mirror_zfs/include/sys/fs/zfs.h

1160 lines
36 KiB
C
Raw Normal View History

2008-11-20 23:01:55 +03:00
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
2009-08-18 22:43:27 +04:00
2008-11-20 23:01:55 +03:00
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2011, 2014 by Delphix. All rights reserved.
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
* Copyright (c) 2013, Joyent, Inc. All rights reserved.
* Copyright (c) 2017 Datto Inc.
2008-11-20 23:01:55 +03:00
*/
/* Portions Copyright 2010 Robert Milkowski */
2008-11-20 23:01:55 +03:00
#ifndef _SYS_FS_ZFS_H
#define _SYS_FS_ZFS_H
2009-08-18 22:43:27 +04:00
#include <sys/time.h>
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
#include <sys/zio_priority.h>
2009-08-18 22:43:27 +04:00
2008-11-20 23:01:55 +03:00
#ifdef __cplusplus
extern "C" {
#endif
/*
* Types and constants shared between userland and the kernel.
*/
/*
* Each dataset can be one of the following types. These constants can be
* combined into masks that can be passed to various functions.
*/
typedef enum {
ZFS_TYPE_FILESYSTEM = (1 << 0),
ZFS_TYPE_SNAPSHOT = (1 << 1),
ZFS_TYPE_VOLUME = (1 << 2),
ZFS_TYPE_POOL = (1 << 3),
ZFS_TYPE_BOOKMARK = (1 << 4)
2008-11-20 23:01:55 +03:00
} zfs_type_t;
/*
* NB: lzc_dataset_type should be updated whenever a new objset type is added,
* if it represents a real type of a dataset that can be created from userland.
*/
Illumos #2882, #2883, #2900 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/2882 https://www.illumos.org/issues/2883 https://www.illumos.org/issues/2900 illumos/illumos-gate@4445fffbbb1ea25fd0e9ea68b9380dd7a6709025 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.
2013-08-28 15:45:09 +04:00
typedef enum dmu_objset_type {
DMU_OST_NONE,
DMU_OST_META,
DMU_OST_ZFS,
DMU_OST_ZVOL,
DMU_OST_OTHER, /* For testing only! */
DMU_OST_ANY, /* Be careful! */
DMU_OST_NUMTYPES
} dmu_objset_type_t;
2008-11-20 23:01:55 +03:00
#define ZFS_TYPE_DATASET \
(ZFS_TYPE_FILESYSTEM | ZFS_TYPE_VOLUME | ZFS_TYPE_SNAPSHOT)
/*
* All of these include the terminating NUL byte.
*/
2009-07-03 02:44:48 +04:00
#define ZAP_MAXNAMELEN 256
#define ZAP_MAXVALUELEN (1024 * 8)
#define ZAP_OLDMAXVALUELEN 1024
#define ZFS_MAX_DATASET_NAME_LEN 256
2009-07-03 02:44:48 +04:00
2008-11-20 23:01:55 +03:00
/*
* Dataset properties are identified by these constants and must be added to
* the end of this list to ensure that external consumers are not affected
* by the change. If you make any changes to this list, be sure to update
* the property table in module/zcommon/zfs_prop.c.
2008-11-20 23:01:55 +03:00
*/
typedef enum {
ZFS_PROP_BAD = -1,
ZFS_PROP_TYPE = 0,
2008-11-20 23:01:55 +03:00
ZFS_PROP_CREATION,
ZFS_PROP_USED,
ZFS_PROP_AVAILABLE,
ZFS_PROP_REFERENCED,
ZFS_PROP_COMPRESSRATIO,
ZFS_PROP_MOUNTED,
ZFS_PROP_ORIGIN,
ZFS_PROP_QUOTA,
ZFS_PROP_RESERVATION,
ZFS_PROP_VOLSIZE,
ZFS_PROP_VOLBLOCKSIZE,
ZFS_PROP_RECORDSIZE,
ZFS_PROP_MOUNTPOINT,
ZFS_PROP_SHARENFS,
ZFS_PROP_CHECKSUM,
ZFS_PROP_COMPRESSION,
ZFS_PROP_ATIME,
ZFS_PROP_DEVICES,
ZFS_PROP_EXEC,
ZFS_PROP_SETUID,
ZFS_PROP_READONLY,
ZFS_PROP_ZONED,
ZFS_PROP_SNAPDIR,
ZFS_PROP_PRIVATE, /* not exposed to user, temporary */
2008-11-20 23:01:55 +03:00
ZFS_PROP_ACLINHERIT,
ZFS_PROP_CREATETXG,
2008-11-20 23:01:55 +03:00
ZFS_PROP_NAME, /* not exposed to the user */
ZFS_PROP_CANMOUNT,
ZFS_PROP_ISCSIOPTIONS, /* not exposed to the user */
ZFS_PROP_XATTR,
ZFS_PROP_NUMCLONES, /* not exposed to the user */
ZFS_PROP_COPIES,
ZFS_PROP_VERSION,
ZFS_PROP_UTF8ONLY,
ZFS_PROP_NORMALIZE,
ZFS_PROP_CASE,
ZFS_PROP_VSCAN,
ZFS_PROP_NBMAND,
ZFS_PROP_SHARESMB,
ZFS_PROP_REFQUOTA,
ZFS_PROP_REFRESERVATION,
ZFS_PROP_GUID,
ZFS_PROP_PRIMARYCACHE,
ZFS_PROP_SECONDARYCACHE,
ZFS_PROP_USEDSNAP,
ZFS_PROP_USEDDS,
ZFS_PROP_USEDCHILD,
ZFS_PROP_USEDREFRESERV,
2009-07-03 02:44:48 +04:00
ZFS_PROP_USERACCOUNTING, /* not exposed to the user */
ZFS_PROP_STMF_SHAREINFO, /* not exposed to the user */
2009-08-18 22:43:27 +04:00
ZFS_PROP_DEFER_DESTROY,
ZFS_PROP_USERREFS,
ZFS_PROP_LOGBIAS,
ZFS_PROP_UNIQUE, /* not exposed to the user */
ZFS_PROP_OBJSETID, /* not exposed to the user */
ZFS_PROP_DEDUP,
ZFS_PROP_MLSLABEL,
ZFS_PROP_SYNC,
Implement large_dnode pool feature 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
2016-03-17 04:25:34 +03:00
ZFS_PROP_DNODESIZE,
ZFS_PROP_REFRATIO,
ZFS_PROP_WRITTEN,
ZFS_PROP_CLONES,
ZFS_PROP_LOGICALUSED,
ZFS_PROP_LOGICALREFERENCED,
ZFS_PROP_INCONSISTENT, /* not exposed to the user */
ZFS_PROP_VOLMODE,
ZFS_PROP_FILESYSTEM_LIMIT,
ZFS_PROP_SNAPSHOT_LIMIT,
ZFS_PROP_FILESYSTEM_COUNT,
ZFS_PROP_SNAPSHOT_COUNT,
Add snapdev=[hidden|visible] dataset property The new snapdev dataset property may be set to control the visibility of zvol snapshot devices. By default this value is set to 'hidden' which will prevent zvol snapshots from appearing under /dev/zvol/ and /dev/<dataset>/. When set to 'visible' all zvol snapshots for the dataset will be visible. This functionality was largely added because when automatic snapshoting is enabled large numbers of read-only zvol snapshots will be created. When creating these devices the kernel will attempt to read their partition tables, and blkid will attempt to identify any filesystems on those partitions. This leads to a variety of issues: 1) The zvol partition tables will be read in the context of the `modprobe zfs` for automatically imported pools. This is undesirable and should be done asynchronously, but for now reducing the number of visible devices helps. 2) Udev expects to be able to complete its work for a new block devices fairly quickly. When many zvol devices are added at the same time this is no longer be true. It can lead to udev timeouts and missing /dev/zvol links. 3) Simply having lots of devices in /dev/ can be aukward from a management standpoint. Hidding the devices your unlikely to ever use helps with this. Any snapshot device which is needed can be made visible by changing the snapdev property. NOTE: This patch changes the default behavior for zvols which was effectively 'snapdev=visible'. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #1235 Closes #945 Issue #956 Issue #756
2013-02-14 03:11:59 +04:00
ZFS_PROP_SNAPDEV,
ZFS_PROP_ACLTYPE,
ZFS_PROP_SELINUX_CONTEXT,
ZFS_PROP_SELINUX_FSCONTEXT,
ZFS_PROP_SELINUX_DEFCONTEXT,
ZFS_PROP_SELINUX_ROOTCONTEXT,
ZFS_PROP_RELATIME,
ZFS_PROP_REDUNDANT_METADATA,
ZFS_PROP_OVERLAY,
ZFS_PROP_PREV_SNAP,
OpenZFS 2605, 6980, 6902 2605 want to resume interrupted zfs send Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed by: Paul Dagnelie <pcd@delphix.com> Reviewed by: Richard Elling <Richard.Elling@RichardElling.com> Reviewed by: Xin Li <delphij@freebsd.org> Reviewed by: Arne Jansen <sensille@gmx.net> Approved by: Dan McDonald <danmcd@omniti.com> Ported-by: kernelOfTruth <kerneloftruth@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> OpenZFS-issue: https://www.illumos.org/issues/2605 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/9c3fd12 6980 6902 causes zfs send to break due to 32-bit/64-bit struct mismatch Reviewed by: Paul Dagnelie <pcd@delphix.com> Reviewed by: George Wilson <george.wilson@delphix.com> Approved by: Robert Mustacchi <rm@joyent.com> Ported by: Brian Behlendorf <behlendorf1@llnl.gov> OpenZFS-issue: https://www.illumos.org/issues/6980 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/ea4a67f Porting notes: - All rsend and snapshop tests enabled and updated for Linux. - Fix misuse of input argument in traverse_visitbp(). - Fix ISO C90 warnings and errors. - Fix gcc 'missing braces around initializer' in 'struct send_thread_arg to_arg =' warning. - Replace 4 argument fletcher_4_native() with 3 argument version, this change was made in OpenZFS 4185 which has not been ported. - Part of the sections for 'zfs receive' and 'zfs send' was rewritten and reordered to approximate upstream. - Fix mktree xattr creation, 'user.' prefix required. - Minor fixes to newly enabled test cases - Long holds for volumes allowed during receive for minor registration.
2016-01-07 00:22:48 +03:00
ZFS_PROP_RECEIVE_RESUME_TOKEN,
2008-11-20 23:01:55 +03:00
ZFS_NUM_PROPS
} zfs_prop_t;
2009-07-03 02:44:48 +04:00
typedef enum {
ZFS_PROP_USERUSED,
ZFS_PROP_USERQUOTA,
ZFS_PROP_GROUPUSED,
ZFS_PROP_GROUPQUOTA,
ZFS_PROP_USEROBJUSED,
ZFS_PROP_USEROBJQUOTA,
ZFS_PROP_GROUPOBJUSED,
ZFS_PROP_GROUPOBJQUOTA,
2009-07-03 02:44:48 +04:00
ZFS_NUM_USERQUOTA_PROPS
} zfs_userquota_prop_t;
extern const char *zfs_userquota_prop_prefixes[ZFS_NUM_USERQUOTA_PROPS];
2008-11-20 23:01:55 +03:00
/*
* Pool properties are identified by these constants and must be added to the
* end of this list to ensure that external consumers are not affected
2008-11-20 23:01:55 +03:00
* by the change. If you make any changes to this list, be sure to update
* the property table in module/zcommon/zpool_prop.c.
2008-11-20 23:01:55 +03:00
*/
typedef enum {
ZPOOL_PROP_NAME,
ZPOOL_PROP_SIZE,
ZPOOL_PROP_CAPACITY,
ZPOOL_PROP_ALTROOT,
ZPOOL_PROP_HEALTH,
ZPOOL_PROP_GUID,
ZPOOL_PROP_VERSION,
ZPOOL_PROP_BOOTFS,
ZPOOL_PROP_DELEGATION,
ZPOOL_PROP_AUTOREPLACE,
ZPOOL_PROP_CACHEFILE,
ZPOOL_PROP_FAILUREMODE,
ZPOOL_PROP_LISTSNAPS,
2009-07-03 02:44:48 +04:00
ZPOOL_PROP_AUTOEXPAND,
ZPOOL_PROP_DEDUPDITTO,
ZPOOL_PROP_DEDUPRATIO,
ZPOOL_PROP_FREE,
ZPOOL_PROP_ALLOCATED,
ZPOOL_PROP_READONLY,
ZPOOL_PROP_ASHIFT,
ZPOOL_PROP_COMMENT,
ZPOOL_PROP_EXPANDSZ,
ZPOOL_PROP_FREEING,
Illumos 4976-4984 - metaslab improvements 4976 zfs should only avoid writing to a failing non-redundant top-level vdev 4978 ztest fails in get_metaslab_refcount() 4979 extend free space histogram to device and pool 4980 metaslabs should have a fragmentation metric 4981 remove fragmented ops vector from block allocator 4982 space_map object should proactively upgrade when feature is enabled 4983 need to collect metaslab information via mdb 4984 device selection should use fragmentation metric Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Adam Leventhal <adam.leventhal@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Approved by: Garrett D'Amore <garrett@damore.org> References: https://www.illumos.org/issues/4976 https://www.illumos.org/issues/4978 https://www.illumos.org/issues/4979 https://www.illumos.org/issues/4980 https://www.illumos.org/issues/4981 https://www.illumos.org/issues/4982 https://www.illumos.org/issues/4983 https://www.illumos.org/issues/4984 https://github.com/illumos/illumos-gate/commit/2e4c998 Notes: The "zdb -M" option has been re-tasked to display the new metaslab fragmentation metric and the new "zdb -I" option is used to control the maximum number of in-flight I/Os. The new fragmentation metric is derived from the space map histogram which has been rolled up to the vdev and pool level and is presented to the user via "zpool list". Add a number of module parameters related to the new metaslab weighting logic. Ported by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #2595
2014-07-20 00:19:24 +04:00
ZPOOL_PROP_FRAGMENTATION,
ZPOOL_PROP_LEAKED,
Illumos 5027 - zfs large block support 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/5027 https://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
2014-11-03 23:15:08 +03:00
ZPOOL_PROP_MAXBLOCKSIZE,
ZPOOL_PROP_TNAME,
Implement large_dnode pool feature 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
2016-03-17 04:25:34 +03:00
ZPOOL_PROP_MAXDNODESIZE,
2008-11-20 23:01:55 +03:00
ZPOOL_NUM_PROPS
} zpool_prop_t;
/* Small enough to not hog a whole line of printout in zpool(1M). */
#define ZPROP_MAX_COMMENT 32
2008-11-20 23:01:55 +03:00
#define ZPROP_CONT -2
#define ZPROP_INVAL -1
#define ZPROP_VALUE "value"
#define ZPROP_SOURCE "source"
typedef enum {
ZPROP_SRC_NONE = 0x1,
ZPROP_SRC_DEFAULT = 0x2,
ZPROP_SRC_TEMPORARY = 0x4,
ZPROP_SRC_LOCAL = 0x8,
ZPROP_SRC_INHERITED = 0x10,
ZPROP_SRC_RECEIVED = 0x20
2008-11-20 23:01:55 +03:00
} zprop_source_t;
#define ZPROP_SRC_ALL 0x3f
#define ZPROP_SOURCE_VAL_RECVD "$recvd"
#define ZPROP_N_MORE_ERRORS "N_MORE_ERRORS"
/*
* Dataset flag implemented as a special entry in the props zap object
* indicating that the dataset has received properties on or after
* SPA_VERSION_RECVD_PROPS. The first such receive blows away local properties
* just as it did in earlier versions, and thereafter, local properties are
* preserved.
*/
#define ZPROP_HAS_RECVD "$hasrecvd"
typedef enum {
ZPROP_ERR_NOCLEAR = 0x1, /* failure to clear existing props */
ZPROP_ERR_NORESTORE = 0x2 /* failure to restore props on error */
} zprop_errflags_t;
2008-11-20 23:01:55 +03:00
typedef int (*zprop_func)(int, void *);
/*
* Properties to be set on the root file system of a new pool
* are stuffed into their own nvlist, which is then included in
* the properties nvlist with the pool properties.
*/
#define ZPOOL_ROOTFS_PROPS "root-props-nvl"
2008-11-20 23:01:55 +03:00
/*
* Dataset property functions shared between libzfs and kernel.
*/
const char *zfs_prop_default_string(zfs_prop_t);
uint64_t zfs_prop_default_numeric(zfs_prop_t);
boolean_t zfs_prop_readonly(zfs_prop_t);
boolean_t zfs_prop_inheritable(zfs_prop_t);
boolean_t zfs_prop_setonce(zfs_prop_t);
const char *zfs_prop_to_name(zfs_prop_t);
zfs_prop_t zfs_name_to_prop(const char *);
boolean_t zfs_prop_user(const char *);
boolean_t zfs_prop_userquota(const char *);
boolean_t zfs_prop_written(const char *);
2008-11-20 23:01:55 +03:00
int zfs_prop_index_to_string(zfs_prop_t, uint64_t, const char **);
int zfs_prop_string_to_index(zfs_prop_t, const char *, uint64_t *);
uint64_t zfs_prop_random_value(zfs_prop_t, uint64_t seed);
boolean_t zfs_prop_valid_for_type(int, zfs_type_t, boolean_t);
2008-11-20 23:01:55 +03:00
/*
* Pool property functions shared between libzfs and kernel.
*/
zpool_prop_t zpool_name_to_prop(const char *);
const char *zpool_prop_to_name(zpool_prop_t);
const char *zpool_prop_default_string(zpool_prop_t);
uint64_t zpool_prop_default_numeric(zpool_prop_t);
boolean_t zpool_prop_readonly(zpool_prop_t);
boolean_t zpool_prop_feature(const char *);
boolean_t zpool_prop_unsupported(const char *);
2008-11-20 23:01:55 +03:00
int zpool_prop_index_to_string(zpool_prop_t, uint64_t, const char **);
int zpool_prop_string_to_index(zpool_prop_t, const char *, uint64_t *);
uint64_t zpool_prop_random_value(zpool_prop_t, uint64_t seed);
2008-11-20 23:01:55 +03:00
/*
* Definitions for the Delegation.
*/
typedef enum {
ZFS_DELEG_WHO_UNKNOWN = 0,
ZFS_DELEG_USER = 'u',
ZFS_DELEG_USER_SETS = 'U',
ZFS_DELEG_GROUP = 'g',
ZFS_DELEG_GROUP_SETS = 'G',
ZFS_DELEG_EVERYONE = 'e',
ZFS_DELEG_EVERYONE_SETS = 'E',
ZFS_DELEG_CREATE = 'c',
ZFS_DELEG_CREATE_SETS = 'C',
ZFS_DELEG_NAMED_SET = 's',
ZFS_DELEG_NAMED_SET_SETS = 'S'
} zfs_deleg_who_type_t;
typedef enum {
ZFS_DELEG_NONE = 0,
ZFS_DELEG_PERM_LOCAL = 1,
ZFS_DELEG_PERM_DESCENDENT = 2,
ZFS_DELEG_PERM_LOCALDESCENDENT = 3,
ZFS_DELEG_PERM_CREATE = 4
} zfs_deleg_inherit_t;
#define ZFS_DELEG_PERM_UID "uid"
#define ZFS_DELEG_PERM_GID "gid"
#define ZFS_DELEG_PERM_GROUPS "groups"
#define ZFS_MLSLABEL_DEFAULT "none"
2009-07-03 02:44:48 +04:00
#define ZFS_SMB_ACL_SRC "src"
#define ZFS_SMB_ACL_TARGET "target"
2008-11-20 23:01:55 +03:00
typedef enum {
ZFS_CANMOUNT_OFF = 0,
ZFS_CANMOUNT_ON = 1,
ZFS_CANMOUNT_NOAUTO = 2
} zfs_canmount_type_t;
typedef enum {
ZFS_LOGBIAS_LATENCY = 0,
ZFS_LOGBIAS_THROUGHPUT = 1
} zfs_logbias_op_t;
2008-11-20 23:01:55 +03:00
typedef enum zfs_share_op {
ZFS_SHARE_NFS = 0,
ZFS_UNSHARE_NFS = 1,
ZFS_SHARE_SMB = 2,
ZFS_UNSHARE_SMB = 3
} zfs_share_op_t;
2009-07-03 02:44:48 +04:00
typedef enum zfs_smb_acl_op {
ZFS_SMB_ACL_ADD,
ZFS_SMB_ACL_REMOVE,
ZFS_SMB_ACL_RENAME,
ZFS_SMB_ACL_PURGE
} zfs_smb_acl_op_t;
typedef enum zfs_cache_type {
ZFS_CACHE_NONE = 0,
ZFS_CACHE_METADATA = 1,
ZFS_CACHE_ALL = 2
} zfs_cache_type_t;
typedef enum {
ZFS_SYNC_STANDARD = 0,
ZFS_SYNC_ALWAYS = 1,
ZFS_SYNC_DISABLED = 2
} zfs_sync_type_t;
Implement SA based xattrs The current ZFS implementation stores xattrs on disk using a hidden directory. In this directory a file name represents the xattr name and the file contexts are the xattr binary data. This approach is very flexible and allows for arbitrarily large xattrs. However, it also suffers from a significant performance penalty. Accessing a single xattr can requires up to three disk seeks. 1) Lookup the dnode object. 2) Lookup the dnodes's xattr directory object. 3) Lookup the xattr object in the directory. To avoid this performance penalty Linux filesystems such as ext3 and xfs try to store the xattr as part of the inode on disk. When the xattr is to large to store in the inode then a single external block is allocated for them. In practice most xattrs are small and this approach works well. The addition of System Attributes (SA) to zfs provides us a clean way to make this optimization. When the dataset property 'xattr=sa' is set then xattrs will be preferentially stored as System Attributes. This allows tiny xattrs (~100 bytes) to be stored with the dnode and up to 64k of xattrs to be stored in the spill block. If additional xattr space is required, which is unlikely under Linux, they will be stored using the traditional directory approach. This optimization results in roughly a 3x performance improvement when accessing xattrs which brings zfs roughly to parity with ext4 and xfs (see table below). When multiple xattrs are stored per-file the performance improvements are even greater because all of the xattrs stored in the spill block will be cached. However, by default SA based xattrs are disabled in the Linux port to maximize compatibility with other implementations. If you do enable SA based xattrs then they will not be visible on platforms which do not support this feature. ---------------------------------------------------------------------- Time in seconds to get/set one xattr of N bytes on 100,000 files ------+--------------------------------+------------------------------ | setxattr | getxattr bytes | ext4 xfs zfs-dir zfs-sa | ext4 xfs zfs-dir zfs-sa ------+--------------------------------+------------------------------ 1 | 2.33 31.88 21.50 4.57 | 2.35 2.64 6.29 2.43 32 | 2.79 30.68 21.98 4.60 | 2.44 2.59 6.78 2.48 256 | 3.25 31.99 21.36 5.92 | 2.32 2.71 6.22 3.14 1024 | 3.30 32.61 22.83 8.45 | 2.40 2.79 6.24 3.27 4096 | 3.57 317.46 22.52 10.73 | 2.78 28.62 6.90 3.94 16384 | n/a 2342.39 34.30 19.20 | n/a 45.44 145.90 7.55 65536 | n/a 2941.39 128.15 131.32* | n/a 141.92 256.85 262.12* Legend: * ext4 - Stock RHEL6.1 ext4 mounted with '-o user_xattr'. * xfs - Stock RHEL6.1 xfs mounted with default options. * zfs-dir - Directory based xattrs only. * zfs-sa - Prefer SAs but spill in to directories as needed, a trailing * indicates overflow in to directories occured. NOTE: Ext4 supports 4096 bytes of xattr name/value pairs per file. NOTE: XFS and ZFS have no limit on xattr name/value pairs per file. NOTE: Linux limits individual name/value pairs to 65536 bytes. NOTE: All setattr/getattr's were done after dropping the cache. NOTE: All tests were run against a single hard drive. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Issue #443
2011-10-25 03:55:20 +04:00
typedef enum {
ZFS_XATTR_OFF = 0,
ZFS_XATTR_DIR = 1,
ZFS_XATTR_SA = 2
} zfs_xattr_type_t;
Implement large_dnode pool feature 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
2016-03-17 04:25:34 +03:00
typedef enum {
ZFS_DNSIZE_LEGACY = 0,
ZFS_DNSIZE_AUTO = 1,
ZFS_DNSIZE_1K = 1024,
ZFS_DNSIZE_2K = 2048,
ZFS_DNSIZE_4K = 4096,
ZFS_DNSIZE_8K = 8192,
ZFS_DNSIZE_16K = 16384
} zfs_dnsize_type_t;
typedef enum {
ZFS_REDUNDANT_METADATA_ALL,
ZFS_REDUNDANT_METADATA_MOST
} zfs_redundant_metadata_type_t;
typedef enum {
ZFS_VOLMODE_DEFAULT = 0,
ZFS_VOLMODE_GEOM = 1,
ZFS_VOLMODE_DEV = 2,
ZFS_VOLMODE_NONE = 3
} zfs_volmode_t;
2008-11-20 23:01:55 +03:00
/*
* On-disk version number.
*/
#define SPA_VERSION_1 1ULL
#define SPA_VERSION_2 2ULL
#define SPA_VERSION_3 3ULL
#define SPA_VERSION_4 4ULL
#define SPA_VERSION_5 5ULL
#define SPA_VERSION_6 6ULL
#define SPA_VERSION_7 7ULL
#define SPA_VERSION_8 8ULL
#define SPA_VERSION_9 9ULL
#define SPA_VERSION_10 10ULL
#define SPA_VERSION_11 11ULL
#define SPA_VERSION_12 12ULL
#define SPA_VERSION_13 13ULL
#define SPA_VERSION_14 14ULL
2009-07-03 02:44:48 +04:00
#define SPA_VERSION_15 15ULL
#define SPA_VERSION_16 16ULL
2009-08-18 22:43:27 +04:00
#define SPA_VERSION_17 17ULL
#define SPA_VERSION_18 18ULL
#define SPA_VERSION_19 19ULL
#define SPA_VERSION_20 20ULL
#define SPA_VERSION_21 21ULL
#define SPA_VERSION_22 22ULL
#define SPA_VERSION_23 23ULL
#define SPA_VERSION_24 24ULL
#define SPA_VERSION_25 25ULL
#define SPA_VERSION_26 26ULL
#define SPA_VERSION_27 27ULL
#define SPA_VERSION_28 28ULL
#define SPA_VERSION_5000 5000ULL
2008-11-20 23:01:55 +03:00
/*
* When bumping up SPA_VERSION, make sure GRUB ZFS understands the on-disk
2009-07-03 02:44:48 +04:00
* format change. Go to usr/src/grub/grub-0.97/stage2/{zfs-include/, fsys_zfs*},
* and do the appropriate changes. Also bump the version number in
* usr/src/grub/capability.
2008-11-20 23:01:55 +03:00
*/
#define SPA_VERSION SPA_VERSION_5000
#define SPA_VERSION_STRING "5000"
2008-11-20 23:01:55 +03:00
/*
* Symbolic names for the changes that caused a SPA_VERSION switch.
* Used in the code when checking for presence or absence of a feature.
* Feel free to define multiple symbolic names for each version if there
* were multiple changes to on-disk structures during that version.
*
* NOTE: When checking the current SPA_VERSION in your code, be sure
* to use spa_version() since it reports the version of the
* last synced uberblock. Checking the in-flight version can
* be dangerous in some cases.
*/
#define SPA_VERSION_INITIAL SPA_VERSION_1
#define SPA_VERSION_DITTO_BLOCKS SPA_VERSION_2
#define SPA_VERSION_SPARES SPA_VERSION_3
2009-08-18 22:43:27 +04:00
#define SPA_VERSION_RAIDZ2 SPA_VERSION_3
#define SPA_VERSION_BPOBJ_ACCOUNT SPA_VERSION_3
2008-11-20 23:01:55 +03:00
#define SPA_VERSION_RAIDZ_DEFLATE SPA_VERSION_3
#define SPA_VERSION_DNODE_BYTES SPA_VERSION_3
#define SPA_VERSION_ZPOOL_HISTORY SPA_VERSION_4
#define SPA_VERSION_GZIP_COMPRESSION SPA_VERSION_5
#define SPA_VERSION_BOOTFS SPA_VERSION_6
#define SPA_VERSION_SLOGS SPA_VERSION_7
#define SPA_VERSION_DELEGATED_PERMS SPA_VERSION_8
#define SPA_VERSION_FUID SPA_VERSION_9
#define SPA_VERSION_REFRESERVATION SPA_VERSION_9
#define SPA_VERSION_REFQUOTA SPA_VERSION_9
#define SPA_VERSION_UNIQUE_ACCURATE SPA_VERSION_9
#define SPA_VERSION_L2CACHE SPA_VERSION_10
#define SPA_VERSION_NEXT_CLONES SPA_VERSION_11
#define SPA_VERSION_ORIGIN SPA_VERSION_11
#define SPA_VERSION_DSL_SCRUB SPA_VERSION_11
#define SPA_VERSION_SNAP_PROPS SPA_VERSION_12
#define SPA_VERSION_USED_BREAKDOWN SPA_VERSION_13
#define SPA_VERSION_PASSTHROUGH_X SPA_VERSION_14
2009-07-03 02:44:48 +04:00
#define SPA_VERSION_USERSPACE SPA_VERSION_15
#define SPA_VERSION_STMF_PROP SPA_VERSION_16
2009-08-18 22:43:27 +04:00
#define SPA_VERSION_RAIDZ3 SPA_VERSION_17
#define SPA_VERSION_USERREFS SPA_VERSION_18
#define SPA_VERSION_HOLES SPA_VERSION_19
#define SPA_VERSION_ZLE_COMPRESSION SPA_VERSION_20
#define SPA_VERSION_DEDUP SPA_VERSION_21
#define SPA_VERSION_RECVD_PROPS SPA_VERSION_22
#define SPA_VERSION_SLIM_ZIL SPA_VERSION_23
#define SPA_VERSION_SA SPA_VERSION_24
#define SPA_VERSION_SCAN SPA_VERSION_25
#define SPA_VERSION_DIR_CLONES SPA_VERSION_26
#define SPA_VERSION_DEADLISTS SPA_VERSION_26
#define SPA_VERSION_FAST_SNAP SPA_VERSION_27
#define SPA_VERSION_MULTI_REPLACE SPA_VERSION_28
#define SPA_VERSION_BEFORE_FEATURES SPA_VERSION_28
#define SPA_VERSION_FEATURES SPA_VERSION_5000
#define SPA_VERSION_IS_SUPPORTED(v) \
(((v) >= SPA_VERSION_INITIAL && (v) <= SPA_VERSION_BEFORE_FEATURES) || \
((v) >= SPA_VERSION_FEATURES && (v) <= SPA_VERSION))
2008-11-20 23:01:55 +03:00
/*
* ZPL version - rev'd whenever an incompatible on-disk format change
* occurs. This is independent of SPA/DMU/ZAP versioning. You must
* also update the version_table[] and help message in zfs_prop.c.
*
* When changing, be sure to teach GRUB how to read the new format!
2009-07-03 02:44:48 +04:00
* See usr/src/grub/grub-0.97/stage2/{zfs-include/,fsys_zfs*}
2008-11-20 23:01:55 +03:00
*/
#define ZPL_VERSION_1 1ULL
#define ZPL_VERSION_2 2ULL
#define ZPL_VERSION_3 3ULL
2009-07-03 02:44:48 +04:00
#define ZPL_VERSION_4 4ULL
#define ZPL_VERSION_5 5ULL
#define ZPL_VERSION ZPL_VERSION_5
#define ZPL_VERSION_STRING "5"
2008-11-20 23:01:55 +03:00
#define ZPL_VERSION_INITIAL ZPL_VERSION_1
#define ZPL_VERSION_DIRENT_TYPE ZPL_VERSION_2
#define ZPL_VERSION_FUID ZPL_VERSION_3
#define ZPL_VERSION_NORMALIZATION ZPL_VERSION_3
#define ZPL_VERSION_SYSATTR ZPL_VERSION_3
2009-07-03 02:44:48 +04:00
#define ZPL_VERSION_USERSPACE ZPL_VERSION_4
#define ZPL_VERSION_SA ZPL_VERSION_5
/* Rewind request information */
#define ZPOOL_NO_REWIND 1 /* No policy - default behavior */
#define ZPOOL_NEVER_REWIND 2 /* Do not search for best txg or rewind */
#define ZPOOL_TRY_REWIND 4 /* Search for best txg, but do not rewind */
#define ZPOOL_DO_REWIND 8 /* Rewind to best txg w/in deferred frees */
#define ZPOOL_EXTREME_REWIND 16 /* Allow extreme measures to find best txg */
#define ZPOOL_REWIND_MASK 28 /* All the possible rewind bits */
#define ZPOOL_REWIND_POLICIES 31 /* All the possible policy bits */
typedef struct zpool_rewind_policy {
uint32_t zrp_request; /* rewind behavior requested */
uint64_t zrp_maxmeta; /* max acceptable meta-data errors */
uint64_t zrp_maxdata; /* max acceptable data errors */
uint64_t zrp_txg; /* specific txg to load */
} zpool_rewind_policy_t;
2008-11-20 23:01:55 +03:00
/*
* The following are configuration names used in the nvlist describing a pool's
* configuration.
*/
#define ZPOOL_CONFIG_VERSION "version"
#define ZPOOL_CONFIG_POOL_NAME "name"
#define ZPOOL_CONFIG_POOL_STATE "state"
#define ZPOOL_CONFIG_POOL_TXG "txg"
#define ZPOOL_CONFIG_POOL_GUID "pool_guid"
#define ZPOOL_CONFIG_CREATE_TXG "create_txg"
#define ZPOOL_CONFIG_TOP_GUID "top_guid"
#define ZPOOL_CONFIG_VDEV_TREE "vdev_tree"
#define ZPOOL_CONFIG_TYPE "type"
#define ZPOOL_CONFIG_CHILDREN "children"
#define ZPOOL_CONFIG_ID "id"
#define ZPOOL_CONFIG_GUID "guid"
#define ZPOOL_CONFIG_PATH "path"
#define ZPOOL_CONFIG_DEVID "devid"
#define ZPOOL_CONFIG_METASLAB_ARRAY "metaslab_array"
#define ZPOOL_CONFIG_METASLAB_SHIFT "metaslab_shift"
#define ZPOOL_CONFIG_ASHIFT "ashift"
#define ZPOOL_CONFIG_ASIZE "asize"
#define ZPOOL_CONFIG_DTL "DTL"
#define ZPOOL_CONFIG_SCAN_STATS "scan_stats" /* not stored on disk */
#define ZPOOL_CONFIG_VDEV_STATS "vdev_stats" /* not stored on disk */
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
/* container nvlist of extended stats */
#define ZPOOL_CONFIG_VDEV_STATS_EX "vdev_stats_ex"
/* Active queue read/write stats */
#define ZPOOL_CONFIG_VDEV_SYNC_R_ACTIVE_QUEUE "vdev_sync_r_active_queue"
#define ZPOOL_CONFIG_VDEV_SYNC_W_ACTIVE_QUEUE "vdev_sync_w_active_queue"
#define ZPOOL_CONFIG_VDEV_ASYNC_R_ACTIVE_QUEUE "vdev_async_r_active_queue"
#define ZPOOL_CONFIG_VDEV_ASYNC_W_ACTIVE_QUEUE "vdev_async_w_active_queue"
#define ZPOOL_CONFIG_VDEV_SCRUB_ACTIVE_QUEUE "vdev_async_scrub_active_queue"
/* Queue sizes */
#define ZPOOL_CONFIG_VDEV_SYNC_R_PEND_QUEUE "vdev_sync_r_pend_queue"
#define ZPOOL_CONFIG_VDEV_SYNC_W_PEND_QUEUE "vdev_sync_w_pend_queue"
#define ZPOOL_CONFIG_VDEV_ASYNC_R_PEND_QUEUE "vdev_async_r_pend_queue"
#define ZPOOL_CONFIG_VDEV_ASYNC_W_PEND_QUEUE "vdev_async_w_pend_queue"
#define ZPOOL_CONFIG_VDEV_SCRUB_PEND_QUEUE "vdev_async_scrub_pend_queue"
/* Latency read/write histogram stats */
#define ZPOOL_CONFIG_VDEV_TOT_R_LAT_HISTO "vdev_tot_r_lat_histo"
#define ZPOOL_CONFIG_VDEV_TOT_W_LAT_HISTO "vdev_tot_w_lat_histo"
#define ZPOOL_CONFIG_VDEV_DISK_R_LAT_HISTO "vdev_disk_r_lat_histo"
#define ZPOOL_CONFIG_VDEV_DISK_W_LAT_HISTO "vdev_disk_w_lat_histo"
#define ZPOOL_CONFIG_VDEV_SYNC_R_LAT_HISTO "vdev_sync_r_lat_histo"
#define ZPOOL_CONFIG_VDEV_SYNC_W_LAT_HISTO "vdev_sync_w_lat_histo"
#define ZPOOL_CONFIG_VDEV_ASYNC_R_LAT_HISTO "vdev_async_r_lat_histo"
#define ZPOOL_CONFIG_VDEV_ASYNC_W_LAT_HISTO "vdev_async_w_lat_histo"
#define ZPOOL_CONFIG_VDEV_SCRUB_LAT_HISTO "vdev_scrub_histo"
/* Request size histograms */
#define ZPOOL_CONFIG_VDEV_SYNC_IND_R_HISTO "vdev_sync_ind_r_histo"
#define ZPOOL_CONFIG_VDEV_SYNC_IND_W_HISTO "vdev_sync_ind_w_histo"
#define ZPOOL_CONFIG_VDEV_ASYNC_IND_R_HISTO "vdev_async_ind_r_histo"
#define ZPOOL_CONFIG_VDEV_ASYNC_IND_W_HISTO "vdev_async_ind_w_histo"
#define ZPOOL_CONFIG_VDEV_IND_SCRUB_HISTO "vdev_ind_scrub_histo"
#define ZPOOL_CONFIG_VDEV_SYNC_AGG_R_HISTO "vdev_sync_agg_r_histo"
#define ZPOOL_CONFIG_VDEV_SYNC_AGG_W_HISTO "vdev_sync_agg_w_histo"
#define ZPOOL_CONFIG_VDEV_ASYNC_AGG_R_HISTO "vdev_async_agg_r_histo"
#define ZPOOL_CONFIG_VDEV_ASYNC_AGG_W_HISTO "vdev_async_agg_w_histo"
#define ZPOOL_CONFIG_VDEV_AGG_SCRUB_HISTO "vdev_agg_scrub_histo"
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
/* vdev enclosure sysfs path */
#define ZPOOL_CONFIG_VDEV_ENC_SYSFS_PATH "vdev_enc_sysfs_path"
2008-11-20 23:01:55 +03:00
#define ZPOOL_CONFIG_WHOLE_DISK "whole_disk"
#define ZPOOL_CONFIG_ERRCOUNT "error_count"
#define ZPOOL_CONFIG_NOT_PRESENT "not_present"
#define ZPOOL_CONFIG_SPARES "spares"
#define ZPOOL_CONFIG_IS_SPARE "is_spare"
#define ZPOOL_CONFIG_NPARITY "nparity"
#define ZPOOL_CONFIG_HOSTID "hostid"
#define ZPOOL_CONFIG_HOSTNAME "hostname"
#define ZPOOL_CONFIG_LOADED_TIME "initial_load_time"
2008-11-20 23:01:55 +03:00
#define ZPOOL_CONFIG_UNSPARE "unspare"
#define ZPOOL_CONFIG_PHYS_PATH "phys_path"
#define ZPOOL_CONFIG_IS_LOG "is_log"
#define ZPOOL_CONFIG_L2CACHE "l2cache"
#define ZPOOL_CONFIG_HOLE_ARRAY "hole_array"
#define ZPOOL_CONFIG_VDEV_CHILDREN "vdev_children"
#define ZPOOL_CONFIG_IS_HOLE "is_hole"
#define ZPOOL_CONFIG_DDT_HISTOGRAM "ddt_histogram"
#define ZPOOL_CONFIG_DDT_OBJ_STATS "ddt_object_stats"
#define ZPOOL_CONFIG_DDT_STATS "ddt_stats"
#define ZPOOL_CONFIG_SPLIT "splitcfg"
#define ZPOOL_CONFIG_ORIG_GUID "orig_guid"
#define ZPOOL_CONFIG_SPLIT_GUID "split_guid"
#define ZPOOL_CONFIG_SPLIT_LIST "guid_list"
#define ZPOOL_CONFIG_REMOVING "removing"
Illumos #3956, #3957, #3958, #3959, #3960, #3961, #3962 3956 ::vdev -r should work with pipelines 3957 ztest should update the cachefile before killing itself 3958 multiple scans can lead to partial resilvering 3959 ddt entries are not always resilvered 3960 dsl_scan can skip over dedup-ed blocks if physical birth != logical birth 3961 freed gang blocks are not resilvered and can cause pool to suspend 3962 ztest should print out zfs debug buffer before exiting Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Adam Leventhal <ahl@delphix.com> Approved by: Richard Lowe <richlowe@richlowe.net> References: https://www.illumos.org/issues/3956 https://www.illumos.org/issues/3957 https://www.illumos.org/issues/3958 https://www.illumos.org/issues/3959 https://www.illumos.org/issues/3960 https://www.illumos.org/issues/3961 https://www.illumos.org/issues/3962 illumos/illumos-gate@b4952e17e8858d3225793b28788278de9fe6038d Ported-by: Richard Yao <ryao@gentoo.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Porting notes: 1. zfs_dbgmsg_print() is only used in userland. Since we do not have mdb on Linux, it does not make sense to make it available in the kernel. This means that a build failure will occur if any future kernel patch depends on it. However, that is unlikely given that this functionality was added to support zdb. 2. zfs_dbgmsg_print() is only invoked for -VVV or greater log levels. This preserves the existing behavior of minimal noise when running with -V, and -VV. 3. In vdev_config_generate() the call to nvlist_alloc() was not changed to fnvlist_alloc() because we must pass KM_PUSHPAGE in the txg_sync context.
2013-08-08 00:16:22 +04:00
#define ZPOOL_CONFIG_RESILVER_TXG "resilver_txg"
#define ZPOOL_CONFIG_COMMENT "comment"
#define ZPOOL_CONFIG_SUSPENDED "suspended" /* not stored on disk */
2008-11-20 23:01:55 +03:00
#define ZPOOL_CONFIG_TIMESTAMP "timestamp" /* not stored on disk */
#define ZPOOL_CONFIG_BOOTFS "bootfs" /* not stored on disk */
#define ZPOOL_CONFIG_MISSING_DEVICES "missing_vdevs" /* not stored on disk */
#define ZPOOL_CONFIG_LOAD_INFO "load_info" /* not stored on disk */
#define ZPOOL_CONFIG_REWIND_INFO "rewind_info" /* not stored on disk */
#define ZPOOL_CONFIG_UNSUP_FEAT "unsup_feat" /* not stored on disk */
#define ZPOOL_CONFIG_ENABLED_FEAT "enabled_feat" /* not stored on disk */
#define ZPOOL_CONFIG_CAN_RDONLY "can_rdonly" /* not stored on disk */
#define ZPOOL_CONFIG_FEATURES_FOR_READ "features_for_read"
#define ZPOOL_CONFIG_FEATURE_STATS "feature_stats" /* not stored on disk */
Add generic errata infrastructure From time to time it may be necessary to inform the pool administrator about an errata which impacts their pool. These errata will by shown to the administrator through the 'zpool status' and 'zpool import' output as appropriate. The errata must clearly describe the issue detected, how the pool is impacted, and what action should be taken to resolve the situation. Additional information for each errata will be provided at http://zfsonlinux.org/msg/ZFS-8000-ER. To accomplish the above this patch adds the required infrastructure to allow the kernel modules to notify the utilities that an errata has been detected. This is done through the ZPOOL_CONFIG_ERRATA uint64_t which has been added to the pool configuration nvlist. To add a new errata the following changes must be made: * A new errata identifier must be assigned by adding a new enum value to the zpool_errata_t type. New enums must be added to the end to preserve the existing ordering. * Code must be added to detect the issue. This does not strictly need to be done at pool import time but doing so will make the errata visible in 'zpool import' as well as 'zpool status'. Once detected the spa->spa_errata member should be set to the new enum. * If possible code should be added to clear the spa->spa_errata member once the errata has been resolved. * The show_import() and status_callback() functions must be updated to include an informational message describing the errata. This should include an action message describing what an administrator should do to address the errata. * The documentation at http://zfsonlinux.org/msg/ZFS-8000-ER must be updated to describe the errata. This space can be used to provide as much additional information as needed to fully describe the errata. A link to this documentation will be automatically generated in the output of 'zpool import' and 'zpool status'. Original-idea-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tim Chase <tim@chase2k.com> Signed-off-by: Richard Yao <ryao@gentoo.or Issue #2094
2014-02-21 07:57:17 +04:00
#define ZPOOL_CONFIG_ERRATA "errata" /* not stored on disk */
#define ZPOOL_CONFIG_VDEV_TOP_ZAP "com.delphix:vdev_zap_top"
#define ZPOOL_CONFIG_VDEV_LEAF_ZAP "com.delphix:vdev_zap_leaf"
#define ZPOOL_CONFIG_HAS_PER_VDEV_ZAPS "com.delphix:has_per_vdev_zaps"
2008-11-20 23:01:55 +03:00
/*
* The persistent vdev state is stored as separate values rather than a single
* 'vdev_state' entry. This is because a device can be in multiple states, such
* as offline and degraded.
*/
#define ZPOOL_CONFIG_OFFLINE "offline"
#define ZPOOL_CONFIG_FAULTED "faulted"
#define ZPOOL_CONFIG_DEGRADED "degraded"
#define ZPOOL_CONFIG_REMOVED "removed"
2009-07-03 02:44:48 +04:00
#define ZPOOL_CONFIG_FRU "fru"
#define ZPOOL_CONFIG_AUX_STATE "aux_state"
/* Rewind policy parameters */
#define ZPOOL_REWIND_POLICY "rewind-policy"
#define ZPOOL_REWIND_REQUEST "rewind-request"
#define ZPOOL_REWIND_REQUEST_TXG "rewind-request-txg"
#define ZPOOL_REWIND_META_THRESH "rewind-meta-thresh"
#define ZPOOL_REWIND_DATA_THRESH "rewind-data-thresh"
/* Rewind data discovered */
#define ZPOOL_CONFIG_LOAD_TIME "rewind_txg_ts"
#define ZPOOL_CONFIG_LOAD_DATA_ERRORS "verify_data_errors"
#define ZPOOL_CONFIG_REWIND_TIME "seconds_of_rewind"
2008-11-20 23:01:55 +03:00
#define VDEV_TYPE_ROOT "root"
#define VDEV_TYPE_MIRROR "mirror"
#define VDEV_TYPE_REPLACING "replacing"
#define VDEV_TYPE_RAIDZ "raidz"
#define VDEV_TYPE_DISK "disk"
#define VDEV_TYPE_FILE "file"
#define VDEV_TYPE_MISSING "missing"
#define VDEV_TYPE_HOLE "hole"
2008-11-20 23:01:55 +03:00
#define VDEV_TYPE_SPARE "spare"
#define VDEV_TYPE_LOG "log"
#define VDEV_TYPE_L2CACHE "l2cache"
/*
* This is needed in userland to report the minimum necessary device size.
*/
#define SPA_MINDEVSIZE (64ULL << 20)
Illumos 4976-4984 - metaslab improvements 4976 zfs should only avoid writing to a failing non-redundant top-level vdev 4978 ztest fails in get_metaslab_refcount() 4979 extend free space histogram to device and pool 4980 metaslabs should have a fragmentation metric 4981 remove fragmented ops vector from block allocator 4982 space_map object should proactively upgrade when feature is enabled 4983 need to collect metaslab information via mdb 4984 device selection should use fragmentation metric Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Adam Leventhal <adam.leventhal@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Approved by: Garrett D'Amore <garrett@damore.org> References: https://www.illumos.org/issues/4976 https://www.illumos.org/issues/4978 https://www.illumos.org/issues/4979 https://www.illumos.org/issues/4980 https://www.illumos.org/issues/4981 https://www.illumos.org/issues/4982 https://www.illumos.org/issues/4983 https://www.illumos.org/issues/4984 https://github.com/illumos/illumos-gate/commit/2e4c998 Notes: The "zdb -M" option has been re-tasked to display the new metaslab fragmentation metric and the new "zdb -I" option is used to control the maximum number of in-flight I/Os. The new fragmentation metric is derived from the space map histogram which has been rolled up to the vdev and pool level and is presented to the user via "zpool list". Add a number of module parameters related to the new metaslab weighting logic. Ported by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #2595
2014-07-20 00:19:24 +04:00
/*
* Set if the fragmentation has not yet been calculated. This can happen
* because the space maps have not been upgraded or the histogram feature
* is not enabled.
*/
#define ZFS_FRAG_INVALID UINT64_MAX
2008-11-20 23:01:55 +03:00
/*
* The location of the pool configuration repository, shared between kernel and
* userland.
*/
#define ZPOOL_CACHE "/etc/zfs/zpool.cache"
2008-11-20 23:01:55 +03:00
/*
* vdev states are ordered from least to most healthy.
* A vdev that's CANT_OPEN or below is considered unusable.
*/
typedef enum vdev_state {
VDEV_STATE_UNKNOWN = 0, /* Uninitialized vdev */
VDEV_STATE_CLOSED, /* Not currently open */
VDEV_STATE_OFFLINE, /* Not allowed to open */
VDEV_STATE_REMOVED, /* Explicitly removed from system */
VDEV_STATE_CANT_OPEN, /* Tried to open, but failed */
VDEV_STATE_FAULTED, /* External request to fault device */
VDEV_STATE_DEGRADED, /* Replicated vdev with unhealthy kids */
VDEV_STATE_HEALTHY /* Presumed good */
} vdev_state_t;
#define VDEV_STATE_ONLINE VDEV_STATE_HEALTHY
/*
* vdev aux states. When a vdev is in the CANT_OPEN state, the aux field
* of the vdev stats structure uses these constants to distinguish why.
*/
typedef enum vdev_aux {
VDEV_AUX_NONE, /* no error */
VDEV_AUX_OPEN_FAILED, /* ldi_open_*() or vn_open() failed */
VDEV_AUX_CORRUPT_DATA, /* bad label or disk contents */
VDEV_AUX_NO_REPLICAS, /* insufficient number of replicas */
VDEV_AUX_BAD_GUID_SUM, /* vdev guid sum doesn't match */
VDEV_AUX_TOO_SMALL, /* vdev size is too small */
VDEV_AUX_BAD_LABEL, /* the label is OK but invalid */
VDEV_AUX_VERSION_NEWER, /* on-disk version is too new */
VDEV_AUX_VERSION_OLDER, /* on-disk version is too old */
VDEV_AUX_UNSUP_FEAT, /* unsupported features */
2008-11-20 23:01:55 +03:00
VDEV_AUX_SPARED, /* hot spare used in another pool */
VDEV_AUX_ERR_EXCEEDED, /* too many errors */
VDEV_AUX_IO_FAILURE, /* experienced I/O failure */
VDEV_AUX_BAD_LOG, /* cannot read log chain(s) */
VDEV_AUX_EXTERNAL, /* external diagnosis or forced fault */
VDEV_AUX_SPLIT_POOL, /* vdev was split off into another pool */
VDEV_AUX_BAD_ASHIFT, /* vdev ashift is invalid */
VDEV_AUX_EXTERNAL_PERSIST /* persistent forced fault */
2008-11-20 23:01:55 +03:00
} vdev_aux_t;
/*
* pool state. The following states are written to disk as part of the normal
* SPA lifecycle: ACTIVE, EXPORTED, DESTROYED, SPARE, L2CACHE. The remaining
* states are software abstractions used at various levels to communicate
* pool state.
*/
typedef enum pool_state {
POOL_STATE_ACTIVE = 0, /* In active use */
POOL_STATE_EXPORTED, /* Explicitly exported */
POOL_STATE_DESTROYED, /* Explicitly destroyed */
POOL_STATE_SPARE, /* Reserved for hot spare use */
POOL_STATE_L2CACHE, /* Level 2 ARC device */
POOL_STATE_UNINITIALIZED, /* Internal spa_t state */
POOL_STATE_UNAVAIL, /* Internal libzfs state */
POOL_STATE_POTENTIALLY_ACTIVE /* Internal libzfs state */
} pool_state_t;
/*
* Scan Functions.
2008-11-20 23:01:55 +03:00
*/
typedef enum pool_scan_func {
POOL_SCAN_NONE,
POOL_SCAN_SCRUB,
POOL_SCAN_RESILVER,
POOL_SCAN_FUNCS
} pool_scan_func_t;
2008-11-20 23:01:55 +03:00
/*
* Used to control scrub pause and resume.
*/
typedef enum pool_scrub_cmd {
POOL_SCRUB_NORMAL = 0,
POOL_SCRUB_PAUSE,
POOL_SCRUB_FLAGS_END
} pool_scrub_cmd_t;
2008-11-20 23:01:55 +03:00
/*
* ZIO types. Needed to interpret vdev statistics below.
*/
typedef enum zio_type {
ZIO_TYPE_NULL = 0,
ZIO_TYPE_READ,
ZIO_TYPE_WRITE,
ZIO_TYPE_FREE,
ZIO_TYPE_CLAIM,
ZIO_TYPE_IOCTL,
ZIO_TYPES
} zio_type_t;
/*
* Pool statistics. Note: all fields should be 64-bit because this
* is passed between kernel and userland as an nvlist uint64 array.
*/
typedef struct pool_scan_stat {
/* values stored on disk */
uint64_t pss_func; /* pool_scan_func_t */
uint64_t pss_state; /* dsl_scan_state_t */
uint64_t pss_start_time; /* scan start time */
uint64_t pss_end_time; /* scan end time */
uint64_t pss_to_examine; /* total bytes to scan */
uint64_t pss_examined; /* total examined bytes */
uint64_t pss_to_process; /* total bytes to process */
uint64_t pss_processed; /* total processed bytes */
uint64_t pss_errors; /* scan errors */
/* values not stored on disk */
uint64_t pss_pass_exam; /* examined bytes per scan pass */
uint64_t pss_pass_start; /* start time of a scan pass */
uint64_t pss_pass_scrub_pause; /* pause time of a scurb pass */
/* cumulative time scrub spent paused, needed for rate calculation */
uint64_t pss_pass_scrub_spent_paused;
} pool_scan_stat_t;
typedef enum dsl_scan_state {
DSS_NONE,
DSS_SCANNING,
DSS_FINISHED,
DSS_CANCELED,
DSS_NUM_STATES
} dsl_scan_state_t;
Add generic errata infrastructure From time to time it may be necessary to inform the pool administrator about an errata which impacts their pool. These errata will by shown to the administrator through the 'zpool status' and 'zpool import' output as appropriate. The errata must clearly describe the issue detected, how the pool is impacted, and what action should be taken to resolve the situation. Additional information for each errata will be provided at http://zfsonlinux.org/msg/ZFS-8000-ER. To accomplish the above this patch adds the required infrastructure to allow the kernel modules to notify the utilities that an errata has been detected. This is done through the ZPOOL_CONFIG_ERRATA uint64_t which has been added to the pool configuration nvlist. To add a new errata the following changes must be made: * A new errata identifier must be assigned by adding a new enum value to the zpool_errata_t type. New enums must be added to the end to preserve the existing ordering. * Code must be added to detect the issue. This does not strictly need to be done at pool import time but doing so will make the errata visible in 'zpool import' as well as 'zpool status'. Once detected the spa->spa_errata member should be set to the new enum. * If possible code should be added to clear the spa->spa_errata member once the errata has been resolved. * The show_import() and status_callback() functions must be updated to include an informational message describing the errata. This should include an action message describing what an administrator should do to address the errata. * The documentation at http://zfsonlinux.org/msg/ZFS-8000-ER must be updated to describe the errata. This space can be used to provide as much additional information as needed to fully describe the errata. A link to this documentation will be automatically generated in the output of 'zpool import' and 'zpool status'. Original-idea-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tim Chase <tim@chase2k.com> Signed-off-by: Richard Yao <ryao@gentoo.or Issue #2094
2014-02-21 07:57:17 +04:00
/*
* Errata described by http://zfsonlinux.org/msg/ZFS-8000-ER. The ordering
* of this enum must be maintained to ensure the errata identifiers map to
* the correct documentation. New errata may only be appended to the list
* and must contain corresponding documentation at the above link.
*/
typedef enum zpool_errata {
ZPOOL_ERRATA_NONE,
Add erratum for issue #2094 ZoL commit 1421c89 unintentionally changed the disk format in a forward- compatible, but not backward compatible way. This was accomplished by adding an entry to zbookmark_t, which is included in a couple of on-disk structures. That lead to the creation of pools with incorrect dsl_scan_phys_t objects that could only be imported by versions of ZoL containing that commit. Such pools cannot be imported by other versions of ZFS or past versions of ZoL. The additional field has been removed by the previous commit. However, affected pools must be imported and scrubbed using a version of ZoL with this commit applied. This will return the pools to a state in which they may be imported by other implementations. The 'zpool import' or 'zpool status' command can be used to determine if a pool is impacted. A message similar to one of the following means your pool must be scrubbed to restore compatibility. $ zpool import pool: zol-0.6.2-173 id: 1165955789558693437 state: ONLINE status: Errata #1 detected. action: The pool can be imported using its name or numeric identifier, however there is a compatibility issue which should be corrected by running 'zpool scrub' see: http://zfsonlinux.org/msg/ZFS-8000-ER config: ... $ zpool status pool: zol-0.6.2-173 state: ONLINE scan: pool compatibility issue detected. see: https://github.com/zfsonlinux/zfs/issues/2094 action: To correct the issue run 'zpool scrub'. config: ... If there was an async destroy in progress 'zpool import' will prevent the pool from being imported. Further advice on how to proceed will be provided by the error message as follows. $ zpool import pool: zol-0.6.2-173 id: 1165955789558693437 state: ONLINE status: Errata #2 detected. action: The pool can not be imported with this version of ZFS due to an active asynchronous destroy. Revert to an earlier version and allow the destroy to complete before updating. see: http://zfsonlinux.org/msg/ZFS-8000-ER config: ... Pools affected by the damaged dsl_scan_phys_t can be detected prior to an upgrade by running the following command as root: zdb -dddd poolname 1 | grep -P '^\t\tscan = ' | sed -e 's;scan = ;;' | wc -w Note that `poolname` must be replaced with the name of the pool you wish to check. A value of 25 indicates the dsl_scan_phys_t has been damaged. A value of 24 indicates that the dsl_scan_phys_t is normal. A value of 0 indicates that there has never been a scrub run on the pool. The regression caused by the change to zbookmark_t never made it into a tagged release, Gentoo backports, Ubuntu, Debian, Fedora, or EPEL stable respositorys. Only those using the HEAD version directly from Github after the 0.6.2 but before the 0.6.3 tag are affected. This patch does have one limitation that should be mentioned. It will not detect errata #2 on a pool unless errata #1 is also present. It expected this will not be a significant problem because pools impacted by errata #2 have a high probably of being impacted by errata #1. End users can ensure they do no hit this unlikely case by waiting for all asynchronous destroy operations to complete before updating ZoL. The presence of any background destroys on any imported pools can be checked by running `zpool get freeing` as root. This will display a non-zero value for any pool with an active asynchronous destroy. Lastly, it is expected that no user data has been lost as a result of this erratum. Original-patch-by: Tim Chase <tim@chase2k.com> Reworked-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tim Chase <tim@chase2k.com> Signed-off-by: Richard Yao <ryao@gentoo.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Issue #2094
2014-02-21 08:28:33 +04:00
ZPOOL_ERRATA_ZOL_2094_SCRUB,
ZPOOL_ERRATA_ZOL_2094_ASYNC_DESTROY,
Add generic errata infrastructure From time to time it may be necessary to inform the pool administrator about an errata which impacts their pool. These errata will by shown to the administrator through the 'zpool status' and 'zpool import' output as appropriate. The errata must clearly describe the issue detected, how the pool is impacted, and what action should be taken to resolve the situation. Additional information for each errata will be provided at http://zfsonlinux.org/msg/ZFS-8000-ER. To accomplish the above this patch adds the required infrastructure to allow the kernel modules to notify the utilities that an errata has been detected. This is done through the ZPOOL_CONFIG_ERRATA uint64_t which has been added to the pool configuration nvlist. To add a new errata the following changes must be made: * A new errata identifier must be assigned by adding a new enum value to the zpool_errata_t type. New enums must be added to the end to preserve the existing ordering. * Code must be added to detect the issue. This does not strictly need to be done at pool import time but doing so will make the errata visible in 'zpool import' as well as 'zpool status'. Once detected the spa->spa_errata member should be set to the new enum. * If possible code should be added to clear the spa->spa_errata member once the errata has been resolved. * The show_import() and status_callback() functions must be updated to include an informational message describing the errata. This should include an action message describing what an administrator should do to address the errata. * The documentation at http://zfsonlinux.org/msg/ZFS-8000-ER must be updated to describe the errata. This space can be used to provide as much additional information as needed to fully describe the errata. A link to this documentation will be automatically generated in the output of 'zpool import' and 'zpool status'. Original-idea-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tim Chase <tim@chase2k.com> Signed-off-by: Richard Yao <ryao@gentoo.or Issue #2094
2014-02-21 07:57:17 +04:00
} zpool_errata_t;
2008-11-20 23:01:55 +03:00
/*
* Vdev statistics. Note: all fields should be 64-bit because this
* is passed between kernel and userland as an nvlist uint64 array.
*/
typedef struct vdev_stat {
hrtime_t vs_timestamp; /* time since vdev load */
uint64_t vs_state; /* vdev state */
uint64_t vs_aux; /* see vdev_aux_t */
uint64_t vs_alloc; /* space allocated */
uint64_t vs_space; /* total capacity */
uint64_t vs_dspace; /* deflated capacity */
uint64_t vs_rsize; /* replaceable dev size */
uint64_t vs_esize; /* expandable dev size */
2008-11-20 23:01:55 +03:00
uint64_t vs_ops[ZIO_TYPES]; /* operation count */
uint64_t vs_bytes[ZIO_TYPES]; /* bytes read/written */
uint64_t vs_read_errors; /* read errors */
uint64_t vs_write_errors; /* write errors */
uint64_t vs_checksum_errors; /* checksum errors */
uint64_t vs_self_healed; /* self-healed bytes */
uint64_t vs_scan_removing; /* removing? */
uint64_t vs_scan_processed; /* scan processed bytes */
Illumos 4976-4984 - metaslab improvements 4976 zfs should only avoid writing to a failing non-redundant top-level vdev 4978 ztest fails in get_metaslab_refcount() 4979 extend free space histogram to device and pool 4980 metaslabs should have a fragmentation metric 4981 remove fragmented ops vector from block allocator 4982 space_map object should proactively upgrade when feature is enabled 4983 need to collect metaslab information via mdb 4984 device selection should use fragmentation metric Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Adam Leventhal <adam.leventhal@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Approved by: Garrett D'Amore <garrett@damore.org> References: https://www.illumos.org/issues/4976 https://www.illumos.org/issues/4978 https://www.illumos.org/issues/4979 https://www.illumos.org/issues/4980 https://www.illumos.org/issues/4981 https://www.illumos.org/issues/4982 https://www.illumos.org/issues/4983 https://www.illumos.org/issues/4984 https://github.com/illumos/illumos-gate/commit/2e4c998 Notes: The "zdb -M" option has been re-tasked to display the new metaslab fragmentation metric and the new "zdb -I" option is used to control the maximum number of in-flight I/Os. The new fragmentation metric is derived from the space map histogram which has been rolled up to the vdev and pool level and is presented to the user via "zpool list". Add a number of module parameters related to the new metaslab weighting logic. Ported by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #2595
2014-07-20 00:19:24 +04:00
uint64_t vs_fragmentation; /* device fragmentation */
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
2008-11-20 23:01:55 +03:00
} vdev_stat_t;
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
/*
* Extended stats
*
* These are stats which aren't included in the original iostat output. For
* convenience, they are grouped together in vdev_stat_ex, although each stat
* is individually exported as an nvlist.
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
*/
typedef struct vdev_stat_ex {
/* Number of ZIOs issued to disk and waiting to finish */
uint64_t vsx_active_queue[ZIO_PRIORITY_NUM_QUEUEABLE];
/* Number of ZIOs pending to be issued to disk */
uint64_t vsx_pend_queue[ZIO_PRIORITY_NUM_QUEUEABLE];
/*
* Below are the histograms for various latencies. Buckets are in
* units of nanoseconds.
*/
/*
* 2^37 nanoseconds = 134s. Timeouts will probably start kicking in
* before this.
*/
#define VDEV_L_HISTO_BUCKETS 37 /* Latency histo buckets */
#define VDEV_RQ_HISTO_BUCKETS 25 /* Request size histo buckets */
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
/* Amount of time in ZIO queue (ns) */
uint64_t vsx_queue_histo[ZIO_PRIORITY_NUM_QUEUEABLE]
[VDEV_L_HISTO_BUCKETS];
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
/* Total ZIO latency (ns). Includes queuing and disk access time */
uint64_t vsx_total_histo[ZIO_TYPES][VDEV_L_HISTO_BUCKETS];
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
/* Amount of time to read/write the disk (ns) */
uint64_t vsx_disk_histo[ZIO_TYPES][VDEV_L_HISTO_BUCKETS];
/* "lookup the bucket for a value" histogram macros */
#define HISTO(val, buckets) (val != 0 ? MIN(highbit64(val) - 1, \
buckets - 1) : 0)
#define L_HISTO(a) HISTO(a, VDEV_L_HISTO_BUCKETS)
#define RQ_HISTO(a) HISTO(a, VDEV_RQ_HISTO_BUCKETS)
/* Physical IO histogram */
uint64_t vsx_ind_histo[ZIO_PRIORITY_NUM_QUEUEABLE]
[VDEV_RQ_HISTO_BUCKETS];
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
/* Delegated (aggregated) physical IO histogram */
uint64_t vsx_agg_histo[ZIO_PRIORITY_NUM_QUEUEABLE]
[VDEV_RQ_HISTO_BUCKETS];
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 21:05:23 +03:00
} vdev_stat_ex_t;
/*
* DDT statistics. Note: all fields should be 64-bit because this
* is passed between kernel and userland as an nvlist uint64 array.
*/
typedef struct ddt_object {
uint64_t ddo_count; /* number of elements in ddt */
uint64_t ddo_dspace; /* size of ddt on disk */
uint64_t ddo_mspace; /* size of ddt in-core */
} ddt_object_t;
typedef struct ddt_stat {
uint64_t dds_blocks; /* blocks */
uint64_t dds_lsize; /* logical size */
uint64_t dds_psize; /* physical size */
uint64_t dds_dsize; /* deflated allocated size */
uint64_t dds_ref_blocks; /* referenced blocks */
uint64_t dds_ref_lsize; /* referenced lsize * refcnt */
uint64_t dds_ref_psize; /* referenced psize * refcnt */
uint64_t dds_ref_dsize; /* referenced dsize * refcnt */
} ddt_stat_t;
typedef struct ddt_histogram {
ddt_stat_t ddh_stat[64]; /* power-of-two histogram buckets */
} ddt_histogram_t;
2008-11-20 23:01:55 +03:00
#define ZVOL_DRIVER "zvol"
#define ZFS_DRIVER "zfs"
#define ZFS_DEV "/dev/zfs"
#define ZFS_SHARETAB "/etc/dfs/sharetab"
2008-11-20 23:01:55 +03:00
#define ZFS_SUPER_MAGIC 0x2fc12fc1
/* general zvol path */
#define ZVOL_DIR "/dev"
#define ZVOL_MAJOR 230
#define ZVOL_MINOR_BITS 4
#define ZVOL_MINOR_MASK ((1U << ZVOL_MINOR_BITS) - 1)
#define ZVOL_MINORS (1 << 4)
#define ZVOL_DEV_NAME "zd"
2008-11-20 23:01:55 +03:00
#define ZVOL_PROP_NAME "name"
#define ZVOL_DEFAULT_BLOCKSIZE 8192
2008-11-20 23:01:55 +03:00
/*
* /dev/zfs ioctl numbers.
*/
typedef enum zfs_ioc {
/*
* Illumos - 71/128 numbers reserved.
*/
Illumos #2882, #2883, #2900 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/2882 https://www.illumos.org/issues/2883 https://www.illumos.org/issues/2900 illumos/illumos-gate@4445fffbbb1ea25fd0e9ea68b9380dd7a6709025 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.
2013-08-28 15:45:09 +04:00
ZFS_IOC_FIRST = ('Z' << 8),
ZFS_IOC = ZFS_IOC_FIRST,
ZFS_IOC_POOL_CREATE = ZFS_IOC_FIRST,
2008-11-20 23:01:55 +03:00
ZFS_IOC_POOL_DESTROY,
ZFS_IOC_POOL_IMPORT,
ZFS_IOC_POOL_EXPORT,
ZFS_IOC_POOL_CONFIGS,
ZFS_IOC_POOL_STATS,
ZFS_IOC_POOL_TRYIMPORT,
ZFS_IOC_POOL_SCAN,
2008-11-20 23:01:55 +03:00
ZFS_IOC_POOL_FREEZE,
ZFS_IOC_POOL_UPGRADE,
ZFS_IOC_POOL_GET_HISTORY,
ZFS_IOC_VDEV_ADD,
ZFS_IOC_VDEV_REMOVE,
ZFS_IOC_VDEV_SET_STATE,
ZFS_IOC_VDEV_ATTACH,
ZFS_IOC_VDEV_DETACH,
ZFS_IOC_VDEV_SETPATH,
2009-07-03 02:44:48 +04:00
ZFS_IOC_VDEV_SETFRU,
2008-11-20 23:01:55 +03:00
ZFS_IOC_OBJSET_STATS,
ZFS_IOC_OBJSET_ZPLPROPS,
ZFS_IOC_DATASET_LIST_NEXT,
ZFS_IOC_SNAPSHOT_LIST_NEXT,
ZFS_IOC_SET_PROP,
ZFS_IOC_CREATE,
ZFS_IOC_DESTROY,
ZFS_IOC_ROLLBACK,
ZFS_IOC_RENAME,
ZFS_IOC_RECV,
ZFS_IOC_SEND,
ZFS_IOC_INJECT_FAULT,
ZFS_IOC_CLEAR_FAULT,
ZFS_IOC_INJECT_LIST_NEXT,
ZFS_IOC_ERROR_LOG,
ZFS_IOC_CLEAR,
ZFS_IOC_PROMOTE,
ZFS_IOC_SNAPSHOT,
ZFS_IOC_DSOBJ_TO_DSNAME,
ZFS_IOC_OBJ_TO_PATH,
ZFS_IOC_POOL_SET_PROPS,
ZFS_IOC_POOL_GET_PROPS,
ZFS_IOC_SET_FSACL,
ZFS_IOC_GET_FSACL,
ZFS_IOC_SHARE,
2009-07-03 02:44:48 +04:00
ZFS_IOC_INHERIT_PROP,
ZFS_IOC_SMB_ACL,
ZFS_IOC_USERSPACE_ONE,
ZFS_IOC_USERSPACE_MANY,
2009-08-18 22:43:27 +04:00
ZFS_IOC_USERSPACE_UPGRADE,
ZFS_IOC_HOLD,
ZFS_IOC_RELEASE,
ZFS_IOC_GET_HOLDS,
ZFS_IOC_OBJSET_RECVD_PROPS,
ZFS_IOC_VDEV_SPLIT,
ZFS_IOC_NEXT_OBJ,
ZFS_IOC_DIFF,
ZFS_IOC_TMP_SNAPSHOT,
Add linux events This topic branch leverages the Solaris style FMA call points in ZFS to create a user space visible event notification system under Linux. This new system is called zevent and it unifies all previous Solaris style ereports and sysevent notifications. Under this Linux specific scheme when a sysevent or ereport event occurs an nvlist describing the event is created which looks almost exactly like a Solaris ereport. These events are queued up in the kernel when they occur and conditionally logged to the console. It is then up to a user space application to consume the events and do whatever it likes with them. To make this possible the existing /dev/zfs ABI has been extended with two new ioctls which behave as follows. * ZFS_IOC_EVENTS_NEXT Get the next pending event. The kernel will keep track of the last event consumed by the file descriptor and provide the next one if available. If no new events are available the ioctl() will block waiting for the next event. This ioctl may also be called in a non-blocking mode by setting zc.zc_guid = ZEVENT_NONBLOCK. In the non-blocking case if no events are available ENOENT will be returned. It is possible that ESHUTDOWN will be returned if the ioctl() is called while module unloading is in progress. And finally ENOMEM may occur if the provided nvlist buffer is not large enough to contain the entire event. * ZFS_IOC_EVENTS_CLEAR Clear are events queued by the kernel. The kernel will keep a fairly large number of recent events queued, use this ioctl to clear the in kernel list. This will effect all user space processes consuming events. The zpool command has been extended to use this events ABI with the 'events' subcommand. You may run 'zpool events -v' to output a verbose log of all recent events. This is very similar to the Solaris 'fmdump -ev' command with the key difference being it also includes what would be considered sysevents under Solaris. You may also run in follow mode with the '-f' option. To clear the in kernel event queue use the '-c' option. $ sudo cmd/zpool/zpool events -fv TIME CLASS May 13 2010 16:31:15.777711000 ereport.fs.zfs.config.sync class = "ereport.fs.zfs.config.sync" ena = 0x40982b7897700001 detector = (embedded nvlist) version = 0x0 scheme = "zfs" pool = 0xed976600de75dfa6 (end detector) time = 0x4bec8bc3 0x2e5aed98 pool = "zpios" pool_guid = 0xed976600de75dfa6 pool_context = 0x0 While the 'zpool events' command is handy for interactive debugging it is not expected to be the primary consumer of zevents. This ABI was primarily added to facilitate the addition of a user space monitoring daemon. This daemon would consume all events posted by the kernel and based on the type of event perform an action. For most events simply forwarding them on to syslog is likely enough. But this interface also cleanly allows for more sophisticated actions to be taken such as generating an email for a failed drive. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
2010-08-26 22:42:43 +04:00
ZFS_IOC_OBJ_TO_STATS,
ZFS_IOC_SPACE_WRITTEN,
ZFS_IOC_SPACE_SNAPS,
ZFS_IOC_DESTROY_SNAPS,
ZFS_IOC_POOL_REGUID,
ZFS_IOC_POOL_REOPEN,
ZFS_IOC_SEND_PROGRESS,
Illumos #2882, #2883, #2900 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/2882 https://www.illumos.org/issues/2883 https://www.illumos.org/issues/2900 illumos/illumos-gate@4445fffbbb1ea25fd0e9ea68b9380dd7a6709025 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.
2013-08-28 15:45:09 +04:00
ZFS_IOC_LOG_HISTORY,
ZFS_IOC_SEND_NEW,
ZFS_IOC_SEND_SPACE,
ZFS_IOC_CLONE,
ZFS_IOC_BOOKMARK,
ZFS_IOC_GET_BOOKMARKS,
ZFS_IOC_DESTROY_BOOKMARKS,
ZFS_IOC_RECV_NEW,
ZFS_IOC_POOL_SYNC,
/*
* Linux - 3/64 numbers reserved.
*/
ZFS_IOC_LINUX = ('Z' << 8) + 0x80,
ZFS_IOC_EVENTS_NEXT,
ZFS_IOC_EVENTS_CLEAR,
ZFS_IOC_EVENTS_SEEK,
/*
* FreeBSD - 1/64 numbers reserved.
*/
ZFS_IOC_FREEBSD = ('Z' << 8) + 0xC0,
Illumos #2882, #2883, #2900 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/2882 https://www.illumos.org/issues/2883 https://www.illumos.org/issues/2900 illumos/illumos-gate@4445fffbbb1ea25fd0e9ea68b9380dd7a6709025 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.
2013-08-28 15:45:09 +04:00
ZFS_IOC_LAST
2008-11-20 23:01:55 +03:00
} zfs_ioc_t;
/*
* zvol ioctl to get dataset name
*/
#define BLKZNAME _IOR(0x12, 125, char[ZFS_MAX_DATASET_NAME_LEN])
2008-11-20 23:01:55 +03:00
/*
* Internal SPA load state. Used by FMA diagnosis engine.
*/
typedef enum {
SPA_LOAD_NONE, /* no load in progress */
SPA_LOAD_OPEN, /* normal open */
SPA_LOAD_IMPORT, /* import in progress */
SPA_LOAD_TRYIMPORT, /* tryimport in progress */
SPA_LOAD_RECOVER, /* recovery requested */
OpenZFS 7090 - zfs should throttle allocations OpenZFS 7090 - zfs should throttle allocations Authored by: George Wilson <george.wilson@delphix.com> Reviewed by: Alex Reece <alex@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Reviewed by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Paul Dagnelie <paul.dagnelie@delphix.com> Reviewed by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Sebastien Roy <sebastien.roy@delphix.com> Approved by: Matthew Ahrens <mahrens@delphix.com> Ported-by: Don Brady <don.brady@intel.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> When write I/Os are issued, they are issued in block order but the ZIO pipeline will drive them asynchronously through the allocation stage which can result in blocks being allocated out-of-order. It would be nice to preserve as much of the logical order as possible. In addition, the allocations are equally scattered across all top-level VDEVs but not all top-level VDEVs are created equally. The pipeline should be able to detect devices that are more capable of handling allocations and should allocate more blocks to those devices. This allows for dynamic allocation distribution when devices are imbalanced as fuller devices will tend to be slower than empty devices. The change includes a new pool-wide allocation queue which would throttle and order allocations in the ZIO pipeline. The queue would be ordered by issued time and offset and would provide an initial amount of allocation of work to each top-level vdev. The allocation logic utilizes a reservation system to reserve allocations that will be performed by the allocator. Once an allocation is successfully completed it's scheduled on a given top-level vdev. Each top-level vdev maintains a maximum number of allocations that it can handle (mg_alloc_queue_depth). The pool-wide reserved allocations (top-levels * mg_alloc_queue_depth) are distributed across the top-level vdevs metaslab groups and round robin across all eligible metaslab groups to distribute the work. As top-levels complete their work, they receive additional work from the pool-wide allocation queue until the allocation queue is emptied. OpenZFS-issue: https://www.illumos.org/issues/7090 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/4756c3d7 Closes #5258 Porting Notes: - Maintained minimal stack in zio_done - Preserve linux-specific io sizes in zio_write_compress - Added module params and documentation - Updated to use optimize AVL cmp macros
2016-10-14 03:59:18 +03:00
SPA_LOAD_ERROR, /* load failed */
SPA_LOAD_CREATE /* creation in progress */
2008-11-20 23:01:55 +03:00
} spa_load_state_t;
/*
* Bookmark name values.
*/
#define ZPOOL_ERR_LIST "error list"
#define ZPOOL_ERR_DATASET "dataset"
#define ZPOOL_ERR_OBJECT "object"
#define HIS_MAX_RECORD_LEN (MAXPATHLEN + MAXPATHLEN + 1)
/*
* The following are names used in the nvlist describing
* the pool's history log.
*/
#define ZPOOL_HIST_RECORD "history record"
#define ZPOOL_HIST_TIME "history time"
#define ZPOOL_HIST_CMD "history command"
#define ZPOOL_HIST_WHO "history who"
#define ZPOOL_HIST_ZONE "history zone"
#define ZPOOL_HIST_HOST "history hostname"
#define ZPOOL_HIST_TXG "history txg"
#define ZPOOL_HIST_INT_EVENT "history internal event"
#define ZPOOL_HIST_INT_STR "history internal str"
Illumos #2882, #2883, #2900 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/2882 https://www.illumos.org/issues/2883 https://www.illumos.org/issues/2900 illumos/illumos-gate@4445fffbbb1ea25fd0e9ea68b9380dd7a6709025 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.
2013-08-28 15:45:09 +04:00
#define ZPOOL_HIST_INT_NAME "internal_name"
#define ZPOOL_HIST_IOCTL "ioctl"
#define ZPOOL_HIST_INPUT_NVL "in_nvl"
#define ZPOOL_HIST_OUTPUT_NVL "out_nvl"
#define ZPOOL_HIST_DSNAME "dsname"
#define ZPOOL_HIST_DSID "dsid"
2008-11-20 23:01:55 +03:00
/*
* Flags for ZFS_IOC_VDEV_SET_STATE
*/
#define ZFS_ONLINE_CHECKREMOVE 0x1
#define ZFS_ONLINE_UNSPARE 0x2
#define ZFS_ONLINE_FORCEFAULT 0x4
2009-07-03 02:44:48 +04:00
#define ZFS_ONLINE_EXPAND 0x8
2008-11-20 23:01:55 +03:00
#define ZFS_OFFLINE_TEMPORARY 0x1
/*
* Flags for ZFS_IOC_POOL_IMPORT
*/
#define ZFS_IMPORT_NORMAL 0x0
#define ZFS_IMPORT_VERBATIM 0x1
#define ZFS_IMPORT_ANY_HOST 0x2
#define ZFS_IMPORT_MISSING_LOG 0x4
#define ZFS_IMPORT_ONLY 0x8
#define ZFS_IMPORT_TEMP_NAME 0x10
2008-11-20 23:01:55 +03:00
/*
* Sysevent payload members. ZFS will generate the following sysevents with the
* given payloads:
*
* ESC_ZFS_RESILVER_START
* ESC_ZFS_RESILVER_END
* ESC_ZFS_POOL_DESTROY
* ESC_ZFS_POOL_REGUID
2008-11-20 23:01:55 +03:00
*
* ZFS_EV_POOL_NAME DATA_TYPE_STRING
* ZFS_EV_POOL_GUID DATA_TYPE_UINT64
*
* ESC_ZFS_VDEV_REMOVE
* ESC_ZFS_VDEV_CLEAR
* ESC_ZFS_VDEV_CHECK
*
* ZFS_EV_POOL_NAME DATA_TYPE_STRING
* ZFS_EV_POOL_GUID DATA_TYPE_UINT64
* ZFS_EV_VDEV_PATH DATA_TYPE_STRING (optional)
* ZFS_EV_VDEV_GUID DATA_TYPE_UINT64
*/
#define ZFS_EV_POOL_NAME "pool_name"
#define ZFS_EV_POOL_GUID "pool_guid"
#define ZFS_EV_VDEV_PATH "vdev_path"
#define ZFS_EV_VDEV_GUID "vdev_guid"
#ifdef __cplusplus
}
#endif
#endif /* _SYS_FS_ZFS_H */