The on-disk format for encrypted datasets protects not only
the encrypted and authenticated blocks themselves, but also
the order and interpretation of these blocks. In order to
make this work while maintaining the ability to do raw
sends, the indirect bps maintain a secure checksum of all
the MACs in the block below it along with a few other
fields that determine how the data is interpreted.
Unfortunately, the current on-disk format erroneously
includes some fields which are not portable and thus cannot
support raw sends. It is not possible to easily work around
this issue due to a separate and much smaller bug which
causes indirect blocks for encrypted dnodes to not be
compressed, which conflicts with the previous bug. In
addition, the current code generates incompatible on-disk
formats on big endian and little endian systems due to an
issue with how block pointers are authenticated. Finally,
raw send streams do not currently include dn_maxblkid when
sending both the metadnode and normal dnodes which are
needed in order to ensure that we are correctly maintaining
the portable objset MAC.
This patch zero's out the offending fields when computing
the bp MAC and ensures that these MACs are always
calculated in little endian order (regardless of the host
system's byte order). This patch also registers an errata
for the old on-disk format, which we detect by adding a
"version" field to newly created DSL Crypto Keys. We allow
datasets without a version (version 0) to only be mounted
for read so that they can easily be migrated. We also now
include dn_maxblkid in raw send streams to ensure the MAC
can be maintained correctly.
This patch also contains minor bug fixes and cleanups.
Reviewed-by: Jorgen Lundman <lundman@lundman.net>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes#6845Closes#6864Closes#7052
PROBLEM
=======
When `dmu_tx_assign` is called from `zil_lwb_write_issue`, it's possible
for either `ERESTART` or `EIO` to be returned.
If `ERESTART` is returned, this will cause an assertion to fail directly
in `zil_lwb_write_issue`, where the code assumes the return value is
`EIO` if `dmu_tx_assign` returns a non-zero value. This can occur if the
SPA is suspended when `dmu_tx_assign` is called, and most often occurs
when running `zloop`.
If `EIO` is returned, this can cause assertions to fail elsewhere in the
ZIL code. For example, `zil_commit_waiter_timeout` contains the
following logic:
lwb_t *nlwb = zil_lwb_write_issue(zilog, lwb);
ASSERT3S(lwb->lwb_state, !=, LWB_STATE_OPENED);
In this case, if `dmu_tx_assign` returned `EIO` from within
`zil_lwb_write_issue`, the `lwb` variable passed in will not be issued
to disk. Thus, it's `lwb_state` field will remain `LWB_STATE_OPENED` and
this assertion will fail. `zil_commit_waiter_timeout` assumes that after
it calls `zil_lwb_write_issue`, the `lwb` will be issued to disk, and
doesn't handle the case where this is not true; i.e. it doesn't handle
the case where `dmu_tx_assign` returns `EIO`.
SOLUTION
========
This change modifies the `dmu_tx_assign` function such that `txg_how` is
a bitmask, rather than of the `txg_how_t` enum type. Now, the previous
`TXG_WAITED` semantics can be used via `TXG_NOTHROTTLE`, along with
specifying either `TXG_NOWAIT` or `TXG_WAIT` semantics.
Previously, when `TXG_WAITED` was specified, `TXG_NOWAIT` semantics was
automatically invoked. This was not ideal when using `TXG_WAITED` within
`zil_lwb_write_issued`, leading the problem described above. Rather, we
want to achieve the semantics of `TXG_WAIT`, while also preventing the
`tx` from being penalized via the dirty delay throttling.
With this change, `zil_lwb_write_issued` can acheive the semtantics that
it requires by passing in the value `TXG_WAIT | TXG_NOTHROTTLE` to
`dmu_tx_assign`.
Further, consumers of `dmu_tx_assign` wishing to achieve the old
`TXG_WAITED` semantics can pass in the value `TXG_NOWAIT | TXG_NOTHROTTLE`.
Authored by: Prakash Surya <prakash.surya@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Reviewed by: Andriy Gapon <avg@FreeBSD.org>
Ported-by: Brian Behlendorf <behlendorf1@llnl.gov>
Porting Notes:
- Additionally updated `zfs_tmpfile` to use `TXG_NOTHROTTLE`
OpenZFS-issue: https://www.illumos.org/issues/8997
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/19ea6cb0f9Closes#7084
Our zfs backed Lustre MDT had soft lockups while under heavy metadata
workloads while handling transaction callbacks from osd_zfs.
The problem is zfs is not taking advantage of the fast path in
Lustre's trans callback handling, where Lustre will skip the calls
to ptlrpc_commit_replies() when it already saw a higher transaction
number.
This patch corrects this, it also has a positive impact on metadata
performance on Lustre with osd_zfs, plus some cleanup in the headers.
A similar issue for ext4/ldiskfs is described on:
https://jira.hpdd.intel.com/browse/LU-6527
Reviewed-by: Olaf Faaland <faaland1@llnl.gov>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Li Dongyang <dongyang.li@anu.edu.au>
Closes#6986
Authored by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Dan McDonald <danmcd@joyent.com>
Ported-by: Prakash Surya <prakash.surya@delphix.com>
Problem
=======
The current implementation of zil_commit() can introduce significant
latency, beyond what is inherent due to the latency of the underlying
storage. The additional latency comes from two main problems:
1. When there's outstanding ZIL blocks being written (i.e. there's
already a "writer thread" in progress), then any new calls to
zil_commit() will block waiting for the currently oustanding ZIL
blocks to complete. The blocks written for each "writer thread" is
coined a "batch", and there can only ever be a single "batch" being
written at a time. When a batch is being written, any new ZIL
transactions will have to wait for the next batch to be written,
which won't occur until the current batch finishes.
As a result, the underlying storage may not be used as efficiently
as possible. While "new" threads enter zil_commit() and are blocked
waiting for the next batch, it's possible that the underlying
storage isn't fully utilized by the current batch of ZIL blocks. In
that case, it'd be better to allow these new threads to generate
(and issue) a new ZIL block, such that it could be serviced by the
underlying storage concurrently with the other ZIL blocks that are
being serviced.
2. Any call to zil_commit() must wait for all ZIL blocks in its "batch"
to complete, prior to zil_commit() returning. The size of any given
batch is proportional to the number of ZIL transaction in the queue
at the time that the batch starts processing the queue; which
doesn't occur until the previous batch completes. Thus, if there's a
lot of transactions in the queue, the batch could be composed of
many ZIL blocks, and each call to zil_commit() will have to wait for
all of these writes to complete (even if the thread calling
zil_commit() only cared about one of the transactions in the batch).
To further complicate the situation, these two issues result in the
following side effect:
3. If a given batch takes longer to complete than normal, this results
in larger batch sizes, which then take longer to complete and
further drive up the latency of zil_commit(). This can occur for a
number of reasons, including (but not limited to): transient changes
in the workload, and storage latency irregularites.
Solution
========
The solution attempted by this change has the following goals:
1. no on-disk changes; maintain current on-disk format.
2. modify the "batch size" to be equal to the "ZIL block size".
3. allow new batches to be generated and issued to disk, while there's
already batches being serviced by the disk.
4. allow zil_commit() to wait for as few ZIL blocks as possible.
5. use as few ZIL blocks as possible, for the same amount of ZIL
transactions, without introducing significant latency to any
individual ZIL transaction. i.e. use fewer, but larger, ZIL blocks.
In theory, with these goals met, the new allgorithm will allow the
following improvements:
1. new ZIL blocks can be generated and issued, while there's already
oustanding ZIL blocks being serviced by the storage.
2. the latency of zil_commit() should be proportional to the underlying
storage latency, rather than the incoming synchronous workload.
Porting Notes
=============
Due to the changes made in commit 119a394ab0, the lifetime of an itx
structure differs than in OpenZFS. Specifically, the itx structure is
kept around until the data associated with the itx is considered to be
safe on disk; this is so that the itx's callback can be called after the
data is committed to stable storage. Since OpenZFS doesn't have this itx
callback mechanism, it's able to destroy the itx structure immediately
after the itx is committed to an lwb (before the lwb is written to
disk).
To support this difference, and to ensure the itx's callbacks can still
be called after the itx's data is on disk, a few changes had to be made:
* A list of itxs was added to the lwb structure. This list contains
all of the itxs that have been committed to the lwb, such that the
callbacks for these itxs can be called from zil_lwb_flush_vdevs_done(),
after the data for the itxs is committed to disk.
* A list of itxs was added on the stack of the zil_process_commit_list()
function; the "nolwb_itxs" list. In some circumstances, an itx may
not be committed to an lwb (e.g. if allocating the "next" ZIL block
on disk fails), so this list is used to keep track of which itxs
fall into this state, such that their callbacks can be called after
the ZIL's writer pipeline is "stalled".
* The logic to actually call the itx's callback was moved into the
zil_itx_destroy() function. Since all consumers of zil_itx_destroy()
were effectively performing the same logic (i.e. if callback is
non-null, call the callback), it seemed like useful code cleanup to
consolidate this logic into a single function.
Additionally, the existing Linux tracepoint infrastructure dealing with
the ZIL's probes and structures had to be updated to reflect these code
changes. Specifically:
* The "zil__cw1" and "zil__cw2" probes were removed, so they had to be
removed from "trace_zil.h" as well.
* Some of the zilog structure's fields were removed, which affected
the tracepoint definitions of the structure.
* New tracepoints had to be added for the following 3 new probes:
* zil__process__commit__itx
* zil__process__normal__itx
* zil__commit__io__error
OpenZFS-issue: https://www.illumos.org/issues/8585
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/5d95a3aCloses#6566
Several issues were uncovered by running stress tests with zfs
encryption and raw sends in particular. The issues and their
associated fixes are as follows:
* arc_read_done() has the ability to chain several requests for
the same block of data via the arc_callback_t struct. In these
cases, the ARC would only use the first request's dsobj from
the bookmark to decrypt the data. This is problematic because
the first request might be a prefetch zio which is able to
handle the key not being loaded, while the second might use a
different key that it is sure will work. The fix here is to
pass the dsobj with each individual arc_callback_t so that each
request can attempt to decrypt the data separately.
* DRR_FREE and DRR_FREEOBJECT records in a send file were not
having their transactions properly tagged as raw during raw
sends, which caused a panic when the dbuf code attempted to
decrypt these blocks.
* traverse_prefetch_metadata() did not properly set
ZIO_FLAG_SPECULATIVE when issuing prefetch IOs.
* Added a few asserts and code cleanups to ensure these issues
are more detectable in the future.
Signed-off-by: Tom Caputi <tcaputi@datto.com>
This patch fixes several issues discovered after
the encryption patch was merged:
* Fixed a bug where encrypted datasets could attempt
to receive embedded data records.
* Fixed a bug where dirty records created by the recv
code wasn't properly setting the dr_raw flag.
* Fixed a typo where a dmu_tx_commit() was changed to
dmu_tx_abort()
* Fixed a few error handling bugs unrelated to the
encryption patch in dmu_recv_stream()
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes#6512Closes#6524Closes#6545
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#494Closes#5769
This continues what was started in
0eef1bde31 by fully converting zvols
to avoid unnecessary dnode_hold() calls. This saves a small amount
of CPU time and slightly improves latencies of operations on zvols.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Richard Yao <richard.yao@prophetstor.com>
Closes#6058
Authored by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Ported-by: Giuseppe Di Natale <dinatale2@llnl.gov>
When writing pre-compressed buffers, arc_write() requires that
the compression algorithm used to compress the buffer matches
the compression algorithm requested by the zio_prop_t, which is
set by dmu_write_policy(). This makes dmu_write_policy() and its
callers a bit more complicated.
We simplify this by making arc_write() trust the caller to supply
the type of pre-compressed buffer that it wants to write,
and override the compression setting in the zio_prop_t.
OpenZFS-issue: https://www.illumos.org/issues/8155
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/b55ff58Closes#6200
Reviewed by: Steve Gonczi <steve.gonczi@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Ported-by: Brian Behlendorf <behlendorf1@llnl.gov>
Background information: This assertion about tx_space_* verifies that we
are not dirtying more stuff than we thought we would. We “need” to know
how much we will dirty so that we can check if we should fail this
transaction with ENOSPC/EDQUOT, in dmu_tx_assign(). While the
transaction is open (i.e. between dmu_tx_assign() and dmu_tx_commit() —
typically less than a millisecond), we call dbuf_dirty() on the exact
blocks that will be modified. Once this happens, the temporary
accounting in tx_space_* is unnecessary, because we know exactly what
blocks are newly dirtied; we call dnode_willuse_space() to track this
more exact accounting.
The fundamental problem causing this bug is that dmu_tx_hold_*() relies
on the current state in the DMU (e.g. dn_nlevels) to predict how much
will be dirtied by this transaction, but this state can change before we
actually perform the transaction (i.e. call dbuf_dirty()).
This bug will be fixed by removing the assertion that the tx_space_*
accounting is perfectly accurate (i.e. we never dirty more than was
predicted by dmu_tx_hold_*()). By removing the requirement that this
accounting be perfectly accurate, we can also vastly simplify it, e.g.
removing most of the logic in dmu_tx_count_*().
The new tx space accounting will be very approximate, and may be more or
less than what is actually dirtied. It will still be used to determine
if this transaction will put us over quota. Transactions that are marked
by dmu_tx_mark_netfree() will be excepted from this check. We won’t make
an attempt to determine how much space will be freed by the transaction
— this was rarely accurate enough to determine if a transaction should
be permitted when we are over quota, which is why dmu_tx_mark_netfree()
was introduced in 2014.
We also won’t attempt to give “credit” when overwriting existing blocks,
if those blocks may be freed. This allows us to remove the
do_free_accounting logic in dbuf_dirty(), and associated routines. This
logic attempted to predict what will be on disk when this txg syncs, to
know if the overwritten block will be freed (i.e. exists, and has no
snapshots).
OpenZFS-issue: https://www.illumos.org/issues/7793
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/3704e0a
Upstream bugs: DLPX-32883a
Closes#5804
Porting notes:
- DNODE_SIZE replaced with DNODE_MIN_SIZE in dmu_tx_count_dnode(),
Using the default dnode size would be slightly better.
- DEBUG_DMU_TX wrappers and configure option removed.
- Resolved _by_dnode() conflicts these changes have not yet been
applied to OpenZFS.
Add *_by_dnode() routines for accessing objects given their
dnode_t *, this is more efficient than accessing the object by
(objset_t *, uint64_t object). This change converts some but
not all of the existing consumers. As performance-sensitive
code paths are discovered they should be converted to use
these routines.
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Closes#5534
Issue #4802
This patch tracks dnode usage for each user/group in the
DMU_USER/GROUPUSED_OBJECT ZAPs. ZAP entries dedicated to dnode
accounting have the key prefixed with "obj-" followed by the UID/GID
in string format (as done for the block accounting).
A new SPA feature has been added for dnode accounting as well as
a new ZPL version. The SPA feature must be enabled in the pool
before upgrading the zfs filesystem. During the zfs version upgrade,
a "quotacheck" will be executed by marking all dnode as dirty.
ZoL-bug-id: https://github.com/zfsonlinux/zfs/issues/3500
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Signed-off-by: Johann Lombardi <johann.lombardi@intel.com>
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:
b5e030c8db
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
Using a benchmark which has 32 threads creating 2 million files in the
same directory, on a machine with 16 CPU cores, I observed poor
performance. I noticed that dmu_tx_hold_zap() was using about 30% of
all CPU, and doing dnode_hold() 7 times on the same object (the ZAP
object that is being held).
dmu_tx_hold_zap() keeps a hold on the dnode_t the entire time it is
running, in dmu_tx_hold_t:txh_dnode, so it would be nice to use the
dnode_t that we already have in hand, rather than repeatedly calling
dnode_hold(). To do this, we need to pass the dnode_t down through
all the intermediate calls that dmu_tx_hold_zap() makes, making these
routines take the dnode_t* rather than an objset_t* and a uint64_t
object number. In particular, the following routines will need to have
analogous *_by_dnode() variants created:
dmu_buf_hold_noread()
dmu_buf_hold()
zap_lookup()
zap_lookup_norm()
zap_count_write()
zap_lockdir()
zap_count_write()
This can improve performance on the benchmark described above by 100%,
from 30,000 file creations per second to 60,000. (This improvement is on
top of that provided by working around the object allocation issue. Peak
performance of ~90,000 creations per second was observed with 8 CPUs;
adding CPUs past that decreased performance due to lock contention.) The
CPU used by dmu_tx_hold_zap() was reduced by 88%, from 340 CPU-seconds
to 40 CPU-seconds.
Sponsored by: Intel Corp.
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
OpenZFS-issue: https://www.illumos.org/issues/7004
OpenZFS-commit: https://github.com/openzfs/openzfs/pull/109Closes#4641Closes#4972
zap_lockdir() / zap_unlockdir() should take a "void *tag" argument which
tags the hold on the zap. This will help diagnose programming errors
which misuse the hold on the ZAP.
Sponsored by: Intel Corp.
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Pavel Zakharov <pavel.zakha@gmail.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
OpenZFS-issue: https://www.illumos.org/issues/7003
OpenZFS-commit: https://github.com/openzfs/openzfs/pull/108Closes#4972
Justification
-------------
This feature adds support for variable length dnodes. Our motivation is
to eliminate the overhead associated with using spill blocks. Spill
blocks are used to store system attribute data (i.e. file metadata) that
does not fit in the dnode's bonus buffer. By allowing a larger bonus
buffer area the use of a spill block can be avoided. Spill blocks
potentially incur an additional read I/O for every dnode in a dnode
block. As a worst case example, reading 32 dnodes from a 16k dnode block
and all of the spill blocks could issue 33 separate reads. Now suppose
those dnodes have size 1024 and therefore don't need spill blocks. Then
the worst case number of blocks read is reduced to from 33 to two--one
per dnode block. In practice spill blocks may tend to be co-located on
disk with the dnode blocks so the reduction in I/O would not be this
drastic. In a badly fragmented pool, however, the improvement could be
significant.
ZFS-on-Linux systems that make heavy use of extended attributes would
benefit from this feature. In particular, ZFS-on-Linux supports the
xattr=sa dataset property which allows file extended attribute data
to be stored in the dnode bonus buffer as an alternative to the
traditional directory-based format. Workloads such as SELinux and the
Lustre distributed filesystem often store enough xattr data to force
spill bocks when xattr=sa is in effect. Large dnodes may therefore
provide a performance benefit to such systems.
Other use cases that may benefit from this feature include files with
large ACLs and symbolic links with long target names. Furthermore,
this feature may be desirable on other platforms in case future
applications or features are developed that could make use of a
larger bonus buffer area.
Implementation
--------------
The size of a dnode may be a multiple of 512 bytes up to the size of
a dnode block (currently 16384 bytes). A dn_extra_slots field was
added to the current on-disk dnode_phys_t structure to describe the
size of the physical dnode on disk. The 8 bits for this field were
taken from the zero filled dn_pad2 field. The field represents how
many "extra" dnode_phys_t slots a dnode consumes in its dnode block.
This convention results in a value of 0 for 512 byte dnodes which
preserves on-disk format compatibility with older software.
Similarly, the in-memory dnode_t structure has a new dn_num_slots field
to represent the total number of dnode_phys_t slots consumed on disk.
Thus dn->dn_num_slots is 1 greater than the corresponding
dnp->dn_extra_slots. This difference in convention was adopted
because, unlike on-disk structures, backward compatibility is not a
concern for in-memory objects, so we used a more natural way to
represent size for a dnode_t.
The default size for newly created dnodes is determined by the value of
a new "dnodesize" dataset property. By default the property is set to
"legacy" which is compatible with older software. Setting the property
to "auto" will allow the filesystem to choose the most suitable dnode
size. Currently this just sets the default dnode size to 1k, but future
code improvements could dynamically choose a size based on observed
workload patterns. Dnodes of varying sizes can coexist within the same
dataset and even within the same dnode block. For example, to enable
automatically-sized dnodes, run
# zfs set dnodesize=auto tank/fish
The user can also specify literal values for the dnodesize property.
These are currently limited to powers of two from 1k to 16k. The
power-of-2 limitation is only for simplicity of the user interface.
Internally the implementation can handle any multiple of 512 up to 16k,
and consumers of the DMU API can specify any legal dnode value.
The size of a new dnode is determined at object allocation time and
stored as a new field in the znode in-memory structure. New DMU
interfaces are added to allow the consumer to specify the dnode size
that a newly allocated object should use. Existing interfaces are
unchanged to avoid having to update every call site and to preserve
compatibility with external consumers such as Lustre. The new
interfaces names are given below. The versions of these functions that
don't take a dnodesize parameter now just call the _dnsize() versions
with a dnodesize of 0, which means use the legacy dnode size.
New DMU interfaces:
dmu_object_alloc_dnsize()
dmu_object_claim_dnsize()
dmu_object_reclaim_dnsize()
New ZAP interfaces:
zap_create_dnsize()
zap_create_norm_dnsize()
zap_create_flags_dnsize()
zap_create_claim_norm_dnsize()
zap_create_link_dnsize()
The constant DN_MAX_BONUSLEN is renamed to DN_OLD_MAX_BONUSLEN. The
spa_maxdnodesize() function should be used to determine the maximum
bonus length for a pool.
These are a few noteworthy changes to key functions:
* The prototype for dnode_hold_impl() now takes a "slots" parameter.
When the DNODE_MUST_BE_FREE flag is set, this parameter is used to
ensure the hole at the specified object offset is large enough to
hold the dnode being created. The slots parameter is also used
to ensure a dnode does not span multiple dnode blocks. In both of
these cases, if a failure occurs, ENOSPC is returned. Keep in mind,
these failure cases are only possible when using DNODE_MUST_BE_FREE.
If the DNODE_MUST_BE_ALLOCATED flag is set, "slots" must be 0.
dnode_hold_impl() will check if the requested dnode is already
consumed as an extra dnode slot by an large dnode, in which case
it returns ENOENT.
* The function dmu_object_alloc() advances to the next dnode block
if dnode_hold_impl() returns an error for a requested object.
This is because the beginning of the next dnode block is the only
location it can safely assume to either be a hole or a valid
starting point for a dnode.
* dnode_next_offset_level() and other functions that iterate
through dnode blocks may no longer use a simple array indexing
scheme. These now use the current dnode's dn_num_slots field to
advance to the next dnode in the block. This is to ensure we
properly skip the current dnode's bonus area and don't interpret it
as a valid dnode.
zdb
---
The zdb command was updated to display a dnode's size under the
"dnsize" column when the object is dumped.
For ZIL create log records, zdb will now display the slot count for
the object.
ztest
-----
Ztest chooses a random dnodesize for every newly created object. The
random distribution is more heavily weighted toward small dnodes to
better simulate real-world datasets.
Unused bonus buffer space is filled with non-zero values computed from
the object number, dataset id, offset, and generation number. This
helps ensure that the dnode traversal code properly skips the interior
regions of large dnodes, and that these interior regions are not
overwritten by data belonging to other dnodes. A new test visits each
object in a dataset. It verifies that the actual dnode size matches what
was stored in the ztest block tag when it was created. It also verifies
that the unused bonus buffer space is filled with the expected data
patterns.
ZFS Test Suite
--------------
Added six new large dnode-specific tests, and integrated the dnodesize
property into existing tests for zfs allow and send/recv.
Send/Receive
------------
ZFS send streams for datasets containing large dnodes cannot be received
on pools that don't support the large_dnode feature. A send stream with
large dnodes sets a DMU_BACKUP_FEATURE_LARGE_DNODE flag which will be
unrecognized by an incompatible receiving pool so that the zfs receive
will fail gracefully.
While not implemented here, it may be possible to generate a
backward-compatible send stream from a dataset containing large
dnodes. The implementation may be tricky, however, because the send
object record for a large dnode would need to be resized to a 512
byte dnode, possibly kicking in a spill block in the process. This
means we would need to construct a new SA layout and possibly
register it in the SA layout object. The SA layout is normally just
sent as an ordinary object record. But if we are constructing new
layouts while generating the send stream we'd have to build the SA
layout object dynamically and send it at the end of the stream.
For sending and receiving between pools that do support large dnodes,
the drr_object send record type is extended with a new field to store
the dnode slot count. This field was repurposed from unused padding
in the structure.
ZIL Replay
----------
The dnode slot count is stored in the uppermost 8 bits of the lr_foid
field. The bits were unused as the object id is currently capped at
48 bits.
Resizing Dnodes
---------------
It should be possible to resize a dnode when it is dirtied if the
current dnodesize dataset property differs from the dnode's size, but
this functionality is not currently implemented. Clearly a dnode can
only grow if there are sufficient contiguous unused slots in the
dnode block, but it should always be possible to shrink a dnode.
Growing dnodes may be useful to reduce fragmentation in a pool with
many spill blocks in use. Shrinking dnodes may be useful to allow
sending a dataset to a pool that doesn't support the large_dnode
feature.
Feature Reference Counting
--------------------------
The reference count for the large_dnode pool feature tracks the
number of datasets that have ever contained a dnode of size larger
than 512 bytes. The first time a large dnode is created in a dataset
the dataset is converted to an extensible dataset. This is a one-way
operation and the only way to decrement the feature count is to
destroy the dataset, even if the dataset no longer contains any large
dnodes. The complexity of reference counting on a per-dnode basis was
too high, so we chose to track it on a per-dataset basis similarly to
the large_block feature.
Signed-off-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#3542
6736 ZFS per-vdev ZAPs
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: John Kennedy <john.kennedy@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Don Brady <don.brady@intel.com>
Reviewed by: Dan McDonald <danmcd@omniti.com>
References:
https://www.illumos.org/issues/6736https://github.com/openzfs/openzfs/commit/215198a
Ported-by: Don Brady <don.brady@intel.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#4515
4950 files sometimes can't be removed from a full filesystem
Reviewed by: Adam Leventhal <adam.leventhal@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Sebastien Roy <sebastien.roy@delphix.com>
Reviewed by: Boris Protopopov <bprotopopov@hotmail.com>
Approved by: Dan McDonald <danmcd@omniti.com>
References:
https://www.illumos.org/issues/4950https://github.com/illumos/illumos-gate/commit/4bb7380
Porting notes:
- ZoL currently does not log discards to zvols, so the portion of
this patch that modifies the discard logging to mark it as
freeing space has been discarded.
2. may_delete_now had been removed from zfs_remove() in ZoL.
It has been reintroduced.
3. We do not try to emulate vnodes, so the following lines are
not valid on Linux:
mutex_enter(&vp->v_lock);
may_delete_now = vp->v_count == 1 && !vn_has_cached_data(vp);
mutex_exit(&vp->v_lock);
This has been replaced with:
mutex_enter(&zp->z_lock);
may_delete_now = atomic_read(&ip->i_count) == 1 && !(zp->z_is_mapped);
mutex_exit(&zp->z_lock);
Ported-by: Richard Yao <richard.yao@clusterhq.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Since uio now supports bvec, we can convert bio into uio and reuse
dmu_{read,write}_uio. This way, we can remove some duplicate code.
Signed-off-by: Chunwei Chen <david.chen@osnexus.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#4078
Internally, zvols are files exposed through the block device API. This
is intended to reduce overhead when things require block devices.
However, the ZoL zvol code emulates a traditional block device in that
it has a top half and a bottom half. This is an unnecessary source of
overhead that does not exist on any other OpenZFS platform does this.
This patch removes it. Early users of this patch reported double digit
performance gains in IOPS on zvols in the range of 50% to 80%.
Comments in the code suggest that the current implementation was done to
obtain IO merging from Linux's IO elevator. However, the DMU already
does write merging while arc_read() should implicitly merge read IOs
because only 1 thread is permitted to fetch the buffer into ARC. In
addition, commercial ZFSOnLinux distributions report that regular files
are more performant than zvols under the current implementation, and the
main consumers of zvols are VMs and iSCSI targets, which have their own
elevators to merge IOs.
Some minor refactoring allows us to register zfs_request() as our
->make_request() handler in place of the generic_make_request()
function. This eliminates the layer of code that broke IO requests on
zvols into a top half and a bottom half. This has several benefits:
1. No per zvol spinlocks.
2. No redundant IO elevator processing.
3. Interrupts are disabled only when actually necessary.
4. No redispatching of IOs when all taskq threads are busy.
5. Linux's page out routines will properly block.
6. Many autotools checks become obsolete.
An unfortunate consequence of eliminating the layer that
generic_make_request() is that we no longer calls the instrumentation
hooks for block IO accounting. Those hooks are GPL-exported, so we
cannot call them ourselves and consequently, we lose the ability to do
IO monitoring via iostat. Since zvols are internally files mapped as
block devices, this should be okay. Anyone who is willing to accept the
performance penalty for the block IO layer's accounting could use the
loop device in between the zvol and its consumer. Alternatively, perf
and ftrace likely could be used. Also, tools like latencytop will still
work. Tools such as latencytop sometimes provide a better view of
performance bottlenecks than the traditional block IO accounting tools
do.
Lastly, if direct reclaim occurs during spacemap loading and swap is on
a zvol, this code will deadlock. That deadlock could already occur with
sync=always on zvols. Given that swap on zvols is not yet production
ready, this is not a blocker.
Signed-off-by: Richard Yao <ryao@gentoo.org>
5175 implement dmu_read_uio_dbuf() to improve cached read performance
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Alex Reece <alex.reece@delphix.com>
Reviewed by: George Wilson <george@delphix.com>
Reviewed by: Richard Elling <richard.elling@gmail.com>
Approved by: Robert Mustacchi <rm@joyent.com>
References:
https://www.illumos.org/issues/5175https://github.com/illumos/illumos-gate/commit/f8554bb
Porting notes:
This patch doesn't include the changes for the COMSTAR (Common
Multiprotocol SCSI Target) - since it's not available for ZoL.
http://thegreyblog.blogspot.co.at/2010/02/setting-up-solaris-comstar-and.html
Ported by: kernelOfTruth <kerneloftruth@gmail.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#3392
5269 zpool import slow
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: George Wilson <george@delphix.com>
Reviewed by: Dan McDonald <danmcd@omniti.com>
Approved by: Dan McDonald <danmcd@omniti.com>
References:
https://www.illumos.org/issues/5269https://github.com/illumos/illumos-gate/commit/12380e1e
Ported-by: DHE <git@dehacked.net>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#3396
The dbu_evict_taskq added in 0c66c32d is only invoked via
taskq_dispatch_ent(). In these cases, ZoL's implementation of taskqs
requires the entries to be initialized first with taskq_init_ent() in
order that, among other things, the embedded spinlock is initialized
properly.
Signed-off-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#3419
5027 zfs large block support
Reviewed by: Alek Pinchuk <pinchuk.alek@gmail.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Josef 'Jeff' Sipek <josef.sipek@nexenta.com>
Reviewed by: Richard Elling <richard.elling@richardelling.com>
Reviewed by: Saso Kiselkov <skiselkov.ml@gmail.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Dan McDonald <danmcd@omniti.com>
References:
https://www.illumos.org/issues/5027https://github.com/illumos/illumos-gate/commit/b515258
Porting Notes:
* Included in this patch is a tiny ISP2() cleanup in zio_init() from
Illumos 5255.
* Unlike the upstream Illumos commit this patch does not impose an
arbitrary 128K block size limit on volumes. Volumes, like filesystems,
are limited by the zfs_max_recordsize=1M module option.
* By default the maximum record size is limited to 1M by the module
option zfs_max_recordsize. This value may be safely increased up to
16M which is the largest block size supported by the on-disk format.
At the moment, 1M blocks clearly offer a significant performance
improvement but the benefits of going beyond this for the majority
of workloads are less clear.
* The illumos version of this patch increased DMU_MAX_ACCESS to 32M.
This was determined not to be large enough when using 16M blocks
because the zfs_make_xattrdir() function will fail (EFBIG) when
assigning a TX. This was immediately observed under Linux because
all newly created files must have a security xattr created and
that was failing. Therefore, we've set DMU_MAX_ACCESS to 64M.
* On 32-bit platforms a hard limit of 1M is set for blocks due
to the limited virtual address space. We should be able to relax
this one the ABD patches are merged.
Ported-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#354
5531 NULL pointer dereference in dsl_prop_get_ds()
Author: Justin T. Gibbs <justing@spectralogic.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Dan McDonald <danmcd@omniti.com>
Reviewed by: George Wilson <george@delphix.com>
Reviewed by: Bayard Bell <buffer.g.overflow@gmail.com>
Approved by: Robert Mustacchi <rm@joyent.com>
References:
https://www.illumos.org/issues/5531https://github.com/illumos/illumos-gate/commit/e57a022
Ported-by: Chris Dunlop <chris@onthe.net.au>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
5056 ZFS deadlock on db_mtx and dn_holds
Author: Justin Gibbs <justing@spectralogic.com>
Reviewed by: Will Andrews <willa@spectralogic.com>
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Approved by: Dan McDonald <danmcd@omniti.com>
References:
https://www.illumos.org/issues/5056https://github.com/illumos/illumos-gate/commit/bc9014e
Porting Notes:
sa_handle_get_from_db():
- the original patch includes an otherwise unmentioned fix for a
possible usage of an uninitialised variable
dmu_objset_open_impl():
- Under Illumos list_link_init() is the same as filling a list_node_t
with NULLs, so they don't notice if they miss doing list_link_init()
on a zero'd containing structure (e.g. allocated with kmem_zalloc as
here). Under Linux, not so much: an uninitialised list_node_t goes
"Boom!" some time later when it's used or destroyed.
dmu_objset_evict_dbufs():
- reduce stack usage using kmem_alloc()
Ported-by: Chris Dunlop <chris@onthe.net.au>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Restore_object should not use two transactions to restore an object:
* one transaction is used for dmu_object_claim
* another transaction is used to set compression, checksum and most
importantly bonus data
* furthermore dmu_object_reclaim internally uses multiple transactions
* dmu_free_long_range frees chunks in separate transactions
* dnode_reallocate is executed in a distinct transaction
The fact the dnode_allocate/dnode_reallocate are executed in one
transaction and bonus (re-)population is executed in a different
transaction may lead to violation of ZFS consistency assertions if the
transactions are assigned to different transaction groups. Also, if
the first transaction group is successfully written to a permanent
storage, but the second transaction is lost, then an invalid dnode may
be created on the stable storage.
3693 restore_object uses at least two transactions to restore an object
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Andriy Gapon <andriy.gapon@hybridcluster.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Original authors: Matthew Ahrens and Andriy Gapon
References:
https://www.illumos.org/issues/3693https://github.com/illumos/illumos-gate/commit/e77d42e
Ported by: Turbo Fredriksson <turbo@bayour.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#2689
4914 zfs on-disk bookmark structure should be named *_phys_t
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Richard Lowe <richlowe@richlowe.net>
Reviewed by: Saso Kiselkov <skiselkov.ml@gmail.com>
Approved by: Robert Mustacchi <rm@joyent.com>
References:
https://www.illumos.org/issues/4914https://github.com/illumos/illumos-gate/commit/7802d7b
Porting notes:
There were a number of zfsonlinux-specific uses of zbookmark_t which
needed to be updated. This should reduce the likelihood of further
problems like issue #2094 from occurring.
Ported by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#2558
4390 i/o errors when deleting filesystem/zvol can lead to space map corruption
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Dan McDonald <danmcd@omniti.com>
Reviewed by: Saso Kiselkov <saso.kiselkov@nexenta.com>
Approved by: Dan McDonald <danmcd@omniti.com>
References:
https://www.illumos.org/issues/4390https://github.com/illumos/illumos-gate/commit/7fd05ac
Porting notes:
Previous stack-reduction efforts in traverse_visitb() caused a fair
number of un-mergable pieces of code. This patch should reduce its
stack footprint a bit more.
The new local bptree_entry_phys_t in bptree_add() is dynamically-allocated
using kmem_zalloc() for the purpose of stack reduction.
The new global zfs_free_leak_on_eio has been defined as an integer
rather than a boolean_t as was the case with the related zfs_recover
global. Also, zfs_free_leak_on_eio's definition has been inserted into
zfs_debug.c for consistency with the existing definition of zfs_recover.
Illumos placed it in spa_misc.c.
Ported by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#2545
4757 ZFS embedded-data block pointers ("zero block compression")
4913 zfs release should not be subject to space checks
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Max Grossman <max.grossman@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Dan McDonald <danmcd@omniti.com>
Approved by: Dan McDonald <danmcd@omniti.com>
References:
https://www.illumos.org/issues/4757https://www.illumos.org/issues/4913https://github.com/illumos/illumos-gate/commit/5d7b4d4
Porting notes:
For compatibility with the fastpath code the zio_done() function
needed to be updated. Because embedded-data block pointers do
not require DVAs to be allocated the associated vdevs will not
be marked and therefore should not be unmarked.
Ported by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#2544
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Dan McDonald <danmcd@omniti.com>
Approved by: Richard Lowe <richlowe@richlowe.net>
Description from Matt Ahrens's bug report at Delphix:
Add a new zfs property, "redundant_metadata" which can have values
"all" or "most". The default will be "all", which is the current
behavior. Setting to "most" will cause us to only store 1 copy of
level-1 indirect blocks of user data files.
Additional notes:
The new man page section for this property states
"The exact behavior of which metadata blocks
are stored redundantly may change in future releases."
and:
"When set to most, ZFS stores an extra copy of most types of
metadata. This can improve performance of random writes,
because less metadata must be written."
The current implementation is as described above in Matt's blog.
It is controlled by a new global integer
"zfs_redundant_metadata_most_ditto_level", currently initialized
to 2. When "redundant_metadata" is set to "most", only indirect
blocks of the specified level and higher will have additional ditto
blocks created.
Ported by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#2542
4370 avoid transmitting holes during zfs send
4371 DMU code clean up
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Josef 'Jeff' Sipek <jeffpc@josefsipek.net>
Approved by: Garrett D'Amore <garrett@damore.org>a
References:
https://www.illumos.org/issues/4370https://www.illumos.org/issues/4371https://github.com/illumos/illumos-gate/commit/43466aa
Ported by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#2529
4045 zfs write throttle & i/o scheduler performance work
1. The ZFS i/o scheduler (vdev_queue.c) now divides i/os into 5 classes: sync
read, sync write, async read, async write, and scrub/resilver. The scheduler
issues a number of concurrent i/os from each class to the device. Once a class
has been selected, an i/o is selected from this class using either an elevator
algorithem (async, scrub classes) or FIFO (sync classes). The number of
concurrent async write i/os is tuned dynamically based on i/o load, to achieve
good sync i/o latency when there is not a high load of writes, and good write
throughput when there is. See the block comment in vdev_queue.c (reproduced
below) for more details.
2. The write throttle (dsl_pool_tempreserve_space() and
txg_constrain_throughput()) is rewritten to produce much more consistent delays
when under constant load. The new write throttle is based on the amount of
dirty data, rather than guesses about future performance of the system. When
there is a lot of dirty data, each transaction (e.g. write() syscall) will be
delayed by the same small amount. This eliminates the "brick wall of wait"
that the old write throttle could hit, causing all transactions to wait several
seconds until the next txg opens. One of the keys to the new write throttle is
decrementing the amount of dirty data as i/o completes, rather than at the end
of spa_sync(). Note that the write throttle is only applied once the i/o
scheduler is issuing the maximum number of outstanding async writes. See the
block comments in dsl_pool.c and above dmu_tx_delay() (reproduced below) for
more details.
This diff has several other effects, including:
* the commonly-tuned global variable zfs_vdev_max_pending has been removed;
use per-class zfs_vdev_*_max_active values or zfs_vdev_max_active instead.
* the size of each txg (meaning the amount of dirty data written, and thus the
time it takes to write out) is now controlled differently. There is no longer
an explicit time goal; the primary determinant is amount of dirty data.
Systems that are under light or medium load will now often see that a txg is
always syncing, but the impact to performance (e.g. read latency) is minimal.
Tune zfs_dirty_data_max and zfs_dirty_data_sync to control this.
* zio_taskq_batch_pct = 75 -- Only use 75% of all CPUs for compression,
checksum, etc. This improves latency by not allowing these CPU-intensive tasks
to consume all CPU (on machines with at least 4 CPU's; the percentage is
rounded up).
--matt
APPENDIX: problems with the current i/o scheduler
The current ZFS i/o scheduler (vdev_queue.c) is deadline based. The problem
with this is that if there are always i/os pending, then certain classes of
i/os can see very long delays.
For example, if there are always synchronous reads outstanding, then no async
writes will be serviced until they become "past due". One symptom of this
situation is that each pass of the txg sync takes at least several seconds
(typically 3 seconds).
If many i/os become "past due" (their deadline is in the past), then we must
service all of these overdue i/os before any new i/os. This happens when we
enqueue a batch of async writes for the txg sync, with deadlines 2.5 seconds in
the future. If we can't complete all the i/os in 2.5 seconds (e.g. because
there were always reads pending), then these i/os will become past due. Now we
must service all the "async" writes (which could be hundreds of megabytes)
before we service any reads, introducing considerable latency to synchronous
i/os (reads or ZIL writes).
Notes on porting to ZFS on Linux:
- zio_t gained new members io_physdone and io_phys_children. Because
object caches in the Linux port call the constructor only once at
allocation time, objects may contain residual data when retrieved
from the cache. Therefore zio_create() was updated to zero out the two
new fields.
- vdev_mirror_pending() relied on the depth of the per-vdev pending queue
(vq->vq_pending_tree) to select the least-busy leaf vdev to read from.
This tree has been replaced by vq->vq_active_tree which is now used
for the same purpose.
- vdev_queue_init() used the value of zfs_vdev_max_pending to determine
the number of vdev I/O buffers to pre-allocate. That global no longer
exists, so we instead use the sum of the *_max_active values for each of
the five I/O classes described above.
- The Illumos implementation of dmu_tx_delay() delays a transaction by
sleeping in condition variable embedded in the thread
(curthread->t_delay_cv). We do not have an equivalent CV to use in
Linux, so this change replaced the delay logic with a wrapper called
zfs_sleep_until(). This wrapper could be adopted upstream and in other
downstream ports to abstract away operating system-specific delay logic.
- These tunables are added as module parameters, and descriptions added
to the zfs-module-parameters.5 man page.
spa_asize_inflation
zfs_deadman_synctime_ms
zfs_vdev_max_active
zfs_vdev_async_write_active_min_dirty_percent
zfs_vdev_async_write_active_max_dirty_percent
zfs_vdev_async_read_max_active
zfs_vdev_async_read_min_active
zfs_vdev_async_write_max_active
zfs_vdev_async_write_min_active
zfs_vdev_scrub_max_active
zfs_vdev_scrub_min_active
zfs_vdev_sync_read_max_active
zfs_vdev_sync_read_min_active
zfs_vdev_sync_write_max_active
zfs_vdev_sync_write_min_active
zfs_dirty_data_max_percent
zfs_delay_min_dirty_percent
zfs_dirty_data_max_max_percent
zfs_dirty_data_max
zfs_dirty_data_max_max
zfs_dirty_data_sync
zfs_delay_scale
The latter four have type unsigned long, whereas they are uint64_t in
Illumos. This accommodates Linux's module_param() supported types, but
means they may overflow on 32-bit architectures.
The values zfs_dirty_data_max and zfs_dirty_data_max_max are the most
likely to overflow on 32-bit systems, since they express physical RAM
sizes in bytes. In fact, Illumos initializes zfs_dirty_data_max_max to
2^32 which does overflow. To resolve that, this port instead initializes
it in arc_init() to 25% of physical RAM, and adds the tunable
zfs_dirty_data_max_max_percent to override that percentage. While this
solution doesn't completely avoid the overflow issue, it should be a
reasonable default for most systems, and the minority of affected
systems can work around the issue by overriding the defaults.
- Fixed reversed logic in comment above zfs_delay_scale declaration.
- Clarified comments in vdev_queue.c regarding when per-queue minimums take
effect.
- Replaced dmu_tx_write_limit in the dmu_tx kstat file
with dmu_tx_dirty_delay and dmu_tx_dirty_over_max. The first counts
how many times a transaction has been delayed because the pool dirty
data has exceeded zfs_delay_min_dirty_percent. The latter counts how
many times the pool dirty data has exceeded zfs_dirty_data_max (which
we expect to never happen).
- The original patch would have regressed the bug fixed in
zfsonlinux/zfs@c418410, which prevented users from setting the
zfs_vdev_aggregation_limit tuning larger than SPA_MAXBLOCKSIZE.
A similar fix is added to vdev_queue_aggregate().
- In vdev_queue_io_to_issue(), dynamically allocate 'zio_t search' on the
heap instead of the stack. In Linux we can't afford such large
structures on the stack.
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Ned Bass <bass6@llnl.gov>
Reviewed by: Brendan Gregg <brendan.gregg@joyent.com>
Approved by: Robert Mustacchi <rm@joyent.com>
References:
http://www.illumos.org/issues/4045illumos/illumos-gate@69962b5647
Ported-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#1913
4047 panic from dbuf_free_range() from dmu_free_object() while
doing zfs receive
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Approved by: Dan McDonald <danmcd@nexenta.com>
References:
https://www.illumos.org/issues/4047illumos/illumos-gate@713d6c2088
Ported-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #1775
Porting notes:
1. The exported symbol dmu_free_object() was renamed to
dmu_free_long_object() in Illumos.
3236 zio nop-write
Reviewed by: Matt Ahrens <matthew.ahrens@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Christopher Siden <chris.siden@delphix.com>
Approved by: Garrett D'Amore <garrett@damore.org>
References:
illumos/illumos-gate@80901aea8ehttps://www.illumos.org/issues/3236
Porting Notes
1. This patch is being merged dispite an increased instance of
https://www.illumos.org/issues/3113 being triggered by ztest.
Ported-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #1489
3741 zfs needs better comments
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Eric Schrock <eric.schrock@delphix.com>
Approved by: Christopher Siden <christopher.siden@delphix.com>
References:
https://www.illumos.org/issues/3741illumos/illumos-gate@3e30c24aee
Ported-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #1775
This resolves merge conflicts when merging Illumos #3588 and Illumos #4047.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #1775
Currently there is no mechanism to inspect which dbufs are being
cached by the system. There are some coarse counters in arcstats
by they only give a rough idea of what's being cached. This patch
aims to improve the current situation by adding a new dbufs kstat.
When read this new kstat will walk all cached dbufs linked in to
the dbuf_hash. For each dbuf it will dump detailed information
about the buffer. It will also dump additional information about
the referenced arc buffer and its related dnode. This provides a
more complete view in to exactly what is being cached.
With this generic infrastructure in place utilities can be written
to post-process the data to understand exactly how the caching is
working. For example, the data could be processed to show a list
of all cached dnodes and how much space they're consuming. Or a
similar list could be generated based on dnode type. Many other
ways to interpret the data exist based on what kinds of questions
you're trying to answer.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Prakash Surya <surya1@llnl.gov>
2882 implement libzfs_core
2883 changing "canmount" property to "on" should not always remount dataset
2900 "zfs snapshot" should be able to create multiple, arbitrary snapshots at once
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Chris Siden <christopher.siden@delphix.com>
Reviewed by: Garrett D'Amore <garrett@damore.org>
Reviewed by: Bill Pijewski <wdp@joyent.com>
Reviewed by: Dan Kruchinin <dan.kruchinin@gmail.com>
Approved by: Eric Schrock <Eric.Schrock@delphix.com>
References:
https://www.illumos.org/issues/2882https://www.illumos.org/issues/2883https://www.illumos.org/issues/2900illumos/illumos-gate@4445fffbbb
Ported-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#1293
Porting notes:
WARNING: This patch changes the user/kernel ABI. That means that
the zfs/zpool utilities built from master are NOT compatible with
the 0.6.2 kernel modules. Ensure you load the matching kernel
modules from master after updating the utilities. Otherwise the
zfs/zpool commands will be unable to interact with your pool and
you will see errors similar to the following:
$ zpool list
failed to read pool configuration: bad address
no pools available
$ zfs list
no datasets available
Add zvol minor device creation to the new zfs_snapshot_nvl function.
Remove the logging of the "release" operation in
dsl_dataset_user_release_sync(). The logging caused a null dereference
because ds->ds_dir is zeroed in dsl_dataset_destroy_sync() and the
logging functions try to get the ds name via the dsl_dataset_name()
function. I've got no idea why this particular code would have worked
in Illumos. This code has subsequently been completely reworked in
Illumos commit 3b2aab1 (3464 zfs synctask code needs restructuring).
Squash some "may be used uninitialized" warning/erorrs.
Fix some printf format warnings for %lld and %llu.
Apply a few spa_writeable() changes that were made to Illumos in
illumos/illumos-gate.git@cd1c8b8 as part of the 3112, 3113, 3114 and
3115 fixes.
Add a missing call to fnvlist_free(nvl) in log_internal() that was added
in Illumos to fix issue 3085 but couldn't be ported to ZoL at the time
(zfsonlinux/zfs@9e11c73) because it depended on future work.
Tom Caputi
Prakash Surya
lidongyang
Richard Yao
Matthew Ahrens
Brian Behlendorf
George Melikov
bzzz77
cao
Jinshan Xiong
Tony Hutter
Dan Kimmel
Igor Kozhukhov
Ned Bass
Joe Stein
Paul Dagnelie
Chunwei Chen
Arne Jansen
Tim Chase
Justin T. Gibbs
Max Grossman
George Wilson
Will Andrews
Saso Kiselkov
Jan Engelhardt