aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Fix zfs(8) mandoc errorsloli10K2019-07-021-1/+0
| | | | | | | | | | | | | | This was accidentally introduced in 765d1f06: mandoc: ./man/man8/zfs.8: ERROR: skipping item outside list: It Ar filesystem Ns | Ns Ar mountpoint mandoc: ./man/man8/zfs.8: ERROR: skipping item outside list: It Xo mandoc: ./man/man8/zfs.8: ERROR: skipping end of block that is not open: Xc mandoc: ./man/man8/zfs.8: ERROR: skipping item outside list: It Xo mandoc: ./man/man8/zfs.8: ERROR: skipping end of block that is not open: Xc Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: George Melikov <[email protected]> Signed-off-by: loli10K <[email protected]> Closes #8980
* nopwrites on dmu_sync-ed blocks can result in a panicGeorge Wilson2019-06-284-2/+103
| | | | | | | | | | | | | | | | | After device removal, performing nopwrites on a dmu_sync-ed block will result in a panic. This panic can show up in two ways: 1. an attempt to issue an IOCTL in vdev_indirect_io_start() 2. a failed comparison of zio->io_bp and zio->io_bp_orig in zio_done() To resolve both of these panics, nopwrites of blocks on indirect vdevs should be ignored and new allocations should be performed on concrete vdevs. Reviewed-by: Igor Kozhukhov <[email protected]> Reviewed-by: Pavel Zakharov <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Don Brady <[email protected]> Signed-off-by: George Wilson <[email protected]> Closes #8957
* Add 'zfs umount -u' for encrypted datasetsTom Caputi2019-06-286-13/+125
| | | | | | | | | | | This patch adds the ability for the user to unload keys for datasets as they are being unmounted. This is analogous to 'zfs mount -l'. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Alek Pinchuk <[email protected]> Signed-off-by: Tom Caputi <[email protected]> Closes: #8917 Closes: #8952
* Concurrent small allocation defeats large allocationPaul Dagnelie2019-06-261-49/+231
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | With the new parallel allocators scheme, there is a possibility for a problem where two threads, allocating from the same allocator at the same time, conflict with each other. There are two primary cases to worry about. First, another thread working on another allocator activates the same metaslab that the first thread was trying to activate. This results in the first thread needing to go back and reselect a new metaslab, even though it may have waited a long time for this metaslab to load. Second, another thread working on the same allocator may have activated a different metaslab while the first thread was waiting for its metaslab to load. Both of these cases can cause the first thread to be significantly delayed in issuing its IOs. The second case can also cause metaslab load/unload churn; because the metaslab is loaded but not fully activated, we never set the selected_txg, which results in the metaslab being immediately unloaded again. This process can repeat many times, wasting disk and cpu resources. This is more likely to happen when the IO of the first thread is a larger one (like a ZIL write) and the other thread is doing a smaller write, because it is more likely to find an acceptable metaslab quickly. There are two primary changes. The first is to always proceed with the allocation when returning from metaslab_activate if we were preempted in either of the ways described in the previous section. The second change is to set the selected_txg before we do the call to activate so that even if the metaslab is not used for an allocation, we won't immediately attempt to unload it. Reviewed by: Jerry Jelinek <[email protected]> Reviewed by: Matt Ahrens <[email protected]> Reviewed by: Serapheim Dimitropoulos <[email protected]> Reviewed by: Brian Behlendorf <[email protected]> Signed-off-by: Paul Dagnelie <[email protected]> External-issue: DLPX-61314 Closes #8843
* zdb -vvvvv on ztest pool dies with "out of memory"Paul Dagnelie2019-06-251-6/+20
| | | | | | | | | | | | | | | ztest creates some extremely large files as part of its operation. When zdb tries to dump a large enough file, it can run out of memory or spend an extremely long time attempting to print millions or billions of uint64_ts. We cap the amount of data from a uint64 object that we are willing to read and print. Reviewed-by: Don Brady <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Paul Dagnelie <[email protected]> External-issue: DLPX-53814 Closes #8947
* Avoid extra taskq_dispatch() calls by DMUAlexander Motin2019-06-253-5/+38
| | | | | | | | | | | | | | | DMU sync code calls taskq_dispatch() for each sublist of os_dirty_dnodes and os_synced_dnodes. Since the number of sublists by default is equal to number of CPUs, it will dispatch equal, potentially large, number of tasks, waking up many CPUs to handle them, even if only one or few of sublists actually have any work to do. This change adds check for empty sublists to avoid this. Reviewed by: Sean Eric Fagan <[email protected]> Reviewed by: Matt Ahrens <[email protected]> Reviewed by: Brian Behlendorf <[email protected]> Signed-off-by: Alexander Motin <[email protected]> Closes #8909
* Redacted Send/Receive causes zdb to dump coreloli10K2019-06-241-1/+1
| | | | | | | | | When used with verbosity >= 4 zdb fails an assertion in dump_bookmarks() because it expects snprintf() to retun 0 on success. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Paul Dagnelie <[email protected]> Signed-off-by: loli10K <[email protected]> Closes #8948
* Fix bp_embedded_type enum definitionloli10K2019-06-242-3/+3
| | | | | | | | | | With the addition of BP_EMBEDDED_TYPE_REDACTED in 30af21b0 a couple of codepaths make wrong assumptions and could potentially result in errors. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Chris Dunlop <[email protected]> Reviewed-by: Paul Dagnelie <[email protected]> Signed-off-by: loli10K <[email protected]> Closes #8951
* -Y option for zdb is validIgor K2019-06-241-1/+1
| | | | | | | | The -Y option was added for ztest to test split block reconstruction. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Richard Elling <[email protected]> Signed-off-by: Igor Kozhukhov <[email protected]> Closes #8926
* Remove code for zfs remapMatthew Ahrens2019-06-2440-947/+29
| | | | | | | | | | | | | | | | The "zfs remap" command was disabled by 6e91a72fe3ff8bb282490773bd687632f3e8c79d, because it has little utility and introduced some tricky bugs. This commit removes the code for it, the associated ZFS_IOC_REMAP ioctl, and tests. Note that the ioctl and property will remain, but have no functionality. This allows older software to fail gracefully if it attempts to use these, and avoids a backwards incompatibility that would be introduced if we renumbered the later ioctls/props. Reviewed-by: Tom Caputi <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes #8944
* Fix error message on promoting encrypted datasetTom Caputi2019-06-242-2/+16
| | | | | | | | | This patch corrects the error message reported when attempting to promote a dataset outside of its encryption root. Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Tom Caputi <[email protected]> Closes #8905 Closes #8935
* Fix out-of-tree build failuresBrian Behlendorf2019-06-2411-72/+88
| | | | | | | | | | | | | | | | | | | | Resolve the incorrect use of srcdir and builddir references for various files in the build system. These have crept in over time and went unnoticed because when building in the top level directory srcdir and builddir are identical. With this change it's again possible to build in a subdirectory. $ mkdir obj $ cd obj $ ../configure $ make Reviewed-by: loli10K <[email protected]> Reviewed-by: Tony Hutter <[email protected]> Reviewed-by: Don Brady <[email protected]> Signed-off-by: Brian Behlendorf <[email protected]> Closes #8921 Closes #8943
* Add missing .gitignore from "Implement Redacted Send/Receive"Tomohiro Kusumi2019-06-231-0/+1
| | | | | | | | | 30af21b025 needed to ignore get_diff executable. Reviewed-by: loli10K <[email protected]> Reviewed-by: George Melikov <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Tomohiro Kusumi <[email protected]> Closes #8950
* OpenZFS 9425 - channel programs can be interruptedDon Brady2019-06-2213-97/+322
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Problem Statement ================= ZFS Channel program scripts currently require a timeout, so that hung or long-running scripts return a timeout error instead of causing ZFS to get wedged. This limit can currently be set up to 100 million Lua instructions. Even with a limit in place, it would be desirable to have a sys admin (support engineer) be able to cancel a script that is taking a long time. Proposed Solution ================= Make it possible to abort a channel program by sending an interrupt signal.In the underlying txg_wait_sync function, switch the cv_wait to a cv_wait_sig to catch the signal. Once a signal is encountered, the dsl_sync_task function can install a Lua hook that will get called before the Lua interpreter executes a new line of code. The dsl_sync_task can resume with a standard txg_wait_sync call and wait for the txg to complete. Meanwhile, the hook will abort the script and indicate that the channel program was canceled. The kernel returns a EINTR to indicate that the channel program run was canceled. Porting notes: Added missing return value from cv_wait_sig() Authored by: Don Brady <[email protected]> Reviewed by: Sebastien Roy <[email protected]> Reviewed by: Serapheim Dimitropoulos <[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: Don Brady <[email protected]> Signed-off-by: Don Brady <[email protected]> OpenZFS-issue: https://www.illumos.org/issues/9425 OpenZFS-commit: https://github.com/illumos/illumos-gate/commit/d0cb1fb926 Closes #8904
* dn_struct_rwlock can not be held in dmu_tx_try_assign()Matthew Ahrens2019-06-221-0/+19
| | | | | | | | | | | | | | | | | The thread calling dmu_tx_try_assign() can't hold the dn_struct_rwlock while assigning the tx, because this can lead to deadlock. Specifically, if this dnode is already assigned to an earlier txg, this thread may need to wait for that txg to sync (the ERESTART case below). The other thread that has assigned this dnode to an earlier txg prevents this txg from syncing until its tx can complete (calling dmu_tx_commit()), but it may need to acquire the dn_struct_rwlock to do so (e.g. via dmu_buf_hold*()). This commit adds an assertion to dmu_tx_try_assign() to ensure that this deadlock is not inadvertently introduced. Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes #8929
* Remove arch and relax version dependencygordan-bobic2019-06-221-1/+2
| | | | | | | | | | Remove arch and relax version dependency for zfs-dracut package. Reviewed-by: Tony Hutter <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Gordan Bobic <[email protected]> Issue #8913 Closes #8914
* Add libnvpair to libzfs pkg-configHarry Mallon2019-06-221-1/+1
| | | | | | | | Functions such as `fnvlist_lookup_nvlist` need libnvpair to be linked. Default pkg-config file did not contain it. Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Harry Mallon <[email protected]> Closes #8919
* Let zfs mount all tolerate in-progress mountsDon Brady2019-06-221-1/+18
| | | | | | | | | | | | | | | | | | | The zfs-mount service can unexpectedly fail to start when zfs encounters a mount that is in progress. This service uses zfs mount -a, which has a window between the time it checks if the dataset was mounted and when the actual mount (via mount.zfs binary) occurs. The reason for the racing mounts is that both zfs-mount.target and zfs-share.target are allowed to execute concurrently after the import. This is more of an issue with the relatively recent addition of parallel mounting, and we should consider serializing the mount and share targets. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed by: John Kennedy <[email protected]> Reviewed-by: Allan Jude <[email protected]> Signed-off-by: Don Brady <[email protected]> Closes #8881
* zstreamdump: add per-record-type counters and an overhead counterAllan Jude2019-06-222-23/+42
| | | | | | | | | | | | | Count the bytes of payload for each replication record type Count the bytes of overhead (replication records themselves) Include these counters in the output summary at the end of the run. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Matt Ahrens <[email protected]> Signed-off-by: Allan Jude <[email protected]> Sponsored-By: Klara Systems and Catalogic Closes #8432
* Fix comments on zfs_bookmark_physPaul Dagnelie2019-06-221-1/+3
| | | | | | | Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: George Melikov <[email protected]> Signed-off-by: Paul Dagnelie <[email protected]> Closes #8945
* Fix build break by "Implement Redacted Send/Receive"Tomohiro Kusumi2019-06-221-2/+3
| | | | | | | | | | | | | | | | | | | 30af21b025 broke build on Fedora. gcc can detect potential overflow on compile-time. Consider strlen of already copied string. Also change strn to strl variants per suggestion from @behlendorf and @ofaaland. -- libzfs_input_check.c: In function 'test_redact': libzfs_input_check.c:711:2: error: 'strncat' specified bound 288 equals destination size [-Werror=stringop-overflow=] strncat(bookmark, "#testbookmark", sizeof (bookmark)); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Olaf Faaland <[email protected]> Signed-off-by: Tomohiro Kusumi <[email protected]> Closes #8939
* Add SCSI_PASSTHROUGH to zvols to enable UNMAP supportPaul Dagnelie2019-06-211-0/+4
| | | | | | | | | | | | | | | When exporting ZVOLs as SCSI LUNs, by default Windows will not issue them UNMAP commands. This reduces storage efficiency in many cases. We add the SCSI_PASSTHROUGH flag to the zvol's device queue, which lets the SCSI target logic know that it can handle SCSI commands. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: George Melikov <[email protected]> Reviewed-by: John Gallagher <[email protected]> Signed-off-by: Paul Dagnelie <[email protected]> Closes #8933
* Redacted Send/Receive broke zfs(8) help messageloli10K2019-06-211-2/+1
| | | | | | | | | | | Since 30af21b0 was merged 'zfs send' help message format is broken and lists "-r" as a valid option: this commit corrects these small issues. Reviewed-by: George Melikov <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Paul Dagnelie <[email protected]> Signed-off-by: loli10K <[email protected]> Closes #8942
* Prevent pointer to an out-of-scope local variableTomohiro Kusumi2019-06-201-2/+1
| | | | | | | | | | | | `show_str` could be a pointer to a local variable in stack which is out-of-scope by the time `return (snprintf(buf, buflen, "%s\n", show_str));` is called. Reviewed-by: Tony Hutter <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Tomohiro Kusumi <[email protected]> Closes #8924 Closes #8940
* dedup=verify doesn't clear the blkptr's dedup flagMatthew Ahrens2019-06-201-0/+2
| | | | | | | | | | | | The logic to handle strong checksum collisions where the data doesn't match is incorrect. It is not clearing the dedup bit of the blkptr, which can cause a panic later in zio_ddt_free() due to the dedup table not matching what is in the blkptr. Reviewed-by: Tom Caputi <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> External-issue: DLPX-48097 Closes #8936
* Update vdev_ops_t from illumosIgor K2019-06-207-143/+143
| | | | | | | | Align vdev_ops_t from illumos for better compatibility. Reviewed-by: Tony Hutter <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Igor Kozhukhov <[email protected]> Closes #8925
* Allow unencrypted children of encrypted datasetsTom Caputi2019-06-2010-163/+63
| | | | | | | | | | | | | | | | | | When encryption was first added to ZFS, we made a decision to prevent users from creating unencrypted children of encrypted datasets. The idea was to prevent users from inadvertently leaving some of their data unencrypted. However, since the release of 0.8.0, some legitimate reasons have been brought up for this behavior to be allowed. This patch simply removes this limitation from all code paths that had checks for it and updates the tests accordingly. Reviewed-by: Jason King <[email protected]> Reviewed-by: Sean Eric Fagan <[email protected]> Reviewed-by: Richard Laager <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Tom Caputi <[email protected]> Closes #8737 Closes #8870
* Replace whereis with type in zfs-lib.shdacianstremtan2019-06-201-1/+1
| | | | | | | | | | | The whereis command should not be used since it may not exist in the initramfs. The dracut plymouth module also uses the type command instead of whereis. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Garrett Fields <[email protected]> Signed-off-by: Dacian Reece-Stremtan <[email protected]> Closes #8920 Closes #8938
* Remove dedupditto functionalityMatthew Ahrens2019-06-1912-340/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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
* Use ZFS_DEV macro instead of literalsTomohiro Kusumi2019-06-192-4/+4
| | | | | | | | | The rest of the code/comments use ZFS_DEV, so sync with that. Reviewed-by: Tony Hutter <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Richard Elling <[email protected]> Signed-off-by: Tomohiro Kusumi <[email protected]> Closes #8912
* Fix memory leak in check_disk()Michael Niewöhner2019-06-191-0/+1
| | | | | | | | Reviewed-by: Allan Jude <[email protected]> Reviewed-by: Tony Hutter <[email protected]> Reviewed-by: Richard Elling <[email protected]> Signed-off-by: Michael Niewöhner <[email protected]> Closes #8897 Closes #8911
* kmod-zfs-devel rpm should provide kmod-spl-develOlaf Faaland2019-06-191-0/+1
| | | | | | | | | | | | | | | When configure is run with --with-spec=redhat, and rpms are built, the kmod-zfs-devel package is missing Provides: kmod-spl-devel = %{version} which is required by software such as Lustre which builds against zfs kmods. Adding it makes it easier for such software to build against both zfs-0.7 (where SPL is separate and may be missing) and zfs-0.8. Reviewed-by: Tony Hutter <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Olaf Faaland <[email protected]> Closes #8930
* ZTS: Fix mmp_interval failureBrian Behlendorf2019-06-191-4/+4
| | | | | | | | | | | | | | | | | | The mmp_interval test case was failing on Fedora 30 due to the built-in 'echo' command terminating the script when it was unable to write to the sysfs module parameter. This change in behavior was observed with ksh-2020.0.0-alpha1. Resolve the issue by using the external cat command which fails gracefully as expected. Additionally, remove some incorrect quotes around the $? return values. Reviewed-by: Giuseppe Di Natale <[email protected]> Reviewed-by: Tony Hutter <[email protected]> Reviewed-by: Olaf Faaland <[email protected]> Reviewed-by: Richard Elling <[email protected]> Reviewed-by: George Melikov <[email protected]> Signed-off-by: Brian Behlendorf <[email protected]> Closes #8906
* Implement Redacted Send/ReceivePaul Dagnelie2019-06-19103-2069/+10914
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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
* Minimize aggsum_compare(&arc_size, arc_c) calls.Alexander Motin2019-06-141-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | For busy ARC situation when arc_size close to arc_c is desired. But then it is quite likely that aggsum_compare(&arc_size, arc_c) will need to flush per-CPU buckets to find exact comparison result. Doing that often in a hot path penalizes whole idea of aggsum usage there, since it replaces few simple atomic additions with dozens of lock acquisitions. Replacing aggsum_compare() with aggsum_upper_bound() in code increasing arc_p when ARC is growing (arc_size < arc_c) according to PMC profiles allows to save ~5% of CPU time in aggsum code during sequential write to 12 ZVOLs with 16KB block size on large dual-socket system. I suppose there some minor arc_p behavior change due to lower precision of the new code, but I don't think it is a big deal, since it should affect only very small window in time (aggsum buckets are flushed every second) and in ARC size (buckets are limited to 10 average ARC blocks per CPU). Reviewed-by: Chris Dunlop <[email protected]> Reviewed-by: Richard Elling <[email protected]> Reviewed-by: George Melikov <[email protected]> Reviewed-by: Allan Jude <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Alexander Motin <[email protected]> Closes #8901
* Python config cleanupRyan Moeller2019-06-132-79/+53
| | | | | | | | | | | Don't require Python at configure/build unless building pyzfs. Move ZFS_AC_PYTHON_MODULE to always-pyzfs.m4 where it is used. Make test syntax more consistent. Sponsored by: iXsystems, Inc. Reviewed-by: Neal Gompa <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Ryan Moeller <[email protected]> Closes #8895
* lz4_decompress_abd declared but not definedMatthew Ahrens2019-06-131-2/+1
| | | | | | | | | | | `lz4_decompress_abd` is declared in zio_compress.h but it is not defined anywhere. The declaration should be removed. Reviewed by: Dan Kimmel <[email protected]> Reviewed-by: Allan Jude <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> External-issue: DLPX-47477 Closes #8894
* panic in removal_remap test on 4K devicesMatthew Ahrens2019-06-134-14/+59
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the zfs_remove_max_segment tunable is changed to be not a multiple of the sector size, then the device removal code will malfunction and try to create mappings that are smaller than one sector, leading to a panic. On debug bits this assertion will fail in spa_vdev_copy_segment(): ASSERT3U(DVA_GET_ASIZE(&dst), ==, size); On nondebug, the system panics with a stack like: metaslab_free_concrete() metaslab_free_impl() metaslab_free_impl_cb() vdev_indirect_remap() free_from_removing_vdev() metaslab_free_impl() metaslab_free_dva() metaslab_free() Fortunately, the default for zfs_remove_max_segment is 1MB, so this can't occur by default. We hit it during this test because removal_remap.ksh changes zfs_remove_max_segment to 1KB. When testing on 4KB-sector disks, we hit the bug. This change makes the zfs_remove_max_segment tunable more robust, automatically rounding it up to a multiple of the sector size. We also turn some key assertions into VERIFY's so that similar bugs would be caught before they are encoded on disk (and thus avoid a panic-reboot-loop). Reviewed-by: Sean Eric Fagan <[email protected]> Reviewed-by: Pavel Zakharov <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Reviewed-by: Sebastien Roy <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> External-issue: DLPX-61342 Closes #8893
* compress metadata in later sync passesMatthew Ahrens2019-06-132-4/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Starting in sync pass 5 (zfs_sync_pass_dont_compress), we disable compression (including of metadata). Ostensibly this helps the sync passes to converge (i.e. for a sync pass to not need to allocate anything because it is 100% overwrites). However, in practice it increases the average number of sync passes, because when we turn compression off, a lot of block's size will change and thus we have to re-allocate (not overwrite) them. It also increases the number of 128KB allocations (e.g. for indirect blocks and spacemaps) because these will not be compressed. The 128K allocations are especially detrimental to performance on highly fragmented systems, which may have very few free segments of this size, and may need to load new metaslabs to satisfy 128K allocations. We should increase zfs_sync_pass_dont_compress. In practice on a highly fragmented system we see a few 5-pass txg's, a tiny number of 6-pass txg's, and no txg's with more than 6 passes. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Richard Elling <[email protected]> Reviewed by: Pavel Zakharov <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Reviewed-by: George Wilson <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> External-issue: DLPX-63431 Closes #8892
* Move write aggregation memory copy out of vq_lockAlexander Motin2019-06-131-10/+12
| | | | | | | | | | | | | | | | | | | Memory copy is too heavy operation to do under the congested lock. Moving it out reduces congestion by many times to almost invisible. Since the original zio removed from the queue, and the child zio is not executed yet, I don't see why would the copy need protection. My guess it just remained like this from the time when lock was not dropped here, which was added later to fix lock ordering issue. Multi-threaded sequential write tests with both HDD and SSD pools with ZVOL block sizes of 4KB, 16KB, 64KB and 128KB all show major reduction of lock congestion, saving from 15% to 35% of CPU time and increasing throughput from 10% to 40%. Reviewed-by: Richard Yao <[email protected]> Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Alexander Motin <[email protected]> Closes #8890
* looping in metaslab_block_picker impacts performance on fragmented poolsMatthew Ahrens2019-06-132-60/+117
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | On fragmented pools with high-performance storage, the looping in metaslab_block_picker() can become the performance-limiting bottleneck. When looking for a larger block (e.g. a 128K block for the ZIL), we may search through many free segments (up to hundreds of thousands) to find one that is large enough to satisfy the allocation. This can take a long time (up to dozens of ms), and is done while holding the ms_lock, which other threads may spin waiting for. When this performance problem is encountered, profiling will show high CPU time in metaslab_block_picker, as well as in mutex_enter from various callers. The problem is very evident on a test system with a sync write workload with 8K writes to a recordsize=8k filesystem, with 4TB of SSD storage, 84% full and 88% fragmented. It has also been observed on production systems with 90TB of storage, 76% full and 87% fragmented. The fix is to change metaslab_df_alloc() to search only up to 16MB from the previous allocation (of this alignment). After that, we will pick a segment that is of the exact size requested (or larger). This reduces the number of iterations to a few hundred on fragmented pools (a ~100x improvement). Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Paul Dagnelie <[email protected]> Reviewed-by: Tony Nguyen <[email protected]> Reviewed-by: George Wilson <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> External-issue: DLPX-62324 Closes #8877
* Restrict filesystem creation if name referred either '.' or '..'Tulsi Jain2019-06-134-1/+36
| | | | | | | | | | | This change restricts filesystem creation if the given name contains either '.' or '..' Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Richard Elling <[email protected]> Signed-off-by: TulsiJain <[email protected]> Closes #8842 Closes #8564
* ztest: dmu_tx_assign() gets ENOSPC in spa_vdev_remove_thread()Matthew Ahrens2019-06-131-1/+1
| | | | | | | | | | | | | | | | | | | | | When running zloop, we occasionally see the following crash: dmu_tx_assign(tx, TXG_WAIT) == 0 (0x1c == 0) ASSERT at ../../module/zfs/vdev_removal.c:1507:spa_vdev_remove_thread()/sbin/ztest(+0x89c3)[0x55faf567b9c3] The error value 0x1c is ENOSPC. The transaction used by spa_vdev_remove_thread() should not be able to fail due to being out of space. i.e. we should not call dmu_tx_hold_space(). This will allow the removal thread to schedule its work even when the pool is low on space. The "slop space" will provide enough free space to sync out the txg. Reviewed-by: Igor Kozhukhov <[email protected]> Reviewed-by: Paul Dagnelie <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> External-issue: DLPX-37853 Closes #8889
* Fix lockdep warning on insmodTomohiro Kusumi2019-06-121-0/+5
| | | | | | | | | | | | | | sysfs_attr_init() is required to make lockdep happy for dynamically allocated sysfs attributes. This fixed #8868 on Fedora 29 running kernel-debug. This requirement was introduced in 2.6.34. See include/linux/sysfs.h for what it actually does. Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Olaf Faaland <[email protected]> Signed-off-by: Tomohiro Kusumi <[email protected]> Closes #8868 Closes #8884
* fat zap should prefetch when iteratingMatthew Ahrens2019-06-126-9/+140
| | | | | | | | | | | | | | | | | When iterating over a ZAP object, we're almost always certain to iterate over the entire object. If there are multiple leaf blocks, we can realize a performance win by issuing reads for all the leaf blocks in parallel when the iteration begins. For example, if we have 10,000 snapshots, "zfs destroy -nv pool/fs@1%9999" can take 30 minutes when the cache is cold. This change provides a >3x performance improvement, by issuing the reads for all ~64 blocks of each ZAP object in parallel. Reviewed-by: Andreas Dilger <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> External-issue: DLPX-58347 Closes #8862
* Target ARC size can get reduced to arc_c_minMatthew Ahrens2019-06-121-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | | Sometimes the target ARC size is reduced to arc_c_min, which impacts performance. We've seen this happen as part of the random_reads performance regression test, where the ARC size is reduced before the reads test starts which impacts how long it takes for system to reach good IOPS performance. We call arc_reduce_target_size when arc_reap_cb_check() returns TRUE, and arc_available_memory() is less than arc_c>>arc_shrink_shift. However, arc_available_memory() could easily be low, even when arc_c is low, because we can have tons of unused bufs in the abd kmem cache. This would be especially true just after the DMU requests a bunch of stuff be evicted from the ARC (e.g. due to "zpool export"). To fix this, the ARC should reduce arc_c by the requested amount, not all the way down to arc_size (or arc_c_min), which can be very small. Reviewed-by: Tim Chase <[email protected]> Reviewed by: Brian Behlendorf <[email protected]> Reviewed-by: George Melikov <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> External-issue: DLPX-59431 Closes #8864
* Fix typo in vdev_raidz_math.cbnjf2019-06-121-1/+1
| | | | | | | | | Fix typo in vdev_raidz_math.c Reviewed by: Brian Behlendorf <[email protected]> Reviewed-by: George Melikov <[email protected]> Signed-off-by: Brad Forschinger <[email protected]> Closes #8875 Closes #8880
* single-chunk scatter ABDs can be treated as linearMatthew Ahrens2019-06-114-55/+103
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Scatter ABD's are allocated from a number of pages. In contrast to linear ABD's, these pages are disjoint in the kernel's virtual address space, so they can't be accessed as a contiguous buffer. Therefore routines that need a linear buffer (e.g. abd_borrow_buf() and friends) must allocate a separate linear buffer (with zio_buf_alloc()), and copy the contents of the pages to/from the linear buffer. This can have a measurable performance overhead on some workloads. https://github.com/zfsonlinux/zfs/commit/87c25d567fb7969b44c7d8af63990e ("abd_alloc should use scatter for >1K allocations") increased the use of scatter ABD's, specifically switching 1.5K through 4K (inclusive) buffers from linear to scatter. For workloads that access blocks whose compressed sizes are in this range, that commit introduced an additional copy into the read code path. For example, the sequential_reads_arc_cached tests in the test suite were reduced by around 5% (this is doing reads of 8K-logical blocks, compressed to 3K, which are cached in the ARC). This commit treats single-chunk scattered buffers as linear buffers, because they are contiguous in the kernel's virtual address space. All single-page (4K) ABD's can be represented this way. Some multi-page ABD's can also be represented this way, if we were able to allocate a single "chunk" (higher-order "page" which represents a power-of-2 series of physically-contiguous pages). This is often the case for 2-page (8K) ABD's. Representing a single-entry scatter ABD as a linear ABD has the performance advantage of avoiding the copy (and allocation) in abd_borrow_buf_copy / abd_return_buf_copy. A performance increase of around 5% has been observed for ARC-cached reads (of small blocks which can take advantage of this), fixing the regression introduced by 87c25d567. Note that this optimization is only possible because all physical memory is always mapped into the kernel's address space. This is not the case for HIGHMEM pages, so the optimization can not be made on 32-bit systems. Reviewed-by: Chunwei Chen <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes #8580
* make zil max block size tunableMatthew Ahrens2019-06-107-32/+96
| | | | | | | | | | | | | | | | | | | | | | | We've observed that on some highly fragmented pools, most metaslab allocations are small (~2-8KB), but there are some large, 128K allocations. The large allocations are for ZIL blocks. If there is a lot of fragmentation, the large allocations can be hard to satisfy. The most common impact of this is that we need to check (and thus load) lots of metaslabs from the ZIL allocation code path, causing sync writes to wait for metaslabs to load, which can take a second or more. In the worst case, we may not be able to satisfy the allocation, in which case the ZIL will resort to txg_wait_synced() to ensure the change is on disk. To provide a workaround for this, this change adds a tunable that can reduce the size of ZIL blocks. External-issue: DLPX-61719 Reviewed-by: George Wilson <[email protected]> Reviewed-by: Paul Dagnelie <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes #8865
* Fix comparison signedness in arc_is_overflowing()Alexander Motin2019-06-101-2/+2
| | | | | | | | | | | | When ARC size is very small, aggsum_lower_bound(&arc_size) may return negative values, that due to unsigned comparison caused delays, waiting for arc_adjust() to "fix" it by calling aggsum_value(&arc_size). Use of signed comparison there fixes the problem. Reviewed-by: Matt Ahrens <[email protected]> Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: George Melikov <[email protected]> Signed-off-by: Alexander Motin <[email protected]> Closes #8873