mirror_zfs/include/sys/dbuf.h

407 lines
11 KiB
C
Raw Normal View History

2008-11-20 23:01:55 +03:00
/*
* 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
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2012, 2015 by Delphix. All rights reserved.
* Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
* Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
2008-11-20 23:01:55 +03:00
*/
#ifndef _SYS_DBUF_H
#define _SYS_DBUF_H
#include <sys/dmu.h>
#include <sys/spa.h>
#include <sys/txg.h>
#include <sys/zio.h>
#include <sys/arc.h>
#include <sys/zfs_context.h>
#include <sys/refcount.h>
#include <sys/zrlock.h>
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
#include <sys/multilist.h>
2008-11-20 23:01:55 +03:00
#ifdef __cplusplus
extern "C" {
#endif
#define IN_DMU_SYNC 2
/*
* define flags for dbuf_read
*/
#define DB_RF_MUST_SUCCEED (1 << 0)
#define DB_RF_CANFAIL (1 << 1)
#define DB_RF_HAVESTRUCT (1 << 2)
#define DB_RF_NOPREFETCH (1 << 3)
#define DB_RF_NEVERWAIT (1 << 4)
#define DB_RF_CACHED (1 << 5)
Native Encryption for ZFS on Linux This change incorporates three major pieces: The first change is a keystore that manages wrapping and encryption keys for encrypted datasets. These commands mostly involve manipulating the new DSL Crypto Key ZAP Objects that live in the MOS. Each encrypted dataset has its own DSL Crypto Key that is protected with a user's key. This level of indirection allows users to change their keys without re-encrypting their entire datasets. The change implements the new subcommands "zfs load-key", "zfs unload-key" and "zfs change-key" which allow the user to manage their encryption keys and settings. In addition, several new flags and properties have been added to allow dataset creation and to make mounting and unmounting more convenient. The second piece of this patch provides the ability to encrypt, decyrpt, and authenticate protected datasets. Each object set maintains a Merkel tree of Message Authentication Codes that protect the lower layers, similarly to how checksums are maintained. This part impacts the zio layer, which handles the actual encryption and generation of MACs, as well as the ARC and DMU, which need to be able to handle encrypted buffers and protected data. The last addition is the ability to do raw, encrypted sends and receives. The idea here is to send raw encrypted and compressed data and receive it exactly as is on a backup system. This means that the dataset on the receiving system is protected using the same user key that is in use on the sending side. By doing so, datasets can be efficiently backed up to an untrusted system without fear of data being compromised. Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Jorgen Lundman <lundman@lundman.net> Signed-off-by: Tom Caputi <tcaputi@datto.com> Closes #494 Closes #5769
2017-08-14 20:36:48 +03:00
#define DB_RF_NO_DECRYPT (1 << 6)
2008-11-20 23:01:55 +03:00
/*
* The simplified state transition diagram for dbufs looks like:
2008-11-20 23:01:55 +03:00
*
* +----> READ ----+
* | |
* | V
* (alloc)-->UNCACHED CACHED-->EVICTING-->(free)
* | ^ ^
* | | |
* +----> FILL ----+ |
* | |
* | |
* +--------> NOFILL -------+
*
* DB_SEARCH is an invalid state for a dbuf. It is used by dbuf_free_range
* to find all dbufs in a range of a dnode and must be less than any other
* dbuf_states_t (see comment on dn_dbufs in dnode.h).
2008-11-20 23:01:55 +03:00
*/
typedef enum dbuf_states {
DB_SEARCH = -1,
2008-11-20 23:01:55 +03:00
DB_UNCACHED,
DB_FILL,
DB_NOFILL,
2008-11-20 23:01:55 +03:00
DB_READ,
DB_CACHED,
DB_EVICTING
} dbuf_states_t;
struct dnode;
struct dmu_tx;
/*
* level = 0 means the user data
* level = 1 means the single indirect block
* etc.
*/
struct dmu_buf_impl;
typedef enum override_states {
DR_NOT_OVERRIDDEN,
DR_IN_DMU_SYNC,
DR_OVERRIDDEN
} override_states_t;
typedef struct dbuf_dirty_record {
/* link on our parents dirty list */
list_node_t dr_dirty_node;
/* transaction group this data will sync in */
uint64_t dr_txg;
/* zio of outstanding write IO */
zio_t *dr_zio;
/* pointer back to our dbuf */
struct dmu_buf_impl *dr_dbuf;
/* pointer to next dirty record */
struct dbuf_dirty_record *dr_next;
/* pointer to parent dirty record */
struct dbuf_dirty_record *dr_parent;
Illumos #4045 write throttle & i/o scheduler performance work 4045 zfs write throttle & i/o scheduler performance work 1. The ZFS i/o scheduler (vdev_queue.c) now divides i/os into 5 classes: sync read, sync write, async read, async write, and scrub/resilver. The scheduler issues a number of concurrent i/os from each class to the device. Once a class has been selected, an i/o is selected from this class using either an elevator algorithem (async, scrub classes) or FIFO (sync classes). The number of concurrent async write i/os is tuned dynamically based on i/o load, to achieve good sync i/o latency when there is not a high load of writes, and good write throughput when there is. See the block comment in vdev_queue.c (reproduced below) for more details. 2. The write throttle (dsl_pool_tempreserve_space() and txg_constrain_throughput()) is rewritten to produce much more consistent delays when under constant load. The new write throttle is based on the amount of dirty data, rather than guesses about future performance of the system. When there is a lot of dirty data, each transaction (e.g. write() syscall) will be delayed by the same small amount. This eliminates the "brick wall of wait" that the old write throttle could hit, causing all transactions to wait several seconds until the next txg opens. One of the keys to the new write throttle is decrementing the amount of dirty data as i/o completes, rather than at the end of spa_sync(). Note that the write throttle is only applied once the i/o scheduler is issuing the maximum number of outstanding async writes. See the block comments in dsl_pool.c and above dmu_tx_delay() (reproduced below) for more details. This diff has several other effects, including: * the commonly-tuned global variable zfs_vdev_max_pending has been removed; use per-class zfs_vdev_*_max_active values or zfs_vdev_max_active instead. * the size of each txg (meaning the amount of dirty data written, and thus the time it takes to write out) is now controlled differently. There is no longer an explicit time goal; the primary determinant is amount of dirty data. Systems that are under light or medium load will now often see that a txg is always syncing, but the impact to performance (e.g. read latency) is minimal. Tune zfs_dirty_data_max and zfs_dirty_data_sync to control this. * zio_taskq_batch_pct = 75 -- Only use 75% of all CPUs for compression, checksum, etc. This improves latency by not allowing these CPU-intensive tasks to consume all CPU (on machines with at least 4 CPU's; the percentage is rounded up). --matt APPENDIX: problems with the current i/o scheduler The current ZFS i/o scheduler (vdev_queue.c) is deadline based. The problem with this is that if there are always i/os pending, then certain classes of i/os can see very long delays. For example, if there are always synchronous reads outstanding, then no async writes will be serviced until they become "past due". One symptom of this situation is that each pass of the txg sync takes at least several seconds (typically 3 seconds). If many i/os become "past due" (their deadline is in the past), then we must service all of these overdue i/os before any new i/os. This happens when we enqueue a batch of async writes for the txg sync, with deadlines 2.5 seconds in the future. If we can't complete all the i/os in 2.5 seconds (e.g. because there were always reads pending), then these i/os will become past due. Now we must service all the "async" writes (which could be hundreds of megabytes) before we service any reads, introducing considerable latency to synchronous i/os (reads or ZIL writes). Notes on porting to ZFS on Linux: - zio_t gained new members io_physdone and io_phys_children. Because object caches in the Linux port call the constructor only once at allocation time, objects may contain residual data when retrieved from the cache. Therefore zio_create() was updated to zero out the two new fields. - vdev_mirror_pending() relied on the depth of the per-vdev pending queue (vq->vq_pending_tree) to select the least-busy leaf vdev to read from. This tree has been replaced by vq->vq_active_tree which is now used for the same purpose. - vdev_queue_init() used the value of zfs_vdev_max_pending to determine the number of vdev I/O buffers to pre-allocate. That global no longer exists, so we instead use the sum of the *_max_active values for each of the five I/O classes described above. - The Illumos implementation of dmu_tx_delay() delays a transaction by sleeping in condition variable embedded in the thread (curthread->t_delay_cv). We do not have an equivalent CV to use in Linux, so this change replaced the delay logic with a wrapper called zfs_sleep_until(). This wrapper could be adopted upstream and in other downstream ports to abstract away operating system-specific delay logic. - These tunables are added as module parameters, and descriptions added to the zfs-module-parameters.5 man page. spa_asize_inflation zfs_deadman_synctime_ms zfs_vdev_max_active zfs_vdev_async_write_active_min_dirty_percent zfs_vdev_async_write_active_max_dirty_percent zfs_vdev_async_read_max_active zfs_vdev_async_read_min_active zfs_vdev_async_write_max_active zfs_vdev_async_write_min_active zfs_vdev_scrub_max_active zfs_vdev_scrub_min_active zfs_vdev_sync_read_max_active zfs_vdev_sync_read_min_active zfs_vdev_sync_write_max_active zfs_vdev_sync_write_min_active zfs_dirty_data_max_percent zfs_delay_min_dirty_percent zfs_dirty_data_max_max_percent zfs_dirty_data_max zfs_dirty_data_max_max zfs_dirty_data_sync zfs_delay_scale The latter four have type unsigned long, whereas they are uint64_t in Illumos. This accommodates Linux's module_param() supported types, but means they may overflow on 32-bit architectures. The values zfs_dirty_data_max and zfs_dirty_data_max_max are the most likely to overflow on 32-bit systems, since they express physical RAM sizes in bytes. In fact, Illumos initializes zfs_dirty_data_max_max to 2^32 which does overflow. To resolve that, this port instead initializes it in arc_init() to 25% of physical RAM, and adds the tunable zfs_dirty_data_max_max_percent to override that percentage. While this solution doesn't completely avoid the overflow issue, it should be a reasonable default for most systems, and the minority of affected systems can work around the issue by overriding the defaults. - Fixed reversed logic in comment above zfs_delay_scale declaration. - Clarified comments in vdev_queue.c regarding when per-queue minimums take effect. - Replaced dmu_tx_write_limit in the dmu_tx kstat file with dmu_tx_dirty_delay and dmu_tx_dirty_over_max. The first counts how many times a transaction has been delayed because the pool dirty data has exceeded zfs_delay_min_dirty_percent. The latter counts how many times the pool dirty data has exceeded zfs_dirty_data_max (which we expect to never happen). - The original patch would have regressed the bug fixed in zfsonlinux/zfs@c418410, which prevented users from setting the zfs_vdev_aggregation_limit tuning larger than SPA_MAXBLOCKSIZE. A similar fix is added to vdev_queue_aggregate(). - In vdev_queue_io_to_issue(), dynamically allocate 'zio_t search' on the heap instead of the stack. In Linux we can't afford such large structures on the stack. Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed by: Adam Leventhal <ahl@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Reviewed by: Ned Bass <bass6@llnl.gov> Reviewed by: Brendan Gregg <brendan.gregg@joyent.com> Approved by: Robert Mustacchi <rm@joyent.com> References: http://www.illumos.org/issues/4045 illumos/illumos-gate@69962b5647e4a8b9b14998733b765925381b727e Ported-by: Ned Bass <bass6@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #1913
2013-08-29 07:01:20 +04:00
/* How much space was changed to dsl_pool_dirty_space() for this? */
unsigned int dr_accounted;
Illumos 6844 - dnode_next_offset can detect fictional holes 6844 dnode_next_offset can detect fictional holes Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> dnode_next_offset is used in a variety of places to iterate over the holes or allocated blocks in a dnode. It operates under the premise that it can iterate over the blockpointers of a dnode in open context while holding only the dn_struct_rwlock as reader. Unfortunately, this premise does not hold. When we create the zio for a dbuf, we pass in the actual block pointer in the indirect block above that dbuf. When we later zero the bp in zio_write_compress, we are directly modifying the bp. The state of the bp is now inconsistent from the perspective of dnode_next_offset: the bp will appear to be a hole until zio_dva_allocate finally finishes filling it in. In the meantime, dnode_next_offset can detect a hole in the dnode when none exists. I was able to experimentally demonstrate this behavior with the following setup: 1. Create a file with 1 million dbufs. 2. Create a thread that randomly dirties L2 blocks by writing to the first L0 block under them. 3. Observe dnode_next_offset, waiting for it to skip over a hole in the middle of a file. 4. Do dnode_next_offset in a loop until we skip over such a non-existent hole. The fix is to ensure that it is valid to iterate over the indirect blocks in a dnode while holding the dn_struct_rwlock by passing the zio a copy of the BP and updating the actual BP in dbuf_write_ready while holding the lock. References: https://www.illumos.org/issues/6844 https://github.com/openzfs/openzfs/pull/82 DLPX-35372 Ported-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4548
2016-04-21 21:23:37 +03:00
/* A copy of the bp that points to us */
blkptr_t dr_bp_copy;
2008-11-20 23:01:55 +03:00
union dirty_types {
struct dirty_indirect {
/* protect access to list */
kmutex_t dr_mtx;
/* Our list of dirty children */
list_t dr_children;
} di;
struct dirty_leaf {
/*
* dr_data is set when we dirty the buffer
* so that we can retain the pointer even if it
* gets COW'd in a subsequent transaction group.
*/
arc_buf_t *dr_data;
blkptr_t dr_overridden_by;
override_states_t dr_override_state;
uint8_t dr_copies;
boolean_t dr_nopwrite;
Native Encryption for ZFS on Linux This change incorporates three major pieces: The first change is a keystore that manages wrapping and encryption keys for encrypted datasets. These commands mostly involve manipulating the new DSL Crypto Key ZAP Objects that live in the MOS. Each encrypted dataset has its own DSL Crypto Key that is protected with a user's key. This level of indirection allows users to change their keys without re-encrypting their entire datasets. The change implements the new subcommands "zfs load-key", "zfs unload-key" and "zfs change-key" which allow the user to manage their encryption keys and settings. In addition, several new flags and properties have been added to allow dataset creation and to make mounting and unmounting more convenient. The second piece of this patch provides the ability to encrypt, decyrpt, and authenticate protected datasets. Each object set maintains a Merkel tree of Message Authentication Codes that protect the lower layers, similarly to how checksums are maintained. This part impacts the zio layer, which handles the actual encryption and generation of MACs, as well as the ARC and DMU, which need to be able to handle encrypted buffers and protected data. The last addition is the ability to do raw, encrypted sends and receives. The idea here is to send raw encrypted and compressed data and receive it exactly as is on a backup system. This means that the dataset on the receiving system is protected using the same user key that is in use on the sending side. By doing so, datasets can be efficiently backed up to an untrusted system without fear of data being compromised. Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Jorgen Lundman <lundman@lundman.net> Signed-off-by: Tom Caputi <tcaputi@datto.com> Closes #494 Closes #5769
2017-08-14 20:36:48 +03:00
boolean_t dr_raw;
2008-11-20 23:01:55 +03:00
} dl;
} dt;
} dbuf_dirty_record_t;
typedef struct dmu_buf_impl {
/*
* The following members are immutable, with the exception of
* db.db_data, which is protected by db_mtx.
*/
/* the publicly visible structure */
dmu_buf_t db;
/* the objset we belong to */
struct objset *db_objset;
2008-11-20 23:01:55 +03:00
/*
* handle to safely access the dnode we belong to (NULL when evicted)
2008-11-20 23:01:55 +03:00
*/
struct dnode_handle *db_dnode_handle;
2008-11-20 23:01:55 +03:00
/*
* our parent buffer; if the dnode points to us directly,
* db_parent == db_dnode_handle->dnh_dnode->dn_dbuf
2008-11-20 23:01:55 +03:00
* only accessed by sync thread ???
* (NULL when evicted)
* May change from NULL to non-NULL under the protection of db_mtx
* (see dbuf_check_blkptr())
2008-11-20 23:01:55 +03:00
*/
struct dmu_buf_impl *db_parent;
/*
* link for hash table of all dmu_buf_impl_t's
*/
struct dmu_buf_impl *db_hash_next;
/* our block number */
uint64_t db_blkid;
/*
* Pointer to the blkptr_t which points to us. May be NULL if we
* don't have one yet. (NULL when evicted)
*/
blkptr_t *db_blkptr;
/*
* Our indirection level. Data buffers have db_level==0.
* Indirect buffers which point to data buffers have
* db_level==1. etc. Buffers which contain dnodes have
* db_level==0, since the dnodes are stored in a file.
*/
uint8_t db_level;
/* db_mtx protects the members below */
kmutex_t db_mtx;
/*
* Current state of the buffer
*/
dbuf_states_t db_state;
/*
* Refcount accessed by dmu_buf_{hold,rele}.
* If nonzero, the buffer can't be destroyed.
* Protected by db_mtx.
*/
refcount_t db_holds;
/* buffer holding our data */
arc_buf_t *db_buf;
kcondvar_t db_changed;
dbuf_dirty_record_t *db_data_pending;
/* pointer to most recent dirty record for this buffer */
dbuf_dirty_record_t *db_last_dirty;
/*
* Our link on the owner dnodes's dn_dbufs list.
* Protected by its dn_dbufs_mtx.
*/
avl_node_t db_link;
2008-11-20 23:01:55 +03:00
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
/*
* Link in dbuf_cache.
*/
multilist_node_t db_cache_link;
2008-11-20 23:01:55 +03:00
/* Data which is unique to data (leaf) blocks: */
/* User callback information. */
dmu_buf_user_t *db_user;
2008-11-20 23:01:55 +03:00
/*
* Evict user data as soon as the dirty and reference
* counts are equal.
*/
uint8_t db_user_immediate_evict;
/*
* This block was freed while a read or write was
* active.
*/
2008-11-20 23:01:55 +03:00
uint8_t db_freed_in_flight;
/*
* dnode_evict_dbufs() or dnode_evict_bonus() tried to
* evict this dbuf, but couldn't due to outstanding
* references. Evict once the refcount drops to 0.
*/
uint8_t db_pending_evict;
2008-11-20 23:01:55 +03:00
uint8_t db_dirtycnt;
} dmu_buf_impl_t;
/* Note: the dbuf hash table is exposed only for the mdb module */
#define DBUF_MUTEXES 8192
2008-11-20 23:01:55 +03:00
#define DBUF_HASH_MUTEX(h, idx) (&(h)->hash_mutexes[(idx) & (DBUF_MUTEXES-1)])
typedef struct dbuf_hash_table {
uint64_t hash_table_mask;
dmu_buf_impl_t **hash_table;
kmutex_t hash_mutexes[DBUF_MUTEXES];
} dbuf_hash_table_t;
uint64_t dbuf_whichblock(const struct dnode *di, const int64_t level,
const uint64_t offset);
2008-11-20 23:01:55 +03:00
void dbuf_create_bonus(struct dnode *dn);
int dbuf_spill_set_blksz(dmu_buf_t *db, uint64_t blksz, dmu_tx_t *tx);
void dbuf_rm_spill(struct dnode *dn, dmu_tx_t *tx);
2008-11-20 23:01:55 +03:00
dmu_buf_impl_t *dbuf_hold(struct dnode *dn, uint64_t blkid, void *tag);
dmu_buf_impl_t *dbuf_hold_level(struct dnode *dn, int level, uint64_t blkid,
void *tag);
int dbuf_hold_impl(struct dnode *dn, uint8_t level, uint64_t blkid,
boolean_t fail_sparse, boolean_t fail_uncached,
2008-11-20 23:01:55 +03:00
void *tag, dmu_buf_impl_t **dbp);
void dbuf_prefetch(struct dnode *dn, int64_t level, uint64_t blkid,
zio_priority_t prio, arc_flags_t aflags);
2008-11-20 23:01:55 +03:00
void dbuf_add_ref(dmu_buf_impl_t *db, void *tag);
boolean_t dbuf_try_add_ref(dmu_buf_t *db, objset_t *os, uint64_t obj,
uint64_t blkid, void *tag);
2008-11-20 23:01:55 +03:00
uint64_t dbuf_refcount(dmu_buf_impl_t *db);
void dbuf_rele(dmu_buf_impl_t *db, void *tag);
void dbuf_rele_and_unlock(dmu_buf_impl_t *db, void *tag);
2008-11-20 23:01:55 +03:00
dmu_buf_impl_t *dbuf_find(struct objset *os, uint64_t object, uint8_t level,
uint64_t blkid);
2008-11-20 23:01:55 +03:00
int dbuf_read(dmu_buf_impl_t *db, zio_t *zio, uint32_t flags);
void dmu_buf_will_not_fill(dmu_buf_t *db, dmu_tx_t *tx);
2008-11-20 23:01:55 +03:00
void dmu_buf_will_fill(dmu_buf_t *db, dmu_tx_t *tx);
void dmu_buf_fill_done(dmu_buf_t *db, dmu_tx_t *tx);
2009-07-03 02:44:48 +04:00
void dbuf_assign_arcbuf(dmu_buf_impl_t *db, arc_buf_t *buf, dmu_tx_t *tx);
2008-11-20 23:01:55 +03:00
dbuf_dirty_record_t *dbuf_dirty(dmu_buf_impl_t *db, dmu_tx_t *tx);
arc_buf_t *dbuf_loan_arcbuf(dmu_buf_impl_t *db);
void dmu_buf_write_embedded(dmu_buf_t *dbuf, void *data,
bp_embedded_type_t etype, enum zio_compress comp,
int uncompressed_size, int compressed_size, int byteorder, dmu_tx_t *tx);
2008-11-20 23:01:55 +03:00
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
void dbuf_destroy(dmu_buf_impl_t *db);
2008-11-20 23:01:55 +03:00
void dbuf_unoverride(dbuf_dirty_record_t *dr);
void dbuf_sync_list(list_t *list, int level, dmu_tx_t *tx);
void dbuf_release_bp(dmu_buf_impl_t *db);
2008-11-20 23:01:55 +03:00
void dbuf_free_range(struct dnode *dn, uint64_t start, uint64_t end,
2008-11-20 23:01:55 +03:00
struct dmu_tx *);
void dbuf_new_size(dmu_buf_impl_t *db, int size, dmu_tx_t *tx);
void dbuf_stats_init(dbuf_hash_table_t *hash);
void dbuf_stats_destroy(void);
#define DB_DNODE(_db) ((_db)->db_dnode_handle->dnh_dnode)
#define DB_DNODE_LOCK(_db) ((_db)->db_dnode_handle->dnh_zrlock)
#define DB_DNODE_ENTER(_db) (zrl_add(&DB_DNODE_LOCK(_db)))
#define DB_DNODE_EXIT(_db) (zrl_remove(&DB_DNODE_LOCK(_db)))
#define DB_DNODE_HELD(_db) (!zrl_is_zero(&DB_DNODE_LOCK(_db)))
2008-11-20 23:01:55 +03:00
void dbuf_init(void);
void dbuf_fini(void);
boolean_t dbuf_is_metadata(dmu_buf_impl_t *db);
#define DBUF_GET_BUFC_TYPE(_db) \
(dbuf_is_metadata(_db) ? ARC_BUFC_METADATA : ARC_BUFC_DATA)
#define DBUF_IS_CACHEABLE(_db) \
((_db)->db_objset->os_primary_cache == ZFS_CACHE_ALL || \
(dbuf_is_metadata(_db) && \
((_db)->db_objset->os_primary_cache == ZFS_CACHE_METADATA)))
#define DBUF_IS_L2CACHEABLE(_db) \
((_db)->db_objset->os_secondary_cache == ZFS_CACHE_ALL || \
(dbuf_is_metadata(_db) && \
((_db)->db_objset->os_secondary_cache == ZFS_CACHE_METADATA)))
2008-11-20 23:01:55 +03:00
#define DNODE_LEVEL_IS_L2CACHEABLE(_dn, _level) \
((_dn)->dn_objset->os_secondary_cache == ZFS_CACHE_ALL || \
(((_level) > 0 || \
DMU_OT_IS_METADATA((_dn)->dn_handle->dnh_dnode->dn_type)) && \
((_dn)->dn_objset->os_secondary_cache == ZFS_CACHE_METADATA)))
2008-11-20 23:01:55 +03:00
#ifdef ZFS_DEBUG
/*
* There should be a ## between the string literal and fmt, to make it
* clear that we're joining two strings together, but gcc does not
* support that preprocessor token.
*/
#define dprintf_dbuf(dbuf, fmt, ...) do { \
if (zfs_flags & ZFS_DEBUG_DPRINTF) { \
char __db_buf[32]; \
uint64_t __db_obj = (dbuf)->db.db_object; \
if (__db_obj == DMU_META_DNODE_OBJECT) \
(void) strcpy(__db_buf, "mdn"); \
else \
(void) snprintf(__db_buf, sizeof (__db_buf), "%lld", \
(u_longlong_t)__db_obj); \
dprintf_ds((dbuf)->db_objset->os_dsl_dataset, \
"obj=%s lvl=%u blkid=%lld " fmt, \
__db_buf, (dbuf)->db_level, \
(u_longlong_t)(dbuf)->db_blkid, __VA_ARGS__); \
} \
_NOTE(CONSTCOND) } while (0)
#define dprintf_dbuf_bp(db, bp, fmt, ...) do { \
if (zfs_flags & ZFS_DEBUG_DPRINTF) { \
char *__blkbuf = kmem_alloc(BP_SPRINTF_LEN, KM_SLEEP); \
snprintf_blkptr(__blkbuf, BP_SPRINTF_LEN, bp); \
dprintf_dbuf(db, fmt " %s\n", __VA_ARGS__, __blkbuf); \
kmem_free(__blkbuf, BP_SPRINTF_LEN); \
} \
2008-11-20 23:01:55 +03:00
_NOTE(CONSTCOND) } while (0)
#define DBUF_VERIFY(db) dbuf_verify(db)
#else
#define dprintf_dbuf(db, fmt, ...)
#define dprintf_dbuf_bp(db, bp, fmt, ...)
#define DBUF_VERIFY(db)
#endif
#ifdef __cplusplus
}
#endif
#endif /* _SYS_DBUF_H */