rclone/cmd/bisync/queue.go

391 lines
11 KiB
Go
Raw Normal View History

package bisync
import (
"context"
"encoding/json"
"fmt"
"io"
"sort"
mutex "sync" // renamed as "sync" already in use
"time"
"github.com/rclone/rclone/cmd/bisync/bilib"
"github.com/rclone/rclone/fs"
bisync: Graceful Shutdown, --recover from interruptions without --resync - fixes #7470 Before this change, bisync had no mechanism to gracefully cancel a sync early and exit in a clean state. Additionally, there was no way to recover on the next run -- any interruption at all would cause bisync to require a --resync, which made bisync more difficult to use as a scheduled background process. This change introduces a "Graceful Shutdown" mode and --recover flag to robustly recover from even un-graceful shutdowns. If --recover is set, in the event of a sudden interruption or other un-graceful shutdown, bisync will attempt to automatically recover on the next run, instead of requiring --resync. Bisync is able to recover robustly by keeping one "backup" listing at all times, representing the state of both paths after the last known successful sync. Bisync can then compare the current state with this snapshot to determine which changes it needs to retry. Changes that were synced after this snapshot (during the run that was later interrupted) will appear to bisync as if they are "new or changed on both sides", but in most cases this is not a problem, as bisync will simply do its usual "equality check" and learn that no action needs to be taken on these files, since they are already identical on both sides. In the rare event that a file is synced successfully during a run that later aborts, and then that same file changes AGAIN before the next run, bisync will think it is a sync conflict, and handle it accordingly. (From bisync's perspective, the file has changed on both sides since the last trusted sync, and the files on either side are not currently identical.) Therefore, --recover carries with it a slightly increased chance of having conflicts -- though in practice this is pretty rare, as the conditions required to cause it are quite specific. This risk can be reduced by using bisync's "Graceful Shutdown" mode (triggered by sending SIGINT or Ctrl+C), when you have the choice, instead of forcing a sudden termination. --recover and --resilient are similar, but distinct -- the main difference is that --resilient is about _retrying_, while --recover is about _recovering_. Most users will probably want both. --resilient allows retrying when bisync has chosen to abort itself due to safety features such as failing --check-access or detecting a filter change. --resilient does not cover external interruptions such as a user shutting down their computer in the middle of a sync -- that is what --recover is for. "Graceful Shutdown" mode is activated by sending SIGINT or pressing Ctrl+C during a run. Once triggered, bisync will use best efforts to exit cleanly before the timer runs out. If bisync is in the middle of transferring files, it will attempt to cleanly empty its queue by finishing what it has started but not taking more. If it cannot do so within 30 seconds, it will cancel the in-progress transfers at that point and then give itself a maximum of 60 seconds to wrap up, save its state for next time, and exit. With the -vP flags you will see constant status updates and a final confirmation of whether or not the graceful shutdown was successful. At any point during the "Graceful Shutdown" sequence, a second SIGINT or Ctrl+C will trigger an immediate, un-graceful exit, which will leave things in a messier state. Usually a robust recovery will still be possible if using --recover mode, otherwise you will need to do a --resync. If you plan to use Graceful Shutdown mode, it is recommended to use --resilient and --recover, and it is important to NOT use --inplace, otherwise you risk leaving partially-written files on one side, which may be confused for real files on the next run. Note also that in the event of an abrupt interruption, a lock file will be left behind to block concurrent runs. You will need to delete it before you can proceed with the next run (or wait for it to expire on its own, if using --max-lock.)
2023-12-03 13:38:18 +08:00
"github.com/rclone/rclone/fs/accounting"
"github.com/rclone/rclone/fs/filter"
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
"github.com/rclone/rclone/fs/hash"
"github.com/rclone/rclone/fs/operations"
"github.com/rclone/rclone/fs/sync"
"github.com/rclone/rclone/lib/terminal"
)
// Results represents a pair of synced files, as reported by the LoggerFn
// Bisync uses this to determine what happened during the sync, and modify the listings accordingly
type Results struct {
Src string
Dst string
Name string
AltName string
Size int64
Modtime time.Time
Hash string
Flags string
Sigil operations.Sigil
Err error
Winner operations.Winner
IsWinner bool
IsSrc bool
IsDst bool
bisync: Graceful Shutdown, --recover from interruptions without --resync - fixes #7470 Before this change, bisync had no mechanism to gracefully cancel a sync early and exit in a clean state. Additionally, there was no way to recover on the next run -- any interruption at all would cause bisync to require a --resync, which made bisync more difficult to use as a scheduled background process. This change introduces a "Graceful Shutdown" mode and --recover flag to robustly recover from even un-graceful shutdowns. If --recover is set, in the event of a sudden interruption or other un-graceful shutdown, bisync will attempt to automatically recover on the next run, instead of requiring --resync. Bisync is able to recover robustly by keeping one "backup" listing at all times, representing the state of both paths after the last known successful sync. Bisync can then compare the current state with this snapshot to determine which changes it needs to retry. Changes that were synced after this snapshot (during the run that was later interrupted) will appear to bisync as if they are "new or changed on both sides", but in most cases this is not a problem, as bisync will simply do its usual "equality check" and learn that no action needs to be taken on these files, since they are already identical on both sides. In the rare event that a file is synced successfully during a run that later aborts, and then that same file changes AGAIN before the next run, bisync will think it is a sync conflict, and handle it accordingly. (From bisync's perspective, the file has changed on both sides since the last trusted sync, and the files on either side are not currently identical.) Therefore, --recover carries with it a slightly increased chance of having conflicts -- though in practice this is pretty rare, as the conditions required to cause it are quite specific. This risk can be reduced by using bisync's "Graceful Shutdown" mode (triggered by sending SIGINT or Ctrl+C), when you have the choice, instead of forcing a sudden termination. --recover and --resilient are similar, but distinct -- the main difference is that --resilient is about _retrying_, while --recover is about _recovering_. Most users will probably want both. --resilient allows retrying when bisync has chosen to abort itself due to safety features such as failing --check-access or detecting a filter change. --resilient does not cover external interruptions such as a user shutting down their computer in the middle of a sync -- that is what --recover is for. "Graceful Shutdown" mode is activated by sending SIGINT or pressing Ctrl+C during a run. Once triggered, bisync will use best efforts to exit cleanly before the timer runs out. If bisync is in the middle of transferring files, it will attempt to cleanly empty its queue by finishing what it has started but not taking more. If it cannot do so within 30 seconds, it will cancel the in-progress transfers at that point and then give itself a maximum of 60 seconds to wrap up, save its state for next time, and exit. With the -vP flags you will see constant status updates and a final confirmation of whether or not the graceful shutdown was successful. At any point during the "Graceful Shutdown" sequence, a second SIGINT or Ctrl+C will trigger an immediate, un-graceful exit, which will leave things in a messier state. Usually a robust recovery will still be possible if using --recover mode, otherwise you will need to do a --resync. If you plan to use Graceful Shutdown mode, it is recommended to use --resilient and --recover, and it is important to NOT use --inplace, otherwise you risk leaving partially-written files on one side, which may be confused for real files on the next run. Note also that in the event of an abrupt interruption, a lock file will be left behind to block concurrent runs. You will need to delete it before you can proceed with the next run (or wait for it to expire on its own, if using --max-lock.)
2023-12-03 13:38:18 +08:00
Origin string
}
// ResultsSlice is a slice of Results (obviously)
type ResultsSlice []Results
func (rs *ResultsSlice) has(name string) bool {
for _, r := range *rs {
if r.Name == name {
return true
}
}
return false
}
var (
logger = operations.NewLoggerOpt()
lock mutex.Mutex
once mutex.Once
ignoreListingChecksum bool
ignoreListingModtime bool
hashTypes map[string]hash.Type
queueCI *fs.ConfigInfo
)
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
// allows us to get the right hashtype during the LoggerFn without knowing whether it's Path1/Path2
func getHashType(fname string) hash.Type {
ht, ok := hashTypes[fname]
if ok {
return ht
}
return hash.None
}
// FsPathIfAny handles type assertions and returns a formatted bilib.FsPath if valid, otherwise ""
func FsPathIfAny(x fs.DirEntry) string {
obj, ok := x.(fs.Object)
if x != nil && ok {
return bilib.FsPath(obj.Fs())
}
return ""
}
func resultName(result Results, side, src, dst fs.DirEntry) string {
if side != nil {
return side.Remote()
} else if result.IsSrc && dst != nil {
return dst.Remote()
} else if src != nil {
return src.Remote()
}
return ""
}
// returns the opposite side's name, only if different
func altName(name string, src, dst fs.DirEntry) string {
if src != nil && dst != nil {
if src.Remote() != dst.Remote() {
switch name {
case src.Remote():
return dst.Remote()
case dst.Remote():
return src.Remote()
}
}
}
return ""
}
// WriteResults is Bisync's LoggerFn
func WriteResults(ctx context.Context, sigil operations.Sigil, src, dst fs.DirEntry, err error) {
lock.Lock()
defer lock.Unlock()
opt := operations.GetLoggerOpt(ctx)
result := Results{
bisync: Graceful Shutdown, --recover from interruptions without --resync - fixes #7470 Before this change, bisync had no mechanism to gracefully cancel a sync early and exit in a clean state. Additionally, there was no way to recover on the next run -- any interruption at all would cause bisync to require a --resync, which made bisync more difficult to use as a scheduled background process. This change introduces a "Graceful Shutdown" mode and --recover flag to robustly recover from even un-graceful shutdowns. If --recover is set, in the event of a sudden interruption or other un-graceful shutdown, bisync will attempt to automatically recover on the next run, instead of requiring --resync. Bisync is able to recover robustly by keeping one "backup" listing at all times, representing the state of both paths after the last known successful sync. Bisync can then compare the current state with this snapshot to determine which changes it needs to retry. Changes that were synced after this snapshot (during the run that was later interrupted) will appear to bisync as if they are "new or changed on both sides", but in most cases this is not a problem, as bisync will simply do its usual "equality check" and learn that no action needs to be taken on these files, since they are already identical on both sides. In the rare event that a file is synced successfully during a run that later aborts, and then that same file changes AGAIN before the next run, bisync will think it is a sync conflict, and handle it accordingly. (From bisync's perspective, the file has changed on both sides since the last trusted sync, and the files on either side are not currently identical.) Therefore, --recover carries with it a slightly increased chance of having conflicts -- though in practice this is pretty rare, as the conditions required to cause it are quite specific. This risk can be reduced by using bisync's "Graceful Shutdown" mode (triggered by sending SIGINT or Ctrl+C), when you have the choice, instead of forcing a sudden termination. --recover and --resilient are similar, but distinct -- the main difference is that --resilient is about _retrying_, while --recover is about _recovering_. Most users will probably want both. --resilient allows retrying when bisync has chosen to abort itself due to safety features such as failing --check-access or detecting a filter change. --resilient does not cover external interruptions such as a user shutting down their computer in the middle of a sync -- that is what --recover is for. "Graceful Shutdown" mode is activated by sending SIGINT or pressing Ctrl+C during a run. Once triggered, bisync will use best efforts to exit cleanly before the timer runs out. If bisync is in the middle of transferring files, it will attempt to cleanly empty its queue by finishing what it has started but not taking more. If it cannot do so within 30 seconds, it will cancel the in-progress transfers at that point and then give itself a maximum of 60 seconds to wrap up, save its state for next time, and exit. With the -vP flags you will see constant status updates and a final confirmation of whether or not the graceful shutdown was successful. At any point during the "Graceful Shutdown" sequence, a second SIGINT or Ctrl+C will trigger an immediate, un-graceful exit, which will leave things in a messier state. Usually a robust recovery will still be possible if using --recover mode, otherwise you will need to do a --resync. If you plan to use Graceful Shutdown mode, it is recommended to use --resilient and --recover, and it is important to NOT use --inplace, otherwise you risk leaving partially-written files on one side, which may be confused for real files on the next run. Note also that in the event of an abrupt interruption, a lock file will be left behind to block concurrent runs. You will need to delete it before you can proceed with the next run (or wait for it to expire on its own, if using --max-lock.)
2023-12-03 13:38:18 +08:00
Sigil: sigil,
Src: FsPathIfAny(src),
Dst: FsPathIfAny(dst),
Err: err,
Origin: "sync",
}
result.Winner = operations.WinningSide(ctx, sigil, src, dst, err)
fss := []fs.DirEntry{src, dst}
for i, side := range fss {
result.Name = resultName(result, side, src, dst)
result.AltName = altName(result.Name, src, dst)
result.IsSrc = i == 0
result.IsDst = i == 1
result.Flags = "-"
if side != nil {
result.Size = side.Size()
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
if !ignoreListingModtime {
result.Modtime = side.ModTime(ctx).In(TZ)
}
if !ignoreListingChecksum {
sideObj, ok := side.(fs.ObjectInfo)
if ok {
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
result.Hash, _ = sideObj.Hash(ctx, getHashType(sideObj.Fs().Name()))
result.Hash, _ = tryDownloadHash(ctx, sideObj, result.Hash)
}
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
}
}
result.IsWinner = result.Winner.Obj == side
// used during resync only
if err == fs.ErrorIsDir {
if src != nil {
result.Src = src.Remote()
result.Name = src.Remote()
} else {
result.Dst = dst.Remote()
result.Name = dst.Remote()
}
result.Flags = "d"
bisync: support files with unknown length, including Google Docs - fixes #5696 Before this change, bisync intentionally ignored Google Docs (albeit in a buggy way that caused problems during --resync.) After this change, Google Docs (including Google Sheets, Slides, etc.) are now supported in bisync, subject to the same options, defaults, and limitations as in `rclone sync`. When bisyncing drive with non-drive backends, the drive -> non-drive direction is controlled by `--drive-export-formats` (default `"docx,xlsx,pptx,svg"`) and the non-drive -> drive direction is controlled by `--drive-import-formats` (default none.) For example, with the default export/import formats, a Google Sheet on the drive side will be synced to an `.xlsx` file on the non-drive side. In the reverse direction, `.xlsx` files with filenames that match an existing Google Sheet will be synced to that Google Sheet, while `.xlsx` files that do NOT match an existing Google Sheet will be copied to drive as normal `.xlsx` files (without conversion to Sheets, although the Google Drive web browser UI may still give you the option to open it as one.) If `--drive-import-formats` is set (it's not, by default), then all of the specified formats will be converted to Google Docs, if there is no existing Google Doc with a matching name. Caution: such conversion can be quite lossy, and in most cases it's probably not what you want! To bisync Google Docs as URL shortcut links (in a manner similar to "Drive for Desktop"), use: `--drive-export-formats url` (or alternatives.) Note that these link files cannot be edited on the non-drive side -- you will get errors if you try to sync an edited link file back to drive. They CAN be deleted (it will result in deleting the corresponding Google Doc.) If you create a `.url` file on the non-drive side that does not match an existing Google Doc, bisyncing it will just result in copying the literal `.url` file over to drive (no Google Doc will be created.) So, as a general rule of thumb, think of them as read-only placeholders on the non-drive side, and make all your changes on the drive side. Likewise, even with other export-formats, it is best to only move/rename Google Docs on the drive side. This is because otherwise, bisync will interpret this as a file deleted and another created, and accordingly, it will delete the Google Doc and create a new file at the new path. (Whether or not that new file is a Google Doc depends on `--drive-import-formats`.) Lastly, take note that all Google Docs on the drive side have a size of `-1` and no checksum. Therefore, they cannot be reliably synced with the `--checksum` or `--size-only` flags. (To be exact: they will still get created/deleted, and bisync's delta engine will notice changes and queue them for syncing, but the underlying sync function will consider them identical and skip them.) To work around this, use the default (modtime and size) instead of `--checksum` or `--size-only`. To ignore Google Docs entirely, use `--drive-skip-gdocs`. Nearly all of the Google Docs logic is outsourced to the Drive backend, so future changes should also be supported by bisync.
2023-08-24 20:13:02 +08:00
result.Size = -1
}
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
prettyprint(result, "writing result", fs.LogLevelDebug)
if result.Size < 0 && result.Flags != "d" && ((queueCI.CheckSum && !downloadHash) || queueCI.SizeOnly) {
bisync: support files with unknown length, including Google Docs - fixes #5696 Before this change, bisync intentionally ignored Google Docs (albeit in a buggy way that caused problems during --resync.) After this change, Google Docs (including Google Sheets, Slides, etc.) are now supported in bisync, subject to the same options, defaults, and limitations as in `rclone sync`. When bisyncing drive with non-drive backends, the drive -> non-drive direction is controlled by `--drive-export-formats` (default `"docx,xlsx,pptx,svg"`) and the non-drive -> drive direction is controlled by `--drive-import-formats` (default none.) For example, with the default export/import formats, a Google Sheet on the drive side will be synced to an `.xlsx` file on the non-drive side. In the reverse direction, `.xlsx` files with filenames that match an existing Google Sheet will be synced to that Google Sheet, while `.xlsx` files that do NOT match an existing Google Sheet will be copied to drive as normal `.xlsx` files (without conversion to Sheets, although the Google Drive web browser UI may still give you the option to open it as one.) If `--drive-import-formats` is set (it's not, by default), then all of the specified formats will be converted to Google Docs, if there is no existing Google Doc with a matching name. Caution: such conversion can be quite lossy, and in most cases it's probably not what you want! To bisync Google Docs as URL shortcut links (in a manner similar to "Drive for Desktop"), use: `--drive-export-formats url` (or alternatives.) Note that these link files cannot be edited on the non-drive side -- you will get errors if you try to sync an edited link file back to drive. They CAN be deleted (it will result in deleting the corresponding Google Doc.) If you create a `.url` file on the non-drive side that does not match an existing Google Doc, bisyncing it will just result in copying the literal `.url` file over to drive (no Google Doc will be created.) So, as a general rule of thumb, think of them as read-only placeholders on the non-drive side, and make all your changes on the drive side. Likewise, even with other export-formats, it is best to only move/rename Google Docs on the drive side. This is because otherwise, bisync will interpret this as a file deleted and another created, and accordingly, it will delete the Google Doc and create a new file at the new path. (Whether or not that new file is a Google Doc depends on `--drive-import-formats`.) Lastly, take note that all Google Docs on the drive side have a size of `-1` and no checksum. Therefore, they cannot be reliably synced with the `--checksum` or `--size-only` flags. (To be exact: they will still get created/deleted, and bisync's delta engine will notice changes and queue them for syncing, but the underlying sync function will consider them identical and skip them.) To work around this, use the default (modtime and size) instead of `--checksum` or `--size-only`. To ignore Google Docs entirely, use `--drive-skip-gdocs`. Nearly all of the Google Docs logic is outsourced to the Drive backend, so future changes should also be supported by bisync.
2023-08-24 20:13:02 +08:00
once.Do(func() {
fs.Logf(result.Name, Color(terminal.YellowFg, "Files of unknown size (such as Google Docs) do not sync reliably with --checksum or --size-only. Consider using modtime instead (the default) or --drive-skip-gdocs"))
})
}
err := json.NewEncoder(opt.JSON).Encode(result)
if err != nil {
fs.Errorf(result, "Error encoding JSON: %v", err)
}
}
}
// ReadResults decodes the JSON data from WriteResults
func ReadResults(results io.Reader) []Results {
dec := json.NewDecoder(results)
var slice []Results
for {
var r Results
if err := dec.Decode(&r); err == io.EOF {
break
}
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
prettyprint(r, "result", fs.LogLevelDebug)
slice = append(slice, r)
}
return slice
}
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
// for setup code shared by both fastCopy and resyncDir
func (b *bisyncRun) preCopy(ctx context.Context) context.Context {
queueCI = fs.GetConfig(ctx)
ignoreListingChecksum = b.opt.IgnoreListingChecksum
ignoreListingModtime = !b.opt.Compare.Modtime
hashTypes = map[string]hash.Type{
b.fs1.Name(): b.opt.Compare.HashType1,
b.fs2.Name(): b.opt.Compare.HashType2,
}
logger.LoggerFn = WriteResults
overridingEqual := false
if (b.opt.Compare.Modtime && b.opt.Compare.Checksum) || b.opt.Compare.DownloadHash {
overridingEqual = true
fs.Debugf(nil, "overriding equal")
// otherwise impossible in Sync, so override Equal
ctx = b.EqualFn(ctx)
}
bisync: add --resync-mode for customizing --resync - fixes #5681 Before this change, the path1 version of a file always prevailed during --resync, and many users requested options to automatically select the winner based on characteristics such as newer, older, larger, and smaller. This change adds support for such options. Note that ideally this feature would have been implemented by allowing the existing `--resync` flag to optionally accept string values such as `--resync newer`. However, this would have been a breaking change, as the existing flag is a `bool` and it does not seem to be possible to have a `string` flag that accepts both `--resync newer` and `--resync` (with no argument.) (`NoOptDefVal` does not work for this, as it would force an `=` like `--resync=newer`.) So instead, the best compromise to avoid a breaking change was to add a new `--resync-mode CHOICE` flag that implies `--resync`, while maintaining the existing behavior of `--resync` (which implies `--resync-mode path1`. i.e. both flags are now valid, and either can be used without the other. --resync-mode CHOICE In the event that a file differs on both sides during a `--resync`, `--resync-mode` controls which version will overwrite the other. The supported options are similar to `--conflict-resolve`. For all of the following options, the version that is kept is referred to as the "winner", and the version that is overwritten (deleted) is referred to as the "loser". The options are named after the "winner": - `path1` - (the default) - the version from Path1 is unconditionally considered the winner (regardless of `modtime` and `size`, if any). This can be useful if one side is more trusted or up-to-date than the other, at the time of the `--resync`. - `path2` - same as `path1`, except the path2 version is considered the winner. - `newer` - the newer file (by `modtime`) is considered the winner, regardless of which side it came from. This may result in having a mix of some winners from Path1, and some winners from Path2. (The implementation is analagous to running `rclone copy --update` in both directions.) - `older` - same as `newer`, except the older file is considered the winner, and the newer file is considered the loser. - `larger` - the larger file (by `size`) is considered the winner (regardless of `modtime`, if any). This can be a useful option for remotes without `modtime` support, or with the kinds of files (such as logs) that tend to grow but not shrink, over time. - `smaller` - the smaller file (by `size`) is considered the winner (regardless of `modtime`, if any). For all of the above options, note the following: - If either of the underlying remotes lacks support for the chosen method, it will be ignored and will fall back to the default of `path1`. (For example, if `--resync-mode newer` is set, but one of the paths uses a remote that doesn't support `modtime`.) - If a winner can't be determined because the chosen method's attribute is missing or equal, it will be ignored, and bisync will instead try to determine whether the files differ by looking at the other `--compare` methods in effect. (For example, if `--resync-mode newer` is set, but the Path1 and Path2 modtimes are identical, bisync will compare the sizes.) If bisync concludes that they differ, preference is given to whichever is the "source" at that moment. (In practice, this gives a slight advantage to Path2, as the 2to1 copy comes before the 1to2 copy.) If the files _do not_ differ, nothing is copied (as both sides are already correct). - These options apply only to files that exist on both sides (with the same name and relative path). Files that exist *only* on one side and not the other are *always* copied to the other, during `--resync` (this is one of the main differences between resync and non-resync runs.). - `--conflict-resolve`, `--conflict-loser`, and `--conflict-suffix` do not apply during `--resync`, and unlike these flags, nothing is renamed during `--resync`. When a file differs on both sides during `--resync`, one version always overwrites the other (much like in `rclone copy`.) (Consider using `--backup-dir` to retain a backup of the losing version.) - Unlike for `--conflict-resolve`, `--resync-mode none` is not a valid option (or rather, it will be interpreted as "no resync", unless `--resync` has also been specified, in which case it will be ignored.) - Winners and losers are decided at the individual file-level only (there is not currently an option to pick an entire winning directory atomically, although the `path1` and `path2` options typically produce a similar result.) - To maintain backward-compatibility, the `--resync` flag implies `--resync-mode path1` unless a different `--resync-mode` is explicitly specified. Similarly, all `--resync-mode` options (except `none`) imply `--resync`, so it is not necessary to use both the `--resync` and `--resync-mode` flags simultaneously -- either one is sufficient without the other.
2023-12-23 03:09:35 +08:00
if b.opt.ResyncMode == PreferOlder || b.opt.ResyncMode == PreferLarger || b.opt.ResyncMode == PreferSmaller {
overridingEqual = true
fs.Debugf(nil, "overriding equal")
ctx = b.EqualFn(ctx)
}
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
ctxCopyLogger := operations.WithSyncLogger(ctx, logger)
if b.opt.Compare.Checksum && (b.opt.Compare.NoSlowHash || b.opt.Compare.SlowHashSyncOnly) && b.opt.Compare.SlowHashDetected {
// set here in case !b.opt.Compare.Modtime
queueCI = fs.GetConfig(ctxCopyLogger)
if b.opt.Compare.NoSlowHash {
queueCI.CheckSum = false
}
if b.opt.Compare.SlowHashSyncOnly && !overridingEqual {
queueCI.CheckSum = true
}
}
return ctxCopyLogger
}
func (b *bisyncRun) fastCopy(ctx context.Context, fsrc, fdst fs.Fs, files bilib.Names, queueName string) ([]Results, error) {
bisync: Graceful Shutdown, --recover from interruptions without --resync - fixes #7470 Before this change, bisync had no mechanism to gracefully cancel a sync early and exit in a clean state. Additionally, there was no way to recover on the next run -- any interruption at all would cause bisync to require a --resync, which made bisync more difficult to use as a scheduled background process. This change introduces a "Graceful Shutdown" mode and --recover flag to robustly recover from even un-graceful shutdowns. If --recover is set, in the event of a sudden interruption or other un-graceful shutdown, bisync will attempt to automatically recover on the next run, instead of requiring --resync. Bisync is able to recover robustly by keeping one "backup" listing at all times, representing the state of both paths after the last known successful sync. Bisync can then compare the current state with this snapshot to determine which changes it needs to retry. Changes that were synced after this snapshot (during the run that was later interrupted) will appear to bisync as if they are "new or changed on both sides", but in most cases this is not a problem, as bisync will simply do its usual "equality check" and learn that no action needs to be taken on these files, since they are already identical on both sides. In the rare event that a file is synced successfully during a run that later aborts, and then that same file changes AGAIN before the next run, bisync will think it is a sync conflict, and handle it accordingly. (From bisync's perspective, the file has changed on both sides since the last trusted sync, and the files on either side are not currently identical.) Therefore, --recover carries with it a slightly increased chance of having conflicts -- though in practice this is pretty rare, as the conditions required to cause it are quite specific. This risk can be reduced by using bisync's "Graceful Shutdown" mode (triggered by sending SIGINT or Ctrl+C), when you have the choice, instead of forcing a sudden termination. --recover and --resilient are similar, but distinct -- the main difference is that --resilient is about _retrying_, while --recover is about _recovering_. Most users will probably want both. --resilient allows retrying when bisync has chosen to abort itself due to safety features such as failing --check-access or detecting a filter change. --resilient does not cover external interruptions such as a user shutting down their computer in the middle of a sync -- that is what --recover is for. "Graceful Shutdown" mode is activated by sending SIGINT or pressing Ctrl+C during a run. Once triggered, bisync will use best efforts to exit cleanly before the timer runs out. If bisync is in the middle of transferring files, it will attempt to cleanly empty its queue by finishing what it has started but not taking more. If it cannot do so within 30 seconds, it will cancel the in-progress transfers at that point and then give itself a maximum of 60 seconds to wrap up, save its state for next time, and exit. With the -vP flags you will see constant status updates and a final confirmation of whether or not the graceful shutdown was successful. At any point during the "Graceful Shutdown" sequence, a second SIGINT or Ctrl+C will trigger an immediate, un-graceful exit, which will leave things in a messier state. Usually a robust recovery will still be possible if using --recover mode, otherwise you will need to do a --resync. If you plan to use Graceful Shutdown mode, it is recommended to use --resilient and --recover, and it is important to NOT use --inplace, otherwise you risk leaving partially-written files on one side, which may be confused for real files on the next run. Note also that in the event of an abrupt interruption, a lock file will be left behind to block concurrent runs. You will need to delete it before you can proceed with the next run (or wait for it to expire on its own, if using --max-lock.)
2023-12-03 13:38:18 +08:00
if b.InGracefulShutdown {
return nil, nil
}
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
ctx = b.preCopy(ctx)
if err := b.saveQueue(files, queueName); err != nil {
return nil, err
}
ctxCopy, filterCopy := filter.AddConfig(b.opt.setDryRun(ctx))
for _, file := range files.ToList() {
if err := filterCopy.AddFile(file); err != nil {
return nil, err
}
alias := b.aliases.Alias(file)
if alias != file {
if err := filterCopy.AddFile(alias); err != nil {
return nil, err
}
}
}
bisync: Graceful Shutdown, --recover from interruptions without --resync - fixes #7470 Before this change, bisync had no mechanism to gracefully cancel a sync early and exit in a clean state. Additionally, there was no way to recover on the next run -- any interruption at all would cause bisync to require a --resync, which made bisync more difficult to use as a scheduled background process. This change introduces a "Graceful Shutdown" mode and --recover flag to robustly recover from even un-graceful shutdowns. If --recover is set, in the event of a sudden interruption or other un-graceful shutdown, bisync will attempt to automatically recover on the next run, instead of requiring --resync. Bisync is able to recover robustly by keeping one "backup" listing at all times, representing the state of both paths after the last known successful sync. Bisync can then compare the current state with this snapshot to determine which changes it needs to retry. Changes that were synced after this snapshot (during the run that was later interrupted) will appear to bisync as if they are "new or changed on both sides", but in most cases this is not a problem, as bisync will simply do its usual "equality check" and learn that no action needs to be taken on these files, since they are already identical on both sides. In the rare event that a file is synced successfully during a run that later aborts, and then that same file changes AGAIN before the next run, bisync will think it is a sync conflict, and handle it accordingly. (From bisync's perspective, the file has changed on both sides since the last trusted sync, and the files on either side are not currently identical.) Therefore, --recover carries with it a slightly increased chance of having conflicts -- though in practice this is pretty rare, as the conditions required to cause it are quite specific. This risk can be reduced by using bisync's "Graceful Shutdown" mode (triggered by sending SIGINT or Ctrl+C), when you have the choice, instead of forcing a sudden termination. --recover and --resilient are similar, but distinct -- the main difference is that --resilient is about _retrying_, while --recover is about _recovering_. Most users will probably want both. --resilient allows retrying when bisync has chosen to abort itself due to safety features such as failing --check-access or detecting a filter change. --resilient does not cover external interruptions such as a user shutting down their computer in the middle of a sync -- that is what --recover is for. "Graceful Shutdown" mode is activated by sending SIGINT or pressing Ctrl+C during a run. Once triggered, bisync will use best efforts to exit cleanly before the timer runs out. If bisync is in the middle of transferring files, it will attempt to cleanly empty its queue by finishing what it has started but not taking more. If it cannot do so within 30 seconds, it will cancel the in-progress transfers at that point and then give itself a maximum of 60 seconds to wrap up, save its state for next time, and exit. With the -vP flags you will see constant status updates and a final confirmation of whether or not the graceful shutdown was successful. At any point during the "Graceful Shutdown" sequence, a second SIGINT or Ctrl+C will trigger an immediate, un-graceful exit, which will leave things in a messier state. Usually a robust recovery will still be possible if using --recover mode, otherwise you will need to do a --resync. If you plan to use Graceful Shutdown mode, it is recommended to use --resilient and --recover, and it is important to NOT use --inplace, otherwise you risk leaving partially-written files on one side, which may be confused for real files on the next run. Note also that in the event of an abrupt interruption, a lock file will be left behind to block concurrent runs. You will need to delete it before you can proceed with the next run (or wait for it to expire on its own, if using --max-lock.)
2023-12-03 13:38:18 +08:00
b.SyncCI = fs.GetConfig(ctxCopy) // allows us to request graceful shutdown
accounting.MaxCompletedTransfers = -1 // we need a complete list in the event of graceful shutdown
ctxCopy, b.CancelSync = context.WithCancel(ctxCopy)
b.testFn()
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
err := sync.Sync(ctxCopy, fdst, fsrc, b.opt.CreateEmptySrcDirs)
prettyprint(logger, "logger", fs.LogLevelDebug)
getResults := ReadResults(logger.JSON)
fs.Debugf(nil, "Got %v results for %v", len(getResults), queueName)
lineFormat := "%s %8d %s %s %s %q\n"
for _, result := range getResults {
fs.Debugf(nil, lineFormat, result.Flags, result.Size, result.Hash, "", result.Modtime, result.Name)
}
return getResults, err
}
func (b *bisyncRun) retryFastCopy(ctx context.Context, fsrc, fdst fs.Fs, files bilib.Names, queueName string, results []Results, err error) ([]Results, error) {
ci := fs.GetConfig(ctx)
if err != nil && b.opt.Resilient && !b.InGracefulShutdown && ci.Retries > 1 {
for tries := 1; tries <= ci.Retries; tries++ {
fs.Logf(queueName, Color(terminal.YellowFg, "Received error: %v - retrying as --resilient is set. Retry %d/%d"), err, tries, ci.Retries)
accounting.GlobalStats().ResetErrors()
if retryAfter := accounting.GlobalStats().RetryAfter(); !retryAfter.IsZero() {
d := time.Until(retryAfter)
if d > 0 {
fs.Logf(nil, "Received retry after error - sleeping until %s (%v)", retryAfter.Format(time.RFC3339Nano), d)
time.Sleep(d)
}
}
if ci.RetriesInterval > 0 {
naptime(ci.RetriesInterval)
}
results, err = b.fastCopy(ctx, fsrc, fdst, files, queueName)
if err == nil || b.InGracefulShutdown {
return results, err
}
}
}
return results, err
}
func (b *bisyncRun) resyncDir(ctx context.Context, fsrc, fdst fs.Fs) ([]Results, error) {
bisync: full support for comparing checksum, size, modtime - fixes #5679 fixes #5683 fixes #5684 fixes #5675 Before this change, bisync could only detect changes based on modtime, and would refuse to run if either path lacked modtime support. This made bisync unavailable for many of rclone's backends. Additionally, bisync did not account for the Fs's precision when comparing modtimes, meaning that they could only be reliably compared within the same side -- not against the opposite side. Size and checksum (even when available) were ignored completely for deltas. After this change, bisync now fully supports comparing based on any combination of size, modtime, and checksum, lifting the prior restriction on backends without modtime support. The comparison logic considers the backend's precision, hash types, and other features as appropriate. The comparison features optionally use a new --compare flag (which takes any combination of size,modtime,checksum) and even supports some combinations not otherwise supported in `sync` (like comparing all three at the same time.) By default (without the --compare flag), bisync inherits the same comparison options as `sync` (that is: size and modtime by default, unless modified with flags such as --checksum or --size-only.) If the --compare flag is set, it will override these defaults. If --compare includes checksum and both remotes support checksums but have no hash types in common with each other, checksums will be considered only for comparisons within the same side (to determine what has changed since the prior sync), but not for comparisons against the opposite side. If one side supports checksums and the other does not, checksums will only be considered on the side that supports them. When comparing with checksum and/or size without modtime, bisync cannot determine whether a file is newer or older -- only whether it is changed or unchanged. (If it is changed on both sides, bisync still does the standard equality-check to avoid declaring a sync conflict unless it absolutely has to.) Also included are some new flags to customize the checksum comparison behavior on backends where hashes are slow or unavailable. --no-slow-hash and --slow-hash-sync-only allow selectively ignoring checksums on backends such as local where they are slow. --download-hash allows computing them by downloading when (and only when) they're otherwise not available. Of course, this option probably won't be practical with large files, but may be a good option for syncing small-but-important files with maximum accuracy (for example, a source code repo on a crypt remote.) An additional advantage over methods like cryptcheck is that the original file is not required for comparison (for example, --download-hash can be used to bisync two different crypt remotes with different passwords.) Additionally, all of the above are now considered during the final --check-sync for much-improved accuracy (before this change, it only compared filenames!) Many other details are explained in the included docs.
2023-12-01 08:44:38 +08:00
ctx = b.preCopy(ctx)
err := sync.CopyDir(ctx, fdst, fsrc, b.opt.CreateEmptySrcDirs)
prettyprint(logger, "logger", fs.LogLevelDebug)
getResults := ReadResults(logger.JSON)
fs.Debugf(nil, "Got %v results for %v", len(getResults), "resync")
return getResults, err
}
// operation should be "make" or "remove"
func (b *bisyncRun) syncEmptyDirs(ctx context.Context, dst fs.Fs, candidates bilib.Names, dirsList *fileList, results *[]Results, operation string) {
bisync: Graceful Shutdown, --recover from interruptions without --resync - fixes #7470 Before this change, bisync had no mechanism to gracefully cancel a sync early and exit in a clean state. Additionally, there was no way to recover on the next run -- any interruption at all would cause bisync to require a --resync, which made bisync more difficult to use as a scheduled background process. This change introduces a "Graceful Shutdown" mode and --recover flag to robustly recover from even un-graceful shutdowns. If --recover is set, in the event of a sudden interruption or other un-graceful shutdown, bisync will attempt to automatically recover on the next run, instead of requiring --resync. Bisync is able to recover robustly by keeping one "backup" listing at all times, representing the state of both paths after the last known successful sync. Bisync can then compare the current state with this snapshot to determine which changes it needs to retry. Changes that were synced after this snapshot (during the run that was later interrupted) will appear to bisync as if they are "new or changed on both sides", but in most cases this is not a problem, as bisync will simply do its usual "equality check" and learn that no action needs to be taken on these files, since they are already identical on both sides. In the rare event that a file is synced successfully during a run that later aborts, and then that same file changes AGAIN before the next run, bisync will think it is a sync conflict, and handle it accordingly. (From bisync's perspective, the file has changed on both sides since the last trusted sync, and the files on either side are not currently identical.) Therefore, --recover carries with it a slightly increased chance of having conflicts -- though in practice this is pretty rare, as the conditions required to cause it are quite specific. This risk can be reduced by using bisync's "Graceful Shutdown" mode (triggered by sending SIGINT or Ctrl+C), when you have the choice, instead of forcing a sudden termination. --recover and --resilient are similar, but distinct -- the main difference is that --resilient is about _retrying_, while --recover is about _recovering_. Most users will probably want both. --resilient allows retrying when bisync has chosen to abort itself due to safety features such as failing --check-access or detecting a filter change. --resilient does not cover external interruptions such as a user shutting down their computer in the middle of a sync -- that is what --recover is for. "Graceful Shutdown" mode is activated by sending SIGINT or pressing Ctrl+C during a run. Once triggered, bisync will use best efforts to exit cleanly before the timer runs out. If bisync is in the middle of transferring files, it will attempt to cleanly empty its queue by finishing what it has started but not taking more. If it cannot do so within 30 seconds, it will cancel the in-progress transfers at that point and then give itself a maximum of 60 seconds to wrap up, save its state for next time, and exit. With the -vP flags you will see constant status updates and a final confirmation of whether or not the graceful shutdown was successful. At any point during the "Graceful Shutdown" sequence, a second SIGINT or Ctrl+C will trigger an immediate, un-graceful exit, which will leave things in a messier state. Usually a robust recovery will still be possible if using --recover mode, otherwise you will need to do a --resync. If you plan to use Graceful Shutdown mode, it is recommended to use --resilient and --recover, and it is important to NOT use --inplace, otherwise you risk leaving partially-written files on one side, which may be confused for real files on the next run. Note also that in the event of an abrupt interruption, a lock file will be left behind to block concurrent runs. You will need to delete it before you can proceed with the next run (or wait for it to expire on its own, if using --max-lock.)
2023-12-03 13:38:18 +08:00
if b.InGracefulShutdown {
return
}
fs.Debugf(nil, "syncing empty dirs")
if b.opt.CreateEmptySrcDirs && (!b.opt.Resync || operation == "make") {
candidatesList := candidates.ToList()
if operation == "remove" {
// reverse the sort order to ensure we remove subdirs before parent dirs
sort.Sort(sort.Reverse(sort.StringSlice(candidatesList)))
}
for _, s := range candidatesList {
var direrr error
if dirsList.has(s) { // make sure it's a dir, not a file
r := Results{}
r.Name = s
bisync: Graceful Shutdown, --recover from interruptions without --resync - fixes #7470 Before this change, bisync had no mechanism to gracefully cancel a sync early and exit in a clean state. Additionally, there was no way to recover on the next run -- any interruption at all would cause bisync to require a --resync, which made bisync more difficult to use as a scheduled background process. This change introduces a "Graceful Shutdown" mode and --recover flag to robustly recover from even un-graceful shutdowns. If --recover is set, in the event of a sudden interruption or other un-graceful shutdown, bisync will attempt to automatically recover on the next run, instead of requiring --resync. Bisync is able to recover robustly by keeping one "backup" listing at all times, representing the state of both paths after the last known successful sync. Bisync can then compare the current state with this snapshot to determine which changes it needs to retry. Changes that were synced after this snapshot (during the run that was later interrupted) will appear to bisync as if they are "new or changed on both sides", but in most cases this is not a problem, as bisync will simply do its usual "equality check" and learn that no action needs to be taken on these files, since they are already identical on both sides. In the rare event that a file is synced successfully during a run that later aborts, and then that same file changes AGAIN before the next run, bisync will think it is a sync conflict, and handle it accordingly. (From bisync's perspective, the file has changed on both sides since the last trusted sync, and the files on either side are not currently identical.) Therefore, --recover carries with it a slightly increased chance of having conflicts -- though in practice this is pretty rare, as the conditions required to cause it are quite specific. This risk can be reduced by using bisync's "Graceful Shutdown" mode (triggered by sending SIGINT or Ctrl+C), when you have the choice, instead of forcing a sudden termination. --recover and --resilient are similar, but distinct -- the main difference is that --resilient is about _retrying_, while --recover is about _recovering_. Most users will probably want both. --resilient allows retrying when bisync has chosen to abort itself due to safety features such as failing --check-access or detecting a filter change. --resilient does not cover external interruptions such as a user shutting down their computer in the middle of a sync -- that is what --recover is for. "Graceful Shutdown" mode is activated by sending SIGINT or pressing Ctrl+C during a run. Once triggered, bisync will use best efforts to exit cleanly before the timer runs out. If bisync is in the middle of transferring files, it will attempt to cleanly empty its queue by finishing what it has started but not taking more. If it cannot do so within 30 seconds, it will cancel the in-progress transfers at that point and then give itself a maximum of 60 seconds to wrap up, save its state for next time, and exit. With the -vP flags you will see constant status updates and a final confirmation of whether or not the graceful shutdown was successful. At any point during the "Graceful Shutdown" sequence, a second SIGINT or Ctrl+C will trigger an immediate, un-graceful exit, which will leave things in a messier state. Usually a robust recovery will still be possible if using --recover mode, otherwise you will need to do a --resync. If you plan to use Graceful Shutdown mode, it is recommended to use --resilient and --recover, and it is important to NOT use --inplace, otherwise you risk leaving partially-written files on one side, which may be confused for real files on the next run. Note also that in the event of an abrupt interruption, a lock file will be left behind to block concurrent runs. You will need to delete it before you can proceed with the next run (or wait for it to expire on its own, if using --max-lock.)
2023-12-03 13:38:18 +08:00
r.Size = -1
r.Modtime = dirsList.getTime(s).In(time.UTC)
r.Flags = "d"
r.Err = nil
bisync: Graceful Shutdown, --recover from interruptions without --resync - fixes #7470 Before this change, bisync had no mechanism to gracefully cancel a sync early and exit in a clean state. Additionally, there was no way to recover on the next run -- any interruption at all would cause bisync to require a --resync, which made bisync more difficult to use as a scheduled background process. This change introduces a "Graceful Shutdown" mode and --recover flag to robustly recover from even un-graceful shutdowns. If --recover is set, in the event of a sudden interruption or other un-graceful shutdown, bisync will attempt to automatically recover on the next run, instead of requiring --resync. Bisync is able to recover robustly by keeping one "backup" listing at all times, representing the state of both paths after the last known successful sync. Bisync can then compare the current state with this snapshot to determine which changes it needs to retry. Changes that were synced after this snapshot (during the run that was later interrupted) will appear to bisync as if they are "new or changed on both sides", but in most cases this is not a problem, as bisync will simply do its usual "equality check" and learn that no action needs to be taken on these files, since they are already identical on both sides. In the rare event that a file is synced successfully during a run that later aborts, and then that same file changes AGAIN before the next run, bisync will think it is a sync conflict, and handle it accordingly. (From bisync's perspective, the file has changed on both sides since the last trusted sync, and the files on either side are not currently identical.) Therefore, --recover carries with it a slightly increased chance of having conflicts -- though in practice this is pretty rare, as the conditions required to cause it are quite specific. This risk can be reduced by using bisync's "Graceful Shutdown" mode (triggered by sending SIGINT or Ctrl+C), when you have the choice, instead of forcing a sudden termination. --recover and --resilient are similar, but distinct -- the main difference is that --resilient is about _retrying_, while --recover is about _recovering_. Most users will probably want both. --resilient allows retrying when bisync has chosen to abort itself due to safety features such as failing --check-access or detecting a filter change. --resilient does not cover external interruptions such as a user shutting down their computer in the middle of a sync -- that is what --recover is for. "Graceful Shutdown" mode is activated by sending SIGINT or pressing Ctrl+C during a run. Once triggered, bisync will use best efforts to exit cleanly before the timer runs out. If bisync is in the middle of transferring files, it will attempt to cleanly empty its queue by finishing what it has started but not taking more. If it cannot do so within 30 seconds, it will cancel the in-progress transfers at that point and then give itself a maximum of 60 seconds to wrap up, save its state for next time, and exit. With the -vP flags you will see constant status updates and a final confirmation of whether or not the graceful shutdown was successful. At any point during the "Graceful Shutdown" sequence, a second SIGINT or Ctrl+C will trigger an immediate, un-graceful exit, which will leave things in a messier state. Usually a robust recovery will still be possible if using --recover mode, otherwise you will need to do a --resync. If you plan to use Graceful Shutdown mode, it is recommended to use --resilient and --recover, and it is important to NOT use --inplace, otherwise you risk leaving partially-written files on one side, which may be confused for real files on the next run. Note also that in the event of an abrupt interruption, a lock file will be left behind to block concurrent runs. You will need to delete it before you can proceed with the next run (or wait for it to expire on its own, if using --max-lock.)
2023-12-03 13:38:18 +08:00
r.Origin = "syncEmptyDirs"
r.Winner = operations.Winner{ // note: Obj not set
Side: "src",
Err: nil,
}
rSrc := r
rDst := r
rSrc.IsSrc = true
rSrc.IsDst = false
rDst.IsSrc = false
rDst.IsDst = true
rSrc.IsWinner = true
rDst.IsWinner = false
if operation == "remove" {
// directories made empty by the sync will have already been deleted during the sync
// this just catches the already-empty ones (excluded from sync by --files-from filter)
direrr = operations.TryRmdir(ctx, dst, s)
rSrc.Sigil = operations.MissingOnSrc
rDst.Sigil = operations.MissingOnSrc
rSrc.Dst = s
rDst.Dst = s
rSrc.Winner.Side = "none"
rDst.Winner.Side = "none"
} else if operation == "make" {
direrr = operations.Mkdir(ctx, dst, s)
rSrc.Sigil = operations.MissingOnDst
rDst.Sigil = operations.MissingOnDst
rSrc.Src = s
rDst.Src = s
} else {
direrr = fmt.Errorf("invalid operation. Expected 'make' or 'remove', received '%q'", operation)
}
if direrr != nil {
fs.Debugf(nil, "Error syncing directory: %v", direrr)
} else {
*results = append(*results, rSrc, rDst)
}
}
}
}
}
func (b *bisyncRun) saveQueue(files bilib.Names, jobName string) error {
if !b.opt.SaveQueues {
return nil
}
queueFile := fmt.Sprintf("%s.%s.que", b.basePath, jobName)
return files.Save(queueFile)
}
func naptime(totalWait time.Duration) {
expireTime := time.Now().Add(totalWait)
fs.Logf(nil, "will retry in %v at %v", totalWait, expireTime.Format("2006-01-02 15:04:05 MST"))
for i := 0; time.Until(expireTime) > 0; i++ {
if i > 0 && i%10 == 0 {
fs.Infof(nil, Color(terminal.Dim, "retrying in %v..."), time.Until(expireTime).Round(1*time.Second))
} else {
fs.Debugf(nil, Color(terminal.Dim, "retrying in %v..."), time.Until(expireTime).Round(1*time.Second))
}
time.Sleep(1 * time.Second)
}
}