mirror_zfs/include/sys/arc_impl.h

620 lines
22 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
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2013 by Delphix. All rights reserved.
* Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
* Copyright 2013 Nexenta Systems, Inc. All rights reserved.
*/
#ifndef _SYS_ARC_IMPL_H
#define _SYS_ARC_IMPL_H
#include <sys/arc.h>
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
#include <sys/zio_crypt.h>
#include <sys/zthr.h>
#include <sys/aggsum.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* Note that buffers can be in one of 6 states:
* ARC_anon - anonymous (discussed below)
* ARC_mru - recently used, currently cached
* ARC_mru_ghost - recently used, no longer in cache
* ARC_mfu - frequently used, currently cached
* ARC_mfu_ghost - frequently used, no longer in cache
* ARC_l2c_only - exists in L2ARC but not other states
* When there are no active references to the buffer, they are
* are linked onto a list in one of these arc states. These are
* the only buffers that can be evicted or deleted. Within each
* state there are multiple lists, one for meta-data and one for
* non-meta-data. Meta-data (indirect blocks, blocks of dnodes,
* etc.) is tracked separately so that it can be managed more
* explicitly: favored over data, limited explicitly.
*
* Anonymous buffers are buffers that are not associated with
* a DVA. These are buffers that hold dirty block copies
* before they are written to stable storage. By definition,
* they are "ref'd" and are considered part of arc_mru
* that cannot be freed. Generally, they will acquire a DVA
* as they are written and migrate onto the arc_mru list.
*
* The ARC_l2c_only state is for buffers that are in the second
* level ARC but no longer in any of the ARC_m* lists. The second
* level ARC itself may also contain buffers that are in any of
* the ARC_m* states - meaning that a buffer can exist in two
* places. The reason for the ARC_l2c_only state is to keep the
* buffer header in the hash table, so that reads that hit the
* second level ARC benefit from these fast lookups.
*/
typedef struct arc_state {
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
/*
* list of evictable buffers
*/
multilist_t *arcs_list[ARC_BUFC_NUMTYPES];
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
/*
* total amount of evictable data in this state
*/
zfs_refcount_t arcs_esize[ARC_BUFC_NUMTYPES];
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
/*
* total amount of data in this state; this includes: evictable,
* non-evictable, ARC_BUFC_DATA, and ARC_BUFC_METADATA.
*/
zfs_refcount_t arcs_size;
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
/*
* supports the "dbufs" kstat
*/
arc_state_type_t arcs_state;
} arc_state_t;
typedef struct arc_callback arc_callback_t;
struct arc_callback {
void *acb_private;
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
arc_read_done_func_t *acb_done;
arc_buf_t *acb_buf;
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 acb_encrypted;
boolean_t acb_compressed;
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 acb_noauth;
zbookmark_phys_t acb_zb;
zio_t *acb_zio_dummy;
zio_t *acb_zio_head;
arc_callback_t *acb_next;
};
typedef struct arc_write_callback arc_write_callback_t;
struct arc_write_callback {
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
void *awcb_private;
arc_write_done_func_t *awcb_ready;
arc_write_done_func_t *awcb_children_ready;
arc_write_done_func_t *awcb_physdone;
arc_write_done_func_t *awcb_done;
arc_buf_t *awcb_buf;
};
/*
* ARC buffers are separated into multiple structs as a memory saving measure:
* - Common fields struct, always defined, and embedded within it:
* - L2-only fields, always allocated but undefined when not in L2ARC
* - L1-only fields, only allocated when in L1ARC
*
* Buffer in L1 Buffer only in L2
* +------------------------+ +------------------------+
* | arc_buf_hdr_t | | arc_buf_hdr_t |
* | | | |
* | | | |
* | | | |
* +------------------------+ +------------------------+
* | l2arc_buf_hdr_t | | l2arc_buf_hdr_t |
* | (undefined if L1-only) | | |
* +------------------------+ +------------------------+
* | l1arc_buf_hdr_t |
* | |
* | |
* | |
* | |
* +------------------------+
*
* Because it's possible for the L2ARC to become extremely large, we can wind
* up eating a lot of memory in L2ARC buffer headers, so the size of a header
* is minimized by only allocating the fields necessary for an L1-cached buffer
* when a header is actually in the L1 cache. The sub-headers (l1arc_buf_hdr and
* l2arc_buf_hdr) are embedded rather than allocated separately to save a couple
* words in pointers. arc_hdr_realloc() is used to switch a header between
* these two allocation states.
*/
typedef struct l1arc_buf_hdr {
kmutex_t b_freeze_lock;
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
zio_cksum_t *b_freeze_cksum;
arc_buf_t *b_buf;
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
uint32_t b_bufcnt;
/* for waiting on writes to complete */
kcondvar_t b_cv;
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
uint8_t b_byteswap;
/* protected by arc state mutex */
arc_state_t *b_state;
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
multilist_node_t b_arc_node;
/* updated atomically */
clock_t b_arc_access;
uint32_t b_mru_hits;
uint32_t b_mru_ghost_hits;
uint32_t b_mfu_hits;
uint32_t b_mfu_ghost_hits;
uint32_t b_l2_hits;
/* self protecting */
zfs_refcount_t b_refcnt;
arc_callback_t *b_acb;
abd_t *b_pabd;
} l1arc_buf_hdr_t;
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
/*
* Encrypted blocks will need to be stored encrypted on the L2ARC
* disk as they appear in the main pool. In order for this to work we
* need to pass around the encryption parameters so they can be used
* to write data to the L2ARC. This struct is only defined in the
* arc_buf_hdr_t if the L1 header is defined and has the ARC_FLAG_ENCRYPTED
* flag set.
*/
typedef struct arc_buf_hdr_crypt {
abd_t *b_rabd; /* raw encrypted data */
dmu_object_type_t b_ot; /* object type */
uint32_t b_ebufcnt; /* count of encrypted buffers */
/* dsobj for looking up encryption key for l2arc encryption */
uint64_t b_dsobj;
/* encryption parameters */
uint8_t b_salt[ZIO_DATA_SALT_LEN];
uint8_t b_iv[ZIO_DATA_IV_LEN];
/*
* Technically this could be removed since we will always be able to
* get the mac from the bp when we need it. However, it is inconvenient
* for callers of arc code to have to pass a bp in all the time. This
* also allows us to assert that L2ARC data is properly encrypted to
* match the data in the main storage pool.
*/
uint8_t b_mac[ZIO_DATA_MAC_LEN];
} arc_buf_hdr_crypt_t;
typedef struct l2arc_dev {
vdev_t *l2ad_vdev; /* vdev */
spa_t *l2ad_spa; /* spa */
uint64_t l2ad_hand; /* next write location */
uint64_t l2ad_start; /* first addr on device */
uint64_t l2ad_end; /* last addr on device */
boolean_t l2ad_first; /* first sweep through */
boolean_t l2ad_writing; /* currently writing */
kmutex_t l2ad_mtx; /* lock for buffer list */
list_t l2ad_buflist; /* buffer list */
list_node_t l2ad_node; /* device list node */
zfs_refcount_t l2ad_alloc; /* allocated bytes */
} l2arc_dev_t;
typedef struct l2arc_buf_hdr {
/* protected by arc_buf_hdr mutex */
l2arc_dev_t *b_dev; /* L2ARC device */
uint64_t b_daddr; /* disk address, offset byte */
uint32_t b_hits;
list_node_t b_l2node;
} l2arc_buf_hdr_t;
Remove duplicate typedefs from trace.h Older versions of GCC (e.g. GCC 4.4.7 on RHEL6) do not allow duplicate typedef declarations with the same type. The trace.h header contains some typedefs to avoid 'unknown type' errors for C files that haven't declared the type in question. But this causes build failures for C files that have already declared the type. Newer versions of GCC (e.g. v4.6) allow duplicate typedefs with the same type unless pedantic error checking is in force. To support the older versions we need to remove the duplicate typedefs. Removal of the typedefs means we can't built tracepoints code using those types unless the required headers have been included. To facilitate this, all tracepoint event declarations have been moved out of trace.h into separate headers. Each new header is explicitly included from the C file that uses the events defined therein. The trace.h header is still indirectly included form zfs_context.h and provides the implementation of the dprintf(), dbgmsg(), and SET_ERROR() interfaces. This makes those interfaces readily available throughout the code base. The macros that redefine DTRACE_PROBE* to use Linux tracepoints are also still provided by trace.h, so it is a prerequisite for the other trace_*.h headers. These new Linux implementation-specific headers do introduce a small divergence from upstream ZFS in several core C files, but this should not present a significant maintenance burden. Signed-off-by: Ned Bass <bass6@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Issue #2953
2014-12-13 05:07:39 +03:00
typedef struct l2arc_write_callback {
l2arc_dev_t *l2wcb_dev; /* device info */
arc_buf_hdr_t *l2wcb_head; /* head of write buflist */
} l2arc_write_callback_t;
struct arc_buf_hdr {
/* protected by hash lock */
dva_t b_dva;
uint64_t b_birth;
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
arc_buf_contents_t b_type;
arc_buf_hdr_t *b_hash_next;
arc_flags_t b_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
/*
* This field stores the size of the data buffer after
* compression, and is set in the arc's zio completion handlers.
* It is in units of SPA_MINBLOCKSIZE (e.g. 1 == 512 bytes).
*
* While the block pointers can store up to 32MB in their psize
* field, we can only store up to 32MB minus 512B. This is due
* to the bp using a bias of 1, whereas we use a bias of 0 (i.e.
* a field of zeros represents 512B in the bp). We can't use a
* bias of 1 since we need to reserve a psize of zero, here, to
* represent holes and embedded blocks.
*
* This isn't a problem in practice, since the maximum size of a
* buffer is limited to 16MB, so we never need to store 32MB in
* this field. Even in the upstream illumos code base, the
* maximum size of a buffer is limited to 16MB.
*/
uint16_t b_psize;
/*
* This field stores the size of the data buffer before
* compression, and cannot change once set. It is in units
* of SPA_MINBLOCKSIZE (e.g. 2 == 1024 bytes)
*/
uint16_t b_lsize; /* immutable */
uint64_t b_spa; /* immutable */
/* L2ARC fields. Undefined when not in L2ARC. */
l2arc_buf_hdr_t b_l2hdr;
/* L1ARC fields. Undefined when in l2arc_only state */
l1arc_buf_hdr_t b_l1hdr;
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
/*
* Encryption parameters. Defined only when ARC_FLAG_ENCRYPTED
* is set and the L1 header exists.
*/
arc_buf_hdr_crypt_t b_crypt_hdr;
};
typedef struct arc_stats {
kstat_named_t arcstat_hits;
kstat_named_t arcstat_misses;
kstat_named_t arcstat_demand_data_hits;
kstat_named_t arcstat_demand_data_misses;
kstat_named_t arcstat_demand_metadata_hits;
kstat_named_t arcstat_demand_metadata_misses;
kstat_named_t arcstat_prefetch_data_hits;
kstat_named_t arcstat_prefetch_data_misses;
kstat_named_t arcstat_prefetch_metadata_hits;
kstat_named_t arcstat_prefetch_metadata_misses;
kstat_named_t arcstat_mru_hits;
kstat_named_t arcstat_mru_ghost_hits;
kstat_named_t arcstat_mfu_hits;
kstat_named_t arcstat_mfu_ghost_hits;
kstat_named_t arcstat_deleted;
/*
* Number of buffers that could not be evicted because the hash lock
* was held by another thread. The lock may not necessarily be held
* by something using the same buffer, since hash locks are shared
* by multiple buffers.
*/
kstat_named_t arcstat_mutex_miss;
/*
* Number of buffers skipped when updating the access state due to the
* header having already been released after acquiring the hash lock.
*/
kstat_named_t arcstat_access_skip;
/*
* Number of buffers skipped because they have I/O in progress, are
* indirect prefetch buffers that have not lived long enough, or are
* not from the spa we're trying to evict from.
*/
kstat_named_t arcstat_evict_skip;
/*
* Number of times arc_evict_state() was unable to evict enough
* buffers to reach its target amount.
*/
kstat_named_t arcstat_evict_not_enough;
kstat_named_t arcstat_evict_l2_cached;
kstat_named_t arcstat_evict_l2_eligible;
kstat_named_t arcstat_evict_l2_ineligible;
kstat_named_t arcstat_evict_l2_skip;
kstat_named_t arcstat_hash_elements;
kstat_named_t arcstat_hash_elements_max;
kstat_named_t arcstat_hash_collisions;
kstat_named_t arcstat_hash_chains;
kstat_named_t arcstat_hash_chain_max;
kstat_named_t arcstat_p;
kstat_named_t arcstat_c;
kstat_named_t arcstat_c_min;
kstat_named_t arcstat_c_max;
/* Not updated directly; only synced in arc_kstat_update. */
kstat_named_t arcstat_size;
/*
* Number of compressed bytes stored in the arc_buf_hdr_t's b_pabd.
* Note that the compressed bytes may match the uncompressed bytes
* if the block is either not compressed or compressed arc is disabled.
*/
kstat_named_t arcstat_compressed_size;
/*
* Uncompressed size of the data stored in b_pabd. If compressed
* arc is disabled then this value will be identical to the stat
* above.
*/
kstat_named_t arcstat_uncompressed_size;
/*
* Number of bytes stored in all the arc_buf_t's. This is classified
* as "overhead" since this data is typically short-lived and will
* be evicted from the arc when it becomes unreferenced unless the
* zfs_keep_uncompressed_metadata or zfs_keep_uncompressed_level
* values have been set (see comment in dbuf.c for more information).
*/
kstat_named_t arcstat_overhead_size;
/*
* Number of bytes consumed by internal ARC structures necessary
* for tracking purposes; these structures are not actually
* backed by ARC buffers. This includes arc_buf_hdr_t structures
* (allocated via arc_buf_hdr_t_full and arc_buf_hdr_t_l2only
* caches), and arc_buf_t structures (allocated via arc_buf_t
* cache).
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_hdr_size;
/*
* Number of bytes consumed by ARC buffers of type equal to
* ARC_BUFC_DATA. This is generally consumed by buffers backing
* on disk user data (e.g. plain file contents).
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_data_size;
/*
* Number of bytes consumed by ARC buffers of type equal to
* ARC_BUFC_METADATA. This is generally consumed by buffers
* backing on disk data that is used for internal ZFS
* structures (e.g. ZAP, dnode, indirect blocks, etc).
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_metadata_size;
/*
* Number of bytes consumed by dmu_buf_impl_t objects.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_dbuf_size;
/*
* Number of bytes consumed by dnode_t objects.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_dnode_size;
/*
* Number of bytes consumed by bonus buffers.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_bonus_size;
/*
* Total number of bytes consumed by ARC buffers residing in the
* arc_anon state. This includes *all* buffers in the arc_anon
* state; e.g. data, metadata, evictable, and unevictable buffers
* are all included in this value.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_anon_size;
/*
* Number of bytes consumed by ARC buffers that meet the
* following criteria: backing buffers of type ARC_BUFC_DATA,
* residing in the arc_anon state, and are eligible for eviction
* (e.g. have no outstanding holds on the buffer).
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_anon_evictable_data;
/*
* Number of bytes consumed by ARC buffers that meet the
* following criteria: backing buffers of type ARC_BUFC_METADATA,
* residing in the arc_anon state, and are eligible for eviction
* (e.g. have no outstanding holds on the buffer).
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_anon_evictable_metadata;
/*
* Total number of bytes consumed by ARC buffers residing in the
* arc_mru state. This includes *all* buffers in the arc_mru
* state; e.g. data, metadata, evictable, and unevictable buffers
* are all included in this value.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mru_size;
/*
* Number of bytes consumed by ARC buffers that meet the
* following criteria: backing buffers of type ARC_BUFC_DATA,
* residing in the arc_mru state, and are eligible for eviction
* (e.g. have no outstanding holds on the buffer).
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mru_evictable_data;
/*
* Number of bytes consumed by ARC buffers that meet the
* following criteria: backing buffers of type ARC_BUFC_METADATA,
* residing in the arc_mru state, and are eligible for eviction
* (e.g. have no outstanding holds on the buffer).
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mru_evictable_metadata;
/*
* Total number of bytes that *would have been* consumed by ARC
* buffers in the arc_mru_ghost state. The key thing to note
* here, is the fact that this size doesn't actually indicate
* RAM consumption. The ghost lists only consist of headers and
* don't actually have ARC buffers linked off of these headers.
* Thus, *if* the headers had associated ARC buffers, these
* buffers *would have* consumed this number of bytes.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mru_ghost_size;
/*
* Number of bytes that *would have been* consumed by ARC
* buffers that are eligible for eviction, of type
* ARC_BUFC_DATA, and linked off the arc_mru_ghost state.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mru_ghost_evictable_data;
/*
* Number of bytes that *would have been* consumed by ARC
* buffers that are eligible for eviction, of type
* ARC_BUFC_METADATA, and linked off the arc_mru_ghost state.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mru_ghost_evictable_metadata;
/*
* Total number of bytes consumed by ARC buffers residing in the
* arc_mfu state. This includes *all* buffers in the arc_mfu
* state; e.g. data, metadata, evictable, and unevictable buffers
* are all included in this value.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mfu_size;
/*
* Number of bytes consumed by ARC buffers that are eligible for
* eviction, of type ARC_BUFC_DATA, and reside in the arc_mfu
* state.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mfu_evictable_data;
/*
* Number of bytes consumed by ARC buffers that are eligible for
* eviction, of type ARC_BUFC_METADATA, and reside in the
* arc_mfu state.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mfu_evictable_metadata;
/*
* Total number of bytes that *would have been* consumed by ARC
* buffers in the arc_mfu_ghost state. See the comment above
* arcstat_mru_ghost_size for more details.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mfu_ghost_size;
/*
* Number of bytes that *would have been* consumed by ARC
* buffers that are eligible for eviction, of type
* ARC_BUFC_DATA, and linked off the arc_mfu_ghost state.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mfu_ghost_evictable_data;
/*
* Number of bytes that *would have been* consumed by ARC
* buffers that are eligible for eviction, of type
* ARC_BUFC_METADATA, and linked off the arc_mru_ghost state.
* Not updated directly; only synced in arc_kstat_update.
*/
kstat_named_t arcstat_mfu_ghost_evictable_metadata;
kstat_named_t arcstat_l2_hits;
kstat_named_t arcstat_l2_misses;
kstat_named_t arcstat_l2_feeds;
kstat_named_t arcstat_l2_rw_clash;
kstat_named_t arcstat_l2_read_bytes;
kstat_named_t arcstat_l2_write_bytes;
kstat_named_t arcstat_l2_writes_sent;
kstat_named_t arcstat_l2_writes_done;
kstat_named_t arcstat_l2_writes_error;
kstat_named_t arcstat_l2_writes_lock_retry;
kstat_named_t arcstat_l2_evict_lock_retry;
kstat_named_t arcstat_l2_evict_reading;
kstat_named_t arcstat_l2_evict_l1cached;
kstat_named_t arcstat_l2_free_on_write;
kstat_named_t arcstat_l2_abort_lowmem;
kstat_named_t arcstat_l2_cksum_bad;
kstat_named_t arcstat_l2_io_error;
kstat_named_t arcstat_l2_lsize;
kstat_named_t arcstat_l2_psize;
/* Not updated directly; only synced in arc_kstat_update. */
kstat_named_t arcstat_l2_hdr_size;
kstat_named_t arcstat_memory_throttle_count;
kstat_named_t arcstat_memory_direct_count;
kstat_named_t arcstat_memory_indirect_count;
kstat_named_t arcstat_memory_all_bytes;
kstat_named_t arcstat_memory_free_bytes;
kstat_named_t arcstat_memory_available_bytes;
kstat_named_t arcstat_no_grow;
kstat_named_t arcstat_tempreserve;
kstat_named_t arcstat_loaned_bytes;
kstat_named_t arcstat_prune;
/* Not updated directly; only synced in arc_kstat_update. */
kstat_named_t arcstat_meta_used;
kstat_named_t arcstat_meta_limit;
kstat_named_t arcstat_dnode_limit;
kstat_named_t arcstat_meta_max;
kstat_named_t arcstat_meta_min;
kstat_named_t arcstat_async_upgrade_sync;
kstat_named_t arcstat_demand_hit_predictive_prefetch;
kstat_named_t arcstat_demand_hit_prescient_prefetch;
kstat_named_t arcstat_need_free;
kstat_named_t arcstat_sys_free;
kstat_named_t arcstat_raw_size;
} arc_stats_t;
typedef enum free_memory_reason_t {
FMR_UNKNOWN,
FMR_NEEDFREE,
FMR_LOTSFREE,
FMR_SWAPFS_MINFREE,
FMR_PAGES_PP_MAXIMUM,
FMR_HEAP_ARENA,
FMR_ZIO_ARENA,
} free_memory_reason_t;
#define ARCSTAT(stat) (arc_stats.stat.value.ui64)
#define ARCSTAT_INCR(stat, val) \
atomic_add_64(&arc_stats.stat.value.ui64, (val))
#define ARCSTAT_BUMP(stat) ARCSTAT_INCR(stat, 1)
#define ARCSTAT_BUMPDOWN(stat) ARCSTAT_INCR(stat, -1)
#define arc_no_grow ARCSTAT(arcstat_no_grow) /* do not grow cache size */
#define arc_p ARCSTAT(arcstat_p) /* target size of MRU */
#define arc_c ARCSTAT(arcstat_c) /* target size of cache */
#define arc_c_min ARCSTAT(arcstat_c_min) /* min target cache size */
#define arc_c_max ARCSTAT(arcstat_c_max) /* max target cache size */
#define arc_sys_free ARCSTAT(arcstat_sys_free) /* target system free bytes */
#define arc_need_free ARCSTAT(arcstat_need_free) /* bytes to be freed */
extern int arc_zio_arena_free_shift;
extern taskq_t *arc_prune_taskq;
extern arc_stats_t arc_stats;
extern hrtime_t arc_growtime;
extern boolean_t arc_warm;
extern int arc_grow_retry;
extern int arc_shrink_shift;
extern zthr_t *arc_adjust_zthr;
extern kmutex_t arc_adjust_lock;
extern kcondvar_t arc_adjust_waiters_cv;
extern boolean_t arc_adjust_needed;
extern kmutex_t arc_prune_mtx;
extern list_t arc_prune_list;
extern aggsum_t arc_size;
extern arc_state_t *arc_mfu;
extern arc_state_t *arc_mru;
extern uint_t zfs_arc_pc_percent;
extern int arc_lotsfree_percent;
extern void arc_reduce_target_size(int64_t to_free);
extern boolean_t arc_reclaim_needed(void);
extern void arc_kmem_reap_soon(void);
extern void arc_lowmem_init(void);
extern void arc_lowmem_fini(void);
extern void arc_prune_async(int64_t);
extern int arc_memory_throttle(spa_t *spa, uint64_t reserve, uint64_t txg);
extern uint64_t arc_free_memory(void);
extern int64_t arc_available_memory(void);
#ifdef __cplusplus
}
#endif
#endif /* _SYS_ARC_IMPL_H */