aboutsummaryrefslogtreecommitdiffstats
path: root/module/zfs/spa.c
Commit message (Collapse)AuthorAgeFilesLines
* Add trim support to zpool waitBrian Behlendorf2020-03-041-18/+29
| | | | | | | | | | | | Manual trims fall into the category of long-running pool activities which people might want to wait synchronously for. This change adds support to 'zpool wait' for waiting for manual trim operations to complete. It also adds a '-w' flag to 'zpool trim' which can be used to turn 'zpool trim' into a synchronous operation. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Signed-off-by: John Gallagher <[email protected]> Closes #10071
* Improve zfs destroy performance with zio_t-free zio_free()Matthew Ahrens2020-02-281-3/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | When "zfs destroy" is run, it completes quickly, and in the background we locate the blocks to free and free them. This background activity can be observed with `zpool get freeing` and `zpool wait -t free ...`. This background activity is processed by a single thread (the spa_sync thread) which calls zio_free() on each of the blocks to free. With even modest storage performance, the CPU consumption of zio_free() can be the performance bottleneck. Performance of zio_free() can be improved by not actually creating a zio_t in the common case (non-dedup, non-gang), instead calling metaslab_free() directly. This avoids the CPU cost of allocating the zio_t, and more importantly the cost of adding and later removing this zio_t from the parent zio's child list. The result is that performance of background freeing more than doubles, from 0.6 million blocks per second to 1.3 million blocks per second. Reviewed-by: Paul Dagnelie <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: George Wilson <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes #10034
* async zvol minor node creation interferes with receiveMatthew Ahrens2020-02-031-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When we finish a zfs receive, dmu_recv_end_sync() calls zvol_create_minors(async=TRUE). This kicks off some other threads that create the minor device nodes (in /dev/zvol/poolname/...). These async threads call zvol_prefetch_minors_impl() and zvol_create_minor(), which both call dmu_objset_own(), which puts a "long hold" on the dataset. Since the zvol minor node creation is asynchronous, this can happen after the `ZFS_IOC_RECV[_NEW]` ioctl and `zfs receive` process have completed. After the first receive ioctl has completed, userland may attempt to do another receive into the same dataset (e.g. the next incremental stream). This second receive and the asynchronous minor node creation can interfere with one another in several different ways, because they both require exclusive access to the dataset: 1. When the second receive is finishing up, dmu_recv_end_check() does dsl_dataset_handoff_check(), which can fail with EBUSY if the async minor node creation already has a "long hold" on this dataset. This causes the 2nd receive to fail. 2. The async udev rule can fail if zvol_id and/or systemd-udevd try to open the device while the the second receive's async attempt at minor node creation owns the dataset (via zvol_prefetch_minors_impl). This causes the minor node (/dev/zd*) to exist, but the udev-generated /dev/zvol/... to not exist. 3. The async minor node creation can silently fail with EBUSY if the first receive's zvol_create_minor() trys to own the dataset while the second receive's zvol_prefetch_minors_impl already owns the dataset. To address these problems, this change synchronously creates the minor node. To avoid the lock ordering problems that the asynchrony was introduced to fix (see #3681), we create the minor nodes from open context, with no locks held, rather than from syncing contex as was originally done. Implementation notes: We generally do not need to traverse children or prefetch anything (e.g. when running the recv, snapshot, create, or clone subcommands of zfs). We only need recursion when importing/opening a pool and when loading encryption keys. The existing recursive, asynchronous, prefetching code is preserved for use in these cases. Channel programs may need to create zvol minor nodes, when creating a snapshot of a zvol with the snapdev property set. We figure out what snapshots are created when running the LUA program in syncing context. In this case we need to remember what snapshots were created, and then try to create their minor nodes from open context, after the LUA code has completed. There are additional zvol use cases that asynchronously own the dataset, which can cause similar problems. E.g. changing the volmode or snapdev properties. These are less problematic because they are not recursive and don't touch datasets that are not involved in the operation, there is still potential for interference with subsequent operations. In the future, these cases should be similarly converted to create the zvol minor node synchronously from open context. The async tasks of removing and renaming minors do not own the objset, so they do not have this problem. However, it may make sense to also convert these operations to happen synchronously from open context, in the future. Reviewed-by: Paul Dagnelie <[email protected]> Reviewed-by: Prakash Surya <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> External-issue: DLPX-65948 Closes #7863 Closes #9885
* Fix "zpool add -n" for dedup, special and log devicesloli10K2020-01-061-1/+1
| | | | | | | | | | | | | | | | | | | | For dedup, special and log devices "zpool add -n" does not print correctly their vdev type: ~# zpool add -n pool dedup /tmp/dedup special /tmp/special log /tmp/log would update 'pool' to the following configuration: pool /tmp/normal /tmp/dedup /tmp/special /tmp/log This could lead storage administrators to modify their ZFS pools to unexpected and unintended vdev configurations. Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: loli10K <[email protected]> Closes #9783 Closes #9390
* Replace ASSERTV macro with compiler annotationMatthew Macy2019-12-051-5/+5
| | | | | | | | | | | Remove the ASSERTV macro and handle suppressing unused compiler warnings for variables only in ASSERTs using the __attribute__((unused)) compiler annotation. The annotation is understood by both gcc and clang. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Jorgen Lundman <[email protected]> Signed-off-by: Matt Macy <[email protected]> Closes #9671
* Prevent unnecessary resilver restartsjwpoduska2019-11-271-4/+10
| | | | | | | | | | | | | | | | | | If a device is participating in an active resilver, then it will have a non-empty DTL. Operations like vdev_{open,reopen,probe}() can cause the resilver to be restarted (or deferred to be restarted later), which is unnecessary if the DTL is still covered by the current scan range. This is similar to the logic in vdev_dtl_should_excise() where the DTL can only be excised if it's max txg is in the resilvered range. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: John Gallagher <[email protected]> Reviewed-by: Kjeld Schouten <[email protected]> Signed-off-by: John Poduska <[email protected]> Issue #840 Closes #9155 Closes #9378 Closes #9551 Closes #9588
* Add zfs_file_* interface, remove vnodesMatthew Macy2019-11-211-11/+10
| | | | | | | | | | | | | | | | | | Provide a common zfs_file_* interface which can be implemented on all platforms to perform normal file access from either the kernel module or the libzpool library. This allows all non-portable vnode_t usage in the common code to be replaced by the new portable zfs_file_t. The associated vnode and kobj compatibility functions, types, and macros have been removed from the SPL. Moving forward, vnodes should only be used in platform specific code when provided by the native operating system. Reviewed-by: Sean Eric Fagan <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Igor Kozhukhov <[email protected]> Reviewed-by: Jorgen Lundman <[email protected]> Signed-off-by: Matt Macy <[email protected]> Closes #9556
* Minor spa portability fixesMatthew Macy2019-10-281-3/+3
| | | | | | | | | | | | - FreeBSD's rootpool import code uses spa_config_parse - Move the zvol_create_minors call out from under the spa_namespace_lock in spa_import. It isn't needed and it causes a lock order reversal on FreeBSD. Reviewed-by: Igor Kozhukhov <[email protected]> Reviewed-by: Jorgen Lundman <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matt Macy <[email protected]> Closes #9499
* Fix pool creation with feature@allocation_classes disabledloli10K2019-10-101-0/+10
| | | | | | | | | | | When "feature@allocation_classes" is not enabled on the pool no vdev with "special" or "dedup" allocation type should be allowed to exist in the vdev tree. Reviewed-by: Pavel Zakharov <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: loli10K <[email protected]> Closes #9427 Closes #9429
* Reduce loaded range tree memory usagePaul Dagnelie2019-10-091-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch implements a new tree structure for ZFS, and uses it to store range trees more efficiently. The new structure is approximately a B-tree, though there are some small differences from the usual characterizations. The tree has core nodes and leaf nodes; each contain data elements, which the elements in the core nodes acting as separators between its children. The difference between core and leaf nodes is that the core nodes have an array of children, while leaf nodes don't. Every node in the tree may be only partially full; in most cases, they are all at least 50% full (in terms of element count) except for the root node, which can be less full. Underfull nodes will steal from their neighbors or merge to remain full enough, while overfull nodes will split in two. The data elements are contained in tree-controlled buffers; they are copied into these on insertion, and overwritten on deletion. This means that the elements are not independently allocated, which reduces overhead, but also means they can't be shared between trees (and also that pointers to them are only valid until a side-effectful tree operation occurs). The overhead varies based on how dense the tree is, but is usually on the order of about 50% of the element size; the per-node overheads are very small, and so don't make a significant difference. The trees can accept arbitrary records; they accept a size and a comparator to allow them to be used for a variety of purposes. The new trees replace the AVL trees used in the range trees today. Currently, the range_seg_t structure contains three 8 byte integers of payload and two 24 byte avl_tree_node_ts to handle its storage in both an offset-sorted tree and a size-sorted tree (total size: 64 bytes). In the new model, the range seg structures are usually two 4 byte integers, but a separate one needs to exist for the size-sorted and offset-sorted tree. Between the raw size, the 50% overhead, and the double storage, the new btrees are expected to use 8*1.5*2 = 24 bytes per record, or 33.3% as much memory as the AVL trees (this is for the purposes of storing metaslab range trees; for other purposes, like scrubs, they use ~50% as much memory). We reduced the size of the payload in the range segments by teaching range trees about starting offsets and shifts; since metaslabs have a fixed starting offset, and they all operate in terms of disk sectors, we can store the ranges using 4-byte integers as long as the size of the metaslab divided by the sector size is less than 2^32. For 512-byte sectors, this is a 2^41 (or 2TB) metaslab, which with the default settings corresponds to a 256PB disk. 4k sector disks can handle metaslabs up to 2^46 bytes, or 2^63 byte disks. Since we do not anticipate disks of this size in the near future, there should be almost no cases where metaslabs need 64-byte integers to store their ranges. We do still have the capability to store 64-byte integer ranges to account for cases where we are storing per-vdev (or per-dnode) trees, which could reasonably go above the limits discussed. We also do not store fill information in the compact version of the node, since it is only used for sorted scrub. We also optimized the metaslab loading process in various other ways to offset some inefficiencies in the btree model. While individual operations (find, insert, remove_from) are faster for the btree than they are for the avl tree, remove usually requires a find operation, while in the AVL tree model the element itself suffices. Some clever changes actually caused an overall speedup in metaslab loading; we use approximately 40% less cpu to load metaslabs in our tests on Illumos. Another memory and performance optimization was achieved by changing what is stored in the size-sorted trees. When a disk is heavily fragmented, the df algorithm used by default in ZFS will almost always find a number of small regions in its initial cursor-based search; it will usually only fall back to the size-sorted tree to find larger regions. If we increase the size of the cursor-based search slightly, and don't store segments that are smaller than a tunable size floor in the size-sorted tree, we can further cut memory usage down to below 20% of what the AVL trees store. This also results in further reductions in CPU time spent loading metaslabs. The 16KiB size floor was chosen because it results in substantial memory usage reduction while not usually resulting in situations where we can't find an appropriate chunk with the cursor and are forced to use an oversized chunk from the size-sorted tree. In addition, even if we do have to use an oversized chunk from the size-sorted tree, the chunk would be too small to use for ZIL allocations, so it isn't as big of a loss as it might otherwise be. And often, more small allocations will follow the initial one, and the cursor search will now find the remainder of the chunk we didn't use all of and use it for subsequent allocations. Practical testing has shown little or no change in fragmentation as a result of this change. If the size-sorted tree becomes empty while the offset sorted one still has entries, it will load all the entries from the offset sorted tree and disregard the size floor until it is unloaded again. This operation occurs rarely with the default setting, only on incredibly thoroughly fragmented pools. There are some other small changes to zdb to teach it to handle btrees, but nothing major. Reviewed-by: George Wilson <[email protected]> Reviewed-by: Matt Ahrens <[email protected]> Reviewed by: Sebastien Roy [email protected] Reviewed-by: Igor Kozhukhov <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Paul Dagnelie <[email protected]> Closes #9181
* Prevent gcc -Werror=maybe-uninitialized warnings in spa_wait_common()loli10K2019-09-161-1/+1
| | | | | | | | | | | | | | | | | This commit fixes the following build failure detected on Debian9 (GCC 6.3.0): CC [M] module/zfs/spa.o module/zfs/spa.c: In function ‘spa_wait_common.part.31’: module/zfs/spa.c:9468:6: error: ‘in_progress’ may be used uninitialized in this function [-Werror=maybe-uninitialized] if (!in_progress || spa->spa_waiters_cancel || error) ^ cc1: all warnings being treated as errors Reviewed-by: Chris Dunlop <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: John Gallagher <[email protected]> Signed-off-by: loli10K <[email protected]> Closes #9326
* Add subcommand to wait for background zfs activity to completeJohn Gallagher2019-09-131-0/+277
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently the best way to wait for the completion of a long-running operation in a pool, like a scrub or device removal, is to poll 'zpool status' and parse its output, which is neither efficient nor convenient. This change adds a 'wait' subcommand to the zpool command. When invoked, 'zpool wait' will block until a specified type of background activity completes. Currently, this subcommand can wait for any of the following: - Scrubs or resilvers to complete - Devices to initialized - Devices to be replaced - Devices to be removed - Checkpoints to be discarded - Background freeing to complete For example, a scrub that is in progress could be waited for by running zpool wait -t scrub <pool> This also adds a -w flag to the attach, checkpoint, initialize, replace, remove, and scrub subcommands. When used, this flag makes the operations kicked off by these subcommands synchronous instead of asynchronous. This functionality is implemented using a new ioctl. The type of activity to wait for is provided as input to the ioctl, and the ioctl blocks until all activity of that type has completed. An ioctl was used over other methods of kernel-userspace communiction primarily for the sake of portability. Porting Notes: This is ported from Delphix OS change DLPX-44432. The following changes were made while porting: - Added ZoL-style ioctl input declaration. - Reorganized error handling in zpool_initialize in libzfs to integrate better with changes made for TRIM support. - Fixed check for whether a checkpoint discard is in progress. Previously it also waited if the pool had a checkpoint, instead of just if a checkpoint was being discarded. - Exposed zfs_initialize_chunk_size as a ZoL-style tunable. - Updated more existing tests to make use of new 'zpool wait' functionality, tests that don't exist in Delphix OS. - Used existing ZoL tunable zfs_scan_suspend_progress, together with zinject, in place of a new tunable zfs_scan_max_blks_per_txg. - Added support for a non-integral interval argument to zpool wait. Future work: ZoL has support for trimming devices, which Delphix OS does not. In the future, 'zpool wait' could be extended to add the ability to wait for trim operations to complete. Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: John Kennedy <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: John Gallagher <[email protected]> Closes #9162
* Enable compiler to typecheck loggingMatthew Macy2019-09-121-4/+7
| | | | | | | | | | Annotate spa logging declarations with printflike Workaround gcc bug (non disable-able warning) by replacing "" with " " Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matt Macy <[email protected]> Closes #9316
* Fix /etc/hostid on root pool deadlockBrian Behlendorf2019-09-101-5/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Accidentally introduced by dc04a8c which now takes the SCL_VDEV lock as a reader in zfs_blkptr_verify(). A deadlock can occur if the /etc/hostid file resides on a dataset in the same pool. This is because reading the /etc/hostid file may occur while the caller is holding the SCL_VDEV lock as a writer. For example, to perform a `zpool attach` as shown in the abbreviated stack below. To resolve the issue we cache the system's hostid when initializing the spa_t, or when modifying the multihost property. The cached value is then relied upon for subsequent accesses. Call Trace: spa_config_enter+0x1e8/0x350 [zfs] zfs_blkptr_verify+0x33c/0x4f0 [zfs] <--- trying read lock zio_read+0x6c/0x140 [zfs] ... vfs_read+0xfc/0x1e0 kernel_read+0x50/0x90 ... spa_get_hostid+0x1c/0x38 [zfs] spa_config_generate+0x1a0/0x610 [zfs] vdev_label_init+0xa0/0xc80 [zfs] vdev_create+0x98/0xe0 [zfs] spa_vdev_attach+0x14c/0xb40 [zfs] <--- grabbed write lock Reviewed-by: loli10K <[email protected]> Signed-off-by: Brian Behlendorf <[email protected]> Closes #9256 Closes #9285
* Make module tunables cross platformMatthew Macy2019-09-051-36/+19
| | | | | | | | | | | Adds ZFS_MODULE_PARAM to abstract module parameter setting to operating systems other than Linux. Reviewed-by: Jorgen Lundman <[email protected]> Reviewed-by: Igor Kozhukhov <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matt Macy <[email protected]> Signed-off-by: Ryan Moeller <[email protected]> Closes #9230
* maxinflight can overflow in spa_load_verify_cb()George Wilson2019-09-021-1/+2
| | | | | | | | | | When running on larger memory systems, we can overflow the value of maxinflight. This can result in maxinflight having a value of 0 causing the system to hang. Reviewed-by: Igor Kozhukhov <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: George Wilson <[email protected]> Closes #9272
* Fix typos in module/zfs/Andrea Gelmini2019-09-021-6/+6
| | | | | | | | Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: Ryan Moeller <[email protected]> Reviewed-by: Richard Laager <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Andrea Gelmini <[email protected]> Closes #9240
* Cap metaslab memory usagePaul Dagnelie2019-08-161-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | On systems with large amounts of storage and high fragmentation, a huge amount of space can be used by storing metaslab range trees. Since metaslabs are only unloaded during a txg sync, and only if they have been inactive for 8 txgs, it is possible to get into a state where all of the system's memory is consumed by range trees and metaslabs, and txgs cannot sync. While ZFS knows how to evict ARC data when needed, it has no such mechanism for range tree data. This can result in boot hangs for some system configurations. First, we add the ability to unload metaslabs outside of syncing context. Second, we store a multilist of all loaded metaslabs, sorted by their selection txg, so we can quickly identify the oldest metaslabs. We use a multilist to reduce lock contention during heavy write workloads. Finally, we add logic that will unload a metaslab when we're loading a new metaslab, if we're using more than a certain fraction of the available memory on range trees. Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: George Wilson <[email protected]> Reviewed-by: Sebastien Roy <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Paul Dagnelie <[email protected]> Closes #9128
* spa_load_verify() may consume too much memoryGeorge Wilson2019-08-131-9/+15
| | | | | | | | | | | | | | | | | | | | When a pool is imported it will scan the pool to verify the integrity of the data and metadata. The amount it scans will depend on the import flags provided. On systems with small amounts of memory or when importing a pool from the crash kernel, it's possible for spa_load_verify to issue too many I/Os that it consumes all the memory of the system resulting in an OOM message or a hang. To prevent this, we limit the amount of memory that the initial pool scan can consume. This change will, by default, use 1/16th of the ARC for scan I/Os to prevent running the system out of memory during import. Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Signed-off-by: George Wilson [email protected] External-issue: DLPX-65237 External-issue: DLPX-65238 Closes #9146
* Fast Clone DeletionSara Hartse2019-07-261-13/+486
| | | | | | | | | | | | | | | | | | | | | Deleting a clone requires finding blocks are clone-only, not shared with the snapshot. This was done by traversing the entire block tree which results in a large performance penalty for sparsely written clones. This is new method keeps track of clone blocks when they are modified in a "Livelist" so that, when it’s time to delete, the clone-specific blocks are already at hand. We see performance improvements because now deletion work is proportional to the number of clone-modified blocks, not the size of the original dataset. Reviewed-by: Sean Eric Fagan <[email protected]> Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Signed-off-by: Sara Hartse <[email protected]> Closes #8416
* Race condition between spa async threads and exportSerapheim Dimitropoulos2019-07-181-1/+17
| | | | | | | | | | | | | | | | | | In the past we've seen multiple race conditions that have to do with open-context threads async threads and concurrent calls to spa_export()/spa_destroy() (including the one referenced in issue #9015). This patch ensures that only one thread can execute the main body of spa_export_common() at a time, with subsequent threads returning with a new error code created just for this situation, eliminating this way any race condition bugs introduced by concurrent calls to this function. Reviewed by: Matt Ahrens <[email protected]> Reviewed by: Brian Behlendorf <[email protected]> Signed-off-by: Serapheim Dimitropoulos <[email protected]> Closes #9015 Closes #9044
* Log Spacemap ProjectSerapheim Dimitropoulos2019-07-161-25/+128
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | = Motivation At Delphix we've seen a lot of customer systems where fragmentation is over 75% and random writes take a performance hit because a lot of time is spend on I/Os that update on-disk space accounting metadata. Specifically, we seen cases where 20% to 40% of sync time is spend after sync pass 1 and ~30% of the I/Os on the system is spent updating spacemaps. The problem is that these pools have existed long enough that we've touched almost every metaslab at least once, and random writes scatter frees across all metaslabs every TXG, thus appending to their spacemaps and resulting in many I/Os. To give an example, assuming that every VDEV has 200 metaslabs and our writes fit within a single spacemap block (generally 4K) we have 200 I/Os. Then if we assume 2 levels of indirection, we need 400 additional I/Os and since we are talking about metadata for which we keep 2 extra copies for redundancy we need to triple that number, leading to a total of 1800 I/Os per VDEV every TXG. We could try and decrease the number of metaslabs so we have less I/Os per TXG but then each metaslab would cover a wider range on disk and thus would take more time to be loaded in memory from disk. In addition, after it's loaded, it's range tree would consume more memory. Another idea would be to just increase the spacemap block size which would allow us to fit more entries within an I/O block resulting in fewer I/Os per metaslab and a speedup in loading time. The problem is still that we don't deal with the number of I/Os going up as the number of metaslabs is increasing and the fact is that we generally write a lot to a few metaslabs and a little to the rest of them. Thus, just increasing the block size would actually waste bandwidth because we won't be utilizing our bigger block size. = About this patch This patch introduces the Log Spacemap project which provides the solution to the above problem while taking into account all the aforementioned tradeoffs. The details on how it achieves that can be found in the references sections below and in the code (see Big Theory Statement in spa_log_spacemap.c). Even though the change is fairly constraint within the metaslab and lower-level SPA codepaths, there is a side-change that is user-facing. The change is that VDEV IDs from VDEV holes will no longer be reused. To give some background and reasoning for this, when a log device is removed and its VDEV structure was replaced with a hole (or was compacted; if at the end of the vdev array), its vdev_id could be reused by devices added after that. Now with the pool-wide space maps recording the vdev ID, this behavior can cause problems (e.g. is this entry referring to a segment in the new vdev or the removed log?). Thus, to simplify things the ID reuse behavior is gone and now vdev IDs for top-level vdevs are truly unique within a pool. = Testing The illumos implementation of this feature has been used internally for a year and has been in production for ~6 months. For this patch specifically there don't seem to be any regressions introduced to ZTS and I have been running zloop for a week without any related problems. = Performance Analysis (Linux Specific) All performance results and analysis for illumos can be found in the links of the references. Redoing the same experiments in Linux gave similar results. Below are the specifics of the Linux run. After the pool reached stable state the percentage of the time spent in pass 1 per TXG was 64% on average for the stock bits while the log spacemap bits stayed at 95% during the experiment (graph: sdimitro.github.io/img/linux-lsm/PercOfSyncInPassOne.png). Sync times per TXG were 37.6 seconds on average for the stock bits and 22.7 seconds for the log spacemap bits (related graph: sdimitro.github.io/img/linux-lsm/SyncTimePerTXG.png). As a result the log spacemap bits were able to push more TXGs, which is also the reason why all graphs quantified per TXG have more entries for the log spacemap bits. Another interesting aspect in terms of txg syncs is that the stock bits had 22% of their TXGs reach sync pass 7, 55% reach sync pass 8, and 20% reach 9. The log space map bits reached sync pass 4 in 79% of their TXGs, sync pass 7 in 19%, and sync pass 8 at 1%. This emphasizes the fact that not only we spend less time on metadata but we also iterate less times to convergence in spa_sync() dirtying objects. [related graphs: stock- sdimitro.github.io/img/linux-lsm/NumberOfPassesPerTXGStock.png lsm- sdimitro.github.io/img/linux-lsm/NumberOfPassesPerTXGLSM.png] Finally, the improvement in IOPs that the userland gains from the change is approximately 40%. There is a consistent win in IOPS as you can see from the graphs below but the absolute amount of improvement that the log spacemap gives varies within each minute interval. sdimitro.github.io/img/linux-lsm/StockVsLog3Days.png sdimitro.github.io/img/linux-lsm/StockVsLog10Hours.png = Porting to Other Platforms For people that want to port this commit to other platforms below is a list of ZoL commits that this patch depends on: Make zdb results for checkpoint tests consistent db587941c5ff6dea01932bb78f70db63cf7f38ba Update vdev_is_spacemap_addressable() for new spacemap encoding 419ba5914552c6185afbe1dd17b3ed4b0d526547 Simplify spa_sync by breaking it up to smaller functions 8dc2197b7b1e4d7ebc1420ea30e51c6541f1d834 Factor metaslab_load_wait() in metaslab_load() b194fab0fb6caad18711abccaff3c69ad8b3f6d3 Rename range_tree_verify to range_tree_verify_not_present df72b8bebe0ebac0b20e0750984bad182cb6564a Change target size of metaslabs from 256GB to 16GB c853f382db731e15a87512f4ef1101d14d778a55 zdb -L should skip leak detection altogether 21e7cf5da89f55ce98ec1115726b150e19eefe89 vs_alloc can underflow in L2ARC vdevs 7558997d2f808368867ca7e5234e5793446e8f3f Simplify log vdev removal code 6c926f426a26ffb6d7d8e563e33fc176164175cb Get rid of space_map_update() for ms_synced_length 425d3237ee88abc53d8522a7139c926d278b4b7f Introduce auxiliary metaslab histograms 928e8ad47d3478a3d5d01f0dd6ae74a9371af65e Error path in metaslab_load_impl() forgets to drop ms_sync_lock 8eef997679ba54547f7d361553d21b3291f41ae7 = References Background, Motivation, and Internals of the Feature - OpenZFS 2017 Presentation: youtu.be/jj2IxRkl5bQ - Slides: slideshare.net/SerapheimNikolaosDim/zfs-log-spacemaps-project Flushing Algorithm Internals & Performance Results (Illumos Specific) - Blogpost: sdimitro.github.io/post/zfs-lsm-flushing/ - OpenZFS 2018 Presentation: youtu.be/x6D2dHRjkxw - Slides: slideshare.net/SerapheimNikolaosDim/zfs-log-spacemap-flushing-algorithm Upstream Delphix Issues: DLPX-51539, DLPX-59659, DLPX-57783, DLPX-61438, DLPX-41227, DLPX-59320 DLPX-63385 Reviewed-by: Sean Eric Fagan <[email protected]> Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: George Wilson <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Serapheim Dimitropoulos <[email protected]> Closes #8442
* Remove dedupditto functionalityMatthew Ahrens2019-06-191-15/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If dedup is in use, the `dedupditto` property can be set, causing ZFS to keep an extra copy of data that is referenced many times (>100x). The idea was that this data is more important than other data and thus we want to be really sure that it is not lost if the disk experiences a small amount of random corruption. ZFS (and system administrators) rely on the pool-level redundancy to protect their data (e.g. mirroring or RAIDZ). Since the user/sysadmin doesn't have control over what data will be offered extra redundancy by dedupditto, this extra redundancy is not very useful. The bulk of the data is still vulnerable to loss based on the pool-level redundancy. For example, if particle strikes corrupt 0.1% of blocks, you will either be saved by mirror/raidz, or you will be sad. This is true even if dedupditto saved another 0.01% of blocks from being corrupted. Therefore, the dedupditto functionality is rarely enabled (i.e. the property is rarely set), and it fulfills its promise of increased redundancy even more rarely. Additionally, this feature does not work as advertised (on existing releases), because scrub/resilver did not repair the extra (dedupditto) copy (see https://github.com/zfsonlinux/zfs/pull/8270). In summary, this seldom-used feature doesn't work, and even if it did it wouldn't provide useful data protection. It has a non-trivial maintenance burden (again see https://github.com/zfsonlinux/zfs/pull/8270). We should remove the dedupditto functionality. For backwards compatibility with the existing CLI, "zpool set dedupditto" will still "succeed" (exit code zero), but won't have any effect. For backwards compatibility with existing pools that had dedupditto enabled at some point, the code will still be able to understand dedupditto blocks and free them when appropriate. However, ZFS won't write any new dedupditto blocks. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Igor Kozhukhov <[email protected]> Reviewed-by: Alek Pinchuk <[email protected]> Issue #8270 Closes #8310
* Implement Redacted Send/ReceivePaul Dagnelie2019-06-191-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Redacted send/receive allows users to send subsets of their data to a target system. One possible use case for this feature is to not transmit sensitive information to a data warehousing, test/dev, or analytics environment. Another is to save space by not replicating unimportant data within a given dataset, for example in backup tools like zrepl. Redacted send/receive is a three-stage process. First, a clone (or clones) is made of the snapshot to be sent to the target. In this clone (or clones), all unnecessary or unwanted data is removed or modified. This clone is then snapshotted to create the "redaction snapshot" (or snapshots). Second, the new zfs redact command is used to create a redaction bookmark. The redaction bookmark stores the list of blocks in a snapshot that were modified by the redaction snapshot(s). Finally, the redaction bookmark is passed as a parameter to zfs send. When sending to the snapshot that was redacted, the redaction bookmark is used to filter out blocks that contain sensitive or unwanted information, and those blocks are not included in the send stream. When sending from the redaction bookmark, the blocks it contains are considered as candidate blocks in addition to those blocks in the destination snapshot that were modified since the creation_txg of the redaction bookmark. This step is necessary to allow the target to rehydrate data in the case where some blocks are accidentally or unnecessarily modified in the redaction snapshot. The changes to bookmarks to enable fast space estimation involve adding deadlists to bookmarks. There is also logic to manage the life cycles of these deadlists. The new size estimation process operates in cases where previously an accurate estimate could not be provided. In those cases, a send is performed where no data blocks are read, reducing the runtime significantly and providing a byte-accurate size estimate. Reviewed-by: Dan Kimmel <[email protected]> Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: Prashanth Sreenivasa <[email protected]> Reviewed-by: John Kennedy <[email protected]> Reviewed-by: George Wilson <[email protected]> Reviewed-by: Chris Williamson <[email protected]> Reviewed-by: Pavel Zhakarov <[email protected]> Reviewed-by: Sebastien Roy <[email protected]> Reviewed-by: Prakash Surya <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Paul Dagnelie <[email protected]> Closes #7958
* zpool import progress kstatOlaf Faaland2019-05-091-2/+24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | When an import requires a long MMP activity check, or when the user requests pool recovery, the import make take a long time. The user may not know why, or be able to tell whether the import is progressing or is hung. Add a kstat which lists all imports currently being processed by the kernel (currently only one at a time is possible, but the kstat allows for more than one). The kstat is /proc/spl/kstat/zfs/import_progress. The kstat contents are as follows: pool_guid load_state multihost_secs max_txg pool_name 16667015954387398 3 15 0 tank3 load_state: the value of spa_load_state multihost_secs: seconds until the end of the multihost activity check; if over, or none required, this is 0 max_txg: current spa_load_max_txg, if rewind is occurring This could be used by outside tools, such as a pacemaker resource agent, to report import progress, or as a part of manual troubleshooting. The zpool import subcommand could also be modified to report this information. Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Olaf Faaland <[email protected]> Closes #8696
* Add feature check for 'zpool resilver' commandTom Caputi2019-05-021-0/+4
| | | | | | | | | | | | The 'zpool resilver' command requires that the resilver_defer feature is active on the pool. Unfortunately, the check for this was left out of the original patch. This commit simply corrects this so that the command properly returns an error in this case. Reviewed by: Brian Behlendorf <[email protected]> Reviewed-by: Igor Kozhukhov <[email protected]> Signed-off-by: Tom Caputi <[email protected]> Closes #8700
* Update a comment to match the codeRichard Laager2019-04-161-2/+2
| | | | | | | | | GRUB supports large_blocks. Reviewed-by: George Melikov <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Richard Laager <[email protected]> Closes #8626
* predictive prefetch disabled on new pools until export/rebootMatthew Ahrens2019-04-051-1/+2
| | | | | | | | | | | | | | | | | | | | | | When a pool is initially created (by `zpool create`), predictive prefetch is inadvertently disabled, until the pool is export/import-ed, or the machine is rebooted. When device removal was introduced, we added some code to disable predictive prefetching until indirect vdevs have been loaded. This resulted in the "default state" of prefetch being disabled, until we proactively enable it after indirect vdevs are loaded. Unfortunately this resulted in a few bugs where in some code paths we neglect to enable predictive prefetch. The first of these was fixed by https://github.com/zfsonlinux/zfs/commit/20507534d4ede14d4dd82c99fc8d461704ce7419 This commit fixes another case where we also need to explicitly enable predictive prefetch, when the pool is initially created. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Richard Elling <[email protected]> Reviewed-by: George Melikov <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes #8577
* Add TRIM supportBrian Behlendorf2019-03-291-21/+185
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | UNMAP/TRIM support is a frequently-requested feature to help prevent performance from degrading on SSDs and on various other SAN-like storage back-ends. By issuing UNMAP/TRIM commands for sectors which are no longer allocated the underlying device can often more efficiently manage itself. This TRIM implementation is modeled on the `zpool initialize` feature which writes a pattern to all unallocated space in the pool. The new `zpool trim` command uses the same vdev_xlate() code to calculate what sectors are unallocated, the same per- vdev TRIM thread model and locking, and the same basic CLI for a consistent user experience. The core difference is that instead of writing a pattern it will issue UNMAP/TRIM commands for those extents. The zio pipeline was updated to accommodate this by adding a new ZIO_TYPE_TRIM type and associated spa taskq. This new type makes is straight forward to add the platform specific TRIM/UNMAP calls to vdev_disk.c and vdev_file.c. These new ZIO_TYPE_TRIM zios are handled largely the same way as ZIO_TYPE_READs or ZIO_TYPE_WRITEs. This makes it possible to largely avoid changing the pipieline, one exception is that TRIM zio's may exceed the 16M block size limit since they contain no data. In addition to the manual `zpool trim` command, a background automatic TRIM was added and is controlled by the 'autotrim' property. It relies on the exact same infrastructure as the manual TRIM. However, instead of relying on the extents in a metaslab's ms_allocatable range tree, a ms_trim tree is kept per metaslab. When 'autotrim=on', ranges added back to the ms_allocatable tree are also added to the ms_free tree. The ms_free tree is then periodically consumed by an autotrim thread which systematically walks a top level vdev's metaslabs. Since the automatic TRIM will skip ranges it considers too small there is value in occasionally running a full `zpool trim`. This may occur when the freed blocks are small and not enough time was allowed to aggregate them. An automatic TRIM and a manual `zpool trim` may be run concurrently, in which case the automatic TRIM will yield to the manual TRIM. Reviewed-by: Jorgen Lundman <[email protected]> Reviewed-by: Tim Chase <[email protected]> Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: George Wilson <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Contributions-by: Saso Kiselkov <[email protected]> Contributions-by: Tim Chase <[email protected]> Contributions-by: Chunwei Chen <[email protected]> Signed-off-by: Brian Behlendorf <[email protected]> Closes #8419 Closes #598
* Panic when running 'zpool split'Roman Strashkin2019-03-221-0/+12
| | | | | | | | | | | Added missing remove of detachable VDEV from txg's DTL list to avoid use-after-free for the split VDEV Reviewed by: Pavel Zakharov <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Jorgen Lundman <[email protected]> Signed-off-by: Roman Strashkin <[email protected]> Closes #5565 Closes #7856
* MMP interval and fail_intervals in uberblockOlaf Faaland2019-03-211-26/+97
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When Multihost is enabled, and a pool is imported, uberblock writes include ub_mmp_delay to allow an importing node to calculate the duration of an activity test. This value, is not enough information. If zfs_multihost_fail_intervals > 0 on the node with the pool imported, the safe minimum duration of the activity test is well defined, but does not depend on ub_mmp_delay: zfs_multihost_fail_intervals * zfs_multihost_interval and if zfs_multihost_fail_intervals == 0 on that node, there is no such well defined safe duration, but the importing host cannot tell whether mmp_delay is high due to I/O delays, or due to a very large zfs_multihost_interval setting on the host which last imported the pool. As a result, it may use a far longer period for the activity test than is necessary. This patch renames ub_mmp_sequence to ub_mmp_config and uses it to record the zfs_multihost_interval and zfs_multihost_fail_intervals values, as well as the mmp sequence. This allows a shorter activity test duration to be calculated by the importing host in most situations. These values are also added to the multihost_history kstat records. It calculates the activity test duration differently depending on whether the new fields are present or not; for importing pools with only ub_mmp_delay, it uses (zfs_multihost_interval + ub_mmp_delay) * zfs_multihost_import_intervals Which results in an activity test duration less sensitive to the leaf count. In addition, it makes a few other improvements: * It updates the "sequence" part of ub_mmp_config when MMP writes in between syncs occur. This allows an importing host to detect MMP on the remote host sooner, when the pool is idle, as it is not limited to the granularity of ub_timestamp (1 second). * It issues writes immediately when zfs_multihost_interval is changed so remote hosts see the updated value as soon as possible. * It fixes a bug where setting zfs_multihost_fail_intervals = 1 results in immediate pool suspension. * Update tests to verify activity check duration is based on recorded tunable values, not tunable values on importing host. * Update tests to verify the expected number of uberblocks have valid MMP fields - fail_intervals, mmp_interval, mmp_seq (sequence number), that sequence number is incrementing, and that uberblock values match tunable settings. Reviewed-by: Andreas Dilger <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Tony Hutter <[email protected]> Signed-off-by: Olaf Faaland <[email protected]> Closes #7842
* Detect and prevent mixed raw and non-raw sendsTom Caputi2019-03-131-0/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently, there is an issue in the raw receive code where raw receives are allowed to happen on top of previously non-raw received datasets. This is a problem because the source-side dataset doesn't know about how the blocks on the destination were encrypted. As a result, any MAC in the objset's checksum-of-MACs tree that is a parent of both blocks encrypted on the source and blocks encrypted by the destination will be incorrect. This will result in authentication errors when we decrypt the dataset. This patch fixes this issue by adding a new check to the raw receive code. The code now maintains an "IVset guid", which acts as an identifier for the set of IVs used to encrypt a given snapshot. When a snapshot is raw received, the destination snapshot will take this value from the DRR_BEGIN payload. Non-raw receives and normal "zfs snap" operations will cause ZFS to generate a new IVset guid. When a raw incremental stream is received, ZFS will check that the "from" IVset guid in the stream matches that of the "from" destination snapshot. If they do not match, the code will error out the receive, preventing the problem. This patch requires an on-disk format change to add the IVset guids to snapshots and bookmarks. As a result, this patch has errata handling and a tunable to help affected users resolve the issue with as little interruption as possible. Reviewed-by: Paul Dagnelie <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Matt Ahrens <[email protected]> Signed-off-by: Tom Caputi <[email protected]> Closes #8308
* Simplify spa_sync by breaking it up to smaller functionsSerapheim Dimitropoulos2019-01-181-169/+197
| | | | | | | | | | | | The point of this refactoring is to break the high-level conceptual steps of spa_sync() to their own helper functions. In general large functions can enhance readability if structured well, but in this case the amount of conceptual steps taken could use the help of helper functions. Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Serapheim Dimitropoulos <[email protected]> Closes #8293
* Serialize ZTHR operations to eliminate racesSerapheim Dimitropoulos2019-01-131-8/+6
| | | | | | | | | | | Adds a new lock for serializing operations on zthrs. The commit also includes some code cleanup and refactoring. Reviewed by: Matt Ahrens <[email protected]> Reviewed by: Tom Caputi <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Serapheim Dimitropoulos <[email protected]> Closes #8229
* zfs initialize performance enhancementsGeorge Wilson2019-01-071-26/+64
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | PROBLEM ======== When invoking "zpool initialize" on a pool the command will create a thread to initialize each disk. Unfortunately, it does this serially across many transaction groups which can result in commands taking a long time to return to the user and may appear hung. The same thing is true when trying to suspend/cancel the operation. SOLUTION ========= This change refactors the way we invoke the initialize interface to ensure we can start or stop the intialization in just a few transaction groups. When stopping or cancelling a vdev initialization perform it in two phases. First signal each vdev initialization thread that it should exit, then after all threads have been signaled wait for them to exit. On a pool with 40 leaf vdevs this reduces the vdev initialize stop/cancel time from ~10 minutes to under a second. The reason for this is spa_vdev_initialize() no longer needs to wait on multiple full TXGs per leaf vdev being stopped. This commit additionally adds some missing checks for the passed "initialize_vdevs" input nvlist. The contents of the user provided input "initialize_vdevs" nvlist must be validated to ensure all values are uint64s. This is done in zfs_ioc_pool_initialize() in order to keep all of these checks in a single location. Updated the innvl and outnvl comments to match the formatting used for all other new sytle ioctls. Reviewed by: Matt Ahrens <[email protected]> Reviewed-by: loli10K <[email protected]> Reviewed-by: Tim Chase <[email protected]> Signed-off-by: Brian Behlendorf <[email protected]> Signed-off-by: George Wilson <[email protected]> Closes #8230
* OpenZFS 9102 - zfs should be able to initialize storage devicesGeorge Wilson2019-01-071-12/+143
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | PROBLEM ======== The first access to a block incurs a performance penalty on some platforms (e.g. AWS's EBS, VMware VMDKs). Therefore we recommend that volumes are "thick provisioned", where supported by the platform (VMware). This can create a large delay in getting a new virtual machines up and running (or adding storage to an existing Engine). If the thick provision step is omitted, write performance will be suboptimal until all blocks on the LUN have been written. SOLUTION ========= This feature introduces a way to 'initialize' the disks at install or in the background to make sure we don't incur this first read penalty. When an entire LUN is added to ZFS, we make all space available immediately, and allow ZFS to find unallocated space and zero it out. This works with concurrent writes to arbitrary offsets, ensuring that we don't zero out something that has been (or is in the middle of being) written. This scheme can also be applied to existing pools (affecting only free regions on the vdev). Detailed design: - new subcommand:zpool initialize [-cs] <pool> [<vdev> ...] - start, suspend, or cancel initialization - Creates new open-context thread for each vdev - Thread iterates through all metaslabs in this vdev - Each metaslab: - select a metaslab - load the metaslab - mark the metaslab as being zeroed - walk all free ranges within that metaslab and translate them to ranges on the leaf vdev - issue a "zeroing" I/O on the leaf vdev that corresponds to a free range on the metaslab we're working on - continue until all free ranges for this metaslab have been "zeroed" - reset/unmark the metaslab being zeroed - if more metaslabs exist, then repeat above tasks. - if no more metaslabs, then we're done. - progress for the initialization is stored on-disk in the vdev’s leaf zap object. The following information is stored: - the last offset that has been initialized - the state of the initialization process (i.e. active, suspended, or canceled) - the start time for the initialization - progress is reported via the zpool status command and shows information for each of the vdevs that are initializing Porting notes: - Added zfs_initialize_value module parameter to set the pattern written by "zpool initialize". - Added zfs_vdev_{initializing,removal}_{min,max}_active module options. Authored by: George Wilson <[email protected]> Reviewed by: John Wren Kennedy <[email protected]> Reviewed by: Matthew Ahrens <[email protected]> Reviewed by: Pavel Zakharov <[email protected]> Reviewed by: Prakash Surya <[email protected]> Reviewed by: loli10K <[email protected]> Reviewed by: Brian Behlendorf <[email protected]> Approved by: Richard Lowe <[email protected]> Signed-off-by: Tim Chase <[email protected]> Ported-by: Tim Chase <[email protected]> OpenZFS-issue: https://www.illumos.org/issues/9102 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/c3963210eb Closes #8230
* OpenZFS 9682 - page fault in dsl_async_clone_destroy() while opening poolSerapheim Dimitropoulos2018-10-191-3/+9
| | | | | | | | | | | | | | Authored by: Serapheim Dimitropoulos <[email protected]> Reviewed by: Brad Lewis <[email protected]> Reviewed by: Matt Ahrens <[email protected]> Reviewed by: Sara Hartse <[email protected]> Reviewed by: Brian Behlendorf <[email protected]> Approved by: Robert Mustacchi <[email protected]> Ported-by: George Melikov <[email protected]> OpenZFS-issue: https://www.illumos.org/issues/9682 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/ade2c82828 Closes #8037
* Defer new resilvers until the current one endsTom Caputi2018-10-181-4/+12
| | | | | | | | | | | | | | | | | | | | | | | | | Currently, if a resilver is triggered for any reason while an existing one is running, zfs will immediately restart the existing resilver from the beginning to include the new drive. This causes problems for system administrators when a drive fails while another is already resilvering. In this case, the optimal thing to do to reduce risk of data loss is to wait for the current resilver to end before immediately replacing the second failed drive, which allows the system to operate with two incomplete drives for the minimum amount of time. This patch introduces the resilver_defer feature that essentially does this for the admin without forcing them to wait and monitor the resilver manually. The change requires an on-disk feature since we must mark drives that are part of a deferred resilver in the vdev config to ensure that we do not assume they are done resilvering when an existing resilver completes. Reviewed-by: Matthew Ahrens <[email protected]> Reviewed-by: John Kennedy <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: @mmaybee Signed-off-by: Tom Caputi <[email protected]> Closes #7732
* Improved error handling for extreme rewindsBrian Behlendorf2018-10-121-3/+4
| | | | | | | | | | | | | | | | | | | | | | | The vdev_checkpoint_sm_object(), vdev_obsolete_sm_object(), and vdev_obsolete_counts_are_precise() functions assume that the only way a zap_lookup() can fail is if the requested entry is missing. While this is the most common cause, it's not the only cause. Attemping to access a damaged ZAP will result in other errors. The most likely scenario for accessing a damaged ZAP is during an extreme rewind pool import. Under these conditions the pool is expected to contain damaged objects and the import code was updated to handle this gracefully. Getting an ECKSUM error from these ZAPs after the pool in import a far less likely, therefore the behavior for call paths was not modified. Reviewed-by: Tim Chase <[email protected]> Reviewed-by: Matthew Ahrens <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Signed-off-by: Brian Behlendorf <[email protected]> Closes #7809 Closes #7921
* Refcounted DSL Crypto Key MappingsTom Caputi2018-10-031-17/+1
| | | | | | | | | | | | | | | | | | | | | | | | Since native ZFS encryption was merged, we have been fighting against a series of bugs that come down to the same problem: Key mappings (which must be present during all I/O operations) are created and destroyed based on dataset ownership, but I/Os can have traditionally been allowed to "leak" into the next txg after the dataset is disowned. In the past we have attempted to solve this problem by trying to ensure that datasets are disowned ater all I/O is finished by calling txg_wait_synced(), but we have repeatedly found edge cases that need to be squashed and code paths that might incur a high number of txg syncs. This patch attempts to resolve this issue differently, by adding a reference to the key mapping for each txg it is dirtied in. By doing so, we can remove many of the unnecessary calls to txg_wait_synced() we have added in the past and ensure we don't need to deal with this problem in the future. Reviewed-by: Jorgen Lundman <[email protected]> Reviewed by: Matthew Ahrens <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Tom Caputi <[email protected]> Closes #7949
* OpenZFS 9700 - ZFS resilvered mirror does not balance readsJerry Jelinek2018-10-021-0/+4
| | | | | | | | | | | | | | | Authored by: Jerry Jelinek <[email protected]> Reviewed by: Toomas Soome <[email protected]> Reviewed by: Sanjay Nadkarni <[email protected]> Reviewed by: George Wilson <[email protected]> Reviewed-by: George Melikov <[email protected]> Reviewed-by: Richard Elling <[email protected]> Approved by: Matthew Ahrens <[email protected]> Ported-by: Brian Behlendorf <[email protected]> OpenZFS-issue: https://illumos.org/issues/9700 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/82f63c3c Closes #7973
* Prefix all refcount functions with zfs_Tim Schumacher2018-10-011-6/+7
| | | | | | | | | | | | Recent changes in the Linux kernel made it necessary to prefix the refcount_add() function with zfs_ due to a name collision. To bring the other functions in line with that and to avoid future collisions, prefix the other refcount functions as well. Reviewed by: Matthew Ahrens <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Tim Schumacher <[email protected]> Closes #7963
* zpool split can create a corrupted poolRoman Strashkin2018-09-121-3/+3
| | | | | | | | | | | Added vdev_resilver_needed() check to verify VDEVs are fully synced, so that after split the new pool will not be corrupted. Reviewed by: Pavel Zakharov <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: loli10K <[email protected]> Signed-off-by: Roman Strashkin <[email protected]> Closes #7865 Closes #7881
* Pool allocation classesDon Brady2018-09-051-13/+54
| | | | | | | | | | | | | | | | | | | | Allocation Classes add the ability to have allocation classes in a pool that are dedicated to serving specific block categories, such as DDT data, metadata, and small file blocks. A pool can opt-in to this feature by adding a 'special' or 'dedup' top-level VDEV. Reviewed by: Pavel Zakharov <[email protected]> Reviewed-by: Richard Laager <[email protected]> Reviewed-by: Alek Pinchuk <[email protected]> Reviewed-by: Håkan Johansson <[email protected]> Reviewed-by: Andreas Dilger <[email protected]> Reviewed-by: DHE <[email protected]> Reviewed-by: Richard Elling <[email protected]> Reviewed-by: Gregor Kopka <[email protected]> Reviewed-by: Kash Pande <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Matthew Ahrens <[email protected]> Signed-off-by: Don Brady <[email protected]> Closes #5182
* Introduce read/write kstats per datasetSerapheim Dimitropoulos2018-08-201-0/+2
| | | | | | | | | | | | | The following patch introduces a few statistics on reads and writes grouped by dataset. These statistics are implemented as kstats (backed by aggregate sums for performance) and can be retrieved by using the dataset objset ID number. The motivation for this change is to provide some preliminary analytics on dataset usage/performance. Reviewed-by: Richard Elling <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed by: Matthew Ahrens <[email protected]> Signed-off-by: Serapheim Dimitropoulos <[email protected]> Closes #7705
* Check encrypted dataset + embedded recv earlierTom Caputi2018-08-151-1/+1
| | | | | | | | | | | | | | This patch fixes a bug where attempting to receive a send stream with embedded data into an encrypted dataset would not cleanup that dataset when the error was reached. The check was moved into dmu_recv_begin_check(), preventing this issue. Reviewed-by: Jorgen Lundman <[email protected]> Reviewed by: Matthew Ahrens <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Richard Elling <[email protected]> Signed-off-by: Tom Caputi <[email protected]> Closes #7650
* OpenZFS 9112 - Improve allocation performance on high-end systemsPaul Dagnelie2018-07-311-14/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Overview ======== We parallelize the allocation process by creating the concept of "allocators". There are a certain number of allocators per metaslab group, defined by the value of a tunable at pool open time. Each allocator for a given metaslab group has up to 2 active metaslabs; one "primary", and one "secondary". The primary and secondary weight mean the same thing they did in in the pre-allocator world; primary metaslabs are used for most allocations, secondary metaslabs are used for ditto blocks being allocated in the same metaslab group. There is also the CLAIM weight, which has been separated out from the other weights, but that is less important to understanding the patch. The active metaslabs for each allocator are moved from their normal place in the metaslab tree for the group to the back of the tree. This way, they will not be selected for use by other allocators searching for new metaslabs unless all the passive metaslabs are unsuitable for allocations. If that does happen, the allocators will "steal" from each other to ensure that IOs don't fail until there is truly no space left to perform allocations. In addition, the alloc queue for each metaslab group has been broken into a separate queue for each allocator. We don't want to dramatically increase the number of inflight IOs on low-end systems, because it can significantly increase txg times. On the other hand, we want to ensure that there are enough IOs for each allocator to allow for good coalescing before sending the IOs to the disk. As a result, we take a compromise path; each allocator's alloc queue max depth starts at a certain value for every txg. Every time an IO completes, we increase the max depth. This should hopefully provide a good balance between the two failure modes, while not dramatically increasing complexity. We also parallelize the spa_alloc_tree and spa_alloc_lock, which cause very similar contention when selecting IOs to allocate. This parallelization uses the same allocator scheme as metaslab selection. Performance Results =================== Performance improvements from this change can vary significantly based on the number of CPUs in the system, whether or not the system has a NUMA architecture, the speed of the drives, the values for the various tunables, and the workload being performed. For an fio async sequential write workload on a 24 core NUMA system with 256 GB of RAM and 8 128 GB SSDs, there is a roughly 25% performance improvement. Future Work =========== Analysis of the performance of the system with this patch applied shows that a significant new bottleneck is the vdev disk queues, which also need to be parallelized. Prototyping of this change has occurred, and there was a performance improvement, but more work needs to be done before its stability has been verified and it is ready to be upstreamed. Authored by: Paul Dagnelie <[email protected]> Reviewed by: Matthew Ahrens <[email protected]> Reviewed by: George Wilson <[email protected]> Reviewed by: Serapheim Dimitropoulos <[email protected]> Reviewed by: Alexander Motin <[email protected]> Reviewed by: Brian Behlendorf <[email protected]> Approved by: Gordon Ross <[email protected]> Ported-by: Paul Dagnelie <[email protected]> Signed-off-by: Paul Dagnelie <[email protected]> Porting Notes: * Fix reservation test failures by increasing tolerance. OpenZFS-issue: https://illumos.org/issues/9112 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/3f3cc3c3 Closes #7682
* OpenZFS 9166 - zfs storage pool checkpointSerapheim Dimitropoulos2018-06-261-40/+411
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Details about the motivation of this feature and its usage can be found in this blogpost: https://sdimitro.github.io/post/zpool-checkpoint/ A lightning talk of this feature can be found here: https://www.youtube.com/watch?v=fPQA8K40jAM Implementation details can be found in big block comment of spa_checkpoint.c Side-changes that are relevant to this commit but not explained elsewhere: * renames members of "struct metaslab trees to be shorter without losing meaning * space_map_{alloc,truncate}() accept a block size as a parameter. The reason is that in the current state all space maps that we allocate through the DMU use a global tunable (space_map_blksz) which defauls to 4KB. This is ok for metaslab space maps in terms of bandwirdth since they are scattered all over the disk. But for other space maps this default is probably not what we want. Examples are device removal's vdev_obsolete_sm or vdev_chedkpoint_sm from this review. Both of these have a 1:1 relationship with each vdev and could benefit from a bigger block size. Porting notes: * The part of dsl_scan_sync() which handles async destroys has been moved into the new dsl_process_async_destroys() function. * Remove "VERIFY(!(flags & FWRITE))" in "kernel.c" so zhack can write to block device backed pools. * ZTS: * Fix get_txg() in zpool_sync_001_pos due to "checkpoint_txg". * Don't use large dd block sizes on /dev/urandom under Linux in checkpoint_capacity. * Adopt Delphix-OS's setting of 4 (spa_asize_inflation = SPA_DVAS_PER_BP + 1) for the checkpoint_capacity test to speed its attempts to fill the pool * Create the base and nested pools with sync=disabled to speed up the "setup" phase. * Clear labels in test pool between checkpoint tests to avoid duplicate pool issues. * The import_rewind_device_replaced test has been marked as "known to fail" for the reasons listed in its DISCLAIMER. * New module parameters: zfs_spa_discard_memory_limit, zfs_remove_max_bytes_pause (not documented - debugging only) vdev_max_ms_count (formerly metaslabs_per_vdev) vdev_min_ms_count Authored by: Serapheim Dimitropoulos <[email protected]> Reviewed by: Matthew Ahrens <[email protected]> Reviewed by: John Kennedy <[email protected]> Reviewed by: Dan Kimmel <[email protected]> Reviewed by: Brian Behlendorf <[email protected]> Approved by: Richard Lowe <[email protected]> Ported-by: Tim Chase <[email protected]> Signed-off-by: Tim Chase <[email protected]> OpenZFS-issue: https://illumos.org/issues/9166 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/7159fdb8 Closes #7570
* Remove suffix from zio taskq namesMatthew Ahrens2018-06-201-8/+3
| | | | | | | | | | | | | | | | | | | | | | | For zio taskq's which have multiple instances (e.g. z_rd_int_0, z_rd_int_1, etc), each one has a unique name (the _0, _1, _2 suffix). This makes performance analysis more difficult, because by default, `perf` includes the thread name (which is the same as the taskq name) in the stack trace. This means that we get 8 different stacks, all of which are doing the same thing, but are executed from different taskq's. We should remove the suffix of the taskq name, so that all the read-interrupt threads are named z_rd_int. Note that we already support multiple taskq's with the same name. This happens when there are multiple pools. In this case the taskq has a different tq_instance, which shows up in /proc/spl/taskq-all. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed by: Richard Elling <[email protected]> Reviewed-by: Giuseppe Di Natale <[email protected]> Reviewed-by: George Melikov <[email protected]> Reviewed by: Pavel Zakharov <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes #7646
* OpenZFS 9235 - rename zpool_rewind_policy_t to zpool_load_policy_tPavel Zakharov2018-06-041-28/+26
| | | | | | | | | | | | | | | | | | | | | | | We want to be able to pass various settings during import/open of a pool, which are not only related to rewind. Instead of adding a new policy and duplicate a bunch of code, we should just rename rewind_policy to a more generic term like load_policy. For instance, we'd like to set spa->spa_import_flags from the nvlist, rather from a flags parameter passed to spa_import as in some cases we want those flags not only for the import case, but also for the open case. One such flag could be ZFS_IMPORT_MISSING_LOG (as used in zdb) which would allow zfs to open a pool when logs are missing. Authored by: Pavel Zakharov <[email protected]> Reviewed by: Matt Ahrens <[email protected]> Reviewed by: George Wilson <[email protected]> Approved by: Robert Mustacchi <[email protected]> Ported-by: Brian Behlendorf <[email protected]> OpenZFS-issue: https://illumos.org/issues/9235 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/d2b1e44 Closes #7532
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-30 03:34:49 +0000