITED)
+ tx->tx_waited = B_TRUE;
+
/* If we might wait, we must not hold the config lock. */
ASSERT(txg_how != TXG_WAIT || !dsl_pool_config_held(tx->tx_pool));
@@ -1128,17 +1282,47 @@ void
dmu_tx_wait(dmu_tx_t *tx)
{
spa_t *spa = tx->tx_pool->dp_spa;
+ dsl_pool_t *dp = tx->tx_pool;
ASSERT(tx->tx_txg == 0);
ASSERT(!dsl_pool_config_held(tx->tx_pool));
- /*
- * It's possible that the pool has become active after this thread
- * has tried to obtain a tx. If that's the case then his
- * tx_lasttried_txg would not have been assigned.
- */
- if (spa_suspended(spa) || tx->tx_lasttried_txg == 0) {
- txg_wait_synced(tx->tx_pool, spa_last_synced_txg(spa) + 1);
+ if (tx->tx_wait_dirty) {
+ uint64_t dirty;
+
+ /*
+ * dmu_tx_try_assign() has determined that we need to wait
+ * because we've consumed much or all of the dirty buffer
+ * space.
+ */
+ mutex_enter(&dp->dp_lock);
+ if (dp->dp_dirty_total >= zfs_dirty_data_max)
+ DMU_TX_STAT_BUMP(dmu_tx_dirty_over_max);
+ while (dp->dp_dirty_total >= zfs_dirty_data_max)
+ cv_wait(&dp->dp_spaceavail_cv, &dp->dp_lock);
+ dirty = dp->dp_dirty_total;
+ mutex_exit(&dp->dp_lock);
+
+ dmu_tx_delay(tx, dirty);
+
+ tx->tx_wait_dirty = B_FALSE;
+
+ /*
+ * Note: setting tx_waited only has effect if the caller
+ * used TX_WAIT. Otherwise they are going to destroy
+ * this tx and try again. The common case, zfs_write(),
+ * uses TX_WAIT.
+ */
+ tx->tx_waited = B_TRUE;
+ } else if (spa_suspended(spa) || tx->tx_lasttried_txg == 0) {
+ /*
+ * If the pool is suspended we need to wait until it
+ * is resumed. Note that it's possible that the pool
+ * has become active after this thread has tried to
+ * obtain a tx. If that's the case then tx_lasttried_txg
+ * would not have been set.
+ */
+ txg_wait_synced(dp, spa_last_synced_txg(spa) + 1);
} else if (tx->tx_needassign_txh) {
dnode_t *dn = tx->tx_needassign_txh->txh_dnode;
@@ -1148,6 +1332,10 @@ dmu_tx_wait(dmu_tx_t *tx)
mutex_exit(&dn->dn_mtx);
tx->tx_needassign_txh = NULL;
} else {
+ /*
+ * A dnode is assigned to the quiescing txg. Wait for its
+ * transaction to complete.
+ */
txg_wait_open(tx->tx_pool, tx->tx_lasttried_txg + 1);
}
}
@@ -1268,7 +1456,6 @@ dmu_tx_pool(dmu_tx_t *tx)
return (tx->tx_pool);
}
-
void
dmu_tx_callback_register(dmu_tx_t *tx, dmu_tx_callback_func_t *func, void *data)
{
diff --git a/module/zfs/dmu_zfetch.c b/module/zfs/dmu_zfetch.c
index 705478c82..feb763947 100644
--- a/module/zfs/dmu_zfetch.c
+++ b/module/zfs/dmu_zfetch.c
@@ -23,6 +23,10 @@
* Use is subject to license terms.
*/
+/*
+ * Copyright (c) 2013 by Delphix. All rights reserved.
+ */
+
#include <sys/zfs_context.h>
#include <sys/dnode.h>
#include <sys/dmu_objset.h>
@@ -287,7 +291,7 @@ dmu_zfetch_fetch(dnode_t *dn, uint64_t blkid, uint64_t nblks)
fetchsz = dmu_zfetch_fetchsz(dn, blkid, nblks);
for (i = 0; i < fetchsz; i++) {
- dbuf_prefetch(dn, blkid + i);
+ dbuf_prefetch(dn, blkid + i, ZIO_PRIORITY_ASYNC_READ);
}
return (fetchsz);
diff --git a/module/zfs/dnode.c b/module/zfs/dnode.c
index 7ac379578..25c77753b 100644
--- a/module/zfs/dnode.c
+++ b/module/zfs/dnode.c
@@ -1789,23 +1789,22 @@ dnode_diduse_space(dnode_t *dn, int64_t delta)
}
/*
- * Call when we think we're going to write/free space in open context.
- * Be conservative (ie. OK to write less than this or free more than
- * this, but don't write more or free less).
+ * Call when we think we're going to write/free space in open context to track
+ * the amount of memory in use by the currently open txg.
*/
void
dnode_willuse_space(dnode_t *dn, int64_t space, dmu_tx_t *tx)
{
objset_t *os = dn->dn_objset;
dsl_dataset_t *ds = os->os_dsl_dataset;
+ int64_t aspace = spa_get_asize(os->os_spa, space);
- if (space > 0)
- space = spa_get_asize(os->os_spa, space);
-
- if (ds)
- dsl_dir_willuse_space(ds->ds_dir, space, tx);
+ if (ds != NULL) {
+ dsl_dir_willuse_space(ds->ds_dir, aspace, tx);
+ dsl_pool_dirty_space(dmu_tx_pool(tx), space, tx);
+ }
- dmu_tx_willuse_space(tx, space);
+ dmu_tx_willuse_space(tx, aspace);
}
/*
diff --git a/module/zfs/dsl_dir.c b/module/zfs/dsl_dir.c
index 44795f344..54a7dffb1 100644
--- a/module/zfs/dsl_dir.c
+++ b/module/zfs/dsl_dir.c
@@ -589,7 +589,6 @@ dsl_dir_space_available(dsl_dir_t *dd,
struct tempreserve {
list_node_t tr_node;
- dsl_pool_t *tr_dp;
dsl_dir_t *tr_ds;
uint64_t tr_size;
};
@@ -740,25 +739,24 @@ dsl_dir_tempreserve_space(dsl_dir_t *dd, uint64_t lsize, uint64_t asize,
tr = kmem_zalloc(sizeof (struct tempreserve), KM_PUSHPAGE);
tr->tr_size = lsize;
list_insert_tail(tr_list, tr);
-
- err = dsl_pool_tempreserve_space(dd->dd_pool, asize, tx);
} else {
if (err == EAGAIN) {
+ /*
+ * If arc_memory_throttle() detected that pageout
+ * is running and we are low on memory, we delay new
+ * non-pageout transactions to give pageout an
+ * advantage.
+ *
+ * It is unfortunate to be delaying while the caller's
+ * locks are held.
+ */
txg_delay(dd->dd_pool, tx->tx_txg,
MSEC2NSEC(10), MSEC2NSEC(10));
err = SET_ERROR(ERESTART);
}
- dsl_pool_memory_pressure(dd->dd_pool);
}
if (err == 0) {
- struct tempreserve *tr;
-
- tr = kmem_zalloc(sizeof (struct tempreserve), KM_PUSHPAGE);
- tr->tr_dp = dd->dd_pool;
- tr->tr_size = asize;
- list_insert_tail(tr_list, tr);
-
err = dsl_dir_tempreserve_impl(dd, asize, fsize >= asize,
FALSE, asize > usize, tr_list, tx, TRUE);
}
@@ -787,10 +785,8 @@ dsl_dir_tempreserve_clear(void *tr_cookie, dmu_tx_t *tx)
if (tr_cookie == NULL)
return;
- while ((tr = list_head(tr_list))) {
- if (tr->tr_dp) {
- dsl_pool_tempreserve_clear(tr->tr_dp, tr->tr_size, tx);
- } else if (tr->tr_ds) {
+ while ((tr = list_head(tr_list)) != NULL) {
+ if (tr->tr_ds) {
mutex_enter(&tr->tr_ds->dd_lock);
ASSERT3U(tr->tr_ds->dd_tempreserved[txgidx], >=,
tr->tr_size);
@@ -806,8 +802,14 @@ dsl_dir_tempreserve_clear(void *tr_cookie, dmu_tx_t *tx)
kmem_free(tr_list, sizeof (list_t));
}
-static void
-dsl_dir_willuse_space_impl(dsl_dir_t *dd, int64_t space, dmu_tx_t *tx)
+/*
+ * This should be called from open context when we think we're going to write
+ * or free space, for example when dirtying data. Be conservative; it's okay
+ * to write less space or free more, but we don't want to write more or free
+ * less than the amount specified.
+ */
+void
+dsl_dir_willuse_space(dsl_dir_t *dd, int64_t space, dmu_tx_t *tx)
{
int64_t parent_space;
uint64_t est_used;
@@ -825,19 +827,7 @@ dsl_dir_willuse_space_impl(dsl_dir_t *dd, int64_t space, dmu_tx_t *tx)
/* XXX this is potentially expensive and unnecessary... */
if (parent_space && dd->dd_parent)
- dsl_dir_willuse_space_impl(dd->dd_parent, parent_space, tx);
-}
-
-/*
- * Call in open context when we think we're going to write/free space,
- * eg. when dirtying data. Be conservative (ie. OK to write less than
- * this or free more than this, but don't write more or free less).
- */
-void
-dsl_dir_willuse_space(dsl_dir_t *dd, int64_t space, dmu_tx_t *tx)
-{
- dsl_pool_willuse_space(dd->dd_pool, space, tx);
- dsl_dir_willuse_space_impl(dd, space, tx);
+ dsl_dir_willuse_space(dd->dd_parent, parent_space, tx);
}
/* call from syncing context when we actually write/free space for this dd */
diff --git a/module/zfs/dsl_pool.c b/module/zfs/dsl_pool.c
index e7127c535..eed4bd497 100644
--- a/module/zfs/dsl_pool.c
+++ b/module/zfs/dsl_pool.c
@@ -46,18 +46,85 @@
#include <sys/zil_impl.h>
#include <sys/dsl_userhold.h>
-int zfs_no_write_throttle = 0;
-int zfs_write_limit_shift = 3; /* 1/8th of physical memory */
-int zfs_txg_synctime_ms = 1000; /* target millisecs to sync a txg */
+/*
+ * ZFS Write Throttle
+ * ------------------
+ *
+ * ZFS must limit the rate of incoming writes to the rate at which it is able
+ * to sync data modifications to the backend storage. Throttling by too much
+ * creates an artificial limit; throttling by too little can only be sustained
+ * for short periods and would lead to highly lumpy performance. On a per-pool
+ * basis, ZFS tracks the amount of modified (dirty) data. As operations change
+ * data, the amount of dirty data increases; as ZFS syncs out data, the amount
+ * of dirty data decreases. When the amount of dirty data exceeds a
+ * predetermined threshold further modifications are blocked until the amount
+ * of dirty data decreases (as data is synced out).
+ *
+ * The limit on dirty data is tunable, and should be adjusted according to
+ * both the IO capacity and available memory of the system. The larger the
+ * window, the more ZFS is able to aggregate and amortize metadata (and data)
+ * changes. However, memory is a limited resource, and allowing for more dirty
+ * data comes at the cost of keeping other useful data in memory (for example
+ * ZFS data cached by the ARC).
+ *
+ * Implementation
+ *
+ * As buffers are modified dsl_pool_willuse_space() increments both the per-
+ * txg (dp_dirty_pertxg[]) and poolwide (dp_dirty_total) accounting of
+ * dirty space used; dsl_pool_dirty_space() decrements those values as data
+ * is synced out from dsl_pool_sync(). While only the poolwide value is
+ * relevant, the per-txg value is useful for debugging. The tunable
+ * zfs_dirty_data_max determines the dirty space limit. Once that value is
+ * exceeded, new writes are halted until space frees up.
+ *
+ * The zfs_dirty_data_sync tunable dictates the threshold at which we
+ * ensure that there is a txg syncing (see the comment in txg.c for a full
+ * description of transaction group stages).
+ *
+ * The IO scheduler uses both the dirty space limit and current amount of
+ * dirty data as inputs. Those values affect the number of concurrent IOs ZFS
+ * issues. See the comment in vdev_queue.c for details of the IO scheduler.
+ *
+ * The delay is also calculated based on the amount of dirty data. See the
+ * comment above dmu_tx_delay() for details.
+ */
+
+/*
+ * zfs_dirty_data_max will be set to zfs_dirty_data_max_percent% of all memory,
+ * capped at zfs_dirty_data_max_max. It can also be overridden with a module
+ * parameter.
+ */
+unsigned long zfs_dirty_data_max = 0;
+unsigned long zfs_dirty_data_max_max = 0;
+int zfs_dirty_data_max_percent = 10;
+int zfs_dirty_data_max_max_percent = 25;
-unsigned long zfs_write_limit_min = 32 << 20; /* min write limit is 32MB */
-unsigned long zfs_write_limit_max = 0; /* max data payload per txg */
-unsigned long zfs_write_limit_inflated = 0;
-unsigned long zfs_write_limit_override = 0;
+/*
+ * If there is at least this much dirty data, push out a txg.
+ */
+unsigned long zfs_dirty_data_sync = 64 * 1024 * 1024;
-kmutex_t zfs_write_limit_lock;
+/*
+ * Once there is this amount of dirty data, the dmu_tx_delay() will kick in
+ * and delay each transaction.
+ * This value should be >= zfs_vdev_async_write_active_max_dirty_percent.
+ */
+int zfs_delay_min_dirty_percent = 60;
-static pgcnt_t old_physmem = 0;
+/*
+ * This controls how quickly the delay approaches infinity.
+ * Larger values cause it to delay more for a given amount of dirty data.
+ * Therefore larger values will cause there to be less dirty data for a
+ * given throughput.
+ *
+ * For the smoothest delay, this value should be about 1 billion divided
+ * by the maximum number of operations per second. This will smoothly
+ * handle between 10x and 1/10th this number.
+ *
+ * Note: zfs_delay_scale * zfs_dirty_data_max must be < 2^64, due to the
+ * multiply in dmu_tx_delay().
+ */
+unsigned long zfs_delay_scale = 1000 * 1000 * 1000 / 2000;
hrtime_t zfs_throttle_delay = MSEC2NSEC(10);
hrtime_t zfs_throttle_resolution = MSEC2NSEC(10);
@@ -87,7 +154,6 @@ dsl_pool_open_impl(spa_t *spa, uint64_t txg)
dp->dp_spa = spa;
dp->dp_meta_rootbp = *bp;
rrw_init(&dp->dp_config_rwlock, B_TRUE);
- dp->dp_write_limit = zfs_write_limit_min;
txg_init(dp, txg);
txg_list_create(&dp->dp_dirty_datasets,
@@ -100,6 +166,7 @@ dsl_pool_open_impl(spa_t *spa, uint64_t txg)
offsetof(dsl_sync_task_t, dst_node));
mutex_init(&dp->dp_lock, NULL, MUTEX_DEFAULT, NULL);
+ cv_init(&dp->dp_spaceavail_cv, NULL, CV_DEFAULT, NULL);
dp->dp_iput_taskq = taskq_create("zfs_iput_taskq", 1, minclsyspri,
1, 4, 0);
@@ -214,9 +281,9 @@ out:
void
dsl_pool_close(dsl_pool_t *dp)
{
- /* drop our references from dsl_pool_open() */
-
/*
+ * Drop our references from dsl_pool_open().
+ *
* Since we held the origin_snap from "syncing" context (which
* includes pool-opening context), it actually only got a "ref"
* and not a hold, so just drop that here.
@@ -346,6 +413,34 @@ deadlist_enqueue_cb(void *arg, const blkptr_t *bp, dmu_tx_t *tx)
return (0);
}
+static void
+dsl_pool_sync_mos(dsl_pool_t *dp, dmu_tx_t *tx)
+{
+ zio_t *zio = zio_root(dp->dp_spa, NULL, NULL, ZIO_FLAG_MUSTSUCCEED);
+ dmu_objset_sync(dp->dp_meta_objset, zio, tx);
+ VERIFY0(zio_wait(zio));
+ dprintf_bp(&dp->dp_meta_rootbp, "meta objset rootbp is %s", "");
+ spa_set_rootblkptr(dp->dp_spa, &dp->dp_meta_rootbp);
+}
+
+static void
+dsl_pool_dirty_delta(dsl_pool_t *dp, int64_t delta)
+{
+ ASSERT(MUTEX_HELD(&dp->dp_lock));
+
+ if (delta < 0)
+ ASSERT3U(-delta, <=, dp->dp_dirty_total);
+
+ dp->dp_dirty_total += delta;
+
+ /*
+ * Note: we signal even when increasing dp_dirty_total.
+ * This ensures forward progress -- each thread wakes the next waiter.
+ */
+ if (dp->dp_dirty_total <= zfs_dirty_data_max)
+ cv_signal(&dp->dp_spaceavail_cv);
+}
+
void
dsl_pool_sync(dsl_pool_t *dp, uint64_t txg)
{
@@ -354,29 +449,18 @@ dsl_pool_sync(dsl_pool_t *dp, uint64_t txg)
dsl_dir_t *dd;
dsl_dataset_t *ds;
objset_t *mos = dp->dp_meta_objset;
- hrtime_t start, write_time;
- uint64_t data_written;
- int err;
list_t synced_datasets;
list_create(&synced_datasets, sizeof (dsl_dataset_t),
offsetof(dsl_dataset_t, ds_synced_link));
- /*
- * We need to copy dp_space_towrite() before doing
- * dsl_sync_task_sync(), because
- * dsl_dataset_snapshot_reserve_space() will increase
- * dp_space_towrite but not actually write anything.
- */
- data_written = dp->dp_space_towrite[txg & TXG_MASK];
-
tx = dmu_tx_create_assigned(dp, txg);
- dp->dp_read_overhead = 0;
- start = gethrtime();
-
+ /*
+ * Write out all dirty blocks of dirty datasets.
+ */
zio = zio_root(dp->dp_spa, NULL, NULL, ZIO_FLAG_MUSTSUCCEED);
- while ((ds = txg_list_remove(&dp->dp_dirty_datasets, txg))) {
+ while ((ds = txg_list_remove(&dp->dp_dirty_datasets, txg)) != NULL) {
/*
* We must not sync any non-MOS datasets twice, because
* we may have taken a snapshot of them. However, we
@@ -386,20 +470,25 @@ dsl_pool_sync(dsl_pool_t *dp, uint64_t txg)
list_insert_tail(&synced_datasets, ds);
dsl_dataset_sync(ds, zio, tx);
}
- DTRACE_PROBE(pool_sync__1setup);
- err = zio_wait(zio);
+ VERIFY0(zio_wait(zio));
- write_time = gethrtime() - start;
- ASSERT(err == 0);
- DTRACE_PROBE(pool_sync__2rootzio);
+ /*
+ * We have written all of the accounted dirty data, so our
+ * dp_space_towrite should now be zero. However, some seldom-used
+ * code paths do not adhere to this (e.g. dbuf_undirty(), also
+ * rounding error in dbuf_write_physdone).
+ * Shore up the accounting of any dirtied space now.
+ */
+ dsl_pool_undirty_space(dp, dp->dp_dirty_pertxg[txg & TXG_MASK], txg);
/*
* After the data blocks have been written (ensured by the zio_wait()
* above), update the user/group space accounting.
*/
- for (ds = list_head(&synced_datasets); ds;
- ds = list_next(&synced_datasets, ds))
+ for (ds = list_head(&synced_datasets); ds != NULL;
+ ds = list_next(&synced_datasets, ds)) {
dmu_objset_do_userquota_updates(ds->ds_objset, tx);
+ }
/*
* Sync the datasets again to push out the changes due to
@@ -409,12 +498,12 @@ dsl_pool_sync(dsl_pool_t *dp, uint64_t txg)
* about which blocks are part of the snapshot).
*/
zio = zio_root(dp->dp_spa, NULL, NULL, ZIO_FLAG_MUSTSUCCEED);
- while ((ds = txg_list_remove(&dp->dp_dirty_datasets, txg))) {
+ while ((ds = txg_list_remove(&dp->dp_dirty_datasets, txg)) != NULL) {
ASSERT(list_link_active(&ds->ds_synced_link));
dmu_buf_rele(ds->ds_dbuf, ds);
dsl_dataset_sync(ds, zio, tx);
}
- err = zio_wait(zio);
+ VERIFY0(zio_wait(zio));
/*
* Now that the datasets have been completely synced, we can
@@ -423,7 +512,7 @@ dsl_pool_sync(dsl_pool_t *dp, uint64_t txg)
* - move dead blocks from the pending deadlist to the on-disk deadlist
* - release hold from dsl_dataset_dirty()
*/
- while ((ds = list_remove_head(&synced_datasets))) {
+ while ((ds = list_remove_head(&synced_datasets)) != NULL) {
ASSERTV(objset_t *os = ds->ds_objset);
bplist_iterate(&ds->ds_pending_deadlist,
deadlist_enqueue_cb, &ds->ds_deadlist, tx);
@@ -431,10 +520,9 @@ dsl_pool_sync(dsl_pool_t *dp, uint64_t txg)
dmu_buf_rele(ds->ds_dbuf, ds);
}
- start = gethrtime();
- while ((dd = txg_list_remove(&dp->dp_dirty_dirs, txg)))
+ while ((dd = txg_list_remove(&dp->dp_dirty_dirs, txg)) != NULL) {
dsl_dir_sync(dd, tx);
- write_time += gethrtime() - start;
+ }
/*
* The MOS's space is accounted for in the pool/$MOS
@@ -452,20 +540,10 @@ dsl_pool_sync(dsl_pool_t *dp, uint64_t txg)
dp->dp_mos_uncompressed_delta = 0;
}
- start = gethrtime();
if (list_head(&mos->os_dirty_dnodes[txg & TXG_MASK]) != NULL ||
list_head(&mos->os_free_dnodes[txg & TXG_MASK]) != NULL) {
- zio = zio_root(dp->dp_spa, NULL, NULL, ZIO_FLAG_MUSTSUCCEED);
- dmu_objset_sync(mos, zio, tx);
- err = zio_wait(zio);
- ASSERT(err == 0);
- dprintf_bp(&dp->dp_meta_rootbp, "meta objset rootbp is %s", "");
- spa_set_rootblkptr(dp->dp_spa, &dp->dp_meta_rootbp);
+ dsl_pool_sync_mos(dp, tx);
}
- write_time += gethrtime() - start;
- DTRACE_PROBE2(pool_sync__4io, hrtime_t, write_time,
- hrtime_t, dp->dp_read_overhead);
- write_time -= dp->dp_read_overhead;
/*
* If we modify a dataset in the same txg that we want to destroy it,
@@ -476,72 +554,29 @@ dsl_pool_sync(dsl_pool_t *dp, uint64_t txg)
* The MOS data dirtied by the sync_tasks will be synced on the next
* pass.
*/
- DTRACE_PROBE(pool_sync__3task);
if (!txg_list_empty(&dp->dp_sync_tasks, txg)) {
dsl_sync_task_t *dst;
/*
* No more sync tasks should have been added while we
* were syncing.
*/
- ASSERT(spa_sync_pass(dp->dp_spa) == 1);
- while ((dst = txg_list_remove(&dp->dp_sync_tasks, txg)))
+ ASSERT3U(spa_sync_pass(dp->dp_spa), ==, 1);
+ while ((dst = txg_list_remove(&dp->dp_sync_tasks, txg)) != NULL)
dsl_sync_task_sync(dst, tx);
}
dmu_tx_commit(tx);
- dp->dp_space_towrite[txg & TXG_MASK] = 0;
- ASSERT(dp->dp_tempreserved[txg & TXG_MASK] == 0);
-
- /*
- * If the write limit max has not been explicitly set, set it
- * to a fraction of available physical memory (default 1/8th).
- * Note that we must inflate the limit because the spa
- * inflates write sizes to account for data replication.
- * Check this each sync phase to catch changing memory size.
- */
- if (physmem != old_physmem && zfs_write_limit_shift) {
- mutex_enter(&zfs_write_limit_lock);
- old_physmem = physmem;
- zfs_write_limit_max = ptob(physmem) >> zfs_write_limit_shift;
- zfs_write_limit_inflated = MAX(zfs_write_limit_min,
- spa_get_asize(dp->dp_spa, zfs_write_limit_max));
- mutex_exit(&zfs_write_limit_lock);
- }
-
- /*
- * Attempt to keep the sync time consistent by adjusting the
- * amount of write traffic allowed into each transaction group.
- * Weight the throughput calculation towards the current value:
- * thru = 3/4 old_thru + 1/4 new_thru
- *
- * Note: write_time is in nanosecs while dp_throughput is expressed in
- * bytes per millisecond.
- */
- ASSERT(zfs_write_limit_min > 0);
- if (data_written > zfs_write_limit_min / 8 &&
- write_time > MSEC2NSEC(1)) {
- uint64_t throughput = data_written / NSEC2MSEC(write_time);
-
- if (dp->dp_throughput)
- dp->dp_throughput = throughput / 4 +
- 3 * dp->dp_throughput / 4;
- else
- dp->dp_throughput = throughput;
- dp->dp_write_limit = MIN(zfs_write_limit_inflated,
- MAX(zfs_write_limit_min,
- dp->dp_throughput * zfs_txg_synctime_ms));
- }
+ DTRACE_PROBE2(dsl_pool_sync__done, dsl_pool_t *dp, dp, uint64_t, txg);
}
void
dsl_pool_sync_done(dsl_pool_t *dp, uint64_t txg)
{
zilog_t *zilog;
- dsl_dataset_t *ds;
while ((zilog = txg_list_remove(&dp->dp_dirty_zilogs, txg))) {
- ds = dmu_objset_ds(zilog->zl_os);
+ dsl_dataset_t *ds = dmu_objset_ds(zilog->zl_os);
zil_clean(zilog, txg);
ASSERT(!dmu_objset_is_dirty(zilog->zl_os, txg));
dmu_buf_rele(ds->ds_dbuf, zilog);
@@ -583,84 +618,49 @@ dsl_pool_adjustedsize(dsl_pool_t *dp, boolean_t netfree)
return (space - resv);
}
-int
-dsl_pool_tempreserve_space(dsl_pool_t *dp, uint64_t space, dmu_tx_t *tx)
+boolean_t
+dsl_pool_need_dirty_delay(dsl_pool_t *dp)
{
- uint64_t reserved = 0;
- uint64_t write_limit = (zfs_write_limit_override ?
- zfs_write_limit_override : dp->dp_write_limit);
-
- if (zfs_no_write_throttle) {
- atomic_add_64(&dp->dp_tempreserved[tx->tx_txg & TXG_MASK],
- space);
- return (0);
- }
-
- /*
- * Check to see if we have exceeded the maximum allowed IO for
- * this transaction group. We can do this without locks since
- * a little slop here is ok. Note that we do the reserved check
- * with only half the requested reserve: this is because the
- * reserve requests are worst-case, and we really don't want to
- * throttle based off of worst-case estimates.
- */
- if (write_limit > 0) {
- reserved = dp->dp_space_towrite[tx->tx_txg & TXG_MASK]
- + dp->dp_tempreserved[tx->tx_txg & TXG_MASK] / 2;
+ uint64_t delay_min_bytes =
+ zfs_dirty_data_max * zfs_delay_min_dirty_percent / 100;
+ boolean_t rv;
- if (reserved && reserved > write_limit) {
- DMU_TX_STAT_BUMP(dmu_tx_write_limit);
- return (SET_ERROR(ERESTART));
- }
- }
-
- atomic_add_64(&dp->dp_tempreserved[tx->tx_txg & TXG_MASK], space);
-
- /*
- * If this transaction group is over 7/8ths capacity, delay
- * the caller 1 clock tick. This will slow down the "fill"
- * rate until the sync process can catch up with us.
- */
- if (reserved && reserved > (write_limit - (write_limit >> 3))) {
- txg_delay(dp, tx->tx_txg, zfs_throttle_delay,
- zfs_throttle_resolution);
- }
-
- return (0);
+ mutex_enter(&dp->dp_lock);
+ if (dp->dp_dirty_total > zfs_dirty_data_sync)
+ txg_kick(dp);
+ rv = (dp->dp_dirty_total > delay_min_bytes);
+ mutex_exit(&dp->dp_lock);
+ return (rv);
}
void
-dsl_pool_tempreserve_clear(dsl_pool_t *dp, int64_t space, dmu_tx_t *tx)
+dsl_pool_dirty_space(dsl_pool_t *dp, int64_t space, dmu_tx_t *tx)
{
- ASSERT(dp->dp_tempreserved[tx->tx_txg & TXG_MASK] >= space);
- atomic_add_64(&dp->dp_tempreserved[tx->tx_txg & TXG_MASK], -space);
+ if (space > 0) {
+ mutex_enter(&dp->dp_lock);
+ dp->dp_dirty_pertxg[tx->tx_txg & TXG_MASK] += space;
+ dsl_pool_dirty_delta(dp, space);
+ mutex_exit(&dp->dp_lock);
+ }
}
void
-dsl_pool_memory_pressure(dsl_pool_t *dp)
+dsl_pool_undirty_space(dsl_pool_t *dp, int64_t space, uint64_t txg)
{
- uint64_t space_inuse = 0;
- int i;
-
- if (dp->dp_write_limit == zfs_write_limit_min)
+ ASSERT3S(space, >=, 0);
+ if (space == 0)
return;
- for (i = 0; i < TXG_SIZE; i++) {
- space_inuse += dp->dp_space_towrite[i];
- space_inuse += dp->dp_tempreserved[i];
- }
- dp->dp_write_limit = MAX(zfs_write_limit_min,
- MIN(dp->dp_write_limit, space_inuse / 4));
-}
-
-void
-dsl_pool_willuse_space(dsl_pool_t *dp, int64_t space, dmu_tx_t *tx)
-{
- if (space > 0) {
- mutex_enter(&dp->dp_lock);
- dp->dp_space_towrite[tx->tx_txg & TXG_MASK] += space;
- mutex_exit(&dp->dp_lock);
+ mutex_enter(&dp->dp_lock);
+ if (dp->dp_dirty_pertxg[txg & TXG_MASK] < space) {
+ /* XXX writing something we didn't dirty? */
+ space = dp->dp_dirty_pertxg[txg & TXG_MASK];
}
+ ASSERT3U(dp->dp_dirty_pertxg[txg & TXG_MASK], >=, space);
+ dp->dp_dirty_pertxg[txg & TXG_MASK] -= space;
+ ASSERT3U(dp->dp_dirty_total, >=, space);
+ dsl_pool_dirty_delta(dp, -space);
+ mutex_exit(&dp->dp_lock);
}
/* ARGSUSED */
@@ -1049,24 +1049,30 @@ dsl_pool_config_held(dsl_pool_t *dp)
EXPORT_SYMBOL(dsl_pool_config_enter);
EXPORT_SYMBOL(dsl_pool_config_exit);
-module_param(zfs_no_write_throttle, int, 0644);
-MODULE_PARM_DESC(zfs_no_write_throttle, "Disable write throttling");
+/* zfs_dirty_data_max_percent only applied at module load time in arc_init(). */
+module_param(zfs_dirty_data_max_percent, int, 0444);
+MODULE_PARM_DESC(zfs_dirty_data_max_percent, "percent of ram can be dirty");
-module_param(zfs_write_limit_shift, int, 0444);
-MODULE_PARM_DESC(zfs_write_limit_shift, "log2(fraction of memory) per txg");
+/* zfs_dirty_data_max_max_percent only applied at module load time in
+ * arc_init(). */
+module_param(zfs_dirty_data_max_max_percent, int, 0444);
+MODULE_PARM_DESC(zfs_dirty_data_max_max_percent,
+ "zfs_dirty_data_max upper bound as % of RAM");
-module_param(zfs_txg_synctime_ms, int, 0644);
-MODULE_PARM_DESC(zfs_txg_synctime_ms, "Target milliseconds between txg sync");
+module_param(zfs_delay_min_dirty_percent, int, 0644);
+MODULE_PARM_DESC(zfs_delay_min_dirty_percent, "transaction delay threshold");
-module_param(zfs_write_limit_min, ulong, 0444);
-MODULE_PARM_DESC(zfs_write_limit_min, "Min txg write limit");
+module_param(zfs_dirty_data_max, ulong, 0644);
+MODULE_PARM_DESC(zfs_dirty_data_max, "determines the dirty space limit");
-module_param(zfs_write_limit_max, ulong, 0444);
-MODULE_PARM_DESC(zfs_write_limit_max, "Max txg write limit");
+/* zfs_dirty_data_max_max only applied at module load time in arc_init(). */
+module_param(zfs_dirty_data_max_max, ulong, 0444);
+MODULE_PARM_DESC(zfs_dirty_data_max_max,
+ "zfs_dirty_data_max upper bound in bytes");
-module_param(zfs_write_limit_inflated, ulong, 0444);
-MODULE_PARM_DESC(zfs_write_limit_inflated, "Inflated txg write limit");
+module_param(zfs_dirty_data_sync, ulong, 0644);
+MODULE_PARM_DESC(zfs_dirty_data_sync, "sync txg when this much dirty data");
-module_param(zfs_write_limit_override, ulong, 0444);
-MODULE_PARM_DESC(zfs_write_limit_override, "Override txg write limit");
+module_param(zfs_delay_scale, ulong, 0644);
+MODULE_PARM_DESC(zfs_delay_scale, "how quickly delay approaches infinity");
#endif
diff --git a/module/zfs/dsl_scan.c b/module/zfs/dsl_scan.c
index 354d5b1df..3780aee79 100644
--- a/module/zfs/dsl_scan.c
+++ b/module/zfs/dsl_scan.c
@@ -1650,7 +1650,6 @@ dsl_scan_scrub_cb(dsl_pool_t *dp,
uint64_t phys_birth = BP_PHYSICAL_BIRTH(bp);
boolean_t needs_io = B_FALSE;
int zio_flags = ZIO_FLAG_SCAN_THREAD | ZIO_FLAG_RAW | ZIO_FLAG_CANFAIL;
- int zio_priority = 0;
int scan_delay = 0;
int d;
@@ -1663,13 +1662,11 @@ dsl_scan_scrub_cb(dsl_pool_t *dp,
ASSERT(DSL_SCAN_IS_SCRUB_RESILVER(scn));
if (scn->scn_phys.scn_func == POOL_SCAN_SCRUB) {
zio_flags |= ZIO_FLAG_SCRUB;
- zio_priority = ZIO_PRIORITY_SCRUB;
needs_io = B_TRUE;
scan_delay = zfs_scrub_delay;
} else {
ASSERT3U(scn->scn_phys.scn_func, ==, POOL_SCAN_RESILVER);
zio_flags |= ZIO_FLAG_RESILVER;
- zio_priority = ZIO_PRIORITY_RESILVER;
needs_io = B_FALSE;
scan_delay = zfs_resilver_delay;
}
@@ -1727,7 +1724,7 @@ dsl_scan_scrub_cb(dsl_pool_t *dp,
delay(scan_delay);
zio_nowait(zio_read(NULL, spa, bp, data, size,
- dsl_scan_scrub_done, NULL, zio_priority,
+ dsl_scan_scrub_done, NULL, ZIO_PRIORITY_SCRUB,
zio_flags, zb));
}
diff --git a/module/zfs/spa.c b/module/zfs/spa.c
index c7ea59536..3daf5805d 100644
--- a/module/zfs/spa.c
+++ b/module/zfs/spa.c
@@ -83,7 +83,6 @@
typedef enum zti_modes {
ZTI_MODE_FIXED, /* value is # of threads (min 1) */
- ZTI_MODE_ONLINE_PERCENT, /* value is % of online CPUs */
ZTI_MODE_BATCH, /* cpu-intensive; value is ignored */
ZTI_MODE_NULL, /* don't create a taskq */
ZTI_NMODES
@@ -142,7 +141,7 @@ static inline int spa_load_impl(spa_t *spa, uint64_t, nvlist_t *config,
char **ereport);
static void spa_vdev_resilver_done(spa_t *spa);
-uint_t zio_taskq_batch_pct = 100; /* 1 thread per cpu in pset */
+uint_t zio_taskq_batch_pct = 75; /* 1 thread per cpu in pset */
id_t zio_taskq_psrset_bind = PS_NONE;
boolean_t zio_taskq_sysdc = B_TRUE; /* use SDC scheduling class */
uint_t zio_taskq_basedc = 80; /* base duty cycle */
@@ -837,31 +836,27 @@ spa_taskqs_init(spa_t *spa, zio_type_t t, zio_taskq_type_t q)
tqs->stqs_count = count;
tqs->stqs_taskq = kmem_alloc(count * sizeof (taskq_t *), KM_SLEEP);
- for (i = 0; i < count; i++) {
- taskq_t *tq;
-
- switch (mode) {
- case ZTI_MODE_FIXED:
- ASSERT3U(value, >=, 1);
- value = MAX(value, 1);
- break;
+ switch (mode) {
+ case ZTI_MODE_FIXED:
+ ASSERT3U(value, >=, 1);
+ value = MAX(value, 1);
+ break;
- case ZTI_MODE_BATCH:
- batch = B_TRUE;
- flags |= TASKQ_THREADS_CPU_PCT;
- value = zio_taskq_batch_pct;
- break;
+ case ZTI_MODE_BATCH:
+ batch = B_TRUE;
+ flags |= TASKQ_THREADS_CPU_PCT;
+ value = zio_taskq_batch_pct;
+ break;
- case ZTI_MODE_ONLINE_PERCENT:
- flags |= TASKQ_THREADS_CPU_PCT;
- break;
+ default:
+ panic("unrecognized mode for %s_%s taskq (%u:%u) in "
+ "spa_activate()",
+ zio_type_name[t], zio_taskq_types[q], mode, value);
+ break;
+ }
- default:
- panic("unrecognized mode for %s_%s taskq (%u:%u) in "
- "spa_activate()",
- zio_type_name[t], zio_taskq_types[q], mode, value);
- break;
- }
+ for (i = 0; i < count; i++) {
+ taskq_t *tq;
if (count > 1) {
(void) snprintf(name, sizeof (name), "%s_%s_%u",
@@ -878,7 +873,16 @@ spa_taskqs_init(spa_t *spa, zio_type_t t, zio_taskq_type_t q)
tq = taskq_create_sysdc(name, value, 50, INT_MAX,
spa->spa_proc, zio_taskq_basedc, flags);
} else {
- tq = taskq_create_proc(name, value, maxclsyspri, 50,
+ pri_t pri = maxclsyspri;
+ /*
+ * The write issue taskq can be extremely CPU
+ * intensive. Run it at slightly lower priority
+ * than the other taskqs.
+ */
+ if (t == ZIO_TYPE_WRITE && q == ZIO_TASKQ_ISSUE)
+ pri--;
+
+ tq = taskq_create_proc(name, value, pri, 50,
INT_MAX, spa->spa_proc, flags);
}
@@ -5775,6 +5779,31 @@ spa_free_sync_cb(void *arg, const blkptr_t *bp, dmu_tx_t *tx)
return (0);
}
+/*
+ * Note: this simple function is not inlined to make it easier to dtrace the
+ * amount of time spent syncing frees.
+ */
+static void
+spa_sync_frees(spa_t *spa, bplist_t *bpl, dmu_tx_t *tx)
+{
+ zio_t *zio = zio_root(spa, NULL, NULL, 0);
+ bplist_iterate(bpl, spa_free_sync_cb, zio, tx);
+ VERIFY(zio_wait(zio) == 0);
+}
+
+/*
+ * Note: this simple function is not inlined to make it easier to dtrace the
+ * amount of time spent syncing deferred frees.
+ */
+static void
+spa_sync_deferred_frees(spa_t *spa, dmu_tx_t *tx)
+{
+ zio_t *zio = zio_root(spa, NULL, NULL, 0);
+ VERIFY3U(bpobj_iterate(&spa->spa_deferred_bpobj,
+ spa_free_sync_cb, zio, tx), ==, 0);
+ VERIFY0(zio_wait(zio));
+}
+
static void
spa_sync_nvlist(spa_t *spa, uint64_t obj, nvlist_t *nv, dmu_tx_t *tx)
{
@@ -6102,7 +6131,6 @@ spa_sync(spa_t *spa, uint64_t txg)
{
dsl_pool_t *dp = spa->spa_dsl_pool;
objset_t *mos = spa->spa_meta_objset;
- bpobj_t *defer_bpo = &spa->spa_deferred_bpobj;
bplist_t *free_bpl = &spa->spa_free_bplist[txg & TXG_MASK];
vdev_t *rvd = spa->spa_root_vdev;
vdev_t *vd;
@@ -6185,10 +6213,7 @@ spa_sync(spa_t *spa, uint64_t txg)
!txg_list_empty(&dp->dp_sync_tasks, txg) ||
((dsl_scan_active(dp->dp_scan) ||
txg_sync_waiting(dp)) && !spa_shutting_down(spa))) {
- zio_t *zio = zio_root(spa, NULL, NULL, 0);
- VERIFY3U(bpobj_iterate(defer_bpo,
- spa_free_sync_cb, zio, tx), ==, 0);
- VERIFY0(zio_wait(zio));
+ spa_sync_deferred_frees(spa, tx);
}
/*
@@ -6206,13 +6231,10 @@ spa_sync(spa_t *spa, uint64_t txg)
dsl_pool_sync(dp, txg);
if (pass < zfs_sync_pass_deferred_free) {
- zio_t *zio = zio_root(spa, NULL, NULL, 0);
- bplist_iterate(free_bpl, spa_free_sync_cb,
- zio, tx);
- VERIFY(zio_wait(zio) == 0);
+ spa_sync_frees(spa, free_bpl, tx);
} else {
bplist_iterate(free_bpl, bpobj_enqueue_cb,
- defer_bpo, tx);
+ &spa->spa_deferred_bpobj, tx);
}
ddt_sync(spa, txg);
diff --git a/module/zfs/spa_misc.c b/module/zfs/spa_misc.c
index 91e7fdf35..d12e233b1 100644
--- a/module/zfs/spa_misc.c
+++ b/module/zfs/spa_misc.c
@@ -238,15 +238,14 @@ kmem_cache_t *spa_buffer_pool;
int spa_mode_global;
/*
- * Expiration time in units of zfs_txg_synctime_ms. This value has two
- * meanings. First it is used to determine when the spa_deadman logic
- * should fire. By default the spa_deadman will fire if spa_sync has
- * not completed in 1000 * zfs_txg_synctime_ms (i.e. 1000 seconds).
- * Secondly, the value determines if an I/O is considered "hung".
- * Any I/O that has not completed in zfs_deadman_synctime is considered
- * "hung" resulting in a zevent being posted.
+ * Expiration time in milliseconds. This value has two meanings. First it is
+ * used to determine when the spa_deadman() logic should fire. By default the
+ * spa_deadman() will fire if spa_sync() has not completed in 1000 seconds.
+ * Secondly, the value determines if an I/O is considered "hung". Any I/O that
+ * has not completed in zfs_deadman_synctime_ms is considered "hung" resulting
+ * in a system panic.
*/
-unsigned long zfs_deadman_synctime = 1000ULL;
+unsigned long zfs_deadman_synctime_ms = 1000000ULL;
/*
* By default the deadman is enabled.
@@ -254,6 +253,17 @@ unsigned long zfs_deadman_synctime = 1000ULL;
int zfs_deadman_enabled = 1;
/*
+ * The worst case is single-sector max-parity RAID-Z blocks, in which
+ * case the space requirement is exactly (VDEV_RAIDZ_MAXPARITY + 1)
+ * times the size; so just assume that. Add to this the fact that
+ * we can have up to 3 DVAs per bp, and one more factor of 2 because
+ * the block may be dittoed with up to 3 DVAs by ddt_sync(). All together,
+ * the worst case is:
+ * (VDEV_RAIDZ_MAXPARITY + 1) * SPA_DVAS_PER_BP * 2 == 24
+ */
+int spa_asize_inflation = 24;
+
+/*
* ==========================================================================
* SPA config locking
* ==========================================================================
@@ -489,8 +499,7 @@ spa_add(const char *name, nvlist_t *config, const char *altroot)
spa->spa_proc = &p0;
spa->spa_proc_state = SPA_PROC_NONE;
- spa->spa_deadman_synctime = MSEC2NSEC(zfs_deadman_synctime *
- zfs_txg_synctime_ms);
+ spa->spa_deadman_synctime = MSEC2NSEC(zfs_deadman_synctime_ms);
refcount_create(&spa->spa_refcount);
spa_config_lock_init(spa);
@@ -1452,14 +1461,7 @@ spa_freeze_txg(spa_t *spa)
uint64_t
spa_get_asize(spa_t *spa, uint64_t lsize)
{
- /*
- * The worst case is single-sector max-parity RAID-Z blocks, in which
- * case the space requirement is exactly (VDEV_RAIDZ_MAXPARITY + 1)
- * times the size; so just assume that. Add to this the fact that
- * we can have up to 3 DVAs per bp, and one more factor of 2 because
- * the block may be dittoed with up to 3 DVAs by ddt_sync().
- */
- return (lsize * (VDEV_RAIDZ_MAXPARITY + 1) * SPA_DVAS_PER_BP * 2);
+ return (lsize * spa_asize_inflation);
}
uint64_t
@@ -1880,9 +1882,13 @@ EXPORT_SYMBOL(spa_mode);
EXPORT_SYMBOL(spa_namespace_lock);
-module_param(zfs_deadman_synctime, ulong, 0644);
-MODULE_PARM_DESC(zfs_deadman_synctime,"Expire in units of zfs_txg_synctime_ms");
+module_param(zfs_deadman_synctime_ms, ulong, 0644);
+MODULE_PARM_DESC(zfs_deadman_synctime_ms,"Expiration time in milliseconds");
module_param(zfs_deadman_enabled, int, 0644);
MODULE_PARM_DESC(zfs_deadman_enabled, "Enable deadman timer");
+
+module_param(spa_asize_inflation, int, 0644);
+MODULE_PARM_DESC(spa_asize_inflation,
+ "SPA size estimate multiplication factor");
#endif
diff --git a/module/zfs/txg.c b/module/zfs/txg.c
index 8d410f7a5..9a594b954 100644
--- a/module/zfs/txg.c
+++ b/module/zfs/txg.c
@@ -46,7 +46,7 @@
* either be processing, or blocked waiting to enter the next state. There may
* be up to three active txgs, and there is always a txg in the open state
* (though it may be blocked waiting to enter the quiescing state). In broad
- * strokes, transactions — operations that change in-memory structures — are
+ * strokes, transactions -- operations that change in-memory structures -- are
* accepted into the txg in the open state, and are completed while the txg is
* in the open or quiescing states. The accumulated changes are written to
* disk in the syncing state.
@@ -54,7 +54,7 @@
* Open
*
* When a new txg becomes active, it first enters the open state. New
- * transactions — updates to in-memory structures — are assigned to the
+ * transactions -- updates to in-memory structures -- are assigned to the
* currently open txg. There is always a txg in the open state so that ZFS can
* accept new changes (though the txg may refuse new changes if it has hit
* some limit). ZFS advances the open txg to the next state for a variety of
@@ -375,6 +375,7 @@ txg_quiesce(dsl_pool_t *dp, uint64_t txg)
ASSERT(txg == tx->tx_open_txg);
tx->tx_open_txg++;
+ tx->tx_open_time = gethrtime();
spa_txg_history_set(dp->dp_spa, txg, TXG_STATE_OPEN, gethrtime());
spa_txg_history_add(dp->dp_spa, tx->tx_open_txg);
@@ -511,7 +512,8 @@ txg_sync_thread(dsl_pool_t *dp)
while (!dsl_scan_active(dp->dp_scan) &&
!tx->tx_exiting && timer > 0 &&
tx->tx_synced_txg >= tx->tx_sync_txg_waiting &&
- tx->tx_quiesced_txg == 0) {
+ tx->tx_quiesced_txg == 0 &&
+ dp->dp_dirty_total < zfs_dirty_data_sync) {
dprintf("waiting; tx_synced=%llu waiting=%llu dp=%p\n",
tx->tx_synced_txg, tx->tx_sync_txg_waiting, dp);
txg_thread_wait(tx, &cpr, &tx->tx_sync_more_cv, timer);
@@ -574,8 +576,7 @@ txg_sync_thread(dsl_pool_t *dp)
vs2->vs_bytes[ZIO_TYPE_WRITE]-vs1->vs_bytes[ZIO_TYPE_WRITE],
vs2->vs_ops[ZIO_TYPE_READ]-vs1->vs_ops[ZIO_TYPE_READ],
vs2->vs_ops[ZIO_TYPE_WRITE]-vs1->vs_ops[ZIO_TYPE_WRITE],
- dp->dp_space_towrite[txg & TXG_MASK] +
- dp->dp_tempreserved[txg & TXG_MASK] / 2);
+ dp->dp_dirty_pertxg[txg & TXG_MASK]);
spa_txg_history_set(spa, txg, TXG_STATE_SYNCED, gethrtime());
}
}
@@ -705,6 +706,28 @@ txg_wait_open(dsl_pool_t *dp, uint64_t txg)
mutex_exit(&tx->tx_sync_lock);
}
+/*
+ * If there isn't a txg syncing or in the pipeline, push another txg through
+ * the pipeline by queiscing the open txg.
+ */
+void
+txg_kick(dsl_pool_t *dp)
+{
+ tx_state_t *tx = &dp->dp_tx;
+
+ ASSERT(!dsl_pool_config_held(dp));
+
+ mutex_enter(&tx->tx_sync_lock);
+ if (tx->tx_syncing_txg == 0 &&
+ tx->tx_quiesce_txg_waiting <= tx->tx_open_txg &&
+ tx->tx_sync_txg_waiting <= tx->tx_synced_txg &&
+ tx->tx_quiesced_txg <= tx->tx_synced_txg) {
+ tx->tx_quiesce_txg_waiting = tx->tx_open_txg + 1;
+ cv_broadcast(&tx->tx_quiesce_more_cv);
+ }
+ mutex_exit(&tx->tx_sync_lock);
+}
+
boolean_t
txg_stalled(dsl_pool_t *dp)
{
diff --git a/module/zfs/vdev.c b/module/zfs/vdev.c
index ff239d72c..7751683d1 100644
--- a/module/zfs/vdev.c
+++ b/module/zfs/vdev.c
@@ -3296,7 +3296,7 @@ vdev_deadman(vdev_t *vd)
vdev_queue_t *vq = &vd->vdev_queue;
mutex_enter(&vq->vq_lock);
- if (avl_numnodes(&vq->vq_pending_tree) > 0) {
+ if (avl_numnodes(&vq->vq_active_tree) > 0) {
spa_t *spa = vd->vdev_spa;
zio_t *fio;
uint64_t delta;
@@ -3306,7 +3306,7 @@ vdev_deadman(vdev_t *vd)
* if any I/O has been outstanding for longer than
* the spa_deadman_synctime we log a zevent.
*/
- fio = avl_first(&vq->vq_pending_tree);
+ fio = avl_first(&vq->vq_active_tree);
delta = gethrtime() - fio->io_timestamp;
if (delta > spa_deadman_synctime(spa)) {
zfs_dbgmsg("SLOW IO: zio timestamp %lluns, "
diff --git a/module/zfs/vdev_cache.c b/module/zfs/vdev_cache.c
index 6d0cb967d..ec215ffa5 100644
--- a/module/zfs/vdev_cache.c
+++ b/module/zfs/vdev_cache.c
@@ -312,7 +312,7 @@ vdev_cache_read(zio_t *zio)
}
fio = zio_vdev_delegated_io(zio->io_vd, cache_offset,
- ve->ve_data, VCBS, ZIO_TYPE_READ, ZIO_PRIORITY_CACHE_FILL,
+ ve->ve_data, VCBS, ZIO_TYPE_READ, ZIO_PRIORITY_NOW,
ZIO_FLAG_DONT_CACHE, vdev_cache_fill, ve);
ve->ve_fill_io = fio;
diff --git a/module/zfs/vdev_mirror.c b/module/zfs/vdev_mirror.c
index 42f7c9713..99b35f085 100644
--- a/module/zfs/vdev_mirror.c
+++ b/module/zfs/vdev_mirror.c
@@ -89,7 +89,7 @@ static const zio_vsd_ops_t vdev_mirror_vsd_ops = {
static int
vdev_mirror_pending(vdev_t *vd)
{
- return (avl_numnodes(&vd->vdev_queue.vq_pending_tree));
+ return (avl_numnodes(&vd->vdev_queue.vq_active_tree));
}
/*
@@ -499,7 +499,7 @@ vdev_mirror_io_done(zio_t *zio)
zio_nowait(zio_vdev_child_io(zio, zio->io_bp,
mc->mc_vd, mc->mc_offset,
zio->io_data, zio->io_size,
- ZIO_TYPE_WRITE, zio->io_priority,
+ ZIO_TYPE_WRITE, ZIO_PRIORITY_ASYNC_WRITE,
ZIO_FLAG_IO_REPAIR | (unexpected_errors ?
ZIO_FLAG_SELF_HEAL : 0), NULL, NULL));
}
diff --git a/module/zfs/vdev_queue.c b/module/zfs/vdev_queue.c
index 06a641087..2e1f098a1 100644
--- a/module/zfs/vdev_queue.c
+++ b/module/zfs/vdev_queue.c
@@ -24,7 +24,7 @@
*/
/*
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2013 by Delphix. All rights reserved.
*/
#include <sys/zfs_context.h>
@@ -32,29 +32,134 @@
#include <sys/spa_impl.h>
#include <sys/zio.h>
#include <sys/avl.h>
+#include <sys/dsl_pool.h>
+#include <sys/spa.h>
+#include <sys/spa_impl.h>
#include <sys/kstat.h>
/*
- * These tunables are for performance analysis.
+ * ZFS I/O Scheduler
+ * ---------------
+ *
+ * ZFS issues I/O operations to leaf vdevs to satisfy and complete zios. The
+ * I/O scheduler determines when and in what order those operations are
+ * issued. The I/O scheduler divides operations into five I/O classes
+ * prioritized in the following order: sync read, sync write, async read,
+ * async write, and scrub/resilver. Each queue defines the minimum and
+ * maximum number of concurrent operations that may be issued to the device.
+ * In addition, the device has an aggregate maximum. Note that the sum of the
+ * per-queue minimums must not exceed the aggregate maximum. If the
+ * sum of the per-queue maximums exceeds the aggregate maximum, then the
+ * number of active i/os may reach zfs_vdev_max_active, in which case no
+ * further i/os will be issued regardless of whether all per-queue
+ * minimums have been met.
+ *
+ * For many physical devices, throughput increases with the number of
+ * concurrent operations, but latency typically suffers. Further, physical
+ * devices typically have a limit at which more concurrent operations have no
+ * effect on throughput or can actually cause it to decrease.
+ *
+ * The scheduler selects the next operation to issue by first looking for an
+ * I/O class whose minimum has not been satisfied. Once all are satisfied and
+ * the aggregate maximum has not been hit, the scheduler looks for classes
+ * whose maximum has not been satisfied. Iteration through the I/O classes is
+ * done in the order specified above. No further operations are issued if the
+ * aggregate maximum number of concurrent operations has been hit or if there
+ * are no operations queued for an I/O class that has not hit its maximum.
+ * Every time an i/o is queued or an operation completes, the I/O scheduler
+ * looks for new operations to issue.
+ *
+ * All I/O classes have a fixed maximum number of outstanding operations
+ * except for the async write class. Asynchronous writes represent the data
+ * that is committed to stable storage during the syncing stage for
+ * transaction groups (see txg.c). Transaction groups enter the syncing state
+ * periodically so the number of queued async writes will quickly burst up and
+ * then bleed down to zero. Rather than servicing them as quickly as possible,
+ * the I/O scheduler changes the maximum number of active async write i/os
+ * according to the amount of dirty data in the pool (see dsl_pool.c). Since
+ * both throughput and latency typically increase with the number of
+ * concurrent operations issued to physical devices, reducing the burstiness
+ * in the number of concurrent operations also stabilizes the response time of
+ * operations from other -- and in particular synchronous -- queues. In broad
+ * strokes, the I/O scheduler will issue more concurrent operations from the
+ * async write queue as there's more dirty data in the pool.
+ *
+ * Async Writes
+ *
+ * The number of concurrent operations issued for the async write I/O class
+ * follows a piece-wise linear function defined by a few adjustable points.
+ *
+ * | o---------| <-- zfs_vdev_async_write_max_active
+ * ^ | /^ |
+ * | | / | |
+ * active | / | |
+ * I/O | / | |
+ * count | / | |
+ * | / | |
+ * |------------o | | <-- zfs_vdev_async_write_min_active
+ * 0|____________^______|_________|
+ * 0% | | 100% of zfs_dirty_data_max
+ * | |
+ * | `-- zfs_vdev_async_write_active_max_dirty_percent
+ * `--------- zfs_vdev_async_write_active_min_dirty_percent
+ *
+ * Until the amount of dirty data exceeds a minimum percentage of the dirty
+ * data allowed in the pool, the I/O scheduler will limit the number of
+ * concurrent operations to the minimum. As that threshold is crossed, the
+ * number of concurrent operations issued increases linearly to the maximum at
+ * the specified maximum percentage of the dirty data allowed in the pool.
+ *
+ * Ideally, the amount of dirty data on a busy pool will stay in the sloped
+ * part of the function between zfs_vdev_async_write_active_min_dirty_percent
+ * and zfs_vdev_async_write_active_max_dirty_percent. If it exceeds the
+ * maximum percentage, this indicates that the rate of incoming data is
+ * greater than the rate that the backend storage can handle. In this case, we
+ * must further throttle incoming writes (see dmu_tx_delay() for details).
*/
-/* The maximum number of I/Os concurrently pending to each device. */
-int zfs_vdev_max_pending = 10;
-
/*
- * The initial number of I/Os pending to each device, before it starts ramping
- * up to zfs_vdev_max_pending.
+ * The maximum number of i/os active to each device. Ideally, this will be >=
+ * the sum of each queue's max_active. It must be at least the sum of each
+ * queue's min_active.
*/
-int zfs_vdev_min_pending = 4;
+uint32_t zfs_vdev_max_active = 1000;
/*
- * The deadlines are grouped into buckets based on zfs_vdev_time_shift:
- * deadline = pri + gethrtime() >> time_shift)
+ * Per-queue limits on the number of i/os active to each device. If the
+ * number of active i/os is < zfs_vdev_max_active, then the min_active comes
+ * into play. We will send min_active from each queue, and then select from
+ * queues in the order defined by zio_priority_t.
+ *
+ * In general, smaller max_active's will lead to lower latency of synchronous
+ * operations. Larger max_active's may lead to higher overall throughput,
+ * depending on underlying storage.
+ *
+ * The ratio of the queues' max_actives determines the balance of performance
+ * between reads, writes, and scrubs. E.g., increasing
+ * zfs_vdev_scrub_max_active will cause the scrub or resilver to complete
+ * more quickly, but reads and writes to have higher latency and lower
+ * throughput.
*/
-int zfs_vdev_time_shift = 29; /* each bucket is 0.537 seconds */
+uint32_t zfs_vdev_sync_read_min_active = 10;
+uint32_t zfs_vdev_sync_read_max_active = 10;
+uint32_t zfs_vdev_sync_write_min_active = 10;
+uint32_t zfs_vdev_sync_write_max_active = 10;
+uint32_t zfs_vdev_async_read_min_active = 1;
+uint32_t zfs_vdev_async_read_max_active = 3;
+uint32_t zfs_vdev_async_write_min_active = 1;
+uint32_t zfs_vdev_async_write_max_active = 10;
+uint32_t zfs_vdev_scrub_min_active = 1;
+uint32_t zfs_vdev_scrub_max_active = 2;
-/* exponential I/O issue ramp-up rate */
-int zfs_vdev_ramp_rate = 2;
+/*
+ * When the pool has less than zfs_vdev_async_write_active_min_dirty_percent
+ * dirty data, use zfs_vdev_async_write_min_active. When it has more than
+ * zfs_vdev_async_write_active_max_dirty_percent, use
+ * zfs_vdev_async_write_max_active. The value is linearly interpolated
+ * between min and max.
+ */
+int zfs_vdev_async_write_active_min_dirty_percent = 30;
+int zfs_vdev_async_write_active_max_dirty_percent = 60;
/*
* To reduce IOPs, we aggregate small adjacent I/Os into one large I/O.
@@ -66,20 +171,12 @@ int zfs_vdev_aggregation_limit = SPA_MAXBLOCKSIZE;
int zfs_vdev_read_gap_limit = 32 << 10;
int zfs_vdev_write_gap_limit = 4 << 10;
-/*
- * Virtual device vector for disk I/O scheduling.
- */
int
-vdev_queue_deadline_compare(const void *x1, const void *x2)
+vdev_queue_offset_compare(const void *x1, const void *x2)
{
const zio_t *z1 = x1;
const zio_t *z2 = x2;
- if (z1->io_deadline < z2->io_deadline)
- return (-1);
- if (z1->io_deadline > z2->io_deadline)
- return (1);
-
if (z1->io_offset < z2->io_offset)
return (-1);
if (z1->io_offset > z2->io_offset)
@@ -94,14 +191,14 @@ vdev_queue_deadline_compare(const void *x1, const void *x2)
}
int
-vdev_queue_offset_compare(const void *x1, const void *x2)
+vdev_queue_timestamp_compare(const void *x1, const void *x2)
{
const zio_t *z1 = x1;
const zio_t *z2 = x2;
- if (z1->io_offset < z2->io_offset)
+ if (z1->io_timestamp < z2->io_timestamp)
return (-1);
- if (z1->io_offset > z2->io_offset)
+ if (z1->io_timestamp > z2->io_timestamp)
return (1);
if (z1 < z2)
@@ -112,25 +209,141 @@ vdev_queue_offset_compare(const void *x1, const void *x2)
return (0);
}
+static int
+vdev_queue_class_min_active(zio_priority_t p)
+{
+ switch (p) {
+ case ZIO_PRIORITY_SYNC_READ:
+ return (zfs_vdev_sync_read_min_active);
+ case ZIO_PRIORITY_SYNC_WRITE:
+ return (zfs_vdev_sync_write_min_active);
+ case ZIO_PRIORITY_ASYNC_READ:
+ return (zfs_vdev_async_read_min_active);
+ case ZIO_PRIORITY_ASYNC_WRITE:
+ return (zfs_vdev_async_write_min_active);
+ case ZIO_PRIORITY_SCRUB:
+ return (zfs_vdev_scrub_min_active);
+ default:
+ panic("invalid priority %u", p);
+ return (0);
+ }
+}
+
+static int
+vdev_queue_max_async_writes(uint64_t dirty)
+{
+ int writes;
+ uint64_t min_bytes = zfs_dirty_data_max *
+ zfs_vdev_async_write_active_min_dirty_percent / 100;
+ uint64_t max_bytes = zfs_dirty_data_max *
+ zfs_vdev_async_write_active_max_dirty_percent / 100;
+
+ if (dirty < min_bytes)
+ return (zfs_vdev_async_write_min_active);
+ if (dirty > max_bytes)
+ return (zfs_vdev_async_write_max_active);
+
+ /*
+ * linear interpolation:
+ * slope = (max_writes - min_writes) / (max_bytes - min_bytes)
+ * move right by min_bytes
+ * move up by min_writes
+ */
+ writes = (dirty - min_bytes) *
+ (zfs_vdev_async_write_max_active -
+ zfs_vdev_async_write_min_active) /
+ (max_bytes - min_bytes) +
+ zfs_vdev_async_write_min_active;
+ ASSERT3U(writes, >=, zfs_vdev_async_write_min_active);
+ ASSERT3U(writes, <=, zfs_vdev_async_write_max_active);
+ return (writes);
+}
+
+static int
+vdev_queue_class_max_active(spa_t *spa, zio_priority_t p)
+{
+ switch (p) {
+ case ZIO_PRIORITY_SYNC_READ:
+ return (zfs_vdev_sync_read_max_active);
+ case ZIO_PRIORITY_SYNC_WRITE:
+ return (zfs_vdev_sync_write_max_active);
+ case ZIO_PRIORITY_ASYNC_READ:
+ return (zfs_vdev_async_read_max_active);
+ case ZIO_PRIORITY_ASYNC_WRITE:
+ return (vdev_queue_max_async_writes(
+ spa->spa_dsl_pool->dp_dirty_total));
+ case ZIO_PRIORITY_SCRUB:
+ return (zfs_vdev_scrub_max_active);
+ default:
+ panic("invalid priority %u", p);
+ return (0);
+ }
+}
+
+/*
+ * Return the i/o class to issue from, or ZIO_PRIORITY_MAX_QUEUEABLE if
+ * there is no eligible class.
+ */
+static zio_priority_t
+vdev_queue_class_to_issue(vdev_queue_t *vq)
+{
+ spa_t *spa = vq->vq_vdev->vdev_spa;
+ zio_priority_t p;
+
+ if (avl_numnodes(&vq->vq_active_tree) >= zfs_vdev_max_active)
+ return (ZIO_PRIORITY_NUM_QUEUEABLE);
+
+ /* find a queue that has not reached its minimum # outstanding i/os */
+ for (p = 0; p < ZIO_PRIORITY_NUM_QUEUEABLE; p++) {
+ if (avl_numnodes(&vq->vq_class[p].vqc_queued_tree) > 0 &&
+ vq->vq_class[p].vqc_active <
+ vdev_queue_class_min_active(p))
+ return (p);
+ }
+
+ /*
+ * If we haven't found a queue, look for one that hasn't reached its
+ * maximum # outstanding i/os.
+ */
+ for (p = 0; p < ZIO_PRIORITY_NUM_QUEUEABLE; p++) {
+ if (avl_numnodes(&vq->vq_class[p].vqc_queued_tree) > 0 &&
+ vq->vq_class[p].vqc_active <
+ vdev_queue_class_max_active(spa, p))
+ return (p);
+ }
+
+ /* No eligible queued i/os */
+ return (ZIO_PRIORITY_NUM_QUEUEABLE);
+}
+
void
vdev_queue_init(vdev_t *vd)
{
vdev_queue_t *vq = &vd->vdev_queue;
+ int max_active_sum;
+ zio_priority_t p;
int i;
mutex_init(&vq->vq_lock, NULL, MUTEX_DEFAULT, NULL);
+ vq->vq_vdev = vd;
- avl_create(&vq->vq_deadline_tree, vdev_queue_deadline_compare,
- sizeof (zio_t), offsetof(struct zio, io_deadline_node));
-
- avl_create(&vq->vq_read_tree, vdev_queue_offset_compare,
- sizeof (zio_t), offsetof(struct zio, io_offset_node));
-
- avl_create(&vq->vq_write_tree, vdev_queue_offset_compare,
- sizeof (zio_t), offsetof(struct zio, io_offset_node));
+ avl_create(&vq->vq_active_tree, vdev_queue_offset_compare,
+ sizeof (zio_t), offsetof(struct zio, io_queue_node));
- avl_create(&vq->vq_pending_tree, vdev_queue_offset_compare,
- sizeof (zio_t), offsetof(struct zio, io_offset_node));
+ for (p = 0; p < ZIO_PRIORITY_NUM_QUEUEABLE; p++) {
+ /*
+ * The synchronous i/o queues are FIFO rather than LBA ordered.
+ * This provides more consistent latency for these i/os, and
+ * they tend to not be tightly clustered anyway so there is
+ * little to no throughput loss.
+ */
+ boolean_t fifo = (p == ZIO_PRIORITY_SYNC_READ ||
+ p == ZIO_PRIORITY_SYNC_WRITE);
+ avl_create(&vq->vq_class[p].vqc_queued_tree,
+ fifo ? vdev_queue_timestamp_compare :
+ vdev_queue_offset_compare,
+ sizeof (zio_t), offsetof(struct zio, io_queue_node));
+ }
/*
* A list of buffers which can be used for aggregate I/O, this
@@ -139,7 +352,10 @@ vdev_queue_init(vdev_t *vd)
list_create(&vq->vq_io_list, sizeof (vdev_io_t),
offsetof(vdev_io_t, vi_node));
- for (i = 0; i < zfs_vdev_max_pending; i++)
+ max_active_sum = zfs_vdev_sync_read_max_active +
+ zfs_vdev_sync_write_max_active + zfs_vdev_async_read_max_active +
+ zfs_vdev_async_write_max_active + zfs_vdev_scrub_max_active;
+ for (i = 0; i < max_active_sum; i++)
list_insert_tail(&vq->vq_io_list, zio_vdev_alloc());
}
@@ -148,11 +364,11 @@ vdev_queue_fini(vdev_t *vd)
{
vdev_queue_t *vq = &vd->vdev_queue;
vdev_io_t *vi;
+ zio_priority_t p;
- avl_destroy(&vq->vq_deadline_tree);
- avl_destroy(&vq->vq_read_tree);
- avl_destroy(&vq->vq_write_tree);
- avl_destroy(&vq->vq_pending_tree);
+ for (p = 0; p < ZIO_PRIORITY_NUM_QUEUEABLE; p++)
+ avl_destroy(&vq->vq_class[p].vqc_queued_tree);
+ avl_destroy(&vq->vq_active_tree);
while ((vi = list_head(&vq->vq_io_list)) != NULL) {
list_remove(&vq->vq_io_list, vi);
@@ -170,8 +386,8 @@ vdev_queue_io_add(vdev_queue_t *vq, zio_t *zio)
spa_t *spa = zio->io_spa;
spa_stats_history_t *ssh = &spa->spa_stats.io_history;
- avl_add(&vq->vq_deadline_tree, zio);
- avl_add(zio->io_vdev_tree, zio);
+ ASSERT3U(zio->io_priority, <, ZIO_PRIORITY_NUM_QUEUEABLE);
+ avl_add(&vq->vq_class[zio->io_priority].vqc_queued_tree, zio);
if (ssh->kstat != NULL) {
mutex_enter(&ssh->lock);
@@ -186,8 +402,8 @@ vdev_queue_io_remove(vdev_queue_t *vq, zio_t *zio)
spa_t *spa = zio->io_spa;
spa_stats_history_t *ssh = &spa->spa_stats.io_history;
- avl_remove(&vq->vq_deadline_tree, zio);
- avl_remove(zio->io_vdev_tree, zio);
+ ASSERT3U(zio->io_priority, <, ZIO_PRIORITY_NUM_QUEUEABLE);
+ avl_remove(&vq->vq_class[zio->io_priority].vqc_queued_tree, zio);
if (ssh->kstat != NULL) {
mutex_enter(&ssh->lock);
@@ -202,7 +418,10 @@ vdev_queue_pending_add(vdev_queue_t *vq, zio_t *zio)
spa_t *spa = zio->io_spa;
spa_stats_history_t *ssh = &spa->spa_stats.io_history;
- avl_add(&vq->vq_pending_tree, zio);
+ ASSERT(MUTEX_HELD(&vq->vq_lock));
+ ASSERT3U(zio->io_priority, <, ZIO_PRIORITY_NUM_QUEUEABLE);
+ vq->vq_class[zio->io_priority].vqc_active++;
+ avl_add(&vq->vq_active_tree, zio);
if (ssh->kstat != NULL) {
mutex_enter(&ssh->lock);
@@ -217,7 +436,10 @@ vdev_queue_pending_remove(vdev_queue_t *vq, zio_t *zio)
spa_t *spa = zio->io_spa;
spa_stats_history_t *ssh = &spa->spa_stats.io_history;
- avl_remove(&vq->vq_pending_tree, zio);
+ ASSERT(MUTEX_HELD(&vq->vq_lock));
+ ASSERT3U(zio->io_priority, <, ZIO_PRIORITY_NUM_QUEUEABLE);
+ vq->vq_class[zio->io_priority].vqc_active--;
+ avl_remove(&vq->vq_active_tree, zio);
if (ssh->kstat != NULL) {
kstat_io_t *ksio = ssh->kstat->ks_data;
@@ -240,12 +462,14 @@ vdev_queue_agg_io_done(zio_t *aio)
{
vdev_queue_t *vq = &aio->io_vd->vdev_queue;
vdev_io_t *vi = aio->io_data;
- zio_t *pio;
- while ((pio = zio_walk_parents(aio)) != NULL)
- if (aio->io_type == ZIO_TYPE_READ)
+ if (aio->io_type == ZIO_TYPE_READ) {
+ zio_t *pio;
+ while ((pio = zio_walk_parents(aio)) != NULL) {
bcopy((char *)aio->io_data + (pio->io_offset -
aio->io_offset), pio->io_data, pio->io_size);
+ }
+ }
mutex_enter(&vq->vq_lock);
list_insert_tail(&vq->vq_io_list, vi);
@@ -262,28 +486,38 @@ vdev_queue_agg_io_done(zio_t *aio)
#define IO_GAP(fio, lio) (-IO_SPAN(lio, fio))
static zio_t *
-vdev_queue_io_to_issue(vdev_queue_t *vq, uint64_t pending_limit)
+vdev_queue_aggregate(vdev_queue_t *vq, zio_t *zio)
{
- zio_t *fio, *lio, *aio, *dio, *nio, *mio;
- avl_tree_t *t;
vdev_io_t *vi;
- int flags;
- uint64_t maxspan = MIN(zfs_vdev_aggregation_limit, SPA_MAXBLOCKSIZE);
- uint64_t maxgap;
- int stretch;
+ zio_t *first, *last, *aio, *dio, *mandatory, *nio;
+ uint64_t maxgap = 0;
+ uint64_t size;
+ boolean_t stretch = B_FALSE;
+ vdev_queue_class_t *vqc = &vq->vq_class[zio->io_priority];
+ avl_tree_t *t = &vqc->vqc_queued_tree;
+ enum zio_flag flags = zio->io_flags & ZIO_FLAG_AGG_INHERIT;
+
+ if (zio->io_flags & ZIO_FLAG_DONT_AGGREGATE)
+ return (NULL);
-again:
- ASSERT(MUTEX_HELD(&vq->vq_lock));
+ /* Prevent users from setting the zfs_vdev_aggregation_limit
+ * tuning larger than SPA_MAXBLOCKSIZE. */
+ zfs_vdev_aggregation_limit =
+ MIN(zfs_vdev_aggregation_limit, SPA_MAXBLOCKSIZE);
- if (avl_numnodes(&vq->vq_pending_tree) >= pending_limit ||
- avl_numnodes(&vq->vq_deadline_tree) == 0)
+ /*
+ * The synchronous i/o queues are not sorted by LBA, so we can't
+ * find adjacent i/os. These i/os tend to not be tightly clustered,
+ * or too large to aggregate, so this has little impact on performance.
+ */
+ if (zio->io_priority == ZIO_PRIORITY_SYNC_READ ||
+ zio->io_priority == ZIO_PRIORITY_SYNC_WRITE)
return (NULL);
- fio = lio = avl_first(&vq->vq_deadline_tree);
+ first = last = zio;
- t = fio->io_vdev_tree;
- flags = fio->io_flags & ZIO_FLAG_AGG_INHERIT;
- maxgap = (t == &vq->vq_read_tree) ? zfs_vdev_read_gap_limit : 0;
+ if (zio->io_type == ZIO_TYPE_READ)
+ maxgap = zfs_vdev_read_gap_limit;
vi = list_head(&vq->vq_io_list);
if (vi == NULL) {
@@ -291,134 +525,172 @@ again:
list_insert_head(&vq->vq_io_list, vi);
}
- if (!(flags & ZIO_FLAG_DONT_AGGREGATE)) {
- /*
- * We can aggregate I/Os that are sufficiently adjacent and of
- * the same flavor, as expressed by the AGG_INHERIT flags.
- * The latter requirement is necessary so that certain
- * attributes of the I/O, such as whether it's a normal I/O
- * or a scrub/resilver, can be preserved in the aggregate.
- * We can include optional I/Os, but don't allow them
- * to begin a range as they add no benefit in that situation.
- */
+ /*
+ * We can aggregate I/Os that are sufficiently adjacent and of
+ * the same flavor, as expressed by the AGG_INHERIT flags.
+ * The latter requirement is necessary so that certain
+ * attributes of the I/O, such as whether it's a normal I/O
+ * or a scrub/resilver, can be preserved in the aggregate.
+ * We can include optional I/Os, but don't allow them
+ * to begin a range as they add no benefit in that situation.
+ */
- /*
- * We keep track of the last non-optional I/O.
- */
- mio = (fio->io_flags & ZIO_FLAG_OPTIONAL) ? NULL : fio;
+ /*
+ * We keep track of the last non-optional I/O.
+ */
+ mandatory = (first->io_flags & ZIO_FLAG_OPTIONAL) ? NULL : first;
- /*
- * Walk backwards through sufficiently contiguous I/Os
- * recording the last non-option I/O.
- */
- while ((dio = AVL_PREV(t, fio)) != NULL &&
- (dio->io_flags & ZIO_FLAG_AGG_INHERIT) == flags &&
- IO_SPAN(dio, lio) <= maxspan &&
- IO_GAP(dio, fio) <= maxgap) {
- fio = dio;
- if (mio == NULL && !(fio->io_flags & ZIO_FLAG_OPTIONAL))
- mio = fio;
- }
+ /*
+ * Walk backwards through sufficiently contiguous I/Os
+ * recording the last non-option I/O.
+ */
+ while ((dio = AVL_PREV(t, first)) != NULL &&
+ (dio->io_flags & ZIO_FLAG_AGG_INHERIT) == flags &&
+ IO_SPAN(dio, last) <= zfs_vdev_aggregation_limit &&
+ IO_GAP(dio, first) <= maxgap) {
+ first = dio;
+ if (mandatory == NULL && !(first->io_flags & ZIO_FLAG_OPTIONAL))
+ mandatory = first;
+ }
- /*
- * Skip any initial optional I/Os.
- */
- while ((fio->io_flags & ZIO_FLAG_OPTIONAL) && fio != lio) {
- fio = AVL_NEXT(t, fio);
- ASSERT(fio != NULL);
- }
+ /*
+ * Skip any initial optional I/Os.
+ */
+ while ((first->io_flags & ZIO_FLAG_OPTIONAL) && first != last) {
+ first = AVL_NEXT(t, first);
+ ASSERT(first != NULL);
+ }
- /*
- * Walk forward through sufficiently contiguous I/Os.
- */
- while ((dio = AVL_NEXT(t, lio)) != NULL &&
- (dio->io_flags & ZIO_FLAG_AGG_INHERIT) == flags &&
- IO_SPAN(fio, dio) <= maxspan &&
- IO_GAP(lio, dio) <= maxgap) {
- lio = dio;
- if (!(lio->io_flags & ZIO_FLAG_OPTIONAL))
- mio = lio;
- }
- /*
- * Now that we've established the range of the I/O aggregation
- * we must decide what to do with trailing optional I/Os.
- * For reads, there's nothing to do. While we are unable to
- * aggregate further, it's possible that a trailing optional
- * I/O would allow the underlying device to aggregate with
- * subsequent I/Os. We must therefore determine if the next
- * non-optional I/O is close enough to make aggregation
- * worthwhile.
- */
- stretch = B_FALSE;
- if (t != &vq->vq_read_tree && mio != NULL) {
- nio = lio;
- while ((dio = AVL_NEXT(t, nio)) != NULL &&
- IO_GAP(nio, dio) == 0 &&
- IO_GAP(mio, dio) <= zfs_vdev_write_gap_limit) {
- nio = dio;
- if (!(nio->io_flags & ZIO_FLAG_OPTIONAL)) {
- stretch = B_TRUE;
- break;
- }
+ /*
+ * Walk forward through sufficiently contiguous I/Os.
+ */
+ while ((dio = AVL_NEXT(t, last)) != NULL &&
+ (dio->io_flags & ZIO_FLAG_AGG_INHERIT) == flags &&
+ IO_SPAN(first, dio) <= zfs_vdev_aggregation_limit &&
+ IO_GAP(last, dio) <= maxgap) {
+ last = dio;
+ if (!(last->io_flags & ZIO_FLAG_OPTIONAL))
+ mandatory = last;
+ }
+
+ /*
+ * Now that we've established the range of the I/O aggregation
+ * we must decide what to do with trailing optional I/Os.
+ * For reads, there's nothing to do. While we are unable to
+ * aggregate further, it's possible that a trailing optional
+ * I/O would allow the underlying device to aggregate with
+ * subsequent I/Os. We must therefore determine if the next
+ * non-optional I/O is close enough to make aggregation
+ * worthwhile.
+ */
+ if (zio->io_type == ZIO_TYPE_WRITE && mandatory != NULL) {
+ zio_t *nio = last;
+ while ((dio = AVL_NEXT(t, nio)) != NULL &&
+ IO_GAP(nio, dio) == 0 &&
+ IO_GAP(mandatory, dio) <= zfs_vdev_write_gap_limit) {
+ nio = dio;
+ if (!(nio->io_flags & ZIO_FLAG_OPTIONAL)) {
+ stretch = B_TRUE;
+ break;
}
}
+ }
- if (stretch) {
- /* This may be a no-op. */
- VERIFY((dio = AVL_NEXT(t, lio)) != NULL);
- dio->io_flags &= ~ZIO_FLAG_OPTIONAL;
- } else {
- while (lio != mio && lio != fio) {
- ASSERT(lio->io_flags & ZIO_FLAG_OPTIONAL);
- lio = AVL_PREV(t, lio);
- ASSERT(lio != NULL);
- }
+ if (stretch) {
+ /* This may be a no-op. */
+ dio = AVL_NEXT(t, last);
+ dio->io_flags &= ~ZIO_FLAG_OPTIONAL;
+ } else {
+ while (last != mandatory && last != first) {
+ ASSERT(last->io_flags & ZIO_FLAG_OPTIONAL);
+ last = AVL_PREV(t, last);
+ ASSERT(last != NULL);
}
}
- if (fio != lio) {
- uint64_t size = IO_SPAN(fio, lio);
- ASSERT(size <= maxspan);
- ASSERT(vi != NULL);
-
- aio = zio_vdev_delegated_io(fio->io_vd, fio->io_offset,
- vi, size, fio->io_type, ZIO_PRIORITY_AGG,
- flags | ZIO_FLAG_DONT_CACHE | ZIO_FLAG_DONT_QUEUE,
- vdev_queue_agg_io_done, NULL);
- aio->io_timestamp = fio->io_timestamp;
-
- nio = fio;
- do {
- dio = nio;
- nio = AVL_NEXT(t, dio);
- ASSERT(dio->io_type == aio->io_type);
- ASSERT(dio->io_vdev_tree == t);
-
- if (dio->io_flags & ZIO_FLAG_NODATA) {
- ASSERT(dio->io_type == ZIO_TYPE_WRITE);
- bzero((char *)aio->io_data + (dio->io_offset -
- aio->io_offset), dio->io_size);
- } else if (dio->io_type == ZIO_TYPE_WRITE) {
- bcopy(dio->io_data, (char *)aio->io_data +
- (dio->io_offset - aio->io_offset),
- dio->io_size);
- }
+ if (first == last)
+ return (NULL);
+
+ ASSERT(vi != NULL);
+
+ size = IO_SPAN(first, last);
+ ASSERT3U(size, <=, zfs_vdev_aggregation_limit);
+
+ aio = zio_vdev_delegated_io(first->io_vd, first->io_offset,
+ vi, size, first->io_type, zio->io_priority,
+ flags | ZIO_FLAG_DONT_CACHE | ZIO_FLAG_DONT_QUEUE,
+ vdev_queue_agg_io_done, NULL);
+ aio->io_timestamp = first->io_timestamp;
+
+ nio = first;
+ do {
+ dio = nio;
+ nio = AVL_NEXT(t, dio);
+ ASSERT3U(dio->io_type, ==, aio->io_type);
+
+ if (dio->io_flags & ZIO_FLAG_NODATA) {
+ ASSERT3U(dio->io_type, ==, ZIO_TYPE_WRITE);
+ bzero((char *)aio->io_data + (dio->io_offset -
+ aio->io_offset), dio->io_size);
+ } else if (dio->io_type == ZIO_TYPE_WRITE) {
+ bcopy(dio->io_data, (char *)aio->io_data +
+ (dio->io_offset - aio->io_offset),
+ dio->io_size);
+ }
- zio_add_child(dio, aio);
- vdev_queue_io_remove(vq, dio);
- zio_vdev_io_bypass(dio);
- zio_execute(dio);
- } while (dio != lio);
+ zio_add_child(dio, aio);
+ vdev_queue_io_remove(vq, dio);
+ zio_vdev_io_bypass(dio);
+ zio_execute(dio);
+ } while (dio != last);
- vdev_queue_pending_add(vq, aio);
- list_remove(&vq->vq_io_list, vi);
+ list_remove(&vq->vq_io_list, vi);
+
+ return (aio);
+}
+
+static zio_t *
+vdev_queue_io_to_issue(vdev_queue_t *vq)
+{
+ zio_t *zio, *aio;
+ zio_priority_t p;
+ avl_index_t idx;
+ vdev_queue_class_t *vqc;
+ zio_t *search;
+
+again:
+ ASSERT(MUTEX_HELD(&vq->vq_lock));
+
+ p = vdev_queue_class_to_issue(vq);
- return (aio);
+ if (p == ZIO_PRIORITY_NUM_QUEUEABLE) {
+ /* No eligible queued i/os */
+ return (NULL);
}
- ASSERT(fio->io_vdev_tree == t);
- vdev_queue_io_remove(vq, fio);
+ /*
+ * For LBA-ordered queues (async / scrub), issue the i/o which follows
+ * the most recently issued i/o in LBA (offset) order.
+ *
+ * For FIFO queues (sync), issue the i/o with the lowest timestamp.
+ */
+ vqc = &vq->vq_class[p];
+ search = zio_buf_alloc(sizeof(*search));
+ search->io_timestamp = 0;
+ search->io_offset = vq->vq_last_offset + 1;
+ VERIFY3P(avl_find(&vqc->vqc_queued_tree, search, &idx), ==, NULL);
+ zio_buf_free(search, sizeof(*search));
+ zio = avl_nearest(&vqc->vqc_queued_tree, idx, AVL_AFTER);
+ if (zio == NULL)
+ zio = avl_first(&vqc->vqc_queued_tree);
+ ASSERT3U(zio->io_priority, ==, p);
+
+ aio = vdev_queue_aggregate(vq, zio);
+ if (aio != NULL)
+ zio = aio;
+ else
+ vdev_queue_io_remove(vq, zio);
/*
* If the I/O is or was optional and therefore has no data, we need to
@@ -426,17 +698,18 @@ again:
* deadlock that we could encounter since this I/O will complete
* immediately.
*/
- if (fio->io_flags & ZIO_FLAG_NODATA) {
+ if (zio->io_flags & ZIO_FLAG_NODATA) {
mutex_exit(&vq->vq_lock);
- zio_vdev_io_bypass(fio);
- zio_execute(fio);
+ zio_vdev_io_bypass(zio);
+ zio_execute(zio);
mutex_enter(&vq->vq_lock);
goto again;
}
- vdev_queue_pending_add(vq, fio);
+ vdev_queue_pending_add(vq, zio);
+ vq->vq_last_offset = zio->io_offset;
- return (fio);
+ return (zio);
}
zio_t *
@@ -445,28 +718,31 @@ vdev_queue_io(zio_t *zio)
vdev_queue_t *vq = &zio->io_vd->vdev_queue;
zio_t *nio;
- ASSERT(zio->io_type == ZIO_TYPE_READ || zio->io_type == ZIO_TYPE_WRITE);
-
if (zio->io_flags & ZIO_FLAG_DONT_QUEUE)
return (zio);
- zio->io_flags |= ZIO_FLAG_DONT_CACHE | ZIO_FLAG_DONT_QUEUE;
+ /*
+ * Children i/os inherent their parent's priority, which might
+ * not match the child's i/o type. Fix it up here.
+ */
+ if (zio->io_type == ZIO_TYPE_READ) {
+ if (zio->io_priority != ZIO_PRIORITY_SYNC_READ &&
+ zio->io_priority != ZIO_PRIORITY_ASYNC_READ &&
+ zio->io_priority != ZIO_PRIORITY_SCRUB)
+ zio->io_priority = ZIO_PRIORITY_ASYNC_READ;
+ } else {
+ ASSERT(zio->io_type == ZIO_TYPE_WRITE);
+ if (zio->io_priority != ZIO_PRIORITY_SYNC_WRITE &&
+ zio->io_priority != ZIO_PRIORITY_ASYNC_WRITE)
+ zio->io_priority = ZIO_PRIORITY_ASYNC_WRITE;
+ }
- if (zio->io_type == ZIO_TYPE_READ)
- zio->io_vdev_tree = &vq->vq_read_tree;
- else
- zio->io_vdev_tree = &vq->vq_write_tree;
+ zio->io_flags |= ZIO_FLAG_DONT_CACHE | ZIO_FLAG_DONT_QUEUE;
mutex_enter(&vq->vq_lock);
-
zio->io_timestamp = gethrtime();
- zio->io_deadline = (zio->io_timestamp >> zfs_vdev_time_shift) +
- zio->io_priority;
-
vdev_queue_io_add(vq, zio);
-
- nio = vdev_queue_io_to_issue(vq, zfs_vdev_min_pending);
-
+ nio = vdev_queue_io_to_issue(vq);
mutex_exit(&vq->vq_lock);
if (nio == NULL)
@@ -484,7 +760,7 @@ void
vdev_queue_io_done(zio_t *zio)
{
vdev_queue_t *vq = &zio->io_vd->vdev_queue;
- int i;
+ zio_t *nio;
if (zio_injection_enabled)
delay(SEC_TO_TICK(zio_handle_io_delay(zio)));
@@ -497,10 +773,7 @@ vdev_queue_io_done(zio_t *zio)
vq->vq_io_complete_ts = gethrtime();
vq->vq_io_delta_ts = vq->vq_io_complete_ts - zio->io_timestamp;
- for (i = 0; i < zfs_vdev_ramp_rate; i++) {
- zio_t *nio = vdev_queue_io_to_issue(vq, zfs_vdev_max_pending);
- if (nio == NULL)
- break;
+ while ((nio = vdev_queue_io_to_issue(vq)) != NULL) {
mutex_exit(&vq->vq_lock);
if (nio->io_done == vdev_queue_agg_io_done) {
zio_nowait(nio);
@@ -515,24 +788,61 @@ vdev_queue_io_done(zio_t *zio)
}
#if defined(_KERNEL) && defined(HAVE_SPL)
-module_param(zfs_vdev_max_pending, int, 0644);
-MODULE_PARM_DESC(zfs_vdev_max_pending, "Max pending per-vdev I/Os");
-
-module_param(zfs_vdev_min_pending, int, 0644);
-MODULE_PARM_DESC(zfs_vdev_min_pending, "Min pending per-vdev I/Os");
-
module_param(zfs_vdev_aggregation_limit, int, 0644);
MODULE_PARM_DESC(zfs_vdev_aggregation_limit, "Max vdev I/O aggregation size");
-module_param(zfs_vdev_time_shift, int, 0644);
-MODULE_PARM_DESC(zfs_vdev_time_shift, "Deadline time shift for vdev I/O");
-
-module_param(zfs_vdev_ramp_rate, int, 0644);
-MODULE_PARM_DESC(zfs_vdev_ramp_rate, "Exponential I/O issue ramp-up rate");
-
module_param(zfs_vdev_read_gap_limit, int, 0644);
MODULE_PARM_DESC(zfs_vdev_read_gap_limit, "Aggregate read I/O over gap");
module_param(zfs_vdev_write_gap_limit, int, 0644);
MODULE_PARM_DESC(zfs_vdev_write_gap_limit, "Aggregate write I/O over gap");
+
+module_param(zfs_vdev_max_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_max_active, "Maximum number of active I/Os per vdev");
+
+module_param(zfs_vdev_async_write_active_max_dirty_percent, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_async_write_active_max_dirty_percent,
+ "Async write concurrency max threshold");
+
+module_param(zfs_vdev_async_write_active_min_dirty_percent, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_async_write_active_min_dirty_percent,
+ "Async write concurrency min threshold");
+
+module_param(zfs_vdev_async_read_max_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_async_read_max_active,
+ "Max active async read I/Os per vdev");
+
+module_param(zfs_vdev_async_read_min_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_async_read_min_active,
+ "Min active async read I/Os per vdev");
+
+module_param(zfs_vdev_async_write_max_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_async_write_max_active,
+ "Max active async write I/Os per vdev");
+
+module_param(zfs_vdev_async_write_min_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_async_write_min_active,
+ "Min active async write I/Os per vdev");
+
+module_param(zfs_vdev_scrub_max_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_scrub_max_active, "Max active scrub I/Os per vdev");
+
+module_param(zfs_vdev_scrub_min_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_scrub_min_active, "Min active scrub I/Os per vdev");
+
+module_param(zfs_vdev_sync_read_max_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_sync_read_max_active,
+ "Max active sync read I/Os per vdev");
+
+module_param(zfs_vdev_sync_read_min_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_sync_read_min_active,
+ "Min active sync read I/Os per vdev");
+
+module_param(zfs_vdev_sync_write_max_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_sync_write_max_active,
+ "Max active sync write I/Os per vdev");
+
+module_param(zfs_vdev_sync_write_min_active, int, 0644);
+MODULE_PARM_DESC(zfs_vdev_sync_write_min_active,
+ "Min active sync write I/Osper vdev");
#endif
diff --git a/module/zfs/vdev_raidz.c b/module/zfs/vdev_raidz.c
index 9632e9af7..4cd21df89 100644
--- a/module/zfs/vdev_raidz.c
+++ b/module/zfs/vdev_raidz.c
@@ -2188,7 +2188,7 @@ done:
zio_nowait(zio_vdev_child_io(zio, NULL, cvd,
rc->rc_offset, rc->rc_data, rc->rc_size,
- ZIO_TYPE_WRITE, zio->io_priority,
+ ZIO_TYPE_WRITE, ZIO_PRIORITY_ASYNC_WRITE,
ZIO_FLAG_IO_REPAIR | (unexpected_errors ?
ZIO_FLAG_SELF_HEAL : 0), NULL, NULL));
}
diff --git a/module/zfs/zfs_fm.c b/module/zfs/zfs_fm.c
index af2030ae7..df47d99cf 100644
--- a/module/zfs/zfs_fm.c
+++ b/module/zfs/zfs_fm.c
@@ -316,8 +316,6 @@ zfs_ereport_start(nvlist_t **ereport_out, nvlist_t **detector_out,
DATA_TYPE_UINT64, zio->io_delay, NULL);
fm_payload_set(ereport, FM_EREPORT_PAYLOAD_ZFS_ZIO_TIMESTAMP,
DATA_TYPE_UINT64, zio->io_timestamp, NULL);
- fm_payload_set(ereport, FM_EREPORT_PAYLOAD_ZFS_ZIO_DEADLINE,
- DATA_TYPE_UINT64, zio->io_deadline, NULL);
fm_payload_set(ereport, FM_EREPORT_PAYLOAD_ZFS_ZIO_DELTA,
DATA_TYPE_UINT64, zio->io_delta, NULL);
diff --git a/module/zfs/zfs_vnops.c b/module/zfs/zfs_vnops.c
index 1552b61e0..6f25a6fff 100644
--- a/module/zfs/zfs_vnops.c
+++ b/module/zfs/zfs_vnops.c
@@ -125,7 +125,11 @@
* forever, because the previous txg can't quiesce until B's tx commits.
*
* If dmu_tx_assign() returns ERESTART and zsb->z_assign is TXG_NOWAIT,
- * then drop all locks, call dmu_tx_wait(), and try again.
+ * then drop all locks, call dmu_tx_wait(), and try again. On subsequent
+ * calls to dmu_tx_assign(), pass TXG_WAITED rather than TXG_NOWAIT,
+ * to indicate that this operation has already called dmu_tx_wait().
+ * This will ensure that we don't retry forever, waiting a short bit
+ * each time.
*
* (5) If the operation succeeded, generate the intent log entry for it
* before dropping locks. This ensures that the ordering of events
@@ -147,12 +151,13 @@
* rw_enter(...); // grab any other locks you need
* tx = dmu_tx_create(...); // get DMU tx
* dmu_tx_hold_*(); // hold each object you might modify
- * error = dmu_tx_assign(tx, TXG_NOWAIT); // try to assign
+ * error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
* if (error) {
* rw_exit(...); // drop locks
* zfs_dirent_unlock(dl); // unlock directory entry
* iput(...); // release held vnodes
* if (error == ERESTART) {
+ * waited = B_TRUE;
* dmu_tx_wait(tx);
* dmu_tx_abort(tx);
* goto top;
@@ -1279,6 +1284,7 @@ zfs_create(struct inode *dip, char *name, vattr_t *vap, int excl,
zfs_acl_ids_t acl_ids;
boolean_t fuid_dirtied;
boolean_t have_acl = B_FALSE;
+ boolean_t waited = B_FALSE;
/*
* If we have an ephemeral id, ACL, or XVATTR then
@@ -1391,10 +1397,11 @@ top:
dmu_tx_hold_write(tx, DMU_NEW_OBJECT,
0, acl_ids.z_aclp->z_acl_bytes);
}
- error = dmu_tx_assign(tx, TXG_NOWAIT);
+ error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
if (error) {
zfs_dirent_unlock(dl);
if (error == ERESTART) {
+ waited = B_TRUE;
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto top;
@@ -1524,6 +1531,7 @@ zfs_remove(struct inode *dip, char *name, cred_t *cr)
#endif /* HAVE_PN_UTILS */
int error;
int zflg = ZEXISTS;
+ boolean_t waited = B_FALSE;
ZFS_ENTER(zsb);
ZFS_VERIFY_ZP(dzp);
@@ -1599,13 +1607,14 @@ top:
/* charge as an update -- would be nice not to charge at all */
dmu_tx_hold_zap(tx, zsb->z_unlinkedobj, FALSE, NULL);
- error = dmu_tx_assign(tx, TXG_NOWAIT);
+ error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
if (error) {
zfs_dirent_unlock(dl);
iput(ip);
if (xzp)
iput(ZTOI(xzp));
if (error == ERESTART) {
+ waited = B_TRUE;
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto top;
@@ -1710,6 +1719,7 @@ zfs_mkdir(struct inode *dip, char *dirname, vattr_t *vap, struct inode **ipp,
gid_t gid = crgetgid(cr);
zfs_acl_ids_t acl_ids;
boolean_t fuid_dirtied;
+ boolean_t waited = B_FALSE;
ASSERT(S_ISDIR(vap->va_mode));
@@ -1801,10 +1811,11 @@ top:
dmu_tx_hold_sa_create(tx, acl_ids.z_aclp->z_acl_bytes +
ZFS_SA_BASE_ATTR_SIZE);
- error = dmu_tx_assign(tx, TXG_NOWAIT);
+ error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
if (error) {
zfs_dirent_unlock(dl);
if (error == ERESTART) {
+ waited = B_TRUE;
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto top;
@@ -1882,6 +1893,7 @@ zfs_rmdir(struct inode *dip, char *name, struct inode *cwd, cred_t *cr,
dmu_tx_t *tx;
int error;
int zflg = ZEXISTS;
+ boolean_t waited = B_FALSE;
ZFS_ENTER(zsb);
ZFS_VERIFY_ZP(dzp);
@@ -1935,13 +1947,14 @@ top:
dmu_tx_hold_zap(tx, zsb->z_unlinkedobj, FALSE, NULL);
zfs_sa_upgrade_txholds(tx, zp);
zfs_sa_upgrade_txholds(tx, dzp);
- error = dmu_tx_assign(tx, TXG_NOWAIT);
+ error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
if (error) {
rw_exit(&zp->z_parent_lock);
rw_exit(&zp->z_name_lock);
zfs_dirent_unlock(dl);
iput(ip);
if (error == ERESTART) {
+ waited = B_TRUE;
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto top;
@@ -3169,6 +3182,7 @@ zfs_rename(struct inode *sdip, char *snm, struct inode *tdip, char *tnm,
int cmp, serr, terr;
int error = 0;
int zflg = 0;
+ boolean_t waited = B_FALSE;
ZFS_ENTER(zsb);
ZFS_VERIFY_ZP(sdzp);
@@ -3383,7 +3397,7 @@ top:
zfs_sa_upgrade_txholds(tx, szp);
dmu_tx_hold_zap(tx, zsb->z_unlinkedobj, FALSE, NULL);
- error = dmu_tx_assign(tx, TXG_NOWAIT);
+ error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
if (error) {
if (zl != NULL)
zfs_rename_unlock(&zl);
@@ -3397,6 +3411,7 @@ top:
if (tzp)
iput(ZTOI(tzp));
if (error == ERESTART) {
+ waited = B_TRUE;
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto top;
@@ -3504,6 +3519,7 @@ zfs_symlink(struct inode *dip, char *name, vattr_t *vap, char *link,
zfs_acl_ids_t acl_ids;
boolean_t fuid_dirtied;
uint64_t txtype = TX_SYMLINK;
+ boolean_t waited = B_FALSE;
ASSERT(S_ISLNK(vap->va_mode));
@@ -3568,10 +3584,11 @@ top:
}
if (fuid_dirtied)
zfs_fuid_txhold(zsb, tx);
- error = dmu_tx_assign(tx, TXG_NOWAIT);
+ error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
if (error) {
zfs_dirent_unlock(dl);
if (error == ERESTART) {
+ waited = B_TRUE;
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto top;
@@ -3699,6 +3716,7 @@ zfs_link(struct inode *tdip, struct inode *sip, char *name, cred_t *cr)
int zf = ZNEW;
uint64_t parent;
uid_t owner;
+ boolean_t waited = B_FALSE;
ASSERT(S_ISDIR(tdip->i_mode));
@@ -3782,10 +3800,11 @@ top:
dmu_tx_hold_zap(tx, dzp->z_id, TRUE, name);
zfs_sa_upgrade_txholds(tx, szp);
zfs_sa_upgrade_txholds(tx, dzp);
- error = dmu_tx_assign(tx, TXG_NOWAIT);
+ error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
if (error) {
zfs_dirent_unlock(dl);
if (error == ERESTART) {
+ waited = B_TRUE;
dmu_tx_wait(tx);
dmu_tx_abort(tx);
goto top;
diff --git a/module/zfs/zil.c b/module/zfs/zil.c
index 839afa956..30035faa0 100644
--- a/module/zfs/zil.c
+++ b/module/zfs/zil.c
@@ -913,7 +913,7 @@ zil_lwb_write_init(zilog_t *zilog, lwb_t *lwb)
}
lwb->lwb_zio = zio_rewrite(zilog->zl_root_zio, zilog->zl_spa,
0, &lwb->lwb_blk, lwb->lwb_buf, BP_GET_LSIZE(&lwb->lwb_blk),
- zil_lwb_write_done, lwb, ZIO_PRIORITY_LOG_WRITE,
+ zil_lwb_write_done, lwb, ZIO_PRIORITY_SYNC_WRITE,
ZIO_FLAG_CANFAIL | ZIO_FLAG_DONT_PROPAGATE |
ZIO_FLAG_FASTWRITE, &zb);
}
diff --git a/module/zfs/zio.c b/module/zfs/zio.c
index bc9d5b920..7cc3d4c9a 100644
--- a/module/zfs/zio.c
+++ b/module/zfs/zio.c
@@ -39,30 +39,10 @@
/*
* ==========================================================================
- * I/O priority table
- * ==========================================================================
- */
-uint8_t zio_priority_table[ZIO_PRIORITY_TABLE_SIZE] = {
- 0, /* ZIO_PRIORITY_NOW */
- 0, /* ZIO_PRIORITY_SYNC_READ */
- 0, /* ZIO_PRIORITY_SYNC_WRITE */
- 0, /* ZIO_PRIORITY_LOG_WRITE */
- 1, /* ZIO_PRIORITY_CACHE_FILL */
- 1, /* ZIO_PRIORITY_AGG */
- 4, /* ZIO_PRIORITY_FREE */
- 4, /* ZIO_PRIORITY_ASYNC_WRITE */
- 6, /* ZIO_PRIORITY_ASYNC_READ */
- 10, /* ZIO_PRIORITY_RESILVER */
- 20, /* ZIO_PRIORITY_SCRUB */
- 2, /* ZIO_PRIORITY_DDT_PREFETCH */
-};
-
-/*
- * ==========================================================================
* I/O type descriptions
* ==========================================================================
*/
-char *zio_type_name[ZIO_TYPES] = {
+const char *zio_type_name[ZIO_TYPES] = {
"z_null", "z_rd", "z_wr", "z_fr", "z_cl", "z_ioctl"
};
@@ -549,7 +529,10 @@ zio_notify_parent(zio_t *pio, zio_t *zio, enum zio_wait_type wait)
*errorp = zio_worst_error(*errorp, zio->io_error);
pio->io_reexecute |= zio->io_reexecute;
ASSERT3U(*countp, >, 0);
- if (--*countp == 0 && pio->io_stall == countp) {
+
+ (*countp)--;
+
+ if (*countp == 0 && pio->io_stall == countp) {
pio->io_stall = NULL;
mutex_exit(&pio->io_lock);
__zio_execute(pio);
@@ -573,7 +556,7 @@ zio_inherit_child_errors(zio_t *zio, enum zio_child c)
static zio_t *
zio_create(zio_t *pio, spa_t *spa, uint64_t txg, const blkptr_t *bp,
void *data, uint64_t size, zio_done_func_t *done, void *private,
- zio_type_t type, int priority, enum zio_flag flags,
+ zio_type_t type, zio_priority_t priority, enum zio_flag flags,
vdev_t *vd, uint64_t offset, const zbookmark_t *zb,
enum zio_stage stage, enum zio_stage pipeline)
{
@@ -620,6 +603,7 @@ zio_create(zio_t *pio, spa_t *spa, uint64_t txg, const blkptr_t *bp,
zio->io_spa = spa;
zio->io_txg = txg;
zio->io_ready = NULL;
+ zio->io_physdone = NULL;
zio->io_done = done;
zio->io_private = private;
zio->io_prev_space_delta = 0;
@@ -629,7 +613,6 @@ zio_create(zio_t *pio, spa_t *spa, uint64_t txg, const blkptr_t *bp,
zio->io_vsd = NULL;
zio->io_vsd_ops = NULL;
zio->io_offset = offset;
- zio->io_deadline = 0;
zio->io_timestamp = 0;
zio->io_delta = 0;
zio->io_delay = 0;
@@ -646,6 +629,7 @@ zio_create(zio_t *pio, spa_t *spa, uint64_t txg, const blkptr_t *bp,
zio->io_transform_stack = NULL;
zio->io_error = 0;
zio->io_child_count = 0;
+ zio->io_phys_children = 0;
zio->io_parent_count = 0;
zio->io_stall = NULL;
zio->io_gang_leader = NULL;
@@ -706,7 +690,7 @@ zio_root(spa_t *spa, zio_done_func_t *done, void *private, enum zio_flag flags)
zio_t *
zio_read(zio_t *pio, spa_t *spa, const blkptr_t *bp,
void *data, uint64_t size, zio_done_func_t *done, void *private,
- int priority, enum zio_flag flags, const zbookmark_t *zb)
+ zio_priority_t priority, enum zio_flag flags, const zbookmark_t *zb)
{
zio_t *zio;
@@ -722,8 +706,9 @@ zio_read(zio_t *pio, spa_t *spa, const blkptr_t *bp,
zio_t *
zio_write(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp,
void *data, uint64_t size, const zio_prop_t *zp,
- zio_done_func_t *ready, zio_done_func_t *done, void *private,
- int priority, enum zio_flag flags, const zbookmark_t *zb)
+ zio_done_func_t *ready, zio_done_func_t *physdone, zio_done_func_t *done,
+ void *private,
+ zio_priority_t priority, enum zio_flag flags, const zbookmark_t *zb)
{
zio_t *zio;
@@ -742,6 +727,7 @@ zio_write(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp,
ZIO_DDT_CHILD_WRITE_PIPELINE : ZIO_WRITE_PIPELINE);
zio->io_ready = ready;
+ zio->io_physdone = physdone;
zio->io_prop = *zp;
return (zio);
@@ -749,8 +735,8 @@ zio_write(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp,
zio_t *
zio_rewrite(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp, void *data,
- uint64_t size, zio_done_func_t *done, void *private, int priority,
- enum zio_flag flags, zbookmark_t *zb)
+ uint64_t size, zio_done_func_t *done, void *private,
+ zio_priority_t priority, enum zio_flag flags, zbookmark_t *zb)
{
zio_t *zio;
@@ -829,7 +815,6 @@ zio_free_sync(zio_t *pio, spa_t *spa, uint64_t txg, const blkptr_t *bp,
NULL, NULL, ZIO_TYPE_FREE, ZIO_PRIORITY_NOW, flags,
NULL, 0, NULL, ZIO_STAGE_OPEN, stage);
-
return (zio);
}
@@ -864,14 +849,14 @@ zio_claim(zio_t *pio, spa_t *spa, uint64_t txg, const blkptr_t *bp,
zio_t *
zio_ioctl(zio_t *pio, spa_t *spa, vdev_t *vd, int cmd,
- zio_done_func_t *done, void *private, int priority, enum zio_flag flags)
+ zio_done_func_t *done, void *private, enum zio_flag flags)
{
zio_t *zio;
int c;
if (vd->vdev_children == 0) {
zio = zio_create(pio, spa, 0, NULL, NULL, 0, done, private,
- ZIO_TYPE_IOCTL, priority, flags, vd, 0, NULL,
+ ZIO_TYPE_IOCTL, ZIO_PRIORITY_NOW, flags, vd, 0, NULL,
ZIO_STAGE_OPEN, ZIO_IOCTL_PIPELINE);
zio->io_cmd = cmd;
@@ -880,7 +865,7 @@ zio_ioctl(zio_t *pio, spa_t *spa, vdev_t *vd, int cmd,
for (c = 0; c < vd->vdev_children; c++)
zio_nowait(zio_ioctl(zio, spa, vd->vdev_child[c], cmd,
- done, private, priority, flags));
+ done, private, flags));
}
return (zio);
@@ -889,7 +874,7 @@ zio_ioctl(zio_t *pio, spa_t *spa, vdev_t *vd, int cmd,
zio_t *
zio_read_phys(zio_t *pio, vdev_t *vd, uint64_t offset, uint64_t size,
void *data, int checksum, zio_done_func_t *done, void *private,
- int priority, enum zio_flag flags, boolean_t labels)
+ zio_priority_t priority, enum zio_flag flags, boolean_t labels)
{
zio_t *zio;
@@ -910,7 +895,7 @@ zio_read_phys(zio_t *pio, vdev_t *vd, uint64_t offset, uint64_t size,
zio_t *
zio_write_phys(zio_t *pio, vdev_t *vd, uint64_t offset, uint64_t size,
void *data, int checksum, zio_done_func_t *done, void *private,
- int priority, enum zio_flag flags, boolean_t labels)
+ zio_priority_t priority, enum zio_flag flags, boolean_t labels)
{
zio_t *zio;
@@ -945,8 +930,8 @@ zio_write_phys(zio_t *pio, vdev_t *vd, uint64_t offset, uint64_t size,
*/
zio_t *
zio_vdev_child_io(zio_t *pio, blkptr_t *bp, vdev_t *vd, uint64_t offset,
- void *data, uint64_t size, int type, int priority, enum zio_flag flags,
- zio_done_func_t *done, void *private)
+ void *data, uint64_t size, int type, zio_priority_t priority,
+ enum zio_flag flags, zio_done_func_t *done, void *private)
{
enum zio_stage pipeline = ZIO_VDEV_CHILD_PIPELINE;
zio_t *zio;
@@ -981,12 +966,16 @@ zio_vdev_child_io(zio_t *pio, blkptr_t *bp, vdev_t *vd, uint64_t offset,
done, private, type, priority, flags, vd, offset, &pio->io_bookmark,
ZIO_STAGE_VDEV_IO_START >> 1, pipeline);
+ zio->io_physdone = pio->io_physdone;
+ if (vd->vdev_ops->vdev_op_leaf && zio->io_logical != NULL)
+ zio->io_logical->io_phys_children++;
+
return (zio);
}
zio_t *
zio_vdev_delegated_io(vdev_t *vd, uint64_t offset, void *data, uint64_t size,
- int type, int priority, enum zio_flag flags,
+ int type, zio_priority_t priority, enum zio_flag flags,
zio_done_func_t *done, void *private)
{
zio_t *zio;
@@ -995,7 +984,7 @@ zio_vdev_delegated_io(vdev_t *vd, uint64_t offset, void *data, uint64_t size,
zio = zio_create(NULL, vd->vdev_spa, 0, NULL,
data, size, done, private, type, priority,
- flags | ZIO_FLAG_CANFAIL | ZIO_FLAG_DONT_RETRY,
+ flags | ZIO_FLAG_CANFAIL | ZIO_FLAG_DONT_RETRY | ZIO_FLAG_DELEGATED,
vd, offset, NULL,
ZIO_STAGE_VDEV_IO_START >> 1, ZIO_VDEV_CHILD_PIPELINE);
@@ -1006,7 +995,7 @@ void
zio_flush(zio_t *zio, vdev_t *vd)
{
zio_nowait(zio_ioctl(zio, zio->io_spa, vd, DKIOCFLUSHWRITECACHE,
- NULL, NULL, ZIO_PRIORITY_NOW,
+ NULL, NULL,
ZIO_FLAG_CANFAIL | ZIO_FLAG_DONT_PROPAGATE | ZIO_FLAG_DONT_RETRY));
}
@@ -1951,7 +1940,7 @@ zio_write_gang_block(zio_t *pio)
zio_nowait(zio_write(zio, spa, txg, &gbh->zg_blkptr[g],
(char *)pio->io_data + (pio->io_size - resid), lsize, &zp,
- zio_write_gang_member_ready, NULL, &gn->gn_child[g],
+ zio_write_gang_member_ready, NULL, NULL, &gn->gn_child[g],
pio->io_priority, ZIO_GANG_CHILD_FLAGS(pio),
&pio->io_bookmark));
}
@@ -2335,7 +2324,7 @@ zio_ddt_write(zio_t *zio)
}
dio = zio_write(zio, spa, txg, bp, zio->io_orig_data,
- zio->io_orig_size, &czp, NULL,
+ zio->io_orig_size, &czp, NULL, NULL,
zio_ddt_ditto_write_done, dde, zio->io_priority,
ZIO_DDT_CHILD_FLAGS(zio), &zio->io_bookmark);
@@ -2357,7 +2346,7 @@ zio_ddt_write(zio_t *zio)
ddt_phys_addref(ddp);
} else {
cio = zio_write(zio, spa, txg, bp, zio->io_orig_data,
- zio->io_orig_size, zp, zio_ddt_child_write_ready,
+ zio->io_orig_size, zp, zio_ddt_child_write_ready, NULL,
zio_ddt_child_write_done, dde, zio->io_priority,
ZIO_DDT_CHILD_FLAGS(zio), &zio->io_bookmark);
@@ -2780,6 +2769,13 @@ zio_vdev_io_assess(zio_t *zio)
if (zio->io_error)
zio->io_pipeline = ZIO_INTERLOCK_PIPELINE;
+ if (vd != NULL && vd->vdev_ops->vdev_op_leaf &&
+ zio->io_physdone != NULL) {
+ ASSERT(!(zio->io_flags & ZIO_FLAG_DELEGATED));
+ ASSERT(zio->io_child_type == ZIO_CHILD_VDEV);
+ zio->io_physdone(zio->io_logical);
+ }
+
return (ZIO_PIPELINE_CONTINUE);
}
@@ -3346,7 +3342,6 @@ EXPORT_SYMBOL(zio_clear_fault);
EXPORT_SYMBOL(zio_handle_fault_injection);
EXPORT_SYMBOL(zio_handle_device_injection);
EXPORT_SYMBOL(zio_handle_label_injection);
-EXPORT_SYMBOL(zio_priority_table);
EXPORT_SYMBOL(zio_type_name);
module_param(zio_bulk_flags, int, 0644);