mirror_zfs/module/Makefile.bsd

422 lines
8.7 KiB
Makefile
Raw Normal View History

.if !defined(WITH_CTF)
WITH_CTF=1
.endif
.include <bsd.sys.mk>
SRCDIR=${.CURDIR}
INCDIR=${.CURDIR:H}/include
KMOD= openzfs
.PATH: ${SRCDIR}/avl \
${SRCDIR}/lua \
${SRCDIR}/nvpair \
${SRCDIR}/icp/algs/edonr \
${SRCDIR}/os/freebsd/spl \
${SRCDIR}/os/freebsd/zfs \
${SRCDIR}/unicode \
${SRCDIR}/zcommon \
Add zstd support to zfs This PR adds two new compression types, based on ZStandard: - zstd: A basic ZStandard compression algorithm Available compression. Levels for zstd are zstd-1 through zstd-19, where the compression increases with every level, but speed decreases. - zstd-fast: A faster version of the ZStandard compression algorithm zstd-fast is basically a "negative" level of zstd. The compression decreases with every level, but speed increases. Available compression levels for zstd-fast: - zstd-fast-1 through zstd-fast-10 - zstd-fast-20 through zstd-fast-100 (in increments of 10) - zstd-fast-500 and zstd-fast-1000 For more information check the man page. Implementation details: Rather than treat each level of zstd as a different algorithm (as was done historically with gzip), the block pointer `enum zio_compress` value is simply zstd for all levels, including zstd-fast, since they all use the same decompression function. The compress= property (a 64bit unsigned integer) uses the lower 7 bits to store the compression algorithm (matching the number of bits used in a block pointer, as the 8th bit was borrowed for embedded block pointers). The upper bits are used to store the compression level. It is necessary to be able to determine what compression level was used when later reading a block back, so the concept used in LZ4, where the first 32bits of the on-disk value are the size of the compressed data (since the allocation is rounded up to the nearest ashift), was extended, and we store the version of ZSTD and the level as well as the compressed size. This value is returned when decompressing a block, so that if the block needs to be recompressed (L2ARC, nop-write, etc), that the same parameters will be used to result in the matching checksum. All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`, `zio_prop_t`, etc.) uses the separated _compress and _complevel variables. Only the properties ZAP contains the combined/bit-shifted value. The combined value is split when the compression_changed_cb() callback is called, and sets both objset members (os_compress and os_complevel). The userspace tools all use the combined/bit-shifted value. Additional notes: zdb can now also decode the ZSTD compression header (flag -Z) and inspect the size, version and compression level saved in that header. For each record, if it is ZSTD compressed, the parameters of the decoded compression header get printed. ZSTD is included with all current tests and new tests are added as-needed. Per-dataset feature flags now get activated when the property is set. If a compression algorithm requires a feature flag, zfs activates the feature when the property is set, rather than waiting for the first block to be born. This is currently only used by zstd but can be extended as needed. Portions-Sponsored-By: The FreeBSD Foundation Co-authored-by: Allan Jude <allanjude@freebsd.org> Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov> Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Co-authored-by: Michael Niewöhner <foss@mniewoehner.de> Signed-off-by: Allan Jude <allan@klarasystems.com> Signed-off-by: Allan Jude <allanjude@freebsd.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Signed-off-by: Michael Niewöhner <foss@mniewoehner.de> Closes #6247 Closes #9024 Closes #10277 Closes #10278
2020-08-18 20:10:17 +03:00
${SRCDIR}/zfs \
${SRCDIR}/zstd \
${SRCDIR}/zstd/lib/common \
${SRCDIR}/zstd/lib/compress \
${SRCDIR}/zstd/lib/decompress
Add zstd support to zfs This PR adds two new compression types, based on ZStandard: - zstd: A basic ZStandard compression algorithm Available compression. Levels for zstd are zstd-1 through zstd-19, where the compression increases with every level, but speed decreases. - zstd-fast: A faster version of the ZStandard compression algorithm zstd-fast is basically a "negative" level of zstd. The compression decreases with every level, but speed increases. Available compression levels for zstd-fast: - zstd-fast-1 through zstd-fast-10 - zstd-fast-20 through zstd-fast-100 (in increments of 10) - zstd-fast-500 and zstd-fast-1000 For more information check the man page. Implementation details: Rather than treat each level of zstd as a different algorithm (as was done historically with gzip), the block pointer `enum zio_compress` value is simply zstd for all levels, including zstd-fast, since they all use the same decompression function. The compress= property (a 64bit unsigned integer) uses the lower 7 bits to store the compression algorithm (matching the number of bits used in a block pointer, as the 8th bit was borrowed for embedded block pointers). The upper bits are used to store the compression level. It is necessary to be able to determine what compression level was used when later reading a block back, so the concept used in LZ4, where the first 32bits of the on-disk value are the size of the compressed data (since the allocation is rounded up to the nearest ashift), was extended, and we store the version of ZSTD and the level as well as the compressed size. This value is returned when decompressing a block, so that if the block needs to be recompressed (L2ARC, nop-write, etc), that the same parameters will be used to result in the matching checksum. All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`, `zio_prop_t`, etc.) uses the separated _compress and _complevel variables. Only the properties ZAP contains the combined/bit-shifted value. The combined value is split when the compression_changed_cb() callback is called, and sets both objset members (os_compress and os_complevel). The userspace tools all use the combined/bit-shifted value. Additional notes: zdb can now also decode the ZSTD compression header (flag -Z) and inspect the size, version and compression level saved in that header. For each record, if it is ZSTD compressed, the parameters of the decoded compression header get printed. ZSTD is included with all current tests and new tests are added as-needed. Per-dataset feature flags now get activated when the property is set. If a compression algorithm requires a feature flag, zfs activates the feature when the property is set, rather than waiting for the first block to be born. This is currently only used by zstd but can be extended as needed. Portions-Sponsored-By: The FreeBSD Foundation Co-authored-by: Allan Jude <allanjude@freebsd.org> Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov> Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Co-authored-by: Michael Niewöhner <foss@mniewoehner.de> Signed-off-by: Allan Jude <allan@klarasystems.com> Signed-off-by: Allan Jude <allanjude@freebsd.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Signed-off-by: Michael Niewöhner <foss@mniewoehner.de> Closes #6247 Closes #9024 Closes #10277 Closes #10278
2020-08-18 20:10:17 +03:00
CFLAGS+= -I${.OBJDIR:H}/include
CFLAGS+= -I${INCDIR}
CFLAGS+= -I${INCDIR}/os/freebsd
CFLAGS+= -I${INCDIR}/os/freebsd/spl
CFLAGS+= -I${INCDIR}/os/freebsd/zfs
Add zstd support to zfs This PR adds two new compression types, based on ZStandard: - zstd: A basic ZStandard compression algorithm Available compression. Levels for zstd are zstd-1 through zstd-19, where the compression increases with every level, but speed decreases. - zstd-fast: A faster version of the ZStandard compression algorithm zstd-fast is basically a "negative" level of zstd. The compression decreases with every level, but speed increases. Available compression levels for zstd-fast: - zstd-fast-1 through zstd-fast-10 - zstd-fast-20 through zstd-fast-100 (in increments of 10) - zstd-fast-500 and zstd-fast-1000 For more information check the man page. Implementation details: Rather than treat each level of zstd as a different algorithm (as was done historically with gzip), the block pointer `enum zio_compress` value is simply zstd for all levels, including zstd-fast, since they all use the same decompression function. The compress= property (a 64bit unsigned integer) uses the lower 7 bits to store the compression algorithm (matching the number of bits used in a block pointer, as the 8th bit was borrowed for embedded block pointers). The upper bits are used to store the compression level. It is necessary to be able to determine what compression level was used when later reading a block back, so the concept used in LZ4, where the first 32bits of the on-disk value are the size of the compressed data (since the allocation is rounded up to the nearest ashift), was extended, and we store the version of ZSTD and the level as well as the compressed size. This value is returned when decompressing a block, so that if the block needs to be recompressed (L2ARC, nop-write, etc), that the same parameters will be used to result in the matching checksum. All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`, `zio_prop_t`, etc.) uses the separated _compress and _complevel variables. Only the properties ZAP contains the combined/bit-shifted value. The combined value is split when the compression_changed_cb() callback is called, and sets both objset members (os_compress and os_complevel). The userspace tools all use the combined/bit-shifted value. Additional notes: zdb can now also decode the ZSTD compression header (flag -Z) and inspect the size, version and compression level saved in that header. For each record, if it is ZSTD compressed, the parameters of the decoded compression header get printed. ZSTD is included with all current tests and new tests are added as-needed. Per-dataset feature flags now get activated when the property is set. If a compression algorithm requires a feature flag, zfs activates the feature when the property is set, rather than waiting for the first block to be born. This is currently only used by zstd but can be extended as needed. Portions-Sponsored-By: The FreeBSD Foundation Co-authored-by: Allan Jude <allanjude@freebsd.org> Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov> Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Co-authored-by: Michael Niewöhner <foss@mniewoehner.de> Signed-off-by: Allan Jude <allan@klarasystems.com> Signed-off-by: Allan Jude <allanjude@freebsd.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Signed-off-by: Michael Niewöhner <foss@mniewoehner.de> Closes #6247 Closes #9024 Closes #10277 Closes #10278
2020-08-18 20:10:17 +03:00
CFLAGS+= -I${SRCDIR}/zstd/include
CFLAGS+= -include ${INCDIR}/os/freebsd/spl/sys/ccompile.h
CFLAGS+= -D__KERNEL__ -DFREEBSD_NAMECACHE -DBUILDING_ZFS -D__BSD_VISIBLE=1 \
-DHAVE_UIO_ZEROCOPY -DWITHOUT_NETDUMP -D__KERNEL -D_SYS_CONDVAR_H_ \
-D_SYS_VMEM_H_ -DKDTRACE_HOOKS -DSMP -DCOMPAT_FREEBSD11
.if ${MACHINE_ARCH} == "amd64"
CFLAGS+= -DHAVE_AVX2 -DHAVE_AVX -D__x86_64 -DHAVE_SSE2 -DHAVE_AVX512F -DHAVE_SSSE3
.endif
.if defined(WITH_DEBUG) && ${WITH_DEBUG} == "true"
CFLAGS+= -DZFS_DEBUG -g
.if defined(WITH_INVARIANTS) && ${WITH_INVARIANTS} == "true"
CFLAGS+= -DINVARIANTS -DWITNESS -DOPENSOLARIS_WITNESS
.endif
.if defined(WITH_O0) && ${WITH_O0} == "true"
CFLAGS+= -O0
.endif
.else
CFLAGS += -DNDEBUG
.endif
.if defined(WITH_VFS_DEBUG) && ${WITH_VFS_DEBUG} == "true"
# kernel must also be built with this option for this to work
CFLAGS+= -DDEBUG_VFS_LOCKS
.endif
.if defined(WITH_GCOV) && ${WITH_GCOV} == "true"
CFLAGS+= -fprofile-arcs -ftest-coverage
.endif
DEBUG_FLAGS=-g
.if ${MACHINE_ARCH} == "i386" || ${MACHINE_ARCH} == "powerpc" || \
${MACHINE_ARCH} == "arm"
CFLAGS+= -DBITS_PER_LONG=32
.else
CFLAGS+= -DBITS_PER_LONG=64
.endif
SRCS= vnode_if.h device_if.h bus_if.h
# avl
SRCS+= avl.c
# icp
SRCS+= edonr.c
#lua
SRCS+= lapi.c \
lauxlib.c \
lbaselib.c \
lcode.c \
lcompat.c \
lcorolib.c \
lctype.c \
ldebug.c \
ldo.c \
lfunc.c \
lgc.c \
llex.c \
lmem.c \
lobject.c \
lopcodes.c \
lparser.c \
lstate.c \
lstring.c \
lstrlib.c \
ltable.c \
ltablib.c \
ltm.c \
lvm.c \
lzio.c
#nvpair
SRCS+= nvpair.c \
fnvpair.c \
nvpair_alloc_spl.c \
nvpair_alloc_fixed.c
#os/freebsd/spl
SRCS+= acl_common.c \
callb.c \
list.c \
sha256c.c \
sha512c.c \
spl_acl.c \
spl_cmn_err.c \
spl_dtrace.c \
spl_kmem.c \
spl_kstat.c \
spl_misc.c \
spl_policy.c \
spl_procfs_list.c \
spl_string.c \
spl_sunddi.c \
spl_sysevent.c \
spl_taskq.c \
spl_uio.c \
spl_vfs.c \
spl_vm.c \
spl_zlib.c \
spl_zone.c
.if ${MACHINE_ARCH} == "i386" || ${MACHINE_ARCH} == "powerpc" || \
${MACHINE_ARCH} == "arm"
SRCS+= spl_atomic.c
.endif
#os/freebsd/zfs
SRCS+= abd_os.c \
arc_os.c \
crypto_os.c \
dmu_os.c \
hkdf.c \
kmod_core.c \
spa_os.c \
sysctl_os.c \
vdev_file.c \
vdev_geom.c \
vdev_label_os.c \
zfs_acl.c \
zfs_ctldir.c \
zfs_debug.c \
zfs_dir.c \
zfs_ioctl_compat.c \
zfs_ioctl_os.c \
zfs_racct.c \
zfs_vfsops.c \
zfs_vnops_os.c \
zfs_znode.c \
zio_crypt.c \
zvol_os.c
#unicode
SRCS+= uconv.c \
u8_textprep.c
#zcommon
SRCS+= zfeature_common.c \
zfs_comutil.c \
zfs_deleg.c \
zfs_fletcher.c \
zfs_fletcher_avx512.c \
zfs_fletcher_intel.c \
zfs_fletcher_sse.c \
zfs_fletcher_superscalar.c \
zfs_fletcher_superscalar4.c \
zfs_namecheck.c \
zfs_prop.c \
zpool_prop.c \
zprop_common.c
#zfs
SRCS+= abd.c \
aggsum.c \
arc.c \
blkptr.c \
bplist.c \
bpobj.c \
btree.c \
cityhash.c \
dbuf.c \
dbuf_stats.c \
bptree.c \
bqueue.c \
dataset_kstats.c \
ddt.c \
ddt_zap.c \
dmu.c \
dmu_diff.c \
dmu_object.c \
dmu_objset.c \
dmu_recv.c \
dmu_redact.c \
dmu_send.c \
dmu_traverse.c \
dmu_tx.c \
dmu_zfetch.c \
dnode.c \
dnode_sync.c \
dsl_dataset.c \
dsl_deadlist.c \
dsl_deleg.c \
dsl_bookmark.c \
dsl_dir.c \
dsl_crypt.c \
dsl_destroy.c \
dsl_pool.c \
dsl_prop.c \
dsl_scan.c \
dsl_synctask.c \
dsl_userhold.c \
edonr_zfs.c \
fm.c \
gzip.c \
lzjb.c \
lz4.c \
lz4_zfs.c \
metaslab.c \
mmp.c \
multilist.c \
objlist.c \
pathname.c \
range_tree.c \
refcount.c \
rrwlock.c \
sa.c \
sha256.c \
skein_zfs.c \
spa.c \
spa_boot.c \
spa_checkpoint.c \
spa_config.c \
spa_errlog.c \
spa_history.c \
spa_log_spacemap.c \
spa_misc.c \
spa_stats.c \
space_map.c \
space_reftree.c \
txg.c \
uberblock.c \
unique.c \
vdev.c \
vdev_cache.c \
Distributed Spare (dRAID) Feature This patch adds a new top-level vdev type called dRAID, which stands for Distributed parity RAID. This pool configuration allows all dRAID vdevs to participate when rebuilding to a distributed hot spare device. This can substantially reduce the total time required to restore full parity to pool with a failed device. A dRAID pool can be created using the new top-level `draid` type. Like `raidz`, the desired redundancy is specified after the type: `draid[1,2,3]`. No additional information is required to create the pool and reasonable default values will be chosen based on the number of child vdevs in the dRAID vdev. zpool create <pool> draid[1,2,3] <vdevs...> Unlike raidz, additional optional dRAID configuration values can be provided as part of the draid type as colon separated values. This allows administrators to fully specify a layout for either performance or capacity reasons. The supported options include: zpool create <pool> \ draid[<parity>][:<data>d][:<children>c][:<spares>s] \ <vdevs...> - draid[parity] - Parity level (default 1) - draid[:<data>d] - Data devices per group (default 8) - draid[:<children>c] - Expected number of child vdevs - draid[:<spares>s] - Distributed hot spares (default 0) Abbreviated example `zpool status` output for a 68 disk dRAID pool with two distributed spares using special allocation classes. ``` pool: tank state: ONLINE config: NAME STATE READ WRITE CKSUM slag7 ONLINE 0 0 0 draid2:8d:68c:2s-0 ONLINE 0 0 0 L0 ONLINE 0 0 0 L1 ONLINE 0 0 0 ... U25 ONLINE 0 0 0 U26 ONLINE 0 0 0 spare-53 ONLINE 0 0 0 U27 ONLINE 0 0 0 draid2-0-0 ONLINE 0 0 0 U28 ONLINE 0 0 0 U29 ONLINE 0 0 0 ... U42 ONLINE 0 0 0 U43 ONLINE 0 0 0 special mirror-1 ONLINE 0 0 0 L5 ONLINE 0 0 0 U5 ONLINE 0 0 0 mirror-2 ONLINE 0 0 0 L6 ONLINE 0 0 0 U6 ONLINE 0 0 0 spares draid2-0-0 INUSE currently in use draid2-0-1 AVAIL ``` When adding test coverage for the new dRAID vdev type the following options were added to the ztest command. These options are leverages by zloop.sh to test a wide range of dRAID configurations. -K draid|raidz|random - kind of RAID to test -D <value> - dRAID data drives per group -S <value> - dRAID distributed hot spares -R <value> - RAID parity (raidz or dRAID) The zpool_create, zpool_import, redundancy, replacement and fault test groups have all been updated provide test coverage for the dRAID feature. Co-authored-by: Isaac Huang <he.huang@intel.com> Co-authored-by: Mark Maybee <mmaybee@cray.com> Co-authored-by: Don Brady <don.brady@delphix.com> Co-authored-by: Matthew Ahrens <mahrens@delphix.com> Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Mark Maybee <mmaybee@cray.com> Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #10102
2020-11-14 00:51:51 +03:00
vdev_draid.c \
vdev_draid_rand.c \
vdev_indirect.c \
vdev_indirect_births.c \
vdev_indirect_mapping.c \
vdev_initialize.c \
vdev_label.c \
vdev_mirror.c \
vdev_missing.c \
vdev_queue.c \
vdev_raidz.c \
vdev_raidz_math.c \
vdev_raidz_math_scalar.c \
vdev_raidz_math_avx2.c \
vdev_raidz_math_avx512bw.c \
vdev_raidz_math_avx512f.c \
vdev_raidz_math_sse2.c \
vdev_raidz_math_ssse3.c \
vdev_rebuild.c \
vdev_removal.c \
vdev_root.c \
vdev_trim.c \
zap.c \
zap_leaf.c \
zap_micro.c \
zcp.c \
zcp_get.c \
zcp_global.c \
zcp_iter.c \
zcp_set.c \
zcp_synctask.c \
zfeature.c \
zfs_byteswap.c \
zfs_file_os.c \
zfs_fm.c \
zfs_fuid.c \
zfs_ioctl.c \
zfs_log.c \
zfs_onexit.c \
zfs_quota.c \
zfs_ratelimit.c \
zfs_replay.c \
zfs_rlock.c \
zfs_sa.c \
zfs_vnops.c \
zil.c \
zio.c \
zio_checksum.c \
zio_compress.c \
zio_inject.c \
zle.c \
zrlock.c \
zthr.c \
zvol.c
Add zstd support to zfs This PR adds two new compression types, based on ZStandard: - zstd: A basic ZStandard compression algorithm Available compression. Levels for zstd are zstd-1 through zstd-19, where the compression increases with every level, but speed decreases. - zstd-fast: A faster version of the ZStandard compression algorithm zstd-fast is basically a "negative" level of zstd. The compression decreases with every level, but speed increases. Available compression levels for zstd-fast: - zstd-fast-1 through zstd-fast-10 - zstd-fast-20 through zstd-fast-100 (in increments of 10) - zstd-fast-500 and zstd-fast-1000 For more information check the man page. Implementation details: Rather than treat each level of zstd as a different algorithm (as was done historically with gzip), the block pointer `enum zio_compress` value is simply zstd for all levels, including zstd-fast, since they all use the same decompression function. The compress= property (a 64bit unsigned integer) uses the lower 7 bits to store the compression algorithm (matching the number of bits used in a block pointer, as the 8th bit was borrowed for embedded block pointers). The upper bits are used to store the compression level. It is necessary to be able to determine what compression level was used when later reading a block back, so the concept used in LZ4, where the first 32bits of the on-disk value are the size of the compressed data (since the allocation is rounded up to the nearest ashift), was extended, and we store the version of ZSTD and the level as well as the compressed size. This value is returned when decompressing a block, so that if the block needs to be recompressed (L2ARC, nop-write, etc), that the same parameters will be used to result in the matching checksum. All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`, `zio_prop_t`, etc.) uses the separated _compress and _complevel variables. Only the properties ZAP contains the combined/bit-shifted value. The combined value is split when the compression_changed_cb() callback is called, and sets both objset members (os_compress and os_complevel). The userspace tools all use the combined/bit-shifted value. Additional notes: zdb can now also decode the ZSTD compression header (flag -Z) and inspect the size, version and compression level saved in that header. For each record, if it is ZSTD compressed, the parameters of the decoded compression header get printed. ZSTD is included with all current tests and new tests are added as-needed. Per-dataset feature flags now get activated when the property is set. If a compression algorithm requires a feature flag, zfs activates the feature when the property is set, rather than waiting for the first block to be born. This is currently only used by zstd but can be extended as needed. Portions-Sponsored-By: The FreeBSD Foundation Co-authored-by: Allan Jude <allanjude@freebsd.org> Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov> Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Co-authored-by: Michael Niewöhner <foss@mniewoehner.de> Signed-off-by: Allan Jude <allan@klarasystems.com> Signed-off-by: Allan Jude <allanjude@freebsd.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Signed-off-by: Michael Niewöhner <foss@mniewoehner.de> Closes #6247 Closes #9024 Closes #10277 Closes #10278
2020-08-18 20:10:17 +03:00
#zstd
SRCS+= zfs_zstd.c \
entropy_common.c \
error_private.c \
fse_decompress.c \
pool.c \
zstd_common.c \
fse_compress.c \
hist.c \
huf_compress.c \
zstd_compress.c \
zstd_compress_literals.c \
zstd_compress_sequences.c \
zstd_compress_superblock.c \
zstd_double_fast.c \
zstd_fast.c \
zstd_lazy.c \
zstd_ldm.c \
zstd_opt.c \
huf_decompress.c \
zstd_ddict.c \
zstd_decompress.c \
zstd_decompress_block.c
Add zstd support to zfs This PR adds two new compression types, based on ZStandard: - zstd: A basic ZStandard compression algorithm Available compression. Levels for zstd are zstd-1 through zstd-19, where the compression increases with every level, but speed decreases. - zstd-fast: A faster version of the ZStandard compression algorithm zstd-fast is basically a "negative" level of zstd. The compression decreases with every level, but speed increases. Available compression levels for zstd-fast: - zstd-fast-1 through zstd-fast-10 - zstd-fast-20 through zstd-fast-100 (in increments of 10) - zstd-fast-500 and zstd-fast-1000 For more information check the man page. Implementation details: Rather than treat each level of zstd as a different algorithm (as was done historically with gzip), the block pointer `enum zio_compress` value is simply zstd for all levels, including zstd-fast, since they all use the same decompression function. The compress= property (a 64bit unsigned integer) uses the lower 7 bits to store the compression algorithm (matching the number of bits used in a block pointer, as the 8th bit was borrowed for embedded block pointers). The upper bits are used to store the compression level. It is necessary to be able to determine what compression level was used when later reading a block back, so the concept used in LZ4, where the first 32bits of the on-disk value are the size of the compressed data (since the allocation is rounded up to the nearest ashift), was extended, and we store the version of ZSTD and the level as well as the compressed size. This value is returned when decompressing a block, so that if the block needs to be recompressed (L2ARC, nop-write, etc), that the same parameters will be used to result in the matching checksum. All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`, `zio_prop_t`, etc.) uses the separated _compress and _complevel variables. Only the properties ZAP contains the combined/bit-shifted value. The combined value is split when the compression_changed_cb() callback is called, and sets both objset members (os_compress and os_complevel). The userspace tools all use the combined/bit-shifted value. Additional notes: zdb can now also decode the ZSTD compression header (flag -Z) and inspect the size, version and compression level saved in that header. For each record, if it is ZSTD compressed, the parameters of the decoded compression header get printed. ZSTD is included with all current tests and new tests are added as-needed. Per-dataset feature flags now get activated when the property is set. If a compression algorithm requires a feature flag, zfs activates the feature when the property is set, rather than waiting for the first block to be born. This is currently only used by zstd but can be extended as needed. Portions-Sponsored-By: The FreeBSD Foundation Co-authored-by: Allan Jude <allanjude@freebsd.org> Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov> Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Co-authored-by: Michael Niewöhner <foss@mniewoehner.de> Signed-off-by: Allan Jude <allan@klarasystems.com> Signed-off-by: Allan Jude <allanjude@freebsd.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Signed-off-by: Michael Niewöhner <foss@mniewoehner.de> Closes #6247 Closes #9024 Closes #10277 Closes #10278
2020-08-18 20:10:17 +03:00
beforeinstall:
.if ${MK_DEBUG_FILES} != "no"
mtree -eu \
-f /etc/mtree/BSD.debug.dist \
-p ${DESTDIR}/usr/lib
.endif
.include <bsd.kmod.mk>
CFLAGS.gcc+= -Wno-pointer-to-int-cast
CFLAGS.lapi.c= -Wno-cast-qual
CFLAGS.lcompat.c= -Wno-cast-qual
CFLAGS.lobject.c= -Wno-cast-qual
CFLAGS.ltable.c= -Wno-cast-qual
CFLAGS.lvm.c= -Wno-cast-qual
CFLAGS.nvpair.c= -DHAVE_RPC_TYPES -Wno-cast-qual
CFLAGS.spl_string.c= -Wno-cast-qual
CFLAGS.spl_vm.c= -Wno-cast-qual
CFLAGS.spl_zlib.c= -Wno-cast-qual
CFLAGS.abd.c= -Wno-cast-qual
CFLAGS.zfs_log.c= -Wno-cast-qual
CFLAGS.zfs_vnops_os.c= -Wno-pointer-arith
CFLAGS.u8_textprep.c= -Wno-cast-qual
CFLAGS.zfs_fletcher.c= -Wno-cast-qual -Wno-pointer-arith
CFLAGS.zfs_fletcher_intel.c= -Wno-cast-qual -Wno-pointer-arith
CFLAGS.zfs_fletcher_sse.c= -Wno-cast-qual -Wno-pointer-arith
CFLAGS.zfs_fletcher_avx512.c= -Wno-cast-qual -Wno-pointer-arith
CFLAGS.zprop_common.c= -Wno-cast-qual
CFLAGS.ddt.c= -Wno-cast-qual
CFLAGS.dmu.c= -Wno-cast-qual
CFLAGS.dmu_traverse.c= -Wno-cast-qual
CFLAGS.dsl_dir.c= -Wno-cast-qual
CFLAGS.dsl_deadlist.c= -Wno-cast-qual
CFLAGS.dsl_prop.c= -Wno-cast-qual
CFLAGS.edonr.c=-Wno-cast-qual
CFLAGS.fm.c= -Wno-cast-qual
CFLAGS.lz4_zfs.c= -Wno-cast-qual
CFLAGS.spa.c= -Wno-cast-qual
CFLAGS.spa_misc.c= -Wno-cast-qual
CFLAGS.sysctl_os.c= -include ../zfs_config.h
Distributed Spare (dRAID) Feature This patch adds a new top-level vdev type called dRAID, which stands for Distributed parity RAID. This pool configuration allows all dRAID vdevs to participate when rebuilding to a distributed hot spare device. This can substantially reduce the total time required to restore full parity to pool with a failed device. A dRAID pool can be created using the new top-level `draid` type. Like `raidz`, the desired redundancy is specified after the type: `draid[1,2,3]`. No additional information is required to create the pool and reasonable default values will be chosen based on the number of child vdevs in the dRAID vdev. zpool create <pool> draid[1,2,3] <vdevs...> Unlike raidz, additional optional dRAID configuration values can be provided as part of the draid type as colon separated values. This allows administrators to fully specify a layout for either performance or capacity reasons. The supported options include: zpool create <pool> \ draid[<parity>][:<data>d][:<children>c][:<spares>s] \ <vdevs...> - draid[parity] - Parity level (default 1) - draid[:<data>d] - Data devices per group (default 8) - draid[:<children>c] - Expected number of child vdevs - draid[:<spares>s] - Distributed hot spares (default 0) Abbreviated example `zpool status` output for a 68 disk dRAID pool with two distributed spares using special allocation classes. ``` pool: tank state: ONLINE config: NAME STATE READ WRITE CKSUM slag7 ONLINE 0 0 0 draid2:8d:68c:2s-0 ONLINE 0 0 0 L0 ONLINE 0 0 0 L1 ONLINE 0 0 0 ... U25 ONLINE 0 0 0 U26 ONLINE 0 0 0 spare-53 ONLINE 0 0 0 U27 ONLINE 0 0 0 draid2-0-0 ONLINE 0 0 0 U28 ONLINE 0 0 0 U29 ONLINE 0 0 0 ... U42 ONLINE 0 0 0 U43 ONLINE 0 0 0 special mirror-1 ONLINE 0 0 0 L5 ONLINE 0 0 0 U5 ONLINE 0 0 0 mirror-2 ONLINE 0 0 0 L6 ONLINE 0 0 0 U6 ONLINE 0 0 0 spares draid2-0-0 INUSE currently in use draid2-0-1 AVAIL ``` When adding test coverage for the new dRAID vdev type the following options were added to the ztest command. These options are leverages by zloop.sh to test a wide range of dRAID configurations. -K draid|raidz|random - kind of RAID to test -D <value> - dRAID data drives per group -S <value> - dRAID distributed hot spares -R <value> - RAID parity (raidz or dRAID) The zpool_create, zpool_import, redundancy, replacement and fault test groups have all been updated provide test coverage for the dRAID feature. Co-authored-by: Isaac Huang <he.huang@intel.com> Co-authored-by: Mark Maybee <mmaybee@cray.com> Co-authored-by: Don Brady <don.brady@delphix.com> Co-authored-by: Matthew Ahrens <mahrens@delphix.com> Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Mark Maybee <mmaybee@cray.com> Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #10102
2020-11-14 00:51:51 +03:00
CFLAGS.vdev_draid.c= -Wno-cast-qual
CFLAGS.vdev_raidz.c= -Wno-cast-qual
CFLAGS.vdev_raidz_math.c= -Wno-cast-qual
CFLAGS.vdev_raidz_math_scalar.c= -Wno-cast-qual
CFLAGS.vdev_raidz_math_avx2.c= -Wno-cast-qual -Wno-duplicate-decl-specifier
CFLAGS.vdev_raidz_math_avx512f.c= -Wno-cast-qual -Wno-duplicate-decl-specifier
CFLAGS.vdev_raidz_math_sse2.c= -Wno-cast-qual -Wno-duplicate-decl-specifier
CFLAGS.zap_leaf.c= -Wno-cast-qual
CFLAGS.zap_micro.c= -Wno-cast-qual
CFLAGS.zcp.c= -Wno-cast-qual
CFLAGS.zfs_fm.c= -Wno-cast-qual
CFLAGS.zfs_ioctl.c= -Wno-cast-qual
CFLAGS.zil.c= -Wno-cast-qual
CFLAGS.zio.c= -Wno-cast-qual
CFLAGS.zrlock.c= -Wno-cast-qual
Add zstd support to zfs This PR adds two new compression types, based on ZStandard: - zstd: A basic ZStandard compression algorithm Available compression. Levels for zstd are zstd-1 through zstd-19, where the compression increases with every level, but speed decreases. - zstd-fast: A faster version of the ZStandard compression algorithm zstd-fast is basically a "negative" level of zstd. The compression decreases with every level, but speed increases. Available compression levels for zstd-fast: - zstd-fast-1 through zstd-fast-10 - zstd-fast-20 through zstd-fast-100 (in increments of 10) - zstd-fast-500 and zstd-fast-1000 For more information check the man page. Implementation details: Rather than treat each level of zstd as a different algorithm (as was done historically with gzip), the block pointer `enum zio_compress` value is simply zstd for all levels, including zstd-fast, since they all use the same decompression function. The compress= property (a 64bit unsigned integer) uses the lower 7 bits to store the compression algorithm (matching the number of bits used in a block pointer, as the 8th bit was borrowed for embedded block pointers). The upper bits are used to store the compression level. It is necessary to be able to determine what compression level was used when later reading a block back, so the concept used in LZ4, where the first 32bits of the on-disk value are the size of the compressed data (since the allocation is rounded up to the nearest ashift), was extended, and we store the version of ZSTD and the level as well as the compressed size. This value is returned when decompressing a block, so that if the block needs to be recompressed (L2ARC, nop-write, etc), that the same parameters will be used to result in the matching checksum. All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`, `zio_prop_t`, etc.) uses the separated _compress and _complevel variables. Only the properties ZAP contains the combined/bit-shifted value. The combined value is split when the compression_changed_cb() callback is called, and sets both objset members (os_compress and os_complevel). The userspace tools all use the combined/bit-shifted value. Additional notes: zdb can now also decode the ZSTD compression header (flag -Z) and inspect the size, version and compression level saved in that header. For each record, if it is ZSTD compressed, the parameters of the decoded compression header get printed. ZSTD is included with all current tests and new tests are added as-needed. Per-dataset feature flags now get activated when the property is set. If a compression algorithm requires a feature flag, zfs activates the feature when the property is set, rather than waiting for the first block to be born. This is currently only used by zstd but can be extended as needed. Portions-Sponsored-By: The FreeBSD Foundation Co-authored-by: Allan Jude <allanjude@freebsd.org> Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov> Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Co-authored-by: Michael Niewöhner <foss@mniewoehner.de> Signed-off-by: Allan Jude <allan@klarasystems.com> Signed-off-by: Allan Jude <allanjude@freebsd.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl> Signed-off-by: Michael Niewöhner <foss@mniewoehner.de> Closes #6247 Closes #9024 Closes #10277 Closes #10278
2020-08-18 20:10:17 +03:00
CFLAGS.zfs_zstd.c= -Wno-cast-qual -Wno-pointer-arith
CFLAGS.entropy_common.c= -fno-tree-vectorize -U__BMI__
CFLAGS.error_private.c= -fno-tree-vectorize -U__BMI__
CFLAGS.fse_decompress.c= -fno-tree-vectorize -U__BMI__
CFLAGS.pool.c= -fno-tree-vectorize -U__BMI__
CFLAGS.xxhash.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_common.c= -fno-tree-vectorize -U__BMI__
CFLAGS.fse_compress.c= -fno-tree-vectorize -U__BMI__
CFLAGS.hist.c= -fno-tree-vectorize -U__BMI__
CFLAGS.huf_compress.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_compress.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_compress_literals.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_compress_sequences.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_compress_superblock.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_double_fast.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_fast.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_lazy.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_ldm.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_opt.c= -fno-tree-vectorize -U__BMI__
CFLAGS.huf_decompress.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_ddict.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_decompress.c= -fno-tree-vectorize -U__BMI__
CFLAGS.zstd_decompress_block.c= -fno-tree-vectorize -U__BMI__