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

man/man5/zpool-features.5

@@ -14,6 +14,8 @@
 .\" CDDL HEADER, with the fields enclosed by brackets "[]" replaced with your
 .\" own identifying information:
 .\" Portions Copyright [yyyy] [name of copyright owner]
+.\" Copyright (c) 2019, Klara Inc.
+.\" Copyright (c) 2019, Allan Jude
 .TH ZPOOL-FEATURES 5 "Jun 8, 2018"
 .SH NAME
 zpool\-features \- ZFS pool feature descriptions
@@ -946,6 +948,38 @@ This feature becomes \fBactive\fR when the \fBzpool checkpoint\fR subcommand
 is used to checkpoint the pool.
 The feature will only return back to being \fBenabled\fR when the pool
 is rewound or the checkpoint has been discarded.
+.RE
+
+.sp
+.ne 2
+.na
+\fBzstd_compress\fR
+.ad
+.RS 4n
+.TS
+l l .
+GUID	org.freebsd:zstd_compress
+READ\-ONLY COMPATIBLE	no
+DEPENDENCIES	extensible_dataset
+.TE
+
+\fBzstd\fR is a high-performance compression algorithm that features a
+combination of high compression ratios and high speed. Compared to \fBgzip\fR,
+\fBzstd\fR offers slighty better compression at much higher speeds. Compared
+to \fBlz4\fR, \fBzstd\fR offers much better compression while being only
+modestly slower. Typically, \fBzstd\fR compression speed ranges from 250 to 500
+MB/s per thread and decompression speed is over 1 GB/s per thread.
+
+When the \fBzstd\fR feature is set to \fBenabled\fR, the administrator can turn
+on \fBzstd\fR compression of any dataset by running
+`zfs set compress=zstd <pool/fs>`.
+
+This feature becomes \fBactive\fR once a \fBcompress\fR property has been set to
+\fBzstd\fR, and will return to being \fBenabled\fR once all filesystems that
+have ever had their compress property set to \fBzstd\fR are destroyed.
+
+Booting off of \fBzstd\fR-compressed root pools is not yet supported.
+.RE
 
 .SH "SEE ALSO"
 zpool(8)

man/man8/zfsprops.8

@@ -36,6 +36,7 @@
 .\" Copyright 2019 Richard Laager. All rights reserved.
 .\" Copyright 2018 Nexenta Systems, Inc.
 .\" Copyright 2019 Joyent, Inc.
+.\" Copyright (c) 2019, Kjeld Schouten-Lebbing
 .\"
 .Dd January 30, 2020
 .Dt ZFSPROPS 8
@@ -773,7 +774,8 @@ for more information on these algorithms.
 Changing this property affects only newly-written data.
 .It Xo
 .Sy compression Ns = Ns Sy on Ns | Ns Sy off Ns | Ns Sy gzip Ns | Ns
-.Sy gzip- Ns Em N Ns | Ns Sy lz4 Ns | Ns Sy lzjb Ns | Ns Sy zle
+.Sy gzip- Ns Em N Ns | Ns Sy lz4 Ns | Ns Sy lzjb Ns | Ns Sy zle Ns | Ns Sy zstd Ns | Ns
+.Sy zstd- Ns Em N Ns | Ns Sy zstd-fast Ns | Ns Sy zstd-fast- Ns Em N
 .Xc
 Controls the compression algorithm used for this dataset.
 .Pp
@@ -841,6 +843,38 @@ is equivalent to
 .Pc .
 .Pp
 The
+.Sy zstd
+compression algorithm provides both high compression ratios and good
+performance. You can specify the
+.Sy zstd
+level by using the value
+.Sy zstd- Ns Em N ,
+where
+.Em N
+is an integer from 1
+.Pq fastest
+to 19
+.Pq best compression ratio .
+.Sy zstd
+is equivalent to
+.Sy zstd-3 .
+.Pp
+Faster speeds at the cost of the compression ratio can be requested by
+setting a negative
+.Sy zstd
+level.  This is done using
+.Sy zstd-fast- Ns Em N ,
+where
+.Em N
+is an integer in [1-9,10,20,30,...,100,500,1000] which maps to a negative
+.Sy zstd
+level. The lower the level the faster the compression - 1000 provides
+the fastest compression and lowest compression ratio.
+.Sy zstd-fast
+is equivalent to
+.Sy zstd-fast-1 .
+.Pp
+The
 .Sy zle
 compression algorithm compresses runs of zeros.
 .Pp