freebsd-nq/module/zfs/ddt.c

1250 lines
29 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) 2009, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2012, 2016 by Delphix. All rights reserved.
*/
#include <sys/zfs_context.h>
#include <sys/spa.h>
#include <sys/spa_impl.h>
#include <sys/zio.h>
#include <sys/ddt.h>
#include <sys/zap.h>
#include <sys/dmu_tx.h>
#include <sys/arc.h>
#include <sys/dsl_pool.h>
#include <sys/zio_checksum.h>
#include <sys/zio_compress.h>
#include <sys/dsl_scan.h>
#include <sys/abd.h>
static kmem_cache_t *ddt_cache;
static kmem_cache_t *ddt_entry_cache;
/*
* Enable/disable prefetching of dedup-ed blocks which are going to be freed.
*/
int zfs_dedup_prefetch = 0;
static const ddt_ops_t *ddt_ops[DDT_TYPES] = {
&ddt_zap_ops,
};
static const char *ddt_class_name[DDT_CLASSES] = {
"ditto",
"duplicate",
"unique",
};
static void
ddt_object_create(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
dmu_tx_t *tx)
{
spa_t *spa = ddt->ddt_spa;
objset_t *os = ddt->ddt_os;
uint64_t *objectp = &ddt->ddt_object[type][class];
OpenZFS 4185 - add new cryptographic checksums to ZFS: SHA-512, Skein, Edon-R Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Saso Kiselkov <saso.kiselkov@nexenta.com> Reviewed by: Richard Lowe <richlowe@richlowe.net> Approved by: Garrett D'Amore <garrett@damore.org> Ported by: Tony Hutter <hutter2@llnl.gov> OpenZFS-issue: https://www.illumos.org/issues/4185 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/45818ee Porting Notes: This code is ported on top of the Illumos Crypto Framework code: https://github.com/zfsonlinux/zfs/pull/4329/commits/b5e030c8dbb9cd393d313571dee4756fbba8c22d The list of porting changes includes: - Copied module/icp/include/sha2/sha2.h directly from illumos - Removed from module/icp/algs/sha2/sha2.c: #pragma inline(SHA256Init, SHA384Init, SHA512Init) - Added 'ctx' to lib/libzfs/libzfs_sendrecv.c:zio_checksum_SHA256() since it now takes in an extra parameter. - Added CTASSERT() to assert.h from for module/zfs/edonr_zfs.c - Added skein & edonr to libicp/Makefile.am - Added sha512.S. It was generated from sha512-x86_64.pl in Illumos. - Updated ztest.c with new fletcher_4_*() args; used NULL for new CTX argument. - In icp/algs/edonr/edonr_byteorder.h, Removed the #if defined(__linux) section to not #include the non-existant endian.h. - In skein_test.c, renane NULL to 0 in "no test vector" array entries to get around a compiler warning. - Fixup test files: - Rename <sys/varargs.h> -> <varargs.h>, <strings.h> -> <string.h>, - Remove <note.h> and define NOTE() as NOP. - Define u_longlong_t - Rename "#!/usr/bin/ksh" -> "#!/bin/ksh -p" - Rename NULL to 0 in "no test vector" array entries to get around a compiler warning. - Remove "for isa in $($ISAINFO); do" stuff - Add/update Makefiles - Add some userspace headers like stdio.h/stdlib.h in places of sys/types.h. - EXPORT_SYMBOL *_Init/*_Update/*_Final... routines in ICP modules. - Update scripts/zfs2zol-patch.sed - include <sys/sha2.h> in sha2_impl.h - Add sha2.h to include/sys/Makefile.am - Add skein and edonr dirs to icp Makefile - Add new checksums to zpool_get.cfg - Move checksum switch block from zfs_secpolicy_setprop() to zfs_check_settable() - Fix -Wuninitialized error in edonr_byteorder.h on PPC - Fix stack frame size errors on ARM32 - Don't unroll loops in Skein on 32-bit to save stack space - Add memory barriers in sha2.c on 32-bit to save stack space - Add filetest_001_pos.ksh checksum sanity test - Add option to write psudorandom data in file_write utility
2016-06-15 22:47:05 +00:00
boolean_t prehash = zio_checksum_table[ddt->ddt_checksum].ci_flags &
ZCHECKSUM_FLAG_DEDUP;
char name[DDT_NAMELEN];
ddt_object_name(ddt, type, class, name);
ASSERT(*objectp == 0);
VERIFY(ddt_ops[type]->ddt_op_create(os, objectp, tx, prehash) == 0);
ASSERT(*objectp != 0);
VERIFY(zap_add(os, DMU_POOL_DIRECTORY_OBJECT, name,
sizeof (uint64_t), 1, objectp, tx) == 0);
VERIFY(zap_add(os, spa->spa_ddt_stat_object, name,
sizeof (uint64_t), sizeof (ddt_histogram_t) / sizeof (uint64_t),
&ddt->ddt_histogram[type][class], tx) == 0);
}
static void
ddt_object_destroy(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
dmu_tx_t *tx)
{
spa_t *spa = ddt->ddt_spa;
objset_t *os = ddt->ddt_os;
uint64_t *objectp = &ddt->ddt_object[type][class];
uint64_t count;
char name[DDT_NAMELEN];
ddt_object_name(ddt, type, class, name);
ASSERT(*objectp != 0);
ASSERT(ddt_histogram_empty(&ddt->ddt_histogram[type][class]));
VERIFY(ddt_object_count(ddt, type, class, &count) == 0 && count == 0);
VERIFY(zap_remove(os, DMU_POOL_DIRECTORY_OBJECT, name, tx) == 0);
VERIFY(zap_remove(os, spa->spa_ddt_stat_object, name, tx) == 0);
VERIFY(ddt_ops[type]->ddt_op_destroy(os, *objectp, tx) == 0);
bzero(&ddt->ddt_object_stats[type][class], sizeof (ddt_object_t));
*objectp = 0;
}
static int
ddt_object_load(ddt_t *ddt, enum ddt_type type, enum ddt_class class)
{
ddt_object_t *ddo = &ddt->ddt_object_stats[type][class];
dmu_object_info_t doi;
uint64_t count;
char name[DDT_NAMELEN];
int error;
ddt_object_name(ddt, type, class, name);
error = zap_lookup(ddt->ddt_os, DMU_POOL_DIRECTORY_OBJECT, name,
sizeof (uint64_t), 1, &ddt->ddt_object[type][class]);
if (error != 0)
return (error);
error = zap_lookup(ddt->ddt_os, ddt->ddt_spa->spa_ddt_stat_object, name,
sizeof (uint64_t), sizeof (ddt_histogram_t) / sizeof (uint64_t),
&ddt->ddt_histogram[type][class]);
if (error != 0)
return (error);
/*
* Seed the cached statistics.
*/
error = ddt_object_info(ddt, type, class, &doi);
if (error)
return (error);
error = ddt_object_count(ddt, type, class, &count);
if (error)
return (error);
ddo->ddo_count = count;
ddo->ddo_dspace = doi.doi_physical_blocks_512 << 9;
ddo->ddo_mspace = doi.doi_fill_count * doi.doi_data_block_size;
return (0);
}
static void
ddt_object_sync(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
dmu_tx_t *tx)
{
ddt_object_t *ddo = &ddt->ddt_object_stats[type][class];
dmu_object_info_t doi;
uint64_t count;
char name[DDT_NAMELEN];
ddt_object_name(ddt, type, class, name);
VERIFY(zap_update(ddt->ddt_os, ddt->ddt_spa->spa_ddt_stat_object, name,
sizeof (uint64_t), sizeof (ddt_histogram_t) / sizeof (uint64_t),
&ddt->ddt_histogram[type][class], tx) == 0);
/*
* Cache DDT statistics; this is the only time they'll change.
*/
VERIFY(ddt_object_info(ddt, type, class, &doi) == 0);
VERIFY(ddt_object_count(ddt, type, class, &count) == 0);
ddo->ddo_count = count;
ddo->ddo_dspace = doi.doi_physical_blocks_512 << 9;
ddo->ddo_mspace = doi.doi_fill_count * doi.doi_data_block_size;
}
static int
ddt_object_lookup(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
ddt_entry_t *dde)
{
if (!ddt_object_exists(ddt, type, class))
return (SET_ERROR(ENOENT));
return (ddt_ops[type]->ddt_op_lookup(ddt->ddt_os,
ddt->ddt_object[type][class], dde));
}
static void
ddt_object_prefetch(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
ddt_entry_t *dde)
{
if (!ddt_object_exists(ddt, type, class))
return;
ddt_ops[type]->ddt_op_prefetch(ddt->ddt_os,
ddt->ddt_object[type][class], dde);
}
int
ddt_object_update(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
ddt_entry_t *dde, dmu_tx_t *tx)
{
ASSERT(ddt_object_exists(ddt, type, class));
return (ddt_ops[type]->ddt_op_update(ddt->ddt_os,
ddt->ddt_object[type][class], dde, tx));
}
static int
ddt_object_remove(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
ddt_entry_t *dde, dmu_tx_t *tx)
{
ASSERT(ddt_object_exists(ddt, type, class));
return (ddt_ops[type]->ddt_op_remove(ddt->ddt_os,
ddt->ddt_object[type][class], dde, tx));
}
int
ddt_object_walk(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
uint64_t *walk, ddt_entry_t *dde)
{
ASSERT(ddt_object_exists(ddt, type, class));
return (ddt_ops[type]->ddt_op_walk(ddt->ddt_os,
ddt->ddt_object[type][class], dde, walk));
}
int
ddt_object_count(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
uint64_t *count)
{
ASSERT(ddt_object_exists(ddt, type, class));
return (ddt_ops[type]->ddt_op_count(ddt->ddt_os,
ddt->ddt_object[type][class], count));
}
int
ddt_object_info(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
dmu_object_info_t *doi)
{
if (!ddt_object_exists(ddt, type, class))
return (SET_ERROR(ENOENT));
return (dmu_object_info(ddt->ddt_os, ddt->ddt_object[type][class],
doi));
}
boolean_t
ddt_object_exists(ddt_t *ddt, enum ddt_type type, enum ddt_class class)
{
return (!!ddt->ddt_object[type][class]);
}
void
ddt_object_name(ddt_t *ddt, enum ddt_type type, enum ddt_class class,
char *name)
{
(void) sprintf(name, DMU_POOL_DDT,
zio_checksum_table[ddt->ddt_checksum].ci_name,
ddt_ops[type]->ddt_op_name, ddt_class_name[class]);
}
void
ddt_bp_fill(const ddt_phys_t *ddp, blkptr_t *bp, uint64_t txg)
{
ASSERT(txg != 0);
for (int d = 0; d < SPA_DVAS_PER_BP; d++)
bp->blk_dva[d] = ddp->ddp_dva[d];
BP_SET_BIRTH(bp, txg, ddp->ddp_phys_birth);
}
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 17:36:48 +00:00
/*
* The bp created via this function may be used for repairs and scrub, but it
* will be missing the salt / IV required to do a full decrypting read.
*/
void
ddt_bp_create(enum zio_checksum checksum,
const ddt_key_t *ddk, const ddt_phys_t *ddp, blkptr_t *bp)
{
BP_ZERO(bp);
if (ddp != NULL)
ddt_bp_fill(ddp, bp, ddp->ddp_phys_birth);
bp->blk_cksum = ddk->ddk_cksum;
BP_SET_LSIZE(bp, DDK_GET_LSIZE(ddk));
BP_SET_PSIZE(bp, DDK_GET_PSIZE(ddk));
BP_SET_COMPRESS(bp, DDK_GET_COMPRESS(ddk));
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 17:36:48 +00:00
BP_SET_CRYPT(bp, DDK_GET_CRYPT(ddk));
BP_SET_FILL(bp, 1);
BP_SET_CHECKSUM(bp, checksum);
BP_SET_TYPE(bp, DMU_OT_DEDUP);
BP_SET_LEVEL(bp, 0);
BP_SET_DEDUP(bp, 1);
BP_SET_BYTEORDER(bp, ZFS_HOST_BYTEORDER);
}
void
ddt_key_fill(ddt_key_t *ddk, const blkptr_t *bp)
{
ddk->ddk_cksum = bp->blk_cksum;
ddk->ddk_prop = 0;
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 17:36:48 +00:00
ASSERT(BP_IS_ENCRYPTED(bp) || !BP_USES_CRYPT(bp));
DDK_SET_LSIZE(ddk, BP_GET_LSIZE(bp));
DDK_SET_PSIZE(ddk, BP_GET_PSIZE(bp));
DDK_SET_COMPRESS(ddk, BP_GET_COMPRESS(bp));
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 17:36:48 +00:00
DDK_SET_CRYPT(ddk, BP_USES_CRYPT(bp));
}
void
ddt_phys_fill(ddt_phys_t *ddp, const blkptr_t *bp)
{
ASSERT(ddp->ddp_phys_birth == 0);
for (int d = 0; d < SPA_DVAS_PER_BP; d++)
ddp->ddp_dva[d] = bp->blk_dva[d];
ddp->ddp_phys_birth = BP_PHYSICAL_BIRTH(bp);
}
void
ddt_phys_clear(ddt_phys_t *ddp)
{
bzero(ddp, sizeof (*ddp));
}
void
ddt_phys_addref(ddt_phys_t *ddp)
{
ddp->ddp_refcnt++;
}
void
ddt_phys_decref(ddt_phys_t *ddp)
{
if (ddp) {
ASSERT(ddp->ddp_refcnt > 0);
ddp->ddp_refcnt--;
}
}
void
ddt_phys_free(ddt_t *ddt, ddt_key_t *ddk, ddt_phys_t *ddp, uint64_t txg)
{
blkptr_t blk;
ddt_bp_create(ddt->ddt_checksum, ddk, ddp, &blk);
/*
* We clear the dedup bit so that zio_free() will actually free the
* space, rather than just decrementing the refcount in the DDT.
*/
BP_SET_DEDUP(&blk, 0);
ddt_phys_clear(ddp);
zio_free(ddt->ddt_spa, txg, &blk);
}
ddt_phys_t *
ddt_phys_select(const ddt_entry_t *dde, const blkptr_t *bp)
{
ddt_phys_t *ddp = (ddt_phys_t *)dde->dde_phys;
for (int p = 0; p < DDT_PHYS_TYPES; p++, ddp++) {
if (DVA_EQUAL(BP_IDENTITY(bp), &ddp->ddp_dva[0]) &&
BP_PHYSICAL_BIRTH(bp) == ddp->ddp_phys_birth)
return (ddp);
}
return (NULL);
}
uint64_t
ddt_phys_total_refcnt(const ddt_entry_t *dde)
{
uint64_t refcnt = 0;
for (int p = DDT_PHYS_SINGLE; p <= DDT_PHYS_TRIPLE; p++)
refcnt += dde->dde_phys[p].ddp_refcnt;
return (refcnt);
}
static void
ddt_stat_generate(ddt_t *ddt, ddt_entry_t *dde, ddt_stat_t *dds)
{
spa_t *spa = ddt->ddt_spa;
ddt_phys_t *ddp = dde->dde_phys;
ddt_key_t *ddk = &dde->dde_key;
uint64_t lsize = DDK_GET_LSIZE(ddk);
uint64_t psize = DDK_GET_PSIZE(ddk);
bzero(dds, sizeof (*dds));
for (int p = 0; p < DDT_PHYS_TYPES; p++, ddp++) {
uint64_t dsize = 0;
uint64_t refcnt = ddp->ddp_refcnt;
if (ddp->ddp_phys_birth == 0)
continue;
for (int d = 0; d < DDE_GET_NDVAS(dde); d++)
dsize += dva_get_dsize_sync(spa, &ddp->ddp_dva[d]);
dds->dds_blocks += 1;
dds->dds_lsize += lsize;
dds->dds_psize += psize;
dds->dds_dsize += dsize;
dds->dds_ref_blocks += refcnt;
dds->dds_ref_lsize += lsize * refcnt;
dds->dds_ref_psize += psize * refcnt;
dds->dds_ref_dsize += dsize * refcnt;
}
}
void
ddt_stat_add(ddt_stat_t *dst, const ddt_stat_t *src, uint64_t neg)
{
const uint64_t *s = (const uint64_t *)src;
uint64_t *d = (uint64_t *)dst;
uint64_t *d_end = (uint64_t *)(dst + 1);
ASSERT(neg == 0 || neg == -1ULL); /* add or subtract */
while (d < d_end)
*d++ += (*s++ ^ neg) - neg;
}
static void
ddt_stat_update(ddt_t *ddt, ddt_entry_t *dde, uint64_t neg)
{
ddt_stat_t dds;
ddt_histogram_t *ddh;
int bucket;
ddt_stat_generate(ddt, dde, &dds);
bucket = highbit64(dds.dds_ref_blocks) - 1;
ASSERT(bucket >= 0);
ddh = &ddt->ddt_histogram[dde->dde_type][dde->dde_class];
ddt_stat_add(&ddh->ddh_stat[bucket], &dds, neg);
}
void
ddt_histogram_add(ddt_histogram_t *dst, const ddt_histogram_t *src)
{
for (int h = 0; h < 64; h++)
ddt_stat_add(&dst->ddh_stat[h], &src->ddh_stat[h], 0);
}
void
ddt_histogram_stat(ddt_stat_t *dds, const ddt_histogram_t *ddh)
{
bzero(dds, sizeof (*dds));
for (int h = 0; h < 64; h++)
ddt_stat_add(dds, &ddh->ddh_stat[h], 0);
}
boolean_t
ddt_histogram_empty(const ddt_histogram_t *ddh)
{
const uint64_t *s = (const uint64_t *)ddh;
const uint64_t *s_end = (const uint64_t *)(ddh + 1);
while (s < s_end)
if (*s++ != 0)
return (B_FALSE);
return (B_TRUE);
}
void
ddt_get_dedup_object_stats(spa_t *spa, ddt_object_t *ddo_total)
{
/* Sum the statistics we cached in ddt_object_sync(). */
for (enum zio_checksum c = 0; c < ZIO_CHECKSUM_FUNCTIONS; c++) {
ddt_t *ddt = spa->spa_ddt[c];
for (enum ddt_type type = 0; type < DDT_TYPES; type++) {
for (enum ddt_class class = 0; class < DDT_CLASSES;
class++) {
ddt_object_t *ddo =
&ddt->ddt_object_stats[type][class];
ddo_total->ddo_count += ddo->ddo_count;
ddo_total->ddo_dspace += ddo->ddo_dspace;
ddo_total->ddo_mspace += ddo->ddo_mspace;
}
}
}
/* ... and compute the averages. */
if (ddo_total->ddo_count != 0) {
ddo_total->ddo_dspace /= ddo_total->ddo_count;
ddo_total->ddo_mspace /= ddo_total->ddo_count;
}
}
void
ddt_get_dedup_histogram(spa_t *spa, ddt_histogram_t *ddh)
{
for (enum zio_checksum c = 0; c < ZIO_CHECKSUM_FUNCTIONS; c++) {
ddt_t *ddt = spa->spa_ddt[c];
for (enum ddt_type type = 0; type < DDT_TYPES; type++) {
for (enum ddt_class class = 0; class < DDT_CLASSES;
class++) {
ddt_histogram_add(ddh,
&ddt->ddt_histogram_cache[type][class]);
}
}
}
}
void
ddt_get_dedup_stats(spa_t *spa, ddt_stat_t *dds_total)
{
ddt_histogram_t *ddh_total;
ddh_total = kmem_zalloc(sizeof (ddt_histogram_t), KM_SLEEP);
ddt_get_dedup_histogram(spa, ddh_total);
ddt_histogram_stat(dds_total, ddh_total);
kmem_free(ddh_total, sizeof (ddt_histogram_t));
}
uint64_t
ddt_get_dedup_dspace(spa_t *spa)
{
ddt_stat_t dds_total;
if (spa->spa_dedup_dspace != ~0ULL)
return (spa->spa_dedup_dspace);
bzero(&dds_total, sizeof (ddt_stat_t));
/* Calculate and cache the stats */
ddt_get_dedup_stats(spa, &dds_total);
spa->spa_dedup_dspace = dds_total.dds_ref_dsize - dds_total.dds_dsize;
return (spa->spa_dedup_dspace);
}
uint64_t
ddt_get_pool_dedup_ratio(spa_t *spa)
{
ddt_stat_t dds_total = { 0 };
ddt_get_dedup_stats(spa, &dds_total);
if (dds_total.dds_dsize == 0)
return (100);
return (dds_total.dds_ref_dsize * 100 / dds_total.dds_dsize);
}
int
ddt_ditto_copies_needed(ddt_t *ddt, ddt_entry_t *dde, ddt_phys_t *ddp_willref)
{
spa_t *spa = ddt->ddt_spa;
uint64_t total_refcnt = 0;
uint64_t ditto = spa->spa_dedup_ditto;
int total_copies = 0;
int desired_copies = 0;
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 17:36:48 +00:00
int copies_needed = 0;
for (int p = DDT_PHYS_SINGLE; p <= DDT_PHYS_TRIPLE; p++) {
ddt_phys_t *ddp = &dde->dde_phys[p];
zio_t *zio = dde->dde_lead_zio[p];
uint64_t refcnt = ddp->ddp_refcnt; /* committed refs */
if (zio != NULL)
refcnt += zio->io_parent_count; /* pending refs */
if (ddp == ddp_willref)
refcnt++; /* caller's ref */
if (refcnt != 0) {
total_refcnt += refcnt;
total_copies += p;
}
}
if (ditto == 0 || ditto > UINT32_MAX)
ditto = UINT32_MAX;
if (total_refcnt >= 1)
desired_copies++;
if (total_refcnt >= ditto)
desired_copies++;
if (total_refcnt >= ditto * ditto)
desired_copies++;
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 17:36:48 +00:00
copies_needed = MAX(desired_copies, total_copies) - total_copies;
/* encrypted blocks store their IV in DVA[2] */
if (DDK_GET_CRYPT(&dde->dde_key))
copies_needed = MIN(copies_needed, SPA_DVAS_PER_BP - 1);
return (copies_needed);
}
int
ddt_ditto_copies_present(ddt_entry_t *dde)
{
ddt_phys_t *ddp = &dde->dde_phys[DDT_PHYS_DITTO];
dva_t *dva = ddp->ddp_dva;
int copies = 0 - DVA_GET_GANG(dva);
for (int d = 0; d < DDE_GET_NDVAS(dde); d++, dva++)
if (DVA_IS_VALID(dva))
copies++;
ASSERT(copies >= 0 && copies < SPA_DVAS_PER_BP);
return (copies);
}
size_t
ddt_compress(void *src, uchar_t *dst, size_t s_len, size_t d_len)
{
uchar_t *version = dst++;
int cpfunc = ZIO_COMPRESS_ZLE;
zio_compress_info_t *ci = &zio_compress_table[cpfunc];
size_t c_len;
ASSERT(d_len >= s_len + 1); /* no compression plus version byte */
c_len = ci->ci_compress(src, dst, s_len, d_len - 1, ci->ci_level);
if (c_len == s_len) {
cpfunc = ZIO_COMPRESS_OFF;
bcopy(src, dst, s_len);
}
*version = cpfunc;
/* CONSTCOND */
if (ZFS_HOST_BYTEORDER)
*version |= DDT_COMPRESS_BYTEORDER_MASK;
return (c_len + 1);
}
void
ddt_decompress(uchar_t *src, void *dst, size_t s_len, size_t d_len)
{
uchar_t version = *src++;
int cpfunc = version & DDT_COMPRESS_FUNCTION_MASK;
zio_compress_info_t *ci = &zio_compress_table[cpfunc];
if (ci->ci_decompress != NULL)
(void) ci->ci_decompress(src, dst, s_len, d_len, ci->ci_level);
else
bcopy(src, dst, d_len);
if (((version & DDT_COMPRESS_BYTEORDER_MASK) != 0) !=
(ZFS_HOST_BYTEORDER != 0))
byteswap_uint64_array(dst, d_len);
}
ddt_t *
ddt_select_by_checksum(spa_t *spa, enum zio_checksum c)
{
return (spa->spa_ddt[c]);
}
ddt_t *
ddt_select(spa_t *spa, const blkptr_t *bp)
{
return (spa->spa_ddt[BP_GET_CHECKSUM(bp)]);
}
void
ddt_enter(ddt_t *ddt)
{
mutex_enter(&ddt->ddt_lock);
}
void
ddt_exit(ddt_t *ddt)
{
mutex_exit(&ddt->ddt_lock);
}
void
ddt_init(void)
{
ddt_cache = kmem_cache_create("ddt_cache",
sizeof (ddt_t), 0, NULL, NULL, NULL, NULL, NULL, 0);
ddt_entry_cache = kmem_cache_create("ddt_entry_cache",
sizeof (ddt_entry_t), 0, NULL, NULL, NULL, NULL, NULL, 0);
}
void
ddt_fini(void)
{
kmem_cache_destroy(ddt_entry_cache);
kmem_cache_destroy(ddt_cache);
}
static ddt_entry_t *
ddt_alloc(const ddt_key_t *ddk)
{
ddt_entry_t *dde;
dde = kmem_cache_alloc(ddt_entry_cache, KM_SLEEP);
bzero(dde, sizeof (ddt_entry_t));
cv_init(&dde->dde_cv, NULL, CV_DEFAULT, NULL);
dde->dde_key = *ddk;
return (dde);
}
static void
ddt_free(ddt_entry_t *dde)
{
ASSERT(!dde->dde_loading);
for (int p = 0; p < DDT_PHYS_TYPES; p++)
ASSERT(dde->dde_lead_zio[p] == NULL);
if (dde->dde_repair_abd != NULL)
abd_free(dde->dde_repair_abd);
cv_destroy(&dde->dde_cv);
kmem_cache_free(ddt_entry_cache, dde);
}
void
ddt_remove(ddt_t *ddt, ddt_entry_t *dde)
{
ASSERT(MUTEX_HELD(&ddt->ddt_lock));
avl_remove(&ddt->ddt_tree, dde);
ddt_free(dde);
}
ddt_entry_t *
ddt_lookup(ddt_t *ddt, const blkptr_t *bp, boolean_t add)
{
ddt_entry_t *dde, dde_search;
enum ddt_type type;
enum ddt_class class;
avl_index_t where;
int error;
ASSERT(MUTEX_HELD(&ddt->ddt_lock));
ddt_key_fill(&dde_search.dde_key, bp);
dde = avl_find(&ddt->ddt_tree, &dde_search, &where);
if (dde == NULL) {
if (!add)
return (NULL);
dde = ddt_alloc(&dde_search.dde_key);
avl_insert(&ddt->ddt_tree, dde, where);
}
while (dde->dde_loading)
cv_wait(&dde->dde_cv, &ddt->ddt_lock);
if (dde->dde_loaded)
return (dde);
dde->dde_loading = B_TRUE;
ddt_exit(ddt);
error = ENOENT;
for (type = 0; type < DDT_TYPES; type++) {
for (class = 0; class < DDT_CLASSES; class++) {
error = ddt_object_lookup(ddt, type, class, dde);
OpenZFS 7614, 9064 - zfs device evacuation/removal OpenZFS 7614 - zfs device evacuation/removal OpenZFS 9064 - remove_mirror should wait for device removal to complete This project allows top-level vdevs to be removed from the storage pool with "zpool remove", reducing the total amount of storage in the pool. This operation copies all allocated regions of the device to be removed onto other devices, recording the mapping from old to new location. After the removal is complete, read and free operations to the removed (now "indirect") vdev must be remapped and performed at the new location on disk. The indirect mapping table is kept in memory whenever the pool is loaded, so there is minimal performance overhead when doing operations on the indirect vdev. The size of the in-memory mapping table will be reduced when its entries become "obsolete" because they are no longer used by any block pointers in the pool. An entry becomes obsolete when all the blocks that use it are freed. An entry can also become obsolete when all the snapshots that reference it are deleted, and the block pointers that reference it have been "remapped" in all filesystems/zvols (and clones). Whenever an indirect block is written, all the block pointers in it will be "remapped" to their new (concrete) locations if possible. This process can be accelerated by using the "zfs remap" command to proactively rewrite all indirect blocks that reference indirect (removed) vdevs. Note that when a device is removed, we do not verify the checksum of the data that is copied. This makes the process much faster, but if it were used on redundant vdevs (i.e. mirror or raidz vdevs), it would be possible to copy the wrong data, when we have the correct data on e.g. the other side of the mirror. At the moment, only mirrors and simple top-level vdevs can be removed and no removal is allowed if any of the top-level vdevs are raidz. Porting Notes: * Avoid zero-sized kmem_alloc() in vdev_compact_children(). The device evacuation code adds a dependency that vdev_compact_children() be able to properly empty the vdev_child array by setting it to NULL and zeroing vdev_children. Under Linux, kmem_alloc() and related functions return a sentinel pointer rather than NULL for zero-sized allocations. * Remove comment regarding "mpt" driver where zfs_remove_max_segment is initialized to SPA_MAXBLOCKSIZE. Change zfs_condense_indirect_commit_entry_delay_ticks to zfs_condense_indirect_commit_entry_delay_ms for consistency with most other tunables in which delays are specified in ms. * ZTS changes: Use set_tunable rather than mdb Use zpool sync as appropriate Use sync_pool instead of sync Kill jobs during test_removal_with_operation to allow unmount/export Don't add non-disk names such as "mirror" or "raidz" to $DISKS Use $TEST_BASE_DIR instead of /tmp Increase HZ from 100 to 1000 which is more common on Linux removal_multiple_indirection.ksh Reduce iterations in order to not time out on the code coverage builders. removal_resume_export: Functionally, the test case is correct but there exists a race where the kernel thread hasn't been fully started yet and is not visible. Wait for up to 1 second for the removal thread to be started before giving up on it. Also, increase the amount of data copied in order that the removal not finish before the export has a chance to fail. * MMP compatibility, the concept of concrete versus non-concrete devices has slightly changed the semantics of vdev_writeable(). Update mmp_random_leaf_impl() accordingly. * Updated dbuf_remap() to handle the org.zfsonlinux:large_dnode pool feature which is not supported by OpenZFS. * Added support for new vdev removal tracepoints. * Test cases removal_with_zdb and removal_condense_export have been intentionally disabled. When run manually they pass as intended, but when running in the automated test environment they produce unreliable results on the latest Fedora release. They may work better once the upstream pool import refectoring is merged into ZoL at which point they will be re-enabled. Authored by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Alex Reece <alex@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Richard Laager <rlaager@wiktel.com> Reviewed by: Tim Chase <tim@chase2k.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Garrett D'Amore <garrett@damore.org> Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Tim Chase <tim@chase2k.com> OpenZFS-issue: https://www.illumos.org/issues/7614 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/f539f1eb Closes #6900
2016-09-22 16:30:13 +00:00
if (error != ENOENT) {
ASSERT0(error);
break;
OpenZFS 7614, 9064 - zfs device evacuation/removal OpenZFS 7614 - zfs device evacuation/removal OpenZFS 9064 - remove_mirror should wait for device removal to complete This project allows top-level vdevs to be removed from the storage pool with "zpool remove", reducing the total amount of storage in the pool. This operation copies all allocated regions of the device to be removed onto other devices, recording the mapping from old to new location. After the removal is complete, read and free operations to the removed (now "indirect") vdev must be remapped and performed at the new location on disk. The indirect mapping table is kept in memory whenever the pool is loaded, so there is minimal performance overhead when doing operations on the indirect vdev. The size of the in-memory mapping table will be reduced when its entries become "obsolete" because they are no longer used by any block pointers in the pool. An entry becomes obsolete when all the blocks that use it are freed. An entry can also become obsolete when all the snapshots that reference it are deleted, and the block pointers that reference it have been "remapped" in all filesystems/zvols (and clones). Whenever an indirect block is written, all the block pointers in it will be "remapped" to their new (concrete) locations if possible. This process can be accelerated by using the "zfs remap" command to proactively rewrite all indirect blocks that reference indirect (removed) vdevs. Note that when a device is removed, we do not verify the checksum of the data that is copied. This makes the process much faster, but if it were used on redundant vdevs (i.e. mirror or raidz vdevs), it would be possible to copy the wrong data, when we have the correct data on e.g. the other side of the mirror. At the moment, only mirrors and simple top-level vdevs can be removed and no removal is allowed if any of the top-level vdevs are raidz. Porting Notes: * Avoid zero-sized kmem_alloc() in vdev_compact_children(). The device evacuation code adds a dependency that vdev_compact_children() be able to properly empty the vdev_child array by setting it to NULL and zeroing vdev_children. Under Linux, kmem_alloc() and related functions return a sentinel pointer rather than NULL for zero-sized allocations. * Remove comment regarding "mpt" driver where zfs_remove_max_segment is initialized to SPA_MAXBLOCKSIZE. Change zfs_condense_indirect_commit_entry_delay_ticks to zfs_condense_indirect_commit_entry_delay_ms for consistency with most other tunables in which delays are specified in ms. * ZTS changes: Use set_tunable rather than mdb Use zpool sync as appropriate Use sync_pool instead of sync Kill jobs during test_removal_with_operation to allow unmount/export Don't add non-disk names such as "mirror" or "raidz" to $DISKS Use $TEST_BASE_DIR instead of /tmp Increase HZ from 100 to 1000 which is more common on Linux removal_multiple_indirection.ksh Reduce iterations in order to not time out on the code coverage builders. removal_resume_export: Functionally, the test case is correct but there exists a race where the kernel thread hasn't been fully started yet and is not visible. Wait for up to 1 second for the removal thread to be started before giving up on it. Also, increase the amount of data copied in order that the removal not finish before the export has a chance to fail. * MMP compatibility, the concept of concrete versus non-concrete devices has slightly changed the semantics of vdev_writeable(). Update mmp_random_leaf_impl() accordingly. * Updated dbuf_remap() to handle the org.zfsonlinux:large_dnode pool feature which is not supported by OpenZFS. * Added support for new vdev removal tracepoints. * Test cases removal_with_zdb and removal_condense_export have been intentionally disabled. When run manually they pass as intended, but when running in the automated test environment they produce unreliable results on the latest Fedora release. They may work better once the upstream pool import refectoring is merged into ZoL at which point they will be re-enabled. Authored by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Alex Reece <alex@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Richard Laager <rlaager@wiktel.com> Reviewed by: Tim Chase <tim@chase2k.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Garrett D'Amore <garrett@damore.org> Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Tim Chase <tim@chase2k.com> OpenZFS-issue: https://www.illumos.org/issues/7614 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/f539f1eb Closes #6900
2016-09-22 16:30:13 +00:00
}
}
if (error != ENOENT)
break;
}
ddt_enter(ddt);
ASSERT(dde->dde_loaded == B_FALSE);
ASSERT(dde->dde_loading == B_TRUE);
dde->dde_type = type; /* will be DDT_TYPES if no entry found */
dde->dde_class = class; /* will be DDT_CLASSES if no entry found */
dde->dde_loaded = B_TRUE;
dde->dde_loading = B_FALSE;
if (error == 0)
ddt_stat_update(ddt, dde, -1ULL);
cv_broadcast(&dde->dde_cv);
return (dde);
}
void
ddt_prefetch(spa_t *spa, const blkptr_t *bp)
{
ddt_t *ddt;
ddt_entry_t dde;
if (!zfs_dedup_prefetch || bp == NULL || !BP_GET_DEDUP(bp))
return;
/*
* We only remove the DDT once all tables are empty and only
* prefetch dedup blocks when there are entries in the DDT.
* Thus no locking is required as the DDT can't disappear on us.
*/
ddt = ddt_select(spa, bp);
ddt_key_fill(&dde.dde_key, bp);
for (enum ddt_type type = 0; type < DDT_TYPES; type++) {
for (enum ddt_class class = 0; class < DDT_CLASSES; class++) {
ddt_object_prefetch(ddt, type, class, &dde);
}
}
}
Performance optimization of AVL tree comparator functions perf: 2.75x faster ddt_entry_compare() First 256bits of ddt_key_t is a block checksum, which are expected to be close to random data. Hence, on average, comparison only needs to look at first few bytes of the keys. To reduce number of conditional jump instructions, the result is computed as: sign(memcmp(k1, k2)). Sign of an integer 'a' can be obtained as: `(0 < a) - (a < 0)` := {-1, 0, 1} , which is computed efficiently. Synthetic performance evaluation of original and new algorithm over 1G random keys on 2.6GHz Intel(R) Xeon(R) CPU E5-2660 v3: old 6.85789 s new 2.49089 s perf: 2.8x faster vdev_queue_offset_compare() and vdev_queue_timestamp_compare() Compute the result directly instead of using conditionals perf: zfs_range_compare() Speedup between 1.1x - 2.5x, depending on compiler version and optimization level. perf: spa_error_entry_compare() `bcmp()` is not suitable for comparator use. Use `memcmp()` instead. perf: 2.8x faster metaslab_compare() and metaslab_rangesize_compare() perf: 2.8x faster zil_bp_compare() perf: 2.8x faster mze_compare() perf: faster dbuf_compare() perf: faster compares in spa_misc perf: 2.8x faster layout_hash_compare() perf: 2.8x faster space_reftree_compare() perf: libzfs: faster avl tree comparators perf: guid_compare() perf: dsl_deadlist_compare() perf: perm_set_compare() perf: 2x faster range_tree_seg_compare() perf: faster unique_compare() perf: faster vdev_cache _compare() perf: faster vdev_uberblock_compare() perf: faster fuid _compare() perf: faster zfs_znode_hold_compare() Signed-off-by: Gvozden Neskovic <neskovic@gmail.com> Signed-off-by: Richard Elling <richard.elling@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #5033
2016-08-27 18:12:53 +00:00
/*
* Opaque struct used for ddt_key comparison
*/
#define DDT_KEY_CMP_LEN (sizeof (ddt_key_t) / sizeof (uint16_t))
typedef struct ddt_key_cmp {
uint16_t u16[DDT_KEY_CMP_LEN];
} ddt_key_cmp_t;
int
ddt_entry_compare(const void *x1, const void *x2)
{
const ddt_entry_t *dde1 = x1;
const ddt_entry_t *dde2 = x2;
Performance optimization of AVL tree comparator functions perf: 2.75x faster ddt_entry_compare() First 256bits of ddt_key_t is a block checksum, which are expected to be close to random data. Hence, on average, comparison only needs to look at first few bytes of the keys. To reduce number of conditional jump instructions, the result is computed as: sign(memcmp(k1, k2)). Sign of an integer 'a' can be obtained as: `(0 < a) - (a < 0)` := {-1, 0, 1} , which is computed efficiently. Synthetic performance evaluation of original and new algorithm over 1G random keys on 2.6GHz Intel(R) Xeon(R) CPU E5-2660 v3: old 6.85789 s new 2.49089 s perf: 2.8x faster vdev_queue_offset_compare() and vdev_queue_timestamp_compare() Compute the result directly instead of using conditionals perf: zfs_range_compare() Speedup between 1.1x - 2.5x, depending on compiler version and optimization level. perf: spa_error_entry_compare() `bcmp()` is not suitable for comparator use. Use `memcmp()` instead. perf: 2.8x faster metaslab_compare() and metaslab_rangesize_compare() perf: 2.8x faster zil_bp_compare() perf: 2.8x faster mze_compare() perf: faster dbuf_compare() perf: faster compares in spa_misc perf: 2.8x faster layout_hash_compare() perf: 2.8x faster space_reftree_compare() perf: libzfs: faster avl tree comparators perf: guid_compare() perf: dsl_deadlist_compare() perf: perm_set_compare() perf: 2x faster range_tree_seg_compare() perf: faster unique_compare() perf: faster vdev_cache _compare() perf: faster vdev_uberblock_compare() perf: faster fuid _compare() perf: faster zfs_znode_hold_compare() Signed-off-by: Gvozden Neskovic <neskovic@gmail.com> Signed-off-by: Richard Elling <richard.elling@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #5033
2016-08-27 18:12:53 +00:00
const ddt_key_cmp_t *k1 = (const ddt_key_cmp_t *)&dde1->dde_key;
const ddt_key_cmp_t *k2 = (const ddt_key_cmp_t *)&dde2->dde_key;
int32_t cmp = 0;
for (int i = 0; i < DDT_KEY_CMP_LEN; i++) {
Performance optimization of AVL tree comparator functions perf: 2.75x faster ddt_entry_compare() First 256bits of ddt_key_t is a block checksum, which are expected to be close to random data. Hence, on average, comparison only needs to look at first few bytes of the keys. To reduce number of conditional jump instructions, the result is computed as: sign(memcmp(k1, k2)). Sign of an integer 'a' can be obtained as: `(0 < a) - (a < 0)` := {-1, 0, 1} , which is computed efficiently. Synthetic performance evaluation of original and new algorithm over 1G random keys on 2.6GHz Intel(R) Xeon(R) CPU E5-2660 v3: old 6.85789 s new 2.49089 s perf: 2.8x faster vdev_queue_offset_compare() and vdev_queue_timestamp_compare() Compute the result directly instead of using conditionals perf: zfs_range_compare() Speedup between 1.1x - 2.5x, depending on compiler version and optimization level. perf: spa_error_entry_compare() `bcmp()` is not suitable for comparator use. Use `memcmp()` instead. perf: 2.8x faster metaslab_compare() and metaslab_rangesize_compare() perf: 2.8x faster zil_bp_compare() perf: 2.8x faster mze_compare() perf: faster dbuf_compare() perf: faster compares in spa_misc perf: 2.8x faster layout_hash_compare() perf: 2.8x faster space_reftree_compare() perf: libzfs: faster avl tree comparators perf: guid_compare() perf: dsl_deadlist_compare() perf: perm_set_compare() perf: 2x faster range_tree_seg_compare() perf: faster unique_compare() perf: faster vdev_cache _compare() perf: faster vdev_uberblock_compare() perf: faster fuid _compare() perf: faster zfs_znode_hold_compare() Signed-off-by: Gvozden Neskovic <neskovic@gmail.com> Signed-off-by: Richard Elling <richard.elling@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #5033
2016-08-27 18:12:53 +00:00
cmp = (int32_t)k1->u16[i] - (int32_t)k2->u16[i];
if (likely(cmp))
break;
}
Performance optimization of AVL tree comparator functions perf: 2.75x faster ddt_entry_compare() First 256bits of ddt_key_t is a block checksum, which are expected to be close to random data. Hence, on average, comparison only needs to look at first few bytes of the keys. To reduce number of conditional jump instructions, the result is computed as: sign(memcmp(k1, k2)). Sign of an integer 'a' can be obtained as: `(0 < a) - (a < 0)` := {-1, 0, 1} , which is computed efficiently. Synthetic performance evaluation of original and new algorithm over 1G random keys on 2.6GHz Intel(R) Xeon(R) CPU E5-2660 v3: old 6.85789 s new 2.49089 s perf: 2.8x faster vdev_queue_offset_compare() and vdev_queue_timestamp_compare() Compute the result directly instead of using conditionals perf: zfs_range_compare() Speedup between 1.1x - 2.5x, depending on compiler version and optimization level. perf: spa_error_entry_compare() `bcmp()` is not suitable for comparator use. Use `memcmp()` instead. perf: 2.8x faster metaslab_compare() and metaslab_rangesize_compare() perf: 2.8x faster zil_bp_compare() perf: 2.8x faster mze_compare() perf: faster dbuf_compare() perf: faster compares in spa_misc perf: 2.8x faster layout_hash_compare() perf: 2.8x faster space_reftree_compare() perf: libzfs: faster avl tree comparators perf: guid_compare() perf: dsl_deadlist_compare() perf: perm_set_compare() perf: 2x faster range_tree_seg_compare() perf: faster unique_compare() perf: faster vdev_cache _compare() perf: faster vdev_uberblock_compare() perf: faster fuid _compare() perf: faster zfs_znode_hold_compare() Signed-off-by: Gvozden Neskovic <neskovic@gmail.com> Signed-off-by: Richard Elling <richard.elling@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #5033
2016-08-27 18:12:53 +00:00
return (AVL_ISIGN(cmp));
}
static ddt_t *
ddt_table_alloc(spa_t *spa, enum zio_checksum c)
{
ddt_t *ddt;
ddt = kmem_cache_alloc(ddt_cache, KM_SLEEP);
bzero(ddt, sizeof (ddt_t));
mutex_init(&ddt->ddt_lock, NULL, MUTEX_DEFAULT, NULL);
avl_create(&ddt->ddt_tree, ddt_entry_compare,
sizeof (ddt_entry_t), offsetof(ddt_entry_t, dde_node));
avl_create(&ddt->ddt_repair_tree, ddt_entry_compare,
sizeof (ddt_entry_t), offsetof(ddt_entry_t, dde_node));
ddt->ddt_checksum = c;
ddt->ddt_spa = spa;
ddt->ddt_os = spa->spa_meta_objset;
return (ddt);
}
static void
ddt_table_free(ddt_t *ddt)
{
ASSERT(avl_numnodes(&ddt->ddt_tree) == 0);
ASSERT(avl_numnodes(&ddt->ddt_repair_tree) == 0);
avl_destroy(&ddt->ddt_tree);
avl_destroy(&ddt->ddt_repair_tree);
mutex_destroy(&ddt->ddt_lock);
kmem_cache_free(ddt_cache, ddt);
}
void
ddt_create(spa_t *spa)
{
spa->spa_dedup_checksum = ZIO_DEDUPCHECKSUM;
for (enum zio_checksum c = 0; c < ZIO_CHECKSUM_FUNCTIONS; c++)
spa->spa_ddt[c] = ddt_table_alloc(spa, c);
}
int
ddt_load(spa_t *spa)
{
int error;
ddt_create(spa);
error = zap_lookup(spa->spa_meta_objset, DMU_POOL_DIRECTORY_OBJECT,
DMU_POOL_DDT_STATS, sizeof (uint64_t), 1,
&spa->spa_ddt_stat_object);
if (error)
return (error == ENOENT ? 0 : error);
for (enum zio_checksum c = 0; c < ZIO_CHECKSUM_FUNCTIONS; c++) {
ddt_t *ddt = spa->spa_ddt[c];
for (enum ddt_type type = 0; type < DDT_TYPES; type++) {
for (enum ddt_class class = 0; class < DDT_CLASSES;
class++) {
error = ddt_object_load(ddt, type, class);
if (error != 0 && error != ENOENT)
return (error);
}
}
/*
* Seed the cached histograms.
*/
bcopy(ddt->ddt_histogram, &ddt->ddt_histogram_cache,
sizeof (ddt->ddt_histogram));
spa->spa_dedup_dspace = ~0ULL;
}
return (0);
}
void
ddt_unload(spa_t *spa)
{
for (enum zio_checksum c = 0; c < ZIO_CHECKSUM_FUNCTIONS; c++) {
if (spa->spa_ddt[c]) {
ddt_table_free(spa->spa_ddt[c]);
spa->spa_ddt[c] = NULL;
}
}
}
boolean_t
ddt_class_contains(spa_t *spa, enum ddt_class max_class, const blkptr_t *bp)
{
ddt_t *ddt;
ddt_entry_t *dde;
if (!BP_GET_DEDUP(bp))
return (B_FALSE);
if (max_class == DDT_CLASS_UNIQUE)
return (B_TRUE);
ddt = spa->spa_ddt[BP_GET_CHECKSUM(bp)];
dde = kmem_cache_alloc(ddt_entry_cache, KM_SLEEP);
ddt_key_fill(&(dde->dde_key), bp);
for (enum ddt_type type = 0; type < DDT_TYPES; type++) {
for (enum ddt_class class = 0; class <= max_class; class++) {
if (ddt_object_lookup(ddt, type, class, dde) == 0) {
kmem_cache_free(ddt_entry_cache, dde);
return (B_TRUE);
}
}
}
kmem_cache_free(ddt_entry_cache, dde);
return (B_FALSE);
}
ddt_entry_t *
ddt_repair_start(ddt_t *ddt, const blkptr_t *bp)
{
ddt_key_t ddk;
ddt_entry_t *dde;
ddt_key_fill(&ddk, bp);
dde = ddt_alloc(&ddk);
for (enum ddt_type type = 0; type < DDT_TYPES; type++) {
for (enum ddt_class class = 0; class < DDT_CLASSES; class++) {
/*
* We can only do repair if there are multiple copies
* of the block. For anything in the UNIQUE class,
* there's definitely only one copy, so don't even try.
*/
if (class != DDT_CLASS_UNIQUE &&
ddt_object_lookup(ddt, type, class, dde) == 0)
return (dde);
}
}
bzero(dde->dde_phys, sizeof (dde->dde_phys));
return (dde);
}
void
ddt_repair_done(ddt_t *ddt, ddt_entry_t *dde)
{
avl_index_t where;
ddt_enter(ddt);
if (dde->dde_repair_abd != NULL && spa_writeable(ddt->ddt_spa) &&
avl_find(&ddt->ddt_repair_tree, dde, &where) == NULL)
avl_insert(&ddt->ddt_repair_tree, dde, where);
else
ddt_free(dde);
ddt_exit(ddt);
}
static void
ddt_repair_entry_done(zio_t *zio)
{
ddt_entry_t *rdde = zio->io_private;
ddt_free(rdde);
}
static void
ddt_repair_entry(ddt_t *ddt, ddt_entry_t *dde, ddt_entry_t *rdde, zio_t *rio)
{
ddt_phys_t *ddp = dde->dde_phys;
ddt_phys_t *rddp = rdde->dde_phys;
ddt_key_t *ddk = &dde->dde_key;
ddt_key_t *rddk = &rdde->dde_key;
zio_t *zio;
blkptr_t blk;
zio = zio_null(rio, rio->io_spa, NULL,
ddt_repair_entry_done, rdde, rio->io_flags);
for (int p = 0; p < DDT_PHYS_TYPES; p++, ddp++, rddp++) {
if (ddp->ddp_phys_birth == 0 ||
ddp->ddp_phys_birth != rddp->ddp_phys_birth ||
bcmp(ddp->ddp_dva, rddp->ddp_dva, sizeof (ddp->ddp_dva)))
continue;
ddt_bp_create(ddt->ddt_checksum, ddk, ddp, &blk);
zio_nowait(zio_rewrite(zio, zio->io_spa, 0, &blk,
rdde->dde_repair_abd, DDK_GET_PSIZE(rddk), NULL, NULL,
ZIO_PRIORITY_SYNC_WRITE, ZIO_DDT_CHILD_FLAGS(zio), NULL));
}
zio_nowait(zio);
}
static void
ddt_repair_table(ddt_t *ddt, zio_t *rio)
{
spa_t *spa = ddt->ddt_spa;
ddt_entry_t *dde, *rdde_next, *rdde;
avl_tree_t *t = &ddt->ddt_repair_tree;
blkptr_t blk;
if (spa_sync_pass(spa) > 1)
return;
ddt_enter(ddt);
for (rdde = avl_first(t); rdde != NULL; rdde = rdde_next) {
rdde_next = AVL_NEXT(t, rdde);
avl_remove(&ddt->ddt_repair_tree, rdde);
ddt_exit(ddt);
ddt_bp_create(ddt->ddt_checksum, &rdde->dde_key, NULL, &blk);
dde = ddt_repair_start(ddt, &blk);
ddt_repair_entry(ddt, dde, rdde, rio);
ddt_repair_done(ddt, dde);
ddt_enter(ddt);
}
ddt_exit(ddt);
}
static void
ddt_sync_entry(ddt_t *ddt, ddt_entry_t *dde, dmu_tx_t *tx, uint64_t txg)
{
dsl_pool_t *dp = ddt->ddt_spa->spa_dsl_pool;
ddt_phys_t *ddp = dde->dde_phys;
ddt_key_t *ddk = &dde->dde_key;
enum ddt_type otype = dde->dde_type;
enum ddt_type ntype = DDT_TYPE_CURRENT;
enum ddt_class oclass = dde->dde_class;
enum ddt_class nclass;
uint64_t total_refcnt = 0;
ASSERT(dde->dde_loaded);
ASSERT(!dde->dde_loading);
for (int p = 0; p < DDT_PHYS_TYPES; p++, ddp++) {
ASSERT(dde->dde_lead_zio[p] == NULL);
if (ddp->ddp_phys_birth == 0) {
ASSERT(ddp->ddp_refcnt == 0);
continue;
}
if (p == DDT_PHYS_DITTO) {
if (ddt_ditto_copies_needed(ddt, dde, NULL) == 0)
ddt_phys_free(ddt, ddk, ddp, txg);
continue;
}
if (ddp->ddp_refcnt == 0)
ddt_phys_free(ddt, ddk, ddp, txg);
total_refcnt += ddp->ddp_refcnt;
}
if (dde->dde_phys[DDT_PHYS_DITTO].ddp_phys_birth != 0)
nclass = DDT_CLASS_DITTO;
else if (total_refcnt > 1)
nclass = DDT_CLASS_DUPLICATE;
else
nclass = DDT_CLASS_UNIQUE;
if (otype != DDT_TYPES &&
(otype != ntype || oclass != nclass || total_refcnt == 0)) {
VERIFY(ddt_object_remove(ddt, otype, oclass, dde, tx) == 0);
ASSERT(ddt_object_lookup(ddt, otype, oclass, dde) == ENOENT);
}
if (total_refcnt != 0) {
dde->dde_type = ntype;
dde->dde_class = nclass;
ddt_stat_update(ddt, dde, 0);
if (!ddt_object_exists(ddt, ntype, nclass))
ddt_object_create(ddt, ntype, nclass, tx);
VERIFY(ddt_object_update(ddt, ntype, nclass, dde, tx) == 0);
/*
* If the class changes, the order that we scan this bp
* changes. If it decreases, we could miss it, so
* scan it right now. (This covers both class changing
* while we are doing ddt_walk(), and when we are
* traversing.)
*/
if (nclass < oclass) {
dsl_scan_ddt_entry(dp->dp_scan,
ddt->ddt_checksum, dde, tx);
}
}
}
static void
ddt_sync_table(ddt_t *ddt, dmu_tx_t *tx, uint64_t txg)
{
spa_t *spa = ddt->ddt_spa;
ddt_entry_t *dde;
void *cookie = NULL;
if (avl_numnodes(&ddt->ddt_tree) == 0)
return;
ASSERT(spa->spa_uberblock.ub_version >= SPA_VERSION_DEDUP);
if (spa->spa_ddt_stat_object == 0) {
spa->spa_ddt_stat_object = zap_create_link(ddt->ddt_os,
DMU_OT_DDT_STATS, DMU_POOL_DIRECTORY_OBJECT,
DMU_POOL_DDT_STATS, tx);
}
while ((dde = avl_destroy_nodes(&ddt->ddt_tree, &cookie)) != NULL) {
ddt_sync_entry(ddt, dde, tx, txg);
ddt_free(dde);
}
for (enum ddt_type type = 0; type < DDT_TYPES; type++) {
uint64_t add, count = 0;
for (enum ddt_class class = 0; class < DDT_CLASSES; class++) {
if (ddt_object_exists(ddt, type, class)) {
ddt_object_sync(ddt, type, class, tx);
VERIFY(ddt_object_count(ddt, type, class,
&add) == 0);
count += add;
}
}
for (enum ddt_class class = 0; class < DDT_CLASSES; class++) {
if (count == 0 && ddt_object_exists(ddt, type, class))
ddt_object_destroy(ddt, type, class, tx);
}
}
bcopy(ddt->ddt_histogram, &ddt->ddt_histogram_cache,
sizeof (ddt->ddt_histogram));
spa->spa_dedup_dspace = ~0ULL;
}
void
ddt_sync(spa_t *spa, uint64_t txg)
{
dsl_scan_t *scn = spa->spa_dsl_pool->dp_scan;
dmu_tx_t *tx;
zio_t *rio;
ASSERT(spa_syncing_txg(spa) == txg);
tx = dmu_tx_create_assigned(spa->spa_dsl_pool, txg);
rio = zio_root(spa, NULL, NULL,
OpenZFS 7614, 9064 - zfs device evacuation/removal OpenZFS 7614 - zfs device evacuation/removal OpenZFS 9064 - remove_mirror should wait for device removal to complete This project allows top-level vdevs to be removed from the storage pool with "zpool remove", reducing the total amount of storage in the pool. This operation copies all allocated regions of the device to be removed onto other devices, recording the mapping from old to new location. After the removal is complete, read and free operations to the removed (now "indirect") vdev must be remapped and performed at the new location on disk. The indirect mapping table is kept in memory whenever the pool is loaded, so there is minimal performance overhead when doing operations on the indirect vdev. The size of the in-memory mapping table will be reduced when its entries become "obsolete" because they are no longer used by any block pointers in the pool. An entry becomes obsolete when all the blocks that use it are freed. An entry can also become obsolete when all the snapshots that reference it are deleted, and the block pointers that reference it have been "remapped" in all filesystems/zvols (and clones). Whenever an indirect block is written, all the block pointers in it will be "remapped" to their new (concrete) locations if possible. This process can be accelerated by using the "zfs remap" command to proactively rewrite all indirect blocks that reference indirect (removed) vdevs. Note that when a device is removed, we do not verify the checksum of the data that is copied. This makes the process much faster, but if it were used on redundant vdevs (i.e. mirror or raidz vdevs), it would be possible to copy the wrong data, when we have the correct data on e.g. the other side of the mirror. At the moment, only mirrors and simple top-level vdevs can be removed and no removal is allowed if any of the top-level vdevs are raidz. Porting Notes: * Avoid zero-sized kmem_alloc() in vdev_compact_children(). The device evacuation code adds a dependency that vdev_compact_children() be able to properly empty the vdev_child array by setting it to NULL and zeroing vdev_children. Under Linux, kmem_alloc() and related functions return a sentinel pointer rather than NULL for zero-sized allocations. * Remove comment regarding "mpt" driver where zfs_remove_max_segment is initialized to SPA_MAXBLOCKSIZE. Change zfs_condense_indirect_commit_entry_delay_ticks to zfs_condense_indirect_commit_entry_delay_ms for consistency with most other tunables in which delays are specified in ms. * ZTS changes: Use set_tunable rather than mdb Use zpool sync as appropriate Use sync_pool instead of sync Kill jobs during test_removal_with_operation to allow unmount/export Don't add non-disk names such as "mirror" or "raidz" to $DISKS Use $TEST_BASE_DIR instead of /tmp Increase HZ from 100 to 1000 which is more common on Linux removal_multiple_indirection.ksh Reduce iterations in order to not time out on the code coverage builders. removal_resume_export: Functionally, the test case is correct but there exists a race where the kernel thread hasn't been fully started yet and is not visible. Wait for up to 1 second for the removal thread to be started before giving up on it. Also, increase the amount of data copied in order that the removal not finish before the export has a chance to fail. * MMP compatibility, the concept of concrete versus non-concrete devices has slightly changed the semantics of vdev_writeable(). Update mmp_random_leaf_impl() accordingly. * Updated dbuf_remap() to handle the org.zfsonlinux:large_dnode pool feature which is not supported by OpenZFS. * Added support for new vdev removal tracepoints. * Test cases removal_with_zdb and removal_condense_export have been intentionally disabled. When run manually they pass as intended, but when running in the automated test environment they produce unreliable results on the latest Fedora release. They may work better once the upstream pool import refectoring is merged into ZoL at which point they will be re-enabled. Authored by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Alex Reece <alex@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Richard Laager <rlaager@wiktel.com> Reviewed by: Tim Chase <tim@chase2k.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Garrett D'Amore <garrett@damore.org> Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Tim Chase <tim@chase2k.com> OpenZFS-issue: https://www.illumos.org/issues/7614 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/f539f1eb Closes #6900
2016-09-22 16:30:13 +00:00
ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE | ZIO_FLAG_SELF_HEAL);
/*
* This function may cause an immediate scan of ddt blocks (see
* the comment above dsl_scan_ddt() for details). We set the
* scan's root zio here so that we can wait for any scan IOs in
* addition to the regular ddt IOs.
*/
ASSERT3P(scn->scn_zio_root, ==, NULL);
scn->scn_zio_root = rio;
for (enum zio_checksum c = 0; c < ZIO_CHECKSUM_FUNCTIONS; c++) {
ddt_t *ddt = spa->spa_ddt[c];
if (ddt == NULL)
continue;
ddt_sync_table(ddt, tx, txg);
ddt_repair_table(ddt, rio);
}
(void) zio_wait(rio);
scn->scn_zio_root = NULL;
dmu_tx_commit(tx);
}
int
ddt_walk(spa_t *spa, ddt_bookmark_t *ddb, ddt_entry_t *dde)
{
do {
do {
do {
ddt_t *ddt = spa->spa_ddt[ddb->ddb_checksum];
int error = ENOENT;
if (ddt_object_exists(ddt, ddb->ddb_type,
ddb->ddb_class)) {
error = ddt_object_walk(ddt,
ddb->ddb_type, ddb->ddb_class,
&ddb->ddb_cursor, dde);
}
dde->dde_type = ddb->ddb_type;
dde->dde_class = ddb->ddb_class;
if (error == 0)
return (0);
if (error != ENOENT)
return (error);
ddb->ddb_cursor = 0;
} while (++ddb->ddb_checksum < ZIO_CHECKSUM_FUNCTIONS);
ddb->ddb_checksum = 0;
} while (++ddb->ddb_type < DDT_TYPES);
ddb->ddb_type = 0;
} while (++ddb->ddb_class < DDT_CLASSES);
return (SET_ERROR(ENOENT));
}
Add missing ZFS tunables This commit adds module options for all existing zfs tunables. Ideally the average user should never need to modify any of these values. However, in practice sometimes you do need to tweak these values for one reason or another. In those cases it's nice not to have to resort to rebuilding from source. All tunables are visable to modinfo and the list is as follows: $ modinfo module/zfs/zfs.ko filename: module/zfs/zfs.ko license: CDDL author: Sun Microsystems/Oracle, Lawrence Livermore National Laboratory description: ZFS srcversion: 8EAB1D71DACE05B5AA61567 depends: spl,znvpair,zcommon,zunicode,zavl vermagic: 2.6.32-131.0.5.el6.x86_64 SMP mod_unload modversions parm: zvol_major:Major number for zvol device (uint) parm: zvol_threads:Number of threads for zvol device (uint) parm: zio_injection_enabled:Enable fault injection (int) parm: zio_bulk_flags:Additional flags to pass to bulk buffers (int) parm: zio_delay_max:Max zio millisec delay before posting event (int) parm: zio_requeue_io_start_cut_in_line:Prioritize requeued I/O (bool) parm: zil_replay_disable:Disable intent logging replay (int) parm: zfs_nocacheflush:Disable cache flushes (bool) parm: zfs_read_chunk_size:Bytes to read per chunk (long) parm: zfs_vdev_max_pending:Max pending per-vdev I/Os (int) parm: zfs_vdev_min_pending:Min pending per-vdev I/Os (int) parm: zfs_vdev_aggregation_limit:Max vdev I/O aggregation size (int) parm: zfs_vdev_time_shift:Deadline time shift for vdev I/O (int) parm: zfs_vdev_ramp_rate:Exponential I/O issue ramp-up rate (int) parm: zfs_vdev_read_gap_limit:Aggregate read I/O over gap (int) parm: zfs_vdev_write_gap_limit:Aggregate write I/O over gap (int) parm: zfs_vdev_scheduler:I/O scheduler (charp) parm: zfs_vdev_cache_max:Inflate reads small than max (int) parm: zfs_vdev_cache_size:Total size of the per-disk cache (int) parm: zfs_vdev_cache_bshift:Shift size to inflate reads too (int) parm: zfs_scrub_limit:Max scrub/resilver I/O per leaf vdev (int) parm: zfs_recover:Set to attempt to recover from fatal errors (int) parm: spa_config_path:SPA config file (/etc/zfs/zpool.cache) (charp) parm: zfs_zevent_len_max:Max event queue length (int) parm: zfs_zevent_cols:Max event column width (int) parm: zfs_zevent_console:Log events to the console (int) parm: zfs_top_maxinflight:Max I/Os per top-level (int) parm: zfs_resilver_delay:Number of ticks to delay resilver (int) parm: zfs_scrub_delay:Number of ticks to delay scrub (int) parm: zfs_scan_idle:Idle window in clock ticks (int) parm: zfs_scan_min_time_ms:Min millisecs to scrub per txg (int) parm: zfs_free_min_time_ms:Min millisecs to free per txg (int) parm: zfs_resilver_min_time_ms:Min millisecs to resilver per txg (int) parm: zfs_no_scrub_io:Set to disable scrub I/O (bool) parm: zfs_no_scrub_prefetch:Set to disable scrub prefetching (bool) parm: zfs_txg_timeout:Max seconds worth of delta per txg (int) parm: zfs_no_write_throttle:Disable write throttling (int) parm: zfs_write_limit_shift:log2(fraction of memory) per txg (int) parm: zfs_txg_synctime_ms:Target milliseconds between tgx sync (int) parm: zfs_write_limit_min:Min tgx write limit (ulong) parm: zfs_write_limit_max:Max tgx write limit (ulong) parm: zfs_write_limit_inflated:Inflated tgx write limit (ulong) parm: zfs_write_limit_override:Override tgx write limit (ulong) parm: zfs_prefetch_disable:Disable all ZFS prefetching (int) parm: zfetch_max_streams:Max number of streams per zfetch (uint) parm: zfetch_min_sec_reap:Min time before stream reclaim (uint) parm: zfetch_block_cap:Max number of blocks to fetch at a time (uint) parm: zfetch_array_rd_sz:Number of bytes in a array_read (ulong) parm: zfs_pd_blks_max:Max number of blocks to prefetch (int) parm: zfs_dedup_prefetch:Enable prefetching dedup-ed blks (int) parm: zfs_arc_min:Min arc size (ulong) parm: zfs_arc_max:Max arc size (ulong) parm: zfs_arc_meta_limit:Meta limit for arc size (ulong) parm: zfs_arc_reduce_dnlc_percent:Meta reclaim percentage (int) parm: zfs_arc_grow_retry:Seconds before growing arc size (int) parm: zfs_arc_shrink_shift:log2(fraction of arc to reclaim) (int) parm: zfs_arc_p_min_shift:arc_c shift to calc min/max arc_p (int)
2011-05-03 22:09:28 +00:00
Update build system and packaging Minimal changes required to integrate the SPL sources in to the ZFS repository build infrastructure and packaging. Build system and packaging: * Renamed SPL_* autoconf m4 macros to ZFS_*. * Removed redundant SPL_* autoconf m4 macros. * Updated the RPM spec files to remove SPL package dependency. * The zfs package obsoletes the spl package, and the zfs-kmod package obsoletes the spl-kmod package. * The zfs-kmod-devel* packages were updated to add compatibility symlinks under /usr/src/spl-x.y.z until all dependent packages can be updated. They will be removed in a future release. * Updated copy-builtin script for in-kernel builds. * Updated DKMS package to include the spl.ko. * Updated stale AUTHORS file to include all contributors. * Updated stale COPYRIGHT and included the SPL as an exception. * Renamed README.markdown to README.md * Renamed OPENSOLARIS.LICENSE to LICENSE. * Renamed DISCLAIMER to NOTICE. Required code changes: * Removed redundant HAVE_SPL macro. * Removed _BOOT from nvpairs since it doesn't apply for Linux. * Initial header cleanup (removal of empty headers, refactoring). * Remove SPL repository clone/build from zimport.sh. * Use of DEFINE_RATELIMIT_STATE and DEFINE_SPINLOCK removed due to build issues when forcing C99 compilation. * Replaced legacy ACCESS_ONCE with READ_ONCE. * Include needed headers for `current` and `EXPORT_SYMBOL`. Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Olaf Faaland <faaland1@llnl.gov> Reviewed-by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> TEST_ZIMPORT_SKIP="yes" Closes #7556
2018-02-16 01:53:18 +00:00
#if defined(_KERNEL)
Add missing ZFS tunables This commit adds module options for all existing zfs tunables. Ideally the average user should never need to modify any of these values. However, in practice sometimes you do need to tweak these values for one reason or another. In those cases it's nice not to have to resort to rebuilding from source. All tunables are visable to modinfo and the list is as follows: $ modinfo module/zfs/zfs.ko filename: module/zfs/zfs.ko license: CDDL author: Sun Microsystems/Oracle, Lawrence Livermore National Laboratory description: ZFS srcversion: 8EAB1D71DACE05B5AA61567 depends: spl,znvpair,zcommon,zunicode,zavl vermagic: 2.6.32-131.0.5.el6.x86_64 SMP mod_unload modversions parm: zvol_major:Major number for zvol device (uint) parm: zvol_threads:Number of threads for zvol device (uint) parm: zio_injection_enabled:Enable fault injection (int) parm: zio_bulk_flags:Additional flags to pass to bulk buffers (int) parm: zio_delay_max:Max zio millisec delay before posting event (int) parm: zio_requeue_io_start_cut_in_line:Prioritize requeued I/O (bool) parm: zil_replay_disable:Disable intent logging replay (int) parm: zfs_nocacheflush:Disable cache flushes (bool) parm: zfs_read_chunk_size:Bytes to read per chunk (long) parm: zfs_vdev_max_pending:Max pending per-vdev I/Os (int) parm: zfs_vdev_min_pending:Min pending per-vdev I/Os (int) parm: zfs_vdev_aggregation_limit:Max vdev I/O aggregation size (int) parm: zfs_vdev_time_shift:Deadline time shift for vdev I/O (int) parm: zfs_vdev_ramp_rate:Exponential I/O issue ramp-up rate (int) parm: zfs_vdev_read_gap_limit:Aggregate read I/O over gap (int) parm: zfs_vdev_write_gap_limit:Aggregate write I/O over gap (int) parm: zfs_vdev_scheduler:I/O scheduler (charp) parm: zfs_vdev_cache_max:Inflate reads small than max (int) parm: zfs_vdev_cache_size:Total size of the per-disk cache (int) parm: zfs_vdev_cache_bshift:Shift size to inflate reads too (int) parm: zfs_scrub_limit:Max scrub/resilver I/O per leaf vdev (int) parm: zfs_recover:Set to attempt to recover from fatal errors (int) parm: spa_config_path:SPA config file (/etc/zfs/zpool.cache) (charp) parm: zfs_zevent_len_max:Max event queue length (int) parm: zfs_zevent_cols:Max event column width (int) parm: zfs_zevent_console:Log events to the console (int) parm: zfs_top_maxinflight:Max I/Os per top-level (int) parm: zfs_resilver_delay:Number of ticks to delay resilver (int) parm: zfs_scrub_delay:Number of ticks to delay scrub (int) parm: zfs_scan_idle:Idle window in clock ticks (int) parm: zfs_scan_min_time_ms:Min millisecs to scrub per txg (int) parm: zfs_free_min_time_ms:Min millisecs to free per txg (int) parm: zfs_resilver_min_time_ms:Min millisecs to resilver per txg (int) parm: zfs_no_scrub_io:Set to disable scrub I/O (bool) parm: zfs_no_scrub_prefetch:Set to disable scrub prefetching (bool) parm: zfs_txg_timeout:Max seconds worth of delta per txg (int) parm: zfs_no_write_throttle:Disable write throttling (int) parm: zfs_write_limit_shift:log2(fraction of memory) per txg (int) parm: zfs_txg_synctime_ms:Target milliseconds between tgx sync (int) parm: zfs_write_limit_min:Min tgx write limit (ulong) parm: zfs_write_limit_max:Max tgx write limit (ulong) parm: zfs_write_limit_inflated:Inflated tgx write limit (ulong) parm: zfs_write_limit_override:Override tgx write limit (ulong) parm: zfs_prefetch_disable:Disable all ZFS prefetching (int) parm: zfetch_max_streams:Max number of streams per zfetch (uint) parm: zfetch_min_sec_reap:Min time before stream reclaim (uint) parm: zfetch_block_cap:Max number of blocks to fetch at a time (uint) parm: zfetch_array_rd_sz:Number of bytes in a array_read (ulong) parm: zfs_pd_blks_max:Max number of blocks to prefetch (int) parm: zfs_dedup_prefetch:Enable prefetching dedup-ed blks (int) parm: zfs_arc_min:Min arc size (ulong) parm: zfs_arc_max:Max arc size (ulong) parm: zfs_arc_meta_limit:Meta limit for arc size (ulong) parm: zfs_arc_reduce_dnlc_percent:Meta reclaim percentage (int) parm: zfs_arc_grow_retry:Seconds before growing arc size (int) parm: zfs_arc_shrink_shift:log2(fraction of arc to reclaim) (int) parm: zfs_arc_p_min_shift:arc_c shift to calc min/max arc_p (int)
2011-05-03 22:09:28 +00:00
module_param(zfs_dedup_prefetch, int, 0644);
MODULE_PARM_DESC(zfs_dedup_prefetch, "Enable prefetching dedup-ed blks");
Add missing ZFS tunables This commit adds module options for all existing zfs tunables. Ideally the average user should never need to modify any of these values. However, in practice sometimes you do need to tweak these values for one reason or another. In those cases it's nice not to have to resort to rebuilding from source. All tunables are visable to modinfo and the list is as follows: $ modinfo module/zfs/zfs.ko filename: module/zfs/zfs.ko license: CDDL author: Sun Microsystems/Oracle, Lawrence Livermore National Laboratory description: ZFS srcversion: 8EAB1D71DACE05B5AA61567 depends: spl,znvpair,zcommon,zunicode,zavl vermagic: 2.6.32-131.0.5.el6.x86_64 SMP mod_unload modversions parm: zvol_major:Major number for zvol device (uint) parm: zvol_threads:Number of threads for zvol device (uint) parm: zio_injection_enabled:Enable fault injection (int) parm: zio_bulk_flags:Additional flags to pass to bulk buffers (int) parm: zio_delay_max:Max zio millisec delay before posting event (int) parm: zio_requeue_io_start_cut_in_line:Prioritize requeued I/O (bool) parm: zil_replay_disable:Disable intent logging replay (int) parm: zfs_nocacheflush:Disable cache flushes (bool) parm: zfs_read_chunk_size:Bytes to read per chunk (long) parm: zfs_vdev_max_pending:Max pending per-vdev I/Os (int) parm: zfs_vdev_min_pending:Min pending per-vdev I/Os (int) parm: zfs_vdev_aggregation_limit:Max vdev I/O aggregation size (int) parm: zfs_vdev_time_shift:Deadline time shift for vdev I/O (int) parm: zfs_vdev_ramp_rate:Exponential I/O issue ramp-up rate (int) parm: zfs_vdev_read_gap_limit:Aggregate read I/O over gap (int) parm: zfs_vdev_write_gap_limit:Aggregate write I/O over gap (int) parm: zfs_vdev_scheduler:I/O scheduler (charp) parm: zfs_vdev_cache_max:Inflate reads small than max (int) parm: zfs_vdev_cache_size:Total size of the per-disk cache (int) parm: zfs_vdev_cache_bshift:Shift size to inflate reads too (int) parm: zfs_scrub_limit:Max scrub/resilver I/O per leaf vdev (int) parm: zfs_recover:Set to attempt to recover from fatal errors (int) parm: spa_config_path:SPA config file (/etc/zfs/zpool.cache) (charp) parm: zfs_zevent_len_max:Max event queue length (int) parm: zfs_zevent_cols:Max event column width (int) parm: zfs_zevent_console:Log events to the console (int) parm: zfs_top_maxinflight:Max I/Os per top-level (int) parm: zfs_resilver_delay:Number of ticks to delay resilver (int) parm: zfs_scrub_delay:Number of ticks to delay scrub (int) parm: zfs_scan_idle:Idle window in clock ticks (int) parm: zfs_scan_min_time_ms:Min millisecs to scrub per txg (int) parm: zfs_free_min_time_ms:Min millisecs to free per txg (int) parm: zfs_resilver_min_time_ms:Min millisecs to resilver per txg (int) parm: zfs_no_scrub_io:Set to disable scrub I/O (bool) parm: zfs_no_scrub_prefetch:Set to disable scrub prefetching (bool) parm: zfs_txg_timeout:Max seconds worth of delta per txg (int) parm: zfs_no_write_throttle:Disable write throttling (int) parm: zfs_write_limit_shift:log2(fraction of memory) per txg (int) parm: zfs_txg_synctime_ms:Target milliseconds between tgx sync (int) parm: zfs_write_limit_min:Min tgx write limit (ulong) parm: zfs_write_limit_max:Max tgx write limit (ulong) parm: zfs_write_limit_inflated:Inflated tgx write limit (ulong) parm: zfs_write_limit_override:Override tgx write limit (ulong) parm: zfs_prefetch_disable:Disable all ZFS prefetching (int) parm: zfetch_max_streams:Max number of streams per zfetch (uint) parm: zfetch_min_sec_reap:Min time before stream reclaim (uint) parm: zfetch_block_cap:Max number of blocks to fetch at a time (uint) parm: zfetch_array_rd_sz:Number of bytes in a array_read (ulong) parm: zfs_pd_blks_max:Max number of blocks to prefetch (int) parm: zfs_dedup_prefetch:Enable prefetching dedup-ed blks (int) parm: zfs_arc_min:Min arc size (ulong) parm: zfs_arc_max:Max arc size (ulong) parm: zfs_arc_meta_limit:Meta limit for arc size (ulong) parm: zfs_arc_reduce_dnlc_percent:Meta reclaim percentage (int) parm: zfs_arc_grow_retry:Seconds before growing arc size (int) parm: zfs_arc_shrink_shift:log2(fraction of arc to reclaim) (int) parm: zfs_arc_p_min_shift:arc_c shift to calc min/max arc_p (int)
2011-05-03 22:09:28 +00:00
#endif