mirror_zfs/module/zfs/dbuf_stats.c

231 lines
6.0 KiB
C
Raw Normal View History

/*
* 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
*/
#include <sys/zfs_context.h>
#include <sys/dbuf.h>
#include <sys/dmu_objset.h>
/*
* Calculate the index of the arc header for the state, disabled by default.
*/
int zfs_dbuf_state_index = 0;
/*
* ==========================================================================
* Dbuf Hash Read Routines
* ==========================================================================
*/
typedef struct dbuf_stats_t {
kmutex_t lock;
kstat_t *kstat;
dbuf_hash_table_t *hash;
int idx;
} dbuf_stats_t;
static dbuf_stats_t dbuf_stats_hash_table;
static int
dbuf_stats_hash_table_headers(char *buf, size_t size)
{
(void) snprintf(buf, size,
"%-88s | %-124s | %s\n"
"%-16s %-8s %-8s %-8s %-8s %-8s %-8s %-5s %-5s %5s | "
Illumos 5497 - lock contention on arcs_mtx Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Richard Elling <richard.elling@richardelling.com> Approved by: Dan McDonald <danmcd@omniti.com> Porting notes and other significant code changes: The illumos 5368 patch (ARC should cache more metadata), which was never picked up by ZoL, is mostly reverted by this patch. Since ZoL relies on the kernel asynchronously calling the shrinker to actually reap memory, the shrinker wakes up arc_reclaim_waiters_cv every time it runs. The arc_adapt_thread() function no longer calls arc_do_user_evicts() since the newly-added arc_user_evicts_thread() calls it periodically. Notable conflicting ZoL commits which conflicted with this patch or whose effects are either duplicated or un-done by this patch: 302f753 - Integrate ARC more tightly with Linux 39e055c - Adjust arc_p based on "bytes" in arc_shrink f521ce1 - Allow "arc_p" to drop to zero or grow to "arc_c" 77765b5 - Remove "arc_meta_used" from arc_adjust calculation 94520ca - Prune metadata from ghost lists in arc_adjust_meta Trace support for multilist_insert() and multilist_remove() has been added and produces the following output: fio-12498 [077] .... 112936.448324: zfs_multilist__insert: ml { offset 240 numsublists 80 sublistidx 63 } fio-12498 [077] .... 112936.448347: zfs_multilist__remove: ml { offset 240 numsublists 80 sublistidx 29 } The following arcstats have been removed: recycle_miss - Used by arcstat.py and arc_summary.py, both of which have been updated appropriately. l2_writes_hdr_miss The following arcstats have been added: evict_not_enough - Number of times arc_evict_state() was unable to evict enough buffers to reach its target amount. evict_l2_skip - Number of times arc_evict_hdr() skipped eviction because it was being written to the l2arc. l2_writes_lock_retry - Replaces l2_writes_hdr_miss. Number of times l2arc_write_done() failed to acquire hash_lock (and re-tries). arc_meta_min - Shows the value of the zfs_arc_meta_min module parameter (see below). The "index" column of the "dbuf" kstat has been removed since it doesn't have a direct analog in the new multilist scheme. Additional multilist- related stats could be added in the future but would likely require extensions to the mulilist API. The following module parameters have been added: zfs_arc_evict_batch_limit - Number of ARC headers to free per sub-list before moving on to the next sub-list. zfs_arc_meta_min - Enforce a floor on the amount of metadata in the ARC. zfs_arc_num_sublists_per_state - Number of multilist sub-lists per ARC state. zfs_arc_overflow_shift - Controls amount by which the ARC must exceed the target size to be considered "overflowing". Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov
2015-01-13 06:52:19 +03:00
"%-5s %-5s %-8s %-6s %-8s %-12s "
"%-6s %-6s %-6s %-6s %-6s %-8s %-8s %-8s %-5s | "
"%-6s %-6s %-8s %-8s %-6s %-6s %-5s %-8s %-8s\n",
"dbuf", "arcbuf", "dnode", "pool", "objset", "object", "level",
"blkid", "offset", "dbsize", "meta", "state", "dbholds", "list",
Illumos 5497 - lock contention on arcs_mtx Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Richard Elling <richard.elling@richardelling.com> Approved by: Dan McDonald <danmcd@omniti.com> Porting notes and other significant code changes: The illumos 5368 patch (ARC should cache more metadata), which was never picked up by ZoL, is mostly reverted by this patch. Since ZoL relies on the kernel asynchronously calling the shrinker to actually reap memory, the shrinker wakes up arc_reclaim_waiters_cv every time it runs. The arc_adapt_thread() function no longer calls arc_do_user_evicts() since the newly-added arc_user_evicts_thread() calls it periodically. Notable conflicting ZoL commits which conflicted with this patch or whose effects are either duplicated or un-done by this patch: 302f753 - Integrate ARC more tightly with Linux 39e055c - Adjust arc_p based on "bytes" in arc_shrink f521ce1 - Allow "arc_p" to drop to zero or grow to "arc_c" 77765b5 - Remove "arc_meta_used" from arc_adjust calculation 94520ca - Prune metadata from ghost lists in arc_adjust_meta Trace support for multilist_insert() and multilist_remove() has been added and produces the following output: fio-12498 [077] .... 112936.448324: zfs_multilist__insert: ml { offset 240 numsublists 80 sublistidx 63 } fio-12498 [077] .... 112936.448347: zfs_multilist__remove: ml { offset 240 numsublists 80 sublistidx 29 } The following arcstats have been removed: recycle_miss - Used by arcstat.py and arc_summary.py, both of which have been updated appropriately. l2_writes_hdr_miss The following arcstats have been added: evict_not_enough - Number of times arc_evict_state() was unable to evict enough buffers to reach its target amount. evict_l2_skip - Number of times arc_evict_hdr() skipped eviction because it was being written to the l2arc. l2_writes_lock_retry - Replaces l2_writes_hdr_miss. Number of times l2arc_write_done() failed to acquire hash_lock (and re-tries). arc_meta_min - Shows the value of the zfs_arc_meta_min module parameter (see below). The "index" column of the "dbuf" kstat has been removed since it doesn't have a direct analog in the new multilist scheme. Additional multilist- related stats could be added in the future but would likely require extensions to the mulilist API. The following module parameters have been added: zfs_arc_evict_batch_limit - Number of ARC headers to free per sub-list before moving on to the next sub-list. zfs_arc_meta_min - Enforce a floor on the amount of metadata in the ARC. zfs_arc_num_sublists_per_state - Number of multilist sub-lists per ARC state. zfs_arc_overflow_shift - Controls amount by which the ARC must exceed the target size to be considered "overflowing". Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov
2015-01-13 06:52:19 +03:00
"atype", "flags", "count", "asize", "access",
"mru", "gmru", "mfu", "gmfu", "l2", "l2_dattr", "l2_asize",
"l2_comp", "aholds", "dtype", "btype", "data_bs", "meta_bs",
"bsize", "lvls", "dholds", "blocks", "dsize");
return (0);
}
int
__dbuf_stats_hash_table_data(char *buf, size_t size, dmu_buf_impl_t *db)
{
arc_buf_info_t abi = { 0 };
dmu_object_info_t doi = { 0 };
dnode_t *dn = DB_DNODE(db);
size_t nwritten;
if (db->db_buf)
arc_buf_info(db->db_buf, &abi, zfs_dbuf_state_index);
Improved dnode allocation and dmu_hold_impl() (#6611) Refactor dmu_object_alloc_dnsize() and dnode_hold_impl() to simplify the code, fix errors introduced by commit dbeb879 (PR #6117) interacting badly with large dnodes, and improve performance. * When allocating a new dnode in dmu_object_alloc_dnsize(), update the percpu object ID for the core's metadnode chunk immediately. This eliminates most lock contention when taking the hold and creating the dnode. * Correct detection of the chunk boundary to work properly with large dnodes. * Separate the dmu_hold_impl() code for the FREE case from the code for the ALLOCATED case to make it easier to read. * Fully populate the dnode handle array immediately after reading a block of the metadnode from disk. Subsequently the dnode handle array provides enough information to determine which dnode slots are in use and which are free. * Add several kstats to allow the behavior of the code to be examined. * Verify dnode packing in large_dnode_008_pos.ksh. Since the test is purely creates, it should leave very few holes in the metadnode. * Add test large_dnode_009_pos.ksh, which performs concurrent creates and deletes, to complement existing test which does only creates. With the above fixes, there is very little contention in a test of about 200,000 racing dnode allocations produced by tests 'large_dnode_008_pos' and 'large_dnode_009_pos'. name type data dnode_hold_dbuf_hold 4 0 dnode_hold_dbuf_read 4 0 dnode_hold_alloc_hits 4 3804690 dnode_hold_alloc_misses 4 216 dnode_hold_alloc_interior 4 3 dnode_hold_alloc_lock_retry 4 0 dnode_hold_alloc_lock_misses 4 0 dnode_hold_alloc_type_none 4 0 dnode_hold_free_hits 4 203105 dnode_hold_free_misses 4 4 dnode_hold_free_lock_misses 4 0 dnode_hold_free_lock_retry 4 0 dnode_hold_free_overflow 4 0 dnode_hold_free_refcount 4 57 dnode_hold_free_txg 4 0 dnode_allocate 4 203154 dnode_reallocate 4 0 dnode_buf_evict 4 23918 dnode_alloc_next_chunk 4 4887 dnode_alloc_race 4 0 dnode_alloc_next_block 4 18 The performance is slightly improved for concurrent creates with 16+ threads, and unchanged for low thread counts. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Olaf Faaland <faaland1@llnl.gov>
2017-09-14 01:46:15 +03:00
__dmu_object_info_from_dnode(dn, &doi);
nwritten = snprintf(buf, size,
"%-16s %-8llu %-8lld %-8lld %-8lld %-8llu %-8llu %-5d %-5d %-5lu | "
Illumos 5497 - lock contention on arcs_mtx Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Richard Elling <richard.elling@richardelling.com> Approved by: Dan McDonald <danmcd@omniti.com> Porting notes and other significant code changes: The illumos 5368 patch (ARC should cache more metadata), which was never picked up by ZoL, is mostly reverted by this patch. Since ZoL relies on the kernel asynchronously calling the shrinker to actually reap memory, the shrinker wakes up arc_reclaim_waiters_cv every time it runs. The arc_adapt_thread() function no longer calls arc_do_user_evicts() since the newly-added arc_user_evicts_thread() calls it periodically. Notable conflicting ZoL commits which conflicted with this patch or whose effects are either duplicated or un-done by this patch: 302f753 - Integrate ARC more tightly with Linux 39e055c - Adjust arc_p based on "bytes" in arc_shrink f521ce1 - Allow "arc_p" to drop to zero or grow to "arc_c" 77765b5 - Remove "arc_meta_used" from arc_adjust calculation 94520ca - Prune metadata from ghost lists in arc_adjust_meta Trace support for multilist_insert() and multilist_remove() has been added and produces the following output: fio-12498 [077] .... 112936.448324: zfs_multilist__insert: ml { offset 240 numsublists 80 sublistidx 63 } fio-12498 [077] .... 112936.448347: zfs_multilist__remove: ml { offset 240 numsublists 80 sublistidx 29 } The following arcstats have been removed: recycle_miss - Used by arcstat.py and arc_summary.py, both of which have been updated appropriately. l2_writes_hdr_miss The following arcstats have been added: evict_not_enough - Number of times arc_evict_state() was unable to evict enough buffers to reach its target amount. evict_l2_skip - Number of times arc_evict_hdr() skipped eviction because it was being written to the l2arc. l2_writes_lock_retry - Replaces l2_writes_hdr_miss. Number of times l2arc_write_done() failed to acquire hash_lock (and re-tries). arc_meta_min - Shows the value of the zfs_arc_meta_min module parameter (see below). The "index" column of the "dbuf" kstat has been removed since it doesn't have a direct analog in the new multilist scheme. Additional multilist- related stats could be added in the future but would likely require extensions to the mulilist API. The following module parameters have been added: zfs_arc_evict_batch_limit - Number of ARC headers to free per sub-list before moving on to the next sub-list. zfs_arc_meta_min - Enforce a floor on the amount of metadata in the ARC. zfs_arc_num_sublists_per_state - Number of multilist sub-lists per ARC state. zfs_arc_overflow_shift - Controls amount by which the ARC must exceed the target size to be considered "overflowing". Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov
2015-01-13 06:52:19 +03:00
"%-5d %-5d 0x%-6x %-6lu %-8llu %-12llu "
"%-6lu %-6lu %-6lu %-6lu %-6lu %-8llu %-8llu %-8d %-5lu | "
"%-6d %-6d %-8lu %-8lu %-6llu %-6lu %-5lu %-8llu %-8llu\n",
/* dmu_buf_impl_t */
spa_name(dn->dn_objset->os_spa),
(u_longlong_t)dmu_objset_id(db->db_objset),
(longlong_t)db->db.db_object,
(longlong_t)db->db_level,
(longlong_t)db->db_blkid,
(u_longlong_t)db->db.db_offset,
(u_longlong_t)db->db.db_size,
!!dbuf_is_metadata(db),
db->db_state,
(ulong_t)refcount_count(&db->db_holds),
/* arc_buf_info_t */
abi.abi_state_type,
abi.abi_state_contents,
abi.abi_flags,
OpenZFS 6950 - ARC should cache compressed data Authored by: George Wilson <george.wilson@delphix.com> Reviewed by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed by: Matt Ahrens <mahrens@delphix.com> Reviewed by: Paul Dagnelie <pcd@delphix.com> Reviewed by: Tom Caputi <tcaputi@datto.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Ported by: David Quigley <david.quigley@intel.com> This review covers the reading and writing of compressed arc headers, sharing data between the arc_hdr_t and the arc_buf_t, and the implementation of a new dbuf cache to keep frequently access data uncompressed. I've added a new member to l1 arc hdr called b_pdata. The b_pdata always hangs off the arc_buf_hdr_t (if an L1 hdr is in use) and points to the physical block for that DVA. The physical block may or may not be compressed. If compressed arc is enabled and the block on-disk is compressed, then the b_pdata will match the block on-disk and remain compressed in memory. If the block on disk is not compressed, then neither will the b_pdata. Lastly, if compressed arc is disabled, then b_pdata will always be an uncompressed version of the on-disk block. Typically the arc will cache only the arc_buf_hdr_t and will aggressively evict any arc_buf_t's that are no longer referenced. This means that the arc will primarily have compressed blocks as the arc_buf_t's are considered overhead and are always uncompressed. When a consumer reads a block we first look to see if the arc_buf_hdr_t is cached. If the hdr is cached then we allocate a new arc_buf_t and decompress the b_pdata contents into the arc_buf_t's b_data. If the hdr already has a arc_buf_t, then we will allocate an additional arc_buf_t and bcopy the uncompressed contents from the first arc_buf_t to the new one. Writing to the compressed arc requires that we first discard the b_pdata since the physical block is about to be rewritten. The new data contents will be passed in via an arc_buf_t (uncompressed) and during the I/O pipeline stages we will copy the physical block contents to a newly allocated b_pdata. When an l2arc is inuse it will also take advantage of the b_pdata. Now the l2arc will always write the contents of b_pdata to the l2arc. This means that when compressed arc is enabled that the l2arc blocks are identical to those stored in the main data pool. This provides a significant advantage since we can leverage the bp's checksum when reading from the l2arc to determine if the contents are valid. If the compressed arc is disabled, then we must first transform the read block to look like the physical block in the main data pool before comparing the checksum and determining it's valid. OpenZFS-issue: https://www.illumos.org/issues/6950 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/7fc10f0 Issue #5078
2016-06-02 07:04:53 +03:00
(ulong_t)abi.abi_bufcnt,
(u_longlong_t)abi.abi_size,
(u_longlong_t)abi.abi_access,
(ulong_t)abi.abi_mru_hits,
(ulong_t)abi.abi_mru_ghost_hits,
(ulong_t)abi.abi_mfu_hits,
(ulong_t)abi.abi_mfu_ghost_hits,
(ulong_t)abi.abi_l2arc_hits,
(u_longlong_t)abi.abi_l2arc_dattr,
(u_longlong_t)abi.abi_l2arc_asize,
abi.abi_l2arc_compress,
(ulong_t)abi.abi_holds,
/* dmu_object_info_t */
doi.doi_type,
doi.doi_bonus_type,
(ulong_t)doi.doi_data_block_size,
(ulong_t)doi.doi_metadata_block_size,
(u_longlong_t)doi.doi_bonus_size,
(ulong_t)doi.doi_indirection,
(ulong_t)refcount_count(&dn->dn_holds),
(u_longlong_t)doi.doi_fill_count,
(u_longlong_t)doi.doi_max_offset);
if (nwritten >= size)
return (size);
return (nwritten + 1);
}
static int
dbuf_stats_hash_table_data(char *buf, size_t size, void *data)
{
dbuf_stats_t *dsh = (dbuf_stats_t *)data;
dbuf_hash_table_t *h = dsh->hash;
dmu_buf_impl_t *db;
int length, error = 0;
ASSERT3S(dsh->idx, >=, 0);
ASSERT3S(dsh->idx, <=, h->hash_table_mask);
memset(buf, 0, size);
mutex_enter(DBUF_HASH_MUTEX(h, dsh->idx));
for (db = h->hash_table[dsh->idx]; db != NULL; db = db->db_hash_next) {
/*
* Returning ENOMEM will cause the data and header functions
* to be called with a larger scratch buffers.
*/
if (size < 512) {
error = ENOMEM;
break;
}
mutex_enter(&db->db_mtx);
if (db->db_state != DB_EVICTING) {
length = __dbuf_stats_hash_table_data(buf, size, db);
buf += length;
size -= length;
}
mutex_exit(&db->db_mtx);
}
mutex_exit(DBUF_HASH_MUTEX(h, dsh->idx));
return (error);
}
static void *
dbuf_stats_hash_table_addr(kstat_t *ksp, loff_t n)
{
dbuf_stats_t *dsh = ksp->ks_private;
ASSERT(MUTEX_HELD(&dsh->lock));
if (n <= dsh->hash->hash_table_mask) {
dsh->idx = n;
return (dsh);
}
return (NULL);
}
static void
dbuf_stats_hash_table_init(dbuf_hash_table_t *hash)
{
dbuf_stats_t *dsh = &dbuf_stats_hash_table;
kstat_t *ksp;
mutex_init(&dsh->lock, NULL, MUTEX_DEFAULT, NULL);
dsh->hash = hash;
ksp = kstat_create("zfs", 0, "dbufs", "misc",
KSTAT_TYPE_RAW, 0, KSTAT_FLAG_VIRTUAL);
dsh->kstat = ksp;
if (ksp) {
ksp->ks_lock = &dsh->lock;
ksp->ks_ndata = UINT32_MAX;
ksp->ks_private = dsh;
kstat_set_raw_ops(ksp, dbuf_stats_hash_table_headers,
dbuf_stats_hash_table_data, dbuf_stats_hash_table_addr);
kstat_install(ksp);
}
}
static void
dbuf_stats_hash_table_destroy(void)
{
dbuf_stats_t *dsh = &dbuf_stats_hash_table;
kstat_t *ksp;
ksp = dsh->kstat;
if (ksp)
kstat_delete(ksp);
mutex_destroy(&dsh->lock);
}
void
dbuf_stats_init(dbuf_hash_table_t *hash)
{
dbuf_stats_hash_table_init(hash);
}
void
dbuf_stats_destroy(void)
{
dbuf_stats_hash_table_destroy();
}
#if defined(_KERNEL) && defined(HAVE_SPL)
module_param(zfs_dbuf_state_index, int, 0644);
MODULE_PARM_DESC(zfs_dbuf_state_index, "Calculate arc header index");
#endif