Compare commits

...

74 Commits

Author SHA1 Message Date
Gilbert Chen
e8b8922754 Continue to check other snapshots when one snapshot has missing chunks 2018-08-06 21:20:04 -04:00
Gilbert Chen
93cc632021 Record deleted snapshots in the fossil collection and if any deleted snapshot still exist nude the fossil collection 2018-08-04 22:59:25 -04:00
Gilbert Chen
48cc5eaedb Print git commit number 2018-08-03 23:45:23 -04:00
Gilbert Chen
f304b64b3f Removed a redundant call to manager.chunkOperator.Resurrect 2018-08-03 11:32:24 -04:00
Gilbert Chen
8ae7d2a97d Remove extra newline in the PRUNE_NEWSNAPSHOT log message 2018-07-26 21:24:33 -04:00
Gilbert Chen
fce4234861 Rearrange struct members to avoid 64-bit int alignment issues 2018-07-26 21:19:03 -04:00
gilbertchen
e499a24202 Merge pull request #459 from jtackaberry/master
Fix "Failed to fossilize chunk" errors in wasabi backend
2018-07-24 21:52:27 -04:00
Gilbert Chen
89769f3906 Add a -storage option to the benchmark command 2018-07-23 22:54:56 -04:00
Gilbert Chen
798cec0714 Bump version to 2.1.1 2018-07-23 22:10:12 -04:00
Gilbert Chen
72dfaa8b6b Fixed a bug causing a new snapshot to be not counted when deciding which fossils can be deleted 2018-07-23 22:08:08 -04:00
Jason Tackaberry
117cfd997f Make Wasabi double slash fix more idiomatic 2018-07-13 12:43:27 -04:00
Jason Tackaberry
84f7c513d5 Fix "Failed to fossilize chunk" errors in wasabi backend
Fixes #458
2018-07-11 22:55:04 -04:00
gilbertchen
dfdbfed64b Merge pull request #449 from gilbertchen/benchmark_command
Benchmark command
2018-07-02 16:26:28 -04:00
gilbertchen
d4a65ffbcf Merge pull request #441 from gilbertchen/threaded_prune
Implement multithreaded pruning
2018-07-02 16:20:41 -04:00
gilbertchen
736003323a Merge pull request #417 from amarcu5/fix-permissions
Fixed restoration of basic UNIX file permissions
2018-07-02 14:31:10 -04:00
gilbertchen
0af74616b7 Merge pull request #415 from amarcu5/master
Add APFS snapshot support
2018-07-02 12:41:19 -04:00
gilbertchen
0f552c8c50 Update ISSUE_TEMPLATE.md 2018-06-20 23:24:59 -04:00
gilbertchen
1adf92e879 Create ISSUE_TEMPLATE.md 2018-06-20 23:24:02 -04:00
Gilbert Chen
f92f1a728c Check in src/duplicacy_benchmark.go 2018-06-17 22:09:47 -04:00
Gilbert Chen
9a0dcdb0b2 Add a benchmark command to test disk and network speeds 2018-06-17 22:00:01 -04:00
Gilbert Chen
9ae306644d Avoid filepath.Dir as it returns paths with back slashes on Windows 2018-06-07 16:00:39 -04:00
Gilbert Chen
6f0166be6d Add a test for multi-threaded pruning 2018-06-06 13:11:19 -04:00
Gilbert Chen
f68eb13584 A few fixes for multi-threaded pruning 2018-06-05 16:09:12 -04:00
Gilbert Chen
dd53b4797e Implement multi-threaded pruning 2018-06-04 21:52:07 -04:00
Gilbert Chen
7e021f26d3 Don't show the nil error when failing to replace a file with a directory during restore 2018-05-30 13:23:35 -04:00
Gilbert Chen
0e585e4be4 Fixed a crashing bug when showing the history of excluded files 2018-05-30 12:05:40 -04:00
Gilbert Chen
e03cd2a880 Add unreferenced fossils to the fossil collection instead of deleting them immediately 2018-05-29 12:57:38 -04:00
Gilbert Chen
f80a5b1025 Fixed format argument errors 2018-05-24 11:37:52 -04:00
Gilbert Chen
aadd2aa390 Add an -enum-only option to the backup command to enumerate the repository only 2018-05-24 11:34:46 -04:00
Gilbert Chen
72239a31c4 Add -repository optiont to init add add to specifiy an alternate repository path 2018-05-22 15:55:52 -04:00
gilbertchen
c9b60cc0e0 Merge pull request #394 from gilbertchen/webdav
Implement the WebDAV backend
2018-05-16 23:31:46 -04:00
gilbertchen
f4cdd1f01b Merge pull request #392 from fhriley/nobackup_file
Add nobackup-file preference.
2018-05-16 23:31:09 -04:00
Gilbert Chen
b1c1b47983 Add an env var DUPLICACY_DECRYPT_WITH_HMACSHA256 to force using HMAC-SHA256 for encryption key in order to be able to manage backups created by Vertical Backup 2018-05-02 22:57:47 -04:00
amarcu5
8c3ef6cae9 Improved cron support
Now calls mount and unmount using absolute path
2018-04-30 00:40:34 +01:00
amarcu5
acd7addc9a Fixed Windows complication 2018-04-30 00:36:11 +01:00
amarcu5
c23ea30da4 Updated VSS flag usage
VSS flag usage now indicates support for macOS using APFS in addition to Windows
2018-04-29 23:24:22 +01:00
amarcu5
a4c46624ea Fix basic UNIX permissions 2018-04-29 20:24:50 +01:00
amarcu5
5747d6763f Improved error handling
Minor improvement to error handling and small formatting changes
2018-04-29 13:33:17 +01:00
amarcu5
ef1d316f33 Cleaned up formatting
Fixed tabbing
2018-04-29 04:21:28 +01:00
amarcu5
714a45c34a Improved macOS VSS checks
VSS support now determined by:
1) Checking that repository filesystem is APFS rather than by inspecting macOS version
2) Checking that repository resides on local device (as external APFS formatted drives are not supported) rather than crudely by path name
2018-04-29 04:11:10 +01:00
Gilbert Chen
23a2d91608 Skipped chunks should not be counted in order to get accurate download percentage 2018-04-28 20:19:24 -04:00
amarcu5
23b98a3034 Added macOS VSS checks
Restricts VSS under macOS to version 10.13 High Sierra or higher and local volume only
2018-04-28 23:09:59 +01:00
amarcu5
8a3c5847a8 Cleaned up formatting 2018-04-28 21:23:00 +01:00
amarcu5
4c3d5dbc2f Add APFS snapshot support
Add's VSS support for macOS using APFS snapshot's
2018-04-28 17:58:47 +01:00
Gilbert Chen
85bc55e374 The -threads option for the copy command specifies the number of uploading threads 2018-04-11 21:11:24 -04:00
gilbertchen
cd0c7b07a9 Update README.md 2018-04-06 22:27:31 -04:00
gilbertchen
0ea26a92dd Update README.md 2018-04-06 09:46:42 -04:00
gilbertchen
ca889fca9f Update README.md 2018-04-06 09:28:05 -04:00
gilbertchen
fbaea6e8b1 Update README.md 2018-04-06 00:06:48 -04:00
gilbertchen
2290c4ace0 Add files via upload 2018-04-05 23:36:57 -04:00
Gilbert Chen
02cd41f4d0 A few improvements to make WebDAV work better with pcloud and box.com 2018-04-05 15:29:41 -04:00
Gilbert Chen
0db8b9831b Implement the WebDAV backend 2018-04-02 20:03:50 -04:00
Frank
4dd5c43307 Add nobackup-file preference.
Directories containing a file with this name will not be backed up. I find it easier to drop a .nobackup file in directories I don't want backed up instead of maintaining a file of exclusions. This is also useful for scripts that create data in the repository but don't want it to be backed up.
2018-04-01 12:50:00 -07:00
Gilbert Chen
6aedc37118 Update the description for the -comment option 2018-03-28 22:19:18 -04:00
gilbertchen
9a56ede07c Merge pull request #391 from jeffaco/jeff-comment
Add -comment capability to allow for duplicacy jobs to be identified with 'ps'
2018-03-28 22:10:58 -04:00
Jeff Coffler
c6e9460b7b Add 'How to build' reference to README.md. 2018-03-28 11:22:46 -07:00
Jeff Coffler
e74ab809ae Add new qualifier, -comment, to more easily identify specific jobs.
This qualifier allows specific text to be associated with a backup
job to easily associate what repository (or other context) a
duplicacy job is running on behalf of.
2018-03-28 10:16:08 -07:00
Gilbert Chen
5d2242d39d Preserve the list of chunk hashes for the latest snapshot when cleaning local snapshot cache 2018-03-27 23:34:40 -04:00
Gilbert Chen
b99f4bffec Follow symlinks that point to paths starting with \\ 2018-03-22 22:37:09 -04:00
Gilbert Chen
be2856ebbd Add a -vss-timeout option to set VSS creation timeout 2018-03-21 22:34:14 -04:00
Gilbert Chen
1ea615fb45 Fix the names of prune tests so they can be run all in once 2018-03-20 15:03:03 -04:00
Gilbert Chen
7d933a2576 Create two identical snapshots in prune test to catch a retrive-after-deletion bug 2018-03-20 14:37:47 -04:00
gilbertchen
13fffc2a11 Merge pull request #329 from pdf/prune_memory
Reduce memory consumption for prune operation
2018-03-20 14:32:12 -04:00
gilbertchen
9658463ebe Merge pull request #331 from markfeit/master
Added semi-dedicated Wasabi storage module.  #322
2018-03-19 12:03:31 -04:00
gilbertchen
cd77a029ea Merge branch 'master' into master 2018-03-19 11:53:11 -04:00
Mark Feit
8fdb399e1b Correct handling of @ in region to be consistent with everythng else. 2018-02-11 07:51:34 -05:00
Mark Feit
9d632c0434 Handle application/testing region string inconsistency. 2018-02-10 10:16:04 -05:00
Mark Feit
cc6e96527e Add/rearrange returns to keep the compiler from complaining. 2018-02-10 10:15:40 -05:00
Peter Fern
57082cd1d2 Reduce memory consumption for prune operation
For non-exhaustive prune, consider only target chunks instead of mapping
all chunks in repository.
2018-01-21 10:12:09 +11:00
Peter Fern
bd5a689b7d Add keepChunkHashes flag to GetSnapshotChunks, allowing reduced memory 2018-01-21 10:11:59 +11:00
Mark Feit
b52d6b3f7f Incorporated PR feedback; call S3 for IsFastListing() #322 2018-01-18 08:34:33 -05:00
Mark Feit
8aaca37a2b Added note about Wasabi dependency. 2018-01-18 08:30:00 -05:00
Mark Feit
30f753e499 Cosmetic and key name fixes. #322 2018-01-16 22:19:41 -05:00
Mark Feit
d0771be2dd Added semi-dedicated Wasabi storage module. #322 2018-01-16 22:06:11 -05:00
30 changed files with 2239 additions and 438 deletions

5
.github/ISSUE_TEMPLATE.md vendored Normal file
View File

@@ -0,0 +1,5 @@
Please submit an issue for bug reports or feature requests. If you have any questions please post them on https://forum.duplicacy.com.
When you're reporting a bug, please specify the OS, version, command line arguments, or any info that you think is helpful for the diagnosis. If Duplicacy reports an error, please post the program output here.
Note that this repository hosts the CLI version of Duplicacy only. If you're reporting anything related to the GUI version, please visit https://forum.duplicacy.com.

119
README.md
View File

@@ -1,129 +1,92 @@
# Duplicacy: A lock-free deduplication cloud backup tool
Duplicacy is a new generation cross-platform cloud backup tool based on the idea of [Lock-Free Deduplication](https://github.com/gilbertchen/duplicacy/wiki/Lock-Free-Deduplication). It is the only cloud backup tool that allows multiple computers to back up to the same storage simultaneously without using any locks (thus readily amenable to various cloud storage services).
Duplicacy is a new generation cross-platform cloud backup tool based on the idea of [Lock-Free Deduplication](https://github.com/gilbertchen/duplicacy/wiki/Lock-Free-Deduplication).
The repository hosts source code, design documents, and binary releases of the command line version. There is also a Duplicacy GUI frontend built for Windows and Mac OS X available from https://duplicacy.com.
This repository hosts source code, design documents, and binary releases of the command line version of Duplicacy. There is also a Duplicacy GUI frontend built for Windows and Mac OS X available from https://duplicacy.com.
There is a special edition of Duplicacy developed for VMware vSphere (ESXi) named [Vertical Backup](https://www.verticalbackup.com) that can back up virtual machine files on ESXi to local drives, network or cloud storages.
## Features
Duplicacy currently supports major cloud storage providers (Amazon S3, Google Cloud Storage, Microsoft Azure, Dropbox, Backblaze B2, Google Drive, Microsoft OneDrive, and Hubic) and offers all essential features of a modern backup tool:
There are 3 core advantages of Duplicacy over any other open-source or commercial backup tools:
* Incremental backup: only back up what has been changed
* Full snapshot: although each backup is incremental, it must behave like a full snapshot for easy restore and deletion
* Deduplication: identical files must be stored as one copy (file-level deduplication), and identical parts from different files must be stored as one copy (block-level deduplication)
* Encryption: encrypt not only file contents but also file paths, sizes, times, etc.
* Deletion: every backup can be deleted independently without affecting others
* Concurrent access: multiple clients can back up to the same storage at the same time
* Snapshot migration: all or selected snapshots can be migrated from one storage to another
* Duplicacy is the *only* cloud backup tool that allows multiple computers to back up to the same cloud storage, taking advantage of cross-computer deduplication whenever possible, without direct communication among them. This feature literally turns any cloud storage server supporting only a basic set of file operations into a sophisticated deduplication-aware server.
The key idea of **[Lock-Free Deduplication](https://github.com/gilbertchen/duplicacy/wiki/Lock-Free-Deduplication)** can be summarized as follows:
* Unlike other chunk-based backup tools where chunks are grouped into pack files and a chunk database is used to track which chunks are stored inside each pack file, Duplicacy takes a database-less approach where every chunk is saved independently using its hash as the file name to facilitate quick lookups. The lack of a centralized chunk database not only makes the implementation less error-prone, but also produces a highly maintainable piece of software with plenty of room for development of new features and usability enhancements.
* Use variable-size chunking algorithm to split files into chunks
* Store each chunk in the storage using a file name derived from its hash, and rely on the file system API to manage chunks without using a centralized indexing database
* Apply a *two-step fossil collection* algorithm to remove chunks that become unreferenced after a backup is deleted
* Duplicacy is fast. While the performance wasn't the top-priority design goal, Duplicacy has been shown to outperform other backup tools by a considerable margin, as indicated by the following results obtained from a [benchmarking experiment](https://github.com/gilbertchen/benchmarking) backing up the [Linux code base](https://github.com/torvalds/linux) using Duplicacy and 3 other open-source backup tools.
[![Comparison of Duplicacy, restic, Attic, duplicity](https://github.com/gilbertchen/duplicacy/blob/master/images/duplicacy_benchmark_speed.png "Comparison of Duplicacy, restic, Attic, duplicity")](https://github.com/gilbertchen/benchmarking)
## Getting Started
* [A brief introduction](https://github.com/gilbertchen/duplicacy/wiki/Quick-Start)
* [Command references](https://github.com/gilbertchen/duplicacy/wiki)
* [Building from source](https://github.com/gilbertchen/duplicacy/wiki/Installation)
## Storages
With Duplicacy, you can back up files to local or networked drives, SFTP servers, or many cloud storage providers. The following table compares the costs of all cloud storages supported by Duplicacy.
Duplicacy currently provides the following storage backends:
| Type | Storage (monthly) | Upload | Download | API Charge |
|:------------:|:-------------:|:------------------:|:--------------:|:-----------:|
| Amazon S3 | $0.023/GB | free | $0.090/GB | [yes](https://aws.amazon.com/s3/pricing/) |
| Wasabi | $3.99 first 1TB <br> $0.0039/GB additional | free | $0.04/GB | no |
| DigitalOcean Spaces| $5 first 250GB <br> $0.020/GB additional | free | first 1TB free <br> $0.01/GB additional| no |
| Backblaze B2 | 10GB free <br> $0.005/GB | free | 1GB free/day <br> $0.02/GB | [yes](https://www.backblaze.com/b2/b2-transactions-price.html) |
| Google Cloud Storage| $0.026/GB | free |$ 0.12/GB | [yes](https://cloud.google.com/storage/pricing) |
| Google Drive | 15GB free <br> $1.99/100GB <br> $9.99/TB | free | free | no |
| Microsoft Azure | $0.0184/GB | free | free | [yes](https://azure.microsoft.com/en-us/pricing/details/storage/blobs/) |
| Microsoft OneDrive | 5GB free <br> $1.99/50GB <br> $5.83/TB | free | free | no |
| Dropbox | 2GB free <br> $8.25/TB | free | free | no |
| Hubic | 25GB free <br> €1/100GB <br> €5/10TB | free | free | no |
* Local disk
* SFTP
* Dropbox
* Amazon S3
* Wasabi
* DigitalOcean Spaces
* Google Cloud Storage
* Microsoft Azure
* Backblaze B2
* Google Drive
* Microsoft OneDrive
* Hubic
* OpenStack Swift
* WebDAV (under beta testing)
* pcloud (via WebDAV)
* Box.com (via WebDAV)
Please consult the [wiki page](https://github.com/gilbertchen/duplicacy/wiki/Storage-Backends) on how to set up Duplicacy to work with each cloud storage.
It should be noted that their performances vary a lot. A [performance comparison](https://github.com/gilbertchen/cloud-storage-comparison) of these storages measured the running times (in seconds) of backing up and restoring the [Linux code base](https://github.com/torvalds/linux) as follows:
For reference, the following chart shows the running times (in seconds) of backing up the [Linux code base](https://github.com/torvalds/linux) to each of those supported storages:
| Storage | initial backup | 2nd | 3rd | initial restore | 2nd | 3rd |
|:--------------------:|:------:|:----:|:-----:|:----:|:-----:|:----:|
| SFTP | 31.5 | 6.6 | 20.6 | 22.5 | 7.8 | 18.4 |
| Amazon S3 | 41.1 | 5.9 | 21.9 | 27.7 | 7.6 | 23.5 |
| Wasabi | 38.7 | 5.7 | 31.7 | 25.7 | 6.5 | 23.2 |
| DigitalOcean Spaces | 51.6 | 7.1 | 31.7 | 29.3 | 6.4 | 27.6 |
| Backblaze B2 | 106.7 | 24.0 | 88.2 | 67.9 | 14.4 | 39.1 |
| Google Cloud Storage | 76.9 | 11.9 | 33.1 | 39.5 | 9.9 | 26.2 |
| Google Drive | 139.3 | 14.7 | 45.2 | 129.4 | 17.8 | 54.4 |
| Microsoft Azure | 35.0 | 5.4 | 20.4 | 30.7 | 7.1 | 21.5 |
| Microsoft OneDrive | 250.0 | 31.6 | 80.2 | 333.4 | 26.2 | 82.0 |
| Dropbox | 267.2 | 35.8 | 113.7 | 164.0 | 31.6 | 80.3 |
For more details please visit https://github.com/gilbertchen/cloud-storage-comparison.
[![Comparison of Cloud Storages](https://github.com/gilbertchen/duplicacy/blob/master/images/duplicacy_benchmark_cloud.png "Comparison of Cloud Storages")](https://github.com/gilbertchen/cloud-storage-comparison)
## Feature Comparison with Other Backup Tools
For complete benchmark results please visit https://github.com/gilbertchen/cloud-storage-comparison.
## Comparison with Other Backup Tools
[duplicity](http://duplicity.nongnu.org) works by applying the rsync algorithm (or more specific, the [librsync](https://github.com/librsync/librsync) library)
to find the differences from previous backups and only then uploading the differences. It is the only existing backup tool with extensive cloud support -- the [long list](http://duplicity.nongnu.org/duplicity.1.html#sect7) of storage backends covers almost every cloud provider one can think of. However, duplicity's biggest flaw lies in its incremental model -- a chain of dependent backups starts with a full backup followed by a number of incremental ones, and ends when another full backup is uploaded. Deleting one backup will render useless all the subsequent backups on the same chain. Periodic full backups are required, in order to make previous backups disposable.
[bup](https://github.com/bup/bup) also uses librsync to split files into chunks but save chunks in the git packfile format. It doesn't support any cloud storage, or deletion of old backups.
[Obnam](http://obnam.org) got the incremental backup model right in the sense that every incremental backup is actually a full snapshot. Although Obnam also splits files into chunks, it does not adopt either the rsync algorithm or the variable-size chunking algorithm. As a result, deletions or insertions of a few bytes will foil the
[deduplication](http://obnam.org/faq/dedup).
Deletion of old backups is possible, but no cloud storages are supported.
Multiple clients can back up to the same storage, but only sequential access is granted by the [locking on-disk data structures](http://obnam.org/locking/).
It is unclear if the lack of cloud backends is due to difficulties in porting the locking data structures to cloud storage APIs.
[Duplicati](https://duplicati.com) is one of the first backup tools that adopt the chunk-based approach to split files into chunks which are then uploaded to the storage. The chunk-based approach got the incremental backup model right in the sense that every incremental backup is actually a full snapshot. As Duplicati splits files into fixed-size chunks, deletions or insertions of a few bytes will foil the deduplication. Cloud support is extensive, but multiple clients can't back up to the same storage location.
[Attic](https://attic-backup.org) has been acclaimed by some as the [Holy Grail of backups](https://www.stavros.io/posts/holy-grail-backups). It follows the same incremental backup model as Obnam, but embraces the variable-size chunk algorithm for better performance and better deduplication. Deletions of old backup is also supported. However, no cloud backends are implemented, as in Obnam. Although concurrent backups from multiple clients to the same storage is in theory possible by the use of locking, it is
[Attic](https://attic-backup.org) has been acclaimed by some as the [Holy Grail of backups](https://www.stavros.io/posts/holy-grail-backups). It follows the same incremental backup model like Duplicati, but embraces the variable-size chunk algorithm for better performance and higher deduplication efficiency (not susceptible to byte insertion and deletion any more). Deletions of old backup is also supported. However, no cloud backends are implemented. Although concurrent backups from multiple clients to the same storage is in theory possible by the use of locking, it is
[not recommended](http://librelist.com/browser//attic/2014/11/11/backing-up-multiple-servers-into-a-single-repository/#e96345aa5a3469a87786675d65da492b) by the developer due to chunk indices being kept in a local cache.
Concurrent access is not only a convenience; it is a necessity for better deduplication. For instance, if multiple machines with the same OS installed can back up their entire drives to the same storage, only one copy of the system files needs to be stored, greatly reducing the storage space regardless of the number of machines. Attic still adopts the traditional approach of using a centralized indexing database to manage chunks, and relies heavily on caching to improve performance. The presence of exclusive locking makes it hard to be adapted for cloud storage APIs and reduces the level of deduplication.
Concurrent access is not only a convenience; it is a necessity for better deduplication. For instance, if multiple machines with the same OS installed can back up their entire drives to the same storage, only one copy of the system files needs to be stored, greatly reducing the storage space regardless of the number of machines. Attic still adopts the traditional approach of using a centralized indexing database to manage chunks, and relies heavily on caching to improve performance. The presence of exclusive locking makes it hard to be extended to cloud storages.
[restic](https://restic.github.io) is a more recent addition. It is worth mentioning here because, like Duplicacy, it is written in Go. It uses a format similar to the git packfile format. Multiple clients backing up to the same storage are still guarded by
[locks](https://github.com/restic/restic/blob/master/doc/Design.md#locks). A prune operation will therefore completely block all other clients connected to the storage from doing their regular backups. Moreover, since most cloud storage services do not provide a locking service, the best effort is to use some basic file operations to simulate a lock, but distributed locking is known to be a hard problem and it is unclear how reliable restic's lock implementation is. A faulty implementation may cause a prune operation to accidentally delete data still in use, resulting in unrecoverable data loss. This is the exact problem that we avoided by taking the lock-free approach.
[restic](https://restic.github.io) is a more recent addition. It uses a format similar to the git packfile format. Multiple clients backing up to the same storage are still guarded by
[locks](https://github.com/restic/restic/blob/master/doc/Design.md#locks), and because a chunk database is used, deduplication isn't real-time (different clients sharing the same files will upload different copies of the same chunks). A prune operation will completely block all other clients connected to the storage from doing their regular backups. Moreover, since most cloud storage services do not provide a locking service, the best effort is to use some basic file operations to simulate a lock, but distributed locking is known to be a hard problem and it is unclear how reliable restic's lock implementation is. A faulty implementation may cause a prune operation to accidentally delete data still in use, resulting in unrecoverable data loss. This is the exact problem that we avoided by taking the lock-free approach.
The following table compares the feature lists of all these backup tools:
| Feature/Tool | duplicity | bup | Obnam | Attic | restic | **Duplicacy** |
| Feature/Tool | duplicity | bup | Duplicati | Attic | restic | **Duplicacy** |
|:------------------:|:---------:|:---:|:-----------------:|:---------------:|:-----------------:|:-------------:|
| Incremental Backup | Yes | Yes | Yes | Yes | Yes | **Yes** |
| Full Snapshot | No | Yes | Yes | Yes | Yes | **Yes** |
| Compression | Yes | Yes | Yes | Yes | No | **Yes** |
| Deduplication | Weak | Yes | Weak | Yes | Yes | **Yes** |
| Encryption | Yes | Yes | Yes | Yes | Yes | **Yes** |
| Deletion | No | No | Yes | Yes | No | **Yes** |
| Concurrent Access | No | No | Exclusive locking | Not recommended | Exclusive locking | **Lock-free** |
| Cloud Support | Extensive | No | No | No | S3, B2, OpenStack | **S3, GCS, Azure, Dropbox, Backblaze B2, Google Drive, OneDrive, and Hubic**|
| Concurrent Access | No | No | No | Not recommended | Exclusive locking | **Lock-free** |
| Cloud Support | Extensive | No | Extensive | No | Limited | **Extensive** |
| Snapshot Migration | No | No | No | No | No | **Yes** |
## Performance Comparison with Other Backup Tools
Duplicacy is not only more feature-rich but also faster than other backup tools. The following table lists the running times in seconds of backing up the [Linux code base](https://github.com/torvalds/linux) using Duplicacy and 3 other tools. Clearly Duplicacy is the fastest by a significant margin.
| | Duplicacy | restic | Attic | duplicity |
|:------------------:|:----------------:|:----------:|:----------:|:-----------:|
| Initial backup | 13.7 | 20.7 | 26.9 | 44.2 |
| 2nd backup | 4.8 | 8.0 | 15.4 | 19.5 |
| 3rd backup | 6.9 | 11.9 | 19.6 | 29.8 |
| 4th backup | 3.3 | 7.0 | 13.7 | 18.6 |
| 5th backup | 9.9 | 11.4 | 19.9 | 28.0 |
| 6th backup | 3.8 | 8.0 | 16.8 | 22.0 |
| 7th backup | 5.1 | 7.8 | 14.3 | 21.6 |
| 8th backup | 9.5 | 13.5 | 18.3 | 35.0 |
| 9th backup | 4.3 | 9.0 | 15.7 | 24.9 |
| 10th backup | 7.9 | 20.2 | 32.2 | 35.0 |
| 11th backup | 4.6 | 9.1 | 16.8 | 28.1 |
| 12th backup | 7.4 | 12.0 | 21.7 | 37.4 |
For more details and other speed comparison results, please visit https://github.com/gilbertchen/benchmarking. There you can also find test scripts that you can use to run your own experiments.
## License
* Free for personal use or commercial trial

View File

@@ -32,6 +32,7 @@ const (
)
var ScriptEnabled bool
var GitCommit = "unofficial"
func getRepositoryPreference(context *cli.Context, storageName string) (repository string,
preference *duplicacy.Preference) {
@@ -71,6 +72,10 @@ func getRepositoryPreference(context *cli.Context, storageName string) (reposito
}
if storageName == "" {
if duplicacy.Preferences[0].RepositoryPath != "" {
repository = duplicacy.Preferences[0].RepositoryPath
duplicacy.LOG_INFO("REPOSITORY_SET", "Repository set to %s", repository)
}
return repository, &duplicacy.Preferences[0]
}
@@ -80,6 +85,12 @@ func getRepositoryPreference(context *cli.Context, storageName string) (reposito
duplicacy.LOG_ERROR("STORAGE_NONE", "No storage named '%s' is found", storageName)
return "", nil
}
if preference.RepositoryPath != "" {
repository = preference.RepositoryPath
duplicacy.LOG_INFO("REPOSITORY_SET", "Repository set to %s", repository)
}
return repository, preference
}
@@ -293,9 +304,14 @@ func configRepository(context *cli.Context, init bool) {
}
}
repositoryPath := ""
if context.String("repository") != "" {
repositoryPath = context.String("repository")
}
preference := duplicacy.Preference{
Name: storageName,
SnapshotID: snapshotID,
RepositoryPath: repositoryPath,
StorageURL: storageURL,
Encrypted: context.Bool("encrypt"),
}
@@ -427,8 +443,12 @@ func configRepository(context *cli.Context, init bool) {
duplicacy.SavePreferences()
if repositoryPath == "" {
repositoryPath = repository
}
duplicacy.LOG_INFO("REPOSITORY_INIT", "%s will be backed up to %s with id %s",
repository, preference.StorageURL, preference.SnapshotID)
repositoryPath, preference.StorageURL, preference.SnapshotID)
}
type TriBool struct {
@@ -514,6 +534,8 @@ func setPreference(context *cli.Context) {
newPreference.DoNotSavePassword = triBool.IsTrue()
}
newPreference.NobackupFile = context.String("nobackup-file")
key := context.String("key")
value := context.String("value")
@@ -689,16 +711,18 @@ func backupRepository(context *cli.Context) {
showStatistics := context.Bool("stats")
enableVSS := context.Bool("vss")
vssTimeout := context.Int("vss-timeout")
dryRun := context.Bool("dry-run")
uploadRateLimit := context.Int("limit-rate")
enumOnly := context.Bool("enum-only")
storage.SetRateLimits(0, uploadRateLimit)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password, preference.NobackupFile)
duplicacy.SavePassword(*preference, "password", password)
backupManager.SetupSnapshotCache(preference.Name)
backupManager.SetDryRun(dryRun)
backupManager.Backup(repository, quickMode, threads, context.String("t"), showStatistics, enableVSS)
backupManager.Backup(repository, quickMode, threads, context.String("t"), showStatistics, enableVSS, vssTimeout, enumOnly)
runScript(context, preference.Name, "post")
}
@@ -782,7 +806,7 @@ func restoreRepository(context *cli.Context) {
duplicacy.LOG_DEBUG("REGEX_DEBUG", "There are %d compiled regular expressions stored", len(duplicacy.RegexMap))
storage.SetRateLimits(context.Int("limit-rate"), 0)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password, preference.NobackupFile)
duplicacy.SavePassword(*preference, "password", password)
backupManager.SetupSnapshotCache(preference.Name)
@@ -822,7 +846,7 @@ func listSnapshots(context *cli.Context) {
tag := context.String("t")
revisions := getRevisions(context)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password, preference.NobackupFile)
duplicacy.SavePassword(*preference, "password", password)
id := preference.SnapshotID
@@ -870,7 +894,7 @@ func checkSnapshots(context *cli.Context) {
tag := context.String("t")
revisions := getRevisions(context)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password, preference.NobackupFile)
duplicacy.SavePassword(*preference, "password", password)
id := preference.SnapshotID
@@ -925,7 +949,7 @@ func printFile(context *cli.Context) {
snapshotID = context.String("id")
}
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password, preference.NobackupFile)
duplicacy.SavePassword(*preference, "password", password)
backupManager.SetupSnapshotCache(preference.Name)
@@ -981,11 +1005,11 @@ func diff(context *cli.Context) {
}
compareByHash := context.Bool("hash")
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password, preference.NobackupFile)
duplicacy.SavePassword(*preference, "password", password)
backupManager.SetupSnapshotCache(preference.Name)
backupManager.SnapshotManager.Diff(repository, snapshotID, revisions, path, compareByHash)
backupManager.SnapshotManager.Diff(repository, snapshotID, revisions, path, compareByHash, preference.NobackupFile)
runScript(context, preference.Name, "post")
}
@@ -1024,7 +1048,7 @@ func showHistory(context *cli.Context) {
revisions := getRevisions(context)
showLocalHash := context.Bool("hash")
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password, preference.NobackupFile)
duplicacy.SavePassword(*preference, "password", password)
backupManager.SetupSnapshotCache(preference.Name)
@@ -1043,12 +1067,17 @@ func pruneSnapshots(context *cli.Context) {
os.Exit(ArgumentExitCode)
}
threads := context.Int("threads")
if threads < 1 {
threads = 1
}
repository, preference := getRepositoryPreference(context, "")
runScript(context, preference.Name, "pre")
duplicacy.LOG_INFO("STORAGE_SET", "Storage set to %s", preference.StorageURL)
storage := duplicacy.CreateStorage(*preference, false, 1)
storage := duplicacy.CreateStorage(*preference, false, threads)
if storage == nil {
return
}
@@ -1082,12 +1111,12 @@ func pruneSnapshots(context *cli.Context) {
os.Exit(ArgumentExitCode)
}
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password)
backupManager := duplicacy.CreateBackupManager(preference.SnapshotID, storage, repository, password, preference.NobackupFile)
duplicacy.SavePassword(*preference, "password", password)
backupManager.SetupSnapshotCache(preference.Name)
backupManager.SnapshotManager.PruneSnapshots(selfID, snapshotID, revisions, tags, retentions,
exhaustive, exclusive, ignoredIDs, dryRun, deleteOnly, collectOnly)
exhaustive, exclusive, ignoredIDs, dryRun, deleteOnly, collectOnly, threads)
runScript(context, preference.Name, "post")
}
@@ -1122,7 +1151,7 @@ func copySnapshots(context *cli.Context) {
sourcePassword = duplicacy.GetPassword(*source, "password", "Enter source storage password:", false, false)
}
sourceManager := duplicacy.CreateBackupManager(source.SnapshotID, sourceStorage, repository, sourcePassword)
sourceManager := duplicacy.CreateBackupManager(source.SnapshotID, sourceStorage, repository, sourcePassword, source.NobackupFile)
sourceManager.SetupSnapshotCache(source.Name)
duplicacy.SavePassword(*source, "password", sourcePassword)
@@ -1155,7 +1184,7 @@ func copySnapshots(context *cli.Context) {
destinationStorage.SetRateLimits(0, context.Int("upload-limit-rate"))
destinationManager := duplicacy.CreateBackupManager(destination.SnapshotID, destinationStorage, repository,
destinationPassword)
destinationPassword, destination.NobackupFile)
duplicacy.SavePassword(*destination, "password", destinationPassword)
destinationManager.SetupSnapshotCache(destination.Name)
@@ -1239,6 +1268,50 @@ func infoStorage(context *cli.Context) {
}
func benchmark(context *cli.Context) {
setGlobalOptions(context)
defer duplicacy.CatchLogException()
fileSize := context.Int("file-size")
if fileSize == 0 {
fileSize = 256
}
chunkCount := context.Int("chunk-count")
if chunkCount == 0 {
chunkCount = 64
}
chunkSize := context.Int("chunk-size")
if chunkSize == 0 {
chunkSize = 4
}
downloadThreads := context.Int("download-threads")
if downloadThreads < 1 {
downloadThreads = 1
}
uploadThreads := context.Int("upload-threads")
if uploadThreads < 1 {
uploadThreads = 1
}
threads := downloadThreads
if (threads < uploadThreads) {
threads = uploadThreads
}
repository, preference := getRepositoryPreference(context, context.String("storage"))
duplicacy.LOG_INFO("STORAGE_SET", "Storage set to %s", preference.StorageURL)
storage := duplicacy.CreateStorage(*preference, false, threads)
if storage == nil {
return
}
duplicacy.Benchmark(repository, storage, int64(fileSize) * 1000000, chunkSize * 1024 * 1024, chunkCount, uploadThreads, downloadThreads)
}
func main() {
duplicacy.SetLoggingLevel(duplicacy.INFO)
@@ -1284,6 +1357,11 @@ func main() {
Usage: "assign a name to the storage",
Argument: "<name>",
},
cli.StringFlag{
Name: "repository",
Usage: "initialize a new repository at the specified path rather than the current working directory",
Argument: "<path>",
},
},
Usage: "Initialize the storage if necessary and the current directory as the repository",
ArgsUsage: "<snapshot id> <storage url>",
@@ -1323,13 +1401,23 @@ func main() {
},
cli.BoolFlag{
Name: "vss",
Usage: "enable the Volume Shadow Copy service (Windows only)",
Usage: "enable the Volume Shadow Copy service (Windows and macOS using APFS only)",
},
cli.IntFlag{
Name: "vss-timeout",
Value: 0,
Usage: "the timeout in seconds to wait for the Volume Shadow Copy operation to complete",
Argument: "<timeout>",
},
cli.StringFlag{
Name: "storage",
Usage: "backup to the specified storage instead of the default one",
Argument: "<storage name>",
},
cli.BoolFlag{
Name: "enum-only",
Usage: "enumerate the repository recursively and then exit",
},
},
Usage: "Save a snapshot of the repository to the storage",
ArgsUsage: " ",
@@ -1620,6 +1708,12 @@ func main() {
Usage: "prune snapshots from the specified storage",
Argument: "<storage name>",
},
cli.IntFlag{
Name: "threads",
Value: 1,
Usage: "number of threads used to prune unreferenced chunks",
Argument: "<n>",
},
},
Usage: "Prune snapshots by revision, tag, or retention policy",
ArgsUsage: " ",
@@ -1682,6 +1776,11 @@ func main() {
Name: "bit-identical",
Usage: "(when using -copy) make the new storage bit-identical to also allow rsync etc.",
},
cli.StringFlag{
Name: "repository",
Usage: "specify the path of the repository (instead of the current working directory)",
Argument: "<path>",
},
},
Usage: "Add an additional storage to be used for the existing repository",
ArgsUsage: "<storage name> <snapshot id> <storage url>",
@@ -1715,6 +1814,12 @@ func main() {
Value: &TriBool{},
Arg: "true",
},
cli.StringFlag{
Name: "nobackup-file",
Usage: "Directories containing a file with this name will not be backed up",
Argument: "<file name>",
Value: "",
},
cli.StringFlag{
Name: "key",
Usage: "add a key/password whose value is supplied by the -value option",
@@ -1771,7 +1876,7 @@ func main() {
cli.IntFlag{
Name: "threads",
Value: 1,
Usage: "number of downloading threads",
Usage: "number of uploading threads",
Argument: "<n>",
},
},
@@ -1806,6 +1911,45 @@ func main() {
ArgsUsage: "<storage url>",
Action: infoStorage,
},
{
Name: "benchmark",
Flags: []cli.Flag{
cli.IntFlag{
Name: "file-size",
Usage: "the size of the local file to write to and read from (in MB, default to 256)",
Argument: "<size>",
},
cli.IntFlag{
Name: "chunk-count",
Usage: "the number of chunks to upload and download (default to 64)",
Argument: "<count>",
},
cli.IntFlag{
Name: "chunk-size",
Usage: "the size of chunks to upload and download (in MB, default to 4)",
Argument: "<size>",
},
cli.IntFlag{
Name: "upload-threads",
Usage: "the number of upload threads (default to 1)",
Argument: "<n>",
},
cli.IntFlag{
Name: "download-threads",
Usage: "the number of download threads (default to 1)",
Argument: "<n>",
},
cli.StringFlag{
Name: "storage",
Usage: "run the download/upload test agaist the specified storage",
Argument: "<storage name>",
},
},
Usage: "Run a set of benchmarks to test download and upload speeds",
ArgsUsage: " ",
Action: benchmark,
},
}
app.Flags = []cli.Flag{
@@ -1839,13 +1983,17 @@ func main() {
Usage: "enable the profiling tool and listen on the specified address:port",
Argument: "<address:port>",
},
}
cli.StringFlag{
Name: "comment",
Usage: "add a comment to identify the process",
},
}
app.HideVersion = true
app.Name = "duplicacy"
app.HelpName = "duplicacy"
app.Usage = "A new generation cloud backup tool based on lock-free deduplication"
app.Version = "2.1.0"
app.Version = "2.1.1" + " (" + GitCommit + ")"
// If the program is interrupted, call the RunAtError function.
c := make(chan os.Signal, 1)

Binary file not shown.

After

Width:  |  Height:  |  Size: 60 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 56 KiB

View File

@@ -55,7 +55,7 @@ func CreateACDStorage(tokenFile string, storagePath string, threads int) (storag
return nil, err
}
} else if !isDir {
return nil, fmt.Errorf("%s/%s is not a directory", storagePath+"/"+dir)
return nil, fmt.Errorf("%s is not a directory", storagePath+"/"+dir)
}
storage.idCache[dir] = dirID
}

View File

@@ -33,6 +33,8 @@ type BackupManager struct {
snapshotCache *FileStorage // for copies of chunks needed by snapshots
config *Config // contains a number of options
nobackupFile string // don't backup directory when this file name is found
}
func (manager *BackupManager) SetDryRun(dryRun bool) {
@@ -42,7 +44,7 @@ func (manager *BackupManager) SetDryRun(dryRun bool) {
// CreateBackupManager creates a backup manager using the specified 'storage'. 'snapshotID' is a unique id to
// identify snapshots created for this repository. 'top' is the top directory of the repository. 'password' is the
// master key which can be nil if encryption is not enabled.
func CreateBackupManager(snapshotID string, storage Storage, top string, password string) *BackupManager {
func CreateBackupManager(snapshotID string, storage Storage, top string, password string, nobackupFile string) *BackupManager {
config, _, err := DownloadConfig(storage, password)
if err != nil {
@@ -63,6 +65,8 @@ func CreateBackupManager(snapshotID string, storage Storage, top string, passwor
SnapshotManager: snapshotManager,
config: config,
nobackupFile: nobackupFile,
}
if IsDebugging() {
@@ -159,7 +163,7 @@ func setEntryContent(entries []*Entry, chunkLengths []int, offset int) {
// unmodified files with last backup). Otherwise (or if this is the first backup), the entire repository will
// be scanned to create the snapshot. 'tag' is the tag assigned to the new snapshot.
func (manager *BackupManager) Backup(top string, quickMode bool, threads int, tag string,
showStatistics bool, shadowCopy bool) bool {
showStatistics bool, shadowCopy bool, shadowCopyTimeout int, enumOnly bool) bool {
var err error
top, err = filepath.Abs(top)
@@ -180,16 +184,20 @@ func (manager *BackupManager) Backup(top string, quickMode bool, threads int, ta
LOG_INFO("BACKUP_START", "Last backup at revision %d found", remoteSnapshot.Revision)
}
shadowTop := CreateShadowCopy(top, shadowCopy)
shadowTop := CreateShadowCopy(top, shadowCopy, shadowCopyTimeout)
defer DeleteShadowCopy()
LOG_INFO("BACKUP_INDEXING", "Indexing %s", top)
localSnapshot, skippedDirectories, skippedFiles, err := CreateSnapshotFromDirectory(manager.snapshotID, shadowTop)
localSnapshot, skippedDirectories, skippedFiles, err := CreateSnapshotFromDirectory(manager.snapshotID, shadowTop, manager.nobackupFile)
if err != nil {
LOG_ERROR("SNAPSHOT_LIST", "Failed to list the directory %s: %v", top, err)
return false
}
if enumOnly {
return true
}
// This cache contains all chunks referenced by last snasphot. Any other chunks will lead to a call to
// UploadChunk.
chunkCache := make(map[string]bool)
@@ -199,7 +207,7 @@ func (manager *BackupManager) Backup(top string, quickMode bool, threads int, ta
// A revision number of 0 means this is the initial backup
if remoteSnapshot.Revision > 0 {
// Add all chunks in the last snapshot to the cache
for _, chunkID := range manager.SnapshotManager.GetSnapshotChunks(remoteSnapshot) {
for _, chunkID := range manager.SnapshotManager.GetSnapshotChunks(remoteSnapshot, true) {
chunkCache[chunkID] = true
}
} else {
@@ -752,7 +760,7 @@ func (manager *BackupManager) Restore(top string, revision int, inPlace bool, qu
remoteSnapshot := manager.SnapshotManager.DownloadSnapshot(manager.snapshotID, revision)
manager.SnapshotManager.DownloadSnapshotContents(remoteSnapshot, patterns, true)
localSnapshot, _, _, err := CreateSnapshotFromDirectory(manager.snapshotID, top)
localSnapshot, _, _, err := CreateSnapshotFromDirectory(manager.snapshotID, top, manager.nobackupFile)
if err != nil {
LOG_ERROR("SNAPSHOT_LIST", "Failed to list the repository: %v", err)
return false
@@ -767,10 +775,7 @@ func (manager *BackupManager) Restore(top string, revision int, inPlace bool, qu
for _, file := range remoteSnapshot.Files {
if MatchPath(file.Path, patterns) {
LOG_TRACE("RESTORE_INCLUDE", "Include %s", file.Path)
includedFiles = append(includedFiles, file)
} else {
LOG_TRACE("RESTORE_EXCLUDE", "Exclude %s", file.Path)
}
}
@@ -837,7 +842,7 @@ func (manager *BackupManager) Restore(top string, revision int, inPlace bool, qu
stat, err := os.Stat(fullPath)
if err == nil && !stat.IsDir() {
LOG_ERROR("RESTORE_NOTDIR", "The path %s is not a directory: %v", fullPath, err)
LOG_ERROR("RESTORE_NOTDIR", "The path %s is not a directory", fullPath)
return false
}

View File

@@ -239,11 +239,11 @@ func TestBackupManager(t *testing.T) {
time.Sleep(time.Duration(delay) * time.Second)
SetDuplicacyPreferencePath(testDir + "/repository1/.duplicacy")
backupManager := CreateBackupManager("host1", storage, testDir, password)
backupManager := CreateBackupManager("host1", storage, testDir, password, "")
backupManager.SetupSnapshotCache("default")
SetDuplicacyPreferencePath(testDir + "/repository1/.duplicacy")
backupManager.Backup(testDir+"/repository1" /*quickMode=*/, true, threads, "first", false, false)
backupManager.Backup(testDir+"/repository1" /*quickMode=*/, true, threads, "first", false, false, 0, false)
time.Sleep(time.Duration(delay) * time.Second)
SetDuplicacyPreferencePath(testDir + "/repository2/.duplicacy")
backupManager.Restore(testDir+"/repository2", threads, /*inPlace=*/false, /*quickMode=*/false, threads, /*overwrite=*/true,
@@ -267,7 +267,7 @@ func TestBackupManager(t *testing.T) {
modifyFile(testDir+"/repository1/dir1/file3", 0.3)
SetDuplicacyPreferencePath(testDir + "/repository1/.duplicacy")
backupManager.Backup(testDir+"/repository1" /*quickMode=*/, true, threads, "second", false, false)
backupManager.Backup(testDir+"/repository1" /*quickMode=*/, true, threads, "second", false, false, 0, false)
time.Sleep(time.Duration(delay) * time.Second)
SetDuplicacyPreferencePath(testDir + "/repository2/.duplicacy")
backupManager.Restore(testDir+"/repository2", 2, /*inPlace=*/true, /*quickMode=*/true, threads, /*overwrite=*/true,
@@ -287,7 +287,7 @@ func TestBackupManager(t *testing.T) {
os.Mkdir(testDir+"/repository1/dir2/dir3", 0700)
os.Mkdir(testDir+"/repository1/dir4", 0700)
SetDuplicacyPreferencePath(testDir + "/repository1/.duplicacy")
backupManager.Backup(testDir+"/repository1" /*quickMode=*/, false, threads, "third", false, false)
backupManager.Backup(testDir+"/repository1" /*quickMode=*/, false, threads, "third", false, false, 0, false)
time.Sleep(time.Duration(delay) * time.Second)
// Create some directories and files under repository2 that will be deleted during restore
@@ -343,16 +343,16 @@ func TestBackupManager(t *testing.T) {
backupManager.SnapshotManager.CheckSnapshots( /*snapshotID*/ "host1" /*revisions*/, []int{1, 2, 3} /*tag*/, "",
/*showStatistics*/ false /*showTabular*/, false /*checkFiles*/, false /*searchFossils*/, false /*resurrect*/, false)
backupManager.SnapshotManager.PruneSnapshots("host1", "host1" /*revisions*/, []int{1} /*tags*/, nil /*retentions*/, nil,
/*exhaustive*/ false /*exclusive=*/, false /*ignoredIDs*/, nil /*dryRun*/, false /*deleteOnly*/, false /*collectOnly*/, false)
/*exhaustive*/ false /*exclusive=*/, false /*ignoredIDs*/, nil /*dryRun*/, false /*deleteOnly*/, false /*collectOnly*/, false, 1)
numberOfSnapshots = backupManager.SnapshotManager.ListSnapshots( /*snapshotID*/ "host1" /*revisionsToList*/, nil /*tag*/, "" /*showFiles*/, false /*showChunks*/, false)
if numberOfSnapshots != 2 {
t.Errorf("Expected 2 snapshots but got %d", numberOfSnapshots)
}
backupManager.SnapshotManager.CheckSnapshots( /*snapshotID*/ "host1" /*revisions*/, []int{2, 3} /*tag*/, "",
/*showStatistics*/ false /*showTabular*/, false /*checkFiles*/, false /*searchFossils*/, false /*resurrect*/, false)
backupManager.Backup(testDir+"/repository1" /*quickMode=*/, false, threads, "fourth", false, false)
backupManager.Backup(testDir+"/repository1" /*quickMode=*/, false, threads, "fourth", false, false, 0, false)
backupManager.SnapshotManager.PruneSnapshots("host1", "host1" /*revisions*/, nil /*tags*/, nil /*retentions*/, nil,
/*exhaustive*/ false /*exclusive=*/, true /*ignoredIDs*/, nil /*dryRun*/, false /*deleteOnly*/, false /*collectOnly*/, false)
/*exhaustive*/ false /*exclusive=*/, true /*ignoredIDs*/, nil /*dryRun*/, false /*deleteOnly*/, false /*collectOnly*/, false, 1)
numberOfSnapshots = backupManager.SnapshotManager.ListSnapshots( /*snapshotID*/ "host1" /*revisionsToList*/, nil /*tag*/, "" /*showFiles*/, false /*showChunks*/, false)
if numberOfSnapshots != 3 {
t.Errorf("Expected 3 snapshots but got %d", numberOfSnapshots)

235
src/duplicacy_benchmark.go Normal file
View File

@@ -0,0 +1,235 @@
// Copyright (c) Acrosync LLC. All rights reserved.
// Free for personal use and commercial trial
// Commercial use requires per-user licenses available from https://duplicacy.com
package duplicacy
import (
"bytes"
"crypto/sha256"
"encoding/hex"
"fmt"
"io"
"io/ioutil"
"math/rand"
"os"
"path/filepath"
"time"
)
func benchmarkSplit(reader *bytes.Reader, fileSize int64, chunkSize int, compression bool, encryption bool, annotation string) {
config := CreateConfig()
config.CompressionLevel = DEFAULT_COMPRESSION_LEVEL
config.AverageChunkSize = chunkSize
config.MaximumChunkSize = chunkSize * 4
config.MinimumChunkSize = chunkSize / 4
config.ChunkSeed = []byte("duplicacy")
config.HashKey = DEFAULT_KEY
config.IDKey = DEFAULT_KEY
maker := CreateChunkMaker(config, false)
startTime := float64(time.Now().UnixNano()) / 1e9
numberOfChunks := 0
reader.Seek(0, os.SEEK_SET)
maker.ForEachChunk(reader,
func(chunk *Chunk, final bool) {
if compression {
key := ""
if encryption {
key = "0123456789abcdef0123456789abcdef"
}
err := chunk.Encrypt([]byte(key), "")
if err != nil {
LOG_ERROR("BENCHMARK_ENCRYPT", "Failed to encrypt the chunk: %v", err)
}
}
config.PutChunk(chunk)
numberOfChunks++
},
func(size int64, hash string) (io.Reader, bool) {
return nil, false
})
runningTime := float64(time.Now().UnixNano())/1e9 - startTime
speed := int64(float64(fileSize) / runningTime)
LOG_INFO("BENCHMARK_SPLIT", "Split %s bytes into %d chunks %s in %.2fs: %s/s", PrettySize(fileSize), numberOfChunks, annotation,
runningTime, PrettySize(speed))
return
}
func benchmarkRun(threads int, chunkCount int, job func(threadIndex int, chunkIndex int)) {
indexChannel := make(chan int, chunkCount)
stopChannel := make(chan int, threads)
finishChannel := make(chan int, threads)
// Start the uploading goroutines
for i := 0; i < threads; i++ {
go func(threadIndex int) {
defer CatchLogException()
for {
select {
case chunkIndex := <-indexChannel:
job(threadIndex, chunkIndex)
finishChannel <- 0
case <-stopChannel:
return
}
}
}(i)
}
for i := 0; i < chunkCount; i++ {
indexChannel <- i
}
for i := 0; i < chunkCount; i++ {
<-finishChannel
}
for i := 0; i < threads; i++ {
stopChannel <- 0
}
}
func Benchmark(localDirectory string, storage Storage, fileSize int64, chunkSize int, chunkCount int, uploadThreads int, downloadThreads int) bool {
filename := filepath.Join(localDirectory, "benchmark.dat")
defer func() {
os.Remove(filename)
}()
LOG_INFO("BENCHMARK_GENERATE", "Generating %s byte random data in memory", PrettySize(fileSize))
data := make([]byte, fileSize)
_, err := rand.Read(data)
if err != nil {
LOG_ERROR("BENCHMARK_RAND", "Failed to generate random data: %v", err)
return false
}
startTime := float64(time.Now().UnixNano()) / 1e9
LOG_INFO("BENCHMARK_WRITE", "Writing random data to local disk")
err = ioutil.WriteFile(filename, data, 0600)
if err != nil {
LOG_ERROR("BENCHMARK_WRITE", "Failed to write the random data: %v", err)
return false
}
runningTime := float64(time.Now().UnixNano())/1e9 - startTime
speed := int64(float64(fileSize) / runningTime)
LOG_INFO("BENCHMARK_WRITE", "Wrote %s bytes in %.2fs: %s/s", PrettySize(fileSize), runningTime, PrettySize(speed))
startTime = float64(time.Now().UnixNano()) / 1e9
LOG_INFO("BENCHMARK_READ", "Reading the random data from local disk")
file, err := os.Open(filename)
if err != nil {
LOG_ERROR("BENCHMARK_OPEN", "Failed to open the random data file: %v", err)
return false
}
segment := make([]byte, 1024*1024)
for err == nil {
_, err = file.Read(segment)
}
if err != io.EOF {
LOG_ERROR("BENCHMARK_OPEN", "Failed to read the random data file: %v", err)
return false
}
file.Close()
runningTime = float64(time.Now().UnixNano())/1e9 - startTime
speed = int64(float64(fileSize) / runningTime)
LOG_INFO("BENCHMARK_READ", "Read %s bytes in %.2fs: %s/s", PrettySize(fileSize), runningTime, PrettySize(speed))
buffer := bytes.NewReader(data)
benchmarkSplit(buffer, fileSize, chunkSize, false, false, "without compression/encryption")
benchmarkSplit(buffer, fileSize, chunkSize, true, false, "with compression but without encryption")
benchmarkSplit(buffer, fileSize, chunkSize, true, true, "with compression and encryption")
storage.CreateDirectory(0, "benchmark")
existingFiles, _, err := storage.ListFiles(0, "benchmark/")
if err != nil {
LOG_ERROR("BENCHMARK_LIST", "Failed to list the benchmark directory: %v", err)
return false
}
var existingChunks []string
for _, f := range existingFiles {
if len(f) > 0 && f[len(f)-1] != '/' {
existingChunks = append(existingChunks, "benchmark/"+f)
}
}
if len(existingChunks) > 0 {
LOG_INFO("BENCHMARK_DELETE", "Deleting %d temporary files from previous benchmark runs", len(existingChunks))
benchmarkRun(uploadThreads, len(existingChunks), func(threadIndex int, chunkIndex int) {
storage.DeleteFile(threadIndex, existingChunks[chunkIndex])
})
}
chunks := make([][]byte, chunkCount)
chunkHashes := make([]string, chunkCount)
LOG_INFO("BENCHMARK_GENERATE", "Generating %d chunks", chunkCount)
for i := 0; i < chunkCount; i++ {
chunks[i] = make([]byte, chunkSize)
_, err = rand.Read(chunks[i])
if err != nil {
LOG_ERROR("BENCHMARK_RAND", "Failed to generate random data: %v", err)
return false
}
hashInBytes := sha256.Sum256(chunks[i])
chunkHashes[i] = hex.EncodeToString(hashInBytes[:])
}
startTime = float64(time.Now().UnixNano()) / 1e9
benchmarkRun(uploadThreads, chunkCount, func(threadIndex int, chunkIndex int) {
err := storage.UploadFile(threadIndex, fmt.Sprintf("benchmark/chunk%d", chunkIndex), chunks[chunkIndex])
if err != nil {
LOG_ERROR("BENCHMARK_UPLOAD", "Failed to upload the chunk: %v", err)
return
}
})
runningTime = float64(time.Now().UnixNano())/1e9 - startTime
speed = int64(float64(chunkSize*chunkCount) / runningTime)
LOG_INFO("BENCHMARK_UPLOAD", "Uploaded %s bytes in %.2fs: %s/s", PrettySize(int64(chunkSize*chunkCount)), runningTime, PrettySize(speed))
config := CreateConfig()
startTime = float64(time.Now().UnixNano()) / 1e9
hashError := false
benchmarkRun(downloadThreads, chunkCount, func(threadIndex int, chunkIndex int) {
chunk := config.GetChunk()
chunk.Reset(false)
err := storage.DownloadFile(threadIndex, fmt.Sprintf("benchmark/chunk%d", chunkIndex), chunk)
if err != nil {
LOG_ERROR("BENCHMARK_DOWNLOAD", "Failed to download the chunk: %v", err)
return
}
hashInBytes := sha256.Sum256(chunk.GetBytes())
hash := hex.EncodeToString(hashInBytes[:])
if hash != chunkHashes[chunkIndex] {
LOG_WARN("BENCHMARK_HASH", "Chunk %d has mismatched hashes: %s != %s", chunkIndex, chunkHashes[chunkIndex], hash)
hashError = true
}
config.PutChunk(chunk)
})
runningTime = float64(time.Now().UnixNano())/1e9 - startTime
speed = int64(float64(chunkSize*chunkCount) / runningTime)
LOG_INFO("BENCHMARK_DOWNLOAD", "Downloaded %s bytes in %.2fs: %s/s", PrettySize(int64(chunkSize*chunkCount)), runningTime, PrettySize(speed))
if !hashError {
benchmarkRun(uploadThreads, chunkCount, func(threadIndex int, chunkIndex int) {
storage.DeleteFile(threadIndex, fmt.Sprintf("benchmark/chunk%d", chunkIndex))
})
LOG_INFO("BENCHMARK_DELETE", "Deleted %d temporary files from the storage", chunkCount)
}
return true
}

View File

@@ -5,11 +5,14 @@
package duplicacy
import (
"os"
"bytes"
"compress/zlib"
"crypto/aes"
"crypto/cipher"
"crypto/rand"
"crypto/hmac"
"crypto/sha256"
"encoding/hex"
"fmt"
"hash"
@@ -267,6 +270,17 @@ func (chunk *Chunk) Encrypt(encryptionKey []byte, derivationKey string) (err err
}
// This is to ensure compability with Vertical Backup, which still uses HMAC-SHA256 (instead of HMAC-BLAKE2) to
// derive the key used to encrypt/decrypt files and chunks.
var DecryptWithHMACSHA256 = false
func init() {
if value, found := os.LookupEnv("DUPLICACY_DECRYPT_WITH_HMACSHA256"); found && value != "0" {
DecryptWithHMACSHA256 = true
}
}
// Decrypt decrypts the encrypted data stored in the chunk buffer. If derivationKey is not nil, the actual
// encryption key will be HMAC-SHA256(encryptionKey, derivationKey).
func (chunk *Chunk) Decrypt(encryptionKey []byte, derivationKey string) (err error) {
@@ -286,7 +300,13 @@ func (chunk *Chunk) Decrypt(encryptionKey []byte, derivationKey string) (err err
key := encryptionKey
if len(derivationKey) > 0 {
hasher := chunk.config.NewKeyedHasher([]byte(derivationKey))
var hasher hash.Hash
if DecryptWithHMACSHA256 {
hasher = hmac.New(sha256.New, []byte(derivationKey))
} else {
hasher = chunk.config.NewKeyedHasher([]byte(derivationKey))
}
hasher.Write(encryptionKey)
key = hasher.Sum(nil)
}
@@ -325,6 +345,7 @@ func (chunk *Chunk) Decrypt(encryptionKey []byte, derivationKey string) (err err
return err
}
paddingLength := int(decryptedBytes[len(decryptedBytes)-1])
if paddingLength == 0 {
paddingLength = 256

View File

@@ -174,7 +174,7 @@ func (downloader *ChunkDownloader) Prefetch(file *Entry) {
// Reclaim releases the downloaded chunk to the chunk pool
func (downloader *ChunkDownloader) Reclaim(chunkIndex int) {
if downloader.lastChunkIndex == chunkIndex {
if downloader.lastChunkIndex >= chunkIndex {
return
}
@@ -187,13 +187,20 @@ func (downloader *ChunkDownloader) Reclaim(chunkIndex int) {
}
}
for i := downloader.lastChunkIndex; i < chunkIndex; i++ {
// These chunks are never downloaded if 'isDownloading' is false; note that 'isDownloading' isn't reset to
// false after a chunk has been downloaded
if !downloader.taskList[i].isDownloading {
atomic.AddInt64(&downloader.totalChunkSize, -int64(downloader.taskList[i].chunkLength))
}
}
downloader.lastChunkIndex = chunkIndex
}
// WaitForChunk waits until the specified chunk is ready
func (downloader *ChunkDownloader) WaitForChunk(chunkIndex int) (chunk *Chunk) {
// Reclain any chunk not needed
// Reclaim any chunk not needed
downloader.Reclaim(chunkIndex)
// If we haven't started download the specified chunk, download it now
@@ -317,8 +324,19 @@ func (downloader *ChunkDownloader) Download(threadIndex int, task ChunkDownloadT
}
if !exist {
// Retry for the Hubic backend as it may return 404 even when the chunk exists
if _, ok := downloader.storage.(*HubicStorage); ok && downloadAttempt < MaxDownloadAttempts {
retry := false
// Retry for Hubic or WebDAV as it may return 404 even when the chunk exists
if _, ok := downloader.storage.(*HubicStorage); ok {
retry = true
}
if _, ok := downloader.storage.(*WebDAVStorage); ok {
retry = true
}
if retry && downloadAttempt < MaxDownloadAttempts {
LOG_WARN("DOWNLOAD_RETRY", "Failed to find the chunk %s; retrying", chunkID)
continue
}

View File

@@ -0,0 +1,209 @@
// Copyright (c) Acrosync LLC. All rights reserved.
// Free for personal use and commercial trial
// Commercial use requires per-user licenses available from https://duplicacy.com
package duplicacy
import (
"sync"
"sync/atomic"
"time"
)
// These are operations that ChunkOperator will perform.
const (
ChunkOperationFind = 0
ChunkOperationDelete = 1
ChunkOperationFossilize = 2
ChunkOperationResurrect = 3
)
// ChunkOperatorTask is used to pass paramaters for different kinds of chunk operations.
type ChunkOperatorTask struct {
operation int // The type of operation
chunkID string // The chunk id
filePath string // The path of the chunk file; it may be empty
}
// ChunkOperator is capable of performing multi-threaded operations on chunks.
type ChunkOperator struct {
numberOfActiveTasks int64 // The number of chunks that are being operated on
storage Storage // This storage
threads int // Number of threads
taskQueue chan ChunkOperatorTask // Operating goroutines are waiting on this channel for input
stopChannel chan bool // Used to stop all the goroutines
fossils []string // For fossilize operation, the paths of the fossils are stored in this slice
fossilsLock *sync.Mutex // The lock for 'fossils'
}
// CreateChunkOperator creates a new ChunkOperator.
func CreateChunkOperator(storage Storage, threads int) *ChunkOperator {
operator := &ChunkOperator{
storage: storage,
threads: threads,
taskQueue: make(chan ChunkOperatorTask, threads*4),
stopChannel: make(chan bool),
fossils: make([]string, 0),
fossilsLock: &sync.Mutex{},
}
// Start the operator goroutines
for i := 0; i < operator.threads; i++ {
go func(threadIndex int) {
defer CatchLogException()
for {
select {
case task := <-operator.taskQueue:
operator.Run(threadIndex, task)
case <-operator.stopChannel:
return
}
}
}(i)
}
return operator
}
func (operator *ChunkOperator) Stop() {
if atomic.LoadInt64(&operator.numberOfActiveTasks) < 0 {
return
}
for atomic.LoadInt64(&operator.numberOfActiveTasks) > 0 {
time.Sleep(100 * time.Millisecond)
}
for i := 0; i < operator.threads; i++ {
operator.stopChannel <- false
}
// Assign -1 to numberOfActiveTasks so Stop() can be called multiple times
atomic.AddInt64(&operator.numberOfActiveTasks, int64(-1))
}
func (operator *ChunkOperator) AddTask(operation int, chunkID string, filePath string) {
task := ChunkOperatorTask{
operation: operation,
chunkID: chunkID,
filePath: filePath,
}
operator.taskQueue <- task
atomic.AddInt64(&operator.numberOfActiveTasks, int64(1))
}
func (operator *ChunkOperator) Find(chunkID string) {
operator.AddTask(ChunkOperationFind, chunkID, "")
}
func (operator *ChunkOperator) Delete(chunkID string, filePath string) {
operator.AddTask(ChunkOperationDelete, chunkID, filePath)
}
func (operator *ChunkOperator) Fossilize(chunkID string, filePath string) {
operator.AddTask(ChunkOperationFossilize, chunkID, filePath)
}
func (operator *ChunkOperator) Resurrect(chunkID string, filePath string) {
operator.AddTask(ChunkOperationResurrect, chunkID, filePath)
}
func (operator *ChunkOperator) Run(threadIndex int, task ChunkOperatorTask) {
defer func() {
atomic.AddInt64(&operator.numberOfActiveTasks, int64(-1))
}()
// task.filePath may be empty. If so, find the chunk first.
if task.operation == ChunkOperationDelete || task.operation == ChunkOperationFossilize {
if task.filePath == "" {
filePath, exist, _, err := operator.storage.FindChunk(threadIndex, task.chunkID, false)
if err != nil {
LOG_ERROR("CHUNK_FIND", "Failed to locate the path for the chunk %s: %v", task.chunkID, err)
return
} else if !exist {
if task.operation == ChunkOperationDelete {
LOG_WARN("CHUNK_FIND", "Chunk %s does not exist in the storage", task.chunkID)
return
}
fossilPath, exist, _, _ := operator.storage.FindChunk(threadIndex, task.chunkID, true)
if exist {
LOG_WARN("CHUNK_FOSSILIZE", "Chunk %s is already a fossil", task.chunkID)
operator.fossilsLock.Lock()
operator.fossils = append(operator.fossils, fossilPath)
operator.fossilsLock.Unlock()
} else {
LOG_ERROR("CHUNK_FIND", "Chunk %s does not exist in the storage", task.chunkID)
}
return
}
task.filePath = filePath
}
}
if task.operation == ChunkOperationFind {
_, exist, _, err := operator.storage.FindChunk(threadIndex, task.chunkID, false)
if err != nil {
LOG_ERROR("CHUNK_FIND", "Failed to locate the path for the chunk %s: %v", task.chunkID, err)
} else if !exist {
LOG_ERROR("CHUNK_FIND", "Chunk %s does not exist in the storage", task.chunkID)
} else {
LOG_DEBUG("CHUNK_FIND", "Chunk %s exists in the storage", task.chunkID)
}
} else if task.operation == ChunkOperationDelete {
err := operator.storage.DeleteFile(threadIndex, task.filePath)
if err != nil {
LOG_WARN("CHUNK_DELETE", "Failed to remove the file %s: %v", task.filePath, err)
} else {
if task.chunkID != "" {
LOG_INFO("CHUNK_DELETE", "The chunk %s has been permanently removed", task.chunkID)
} else {
LOG_INFO("CHUNK_DELETE", "Deleted file %s from the storage", task.filePath)
}
}
} else if task.operation == ChunkOperationFossilize {
fossilPath := task.filePath + ".fsl"
err := operator.storage.MoveFile(threadIndex, task.filePath, fossilPath)
if err != nil {
if _, exist, _, _ := operator.storage.FindChunk(threadIndex, task.chunkID, true); exist {
err := operator.storage.DeleteFile(threadIndex, task.filePath)
if err == nil {
LOG_TRACE("CHUNK_DELETE", "Deleted chunk file %s as the fossil already exists", task.chunkID)
}
operator.fossilsLock.Lock()
operator.fossils = append(operator.fossils, fossilPath)
operator.fossilsLock.Unlock()
} else {
LOG_ERROR("CHUNK_DELETE", "Failed to fossilize the chunk %s: %v", task.chunkID, err)
}
} else {
LOG_TRACE("CHUNK_FOSSILIZE", "The chunk %s has been marked as a fossil", task.chunkID)
operator.fossilsLock.Lock()
operator.fossils = append(operator.fossils, fossilPath)
operator.fossilsLock.Unlock()
}
} else if task.operation == ChunkOperationResurrect {
chunkPath, exist, _, err := operator.storage.FindChunk(threadIndex, task.chunkID, false)
if err != nil {
LOG_ERROR("CHUNK_FIND", "Failed to locate the path for the chunk %s: %v", task.chunkID, err)
}
if exist {
operator.storage.DeleteFile(threadIndex, task.filePath)
LOG_INFO("FOSSIL_RESURRECT", "The chunk %s already exists", task.chunkID)
} else {
err := operator.storage.MoveFile(threadIndex, task.filePath, chunkPath)
if err != nil {
LOG_ERROR("FOSSIL_RESURRECT", "Failed to resurrect the chunk %s from the fossil %s: %v",
task.chunkID, task.filePath, err)
} else {
LOG_INFO("FOSSIL_RESURRECT", "The chunk %s has been resurrected", task.filePath)
}
}
}
}

View File

@@ -111,7 +111,7 @@ func TestUploaderAndDownloader(t *testing.T) {
for i, chunk := range chunks {
downloaded := chunkDownloader.WaitForChunk(i)
if downloaded.GetID() != chunk.GetID() {
t.Error("Uploaded: %s, downloaded: %s", chunk.GetID(), downloaded.GetID())
t.Errorf("Uploaded: %s, downloaded: %s", chunk.GetID(), downloaded.GetID())
}
}

View File

@@ -22,6 +22,9 @@ import (
var DUPLICACY_DIRECTORY = ".duplicacy"
var DUPLICACY_FILE = ".duplicacy"
// Mask for file permission bits
var fileModeMask = os.ModePerm | os.ModeSetuid | os.ModeSetgid | os.ModeSticky
// Regex for matching 'StartChunk:StartOffset:EndChunk:EndOffset'
var contentRegex = regexp.MustCompile(`^([0-9]+):([0-9]+):([0-9]+):([0-9]+)`)
@@ -269,7 +272,7 @@ func (entry *Entry) IsLink() bool {
}
func (entry *Entry) GetPermissions() os.FileMode {
return os.FileMode(entry.Mode) & os.ModePerm
return os.FileMode(entry.Mode)&fileModeMask
}
func (entry *Entry) IsSameAs(other *Entry) bool {
@@ -297,7 +300,14 @@ func (entry *Entry) RestoreMetadata(fullPath string, fileInfo *os.FileInfo, setO
}
}
if (*fileInfo).Mode()&os.ModePerm != entry.GetPermissions() {
// Note that chown can remove setuid/setgid bits so should be called before chmod
if setOwner {
if !SetOwner(fullPath, entry, fileInfo) {
return false
}
}
if (*fileInfo).Mode()&fileModeMask != entry.GetPermissions() {
err := os.Chmod(fullPath, entry.GetPermissions())
if err != nil {
LOG_ERROR("RESTORE_CHMOD", "Failed to set the file permissions: %v", err)
@@ -318,11 +328,7 @@ func (entry *Entry) RestoreMetadata(fullPath string, fileInfo *os.FileInfo, setO
entry.SetAttributesToFile(fullPath)
}
if setOwner {
return SetOwner(fullPath, entry, fileInfo)
} else {
return true
}
}
// Return -1 if 'left' should appear before 'right', 1 if opposite, and 0 if they are the same.
@@ -435,7 +441,7 @@ func (files FileInfoCompare) Less(i, j int) bool {
// ListEntries returns a list of entries representing file and subdirectories under the directory 'path'. Entry paths
// are normalized as relative to 'top'. 'patterns' are used to exclude or include certain files.
func ListEntries(top string, path string, fileList *[]*Entry, patterns []string, discardAttributes bool) (directoryList []*Entry,
func ListEntries(top string, path string, fileList *[]*Entry, patterns []string, nobackupFile string, discardAttributes bool) (directoryList []*Entry,
skippedFiles []string, err error) {
LOG_DEBUG("LIST_ENTRIES", "Listing %s", path)
@@ -449,6 +455,15 @@ func ListEntries(top string, path string, fileList *[]*Entry, patterns []string,
return directoryList, nil, err
}
// This binary search works because ioutil.ReadDir returns files sorted by Name() by default
if nobackupFile != "" {
ii := sort.Search(len(files), func(ii int) bool { return strings.Compare(files[ii].Name(), nobackupFile) >= 0})
if ii < len(files) && files[ii].Name() == nobackupFile {
LOG_DEBUG("LIST_NOBACKUP", "%s is excluded due to nobackup file", path)
return directoryList, skippedFiles, nil
}
}
normalizedPath := path
if len(normalizedPath) > 0 && normalizedPath[len(normalizedPath)-1] != '/' {
normalizedPath += "/"
@@ -469,7 +484,6 @@ func ListEntries(top string, path string, fileList *[]*Entry, patterns []string,
}
entry := CreateEntryFromFileInfo(f, normalizedPath)
if len(patterns) > 0 && !MatchPath(entry.Path, patterns) {
LOG_DEBUG("LIST_EXCLUDE", "%s is excluded", entry.Path)
continue
}
if entry.IsLink() {
@@ -483,7 +497,7 @@ func ListEntries(top string, path string, fileList *[]*Entry, patterns []string,
if isRegular {
entry.Mode ^= uint32(os.ModeSymlink)
} else if path == "" && filepath.IsAbs(entry.Link) && !strings.HasPrefix(entry.Link, normalizedTop) {
} else if path == "" && (filepath.IsAbs(entry.Link) || filepath.HasPrefix(entry.Link, `\\`)) && !strings.HasPrefix(entry.Link, normalizedTop) {
stat, err := os.Stat(filepath.Join(top, entry.Path))
if err != nil {
LOG_WARN("LIST_LINK", "Failed to read the symlink: %v", err)

View File

@@ -173,7 +173,7 @@ func TestEntryList(t *testing.T) {
directory := directories[len(directories)-1]
directories = directories[:len(directories)-1]
entries = append(entries, directory)
subdirectories, _, err := ListEntries(testDir, directory.Path, &entries, nil, false)
subdirectories, _, err := ListEntries(testDir, directory.Path, &entries, nil, "", false)
if err != nil {
t.Errorf("ListEntries(%s, %s) returned an error: %s", testDir, directory.Path, err)
}

View File

@@ -129,7 +129,7 @@ func logf(level int, logID string, format string, v ...interface{}) {
// fmt.Printf("%s %s %s %s\n", now.Format("2006-01-02 15:04:05.000"), getLevelName(level), logID, message)
if testingT != nil {
if level < WARN {
if level <= WARN {
if level >= loggingLevel {
testingT.Logf("%s %s %s %s\n",
now.Format("2006-01-02 15:04:05.000"), getLevelName(level), logID, message)

View File

@@ -17,11 +17,13 @@ import (
type Preference struct {
Name string `json:"name"`
SnapshotID string `json:"id"`
RepositoryPath string `json:"repository"`
StorageURL string `json:"storage"`
Encrypted bool `json:"encrypted"`
BackupProhibited bool `json:"no_backup"`
RestoreProhibited bool `json:"no_restore"`
DoNotSavePassword bool `json:"no_save_password"`
NobackupFile string `json:"nobackup_file"`
Keys map[string]string `json:"keys"`
}

View File

@@ -2,6 +2,11 @@
// Free for personal use and commercial trial
// Commercial use requires per-user licenses available from https://duplicacy.com
// NOTE: The code in the Wasabi storage module relies on all functions
// in this one except MoveFile(), IsMoveFileImplemented() and
// IsStrongConsistent(). Changes to the API here will need to be
// reflected there.
package duplicacy
import (

3
src/duplicacy_shadowcopy.go Normal file → Executable file
View File

@@ -3,10 +3,11 @@
// Commercial use requires per-user licenses available from https://duplicacy.com
// +build !windows
// +build !darwin
package duplicacy
func CreateShadowCopy(top string, shadowCopy bool) (shadowTop string) {
func CreateShadowCopy(top string, shadowCopy bool, timeoutInSeconds int) (shadowTop string) {
return top
}

View File

@@ -0,0 +1,170 @@
//
// Shadow copy module for Mac OSX using APFS snapshot
//
//
// This module copyright 2018 Adam Marcus (https://github.com/amarcu5)
// and may be distributed under the same terms as Duplicacy.
package duplicacy
import (
"context"
"errors"
"io/ioutil"
"os"
"os/exec"
"strings"
"syscall"
"time"
)
var snapshotPath string
var snapshotDate string
// Converts char array to string
func CharsToString(ca []int8) string {
len := len(ca)
ba := make([]byte, len)
for i, v := range ca {
ba[i] = byte(v)
if ba[i] == 0 {
len = i
break
}
}
return string(ba[:len])
}
// Get ID of device containing path
func GetPathDeviceId(path string) (deviceId int32, err error) {
stat := syscall.Stat_t{}
err = syscall.Stat(path, &stat)
if err != nil {
return 0, err
}
return stat.Dev, nil
}
// Executes shell command with timeout and returns stdout
func CommandWithTimeout(timeoutInSeconds int, name string, arg ...string) (output string, err error) {
ctx, cancel := context.WithTimeout(context.Background(), time.Duration(timeoutInSeconds) * time.Second)
defer cancel()
cmd := exec.CommandContext(ctx, name, arg...)
out, err := cmd.Output()
if ctx.Err() == context.DeadlineExceeded {
err = errors.New("Command '" + name + "' timed out")
}
output = string(out)
return output, err
}
func DeleteShadowCopy() {
if snapshotPath == "" {
return
}
err := exec.Command("/sbin/umount", "-f", snapshotPath).Run()
if err != nil {
LOG_ERROR("VSS_DELETE", "Error while unmounting snapshot")
return
}
err = exec.Command("tmutil", "deletelocalsnapshots", snapshotDate).Run()
if err != nil {
LOG_ERROR("VSS_DELETE", "Error while deleting local snapshot")
return
}
err = os.RemoveAll(snapshotPath)
if err != nil {
LOG_ERROR("VSS_DELETE", "Error while deleting temporary mount directory")
return
}
LOG_INFO("VSS_DELETE", "Shadow copy unmounted and deleted at %s", snapshotPath)
snapshotPath = ""
}
func CreateShadowCopy(top string, shadowCopy bool, timeoutInSeconds int) (shadowTop string) {
if !shadowCopy {
return top
}
// Check repository filesystem is APFS
stat := syscall.Statfs_t{}
err := syscall.Statfs(top, &stat)
if err != nil {
LOG_ERROR("VSS_INIT", "Unable to determine filesystem of repository path")
return top
}
if CharsToString(stat.Fstypename[:]) != "apfs" {
LOG_WARN("VSS_INIT", "VSS requires APFS filesystem")
return top
}
// Check path is local as tmutil snapshots will not support APFS formatted external drives
deviceIdLocal, err := GetPathDeviceId("/")
if err != nil {
LOG_ERROR("VSS_INIT", "Unable to get device ID of path: /")
return top
}
deviceIdRepository, err := GetPathDeviceId(top)
if err != nil {
LOG_ERROR("VSS_INIT", "Unable to get device ID of path: ", top)
return top
}
if deviceIdLocal != deviceIdRepository {
LOG_WARN("VSS_PATH", "VSS not supported for non-local repository path: ", top)
return top
}
if timeoutInSeconds <= 60 {
timeoutInSeconds = 60
}
// Create mount point
snapshotPath, err = ioutil.TempDir("/tmp/", "snp_")
if err != nil {
LOG_ERROR("VSS_CREATE", "Failed to create temporary mount directory")
return top
}
// Use tmutil to create snapshot
tmutilOutput, err := CommandWithTimeout(timeoutInSeconds, "tmutil", "snapshot")
if err != nil {
LOG_ERROR("VSS_CREATE", "Error while calling tmutil: ", err)
return top
}
colonPos := strings.IndexByte(tmutilOutput, ':')
if colonPos < 0 {
LOG_ERROR("VSS_CREATE", "Snapshot creation failed: ", tmutilOutput)
return top
}
snapshotDate = strings.TrimSpace(tmutilOutput[colonPos+1:])
// Mount snapshot as readonly and hide from GUI i.e. Finder
_, err = CommandWithTimeout(timeoutInSeconds,
"/sbin/mount", "-t", "apfs", "-o", "nobrowse,-r,-s=com.apple.TimeMachine." + snapshotDate, "/", snapshotPath)
if err != nil {
LOG_ERROR("VSS_CREATE", "Error while mounting snapshot: ", err)
return top
}
LOG_INFO("VSS_DONE", "Shadow copy created and mounted at %s", snapshotPath)
return snapshotPath + top
}

View File

@@ -353,12 +353,15 @@ func DeleteShadowCopy() {
ole.CoUninitialize()
}
func CreateShadowCopy(top string, shadowCopy bool) (shadowTop string) {
func CreateShadowCopy(top string, shadowCopy bool, timeoutInSeconds int) (shadowTop string) {
if !shadowCopy {
return top
}
if timeoutInSeconds <= 60 {
timeoutInSeconds = 60
}
ole.CoInitialize(0)
defer ole.CoUninitialize()
@@ -416,7 +419,7 @@ func CreateShadowCopy(top string, shadowCopy bool) (shadowTop string) {
return top
}
if !async.Wait(60) {
if !async.Wait(timeoutInSeconds) {
LOG_ERROR("VSS_GATHER", "Shadow copy creation failed: GatherWriterMetadata didn't finish properly")
return top
}
@@ -456,7 +459,7 @@ func CreateShadowCopy(top string, shadowCopy bool) (shadowTop string) {
return top
}
if !async.Wait(60) {
if !async.Wait(timeoutInSeconds) {
LOG_ERROR("VSS_PREPARE", "Shadow copy creation failed: PrepareForBackup didn't finish properly")
return top
}
@@ -473,7 +476,7 @@ func CreateShadowCopy(top string, shadowCopy bool) (shadowTop string) {
return top
}
if !async.Wait(180) {
if !async.Wait(timeoutInSeconds) {
LOG_ERROR("VSS_SNAPSHOT", "Shadow copy creation failed: DoSnapshotSet didn't finish properly")
return top
}

View File

@@ -57,7 +57,7 @@ func CreateEmptySnapshot(id string) (snapshto *Snapshot) {
// CreateSnapshotFromDirectory creates a snapshot from the local directory 'top'. Only 'Files'
// will be constructed, while 'ChunkHashes' and 'ChunkLengths' can only be populated after uploading.
func CreateSnapshotFromDirectory(id string, top string) (snapshot *Snapshot, skippedDirectories []string,
func CreateSnapshotFromDirectory(id string, top string, nobackupFile string) (snapshot *Snapshot, skippedDirectories []string,
skippedFiles []string, err error) {
snapshot = &Snapshot{
@@ -125,7 +125,7 @@ func CreateSnapshotFromDirectory(id string, top string) (snapshot *Snapshot, ski
directory := directories[len(directories)-1]
directories = directories[:len(directories)-1]
snapshot.Files = append(snapshot.Files, directory)
subdirectories, skipped, err := ListEntries(top, directory.Path, &snapshot.Files, patterns, snapshot.discardAttributes)
subdirectories, skipped, err := ListEntries(top, directory.Path, &snapshot.Files, patterns, nobackupFile, snapshot.discardAttributes)
if err != nil {
LOG_WARN("LIST_FAILURE", "Failed to list subdirectory: %v", err)
skippedDirectories = append(skippedDirectories, directory.Path)
@@ -357,6 +357,11 @@ func (snapshot *Snapshot) LoadChunks(description []byte) (err error) {
return err
}
// ClearChunks removes loaded chunks from memory
func (snapshot *Snapshot) ClearChunks() {
snapshot.ChunkHashes = nil
}
// LoadLengths construct 'ChunkLengths' from the json description.
func (snapshot *Snapshot) LoadLengths(description []byte) (err error) {
return json.Unmarshal(description, &snapshot.ChunkLengths)

View File

@@ -26,6 +26,7 @@ import (
const (
secondsInDay = 86400
chunkDir = "chunks/"
)
// FossilCollection contains fossils and temporary files found during a snapshot deletions.
@@ -37,6 +38,9 @@ type FossilCollection struct {
// The lastest revision for each snapshot id when the fossil collection was created.
LastRevisions map[string]int `json:"last_revisions"`
// Record the set of snapshots that have been removed by the prune command that created this fossil collection
DeletedRevisions map[string][]int `json:"deleted_revisions"`
// Fossils (i.e., chunks not referenced by any snapshots)
Fossils []string `json:"fossils"`
@@ -54,6 +58,7 @@ func CreateFossilCollection(allSnapshots map[string][]*Snapshot) *FossilCollecti
return &FossilCollection{
LastRevisions: lastRevisions,
DeletedRevisions: make(map[string][]int),
}
}
@@ -104,6 +109,8 @@ func (collection *FossilCollection) IsDeletable(isStrongConsistent bool, ignored
continue
}
newSnapshots = append(newSnapshots, snapshot)
extraTime := 0
if !isStrongConsistent {
extraTime = secondsInDay / 2
@@ -113,7 +120,6 @@ func (collection *FossilCollection) IsDeletable(isStrongConsistent bool, ignored
// might be in progress (although very unlikely). So we only deem it deletable if that is not the case.
if snapshot.EndTime > collection.EndTime+int64(extraTime) {
hasNewSnapshot[hostID] = true
newSnapshots = append(newSnapshots, snapshot)
break
} else {
LOG_TRACE("SNAPSHOT_UNDELETABLE",
@@ -174,6 +180,7 @@ type SnapshotManager struct {
snapshotCache *FileStorage
chunkDownloader *ChunkDownloader
chunkOperator *ChunkOperator
}
// CreateSnapshotManager creates a snapshot manager
@@ -388,7 +395,7 @@ func (manager *SnapshotManager) CleanSnapshotCache(latestSnapshot *Snapshot, all
chunks := make(map[string]bool)
if latestSnapshot != nil {
for _, chunkID := range manager.GetSnapshotChunks(latestSnapshot) {
for _, chunkID := range manager.GetSnapshotChunks(latestSnapshot, true) {
chunks[chunkID] = true
}
}
@@ -456,7 +463,7 @@ func (manager *SnapshotManager) CleanSnapshotCache(latestSnapshot *Snapshot, all
}
}
allFiles, _ := manager.ListAllFiles(manager.snapshotCache, "chunks/")
allFiles, _ := manager.ListAllFiles(manager.snapshotCache, chunkDir)
for _, file := range allFiles {
if file[len(file)-1] != '/' {
chunkID := strings.Replace(file, "/", "", -1)
@@ -598,8 +605,9 @@ func (manager *SnapshotManager) ListAllFiles(storage Storage, top string) (allFi
return allFiles, allSizes
}
// GetSnapshotChunks returns all chunks referenced by a given snapshot.
func (manager *SnapshotManager) GetSnapshotChunks(snapshot *Snapshot) (chunks []string) {
// GetSnapshotChunks returns all chunks referenced by a given snapshot. If
// keepChunkHashes is true, snapshot.ChunkHashes will be populated.
func (manager *SnapshotManager) GetSnapshotChunks(snapshot *Snapshot, keepChunkHashes bool) (chunks []string) {
for _, chunkHash := range snapshot.FileSequence {
chunks = append(chunks, manager.config.GetChunkIDFromHash(chunkHash))
@@ -628,6 +636,10 @@ func (manager *SnapshotManager) GetSnapshotChunks(snapshot *Snapshot) (chunks []
chunks = append(chunks, manager.config.GetChunkIDFromHash(chunkHash))
}
if !keepChunkHashes {
snapshot.ClearChunks()
}
return chunks
}
@@ -716,7 +728,7 @@ func (manager *SnapshotManager) ListSnapshots(snapshotID string, revisionsToList
}
if showChunks {
for _, chunkID := range manager.GetSnapshotChunks(snapshot) {
for _, chunkID := range manager.GetSnapshotChunks(snapshot, false) {
LOG_INFO("SNAPSHOT_CHUNKS", "chunk: %s", chunkID)
}
}
@@ -749,7 +761,7 @@ func (manager *SnapshotManager) CheckSnapshots(snapshotID string, revisionsToChe
chunkSnapshotMap := make(map[string]int)
LOG_INFO("SNAPSHOT_CHECK", "Listing all chunks")
allChunks, allSizes := manager.ListAllFiles(manager.storage, "chunks/")
allChunks, allSizes := manager.ListAllFiles(manager.storage, chunkDir)
for i, chunk := range allChunks {
if len(chunk) == 0 || chunk[len(chunk)-1] == '/' {
@@ -780,6 +792,7 @@ func (manager *SnapshotManager) CheckSnapshots(snapshotID string, revisionsToChe
}
snapshotIDIndex := 0
totalMissingChunks := 0
for snapshotID, _ = range snapshotMap {
revisions := revisionsToCheck
@@ -806,7 +819,7 @@ func (manager *SnapshotManager) CheckSnapshots(snapshotID string, revisionsToChe
}
chunks := make(map[string]bool)
for _, chunkID := range manager.GetSnapshotChunks(snapshot) {
for _, chunkID := range manager.GetSnapshotChunks(snapshot, false) {
chunks[chunkID] = true
}
@@ -865,18 +878,23 @@ func (manager *SnapshotManager) CheckSnapshots(snapshotID string, revisionsToChe
}
if missingChunks > 0 {
LOG_ERROR("SNAPSHOT_CHECK", "Some chunks referenced by snapshot %s at revision %d are missing",
LOG_WARN("SNAPSHOT_CHECK", "Some chunks referenced by snapshot %s at revision %d are missing",
snapshotID, revision)
return false
}
totalMissingChunks += missingChunks
} else {
LOG_INFO("SNAPSHOT_CHECK", "All chunks referenced by snapshot %s at revision %d exist",
snapshotID, revision)
}
}
snapshotIDIndex += 1
}
if totalMissingChunks > 0 {
LOG_ERROR("SNAPSHOT_CHECK", "Some chunks referenced by some snapshots do not exist in the storage")
return false
}
if showTabular {
manager.ShowStatisticsTabular(snapshotMap, chunkSizeMap, chunkUniqueMap, chunkSnapshotMap)
} else if showStatistics {
@@ -896,7 +914,7 @@ func (manager *SnapshotManager) ShowStatistics(snapshotMap map[string][]*Snapsho
for _, snapshot := range snapshotList {
chunks := make(map[string]bool)
for _, chunkID := range manager.GetSnapshotChunks(snapshot) {
for _, chunkID := range manager.GetSnapshotChunks(snapshot, false) {
chunks[chunkID] = true
snapshotChunks[chunkID] = true
}
@@ -949,7 +967,7 @@ func (manager *SnapshotManager) ShowStatisticsTabular(snapshotMap map[string][]*
earliestSeenChunks := make(map[string]int)
for _, snapshot := range snapshotList {
for _, chunkID := range manager.GetSnapshotChunks(snapshot) {
for _, chunkID := range manager.GetSnapshotChunks(snapshot, true) {
if earliestSeenChunks[chunkID] == 0 {
earliestSeenChunks[chunkID] = math.MaxInt32
}
@@ -960,7 +978,7 @@ func (manager *SnapshotManager) ShowStatisticsTabular(snapshotMap map[string][]*
for _, snapshot := range snapshotList {
chunks := make(map[string]bool)
for _, chunkID := range manager.GetSnapshotChunks(snapshot) {
for _, chunkID := range manager.GetSnapshotChunks(snapshot, true) {
chunks[chunkID] = true
snapshotChunks[chunkID] = true
}
@@ -1234,7 +1252,7 @@ func (manager *SnapshotManager) PrintFile(snapshotID string, revision int, path
// Diff compares two snapshots, or two revision of a file if the file argument is given.
func (manager *SnapshotManager) Diff(top string, snapshotID string, revisions []int,
filePath string, compareByHash bool) bool {
filePath string, compareByHash bool, nobackupFile string) bool {
LOG_DEBUG("DIFF_PARAMETERS", "top: %s, id: %s, revision: %v, path: %s, compareByHash: %t",
top, snapshotID, revisions, filePath, compareByHash)
@@ -1247,7 +1265,7 @@ func (manager *SnapshotManager) Diff(top string, snapshotID string, revisions []
if len(revisions) <= 1 {
// Only scan the repository if filePath is not provided
if len(filePath) == 0 {
rightSnapshot, _, _, err = CreateSnapshotFromDirectory(snapshotID, top)
rightSnapshot, _, _, err = CreateSnapshotFromDirectory(snapshotID, top, nobackupFile)
if err != nil {
LOG_ERROR("SNAPSHOT_LIST", "Failed to list the directory %s: %v", top, err)
return false
@@ -1484,7 +1502,7 @@ func (manager *SnapshotManager) ShowHistory(top string, snapshotID string, revis
}
if showLocalHash {
localFile.Hash = manager.config.ComputeFileHash(joinPath(top, filePath), make([]byte, 32*1024))
if lastVersion.Hash != localFile.Hash {
if lastVersion == nil || lastVersion.Hash != localFile.Hash {
modifiedFlag = "*"
}
}
@@ -1497,36 +1515,11 @@ func (manager *SnapshotManager) ShowHistory(top string, snapshotID string, revis
}
// fossilizeChunk turns the chunk into a fossil.
func (manager *SnapshotManager) fossilizeChunk(chunkID string, filePath string,
exclusive bool, collection *FossilCollection) bool {
func (manager *SnapshotManager) fossilizeChunk(chunkID string, filePath string, exclusive bool) bool {
if exclusive {
err := manager.storage.DeleteFile(0, filePath)
if err != nil {
LOG_ERROR("CHUNK_DELETE", "Failed to remove the chunk %s: %v", chunkID, err)
return false
manager.chunkOperator.Delete(chunkID, filePath)
} else {
LOG_TRACE("CHUNK_DELETE", "Deleted chunk file %s", chunkID)
}
} else {
fossilPath := filePath + ".fsl"
err := manager.storage.MoveFile(0, filePath, fossilPath)
if err != nil {
if _, exist, _, _ := manager.storage.FindChunk(0, chunkID, true); exist {
err := manager.storage.DeleteFile(0, filePath)
if err == nil {
LOG_TRACE("CHUNK_DELETE", "Deleted chunk file %s as the fossil already exists", chunkID)
}
} else {
LOG_ERROR("CHUNK_DELETE", "Failed to fossilize the chunk %s: %v", chunkID, err)
return false
}
} else {
LOG_TRACE("CHUNK_FOSSILIZE", "Fossilized chunk %s", chunkID)
}
collection.AddFossil(fossilPath)
manager.chunkOperator.Fossilize(chunkID, filePath)
}
return true
@@ -1575,7 +1568,7 @@ func (manager *SnapshotManager) resurrectChunk(fossilPath string, chunkID string
func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string, revisionsToBeDeleted []int,
tags []string, retentions []string,
exhaustive bool, exclusive bool, ignoredIDs []string,
dryRun bool, deleteOnly bool, collectOnly bool) bool {
dryRun bool, deleteOnly bool, collectOnly bool, threads int) bool {
LOG_DEBUG("DELETE_PARAMETERS",
"id: %s, revisions: %v, tags: %v, retentions: %v, exhaustive: %t, exclusive: %t, "+
@@ -1587,15 +1580,27 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
LOG_WARN("DELETE_OPTIONS", "Tags or retention policy will be ignored if at least one revision is specified")
}
preferencePath := GetDuplicacyPreferencePath()
logDir := path.Join(preferencePath, "logs")
os.Mkdir(logDir, 0700)
manager.chunkOperator = CreateChunkOperator(manager.storage, threads)
defer manager.chunkOperator.Stop()
prefPath := GetDuplicacyPreferencePath()
logDir := path.Join(prefPath, "logs")
err := os.MkdirAll(logDir, 0700)
if err != nil {
LOG_ERROR("LOG_DIR", "Could not open log directory %s: %v", logDir, err)
}
logFileName := path.Join(logDir, time.Now().Format("prune-log-20060102-150405"))
logFile, err := os.OpenFile(logFileName, os.O_WRONLY|os.O_CREATE|os.O_TRUNC, 0600)
if err != nil {
LOG_ERROR("LOG_FILE", "Could not open log file %s: %v", logFileName, err)
}
defer func() {
if logFile != nil {
logFile.Close()
cerr := logFile.Close()
if cerr != nil {
LOG_WARN("LOG_FILE", "Could not close log file %s: %v", logFileName, cerr)
}
}
}()
@@ -1674,7 +1679,8 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
}
for _, id := range snapshotIDs {
revisions, err := manager.ListSnapshotRevisions(id)
var revisions []int
revisions, err = manager.ListSnapshotRevisions(id)
if err != nil {
LOG_ERROR("SNAPSHOT_LIST", "Failed to list all revisions for snapshot %s: %v", id, err)
return false
@@ -1694,14 +1700,20 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
}
}
chunkDir := "chunks/"
collectionRegex := regexp.MustCompile(`^([0-9]+)$`)
collectionDir := "fossils"
manager.snapshotCache.CreateDirectory(0, collectionDir)
err = manager.snapshotCache.CreateDirectory(0, collectionDir)
if err != nil {
LOG_ERROR("FOSSIL_COLLECT", "Failed to create collection directory %s: %v", collectionDir, err)
return false
}
collections, _, err := manager.snapshotCache.ListFiles(0, collectionDir)
if err != nil {
LOG_ERROR("FOSSIL_COLLECT", "Failed to list fossil collection files for dir %s: %v", collectionDir, err)
return false
}
maxCollectionNumber := 0
referencedFossils := make(map[string]bool)
@@ -1727,7 +1739,7 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
collectionFile := path.Join(collectionDir, collectionName)
manager.fileChunk.Reset(false)
err := manager.snapshotCache.DownloadFile(0, collectionFile, manager.fileChunk)
err = manager.snapshotCache.DownloadFile(0, collectionFile, manager.fileChunk)
if err != nil {
LOG_ERROR("FOSSIL_COLLECT", "Failed to read the fossil collection file %s: %v", collectionFile, err)
return false
@@ -1740,6 +1752,29 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
return false
}
// Determine if any deleted revisions exist
exist := false
for snapshotID, revisionList := range collection.DeletedRevisions {
for _, revision := range revisionList {
for _, snapshot := range allSnapshots[snapshotID] {
if revision == snapshot.Revision {
LOG_INFO("FOSSIL_GHOSTSNAPSHOT", "Snapshot %s revision %d should have been deleted already", snapshotID, revision)
exist = true
}
}
}
}
if exist {
err = manager.snapshotCache.DeleteFile(0, collectionFile)
if err != nil {
LOG_WARN("FOSSIL_FILE", "Failed to remove the fossil collection file %s: %v", collectionFile, err)
} else {
LOG_INFO("FOSSIL_IGNORE", "The fossil collection file %s has been ignored due to ghost snapshots", collectionFile)
}
continue
}
for _, fossil := range collection.Fossils {
referencedFossils[fossil] = true
}
@@ -1756,7 +1791,9 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
newChunks := make(map[string]bool)
for _, newSnapshot := range newSnapshots {
for _, chunk := range manager.GetSnapshotChunks(newSnapshot) {
fmt.Fprintf(logFile, "Snapshot %s revision %d was created after collection %s\n", newSnapshot.ID, newSnapshot.Revision, collectionName)
LOG_INFO("PRUNE_NEWSNAPSHOT", "Snapshot %s revision %d was created after collection %s", newSnapshot.ID, newSnapshot.Revision, collectionName)
for _, chunk := range manager.GetSnapshotChunks(newSnapshot, false) {
newChunks[chunk] = true
}
}
@@ -1774,15 +1811,14 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
continue
}
manager.resurrectChunk(fossil, chunk)
manager.chunkOperator.Resurrect(chunk, fossil)
fmt.Fprintf(logFile, "Resurrected fossil %s (collection %s)\n", chunk, collectionName)
} else {
if dryRun {
LOG_INFO("FOSSIL_DELETE", "The chunk %s would be permanently removed", chunk)
} else {
manager.storage.DeleteFile(0, fossil)
LOG_INFO("FOSSIL_DELETE", "The chunk %s has been permanently removed", chunk)
manager.chunkOperator.Delete(chunk, fossil)
fmt.Fprintf(logFile, "Deleted fossil %s (collection %s)\n", chunk, collectionName)
}
}
@@ -1794,8 +1830,7 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
LOG_INFO("TEMPORARY_DELETE", "The temporary file %s would be deleted", temporary)
} else {
// Fail silently, since temporary files are supposed to be renamed or deleted after upload is done
manager.storage.DeleteFile(0, temporary)
LOG_INFO("TEMPORARY_DELETE", "The temporary file %s has been deleted", temporary)
manager.chunkOperator.Delete("", temporary)
fmt.Fprintf(logFile, "Deleted temporary %s (collection %s)\n", temporary, collectionName)
}
}
@@ -1912,208 +1947,46 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
}
}
if toBeDeleted == 0 && exhaustive == false {
if toBeDeleted == 0 && !exhaustive {
LOG_INFO("SNAPSHOT_NONE", "No snapshot to delete")
return false
}
chunkRegex := regexp.MustCompile(`^[0-9a-f]+$`)
referencedChunks := make(map[string]bool)
// Now build all chunks referened by snapshot not deleted
for _, snapshots := range allSnapshots {
if len(snapshots) > 0 {
latest := snapshots[len(snapshots)-1]
if latest.Flag && !exclusive {
LOG_ERROR("SNAPSHOT_DELETE",
"The latest snapshot %s at revision %d can't be deleted in non-exclusive mode",
latest.ID, latest.Revision)
return false
}
}
for _, snapshot := range snapshots {
if snapshot.Flag {
LOG_INFO("SNAPSHOT_DELETE", "Deleting snapshot %s at revision %d", snapshot.ID, snapshot.Revision)
continue
}
chunks := manager.GetSnapshotChunks(snapshot)
for _, chunk := range chunks {
// The initial value is 'false'. When a referenced chunk is found it will change the value to 'true'.
referencedChunks[chunk] = false
}
}
}
collection := CreateFossilCollection(allSnapshots)
var success bool
if exhaustive {
// In exhaustive, we scan the entire chunk tree to find dangling chunks and temporaries.
allFiles, _ := manager.ListAllFiles(manager.storage, chunkDir)
for _, file := range allFiles {
if file[len(file)-1] == '/' {
continue
success = manager.pruneSnapshotsExhaustive(referencedFossils, allSnapshots, collection, logFile, dryRun, exclusive)
} else {
success = manager.pruneSnapshotsNonExhaustive(allSnapshots, collection, logFile, dryRun, exclusive)
}
if strings.HasSuffix(file, ".tmp") {
// This is a temporary chunk file. It can be a result of a restore operation still in progress, or
// a left-over from a restore operation that was terminated abruptly.
if dryRun {
LOG_INFO("CHUNK_TEMPORARY", "Found temporary file %s", file)
continue
}
if exclusive {
// In exclusive mode, we assume no other restore operation is running concurrently.
err := manager.storage.DeleteFile(0, chunkDir+file)
if err != nil {
LOG_ERROR("CHUNK_TEMPORARY", "Failed to remove the temporary file %s: %v", file, err)
if !success {
return false
} else {
LOG_DEBUG("CHUNK_TEMPORARY", "Deleted temporary file %s", file)
}
fmt.Fprintf(logFile, "Deleted temporary %s\n", file)
} else {
collection.AddTemporary(file)
}
continue
} else if strings.HasSuffix(file, ".fsl") {
// This is a fossil. If it is unreferenced, it can be a result of failing to save the fossil
// collection file after making it a fossil.
if _, found := referencedFossils[file]; !found {
if dryRun {
LOG_INFO("FOSSIL_UNREFERENCED", "Found unreferenced fossil %s", file)
continue
}
chunk := strings.Replace(file, "/", "", -1)
chunk = strings.Replace(chunk, ".fsl", "", -1)
if _, found := referencedChunks[chunk]; found {
manager.resurrectChunk(chunkDir+file, chunk)
} else {
err := manager.storage.DeleteFile(0, chunkDir+file)
if err != nil {
LOG_WARN("FOSSIL_DELETE", "Failed to remove the unreferenced fossil %s: %v", file, err)
} else {
LOG_DEBUG("FOSSIL_DELETE", "Deleted unreferenced fossil %s", file)
}
fmt.Fprintf(logFile, "Deleted unreferenced fossil %s\n", file)
}
manager.chunkOperator.Stop()
for _, fossil := range manager.chunkOperator.fossils {
collection.AddFossil(fossil)
}
continue
}
chunk := strings.Replace(file, "/", "", -1)
if !chunkRegex.MatchString(chunk) {
LOG_WARN("CHUNK_UNKONWN_FILE", "File %s is not a chunk", file)
continue
}
if value, found := referencedChunks[chunk]; !found {
if dryRun {
LOG_INFO("CHUNK_UNREFERENCED", "Found unreferenced chunk %s", chunk)
continue
}
manager.fossilizeChunk(chunk, chunkDir+file, exclusive, collection)
if exclusive {
fmt.Fprintf(logFile, "Deleted chunk %s (exclusive mode)\n", chunk)
} else {
fmt.Fprintf(logFile, "Marked fossil %s\n", chunk)
}
} else if value {
// Note that the initial value is false. So if the value is true it means another copy of the chunk
// exists in a higher-level directory.
if dryRun {
LOG_INFO("CHUNK_REDUNDANT", "Found redundant chunk %s", chunk)
continue
}
// This is a redundant chunk file (for instance D3/495A8D and D3/49/5A8D )
err := manager.storage.DeleteFile(0, chunkDir+file)
if err != nil {
LOG_WARN("CHUNK_DELETE", "Failed to remove the redundant chunk file %s: %v", file, err)
} else {
LOG_TRACE("CHUNK_DELETE", "Removed the redundant chunk file %s", file)
}
fmt.Fprintf(logFile, "Deleted redundant chunk %s\n", file)
} else {
referencedChunks[chunk] = true
LOG_DEBUG("CHUNK_KEEP", "Chunk %s is referenced", chunk)
}
}
} else {
// In non-exhaustive mode, only chunks that exist in the snapshots to be deleted but not other are identified
// as unreferenced chunks.
// Save the deleted revision in the fossil collection
for _, snapshots := range allSnapshots {
for _, snapshot := range snapshots {
if !snapshot.Flag {
continue
}
chunks := manager.GetSnapshotChunks(snapshot)
for _, chunk := range chunks {
if _, found := referencedChunks[chunk]; found {
continue
}
if dryRun {
LOG_INFO("CHUNK_UNREFERENCED", "Found unreferenced chunk %s", chunk)
continue
}
chunkPath, exist, _, err := manager.storage.FindChunk(0, chunk, false)
if err != nil {
LOG_ERROR("CHUNK_FIND", "Failed to locate the path for the chunk %s: %v", chunk, err)
return false
}
if !exist {
LOG_WARN("CHUNK_MISSING", "The chunk %s referenced by snapshot %s revision %d does not exist",
chunk, snapshot.ID, snapshot.Revision)
continue
}
manager.fossilizeChunk(chunk, chunkPath, exclusive, collection)
if exclusive {
fmt.Fprintf(logFile, "Deleted chunk %s (exclusive mode)\n", chunk)
} else {
fmt.Fprintf(logFile, "Marked fossil %s\n", chunk)
}
referencedChunks[chunk] = true
if snapshot.Flag {
collection.DeletedRevisions[snapshot.ID] = append(collection.DeletedRevisions[snapshot.ID], snapshot.Revision)
}
}
}
}
// Save the fossil collection if it is not empty.
if !collection.IsEmpty() && !dryRun {
if !collection.IsEmpty() && !dryRun && !exclusive {
collection.EndTime = time.Now().Unix()
collectionNumber := maxCollectionNumber + 1
collectionFile := path.Join(collectionDir, fmt.Sprintf("%d", collectionNumber))
description, err := json.Marshal(collection)
var description []byte
description, err = json.Marshal(collection)
if err != nil {
LOG_ERROR("FOSSIL_COLLECT", "Failed to create a json file for the fossil collection: %v", err)
return false
@@ -2142,21 +2015,27 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
LOG_ERROR("SNAPSHOT_DELETE", "Failed to delete the snapshot %s at revision %d: %v",
snapshot.ID, snapshot.Revision, err)
return false
} else {
}
LOG_INFO("SNAPSHOT_DELETE", "The snapshot %s at revision %d has been removed",
snapshot.ID, snapshot.Revision)
}
manager.snapshotCache.DeleteFile(0, snapshotPath)
err = manager.snapshotCache.DeleteFile(0, snapshotPath)
if err != nil {
LOG_WARN("SNAPSHOT_DELETE", "The cached snapshot %s at revision %d could not be removed: %v",
snapshot.ID, snapshot.Revision, err)
fmt.Fprintf(logFile, "Cached snapshot %s at revision %d could not be removed: %v",
snapshot.ID, snapshot.Revision, err)
} else {
fmt.Fprintf(logFile, "Deleted cached snapshot %s at revision %d\n", snapshot.ID, snapshot.Revision)
}
}
}
if collection.IsEmpty() && !dryRun && toBeDeleted != 0 && !exclusive {
LOG_INFO("FOSSIL_NONE",
"No fossil collection has been created since deleted snapshots did not reference any unique chunks")
}
var latestSnapshot *Snapshot = nil
var latestSnapshot *Snapshot
if len(allSnapshots[selfID]) > 0 {
latestSnapshot = allSnapshots[selfID][len(allSnapshots[selfID])-1]
}
@@ -2170,6 +2049,211 @@ func (manager *SnapshotManager) PruneSnapshots(selfID string, snapshotID string,
return true
}
// pruneSnapshots in non-exhaustive mode, only chunks that exist in the
// snapshots to be deleted but not other are identified as unreferenced chunks.
func (manager *SnapshotManager) pruneSnapshotsNonExhaustive(allSnapshots map[string][]*Snapshot, collection *FossilCollection, logFile io.Writer, dryRun, exclusive bool) bool {
targetChunks := make(map[string]bool)
// Now build all chunks referened by snapshot not deleted
for _, snapshots := range allSnapshots {
if len(snapshots) > 0 {
latest := snapshots[len(snapshots)-1]
if latest.Flag && !exclusive {
LOG_ERROR("SNAPSHOT_DELETE",
"The latest snapshot %s at revision %d can't be deleted in non-exclusive mode",
latest.ID, latest.Revision)
return false
}
}
for _, snapshot := range snapshots {
if !snapshot.Flag {
continue
}
LOG_INFO("SNAPSHOT_DELETE", "Deleting snapshot %s at revision %d", snapshot.ID, snapshot.Revision)
chunks := manager.GetSnapshotChunks(snapshot, false)
for _, chunk := range chunks {
// The initial value is 'false'. When a referenced chunk is found it will change the value to 'true'.
targetChunks[chunk] = false
}
}
}
for _, snapshots := range allSnapshots {
for _, snapshot := range snapshots {
if snapshot.Flag {
continue
}
chunks := manager.GetSnapshotChunks(snapshot, false)
for _, chunk := range chunks {
if _, found := targetChunks[chunk]; found {
targetChunks[chunk] = true
}
}
}
}
for chunk, value := range targetChunks {
if value {
continue
}
if dryRun {
LOG_INFO("CHUNK_UNREFERENCED", "Found unreferenced chunk %s", chunk)
continue
}
manager.fossilizeChunk(chunk, "", exclusive)
if exclusive {
fmt.Fprintf(logFile, "Deleted chunk %s (exclusive mode)\n", chunk)
} else {
fmt.Fprintf(logFile, "Marked fossil %s\n", chunk)
}
targetChunks[chunk] = true
}
return true
}
// pruneSnapshotsExhaustive in exhaustive, we scan the entire chunk tree to
// find dangling chunks and temporaries.
func (manager *SnapshotManager) pruneSnapshotsExhaustive(referencedFossils map[string]bool, allSnapshots map[string][]*Snapshot, collection *FossilCollection, logFile io.Writer, dryRun, exclusive bool) bool {
chunkRegex := regexp.MustCompile(`^[0-9a-f]+$`)
referencedChunks := make(map[string]bool)
// Now build all chunks referened by snapshot not deleted
for _, snapshots := range allSnapshots {
if len(snapshots) > 0 {
latest := snapshots[len(snapshots)-1]
if latest.Flag && !exclusive {
LOG_ERROR("SNAPSHOT_DELETE",
"The latest snapshot %s at revision %d can't be deleted in non-exclusive mode",
latest.ID, latest.Revision)
return false
}
}
for _, snapshot := range snapshots {
if snapshot.Flag {
LOG_INFO("SNAPSHOT_DELETE", "Deleting snapshot %s at revision %d", snapshot.ID, snapshot.Revision)
continue
}
chunks := manager.GetSnapshotChunks(snapshot, false)
for _, chunk := range chunks {
// The initial value is 'false'. When a referenced chunk is found it will change the value to 'true'.
referencedChunks[chunk] = false
}
}
}
allFiles, _ := manager.ListAllFiles(manager.storage, chunkDir)
for _, file := range allFiles {
if file[len(file)-1] == '/' {
continue
}
if strings.HasSuffix(file, ".tmp") {
// This is a temporary chunk file. It can be a result of a restore operation still in progress, or
// a left-over from a restore operation that was terminated abruptly.
if dryRun {
LOG_INFO("CHUNK_TEMPORARY", "Found temporary file %s", file)
continue
}
if exclusive {
// In exclusive mode, we assume no other restore operation is running concurrently.
manager.chunkOperator.Delete("", chunkDir+file)
fmt.Fprintf(logFile, "Deleted temporary %s\n", file)
} else {
collection.AddTemporary(file)
}
continue
} else if strings.HasSuffix(file, ".fsl") {
// This is a fossil. If it is unreferenced, it can be a result of failing to save the fossil
// collection file after making it a fossil.
if _, found := referencedFossils[file]; !found {
chunk := strings.Replace(file, "/", "", -1)
chunk = strings.Replace(chunk, ".fsl", "", -1)
if _, found := referencedChunks[chunk]; found {
if dryRun {
LOG_INFO("FOSSIL_REFERENCED", "Found referenced fossil %s", file)
continue
}
manager.chunkOperator.Resurrect(chunk, chunkDir + file)
fmt.Fprintf(logFile, "Found referenced fossil %s\n", file)
} else {
if dryRun {
LOG_INFO("FOSSIL_UNREFERENCED", "Found unreferenced fossil %s", file)
continue
}
if exclusive {
manager.chunkOperator.Delete(chunk, chunkDir + file)
} else {
collection.AddFossil(chunkDir + file)
LOG_DEBUG("FOSSIL_FIND", "Found unreferenced fossil %s", file)
}
fmt.Fprintf(logFile, "Found unreferenced fossil %s\n", file)
}
}
continue
}
chunk := strings.Replace(file, "/", "", -1)
if !chunkRegex.MatchString(chunk) {
LOG_WARN("CHUNK_UNKONWN_FILE", "File %s is not a chunk", file)
continue
}
if value, found := referencedChunks[chunk]; !found {
if dryRun {
LOG_INFO("CHUNK_UNREFERENCED", "Found unreferenced chunk %s", chunk)
continue
}
manager.fossilizeChunk(chunk, chunkDir+file, exclusive)
if exclusive {
fmt.Fprintf(logFile, "Deleted chunk %s (exclusive mode)\n", chunk)
} else {
fmt.Fprintf(logFile, "Marked fossil %s\n", chunk)
}
} else if value {
// Note that the initial value is false. So if the value is true it means another copy of the chunk
// exists in a higher-level directory.
if dryRun {
LOG_INFO("CHUNK_REDUNDANT", "Found redundant chunk %s", chunk)
continue
}
// This is a redundant chunk file (for instance D3/495A8D and D3/49/5A8D )
manager.chunkOperator.Delete(chunk, chunkDir+file)
fmt.Fprintf(logFile, "Deleted redundant chunk %s\n", file)
} else {
referencedChunks[chunk] = true
LOG_DEBUG("CHUNK_KEEP", "Chunk %s is referenced", chunk)
}
}
return true
}
// CheckSnapshot performs sanity checks on the given snapshot.
func (manager *SnapshotManager) CheckSnapshot(snapshot *Snapshot) (err error) {

View File

@@ -14,6 +14,7 @@ import (
"strings"
"testing"
"time"
"io/ioutil"
)
func createDummySnapshot(snapshotID string, revision int, endTime int64) *Snapshot {
@@ -143,6 +144,15 @@ func uploadRandomChunk(manager *SnapshotManager, chunkSize int) string {
return uploadTestChunk(manager, content)
}
func uploadRandomChunks(manager *SnapshotManager, chunkSize int, numberOfChunks int) []string {
chunkList := make([]string, 0)
for i := 0; i < numberOfChunks; i++ {
chunkHash := uploadRandomChunk(manager, chunkSize)
chunkList = append(chunkList, chunkHash)
}
return chunkList
}
func createTestSnapshot(manager *SnapshotManager, snapshotID string, revision int, startTime int64, endTime int64, chunkHashes []string, tag string) {
snapshot := &Snapshot{
@@ -203,7 +213,7 @@ func checkTestSnapshots(manager *SnapshotManager, expectedSnapshots int, expecte
snapshot := manager.DownloadSnapshot(snapshotID, revision)
numberOfSnapshots++
for _, chunk := range manager.GetSnapshotChunks(snapshot) {
for _, chunk := range manager.GetSnapshotChunks(snapshot, false) {
chunks[chunk] = true
}
}
@@ -226,7 +236,7 @@ func checkTestSnapshots(manager *SnapshotManager, expectedSnapshots int, expecte
}
}
func TestSingleRepositoryPrune(t *testing.T) {
func TestPruneSingleRepository(t *testing.T) {
setTestingT(t)
@@ -242,34 +252,35 @@ func TestSingleRepositoryPrune(t *testing.T) {
now := time.Now().Unix()
day := int64(24 * 3600)
t.Logf("Creating 1 snapshot")
createTestSnapshot(snapshotManager, "repository1", 1, now-3*day-3600, now-3*day-60, []string{chunkHash1, chunkHash2}, "tag")
checkTestSnapshots(snapshotManager, 1, 2)
t.Logf("Creating 2 snapshots")
createTestSnapshot(snapshotManager, "repository1", 1, now-4*day-3600, now-3*day-60, []string{chunkHash1, chunkHash2}, "tag")
createTestSnapshot(snapshotManager, "repository1", 2, now-4*day-3600, now-3*day-60, []string{chunkHash1, chunkHash2}, "tag")
checkTestSnapshots(snapshotManager, 2, 2)
t.Logf("Creating 2 snapshots")
createTestSnapshot(snapshotManager, "repository1", 2, now-2*day-3600, now-2*day-60, []string{chunkHash2, chunkHash3}, "tag")
createTestSnapshot(snapshotManager, "repository1", 3, now-1*day-3600, now-1*day-60, []string{chunkHash3, chunkHash4}, "tag")
checkTestSnapshots(snapshotManager, 3, 0)
createTestSnapshot(snapshotManager, "repository1", 3, now-2*day-3600, now-2*day-60, []string{chunkHash2, chunkHash3}, "tag")
createTestSnapshot(snapshotManager, "repository1", 4, now-1*day-3600, now-1*day-60, []string{chunkHash3, chunkHash4}, "tag")
checkTestSnapshots(snapshotManager, 4, 0)
t.Logf("Removing snapshot repository1 revision 1 with --exclusive")
snapshotManager.PruneSnapshots("repository1", "repository1", []int{1}, []string{}, []string{}, false, true, []string{}, false, false, false)
t.Logf("Removing snapshot repository1 revisions 1 and 2 with --exclusive")
snapshotManager.PruneSnapshots("repository1", "repository1", []int{1, 2}, []string{}, []string{}, false, true, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 0)
t.Logf("Removing snapshot repository1 revision 2 without --exclusive")
snapshotManager.PruneSnapshots("repository1", "repository1", []int{2}, []string{}, []string{}, false, false, []string{}, false, false, false)
t.Logf("Removing snapshot repository1 revision 3 without --exclusive")
snapshotManager.PruneSnapshots("repository1", "repository1", []int{3}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 1, 2)
t.Logf("Creating 1 snapshot")
chunkHash5 := uploadRandomChunk(snapshotManager, chunkSize)
createTestSnapshot(snapshotManager, "repository1", 4, now+1*day-3600, now+1*day, []string{chunkHash4, chunkHash5}, "tag")
createTestSnapshot(snapshotManager, "repository1", 5, now+1*day-3600, now+1*day, []string{chunkHash4, chunkHash5}, "tag")
checkTestSnapshots(snapshotManager, 2, 2)
t.Logf("Prune without removing any snapshots -- fossils will be deleted")
snapshotManager.PruneSnapshots("repository1", "repository1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("repository1", "repository1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 0)
}
func TestSingleHostPrune(t *testing.T) {
func TestPruneSingleHost(t *testing.T) {
setTestingT(t)
@@ -292,11 +303,11 @@ func TestSingleHostPrune(t *testing.T) {
checkTestSnapshots(snapshotManager, 3, 0)
t.Logf("Removing snapshot vm1@host1 revision 1 without --exclusive")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 2)
t.Logf("Prune without removing any snapshots -- no fossils will be deleted")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 2)
t.Logf("Creating 1 snapshot")
@@ -305,12 +316,12 @@ func TestSingleHostPrune(t *testing.T) {
checkTestSnapshots(snapshotManager, 3, 2)
t.Logf("Prune without removing any snapshots -- fossils will be deleted")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 3, 0)
}
func TestMultipleHostPrune(t *testing.T) {
func TestPruneMultipleHost(t *testing.T) {
setTestingT(t)
@@ -333,11 +344,11 @@ func TestMultipleHostPrune(t *testing.T) {
checkTestSnapshots(snapshotManager, 3, 0)
t.Logf("Removing snapshot vm1@host1 revision 1 without --exclusive")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 2)
t.Logf("Prune without removing any snapshots -- no fossils will be deleted")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 2)
t.Logf("Creating 1 snapshot")
@@ -346,7 +357,7 @@ func TestMultipleHostPrune(t *testing.T) {
checkTestSnapshots(snapshotManager, 3, 2)
t.Logf("Prune without removing any snapshots -- no fossils will be deleted")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 3, 2)
t.Logf("Creating 1 snapshot")
@@ -355,7 +366,7 @@ func TestMultipleHostPrune(t *testing.T) {
checkTestSnapshots(snapshotManager, 4, 2)
t.Logf("Prune without removing any snapshots -- fossils will be deleted")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 4, 0)
}
@@ -380,7 +391,7 @@ func TestPruneAndResurrect(t *testing.T) {
checkTestSnapshots(snapshotManager, 2, 0)
t.Logf("Removing snapshot vm1@host1 revision 1 without --exclusive")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 1, 2)
t.Logf("Creating 1 snapshot")
@@ -389,11 +400,11 @@ func TestPruneAndResurrect(t *testing.T) {
checkTestSnapshots(snapshotManager, 2, 2)
t.Logf("Prune without removing any snapshots -- one fossil will be resurrected")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 0)
}
func TestInactiveHostPrune(t *testing.T) {
func TestPruneWithInactiveHost(t *testing.T) {
setTestingT(t)
@@ -417,11 +428,11 @@ func TestInactiveHostPrune(t *testing.T) {
checkTestSnapshots(snapshotManager, 3, 0)
t.Logf("Removing snapshot vm1@host1 revision 1")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 2)
t.Logf("Prune without removing any snapshots -- no fossils will be deleted")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 2)
t.Logf("Creating 1 snapshot")
@@ -430,11 +441,11 @@ func TestInactiveHostPrune(t *testing.T) {
checkTestSnapshots(snapshotManager, 3, 2)
t.Logf("Prune without removing any snapshots -- fossils will be deleted")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 3, 0)
}
func TestRetentionPolicy(t *testing.T) {
func TestPruneWithRetentionPolicy(t *testing.T) {
setTestingT(t)
@@ -458,19 +469,19 @@ func TestRetentionPolicy(t *testing.T) {
checkTestSnapshots(snapshotManager, 30, 0)
t.Logf("Removing snapshot vm1@host1 0:20 with --exclusive")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{"0:20"}, false, true, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{"0:20"}, false, true, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 19, 0)
t.Logf("Removing snapshot vm1@host1 -k 0:20 with --exclusive")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{"0:20"}, false, true, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{"0:20"}, false, true, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 19, 0)
t.Logf("Removing snapshot vm1@host1 -k 3:14 -k 2:7 with --exclusive")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{"3:14", "2:7"}, false, true, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{"3:14", "2:7"}, false, true, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 12, 0)
}
func TestRetentionPolicyAndTag(t *testing.T) {
func TestPruneWithRetentionPolicyAndTag(t *testing.T) {
setTestingT(t)
@@ -498,6 +509,179 @@ func TestRetentionPolicyAndTag(t *testing.T) {
checkTestSnapshots(snapshotManager, 30, 0)
t.Logf("Removing snapshot vm1@host1 0:20 with --exclusive and --tag manual")
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{"manual"}, []string{"0:7"}, false, true, []string{}, false, false, false)
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{"manual"}, []string{"0:7"}, false, true, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 22, 0)
}
// Test that an unreferenced fossil shouldn't be removed as it may be the result of another prune job in-progress.
func TestPruneWithFossils(t *testing.T) {
setTestingT(t)
testDir := path.Join(os.TempDir(), "duplicacy_test", "snapshot_test")
snapshotManager := createTestSnapshotManager(testDir)
chunkSize := 1024
chunkHash1 := uploadRandomChunk(snapshotManager, chunkSize)
chunkHash2 := uploadRandomChunk(snapshotManager, chunkSize)
chunkHash3 := uploadRandomChunk(snapshotManager, chunkSize)
// Create an unreferenced fossil
snapshotManager.storage.UploadFile(0, "chunks/113b6a2350dcfd836829c47304dd330fa6b58b93dd7ac696c6b7b913e6868662.fsl", []byte("this is a test fossil"))
now := time.Now().Unix()
day := int64(24 * 3600)
t.Logf("Creating 2 snapshots")
createTestSnapshot(snapshotManager, "vm1@host1", 1, now-3*day-3600, now-3*day-60, []string{chunkHash1, chunkHash2}, "tag")
createTestSnapshot(snapshotManager, "vm1@host1", 2, now-2*day-3600, now-2*day-60, []string{chunkHash2, chunkHash3}, "tag")
checkTestSnapshots(snapshotManager, 2, 1)
t.Logf("Prune without removing any snapshots but with --exhaustive")
// The unreferenced fossil shouldn't be removed
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, true, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 1)
t.Logf("Prune without removing any snapshots but with --exclusive")
// Now the unreferenced fossil should be removed
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, true, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 0)
}
func TestPruneMultipleThread(t *testing.T) {
setTestingT(t)
testDir := path.Join(os.TempDir(), "duplicacy_test", "snapshot_test")
snapshotManager := createTestSnapshotManager(testDir)
chunkSize := 1024
numberOfChunks := 256
numberOfThreads := 4
chunkList1 := uploadRandomChunks(snapshotManager, chunkSize, numberOfChunks)
chunkList2 := uploadRandomChunks(snapshotManager, chunkSize, numberOfChunks)
now := time.Now().Unix()
day := int64(24 * 3600)
t.Logf("Creating 2 snapshots")
createTestSnapshot(snapshotManager, "repository1", 1, now-4*day-3600, now-3*day-60, chunkList1, "tag")
createTestSnapshot(snapshotManager, "repository1", 2, now-3*day-3600, now-2*day-60, chunkList2, "tag")
checkTestSnapshots(snapshotManager, 2, 0)
t.Logf("Removing snapshot revisions 1 with --exclusive")
snapshotManager.PruneSnapshots("repository1", "repository1", []int{1}, []string{}, []string{}, false, true, []string{}, false, false, false, numberOfThreads)
checkTestSnapshots(snapshotManager, 1, 0)
t.Logf("Creating 1 more snapshot")
chunkList3 := uploadRandomChunks(snapshotManager, chunkSize, numberOfChunks)
createTestSnapshot(snapshotManager, "repository1", 3, now-2*day-3600, now-1*day-60, chunkList3, "tag")
t.Logf("Removing snapshot repository1 revision 2 without --exclusive")
snapshotManager.PruneSnapshots("repository1", "repository1", []int{2}, []string{}, []string{}, false, false, []string{}, false, false, false, numberOfThreads)
t.Logf("Prune without removing any snapshots but with --exclusive")
snapshotManager.PruneSnapshots("repository1", "repository1", []int{}, []string{}, []string{}, false, true, []string{}, false, false, false, numberOfThreads)
checkTestSnapshots(snapshotManager, 1, 0)
}
// A snapshot not seen by a fossil collection should always be consider a new snapshot in the fossil deletion step
func TestPruneNewSnapshots(t *testing.T) {
setTestingT(t)
testDir := path.Join(os.TempDir(), "duplicacy_test", "snapshot_test")
snapshotManager := createTestSnapshotManager(testDir)
chunkSize := 1024
chunkHash1 := uploadRandomChunk(snapshotManager, chunkSize)
chunkHash2 := uploadRandomChunk(snapshotManager, chunkSize)
chunkHash3 := uploadRandomChunk(snapshotManager, chunkSize)
chunkHash4 := uploadRandomChunk(snapshotManager, chunkSize)
now := time.Now().Unix()
day := int64(24 * 3600)
t.Logf("Creating 3 snapshots")
createTestSnapshot(snapshotManager, "vm1@host1", 1, now-3*day-3600, now-3*day-60, []string{chunkHash1, chunkHash2}, "tag")
createTestSnapshot(snapshotManager, "vm1@host1", 2, now-2*day-3600, now-2*day-60, []string{chunkHash2, chunkHash3}, "tag")
createTestSnapshot(snapshotManager, "vm2@host1", 1, now-2*day-3600, now-2*day-60, []string{chunkHash3, chunkHash4}, "tag")
checkTestSnapshots(snapshotManager, 3, 0)
t.Logf("Prune snapshot 1")
// chunkHash1 should be marked as fossil
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 2)
chunkHash5 := uploadRandomChunk(snapshotManager, chunkSize)
// Create another snapshot of vm1 that brings back chunkHash1
createTestSnapshot(snapshotManager, "vm1@host1", 3, now-0*day-3600, now-0*day-60, []string{chunkHash1, chunkHash3}, "tag")
// Create another snapshot of vm2 so the fossil collection will be processed by next prune
createTestSnapshot(snapshotManager, "vm2@host1", 2, now + 3600, now + 3600 * 2, []string{chunkHash4, chunkHash5}, "tag")
// Now chunkHash1 wil be resurrected
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 4, 0)
snapshotManager.CheckSnapshots("vm1@host1", []int{2, 3}, "", false, false, false, false, false);
}
// A fossil collection left by an aborted prune should be ignored if any supposedly deleted snapshot exists
func TestPruneGhostSnapshots(t *testing.T) {
setTestingT(t)
EnableStackTrace()
testDir := path.Join(os.TempDir(), "duplicacy_test", "snapshot_test")
snapshotManager := createTestSnapshotManager(testDir)
chunkSize := 1024
chunkHash1 := uploadRandomChunk(snapshotManager, chunkSize)
chunkHash2 := uploadRandomChunk(snapshotManager, chunkSize)
chunkHash3 := uploadRandomChunk(snapshotManager, chunkSize)
now := time.Now().Unix()
day := int64(24 * 3600)
t.Logf("Creating 2 snapshots")
createTestSnapshot(snapshotManager, "vm1@host1", 1, now-3*day-3600, now-3*day-60, []string{chunkHash1, chunkHash2}, "tag")
createTestSnapshot(snapshotManager, "vm1@host1", 2, now-2*day-3600, now-2*day-60, []string{chunkHash2, chunkHash3}, "tag")
checkTestSnapshots(snapshotManager, 2, 0)
snapshot1, err := ioutil.ReadFile(path.Join(testDir, "snapshots", "vm1@host1", "1"))
if err != nil {
t.Errorf("Failed to read snapshot file: %v", err)
}
t.Logf("Prune snapshot 1")
// chunkHash1 should be marked as fossil
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 1, 2)
// Recover the snapshot file for revision 1; this is to simulate a scenario where prune may encounter a network error after
// leaving the fossil collection but before deleting any snapshots.
err = ioutil.WriteFile(path.Join(testDir, "snapshots", "vm1@host1", "1"), snapshot1, 0644)
if err != nil {
t.Errorf("Failed to write snapshot file: %v", err)
}
// Create another snapshot of vm1 so the fossil collection becomes eligible for processing.
chunkHash4 := uploadRandomChunk(snapshotManager, chunkSize)
createTestSnapshot(snapshotManager, "vm1@host1", 3, now - day - 3600, now - day - 60, []string{chunkHash3, chunkHash4}, "tag")
// Run the prune again but the fossil collection should be igored, since revision 1 still exists
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 3, 2)
snapshotManager.CheckSnapshots("vm1@host1", []int{1, 2, 3}, "", false, false, false, true /*searchFossils*/, false);
// Prune snapshot 1 again
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{1}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 2, 2)
// Create another snapshot
chunkHash5 := uploadRandomChunk(snapshotManager, chunkSize)
createTestSnapshot(snapshotManager, "vm1@host1", 4, now + 3600, now + 3600 * 2, []string{chunkHash5, chunkHash5}, "tag")
checkTestSnapshots(snapshotManager, 3, 2)
// Run the prune again and this time the fossil collection will be processed and the fossils removed
snapshotManager.PruneSnapshots("vm1@host1", "vm1@host1", []int{}, []string{}, []string{}, false, false, []string{}, false, false, false, 1)
checkTestSnapshots(snapshotManager, 3, 0)
snapshotManager.CheckSnapshots("vm1@host1", []int{2, 3, 4}, "", false, false, false, false, false);
}

View File

@@ -261,7 +261,7 @@ func CreateStorage(preference Preference, resetPassword bool, threads int) (stor
return fileStorage
}
urlRegex := regexp.MustCompile(`^(\w+)://([\w\-]+@)?([^/]+)(/(.+))?`)
urlRegex := regexp.MustCompile(`^([\w-]+)://([\w\-@\.]+@)?([^/]+)(/(.+))?`)
matched := urlRegex.FindStringSubmatch(storageURL)
@@ -461,6 +461,42 @@ func CreateStorage(preference Preference, resetPassword bool, threads int) (stor
SavePassword(preference, "s3_secret", secretKey)
return storage
} else if matched[1] == "wasabi" {
region := matched[2]
endpoint := matched[3]
bucket := matched[5]
if region != "" {
region = region[:len(region)-1]
}
key := GetPassword(preference, "wasabi_key",
"Enter Wasabi key:", true, resetPassword)
secret := GetPassword(preference, "wasabi_secret",
"Enter Wasabi secret:", true, resetPassword)
storageDir := ""
if strings.Contains(bucket, "/") {
firstSlash := strings.Index(bucket, "/")
storageDir = bucket[firstSlash+1:]
bucket = bucket[:firstSlash]
}
storage, err := CreateWasabiStorage(region, endpoint,
bucket, storageDir, key, secret, threads)
if err != nil {
LOG_ERROR("STORAGE_CREATE", "Failed to load the Wasabi storage at %s: %v", storageURL, err)
return nil
}
SavePassword(preference, "wasabi_key", key)
SavePassword(preference, "wasabi_secret", secret)
return storage
} else if matched[1] == "dropbox" {
storageDir := matched[3] + matched[5]
token := GetPassword(preference, "dropbox_token", "Enter Dropbox access token:", true, resetPassword)
@@ -570,6 +606,29 @@ func CreateStorage(preference Preference, resetPassword bool, threads int) (stor
}
SavePassword(preference, "swift_key", key)
return swiftStorage
} else if matched[1] == "webdav" || matched[1] == "webdav-http" {
server := matched[3]
username := matched[2]
username = username[:len(username) - 1]
storageDir := matched[5]
port := 0
useHTTP := matched[1] == "webdav-http"
if strings.Contains(server, ":") {
index := strings.Index(server, ":")
port, _ = strconv.Atoi(server[index+1:])
server = server[:index]
}
prompt := fmt.Sprintf("Enter the WebDAV password:")
password := GetPassword(preference, "webdav_password", prompt, true, resetPassword)
webDAVStorage, err := CreateWebDAVStorage(server, port, username, password, storageDir, useHTTP, threads)
if err != nil {
LOG_ERROR("STORAGE_CREATE", "Failed to load the WebDAV storage at %s: %v", storageURL, err)
return nil
}
SavePassword(preference, "webdav_password", password)
return webDAVStorage
} else {
LOG_ERROR("STORAGE_CREATE", "The storage type '%s' is not supported", matched[1])
return nil

View File

@@ -78,10 +78,14 @@ func loadStorage(localStoragePath string, threads int) (Storage, error) {
storage, err := CreateSFTPStorageWithPassword(config["server"], port, config["username"], config["directory"], 2, config["password"], threads)
storage.SetDefaultNestingLevels([]int{2, 3}, 2)
return storage, err
} else if testStorageName == "s3" || testStorageName == "wasabi" {
} else if testStorageName == "s3" {
storage, err := CreateS3Storage(config["region"], config["endpoint"], config["bucket"], config["directory"], config["access_key"], config["secret_key"], threads, true, false)
storage.SetDefaultNestingLevels([]int{2, 3}, 2)
return storage, err
storage.SetDefaultNestingLevels([]int{2, 3}, 2)
} else if testStorageName == "wasabi" {
storage, err := CreateWasabiStorage(config["region"], config["endpoint"], config["bucket"], config["directory"], config["access_key"], config["secret_key"], threads)
return storage, err
storage.SetDefaultNestingLevels([]int{2, 3}, 2)
} else if testStorageName == "s3c" {
storage, err := CreateS3CStorage(config["region"], config["endpoint"], config["bucket"], config["directory"], config["access_key"], config["secret_key"], threads)
storage.SetDefaultNestingLevels([]int{2, 3}, 2)
@@ -142,9 +146,18 @@ func loadStorage(localStoragePath string, threads int) (Storage, error) {
storage, err := CreateSwiftStorage(config["storage_url"], config["key"], threads)
storage.SetDefaultNestingLevels([]int{2, 3}, 2)
return storage, err
} else if testStorageName == "pcloud" || testStorageName == "box" {
storage, err := CreateWebDAVStorage(config["host"], 0, config["username"], config["password"], config["storage_path"], false, threads)
if err != nil {
return nil, err
}
storage.SetDefaultNestingLevels([]int{2, 3}, 2)
return storage, err
} else {
return nil, fmt.Errorf("Invalid storage named: %s", testStorageName)
}
return nil, fmt.Errorf("Invalid storage named: %s", testStorageName)
}
func cleanStorage(storage Storage) {
@@ -374,6 +387,7 @@ func TestStorage(t *testing.T) {
snapshotIDs := []string{}
for _, snapshotDir := range snapshotDirs {
LOG_INFO("debug", "snapshot dir: %s", snapshotDir)
if len(snapshotDir) > 0 && snapshotDir[len(snapshotDir)-1] == '/' {
snapshotIDs = append(snapshotIDs, snapshotDir[:len(snapshotDir)-1])
}
@@ -500,7 +514,7 @@ func TestStorage(t *testing.T) {
} else {
err = storage.DeleteFile(0, filePath)
if err != nil {
t.Errorf("Failed to delete file %s: %v", filePath)
t.Errorf("Failed to delete file %s: %v", filePath, err)
} else {
time.Sleep(time.Duration(delay) * time.Second)
filePath, exist, _, err = storage.FindChunk(0, chunks[1], true)
@@ -587,7 +601,6 @@ func TestCleanStorage(t *testing.T) {
storage.DeleteFile(0, "config")
LOG_INFO("DELETE_FILE", "Deleted config")
files, _, err := storage.ListFiles(0, "chunks/")
for _, file := range files {
if len(file) > 0 && file[len(file)-1] != '/' {

View File

@@ -344,11 +344,13 @@ func MatchPath(filePath string, patterns []string) (included bool) {
for _, pattern := range patterns {
if pattern[0] == '+' {
if matchPattern(filePath, pattern[1:]) {
LOG_DEBUG("PATTERN_INCLUDE", "%s is included by pattern %s", filePath, pattern)
return true
}
} else if pattern[0] == '-' {
allIncludes = false
if matchPattern(filePath, pattern[1:]) {
LOG_DEBUG("PATTERN_EXCLUDE", "%s is excluded by pattern %s", filePath, pattern)
return false
}
} else if strings.HasPrefix(pattern, "i:") || strings.HasPrefix(pattern, "e:") {
@@ -363,7 +365,14 @@ func MatchPath(filePath string, patterns []string) (included bool) {
matched = re.MatchString(filePath)
}
if matched {
return strings.HasPrefix(pattern, "i:")
if strings.HasPrefix(pattern, "i:") {
LOG_DEBUG("PATTERN_INCLUDE", "%s is included by pattern %s", filePath, pattern)
return true
} else {
LOG_DEBUG("PATTERN_EXCLUDE", "%s is excluded by pattern %s", filePath, pattern)
return false
}
} else {
if strings.HasPrefix(pattern, "e:") {
allIncludes = false
@@ -372,7 +381,13 @@ func MatchPath(filePath string, patterns []string) (included bool) {
}
}
return !allIncludes
if allIncludes {
LOG_DEBUG("PATTERN_EXCLUDE", "%s is excluded", filePath)
return false
} else {
LOG_DEBUG("PATTERN_INCLUDE", "%s is included", filePath)
return true
}
}
func joinPath(components ...string) string {

View File

@@ -112,7 +112,7 @@ func TestRateLimit(t *testing.T) {
return
}
if int(n) != len(content) {
t.Errorf("Wrote %s bytes instead of %s", n, len(content))
t.Errorf("Wrote %d bytes instead of %d", n, len(content))
return
}
@@ -127,7 +127,7 @@ func TestRateLimit(t *testing.T) {
return
}
if int(n) != len(content) {
t.Errorf("Copied %s bytes instead of %s", n, len(content))
t.Errorf("Copied %d bytes instead of %d", n, len(content))
return
}

View File

@@ -0,0 +1,192 @@
//
// Storage module for Wasabi (https://www.wasabi.com)
//
// Wasabi is nominally compatible with AWS S3, but the copy-and-delete
// method used for renaming objects creates additional expense under
// Wasabi's billing system. This module is a pass-through to the
// existing S3 module for everything other than that one operation.
//
// This module copyright 2017 Mark Feit (https://github.com/markfeit)
// and may be distributed under the same terms as Duplicacy.
package duplicacy
import (
"crypto/hmac"
"crypto/sha1"
"encoding/base64"
"errors"
"fmt"
"net/http"
"time"
)
type WasabiStorage struct {
StorageBase
s3 *S3Storage
region string
endpoint string
bucket string
storageDir string
key string
secret string
client *http.Client
}
// See the Storage interface in duplicacy_storage.go for function
// descriptions.
func CreateWasabiStorage(
regionName string, endpoint string,
bucketName string, storageDir string,
accessKey string, secretKey string,
threads int,
) (storage *WasabiStorage, err error) {
s3storage, error := CreateS3Storage(regionName, endpoint, bucketName,
storageDir, accessKey, secretKey, threads,
true, // isSSLSupported
false, // isMinioCompatible
)
if err != nil {
return nil, error
}
wasabi := &WasabiStorage{
// Pass-through to existing S3 module
s3: s3storage,
// Local copies required for renaming
region: regionName,
endpoint: endpoint,
bucket: bucketName,
storageDir: storageDir,
key: accessKey,
secret: secretKey,
client: &http.Client{},
}
wasabi.DerivedStorage = wasabi
wasabi.SetDefaultNestingLevels([]int{0}, 0)
return wasabi, nil
}
func (storage *WasabiStorage) ListFiles(
threadIndex int, dir string,
) (files []string, sizes []int64, err error) {
return storage.s3.ListFiles(threadIndex, dir)
}
func (storage *WasabiStorage) DeleteFile(
threadIndex int, filePath string,
) (err error) {
return storage.s3.DeleteFile(threadIndex, filePath)
}
// This is a lightweight implementation of a call to Wasabi for a
// rename. It's designed to get the job done with as few dependencies
// on other packages as possible rather than being somethng
// general-purpose and reusable.
func (storage *WasabiStorage) MoveFile(
threadIndex int, from string, to string,
) (err error) {
var from_path string
// The from path includes the bucket. Take care not to include an empty storageDir
// string as Wasabi's backend will return 404 on URLs with double slashes.
if (storage.storageDir == "") {
from_path = fmt.Sprintf("/%s/%s", storage.bucket, from)
} else {
from_path = fmt.Sprintf("/%s/%s/%s", storage.bucket, storage.storageDir, from)
}
object := fmt.Sprintf("https://%s@%s%s",
storage.region, storage.endpoint, from_path)
// The object's new name is relative to the top of the bucket.
new_name := fmt.Sprintf("%s/%s", storage.storageDir, to)
timestamp := time.Now().Format(time.RFC1123Z)
signing_string := fmt.Sprintf("MOVE\n\n\n%s\n%s", timestamp, from_path)
signer := hmac.New(sha1.New, []byte(storage.secret))
signer.Write([]byte(signing_string))
signature := base64.StdEncoding.EncodeToString(signer.Sum(nil))
authorization := fmt.Sprintf("AWS %s:%s", storage.key, signature)
request, error := http.NewRequest("MOVE", object, nil)
if error != nil {
return error
}
request.Header.Add("Authorization", authorization)
request.Header.Add("Date", timestamp)
request.Header.Add("Destination", new_name)
request.Header.Add("Host", storage.endpoint)
request.Header.Add("Overwrite", "true")
response, error := storage.client.Do(request)
if error != nil {
return error
}
defer response.Body.Close()
if response.StatusCode != 200 {
return errors.New(response.Status)
}
return nil
}
func (storage *WasabiStorage) CreateDirectory(
threadIndex int, dir string,
) (err error) {
return storage.s3.CreateDirectory(threadIndex, dir)
}
func (storage *WasabiStorage) GetFileInfo(
threadIndex int, filePath string,
) (exist bool, isDir bool, size int64, err error) {
return storage.s3.GetFileInfo(threadIndex, filePath)
}
func (storage *WasabiStorage) DownloadFile(
threadIndex int, filePath string, chunk *Chunk,
) (err error) {
return storage.s3.DownloadFile(threadIndex, filePath, chunk)
}
func (storage *WasabiStorage) UploadFile(
threadIndex int, filePath string, content []byte,
) (err error) {
return storage.s3.UploadFile(threadIndex, filePath, content)
}
func (storage *WasabiStorage) IsCacheNeeded() bool {
return storage.s3.IsCacheNeeded()
}
func (storage *WasabiStorage) IsMoveFileImplemented() bool {
// This is implemented locally since S3 does a copy and delete
return true
}
func (storage *WasabiStorage) IsStrongConsistent() bool {
// Wasabi has it, S3 doesn't.
return true
}
func (storage *WasabiStorage) IsFastListing() bool {
return storage.s3.IsFastListing()
}
func (storage *WasabiStorage) EnableTestMode() {
}

View File

@@ -0,0 +1,450 @@
// Copyright (c) Acrosync LLC. All rights reserved.
// Free for personal use and commercial trial
// Commercial use requires per-user licenses available from https://duplicacy.com
//
//
// This storage backend is based on the work by Yuri Karamani from https://github.com/karamani/webdavclnt,
// released under the MIT license.
//
package duplicacy
import (
"bytes"
"encoding/xml"
"errors"
"fmt"
"io"
"io/ioutil"
"math/rand"
"net/http"
//"net/http/httputil"
"strconv"
"sync"
"time"
"strings"
)
type WebDAVStorage struct {
StorageBase
host string
port int
username string
password string
storageDir string
useHTTP bool
client *http.Client
threads int
directoryCache map[string]int // stores directories known to exist by this backend
directoryCacheLock sync.Mutex // lock for accessing directoryCache
}
var (
errWebDAVAuthorizationFailure = errors.New("Authentication failed")
errWebDAVMovedPermanently = errors.New("Moved permanently")
errWebDAVNotExist = errors.New("Path does not exist")
errWebDAVMaximumBackoff = errors.New("Maximum backoff reached")
errWebDAVMethodNotAllowed = errors.New("Method not allowed")
)
func CreateWebDAVStorage(host string, port int, username string, password string, storageDir string, useHTTP bool, threads int) (storage *WebDAVStorage, err error) {
if storageDir[len(storageDir)-1] != '/' {
storageDir += "/"
}
storage = &WebDAVStorage{
host: host,
port: port,
username: username,
password: password,
storageDir: "",
useHTTP: false,
client: http.DefaultClient,
threads: threads,
directoryCache: make(map[string]int),
}
// Make sure it doesn't follow redirect
storage.client.CheckRedirect = func(req *http.Request, via []*http.Request) error {
return http.ErrUseLastResponse
}
exist, isDir, _, err := storage.GetFileInfo(0, storageDir)
if err != nil {
return nil, err
}
if !exist {
return nil, fmt.Errorf("Storage path %s does not exist", storageDir)
}
if !isDir {
return nil, fmt.Errorf("Storage path %s is not a directory", storageDir)
}
storage.storageDir = storageDir
for _, dir := range []string{"snapshots", "chunks"} {
storage.CreateDirectory(0, dir)
}
storage.DerivedStorage = storage
storage.SetDefaultNestingLevels([]int{0}, 0)
return storage, nil
}
func (storage *WebDAVStorage) createConnectionString(uri string) string {
url := storage.host
if storage.useHTTP {
url = "http://" + url
} else {
url = "https://" + url
}
if storage.port > 0 {
url += fmt.Sprintf(":%d", storage.port)
}
return url + "/" + storage.storageDir + uri
}
func (storage *WebDAVStorage) retry(backoff int) int {
delay := rand.Intn(backoff*500) + backoff*500
time.Sleep(time.Duration(delay) * time.Millisecond)
backoff *= 2
return backoff
}
func (storage *WebDAVStorage) sendRequest(method string, uri string, depth int, data []byte) (io.ReadCloser, http.Header, error) {
backoff := 1
for i := 0; i < 8; i++ {
var dataReader io.Reader
headers := make(map[string]string)
if method == "PROPFIND" {
headers["Content-Type"] = "application/xml"
headers["Depth"] = fmt.Sprintf("%d", depth)
dataReader = bytes.NewReader(data)
} else if method == "PUT" {
headers["Content-Type"] = "application/octet-stream"
dataReader = CreateRateLimitedReader(data, storage.UploadRateLimit/storage.threads)
} else if method == "MOVE" {
headers["Destination"] = storage.createConnectionString(string(data))
headers["Content-Type"] = "application/octet-stream"
dataReader = bytes.NewReader([]byte(""))
} else {
headers["Content-Type"] = "application/octet-stream"
dataReader = bytes.NewReader(data)
}
request, err := http.NewRequest(method, storage.createConnectionString(uri), dataReader)
if err != nil {
return nil, nil, err
}
if len(storage.username) > 0 {
request.SetBasicAuth(storage.username, storage.password)
}
for key, value := range headers {
request.Header.Set(key, value)
}
//requestDump, err := httputil.DumpRequest(request, true)
//LOG_INFO("debug", "Request: %s", requestDump)
response, err := storage.client.Do(request)
if err != nil {
LOG_TRACE("WEBDAV_RETRY", "URL request '%s %s' returned an error (%v)", method, uri, err)
backoff = storage.retry(backoff)
continue
}
if response.StatusCode < 300 {
return response.Body, response.Header, nil
}
if response.StatusCode == 301 {
return nil, nil, errWebDAVMovedPermanently
}
response.Body.Close()
if response.StatusCode == 404 {
// Retry if it is UPLOAD, otherwise return immediately
if method != "PUT" {
return nil, nil, errWebDAVNotExist
}
} else if response.StatusCode == 405 {
return nil, nil, errWebDAVMethodNotAllowed
}
LOG_INFO("WEBDAV_RETRY", "URL request '%s %s' returned status code %d", method, uri, response.StatusCode)
backoff = storage.retry(backoff)
}
return nil, nil, errWebDAVMaximumBackoff
}
type WebDAVProperties map[string]string
type WebDAVPropValue struct {
XMLName xml.Name `xml:""`
Value string `xml:",innerxml"`
}
type WebDAVProp struct {
PropList []WebDAVPropValue `xml:",any"`
}
type WebDAVPropStat struct {
Prop *WebDAVProp `xml:"prop"`
}
type WebDAVResponse struct {
Href string `xml:"href"`
PropStat *WebDAVPropStat `xml:"propstat"`
}
type WebDAVMultiStatus struct {
Responses []WebDAVResponse `xml:"response"`
}
func (storage *WebDAVStorage) getProperties(uri string, depth int, properties ...string) (map[string]WebDAVProperties, error) {
propfind := "<prop>"
for _, p := range properties {
propfind += fmt.Sprintf("<%s/>", p)
}
propfind += "</prop>"
body := fmt.Sprintf(`<?xml version="1.0" encoding="utf-8" ?><propfind xmlns="DAV:">%s</propfind>`, propfind)
readCloser, _, err := storage.sendRequest("PROPFIND", uri, depth, []byte(body))
if err != nil {
return nil, err
}
defer readCloser.Close()
content, err := ioutil.ReadAll(readCloser)
if err != nil {
return nil, err
}
object := WebDAVMultiStatus{}
err = xml.Unmarshal(content, &object)
if err != nil {
return nil, err
}
if object.Responses == nil || len(object.Responses) == 0 {
return nil, errors.New("no WebDAV responses")
}
responses := make(map[string]WebDAVProperties)
for _, responseTag := range object.Responses {
if responseTag.PropStat == nil || responseTag.PropStat.Prop == nil || responseTag.PropStat.Prop.PropList == nil {
return nil, errors.New("no WebDAV properties")
}
properties := make(WebDAVProperties)
for _, prop := range responseTag.PropStat.Prop.PropList {
properties[prop.XMLName.Local] = prop.Value
}
responseKey := responseTag.Href
responses[responseKey] = properties
}
return responses, nil
}
// ListFiles return the list of files and subdirectories under 'dir'. A subdirectories returned must have a trailing '/', with
// a size of 0. If 'dir' is 'snapshots', only subdirectories will be returned. If 'dir' is 'snapshots/repository_id', then only
// files will be returned. If 'dir' is 'chunks', the implementation can return the list either recusively or non-recusively.
func (storage *WebDAVStorage) ListFiles(threadIndex int, dir string) (files []string, sizes []int64, err error) {
if dir[len(dir)-1] != '/' {
dir += "/"
}
properties, err := storage.getProperties(dir, 1, "getcontentlength", "resourcetype")
if err != nil {
return nil, nil, err
}
prefixLength := len(storage.storageDir) + len(dir) + 1
for file, m := range properties {
if len(file) <= prefixLength {
continue
}
isDir := false
size := 0
if resourceType, exist := m["resourcetype"]; exist && strings.Contains(resourceType, "collection") {
isDir = true
} else if length, exist := m["getcontentlength"]; exist {
if length == "" {
isDir = true
} else {
size, _ = strconv.Atoi(length)
}
} else {
continue
}
if !isDir {
if dir != "snapshots/" {
files = append(files, file[prefixLength:])
sizes = append(sizes, int64(size))
}
} else {
// This is a dir
file := file[prefixLength:]
if file[len(file)-1] != '/' {
file += "/"
}
files = append(files, file)
sizes = append(sizes, int64(0))
}
}
return files, sizes, nil
}
// GetFileInfo returns the information about the file or directory at 'filePath'.
func (storage *WebDAVStorage) GetFileInfo(threadIndex int, filePath string) (exist bool, isDir bool, size int64, err error) {
properties, err := storage.getProperties(filePath, 0, "getcontentlength", "resourcetype")
if err != nil {
if err == errWebDAVNotExist {
return false, false, 0, nil
}
if err == errWebDAVMovedPermanently {
// This must be a directory
return true, true, 0, nil
}
return false, false, 0, err
}
if m, exist := properties["/" + storage.storageDir + filePath]; !exist {
return false, false, 0, nil
} else if resourceType, exist := m["resourcetype"]; exist && strings.Contains(resourceType, "collection") {
return true, true, 0, nil
} else if length, exist := m["getcontentlength"]; exist && length != ""{
value, _ := strconv.Atoi(length)
return true, false, int64(value), nil
} else {
return true, true, 0, nil
}
}
// DeleteFile deletes the file or directory at 'filePath'.
func (storage *WebDAVStorage) DeleteFile(threadIndex int, filePath string) (err error) {
readCloser, _, err := storage.sendRequest("DELETE", filePath, 0, []byte(""))
if err != nil {
return err
}
readCloser.Close()
return nil
}
// MoveFile renames the file.
func (storage *WebDAVStorage) MoveFile(threadIndex int, from string, to string) (err error) {
readCloser, _, err := storage.sendRequest("MOVE", from, 0, []byte(to))
if err != nil {
return err
}
readCloser.Close()
return nil
}
// createParentDirectory creates the parent directory if it doesn't exist in the cache
func (storage *WebDAVStorage) createParentDirectory(threadIndex int, dir string) (err error) {
found := strings.LastIndex(dir, "/")
if found == -1 {
return nil
}
parent := dir[:found]
storage.directoryCacheLock.Lock()
_, exist := storage.directoryCache[parent]
storage.directoryCacheLock.Unlock()
if exist {
return nil
}
err = storage.CreateDirectory(threadIndex, parent)
if err == nil {
storage.directoryCacheLock.Lock()
storage.directoryCache[parent] = 1
storage.directoryCacheLock.Unlock()
}
return err
}
// CreateDirectory creates a new directory.
func (storage *WebDAVStorage) CreateDirectory(threadIndex int, dir string) (err error) {
for dir != "" && dir[len(dir)-1] == '/' {
dir = dir[:len(dir)-1]
}
if dir == "" {
return nil
}
// If there is an error in creating the parent directory, proceed anyway
storage.createParentDirectory(threadIndex, dir)
readCloser, _, err := storage.sendRequest("MKCOL", dir, 0, []byte(""))
if err != nil {
if err == errWebDAVMethodNotAllowed || err == errWebDAVMovedPermanently {
// We simply ignore these errors and assume that the directory already exists
return nil
}
return err
}
readCloser.Close()
return nil
}
// DownloadFile reads the file at 'filePath' into the chunk.
func (storage *WebDAVStorage) DownloadFile(threadIndex int, filePath string, chunk *Chunk) (err error) {
readCloser, _, err := storage.sendRequest("GET", filePath, 0, nil)
if err != nil {
return err
}
_, err = RateLimitedCopy(chunk, readCloser, storage.DownloadRateLimit/storage.threads)
return err
}
// UploadFile writes 'content' to the file at 'filePath'.
func (storage *WebDAVStorage) UploadFile(threadIndex int, filePath string, content []byte) (err error) {
// If there is an error in creating the parent directory, proceed anyway
storage.createParentDirectory(threadIndex, filePath)
readCloser, _, err := storage.sendRequest("PUT", filePath, 0, content)
if err != nil {
return err
}
readCloser.Close()
return nil
}
// If a local snapshot cache is needed for the storage to avoid downloading/uploading chunks too often when
// managing snapshots.
func (storage *WebDAVStorage) IsCacheNeeded() bool { return true }
// If the 'MoveFile' method is implemented.
func (storage *WebDAVStorage) IsMoveFileImplemented() bool { return true }
// If the storage can guarantee strong consistency.
func (storage *WebDAVStorage) IsStrongConsistent() bool { return false }
// If the storage supports fast listing of files names.
func (storage *WebDAVStorage) IsFastListing() bool { return false }
// Enable the test mode.
func (storage *WebDAVStorage) EnableTestMode() {}