The bottom line is delete markers are a nuisance,
most applications are not version aware and this
has simply complicated the version management.
AWS S3 gave an unnecessary complication overhead
for customers, they need to now manage these
markers by applying ILM settings and clean
them up on a regular basis.
To make matters worse all these delete markers
get replicated as well in a replicated setup,
requiring two ILM settings on each site.
This PR is an attempt to address this inferior
implementation by deviating MinIO towards an
idempotent delete marker implementation i.e
MinIO will never create any more than single
consecutive delete markers.
This significantly reduces operational overhead
by making versioning more useful for real data.
This is an S3 spec deviation for pragmatic reasons.
The path is marked dirty automatically when healObject() is called, which is
wrong. HealObject() is called during self-healing and this will lead to
an increase in the false positive result of the bloom filter.
Also move NSUpdated() from renameData() and call it directly in
CompleteMultipart and PutObject, this is not a functional change but
it will make it less prone to errors in the future.
Add up to 256 bytes of padding for compressed+encrypted files.
This will obscure the obvious cases of extremely compressible content
and leave a similar output size for a very wide variety of inputs.
This does *not* mean the compression ratio doesn't leak information
about the content, but the outcome space is much smaller,
so often *less* information is leaked.
We need to make sure if we cannot read bucket metadata
for some reason, and bucket metadata is not missing and
returning corrupted information we should panic such
handlers to disallow I/O to protect the overall state
on the system.
In-case of such corruption we have a mechanism now
to force recreate the metadata on the bucket, using
`x-minio-force-create` header with `PUT /bucket` API
call.
Additionally fix the versioning config updated state
to be set properly for the site replication healing
to trigger correctly.
readAllXL would return inlined data for outdated disks
causing "read" to return incorrect content to the client,
this PR fixes this behavior by making sure we skip such
outdated disks appropriately based on the latest ModTime
on the disk.
Main motivation is move towards a common backend format
for all different types of modes in MinIO, allowing for
a simpler code and predictable behavior across all features.
This PR also brings features such as versioning, replication,
transitioning to single drive setups.
updating metadata with CopyObject on a versioned bucket
causes the latest version to be not readable, this PR fixes
this properly by handling the inline data bug fix introduced
in PR #14780.
This bug affects only inlined data.
- do not need to restrict prefix exclusions that do not
have `/` as suffix, relax this requirement as spark may
have staging folders with other autogenerated characters
, so we are better off doing full prefix March and skip.
- multiple delete objects was incorrectly creating a
null delete marker on a versioned bucket instead of
creating a proper versioned delete marker.
- do not suspend paths on the excluded prefixes during
delete operations to avoid creating `null` delete markers,
honor suspension of versioning only at bucket level for
delete markers.
Spark/Hadoop workloads which use Hadoop MR
Committer v1/v2 algorithm upload objects to a
temporary prefix in a bucket. These objects are
'renamed' to a different prefix on Job commit.
Object storage admins are forced to configure
separate ILM policies to expire these objects
and their versions to reclaim space.
Our solution:
This can be avoided by simply marking objects
under these prefixes to be excluded from versioning,
as shown below. Consequently, these objects are
excluded from replication, and don't require ILM
policies to prune unnecessary versions.
- MinIO Extension to Bucket Version Configuration
```xml
<VersioningConfiguration xmlns="http://s3.amazonaws.com/doc/2006-03-01/">
<Status>Enabled</Status>
<ExcludeFolders>true</ExcludeFolders>
<ExcludedPrefixes>
<Prefix>app1-jobs/*/_temporary/</Prefix>
</ExcludedPrefixes>
<ExcludedPrefixes>
<Prefix>app2-jobs/*/__magic/</Prefix>
</ExcludedPrefixes>
<!-- .. up to 10 prefixes in all -->
</VersioningConfiguration>
```
Note: `ExcludeFolders` excludes all folders in a bucket
from versioning. This is required to prevent the parent
folders from accumulating delete markers, especially
those which are shared across spark workloads
spanning projects/teams.
- To enable version exclusion on a list of prefixes
```
mc version enable --excluded-prefixes "app1-jobs/*/_temporary/,app2-jobs/*/_magic," --exclude-prefix-marker myminio/test
```
do not modify opts.UserDefined after object-handler
has set all the necessary values, any mutation needed
should be done on a copy of this value not directly.
As there are other pieces of code that access opts.UserDefined
concurrently this becomes challenging.
fixes#14856
This PR fixes two issues
- The first fix is a regression from #14555, the fix itself in #14555
is correct but the interpretation of that information by the
object layer code for "replication" was not correct. This PR
tries to fix this situation by making sure the "Delete" replication
works as expected when "VersionPurgeStatus" is already set.
Without this fix, there is a DELETE marker created incorrectly on
the source where the "DELETE" was triggered.
- The second fix is perhaps an older problem started since we inlined-data
on the disk for small objects, CopyObject() incorrectly inline's
a non-inlined data. This is due to the fact that we have code where
we read the `part.1` under certain conditions where the size of the
`part.1` is less than the specific "threshold".
This eventually causes problems when we are "deleting" the data that
is only inlined, which means dataDir is ignored leaving such
dataDir on the disk, that looks like an inconsistent content on
the namespace.
fixes#14767
- GetObject() with vid should return 405
- GetObject() without vid should return 404
- ListObjects() should ignore this object if this is the "latest" version of the object
- ListObjectVersions() should list this object as "DELETE marker"
- Remove data parts before sync'ing the version pending purge
- speedtest logs calls that were canceled
spuriously, in situations where it should
be ignored.
- all errors of interest are always sent back
to the client there is no need to log them
on the server console.
- PUT failures should negate the increments
such that GET is not attempted on unsuccessful
calls.
- do not attempt MRF on speedtest objects.
Deleting bulk objects had an issue since the relevant versionID
is not passed through the layers to ensure that the dangling
object purge actually works cleanly.
This is a continuation of quorum related error returned by
multi-object delete API from #14248
This PR ensures that we pass down correct information as
well as extend the scope of dangling object detection.
some upgraded objects might not get listed due
to different quorum ratios across objects.
make sure to list all objects that satisfy the
maximum possible quorum.
When reading input for PutObject or PutObjectPart add a readahead buffer for big inputs.
This will make network reads+hashing separate run async with erasure coding and writes. This will reduce overall latency in distributed setups where the input is from upstream and writes go to other servers.
We will read at 2 buffers ahead, meaning one will always be ready/waiting and one is currently being read from.
This improves PutObject and PutObjectParts for these cases.
This PR simplifies few things
- Multipart parts are renamed, upon failure are unrenamed() keep this
multipart specific behavior it is needed and works fine.
- AbortMultipart should blindly delete once lock is acquired instead
of re-reading metadata and calculating quorum, abort is a delete()
operation and client has no business looking for errors on this.
- Skip Access() calls to folders that are operating on
`.minio.sys/multipart` folder as well.
Large clusters with multiple sets, or multi-pool setups at times might
fail and report unexpected "file not found" errors. This can become
a problem during startup sequence when some files need to be created
at multiple locations.
- This PR ensures that we nil the erasure writers such that they
are skipped in RenameData() call.
- RenameData() doesn't need to "Access()" calls for `.minio.sys`
folders they always exist.
- Make sure PutObject() never returns ObjectNotFound{} for any
errors, make sure it always returns "WriteQuorum" when renameData()
fails with ObjectNotFound{}. Return appropriate errors for all
other cases.
Currently tag removal leaves replication state as `PENDING`
because the `HEAD` api returns just a tag count but not the
actual tags, and this is treated as a no-op
```
λ mc admin decommission start alias/ http://minio{1...2}/data{1...4}
```
```
λ mc admin decommission status alias/
┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────┐
│ ID │ Pools │ Capacity │ Status │
│ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Active │
│ 2nd │ http://minio{3...4}/data{1...4} │ 329 GiB (used) / 421 GiB (total) │ Active │
└─────┴─────────────────────────────────┴──────────────────────────────────┴────────┘
```
```
λ mc admin decommission status alias/ http://minio{1...2}/data{1...4}
Progress: ===================> [1GiB/sec] [15%] [4TiB/50TiB]
Time Remaining: 4 hours (started 3 hours ago)
```
```
λ mc admin decommission status alias/ http://minio{1...2}/data{1...4}
ERROR: This pool is not scheduled for decommissioning currently.
```
```
λ mc admin decommission cancel alias/
┌─────┬─────────────────────────────────┬──────────────────────────────────┬──────────┐
│ ID │ Pools │ Capacity │ Status │
│ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining │
└─────┴─────────────────────────────────┴──────────────────────────────────┴──────────┘
```
> NOTE: Canceled decommission will not make the pool active again, since we might have
> Potentially partial duplicate content on the other pools, to avoid this scenario be
> very sure to start decommissioning as a planned activity.
```
λ mc admin decommission cancel alias/ http://minio{1...2}/data{1...4}
┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────────────────┐
│ ID │ Pools │ Capacity │ Status │
│ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining(Canceled) │
└─────┴─────────────────────────────────┴──────────────────────────────────┴────────────────────┘
```
This PR is an attempt to make this configurable
as not all situations have same level of tolerable
delta, i.e disks are replaced days apart or even
hours.
There is also a possibility that nodes have drifted
in time, when NTP is not configured on the system.
data shards were wrong due to a healing bug
reported in #13803 mainly with unaligned object
sizes.
This PR is an attempt to automatically avoid
these shards, with available information about
the `xl.meta` and actually disk mtime.
single object delete was not working properly
on a bucket when versioning was suspended,
current version 'null' object was never removed.
added unit tests to cover the behavior
fixes#13783
dataDir loosely based on maxima is incorrect and does not
work in all situations such as disks in the following order
- xl.json migration to xl.meta there may be partial xl.json's
leftover if some disks are not yet connected when the disk
is yet to come up, since xl.json mtime and xl.meta is
same the dataDir maxima doesn't work properly leading to
quorum issues.
- its also possible that XLV1 might be true among the disks
available, make sure to keep FileInfo based on common quorum
and skip unexpected disks with the older data format.
Also, this PR tests upgrade from older to a newer release if the
data is readable and matches the checksum.
NOTE: this is just initial work we can build on top of this to do further tests.
- remove some duplicated code
- reported a bug, separately fixed in #13664
- using strings.ReplaceAll() when needed
- using filepath.ToSlash() use when needed
- remove all non-Go style comments from the codebase
Co-authored-by: Aditya Manthramurthy <donatello@users.noreply.github.com>
deleting collection of versions belonging
to same object, we can avoid re-reading
the xl.meta from the disk instead purge
all the requested versions in-memory,
the tradeoff is to allocate a map to de-dup
the versions, allow disks to be read only
once per object.
additionally reduce the data transfer between
nodes by shortening msgp data values.
Removes RLock/RUnlock for updating metadata,
since we already take a write lock to update
metadata, this change removes reading of xl.meta
as well as an additional lock, the performance gain
should increase 3x theoretically for
- PutObjectRetention
- PutObjectLegalHold
This optimization is mainly for Veeam like
workloads that require a certain level of iops
from these API calls, we were losing iops.
offset+length should match the Size() of the individual parts
return 'errFileCorrupt' otherwise, to trigger healing of the individual
parts do not error out prematurely when healing such bitrot's upon
successful parts being written to the client.
another issue this PR fixes is to not return and error to
the client if we have just triggered a heal on a specific
part of the object, instead continue to read all the content
and let the heal happen asynchronously later.
This was a regression introduced in '14bb969782'
this has the potential to cause corruption when
there are concurrent overwrites attempting to update
the content on the namespace.
This PR adds a situation where PutObject(), CopyObject()
compete properly for the same locks with NewMultipartUpload()
however it ends up turning off competing locks for the actual
object with GetObject() and DeleteObject() - since they do not
compete due to concurrent I/O on a versioned bucket it can lead
to loss of versions.
This PR fixes this bug with multi-pool setup with replication
that causes corruption of inlined data due to lack of competing
locks in a multi-pool setup.
Instead CompleteMultipartUpload holds the necessary
locks when finishing the transaction, knowing the exact
location of an object to schedule the multipart upload
doesn't need to compete in this manner, a pool id location
for existing object.
* reduce extra getObjectInfo() calls during ILM transition
This PR also changes expiration logic to be non-blocking,
scanner is now free from additional costs incurred due
to slower object layer calls and hitting the drives.
* move verifying expiration inside locks
Use `readMetadata` when reading version
information without data requested.
Reduces IO on inlined data.
Bonus: Inline compressed data as well when
compression is enabled.
- avoid extra lookup for 'xl.meta' since we are
definitely sure that it doesn't exist.
- use this in newMultipartUpload() as well
- also additionally do not write with O_DSYNC
to avoid loading the drives, instead create
'xl.meta' for listing operations without
O_DSYNC since these are ephemeral objects.
- do the same with newMultipartUpload() since
it gets synced when the PutObjectPart() is
attempted, we do not need to tax newMultipartUpload()
instead.
removes unexpected features from regular putObject() such as
- increasing parity when disks are down, avoids
a lot of DiskInfo() calls.
- triggering MRF for metacache objects
if disks are offline
- avoiding renames from temporary location
to actual namespace, not needed since
metacache files are unique.
we will allow situations such as
```
a/b/1.txt
a/b
```
and
```
a/b
a/b/1.txt
```
we are going to document that this usecase is
not supported and we will never support it, if
any application does this users have to delete
the top level parent to make sure namespace is
accessible at lower level.
rest of the situations where the prefixes get
created across sets are supported as is.
- delete-markers are incorrectly reported
as corrupt with wrong data sent to client
'mc admin heal -r' on objects with delete
marker will report as 'grey' incorrectly.
- do not heal delete-markers during HeadObject()
this can lead to inconsistent order of heals
on the object, although this is not an issue
in terms of order of versions it is rather
simpler to keep the same order on all drives.
- defaultHealResult() should handle 'err == nil'
case such that valid cases should be handled
as 'drive' status OK.
This allows remote bucket admin to identify the origin of transitioned
objects by simply inspecting the object prefixes.
e.g let's take a remote tier TIER-1 pointing to a remote bucket (prefix)
testbucket/testprefix-1. The remote bucket admin can list all transitioned objects
from a MinIO deployment identified by '2e78e906-1c5d-4f94-8689-9df44cafde39' and
source bucket 'mybucket' like so,
```
$ ./mc ls -r minio-tier-target/testbucket/testprefix-1/2e78e906-1c5d-4f94-8689-9df44cafde39/mybucket/
[2021-07-12 17:15:50 PDT] 160B 48/fb/48fbc0e6-3a73-458b-9337-8e722c619ca4
[2021-07-12 16:58:46 PDT] 160B 7d/1c/7d1c96bd-031a-48d4-99ea-b1304e870830
```
This commit gathers MRF metrics from
all nodes in a cluster and return it to the caller. This will show information about the
number of objects in the MRF queues
waiting to be healed.
DiskInfo() calls can stagger and wait if run
serially timing out 10secs per drive, to avoid
this lets check DiskInfo in parallel to avoid
delays when nodes get disconnected.
- Adds versioning support for S3 based remote tiers that have versioning
enabled. This ensures that when reading or deleting we specify the specific
version ID of the object. In case of deletion, this is important to ensure that
the object version is actually deleted instead of simply being marked for
deletion.
- Stores the remote object's version id in the tier-journal. Tier-journal file
version is not bumped up as serializing the new struct version is
compatible with old journals without the remote object version id.
- `storageRESTVersion` is bumped up as FileInfo struct now includes a
`TransitionRemoteVersionID` member.
- Azure and GCS support for this feature will be added subsequently.
Co-authored-by: Krishnan Parthasarathi <krisis@users.noreply.github.com>
This is to ensure that there are no projects
that try to import `minio/minio/pkg` into
their own repo. Any such common packages should
go to `https://github.com/minio/pkg`
In cases where a cluster is degraded, we do not uphold our consistency
guarantee and we will write fewer erasure codes and rely on healing
to recreate the missing shards.
In some cases replacing known bad disks in practice take days.
We want to change the behavior of a known degraded system to keep
the erasure code promise of the storage class for each object.
This will create the objects with the same confidence as a fully
functional cluster. The tradeoff will be that objects created
during a partial outage will take up slightly more space.
This means that when the storage class is EC:4, there should
always be written 4 parity shards, even if some disks are unavailable.
When an object is created on a set, the disks are immediately
checked. If any disks are unavailable additional parity shards
will be made for each offline disk, up to 50% of the number of disks.
We add an internal metadata field with the actual and intended
erasure code level, this can optionally be picked up later by
the scanner if we decide that data like this should be re-sharded.
This PR fixes two bugs
- Remove fi.Data upon overwrite of objects from inlined-data to non-inlined-data
- Workaround for an existing bug on disk with latest releases to ignore fi.Data
and instead read from the disk for non-inlined-data
- Addtionally add a reserved metadata header to indicate data is inlined for
a given version.
However, this slice is also used for closing the writers, so close is never called on these.
Furthermore when an error is returned from a write it is now reported to the reader.
bonus: remove unused heal param from `newBitrotWriter`.
* Remove copy, now that we don't mutate.
At some places bloom filter tracker was getting
updated for `.minio.sys/tmp` bucket, there is no
reason to update bloom filters for those.
And add a missing bloom filter update for MakeBucket()
Bonus: purge unused function deleteEmptyDir()
- GetObject() should always use a common dataDir to
read from when it starts reading, this allows the
code in erasure decoding to have sane expectations.
- Healing should always heal on the common dataDir, this
allows the code in dangling object detection to purge
dangling content.
These both situations can happen under certain types of
retries during PUT when server is restarting etc, some
namespace entries might be left over.
wait groups are necessary with io.Pipes() to avoid
races when a blocking function may not be expected
and a Write() -> Close() before Read() races on each
other. We should avoid such situations..
Co-authored-by: Klaus Post <klauspost@gmail.com>
cleanup functions should never be cleaned before the reader is
instantiated, this type of design leads to situations where order
of lockers and places for them to use becomes confusing.
Allow WithCleanupFuncs() if the caller wishes to add cleanupFns
to be run upon close() or an error during initialization of the
reader.
Also make sure streams are closed before we unlock the resources,
this allows for ordered cleanup of resources.
upon errors to acquire lock context would still leak,
since the cancel would never be called. since the lock
is never acquired - proactively clear it before returning.
* lock: Always cancel the returned Get(R)Lock context
There is a leak with cancel created inside the locking mechanism. The
cancel purpose was to cancel operations such erasure get/put that are
holding non-refreshable locks.
This PR will ensure the created context.Cancel is passed to the unlock
API so it will cleanup and avoid leaks.
* locks: Avoid returning nil cancel in local lockers
Since there is no Refresh mechanism in the local locking mechanism, we
do not generate a new context or cancel. Currently, a nil cancel
function is returned but this can cause a crash. Return a dummy function
instead.
Part ETags are not available after multipart finalizes, removing this
check as not useful.
Signed-off-by: Poorna Krishnamoorthy <poorna@minio.io>
Co-authored-by: Harshavardhana <harsha@minio.io>
avoid re-read of xl.meta instead just use
the success criteria from PutObjectPart()
and check the ETag matches per Part, if
they match then the parts have been
successfully restored as is.
Signed-off-by: Harshavardhana <harsha@minio.io>
With this change, MinIO's ILM supports transitioning objects to a remote tier.
This change includes support for Azure Blob Storage, AWS S3 compatible object
storage incl. MinIO and Google Cloud Storage as remote tier storage backends.
Some new additions include:
- Admin APIs remote tier configuration management
- Simple journal to track remote objects to be 'collected'
This is used by object API handlers which 'mutate' object versions by
overwriting/replacing content (Put/CopyObject) or removing the version
itself (e.g DeleteObjectVersion).
- Rework of previous ILM transition to fit the new model
In the new model, a storage class (a.k.a remote tier) is defined by the
'remote' object storage type (one of s3, azure, GCS), bucket name and a
prefix.
* Fixed bugs, review comments, and more unit-tests
- Leverage inline small object feature
- Migrate legacy objects to the latest object format before transitioning
- Fix restore to particular version if specified
- Extend SharedDataDirCount to handle transitioned and restored objects
- Restore-object should accept version-id for version-suspended bucket (#12091)
- Check if remote tier creds have sufficient permissions
- Bonus minor fixes to existing error messages
Co-authored-by: Poorna Krishnamoorthy <poorna@minio.io>
Co-authored-by: Krishna Srinivas <krishna@minio.io>
Signed-off-by: Harshavardhana <harsha@minio.io>
* fix: pick valid FileInfo additionally based on dataDir
historically we have always relied on modTime
to be consistent and same, we can now add additional
reference to look for the same dataDir value.
A dataDir is the same for an object at a given point in
time for a given version, let's say a `null` version
is overwritten in quorum we do not by mistake pick
up the fileInfo's incorrectly.
* make sure to not preserve fi.Data
Signed-off-by: Harshavardhana <harsha@minio.io>
This is an optimization by reducing one extra system call,
and many network operations. This reduction should increase
the performance for small file workloads.
Current implementation heavily relies on readAllFileInfo
but with the advent of xl.meta inlined with data, we cannot
easily avoid reading data when we are only interested is
updating metadata, this leads to invariably write
amplification during metadata updates, repeatedly reading
data when we are only interested in updating metadata.
This PR ensures that we implement a metadata only update
API at storage layer, that handles updates to metadata alone
for any given version - given the version is valid and
present.
This helps reduce the chattiness for following calls..
- PutObjectTags
- DeleteObjectTags
- PutObjectLegalHold
- PutObjectRetention
- ReplicateObject (updates metadata on replication status)
- collect real time replication metrics for prometheus.
- add pending_count, failed_count metric for total pending/failed replication operations.
- add API to get replication metrics
- add MRF worker to handle spill-over replication operations
- multiple issues found with replication
- fixes an issue when client sends a bucket
name with `/` at the end from SetRemoteTarget
API call make sure to trim the bucket name to
avoid any extra `/`.
- hold write locks in GetObjectNInfo during replication
to ensure that object version stack is not overwritten
while reading the content.
- add additional protection during WriteMetadata() to
ensure that we always write a valid FileInfo{} and avoid
ever writing empty FileInfo{} to the lowest layers.
Co-authored-by: Poorna Krishnamoorthy <poorna@minio.io>
Co-authored-by: Harshavardhana <harsha@minio.io>
current master breaks this important requirement
we need to preserve legacyXLv1 format, this is simply
ignored and overwritten causing a myriad of issues
by leaving stale files on the namespace etc.
for now lets still use the two-phase approach of
writing to `tmp` and then renaming the content to
the actual namespace.
Poorna
Harshavardhana
Anis Elleuch
Klaus Post
Praveen raj Mani
Minio Trusted
Krishnan Parthasarathi
Aditya Manthramurthy