only newly replaced drives get the new `format.json`,
this avoids disks reloading their in-memory reference
format, ensures that drives are online without
reloading the in-memory reference format.
keeping reference format in-tact means UUIDs
never change once they are formatted.
lockers currently might leave stale lockers,
in unknown ways waiting for downed lockers.
locker check interval is high enough to safely
cleanup stale locks.
reference format should be source of truth
for inconsistent drives which reconnect,
add them back to their original position
remove automatic fix for existing offline
disk uuids
Bonus fixes
- logging improvements to ensure that we don't use
`go logger.LogIf` to avoid runtime.Caller missing
the function name. log where necessary.
- remove unused code at erasure sets
Test TestDialContextWithDNSCacheRand was failing sometimes because it depends
on a random selection of addresses when testing random DNS resolution from cache.
Lower addr selection exception to 10%
Allow requests to come in for users as soon as object
layer and config are initialized, this allows users
to be authenticated sooner and would succeed automatically
on servers which are yet to fully initialize.
Go stdlib resolver doesn't support caching DNS
resolutions, since we compile with CGO disabled
we are more probe to DNS flooding for all network
calls to resolve for DNS from the DNS server.
Under various containerized environments such as
VMWare this becomes a problem because there are
no DNS caches available and we may end up overloading
the kube-dns resolver under concurrent I/O.
To circumvent this issue implement a DNSCache resolver
which resolves DNS and caches them for around 10secs
with every 3sec invalidation attempted.
connect disks pre-emptively upon startup, to ensure we have
enough disks are connected at startup rather than wait
for them.
we need to do this to avoid long wait times for server to
be online when we have servers come up in rolling upgrade
fashion
Only use dynamic delays for the crawler. Even though the max wait was 1 second the number
of waits could severely impact crawler speed.
Instead of relying on a global metric, we use the stateless local delays to keep the crawler
running at a speed more adjusted to current conditions.
The only case we keep it is before bitrot checks when enabled.
This PR fixes a hang which occurs quite commonly at higher concurrency
by allowing following changes
- allowing lower connections in time_wait allows faster socket open's
- lower idle connection timeout to ensure that we let kernel
reclaim the time_wait connections quickly
- increase somaxconn to 4096 instead of 2048 to allow larger tcp
syn backlogs.
fixes#10413
This change tracks bandwidth for a bucket and object
- [x] Add Admin API
- [x] Add Peer API
- [x] Add BW throttling
- [x] Admin APIs to set replication limit
- [x] Admin APIs for fetch bandwidth
In almost all scenarios MinIO now is
mostly ready for all sub-systems
independently, safe-mode is not useful
anymore and do not serve its original
intended purpose.
allow server to be fully functional
even with config partially configured,
this is to cater for availability of actual
I/O v/s manually fixing the server.
In k8s like environments it will never make
sense to take pod into safe-mode state,
because there is no real access to perform
any remote operation on them.
- select lockers which are non-local and online to have
affinity towards remote servers for lock contention
- optimize lock retry interval to avoid sending too many
messages during lock contention, reduces average CPU
usage as well
- if bucket is not set, when deleteObject fails make sure
setPutObjHeaders() honors lifecycle only if bucket name
is set.
- fix top locks to list out always the oldest lockers always,
avoid getting bogged down into map's unordered nature.
This is to allow remote targets to be generalized
for replication/ILM transition
Also adding a field in BucketTarget to identify
a remote target with a label.
This commit fixes a misuse of the `http.ResponseWriter.WriteHeader`.
A caller should **either** call `WriteHeader` exactly once **or**
write to the response writer and causing an implicit 200 OK.
Writing the response headers more than once causes a `http: superfluous
response.WriteHeader call` log message. This commit fixes this
by preventing a 2nd `WriteHeader` call being forwarded to the underlying
`ResponseWriter`.
Updates #10587
* add NVMe drive info [model num, serial num, drive temp. etc.]
* Ignore fuse partitions
* Add the nvme logic only for linux
* Move smart/nvme structs to a separate file
Co-authored-by: wlan0 <sidharthamn@gmail.com>
throw proper error when port is not accessible
for the regular user, this is possibly a regression.
```
ERROR Unable to start the server: Insufficient permissions to use specified port
> Please ensure MinIO binary has 'cap_net_bind_service=+ep' permissions
HINT:
Use 'sudo setcap cap_net_bind_service=+ep /path/to/minio' to provide sufficient permissions
```
After #10594 let's invalidate the bloom filters to force the next cycles to go through all data.
There is a small chance that the linked PR could have caused missing bloom filter data.
This will invalidate the current bloom filters and make the crawler go through everything.
Routing using on source IP if found. This should distribute
the listing load for V1 and versioning on multiple nodes
evenly between different clients.
If source IP is not found from the http request header, then falls back
to bucket name instead.
Disallow versioning suspension on a bucket with
pre-existing replication configuration
If versioning is suspended on the target,replication
should fail.
`mc admin info` on busy setups will not move HDD
heads unnecessarily for repeated calls, provides
a better responsiveness for the call overall.
Bonus change allow listTolerancePerSet be N-1
for good entries, to avoid skipping entries
for some reason one of the disk went offline.
add a hint on the disk to allow for tracking fresh disk
being healed, to allow for restartable heals, and also
use this as a way to track and remove disks.
There are more pending changes where we should move
all the disk formatting logic to backend drives, this
PR doesn't deal with this refactor instead makes it
easier to track healing in the future.
- Add owner information for expiry, locking, unlocking a resource
- TopLocks returns now locks in quorum by default, provides
a way to capture stale locks as well with `?stale=true`
- Simplify the quorum handling for locks to avoid from storage
class, because there were challenges to make it consistent
across all situations.
- And other tiny simplifications to reset locks.
context canceled errors bubbling up from the network
layer has the potential to be misconstrued as network
errors, taking prematurely a server offline and triggering
a health check routine avoid this potential occurrence.
isEnded() was incorrectly calculating if the current healing sequence is
ended or not. h.currentStatus.Items could be empty if healing is very
slow and mc admin heal consumed all items.
As the bulk/recursive delete will require multiple connections to open at an instance,
The default open connections limit will be reached which results in the following error
```FATAL: sorry, too many clients already```
By setting the open connections to a reasonable value - `2`, We ensure that the max open connections
will not be exhausted and lie under bounds.
The queries are simple inserts/updates/deletes which is operational and sufficient with the
the maximum open connection limit is 2.
Fixes#10553
Allow user configuration for MaxOpenConnections
It is possible the heal drives are not reported from
the maintenance check because the background heal
state simply relied on the `format.json` for capturing
unformatted drives. It is possible that drives might
be still healing - make sure that applications which
rely on cluster health check respond back this detail.
Also, revamp the way ListBuckets work make few portions
of the healing logic parallel
- walk objects for healing disks in parallel
- collect the list of buckets in parallel across drives
- provide consistent view for listBuckets()
Healing was not working correctly in the distributed mode because
errFileVersionNotFound was not properly converted in storage rest
client.
Besides, fixing the healing delete marker is not working as expected.
performance improves by around 100x or more
```
go test -v -run NONE -bench BenchmarkGetPartFile
goos: linux
goarch: amd64
pkg: github.com/minio/minio/cmd
BenchmarkGetPartFileWithTrie
BenchmarkGetPartFileWithTrie-4 1000000000 0.140 ns/op 0 B/op 0 allocs/op
PASS
ok github.com/minio/minio/cmd 1.737s
```
fixes#10520
* Fix cases where minimum timeout > default timeout.
* Add defensive code for too small/negative timeouts.
* Never set timeout below the maximum value of a request.
* Protect against (unlikely) int64 wraps.
* Decrease timeout slower.
* Don't re-lock before copying.
This bug was introduced in 14f0047295
almost 3yrs ago, as a side affect of removing stale `fs.json`
but we in-fact end up removing existing good `fs.json` for an
existing object, leading to some form of a data loss.
fixes#10496
from 20s for 10000 parts to less than 1sec
Without the patch
```
~ time aws --endpoint-url=http://localhost:9000 --profile minio s3api \
list-parts --bucket testbucket --key test \
--upload-id c1cd1f50-ea9a-4824-881c-63b5de95315a
real 0m20.394s
user 0m0.589s
sys 0m0.174s
```
With the patch
```
~ time aws --endpoint-url=http://localhost:9000 --profile minio s3api \
list-parts --bucket testbucket --key test \
--upload-id c1cd1f50-ea9a-4824-881c-63b5de95315a
real 0m0.891s
user 0m0.624s
sys 0m0.182s
```
fixes#10503
It was observed in VMware vsphere environment during a
pod replacement, `mc admin info` might report incorrect
offline nodes for the replaced drive. This issue eventually
goes away but requires quite a lot of time for all servers
to be in sync.
This PR fixes this behavior properly.
If the ILM document requires removing noncurrent versions, the
the server should be able to remove 'null' versions as well.
'null' versions are created when versioning is not enabled
or suspended.
The entire encryption layer is dependent on the fact that
KMS should be configured for S3 encryption to work properly
and we only support passing the headers as is to the backend
for encryption only if KMS is configured.
Make sure that this predictability is maintained, currently
the code was allowing encryption to go through and fail
at later to indicate that KMS was not configured. We should
simply reply "NotImplemented" if KMS is not configured, this
allows clients to simply proceed with their tests.
This is to ensure that Go contexts work properly, after some
interesting experiments I found that Go net/http doesn't
cancel the context when Body is non-zero and hasn't been
read till EOF.
The following gist explains this, this can lead to pile up
of go-routines on the server which will never be canceled
and will die at a really later point in time, which can
simply overwhelm the server.
https://gist.github.com/harshavardhana/c51dcfd055780eaeb71db54f9c589150
To avoid this refactor the locking such that we take locks after we
have started reading from the body and only take locks when needed.
Also, remove contextReader as it's not useful, doesn't work as expected
context is not canceled until the body reaches EOF so there is no point
in wrapping it with context and putting a `select {` on it which
can unnecessarily increase the CPU overhead.
We will still use the context to cancel the lockers etc.
Additional simplification in the locker code to avoid timers
as re-using them is a complicated ordeal avoid them in
the hot path, since locking is very common this may avoid
lots of allocations.
configurable remote transport timeouts for some special cases
where this value needs to be bumped to a higher value when
transferring large data between federated instances.
In `(*cacheObjects).GetObjectNInfo` copy the metadata before spawning a goroutine.
Clean up a few map[string]string copies as well, reducing allocs and simplifying the code.
Fixes#10426
From https://docs.aws.amazon.com/AmazonS3/latest/dev/intro-lifecycle-rules.html#intro-lifecycle-rules-actions
```
When specifying the number of days in the NoncurrentVersionTransition
and NoncurrentVersionExpiration actions in a Lifecycle configuration,
note the following:
It is the number of days from when the version of the object becomes
noncurrent (that is, when the object is overwritten or deleted), that
Amazon S3 will perform the action on the specified object or objects.
Amazon S3 calculates the time by adding the number of days specified in
the rule to the time when the new successor version of the object is
created and rounding the resulting time to the next day midnight UTC.
For example, in your bucket, suppose that you have a current version of
an object that was created at 1/1/2014 10:30 AM UTC. If the new version
of the object that replaces the current version is created at 1/15/2014
10:30 AM UTC, and you specify 3 days in a transition rule, the
transition date of the object is calculated as 1/19/2014 00:00 UTC.
```
This PR adds a DNS target that ensures to update an entry
into Kubernetes operator when a bucket is created or deleted.
See minio/operator#264 for details.
Co-authored-by: Harshavardhana <harsha@minio.io>
MaxConnsPerHost can potentially hang a call without any
way to timeout, we do not need this setting for our proxy
and gateway implementations instead IdleConn settings are
good enough.
Also ensure to use NewRequestWithContext and make sure to
take the disks offline only for network errors.
Fixes#10304
inconsistent drive healing when one of the drive is offline
while a new drive was replaced, this change is to ensure
that we can add the offline drive back into the mix by
healing it again.
Add context to all (non-trivial) calls to the storage layer.
Contexts are propagated through the REST client.
- `context.TODO()` is left in place for the places where it needs to be added to the caller.
- `endWalkCh` could probably be removed from the walkers, but no changes so far.
The "dangerous" part is that now a caller disconnecting *will* propagate down, so a
"delete" operation will now be interrupted. In some cases we might want to disconnect
this functionality so the operation completes if it has started, leaving the system in a cleaner state.
This commit refactors the certificate management implementation
in the `certs` package such that multiple certificates can be
specified at the same time. Therefore, the following layout of
the `certs/` directory is expected:
```
certs/
│
├─ public.crt
├─ private.key
├─ CAs/ // CAs directory is ignored
│ │
│ ...
│
├─ example.com/
│ │
│ ├─ public.crt
│ └─ private.key
└─ foobar.org/
│
├─ public.crt
└─ private.key
...
```
However, directory names like `example.com` are just for human
readability/organization and don't have any meaning w.r.t whether
a particular certificate is served or not. This decision is made based
on the SNI sent by the client and the SAN of the certificate.
***
The `Manager` will pick a certificate based on the client trying
to establish a TLS connection. In particular, it looks at the client
hello (i.e. SNI) to determine which host the client tries to access.
If the manager can find a certificate that matches the SNI it
returns this certificate to the client.
However, the client may choose to not send an SNI or tries to access
a server directly via IP (`https://<ip>:<port>`). In this case, we
cannot use the SNI to determine which certificate to serve. However,
we also should not pick "the first" certificate that would be accepted
by the client (based on crypto. parameters - like a signature algorithm)
because it may be an internal certificate that contains internal hostnames.
We would disclose internal infrastructure details doing so.
Therefore, the `Manager` returns the "default" certificate when the
client does not specify an SNI. The default certificate the top-level
`public.crt` - i.e. `certs/public.crt`.
This approach has some consequences:
- It's the operator's responsibility to ensure that the top-level
`public.crt` does not disclose any information (i.e. hostnames)
that are not publicly visible. However, this was the case in the
past already.
- Any other `public.crt` - except for the top-level one - must not
contain any IP SAN. The reason for this restriction is that the
Manager cannot match a SNI to an IP b/c the SNI is the server host
name. The entire purpose of SNI is to indicate which host the client
tries to connect to when multiple hosts run on the same IP. So, a
client will not set the SNI to an IP.
If we would allow IP SANs in a lower-level `public.crt` a user would
expect that it is possible to connect to MinIO directly via IP address
and that the MinIO server would pick "the right" certificate. However,
the MinIO server cannot determine which certificate to serve, and
therefore always picks the "default" one. This may lead to all sorts
of confusing errors like:
"It works if I use `https:instance.minio.local` but not when I use
`https://10.0.2.1`.
These consequences/limitations should be pointed out / explained in our
docs in an appropriate way. However, the support for multiple
certificates should not have any impact on how deployment with a single
certificate function today.
Co-authored-by: Harshavardhana <harsha@minio.io>
- do not fail the healthcheck if heal status
was not obtained from one of the nodes,
if many nodes fail then report this as a
catastrophic error.
- add "x-minio-write-quorum" value to match
the write tolerance supported by server.
- admin info now states if a drive is healing
where madmin.Disk.Healing is set to true
and madmin.Disk.State is "ok"
Currently, cache purges are triggered as soon as the low watermark is exceeded.
To reduce IO this should only be done when reaching the high watermark.
This simplifies checks and reduces all calls for a GC to go through
`dcache.diskSpaceAvailable(size)`. While a comment claims that
`dcache.triggerGC <- struct{}{}` was non-blocking I don't see how
that was possible. Instead, we add a 1 size to the queue channel
and use channel semantics to avoid blocking when a GC has
already been requested.
`bytesToClear` now takes the high watermark into account to it will
not request any bytes to be cleared until that is reached.
This commit reduces the retry delay when retrying a request
to a KES server by:
- reducing the max. jitter delay from 3s to 1.5s
- skipping the random delay when there are more KES endpoints
available.
If there are more KES endpoints we can directly retry to the request
by sending it to the next endpoint - as pointed out by @krishnasrinivas
- delete-marker should be created on a suspended bucket as `null`
- delete-marker should delete any pre-existing `null` versioned
object and create an entry `null`
When checking parts we already do a stat for each part.
Since we have the on disk size check if it is at least what we expect.
When checking metadata check if metadata is 0 bytes.
The `getNonLoopBackIP` may grab an IP from an interface that
doesn't allow binding (on Windows), so this test consistently fails.
We exclude that specific error.
* readDirN: Check if file is directory
`syscall.FindNextFile` crashes if the handle is a file.
`errFileNotFound` matches 'unix' functionality: d19b434ffc/cmd/os-readdir_unix.go (L106)Fixes#10384
This commit addresses a maintenance / automation problem when MinIO-KES
is deployed on bare-metal. In orchestrated env. the orchestrator (K8S)
will make sure that `n` KES servers (IPs) are available via the same DNS
name. There it is sufficient to provide just one endpoint.
ListObjectsV1 requests are actually redirected to a specific node,
depending on the bucket name. The purpose of this behavior was
to optimize listing.
However, the current code sends a Bad Gateway error if the
target node is offline, which is a bad behavior because it means
that the list request will fail, although this is unnecessary since
we can still use the current node to list as well (the default behavior
without using proxying optimization)
Currently, you can see mint fails when there is one offline node, after
this PR, mint will always succeed.
We can reduce this further in the future, but this is a good
value to keep around. With the advent of continuous healing,
we can be assured that namespace will eventually be
consistent so we are okay to avoid the necessity to
a list across all drives on all sets.
Bonus Pop()'s in parallel seem to have the potential to
wait too on large drive setups and cause more slowness
instead of gaining any performance remove it for now.
Also, implement load balanced reply for local disks,
ensuring that local disks have an affinity for
- cleanupStaleMultipartUploads()
If DiskInfo calls failed the information returned was used anyway
resulting in no endpoint being set.
This would make the drive be attributed to the local system since
`disk.Endpoint == disk.DrivePath` in that case.
Instead, if the call fails record the endpoint and the error only.
bonus make sure to ignore objectNotFound, and versionNotFound
errors properly at all layers, since HealObjects() returns
objectNotFound error if the bucket or prefix is empty.
When crawling never use a disk we know is healing.
Most of the change involves keeping track of the original endpoint on xlStorage
and this also fixes DiskInfo.Endpoint never being populated.
Heal master will print `data-crawl: Disk "http://localhost:9001/data/mindev/data2/xl1" is
Healing, skipping` once on a cycle (no more often than every 5m).
We should only enforce quotas if no error has been returned.
firstErr is safe to access since all goroutines have exited at this point.
If `firstErr` hasn't been set by something else return the context error if cancelled.
Keep dataUpdateTracker while goroutine is starting.
This will ensure the object is updated one `start` returns
Tested with
```
λ go test -cpu=1,2,4,8 -test.run TestDataUpdateTracker -count=1000
PASS
ok github.com/minio/minio/cmd 8.913s
```
Fixes#10295
fresh drive setups when one of the drive is
a root drive, we should ignore such a root
drive and not proceed to format.
This PR handles this properly by marking
the disks which are root disk and they are
taken offline.
newDynamicTimeout should be allocated once, in-case
of temporary locks in config and IAM we should
have allocated timeout once before the `for loop`
This PR doesn't fix any issue as such, but provides
enough dynamism for the timeout as per expectation.
Based on our previous conversations I assume we should send the version
id when healing an object.
Maybe we should even list object versions and heal all?
In a non recursive mode, issuing a list request where prefix
is an existing object with a slash and delimiter is a slash will
return entries in the object directory (data dir IDs)
```
$ aws s3api --profile minioadmin --endpoint-url http://localhost:9000 \
list-objects-v2 --bucket testbucket --prefix code_of_conduct.md/ --delimiter '/'
{
"CommonPrefixes": [
{
"Prefix":
"code_of_conduct.md/ec750fe0-ea7e-4b87-bbec-1e32407e5e47/"
}
]
}
```
This commit adds a fast exit track in Walk() in this specific case.
use `/etc/hosts` instead of `/` to check for common
device id, if the device is same for `/etc/hosts`
and the --bind mount to detect root disks.
Bonus enhance healthcheck logging by adding maintenance
tags, for all messages.
adds a feature where we can fetch the MinIO
command-line remotely, this
is primarily meant to add some stateless
nature to the MinIO deployment in k8s
environments, MinIO operator would run a
webhook service endpoint
which can be used to fetch any environment
value in a generalized approach.
It is possible in situations when server was deployed
in asymmetric configuration in the past such as
```
minio server ~/fs{1...4}/disk{1...5}
```
Results in setDriveCount of 10 in older releases
but with fairly recent releases we have moved to
having server affinity which means that a set drive
count ascertained from above config will be now '4'
While the object layer make sure that we honor
`format.json` the storageClass configuration however
was by mistake was using the global value obtained
by heuristics. Which leads to prematurely using
lower parity without being requested by the an
administrator.
This PR fixes this behavior.
Bonus also fix a bug where we did not purge relevant
service accounts generated by rotating credentials
appropriately, service accounts should become invalid
as soon as its corresponding parent user becomes invalid.
Since service account themselves carry parent claim always
we would never reach this problem, as the access get
rejected at IAM policy layer.
when source and destination are same and versioning is enabled
on the destination bucket - we do not need to re-create the entire
object once again to optimize on space utilization.
Cases this PR is not supporting
- any pre-existing legacy object will not
be preserved in this manner, meaning a new
dataDir will be created.
- key-rotation and storage class changes
of course will never re-use the dataDir
conflicting files can exist on FS at
`.minio.sys/buckets/testbucket/policy.json/`, this is an
expected valid scenario for FS mode allow it to work,
i.e ignore and move forward
With reduced parity our write quorum should be same
as read quorum, but code was still assuming
```
readQuorum+1
```
In all situations which is not necessary.
Generalize replication target management so
that remote targets for a bucket can be
managed with ARNs. `mc admin bucket remote`
command will be used to manage targets.
Context timeout might race on each other when timeouts are lower
i.e when two lock attempts happened very quickly on the same resource
and the servers were yet trying to establish quorum.
This situation can lead to locks held which wouldn't be unlocked
and subsequent lock attempts would fail.
This would require a complete server restart. A potential of this
issue happening is when server is booting up and we are trying
to hold a 'transaction.lock' in quick bursts of timeout.
replace dummy buffer with nullReader{} instead,
to avoid large memory allocations in memory
constrainted environments. allows running
obd tests in such environments.
Currently, listing directories on HDFS incurs a per-entry remote Stat() call
penalty, the cost of which can really blow up on directories with many
entries (+1,000) especially when considered in addition to peripheral
calls (such as validation) and the fact that minio is an intermediary to the
client (whereas other clients listed below can query HDFS directly).
Because listing directories this way is expensive, the Golang HDFS library
provides the [`Client.Open()`] function which creates a [`FileReader`] that is
able to batch multiple calls together through the [`Readdir()`] function.
This is substantially more efficient for very large directories.
In one case we were witnessing about +20 seconds to list a directory with 1,500
entries, admittedly large, but the Java hdfs ls utility as well as the HDFS
library sample ls utility were much faster.
Hadoop HDFS DFS (4.02s):
λ ~/code/minio → use-readdir
» time hdfs dfs -ls /directory/with/1500/entries/
…
hdfs dfs -ls 5.81s user 0.49s system 156% cpu 4.020 total
Golang HDFS library (0.47s):
λ ~/code/hdfs → master
» time ./hdfs ls -lh /directory/with/1500/entries/
…
./hdfs ls -lh 0.13s user 0.14s system 56% cpu 0.478 total
mc and minio **without** optimization (16.96s):
λ ~/code/minio → master
» time mc ls myhdfs/directory/with/1500/entries/
…
./mc ls 0.22s user 0.29s system 3% cpu 16.968 total
mc and minio **with** optimization (0.40s):
λ ~/code/minio → use-readdir
» time mc ls myhdfs/directory/with/1500/entries/
…
./mc ls 0.13s user 0.28s system 102% cpu 0.403 total
[`Client.Open()`]: https://godoc.org/github.com/colinmarc/hdfs#Client.Open
[`FileReader`]: https://godoc.org/github.com/colinmarc/hdfs#FileReader
[`Readdir()`]: https://godoc.org/github.com/colinmarc/hdfs#FileReader.Readdir
If there are many listeners to bucket notifications or to the trace
subsystem, healing fails to work properly since it suspends itself when
the number of concurrent connections is above a certain threshold.
These connections are also continuous and not costly (*no disk access*),
it is okay to just ignore them in waitForLowHTTPReq().
this is to detect situations of corruption disk
format etc errors quickly and keep the disk online
in such scenarios for requests to fail appropriately.
Fixes two different types of problems
- continuation of the problem seen in FS #9992
as not fixed for erasure coded deployments,
reproduced this issue with spark and its fixed now
- another issue was leaking walk go-routines which
would lead to high memory usage and crash the system
this is simply because all the walks which were purged
at the top limit had leaking end walkers which would
consume memory endlessly.
closes#9966closes#10088
not all claims need to be present for
the JWT claim, let the policies not
exist and only apply which are present
when generating the credentials
once credentials are generated then
those policies should exist, otherwise
the request will fail.
- copyObject in-place decryption failed
due to incorrect verification of headers
- do not decode ETag when object is encrypted
with SSE-C, so that pre-conditions don't fail
prematurely.
This PR adds support for healing older
content i.e from 2yrs, 1yr. Also handles
other situations where our config was
not encrypted yet.
This PR also ensures that our Listing
is consistent and quorum friendly,
such that we don't list partial objects
In federated NAS gateway setups, multiple hosts in srvRecords
was picked at random which could mean that if one of the
host was down the request can indeed fail and if client
retries it would succeed. Instead allow server to figure
out the current online host quickly such that we can
exclude the host which is down.
At the max the attempt to look for a downed node is to
300 millisecond, if the node is taking longer to respond
than this value we simply ignore and move to the node,
total attempts are equal to number of srvRecords if no
server is online we simply fallback to last dialed host.
healing was not working properly when drives were
replaced, due to the error check in root disk
calculation this PR fixes this behavior
This PR also adds additional fix for missing
metadata entries from .minio.sys as part of
disk healing as well.
Added code to ignore and print more context
sensitive errors for better debugging.
This PR is continuation of fix in 7b14e9b660
Enforce bucket quotas when crawling has finished.
This ensures that we will not do quota enforcement on old data.
Additionally, delete less if we are closer to quota than we thought.
for users who don't have access to HDFS rootPath '/'
can optionally specify `minio gateway hdfs hdfs://namenode:8200/path`
for which they have access to, allowing all writes to be
performed at `/path`.
NOTE: once configured in this manner you need to make
sure command line is correctly specified, otherwise
your data might not be visible
closes#10011
this PR to allow legacy support for big-data
applications which run older Java versions
which do not support the secure ciphers
currently defaulted in MinIO. This option
allows optionally to turn them off such
that client and server can negotiate the
best ciphers themselves.
This env is purposefully not documented,
meant as a last resort when client
application cannot be changed easily.
- admin info node offline check is now quicker
- admin info now doesn't duplicate the code
across doing the same checks for disks
- rely on StorageInfo to return appropriate errors
instead of calling locally.
- diskID checks now return proper errors when
disk not found v/s format.json missing.
- add more disk states for more clarity on the
underlying disk errors.
while we handle all situations for writes and reads
on older format, what we didn't cater for properly
yet was delete where we only ended up deleting
just `xl.meta` - instead we should allow all the
deletes to go through for older format without
versioning enabled buckets.
CORS is notorious requires specific headers to be
handled appropriately in request and response,
using cors package as part of handlerFunc() for
options method lacks the necessary control this
package needs to add headers.
Without instantiating a new rest client we can
have a recursive error which can lead to
healthcheck returning always offline, this can
prematurely take the servers offline.
gorilla/mux broke their recent release 1.7.4 which we
upgraded to, we need the current workaround to ensure
that our regex matches appropriately.
An upstream PR is sent, we should remove the
workaround once we have a new release.
- reduce locker timeout for early transaction lock
for more eagerness to timeout
- reduce leader lock timeout to range from 30sec to 1minute
- add additional log message during bootstrap phase
Main issue is that `t.pool[params]` should be `t.pool[oldest]`.
We add a bit more safety features for the code.
* Make writes to the endTimerCh non-blocking in all cases
so multiple releases cannot lock up.
* Double check expectations.
* Shift down deletes with copy instead of truncating slice.
* Actually delete the oldest if we are above total limit.
* Actually delete the oldest found and not the current.
* Unexport the mutex so nobody from the outside can meddle with it.
This commit adds a new admin API for creating master keys.
An admin client can send a POST request to:
```
/minio/admin/v3/kms/key/create?key-id=<keyID>
```
The name / ID of the new key is specified as request
query parameter `key-id=<ID>`.
Creating new master keys requires KES - it does not work with
the native Vault KMS (deprecated) nor with a static master key
(deprecated).
Further, this commit removes the `UpdateKey` method from the `KMS`
interface. This method is not needed and not used anymore.
with the merge of https://github.com/etcd-io/etcd/pull/11823
etcd v3.5.0 will now have a properly imported versioned path
this fixes our pending migration to newer repo
Use a separate client for these calls that can take a long time.
Add request context to these so they are canceled when the client
disconnects instead except for ListObject which doesn't have any equivalent.
Healing an object which has multiple versions was not working because
the healing code forgot to consider errFileVersionNotFound error as a
use case that needs healing
Currently, lifecycle expiry is deleting all object versions which is not
correct, unless noncurrent versions field is specified.
Also, only delete the delete marker if it is the only version of the
given object.
- additionally upgrade to msgp@v1.1.2
- change StatModTime,StatSize fields as
simple Size/ModTime
- reduce 50000 entries per List batch to 10000
as client needs to wait too long to see the
first batch some times which is not desired
and it is worth we write the data as soon
as we have it.
object KMS is configured with auto-encryption,
there were issues when using docker registry -
this has been left unnoticed for a while.
This PR fixes an issue with compatibility.
Additionally also fix the continuation-token implementation
infinite loop issue which was missed as part of #9939
Also fix the heal token to be generated as a client
facing value instead of what is remembered by the
server, this allows for the server to be stateless
regarding the token's behavior.
When manual healing is triggered, one node in a cluster will
become the authority to heal. mc regularly sends new requests
to fetch the status of the ongoing healing process, but a load
balancer could land the healing request to a node that is not
doing the healing request.
This PR will redirect a request to the node based on the node
index found described as part of the client token. A similar
technique is also used to proxy ListObjectsV2 requests
by encoding this information in continuation-token
The S3 specification says that versions are ordered in the response of
list object versions.
mc snapshot needs this to know which version comes first especially when
two versions have the same exact last-modified field.
Readiness as no reasoning to be cluster scope
because that is not how the k8s networking works
for pods, all the pods to a deployment are not
sharing the network in a singleton. Instead they
are run as local scopes to themselves, with
readiness failures the pod is potentially taken
out of the network to be resolvable - this
affects the distributed setup in myriad of
different ways.
Instead readiness should behave like liveness
with local scope alone, and should be a dummy
implementation.
This PR all the startup times and overal k8s
startup time dramatically improves.
Added another handler called as `/minio/health/cluster`
to understand the cluster scope health.
Walk() functionality was missing on gateway
implementations leading to missing functionality
for the browser UI such as remove multiple objects,
download as zip file etc.
This PR brings a generic implementation across
all gateway's, it is not required to repeat the
same code in all gateway's
The default behavior is to cache each range requested
to cache drive. Add an environment variable
`MINIO_RANGE_CACHE` - when set to off, it disables
range caching and instead downloads entire object
in the background.
Fixes#9870
Bonus fix during versioning merge one of the PR was missing
the offline/online disk count fix from #9801 port it correctly
over to the master branch from release.
Additionally, add versionID support for MRF
Fixes#9910Fixes#9931
This PR has the following changes
- Removing duplicate lookupConfigs() calls.
- Deprecate admin config APIs for NAS gateways. This will avoid repeated reloads of the config from the disk.
- WatchConfigNASDisk will be removed
- Migration guide for NAS gateways users to migrate to ENV settings.
NOTE: THIS PR HAS A BREAKING CHANGE
Fixes#9875
Co-authored-by: Harshavardhana <harsha@minio.io>
Looking into full disk errors on zoned setup. We don't take the
5% space requirement into account when selecting a zone.
The interesting part is that even considering this we don't
know the size of the object the user wants to upload when
they do multipart uploads.
It seems quite defensive to always upload multiparts to
the zone where there is the most space since all load will
be directed to a part of the cluster.
In these cases we make sure it can at least hold a 1GiB file
and we disadvantage fuller zones more by subtracting the
expected size before weighing.
- x-amz-storage-class specified CopyObject
should proceed regardless, its not a precondition
- sourceVersionID is specified CopyObject should
proceed regardless, its not a precondition
This PR fixes all the below scenarios
and handles them correctly.
- existing data/bucket is replaced with
new content, no versioning enabled old
structure vanishes.
- existing data/bucket - enable versioning
before uploading any data, once versioning
enabled upload new content, old content
is preserved.
- suspend versioning on the bucket again, now
upload content again the old content is purged
since that is the default "null" version.
Additionally sync data after xl.json -> xl.meta
rename(), to avoid any surprises if there is a
crash during this rename operation.
- Add changes to ensure remote disks are not
incorrectly taken online if their order has
changed or are incorrect disks.
- Bring changes to peer to detect disconnection
with separate Health handler, to avoid a
rather expensive call GetLocakDiskIDs()
- Follow up on the same changes for Lockers
as well
Just like GET/DELETE APIs it is possible to preserve
client supplied versionId's, of course the versionIds
have to be uuid, if an existing versionId is found
it is overwritten if no object locking policies
are found.
- PUT /bucketname/objectname?versionId=<id>
- POST /bucketname/objectname?uploads=&versionId=<id>
- PUT /bucketname/objectname?verisonId=<id> (with x-amz-copy-source)
Fixes potentially infinite allocations, especially in FS mode,
since lookups live up to 30 minutes. Limit walk pool sizes to 50
max parameter entries and 4 concurrent operations with the same
parameters.
Fixes#9835
PutObject on multiple-zone with versioning would not
overwrite the correct location of the object if the
object has delete marker, leading to duplicate objects
on two zones.
This PR fixes by adding affinity towards delete marker
when GetObjectInfo() returns error, use the zone index
which has the delete marker.
Bonus change to use channel to serialize triggers,
instead of using atomic variables. More efficient
mechanism for synchronization.
Co-authored-by: Nitish Tiwari <nitish@minio.io>
In the Current bug we were re-using the context
from previously granted lockers, this would
lead to lock timeouts for existing valid
read or write locks, leading to premature
timeout of locks.
This bug affects only local lockers in FS
or standalone erasure coded mode. This issue
is rather historical as well and was present
in lsync for some time but we were lucky to
not see it.
Similar changes are done in dsync as well
to keep the code more familiar
Fixes#9827
When updating all servers following the constructions of mc update,
only the endpoint server will be updated successfully.
All the other peer servers' updating failed due to the error below:
--------------------------------------------------------------------------
parsing time "2006-01-02T15:04:05Z07:00" as "<release version>": cannot parse "-01-02T15:04:05Z07:00" as "0-"
--------------------------------------------------------------------------
- Implement a new xl.json 2.0.0 format to support,
this moves the entire marshaling logic to POSIX
layer, top layer always consumes a common FileInfo
construct which simplifies the metadata reads.
- Implement list object versions
- Migrate to siphash from crchash for new deployments
for object placements.
Fixes#2111
Historically due to lack of support for middlewares
we ended up writing wrapped handlers for all
middlewares on top of the gorilla/mux, this causes
multiple issues when we want to let's say
- Overload r.Body with some custom implementation
to track the incoming Reads()
- Add other sort of top level checks to avoid
DDOSing the server with large incoming HTTP
bodies.
Since 1.7.x release gorilla/mux provides proper
use of middlewares, which are honored by the muxer
directly. This makes sure that Go can honor its
own internal ServeHTTP(w, r) implementation where
Go net/http can wrap into its own customer readers.
This PR as a side-affect fixes rare issues of client
hangs which were reported in the wild but never really
understood or fixed in our codebase.
Fixes#9759Fixes#7266Fixes#6540Fixes#5455Fixes#5150
Refer https://github.com/boto/botocore/pull/1328 for
one variation of the same issue in #9759
PR #9801 while it is correct, the loop isEndpointConnected()
was changed to rely on endpoint.String() which has the host
information as well, which is not correct value as input to
detect if the disk is down or up, if endpoint is local use
its local path value instead.
This commit changes the data key generation such that
if a MinIO server/nodes tries to generate a new DEK
but the particular master key does not exist - then
MinIO asks KES to create a new master key and then
requests the DEK again.
From now on, a SSE-S3 master key must not be created
explicitly via: `kes key create <key-name>`.
Instead, it is sufficient to just set the env. var.
```
export MINIO_KMS_KES_KEY_NAME=<key-name>
```
However, the MinIO identity (mTLS client certificate)
must have the permission to access the `/v1/key/create/`
API. Therefore, KES policy for MinIO must look similar to:
```
[
/v1/key/create/<key-name-pattern>
/v1/key/generate/<key-name-pattern>
/v1/key/decrypt/<key-name-pattern>
]
```
However, in our guides we already suggest that.
See e.g.: https://github.com/minio/kes/wiki/MinIO-Object-Storage#kes-server-setup
***
The ability to create master keys on request may also be
necessary / useful in case of SSE-KMS.
Current code was relying on globalEndpoints as
the source of secondary truth to obtain
the missing endpoints list when the disk
is offline, this is problematic
- there is no way to know if the getDisks()
returned endpoints total is same as the
ones list of globalEndpoints and it
belongs to a particular set.
- there is no order guarantee as getDisks()
is ordered as per format.json, globalEndpoints
may not be, so potentially end up including
incorrect endpoints.
To fix this bring getEndpoints() just like getDisks()
to ensure that consistently ordered endpoints are
always available for us to ensure that returned values
are consistent with what each erasure set would observe.
Uploading files with names that could not be written to disk
would result in "reduce your request" errors returned.
Instead check explicitly for disallowed characters and reject
files with `Object name contains unsupported characters.`
At a customer setup with lots of concurrent calls
it can be observed that in newRetryTimer there
were lots of tiny alloations which are not
relinquished upon retries, in this codepath
we were only interested in re-using the timer
and use it wisely for each locker.
```
(pprof) top
Showing nodes accounting for 8.68TB, 97.02% of 8.95TB total
Dropped 1198 nodes (cum <= 0.04TB)
Showing top 10 nodes out of 79
flat flat% sum% cum cum%
5.95TB 66.50% 66.50% 5.95TB 66.50% time.NewTimer
1.16TB 13.02% 79.51% 1.16TB 13.02% github.com/ncw/directio.AlignedBlock
0.67TB 7.53% 87.04% 0.70TB 7.78% github.com/minio/minio/cmd.xlObjects.putObject
0.21TB 2.36% 89.40% 0.21TB 2.36% github.com/minio/minio/cmd.(*posix).Walk
0.19TB 2.08% 91.49% 0.27TB 2.99% os.statNolog
0.14TB 1.59% 93.08% 0.14TB 1.60% os.(*File).readdirnames
0.10TB 1.09% 94.17% 0.11TB 1.25% github.com/minio/minio/cmd.readDirN
0.10TB 1.07% 95.23% 0.10TB 1.07% syscall.ByteSliceFromString
0.09TB 1.03% 96.27% 0.09TB 1.03% strings.(*Builder).grow
0.07TB 0.75% 97.02% 0.07TB 0.75% path.(*lazybuf).append
```
For example `{1...17}/{1...52}` symmetrical
distribution of drives cannot be obtained
- Because 17 is a prime number
- Is not divisible by any pre-defined setCounts i.e
from 1 to 16
Manual healing (as background healing) creates a heal task with a
possiblity to override healing options, such as deep or normal mode.
Use a pointer type in heal opts so nil would mean use the default
healing options.
aws cli fails to set a bucket encryption configuration to MinIO server.
The reason is that aws cli does not send MD5-Content header. It seems
that MD5-Content is not required anymore.
This commit also returns Not Implemented header early to help mint tests
to ignore testing this API in gateway modes.
CopyObject was not correctly figuring out the correct
destination object location and would end up creating
duplicate objects on two different zones, reproduced
by doing encryption based key rotation.
Advantages avoids 100's of stats which are needed for each
upload operation in FS/NAS gateway mode when uploading a large
multipart object, dramatically increases performance for
multipart uploads by avoiding recursive calls.
For other gateway's simplifies the approach since
azure, gcs, hdfs gateway's don't capture any specific
metadata during upload which needs handler validation
for encryption/compression.
Erasure coding was already optimized, additionally
just avoids small allocations of large data structure.
Fixes#7206
GetDiskID() in storage rest client does not really issue a REST request
to the remote disk, but returns an in-memory value instead.
However, GetDiskID() should return an error when format.json is not
found or for other similar issues (unmounted disks, etc..)
GetDiskID() is only called when formatting disks and getting storage
informatio, hence this commit should not have a performance degradation.
Additionally also fix STS logs to filter out LDAP
password to be sent out in audit logs.
Bonus fix handle the reload of users properly by
making sure to preserve the newer users during the
reload to be not invalidated.
Fixes#9707Fixes#9644Fixes#9651
Bonus fixes in quota enforcement to use the
new datastructure and use timedValue to cache
a value/reload automatically avoids one less
global variable.
If the requested server is part of the set this will always read
from the local disk, even if the disk contains a parity shard.
In default setup there is a 50% chance that at least
one shard that otherwise would have been fetched remotely
will be read locally instead.
It basically trades RPC call overhead for reed-solomon.
On distributed localhost this seems to be fairly break-even,
with a very small gain in throughput and latency.
However on networked servers this should be a bigger
1MB objects, before:
```
Operation: GET. Concurrency: 32. Hosts: 4.
Requests considered: 76257:
* Avg: 25ms 50%: 24ms 90%: 32ms 99%: 42ms Fastest: 7ms Slowest: 67ms
* First Byte: Average: 23ms, Median: 22ms, Best: 5ms, Worst: 65ms
Throughput:
* Average: 1213.68 MiB/s, 1272.63 obj/s (59.948s, starting 14:45:44 CEST)
```
After:
```
Operation: GET. Concurrency: 32. Hosts: 4.
Requests considered: 78845:
* Avg: 24ms 50%: 24ms 90%: 31ms 99%: 39ms Fastest: 8ms Slowest: 62ms
* First Byte: Average: 22ms, Median: 21ms, Best: 6ms, Worst: 57ms
Throughput:
* Average: 1255.11 MiB/s, 1316.08 obj/s (59.938s, starting 14:43:58 CEST)
```
Bonus fix: Only ask for heal once on an object.
This value is requested on every upload when there are multiple zones.
Since this will result in an RPC call to every remote disk this scales
quite badly in a distributed setup. Load every 1second interval.
2 servers, localhost only. In large distributed setups much bigger
gains can be expected.
```
Operations: 21743 -> 22454
* Average: +3.28% (+0.0 MiB/s) throughput, +3.28% (+11.9) obj/s
* Fastest: +3.37% (+0.0 MiB/s) throughput, +3.37% (+13.0) obj/s
* 50% Median: +3.03% (+0.0 MiB/s) throughput, +3.03% (+11.2) obj/s
* Slowest: +8.03% (+0.0 MiB/s) throughput, +8.03% (+22.8) obj/s
```
For easy management of this a generic helper has been added.
some clients such as veeam expect the x-amz-meta to
be sent in lower cased form, while this does indeed
defeats the HTTP protocol contract it is harder to
change these applications, while these applications
get fixed appropriately in future.
x-amz-meta is usually sent in lowercased form
by AWS S3 and some applications like veeam
incorrectly end up relying on the case sensitivity
of the HTTP headers.
Bonus fixes
- Fix the iso8601 time format to keep it same as
AWS S3 response
- Increase maxObjectList to 50,000 and use
maxDeleteList as 10,000 whenever multi-object
deletes are needed.
No one really uses FS for large scale accounting
usage, neither we crawl in NAS gateway mode. It is
worthwhile to simply disable this feature as its
not useful for anyone.
Bonus disable bucket quota ops as well in, FS
and gateway mode
size calculation in crawler was using the real size
of the object instead of its actual size i.e either
a decrypted or uncompressed size.
this is needed to make sure all other accounting
such as bucket quota and mcs UI to display the
correct values.
This PR adds a new configuration parameter which allows readiness
check to respond within 10secs, this can be reduced to a lower value
if necessary using
```
mc admin config set api ready_deadline=5s
```
or
```
export MINIO_API_READY_DEADLINE=5s
```
net/http exposes ErrorLog but it is log.Logger
instance not an interface which can be overridden,
because of this reason the logging is interleaved
sometimes with TLS with messages like this on the
server
```
http: TLS handshake error from 139.178.70.188:63760: EOF
```
This is bit problematic for us as we need to have
consistent logging view for allow --json or --quiet
flags.
With this PR we ensure that this format is adhered to.
Groups information shall be now stored as part of the
credential data structure, this is a more idiomatic
way to support large LDAP groups.
Avoids the complication of setups where LDAP groups
can be in the range of 150+ which may lead to excess
HTTP header size > 8KiB, to reduce such an occurrence
we shall save the group information on the server as
part of the credential data structure.
Bonus change support multiple mapped policies, across
all types of users.
This PR is a continuation from #9586, now the
entire parsing logic is fully merged into
bucket metadata sub-system, simplify the
quota API further by reducing the remove
quota handler implementation.
Shuffling arguments that we pass to MinIO server are supported. However,
when that happens, Prometheus returns wrong information about disks usage
and online/offline status.
The commit fixes the issue by avoiding relying on xl.endpoints since
it is not ordered.
this is a major overhaul by migrating off all
bucket metadata related configs into a single
object '.metadata.bin' this allows us for faster
bootups across 1000's of buckets and as well
as keeps the code simple enough for future
work and additions.
Additionally also fixes#9396, #9394
To avoid this issue with refCounter refactor the code
such that
- locker() always increases refCount upon success
- unlocker() always decrements refCount upon success
(as a special case removes the resource if the
refCount is zero)
By these two assumptions we are able to see that we
are never granted two write lockers in any situation.
Thanks to @vcabbage for writing a nice reproducer.
enable linter using golangci-lint across
codebase to run a bunch of linters together,
we shall enable new linters as we fix more
things the codebase.
This PR fixes the first stage of this
cleanup.
There is a disparency of behavior under Linux & Windows about
the returned error when trying to rename a non existant path.
err := os.Rename("/path/does/not/exist", "/tmp/copy")
Linux:
isSysErrNotDir(err) = false
os.IsNotExist(err) = true
Windows:
isSysErrNotDir(err) = true
os.IsNotExist(err) = true
ENOTDIR in Linux is returned when the destination path
of the rename call contains a file in one of the middle
segments of the path (e.g. /tmp/file/dst, where /tmp/file
is an actual file not a directory)
However, as shown above, Windows has more scenarios when
it returns ENOTDIR. For example, when the source path contains
an inexistant directory in its path.
In that case, we want errFileNotFound returned and not
errFileAccessDenied, so this commit will add a further check to close
the disparency between Windows & Linux.
The `ioutil.NopCloser(reader)` was hiding nested hash readers.
We make it an `io.Closer` so it can be attached without wrapping
and allows for nesting, by merging the requests.
The `keepHTTPResponseAlive` would cause errors to be
returned with status OK.
- Add '32' as a filler byte until a response is ready
- '0' to indicate the response is ready to be consumed
- '1' to indicate response has an error which needs
to be returned to the caller
Clear out 'file not found' errors from dir walker, since it may be
in a folder that has been deleted since it was scanned.
This PR is to ensure that we call the relevant object
layer APIs for necessary S3 API level functionalities
allowing gateway implementations to return proper
errors as NotImplemented{}
This allows for all our tests in mint to behave
appropriately and can be handled appropriately as
well.
S3 is now natively supported by B2 cloud storage provider
there is no reason to use specialized gateway for B2 anymore,
our current S3 gateway with caching would work with B2.
Resolves#8584
requests in federated setups for STS type calls which are
performed at '/' resource should be routed by the muxer,
the assumption is simply such that requests without a bucket
in a federated setup cannot be proxied, so serve them at
current server.
This commit makes the KES client use HTTP/2
when establishing a connection to the KES server.
This is necessary since the next KES server release
will require HTTP/2.
We should allow quorum errors to be send upwards
such that caller can retry while reading bucket
encryption/policy configs when server is starting
up, this allows distributed setups to load the
configuration properly.
Current code didn't facilitate this and would have
never loaded the actual configs during rolling,
server restarts.
In large setups this avoids unnecessary data transfer
across nodes and potential locks.
This PR also optimizes heal result channel, which should
be avoided for each queueHealTask as its expensive
to create/close channels for large number of objects.
This PR allows setting a "hard" or "fifo" quota
restriction at the bucket level. Buckets that
have reached the FIFO quota configured, will
automatically be cleaned up in FIFO manner until
bucket usage drops to configured quota.
If a bucket is configured with a "hard" quota
ceiling, all further writes are disallowed.
ResponseWriter & RecordAPIStats has similar role, merge them.
This commit will also fix wrong auditing for STS and Web and others
since they are using ResponseWriter instead of the RecordAPIStats.
A user can incorrectly mounts a newly fresh disk. MinIO will detect
that it is writing with a rootfs disk and will mark it down. However,
it is hard for the user to understand what's going on.
This commit will just print a notice so it will be easy to spot
such use case.
- elasticsearch client should rely on the SDK helpers
instead of pure HTTP calls.
- webhook shouldn't need to check for IsActive() for
all notifications, failure should be delayed.
- Remove DialHTTP as its never used properly
Fixes#9460
allow generating service accounts for temporary credentials
which have a designated parent, currently OpenID is not yet
supported.
added checks to ensure that service account cannot generate
further service accounts for itself, service accounts can
never be a parent to any credential.
Audit was not working properly when enabled from the environment
caused by a typo in the code.
This commit fixes that but also consider the following variables:
`MINIO_LOGGER_WEBHOOK_ENABLE_*` and
`MINIO_AUDIT_WEBHOOK_ENABLE_*` so the user can use
this latter to temporarily disable a logger or audit configuration.
data usage tracker and crawler seem to be logging
non-actionable information on console, which is not
useful and is fixed on its own in almost all deployments,
lets keep this logging to minimal.
it is possible in many screnarios that even
if the divisible value is optimal, we may
end up with uneven distribution due to number
of nodes present in the configuration.
added code allow for affinity towards various
ellipses to figure out optimal value across
ellipses such that we can always reach a
symmetric value automatically.
Fixes#9416
By monitoring PUT/DELETE and heal operations it is possible
to track changed paths and keep a bloom filter for this data.
This can help prioritize paths to scan. The bloom filter can identify
paths that have not changed, and the few collisions will only result
in a marginal extra workload. This can be implemented on either a
bucket+(1 prefix level) with reasonable performance.
The bloom filter is set to have a false positive rate at 1% at 1M
entries. A bloom table of this size is about ~2500 bytes when serialized.
To not force a full scan of all paths that have changed cycle bloom
filters would need to be kept, so we guarantee that dirty paths have
been scanned within cycle runs. Until cycle bloom filters have been
collected all paths are considered dirty.
this commit avoids lots of tiny allocations, repeated
channel creates which are performed when filtering
the incoming events, unescaping a key just for matching.
also remove deprecated code which is not needed
anymore, avoids unexpected data structure transformations
from the map to slice.
we have policy available for sub-admin users to set/get/delete
config, but we incorrectly decrypt the content using admin secret
key which in-fact should be the credential authenticating the
request.
global WORM mode is a complex piece for which
the time has passed, with the advent of S3 compatible
object locking and retention implementation global
WORM is sort of deprecated, this has been mentioned
in our documentation for some time, now the time
has come for this to go.
re-implement the cache purging routine to
avoid using ioutil.ReadDir which can lead
to high allocations when there are cache
directories with lots of content, or
when cache is installed in memory constrainted
environments.
Instead rely on a callback function where we
are not using memory no-more than 8KiB per
cycle.
Precursor for this change refer #9425, original
issue pointed by Caleb Case <caleb@storj.io>
OSS go sdk lacks licensing terms in their
repository, and there has been no activity
On the issue here https://github.com/aliyun/aliyun-oss-go-sdk/issues/245
This PR is to ensure we remove any dependency code which
lacks explicit license file in their repo.
- keep long running obd network tests alive
- fix error - wrong number of parents in process OBD info
- ensure that osinfo does not error out when inside containers
- remove limit on max number of connections per client transport
The generic client transport uses a default limit of 64 conns per transport.
This could end up limiting and throttling usage, and artificially slowing
down the performance of MinIO even on hardware capable of doing better.
New value defaults to 100K events by default,
but users can tune this value upto any value
they seem necessary.
* increase the limit to maxint64 while validating
This PR also fixes issues when
deletePolicy, deleteUser is idempotent so can lead to
issues when client can prematurely timeout, so a retry
call error response should be ignored when call returns
http.StatusNotFound
Fixes#9347
allow `mc admin config set mygateway/ audit_webhook --env`
to fetch the documentation as needed, this is just to
ensure that our users can still access the relevant
ENV docs while running in gateway mode.
Instead of GlobalContext use a local context for tests.
Most notably this allows stuff created to be shut down
when tests using it is done. After PR #9345 9331 CI is
often running out of memory/time.
Add two new configuration entries, api.requests-max and
api.requests-deadline which have the same role of
MINIO_API_REQUESTS_MAX and MINIO_API_REQUESTS_DEADLINE.
This PR fixes couple of behaviors with service accounts
- not need to have session token for service accounts
- service accounts can be generated by any user for themselves
implicitly, with a valid signature.
- policy input for AddNewServiceAccount API is not fully typed
allowing for validation before it is sent to the server.
- also bring in additional context for admin API errors if any
when replying back to client.
- deprecate GetServiceAccount API as we do not need to reply
back session tokens
- Introduced a function `FetchRegisteredTargets` which will return
a complete set of registered targets irrespective to their states,
if the `returnOnTargetError` flag is set to `False`
- Refactor NewTarget functions to return non-nil targets
- Refactor GetARNList() to return a complete list of configured targets
- Removes PerfInfo admin API as its not OBDInfo
- Keep the drive path without the metaBucket in OBD
global latency map.
- Remove all the unused code related to PerfInfo API
- Do not redefined global mib,gib constants use
humanize.MiByte and humanize.GiByte instead always
if needed use --no-compat to disable md5sum while
verifying any performance numbers.
bring back --compat behavior as default to avoid
additional documentation and confusing behavior,
as we are working towards improving md5sum to
be faster on AVX instructions, enabling this
should be hardly a problem in future versions
of MinIO.
fixes#8012fixes#7859fixes#7642
Continuing from previous PR #9304, comment
is a special key is not present in the
default KV list. Add it explicitly when
tokenizing fields as it may be possible that
some clients might try to set comments.
This PR adds context-based `k=v` splits based
on the sub-system which was obtained, if the
keys are not provided an error will be thrown
during parsing, if keys are provided with wrong
values an error will be thrown. Keys can now
have values which are of a much more complex
form such as `k="v=v"` or `k=" v = v"`
and other variations.
additionally, deprecate unnecessary postgres/mysql
configuration styles, support only
- connection_string for Postgres
- dsn_string for MySQL
All other parameters are removed.
This commit fixes a performance issue caused
by too many calls to the external KMS - i.e.
for single-part PUT requests.
In general, the issue is caused by a sub-optimal
code structure. In particular, when the server
encrypts an object it requests a new data encryption
key from the KMS. With this key it does some key
derivation and encrypts the object content and
ETag.
However, to behave S3-compatible the MinIO server
has to return the plaintext ETag to the client
in case SSE-S3.
Therefore, the server code used to decrypt the
(previously encrypted) ETag again by requesting
the data encryption key (KMS decrypt API) from
the KMS.
This leads to 2 KMS API calls (1 generate key and
1 decrypt key) per PUT operation - while only
one KMS call is necessary.
This commit fixes this by fetching a data key only
once from the KMS and keeping the derived object
encryption key around (for the lifetime of the request).
This leads to a significant performance improvement
w.r.t. to PUT workloads:
```
Operation: PUT
Operations: 161 -> 239
Duration: 28s -> 29s
* Average: +47.56% (+25.8 MiB/s) throughput, +47.56% (+2.6) obj/s
* Fastest: +55.49% (+34.5 MiB/s) throughput, +55.49% (+3.5) obj/s
* 50% Median: +58.24% (+32.8 MiB/s) throughput, +58.24% (+3.3) obj/s
* Slowest: +1.83% (+0.6 MiB/s) throughput, +1.83% (+0.1) obj/s
```
Fixes#8667
In addition to the above, if the user is mapped to a policy or
belongs in a group, the user-info API returns this information,
but otherwise, the API will now return a non-existent user error.
make rest of the Walk() function more predictable,
it was observed that in nominal deployments even
without much workload the drives are generally
slow for respond for readdir operations, for the
sleepDuration factor of 10 this can cause
unexpected slowness in the Listing calls, while
it is good for all other I/O, it may simply slow
down Listing immensely which is not useful.
fixes#9261
In FS mode under Windows, removing an object will not automatically.
remove parent empty prefixes.
The reason is that path.Dir() was used, however filepath.Dir() is
more appropriate since filepath is physical (meaning it operates
on OS filesystem paths)
This is not caught because failure for Windows CI is not caught.
fs-v1 in server mode only checks to see if the path exist, so that it
returns ready before it is indeed ready.
This change adds a check to ensure that the global object api is
available too before reporting ready.
Fixes#9283
It is some times common and convenient to use
just local IPs for testing purposes, 127.0.0.x
are special IPs regardless of being available on
an interface they can be bound to on all operating
systems.
Allow this behavior to work for minio server
fixes#9274
also, bring in an additional policy to ensure that
force delete bucket is only allowed with the right
policy for the user, just DeleteBucketAction
policy action is not enough.
This PR also tries to simplify the approach taken in
object-locking implementation by preferential treatment
given towards full validation.
This in-turn has fixed couple of bugs related to
how policy should have been honored when ByPassGovernance
is provided.
Simplifies code a bit, but also duplicates code intentionally
for clarity due to complex nature of object locking
implementation.
Too many deployments come up with an odd number
of hosts or drives, to facilitate even distribution
among those setups allow for odd and prime numbers
based packs.
- B2 does actually return an MD5 hash for newly uploaded objects
so we can use it to provide better compatibility with S3 client
libraries that assume the ETag is the MD5 hash such as boto.
- depends on change in blazer library.
- new behaviour is only enabled if MinIO's --compat mode is active.
- behaviour for multipart uploads is unchanged (works fine as is).
- Implement a graph algorithm to test network bandwidth from every
node to every other node
- Saturate any network bandwidth adaptively, accounting for slow
and fast network capacity
- Implement parallel drive OBD tests
- Implement a paging mechanism for OBD test to provide periodic updates to client
- Implement Sys, Process, Host, Mem OBD Infos
- total number of S3 API calls per server
- maximum wait duration for any S3 API call
This implementation is primarily meant for situations
where HDDs are not capable enough to handle the incoming
workload and there is no way to throttle the client.
This feature allows MinIO server to throttle itself
such that we do not overwhelm the HDDs.
- acquire since leader lock for all background operations
- healing, crawling and applying lifecycle policies.
- simplify lifecyle to avoid network calls, which was a
bug in implementation - we should hold a leader and
do everything from there, we have access to entire
name space.
- make listing, walking not interfere by slowing itself
down like the crawler.
- effectively use global context everywhere to ensure
proper shutdown, in cache, lifecycle, healing
- don't read `format.json` for prometheus metrics in
StorageInfo() call.
- Add conservative timeouts upto 3 minutes
for internode communication
- Add aggressive timeouts of 30 seconds
for gateway communication
Fixes#9105Fixes#8732Fixes#8881Fixes#8376Fixes#9028
This is to improve responsiveness for all
admin API operations and allowing callers
to cancel any on-going admin operations,
if they happen to be waiting too long.
canonicalize the ENVs such that we can bring these ENVs
as part of the config values, as a subsequent change.
- fix location of per bucket usage to `.minio.sys/buckets/<bucket_name>/usage-cache.bin`
- fix location of the overall usage in `json` at `.minio.sys/buckets/.usage.json`
(avoid conflicts with a bucket named `usage.json` )
- fix location of the overall usage in `msgp` at `.minio.sys/buckets/.usage.bin`
(avoid conflicts with a bucket named `usage.bin`
As an optimization of the healing, HealObjects() avoid sending an
object to the background healing subsystem when the object is
present in all disks.
However, HealObjects() should have checked the scan type, if this
deep, always pass the object to the healing subsystem.
Currently, a tree walking, needed to a list objects in a specific
set quits listing as long as it finds no entries in a disk, which
is wrong.
This affected background healing, because the latter is using
tree walk directly. If one object does not exist in the first
disk for example, it will be seemed like the object does not
exist at all and no healing work is needed.
This commit fixes the behavior.
The staleness of a lock should be determined by
the quorum number of entries returning stale,
this allows for situations when locks are held
when nodes are down - we don't accidentally
clear locks unintentionally when they are valid
and correct.
Also lock maintenance should be run by all servers,
not one server, stale locks need to be run outside
the requirement for holding distributed locks.
Thanks @klauspost for reproducing this issue
Some AWS SDKs latently rely on this value some times
to calculate the right number of parts during a parallel
GetObject request, this is feature used along with
content-range - we should support this as well.
- avoid setting last heal activity when starting self-healing
This can be confusing to users thinking that the self healing
cycle was already performed.
- add info about the next background healing round
OperationTimedout error occurs when locking
timesout, trying to acquire a lock. This
error should be returned appropriately to
the client with http status "408" (request timedout)
This translation was broken, fix it.
Bulk delete API was using cleanupObjectsBulk() which calls posix
listing and delete API to remove objects internal files in the
backend (xl.json and parts) one by one.
Add DeletePrefixes in the storage API to remove the content
of a directory in a single call.
Also use a remove goroutine for each disk to accelerate removal.
Currently the code assumed some orthogonal requirements
which led situations where when we have a setup where
we have let's say for example 168 drives, the final
set_drive_count chosen was 14. Indeed 168 drives are
divisible by 12 but this wasn't allowed due to an
unexpected requirement to have 12 to be a perfect modulo
of 14 which is not possible. This assumption was incorrect.
This PR fixes this old assumption properly, also adds
few tests and some negative tests as well. Improvements
are seen in error messages as well.
- Remove the requirement to honor storage class for deletes
- Improve `posix.DeleteFileBulk` code to Stat the volumeDir
only once per call, rather than for all object paths.
Recent modification in the code led to incorrect calculation
of offline disks.
This commit saves the endpoint list in a xlObjects then we know
the name of each disk.
lock ownership is limited to endpoints on first zone,
as we do not hold locks on other zones in an expanded
setup. current code unintentionally expired active locks
when it couldn't see ownership from the secondary zone
which leads to unexpected bugs as locking fails to work
as expected.
this PR enforces md5sum verification for following
API's to be compatible with AWS S3 spec
- PutObjectRetention
- PutObjectLegalHold
Co-authored-by: Harshavardhana <harsha@minio.io>
Allow downloading goroutine dump to help detect leaks
or overuse of goroutines.
Extensions are now type dependent.
Change `profiling` -> `profile` prefix, since that is what they are
not the abstract concept.
This is a precursor change before versioning,
removes/deprecates the requirement of remembering
partName and partETag which are not useful after
a multipart transaction has finished.
This PR reduces the overall size of the backend
JSON for large file uploads.
For a non-existent user server would return STS not initialized
```
aws --profile harsha --endpoint-url http://localhost:9000 \
sts assume-role \
--role-arn arn:xxx:xxx:xxx:xxxx \
--role-session-name anything
```
instead return an appropriate error as expected by STS API
Additionally also format the `trace` output for STS APIs
Upgrades between releases are failing due to strict
rule to avoid rolling upgrades, it is enough to
bump up APIs between versions to allow for quorum
failure and wait times. Authentication failures are
catastrophic in nature which leads to server not
be able to upgrade properly.
Fixes#9021Fixes#8968
To allow better control the cache eviction process.
Introduce MINIO_CACHE_WATERMARK_LOW and
MINIO_CACHE_WATERMARK_HIGH env. variables to specify
when to stop/start cache eviction process.
Deprecate MINIO_CACHE_EXPIRY environment variable. Cache
gc sweeps at 30 minute intervals whenever high watermark is
reached to clear least recently accessed entries in the cache
until sufficient space is cleared to reach the low watermark.
Garbage collection uses an adaptive file scoring approach based
on last access time, with greater weights assigned to larger
objects and those with more hits to find the candidates for eviction.
Thanks to @klauspost for this file scoring algorithm
Co-authored-by: Klaus Post <klauspost@minio.io>
Change distributed locking to allow taking bulk locks
across objects, reduces usually 1000 calls to 1.
Also allows for situations where multiple clients sends
delete requests to objects with following names
```
{1,2,3,4,5}
```
```
{5,4,3,2,1}
```
will block and ensure that we do not fail the request
on each other.
Metrics used to have its own code to calculate offline disks.
StorageInfo() was avoided because it is an expensive operation
by sending calls to all nodes.
To make metrics & server info share the same code, a new
argument `local` is added to StorageInfo() so it will only
query local disks when needed.
Metrics now calls StorageInfo() as server info handler does
but with the local flag set to false.
Co-authored-by: Praveen raj Mani <praveen@minio.io>
Co-authored-by: Harshavardhana <harsha@minio.io>
Add dummy calls which respond success when ACL's
are set to be private and fails, if user tries
to change them from their default 'private'
Some applications such as nuxeo may have an
unnecessary requirement for this operation,
we support this anyways such that don't have
to fully implement the functionality just that
we can respond with success for default ACLs
Avoid GetObjectNInfo call from cache in CopyObjectHandler
- in the case of server side copy with metadata replacement,
the reader returned from cache is never consumed, but the net
effect of GetObjectNInfo from cache layer, is cache holding a
write lock to fill the cache. Subsequent stat operation on cache in
CopyObject is not able to acquire a read lock, thus causing the hang.
Fixes#8991
we don't need to validateFormats again once we have obtained
reference format, because it is possible that at this stage
another server is doing a disk heal during startup, once
in a while due to delays we get false positives and our
server doesn't start.
Format in quorum as reference format can be assumed as valid
and we proceed further, until and unless HealFormat re-inits
the disks after a successful heal.
Also use separate port for healing tests to avoid any
conflicts with regular build testing.
Fixes#8884
RegisterNotificationTargets() cleans up all connections
that it makes to notification targets when an error occurs
during its execution.
However there is a typo in the code that makes the function to always
try to access to a nil pointer in the defer code since the function
in question will always return nil in the case of any error.
This commit fixes the typo in the code.
http.Request.ContentLength can be negative, which affects
the gateway_s3_bytes_received value in Prometheus output.
The commit only increases the value of the total received bytes
in gateway mode when r.ContentLength is greater than zero.
First step is to ensure that Path component is not decoded
by gorilla/mux to avoid routing issues while handling
certain characters while uploading through PutObject()
Delay the decoding and use PathUnescape() to escape
the `object` path component.
Thanks to @buengese and @ncw for neat test cases for us
to test with.
Fixes#8950Fixes#8647
We added support for caching and S3 related metrics in #8591. As
a continuation, it would be helpful to add support for Azure & GCS
gateway related metrics as well.
The logging subsystem was initialized under init() method in
both gateway-main.go and server-main.go which are part of
same package. This created two logging targets and hence
errors were logged twice. This PR moves the init() method
to common-main.go
Streams are returning a readcloser and returning would
decrement io count instantly, fix it.
change maxActiveIOCount to 3, meaning it will pause
crawling if 3 operations are running.
Remove the random sleep. This is running in 4 goroutines,
so mostly doing nothing.
We use the getSize latency to estimate system load,
meaning when there is little load on the system and
we get the result fast we sleep a little.
If it took a long time we have high load and release
ourselves longer.
We are sleeping inside the mutex so this affects all
goroutines doing IO.
Due to a typo in the code, a cluster was not correctly creating
`background-ops` in all disks and nodes print the following error:
minio3_1 | API: SYSTEM()
minio3_1 | Time: 19:32:45 UTC 02/06/2020
minio3_1 | DeploymentID: d67c20fa-4a1e-41f5-b319-7e3e90f425d8
minio3_1 | Error: Bucket not found: .minio.sys/background-ops
minio3_1 | 2: cmd/data-usage.go:109:cmd.runDataUsageInfo()
minio3_1 | 1: cmd/data-usage.go:56:cmd.runDataUsageInfoUpdateRoutine()
This commit fixes the typo.
Adding mutex slows down the crawler to avoid large
spikes in CPU, also add millisecond interval jitter
in calculation of disk usage to slow down the spikes
further.
This is to fix a situation where an object name incorrectly
is sent with '//' in its path heirarchy, we should reject
such object names because they may be hashed to a set where
the object might not originally belong because, this can
cause situations where once object is uploaded we cannot
delete it anymore.
Fixes#8873
This commit fixes typos in the displayed server info
w.r.t. the KMS and removes the update status.
For more information about why the update status
is removed see: PR #8943
This commit removes the `Update` functionality
from the admin API. While this is technically
a breaking change I think this will not cause
any harm because:
- The KMS admin API is not complete, yet.
At the moment only the status can be fetched.
- The `mc` integration hasn't been merged yet.
So no `mc` client could have used this API
in the past.
The `Update`/`Rewrap` status is not useful anymore.
It provided a way to migrate from one master key version
to another. However, KES does not support the concept of
key versions. Instead, key migration should be implemented
as migration from one master key to another.
Basically, the `Update` functionality has been implemented just
for Vault.
- pkg/bucket/encryption provides support for handling bucket
encryption configuration
- changes under cmd/ provide support for AES256 algorithm only
Co-Authored-By: Poorna <poornas@users.noreply.github.com>
Co-authored-by: Harshavardhana <harsha@minio.io>
XL crawling wrongly returns a zero buckets count when
there are no objects uploaded in the server yet. The reason is
data of the crawler of posix returns invalid result when all
disks has zero objects.
A simple fix is to always pick the crawling result of the first
disk but choose over the result of the disk which has the most
objects in it.
looks like 1024 buffer size is not enough in
all situations, use 8192 instead which
can satisfy all the rare situations that
may arise in base64 decoding.
multi-delete API failed with write quorum errors
under following situations
- list of files requested for delete doesn't exist
anymore can lead to quorum errors and failure
- due to usage of query param for paths, for really
long paths MinIO server rejects these requests as
malformed as unexpected.
This was reproduced with warp
The server info handler makes a http connection to other
nodes to check if they are up but does not load the custom
CAs in ~/.minio/certs/CAs.
This commit fix it.
Co-authored-by: Harshavardhana <harsha@minio.io>
JWT parsing is simplified by using a custom claim
data structure such as MapClaims{}, also writes
a custom Unmarshaller for faster unmarshalling.
- Avoid as much reflections as possible
- Provide the right types for functions as much
as possible
- Avoid strings.Join, strings.Split to reduce
allocations, rely on indexes directly.
For 'snapshot' type profiles, record a 'before' profile that can be used
as `go tool pprof -base=before ...` to compare before and after.
"Before" profiles are included in the zipped package.
[`runtime.MemProfileRate`](https://golang.org/pkg/runtime/#pkg-variables)
should not be updated while the application is running, so we set it at startup.
Co-authored-by: Harshavardhana <harsha@minio.io>
On every restart of the server, usage was being
calculated which is not useful instead wait for
sufficient time to start the crawling routine.
This PR also avoids lots of double allocations
through strings, optimizes usage of string builders
and also avoids crawling through symbolic links.
Fixes#8844
Choosing maxAllowedIOError is arbitrary and
prone to errors, when drives might be perfectly
capable of taking I/O with only few locations
return I/O error. This is a hindrance of sort
where backend filesystems like ZFS can automatically
fix and handle these scenarios.
The added problem with current approach that we
take the drive offline, making it virtually impossible
to bring it online without restart the server which
is not desirable on a busy cluster. Remove this state
such that let the backend return error appropriately
to caller and let the caller decide what to do with
the error.
return http.ErrServerClosed with proper body when
server is shutting down, allowing more context instead
of just returning '503' which doesn't mean the same
thing.
code of this form is always racy, when the
map itself is being written to as well
```
func (r Map) retMap() map[string]string {
.. lock ..
return r.internalMap
}
func (r Map) addMap(k, v string) {
.. lock ..
r.internalMap[k] = v
}
```
Anyone reading from `retMap()` is not protected
because of locking and we need to make sure
to avoid code in this manner. Always safe to
copy the map and return.
Zone abstraction of object layer was returning `nil`
incorrectly under situations where disk healing is
not required. Returning `nil` is considered as healing
successful, which leads to unexpected ReloadFormat()
peer notification calls during startup.
This PR fixes this behavior properly for zones.
Meta volumes directories, tmp/, background-ops/, etc..
undr .minio.sys are created when disks are formatted
but also when the cluster is started.
However using MakeVolBulk() is not appropriate in the
case of a user migrating from a version which does not
have .minio.sys/background-ops/. The reason is that
MakeVolBulk() exits early when an error is occured:
errVolumeExists in this case, which is expected since
some directories such as tmp/ already exist.
This commit will avoid use MakeVolBulk and use MakeVol
instead.
Also the PR will make each node creates meta volumes
in its local disks and stop relying on the first disk
since the first node could be offline.
instead perform a liveness check call to
verify if server is online and print relevant
errors.
Also introduce a StorageErr string error type
instead of errors.New() deprecate usage of
VerifyFileError, DeleteFileError for gob,
change in datastructure also requires bump in
storage REST version to v13.
Fixes#8811
Enabling the memory profiling has a significant impact on performance.
Reduce the profiling rate by 2 orders of magnitude. It is still 128x smaller than default so it should be plenty.
object lock config is enabled for a bucket.
Creating a bucket with object lock configuration
enabled does not automatically cause WORM protection
to be applied. PUT operation needs to specifically
request object locking or bucket has to have default
retention settings configured.
Fixes regression introduced in #8657
When formatting a set validate if a host failure will likely lead to data loss.
While we don't know what config will be set in the future
evaluate to our best knowledge, assuming default settings.
X-Cache sets cache status of HIT if object is
served from the disk cache, or MISS otherwise.
X-Cache-Lookup is set to HIT if object was found
in the cache even if not served (for e.g. if cache
entry was invalidated by ETag verification)
A new key was added in identity_openid recently
required explicitly for client to set the optional
value without that it would be empty, handle this
appropriately.
Fixes#8787
Use reference format to initialize lockers
during startup, also handle `nil` for NetLocker
in dsync and remove *errorLocker* implementation
Add further tuning parameters such as
- DialTimeout is now 15 seconds from 30 seconds
- KeepAliveTimeout is not 20 seconds, 5 seconds
more than default 15 seconds
- ResponseHeaderTimeout to 10 seconds
- ExpectContinueTimeout is reduced to 3 seconds
- DualStack is enabled by default remove setting
it to `true`
- Reduce IdleConnTimeout to 30 seconds from
1 minute to avoid idleConn build up
Fixes#8773
- Stop spawning store replay routines when testing the notification targets
- Properly honor the target.Close() to clean the resources used
Fixes#8707
Co-authored-by: Harshavardhana <harsha@minio.io>
In certain organizations policy claim names
can be not just 'policy' but also things like
'roles', the value of this field might also
be *string* or *[]string* support this as well
In this PR we are still not supporting multiple
policies per STS account which will require a
more comprehensive change.
Exponential backoff does not seem like a good fit for
this function since we can expect a few roundtrips on
initial startup.
This retry loop get slow pretty quickly with initial
wait being 1 second and each try being double the
wait until 30 seconds is reached.
Instead simply try 2 times per second.
This PR adds jsoniter package to replace encoding/json
in places where faster json unmarshal is necessary
whenever input JSON is large enough.
Some benchmarking comparison between jsoniter and enconding/json
benchmark old MB/s new MB/s speedup
BenchmarkParseUnmarshal/N10-4 110.02 331.17 3.01x
BenchmarkParseUnmarshal/N100-4 125.74 524.09 4.17x
BenchmarkParseUnmarshal/N500-4 131.68 542.60 4.12x
BenchmarkParseUnmarshal/N1000-4 133.93 514.88 3.84x
BenchmarkParseUnmarshal/N5000-4 122.10 415.36 3.40x
BenchmarkParseUnmarshal/N10000-4 132.13 403.90 3.06x
Fixes scenario where zones are appropriately
handled, along with supporting overriding set
count. The new fix also ensures that we handle
the various setup types properly.
Update documentation to properly indicate the
behavior.
Fixes#8750
Co-authored-by: Nitish Tiwari <nitish@minio.io>
Currently when connections to vault fail, client
perpetually retries this leads to assumptions that
the server has issues and masks the problem.
Re-purpose *crypto.Error* type to send appropriate
errors back to the client.
In existing functionality we simply return a generic
error such as "MalformedPolicy" which indicates just
a generic string "invalid resource" which is not very
meaningful when there might be multiple types of errors
during policy parsing. This PR ensures that we send
these errors back to client to indicate the actual
error, brings in two concrete types such as
- iampolicy.Error
- policy.Error
Refer #8202
minio server /data{1..4} shows an error about inability to bind a port, though
the real problem is /data{1..4} cannot be created because of the lack of
permissions.
This commit fix the behavior.
- We should declare a cluster ready even if read quorum is achieved (atleast n/2 disks are online).
- Such that, all the zones should have enough read quorum. Thus making the cluster ready for reads.
We had messy cyclical dependency problem with `mc`
due to dependencies in pkg/console, moved the pkg/console
to minio for more control and also to avoid any further
cyclical dependencies of `mc` clobbering up the
dependencies on server.
Fixes#8659
If two distinct clusters are started with different domains
along with single common domain, this situation was leading
to conflicting buckets getting created on different clusters
To avoid this do not prematurely error out if the key has no
entries, let the caller decide on which entry matches and
which entry is valid. This allows support for MINIO_DOMAIN
with one common domain, but each cluster may have their own
domains.
Fixes#8705
This is to ensure that when we have multiple tenants
deployed all sharing the same etcd for global bucket
should avoid listing each others buckets, this leads
to information leak which should be avoided unless
etcd is not namespaced for IAM assets in which case
it can be assumed that its a federated setup.
Federated setup and namespaced IAM assets on etcd
is not supported since namespacing is only useful
when you wish to separate the tenants as isolated
instances of MinIO.
This PR allows a new type of behavior, primarily
driven by the usecase of m3(mkube) multi-tenant
deployments with global bucket support.
Currently all bucket events are sent to all watchers
with matching prefix and event names, this becomes
problematic and prone to performance issues, fix this
situation by filtering based on buckets as well.
This PR fixes the issue where we might allow policy changes
for temporary credentials out of band, this situation allows
privilege escalation for those temporary credentials. We
should disallow any external actions on temporary creds
as a practice and we should clearly differentiate which
are static and which are temporary credentials.
Refer #8667
Changes in IP underneath are dynamic in replica sets
with multiple tenants, so deploying in that fashion
will not work until we wait for atleast one participatory
server to be local.
This PR also ensures that multi-tenant zone expansion also
works in replica set k8s deployments.
Introduces a new ENV `KUBERNETES_REPLICA_SET` check to call
appropriate code paths.
Continuation from #8629 which basically broke
zone deployments on k8s statefulset environment
due to incorrect assumptions which made it work
on replicated set.
Fix this properly such that this container works
for both replicated set and stateful set deployment
This commit removes github.com/minio/kes as
a dependency and implements the necessary
client-side functionality without relying
on the KES project.
This resolves the licensing issue since
KES is licensed under AGPL while MinIO
is licensed under Apache.
With this PR,cache eviction will continue until
no LRU entries older than an hour can be cache
evicted or sufficient percentage of disk space
has been reclaimed.
This ensures that we can update the
- .minio.sys is updated for accounting/data usage purposes
- .minio.sys is updated to indicate if backend is encrypted
or not.
The approach is that now safe mode is only invoked when
we cannot read the config or under some catastrophic
situations, but not under situations when config entries
are invalid or unreachable. This allows for maximum
availability for MinIO and not fail on our users unlike
most of our historical releases.
This commit adds support for the minio/kes KMS.
See: https://github.com/minio/kes
In particular you can configure it as KMS by:
- `export MINIO_KMS_KES_ENDPOINT=` // Server URL
- `export MINIO_KMS_KES_KEY_FILE=` // TLS client private key
- `export MINIO_KMS_KES_CERT_FILE=` // TLS client certificate
- `export MINIO_KMS_KES_CA_PATH=` // Root CAs issuing server cert
- `export MINIO_KMS_KES_KEY_NAME=` // The name of the (default)
master key
Admin data usage info API returns the following
(Only FS & XL, for now)
- Number of buckets
- Number of objects
- The total size of objects
- Objects histogram
- Bucket sizes
In replica sets, hosts resolve to localhost
IP automatically until the deployment fully
comes up. To avoid this issue we need to
wait for such resolution.
Final update to all messages across sub-systems
after final review, the only change here is that
NATS now has TLS and TLSSkipVerify to be consistent
for all other notification targets.
This PR adds support below metrics
- Cache Hit Count
- Cache Miss Count
- Data served from Cache (in Bytes)
- Bytes received from AWS S3
- Bytes sent to AWS S3
- Number of requests sent to AWS S3
Fixes#8549
Fixes an issue reported by @klauspost and @vadmeste
This PR also allows users to expand their clusters
from single node XL deployment to distributed mode.
Currently, we use the top-level prefix "config/"
for all our IAM assets, instead of to provide
tenant-level separation bring 'path_prefix'
to namespace the access properly.
Fixes#8567
StorageInfo() call is supposed to give each
server/disk information independently, rely
on this appropriately so that `mc admin info server`
gets correct information all the time.
Regression from #8509 which changes objectsToDelete entry
from a list to map. This will cause index out of range
panic if object is not selected for delete.
level - this PR builds on #8120 which
added PutBucketObjectLockConfiguration and
GetBucketObjectLockConfiguration APIS
This PR implements PutObjectRetention,
GetObjectRetention API and enhances
PUT and GET API operations to display
governance metadata if permissions allow.
- added ability to specify CA for self-signed certificates
- added option to authenticate using client certificates
- added unit tests for nats connections
We should only read ahead if we are reading big files. We enable it for files >= 16MB.
Benchmark on 64KB objects.
Before:
```
Operation: GET
Errors: 0
Average: 59.976s, 87.13 MB/s, 1394.07 ops ended/s.
Fastest: 1s, 90.99 MB/s, 1455.00 ops ended/s.
50% Median: 1s, 87.53 MB/s, 1401.00 ops ended/s.
Slowest: 1s, 81.39 MB/s, 1301.00 ops ended/s.
```
After:
```
Operation: GET
Errors: 0
Average: 59.992s, 207.99 MB/s, 3327.85 ops ended/s.
Fastest: 1s, 219.20 MB/s, 3507.00 ops ended/s.
50% Median: 1s, 210.54 MB/s, 3368.00 ops ended/s.
Slowest: 1s, 179.14 MB/s, 2865.00 ops ended/s.
```
The 64KB buffer is actually a small disadvantage for this case, but I believe it will be better in general than no buffer.
- Migrate and save only settings which are enabled
- Rename logger_http to logger_webhook and
logger_http_audit to audit_webhook
- No more pretty printing comments, comment
is a key=value pair now.
- Avoid quotes on values which do not have space in them
- `state="on"` is implicit for all SetConfigKV unless
specified explicitly as `state="off"`
- Disabled IAM users should be disabled always
The code does not properly set a new deployemnt ID when not present
in format.json: it loops twice without releasing write lock on format.json
causing an infinite locking error on the same file.
This commit fixes and simplifies a little the code.
This PR implements locking from a global entity into
a more localized set level entity, allowing for locks
to be held only on the resources which are writing
to a collection of disks rather than a global level.
In this process this PR also removes the top-level
limit of 32 nodes to an unlimited number of nodes. This
is a precursor change before bring in bucket expansion.
This PR also fixes issues related to
- Add proper newline for `mc admin config get` output
for more than one targets
- Fixes issue of temporary user credentials to have
consistent output
- Fixes a crash when setting a key with empty values
- Fixes a parsing issue with `mc admin config history`
- Fixes gateway ENV handling for etcd server and gateway
This PR fixes issues found in config migration
- StorageClass migration error when rrs is empty
- Plain-text migration of older config
- Do not run in safe mode with incorrect credentials
- Update logger_http documentation for _STATE env
Refer more reported issues at #8434
This PR refactors object layer handling such
that upon failure in sub-system initialization
server reaches a stage of safe-mode operation
wherein only certain API operations are enabled
and available.
This allows for fixing many scenarios such as
- incorrect configuration in vault, etcd,
notification targets
- missing files, incomplete config migrations
unable to read encrypted content etc
- any other issues related to notification,
policies, lifecycle etc
This PR brings support for `history` list to
list in the following agreed format
```
~ mc admin config history list -n 2 myminio
RestoreId: df0ebb1e-69b0-4043-b9dd-ab54508f2897
Date: Mon, 04 Nov 2019 17:27:27 GMT
region name="us-east-1" state="on"
region name="us-east-1" state="on"
region name="us-east-1" state="on"
region name="us-east-1" state="on"
RestoreId: ecc6873a-0ed3-41f9-b03e-a2a1bab48b5f
Date: Mon, 04 Nov 2019 17:28:23 GMT
region name=us-east-1 state=off
```
This PR also moves the help templating and coloring to
fully `mc` side instead than `madmin` API.
This PR adds code to appropriately handle versioning issues
that come up quite constantly across our API changes. Currently
we were also routing our requests wrong which sort of made it
harder to write a consistent error handling code to appropriately
reject or honor requests.
This PR potentially fixes issues
- old mc is used against new minio release which is incompatible
returns an appropriate for client action.
- any older servers talking to each other, report appropriate error
- incompatible peer servers should report error and reject the calls
with appropriate error
This is to avoid making calls to backend and requiring
gateways to allow permissions for ListBuckets() operation
just for Liveness checks, we can avoid this and make
our liveness checks to be more performant.
- Supports migrating only when the credential ENVs are set,
so any FS mode deployments which do not have ENVs set will
continue to remain as is.
- Credential ENVs can be rotated using MINIO_ACCESS_KEY_OLD
and MINIO_SECRET_KEY_OLD envs, in such scenarios it allowed
to rotate the encrypted content to a new admin key.
This commit replaces the returned error message by
the hardware info handler from `Method-Not-Allowed`
to `Bad-Request` since the current HTTP error is not
correct according to the HTTP spec.
In particular:
```
The origin server MUST generate an Allow header field
in a 405 response containing a list of the target
resource's currently supported methods.
```
From: https://tools.ietf.org/html/rfc7231#section-6.5.5
- This PR allows config KVS to be validated properly
without being affected by ENV overrides, rejects
invalid values during set operation
- Expands unit tests and refactors the error handling
for notification targets, returns error instead of
ignoring targets for invalid KVS
- Does all the prep-work for implementing safe-mode
style operation for MinIO server, introduces a new
global variable to toggle safe mode based operations
NOTE: this PR itself doesn't provide safe mode operations
The new auto healing model selects one node always responsible
for auto-healing the whole cluster, erasure set by erasure set.
If that node dies, another node will be elected as a leading
operator to perform healing.
This code also adds a goroutine which checks each 10 minutes
if there are any new unformatted disks and performs its healing
in that case, only the erasure set which has the new disk will
be healed.
While Tracing requests on server, type assertion on logger.ResponseWriter
caused nil pointer exception because of recordAPIStats{} being
used as ResponseWriter. This PR avoids the type assertion and
initializes a new logger.ResponseWriter.
Fixes regression introduced in #8003
- adding oauth support to MinIO browser (#8400) by @kanagaraj
- supports multi-line get/set/del for all config fields
- add support for comments, allow toggle
- add extensive validation of config before saving
- support MinIO browser to support proper claims, using STS tokens
- env support for all config parameters, legacy envs are also
supported with all documentation now pointing to latest ENVs
- preserve accessKey/secretKey from FS mode setups
- add history support implements three APIs
- ClearHistory
- RestoreHistory
- ListHistory
- add help command support for each config parameters
- all the bug fixes after migration to KV, and other bug
fixes encountered during testing.
The measures are consolidated to the following metrics
- `disk_storage_used` : Disk space used by the disk.
- `disk_storage_available`: Available disk space left on the disk.
- `disk_storage_total`: Total disk space on the disk.
- `disks_offline`: Total number of offline disks in current MinIO instance.
- `disks_total`: Total number of disks in current MinIO instance.
- `s3_requests_total`: Total number of s3 requests in current MinIO instance.
- `s3_errors_total`: Total number of errors in s3 requests in current MinIO instance.
- `s3_requests_current`: Total number of active s3 requests in current MinIO instance.
- `internode_rx_bytes_total`: Total number of internode bytes received by current MinIO server instance.
- `internode_tx_bytes_total`: Total number of bytes sent to the other nodes by current MinIO server instance.
- `s3_rx_bytes_total`: Total number of s3 bytes received by current MinIO server instance.
- `s3_tx_bytes_total`: Total number of s3 bytes sent by current MinIO server instance.
- `minio_version_info`: Current MinIO version with commit-id.
- `s3_ttfb_seconds_bucket`: Histogram that holds the latency information of the requests.
And this PR also modifies the current StorageInfo queries
- Decouples StorageInfo from ServerInfo .
- StorageInfo is enhanced to give endpoint information.
NOTE: ADMIN API VERSION IS BUMPED UP IN THIS PR
Fixes#7873
xl.isObject() returns 'nil' for not found disks when
calculating the existance of xl.json for a given object,
which what StatFile() is also doing (setting nil) if
xl.json exists.
This commit avoids this confusion by setting errDiskNotFound
error when the storage disk is not found.
When `mc admin user add` is attempted in gateway mode without
etcd setup, NoSuchBucket error is returned instead of MethodNotAllowed.
Regression from commit - e48005ddc7
Background append creates a temporary file which appends
uploaded parts as long as they are available, but when a
client stops the upload, the temporary file is not removed
by any way.
This commit removes the temporary file when the server does
its regular removing stale multipart uploads.
specific errors, `application` errors or `all` by default.
console logging on server by default lists all logs -
enhance admin console API to accept `type` as query parameter to
subscribe to application/minio logs.
- This PR fixes situation to avoid underflow, this is possible
because of disconnected operations in replay/sendEvents
- Hold right locks if Del() operation is performed in Get()
- Remove panic in the code and use loggerOnce
- Remove Timer and instead use Ticker instead for proper ticks
On Kubernetes/Docker setups DNS resolves inappropriately
sometimes where there are situations same endpoints with
multiple disks come online indicating either one of them
is local and some of them are not local. This situation
can never happen and its only a possibility in orchestrated
deployments with dynamic DNS. Following code ensures that we
treat if one of the endpoint says its local for a given host
it is true for all endpoints for the same host. Following code
ensures that this assumption is true and it works in all
scenarios and it is safe to assume for a given host.
This PR also adds validation such that we do not crash the
server if there are bugs in the endpoints list in dsync
initialization.
Thanks to Daniel Valdivia <hola@danielvaldivia.com> for
reproducing this, this fix is needed as part of the
https://github.com/minio/m3 project.
This change is related to larger config migration PR
change, this is a first stage change to move our
configs to `cmd/config/` - divided into its subsystems
Current master repeatedly calls ListBuckets() during
initialization of multiple sub-systems
Use single ListBuckets() call for each sub-system as
follows
- LifeCycle
- Policy
- Notification
- Heal if the part.1 is truncated from its original size
- Heal if the part.1 fails while being verified in between
- Heal if the part.1 fails while being at a certain offset
Other cleanups include make sure to flush the HTTP responses
properly from storage-rest-server, avoid using 'defer' to
improve call latency. 'defer' incurs latency avoid them
in our hot-paths such as storage-rest handlers.
Fixes#8319
Minio V2 listing uses object names/prefixes as continuation tokens. This
is problematic when object names contain some characters that are forbidden
in XML documents. This PR will use base64 encoded form of continuation
and next continuation tokens to address that corner case.
errors.errorString() cannot be marshalled by gob
encoder, so using a slice of []error would fail
to be encoded. This leads to no errors being
generated instead gob.Decoder on the storage-client
would see an io.EOF
To avoid such bugs introduce a typed error for
handling such translations and register this type
for gob encoding support.
On objects bigger than 100MiB can have a corrupted object
stored due to partial blockListing attempted right after
each blocks uploaded. Simplify this code to ensure that
all the blocks successfully uploaded are committed right
away.
This PR also updates the azure-sdk-go to latest release.
- Choose a unique uuid such that under situations of duplicate
mounts we do not append to an existing json entry.
- Avoid AppendFile instead use WriteAll() to write the entire
byte array atomically.
When url encoding is passed in v2 listing handler, continuationToken
and nextContinuationToken needs to be encoded. The reason is that
both represents an object name/prefix in Minio server and it could
contain a character unsupported by XML specification.
This PR additionally also adds support for missing
- Session policy support for AD/LDAP
- Add API request/response parameters detail
- Update example to take ldap username,
password input from the command line
- Fixes session policy handling for
ClientGrants and WebIdentity
This commit removes the SSE-S3 key rotation functionality
from CopyObject since there will be a dedicated Admin-API
for this purpose.
Also update the security documentation to link to mc and
the admin documentation.
This commit allows the MinIO server to parse the metadata if:
- either the `X-Minio-Internal-Server-Side-Encryption-S3-Key-Id`
and the `X-Minio-Internal-Server-Side-Encryption-S3-Kms-Sealed-Key`
entries are present.
- or *both* headers are not present.
This is in service to support a K/V data key store.
In commit a8296445ad we changed the code to handle
some corner cases on ARM and other platforms, this
PR just avoids the return for unknown filetypes
prematurely and let the name be populated appropriately.
This fixes bug for older XFS implementations such as
in Ubuntu 14.04
This commit fixes a subtle bug that (probably)
caused an issue affecting encrypted multipart objects.
When a cluster has no quorum this bug causes `ListObjectParts`
to return nil as error instead of a quorum error.
Thanks to @harshavardhana for detecting this.
This PR changes cache on PUT behavior to background fill the cache
after PutObject completes. This will avoid concurrency issues as in #8219.
Added cleanup of partially filled cache to prevent cache corruption
- Fixes#8208
VerifyFile in the distributed setup does not work with
the non streaming highway hash. The reason is that the
internode mux router did not expect `storageRESTBitrotHash`
parameter.
endpoint.IsLocal will not have .Host entries so
using them to skip double entries will never work.
change the code such that we look for endpoint.Host
outside of endpoint.IsLocal logic to skip double
hosts appropriately.
Move these functions to their appropriate file.
- ListObjectsHeal should list only objects
which need healing, not the entire namespace.
- DeleteObjects() to be used to delete 1000s of
objects in bulk instead of serially.
Add LDAP based users-groups system
This change adds support to integrate an LDAP server for user
authentication. This works via a custom STS API for LDAP. Each user
accessing the MinIO who can be authenticated via LDAP receives
temporary credentials to access the MinIO server.
LDAP is enabled only over TLS.
User groups are also supported via LDAP. The administrator may
configure an LDAP search query to find the group attribute of a user -
this may correspond to any attribute in the LDAP tree (that the user
has access to view). One or more groups may be returned by such a
query.
A group is mapped to an IAM policy in the usual way, and the server
enforces a policy corresponding to all the groups and the user's own
mapped policy.
When LDAP is configured, the internal MinIO users system is disabled.
It looks like from implementation point of view fastjson
parser pool doesn't behave the same way as expected
when dealing many `xl.json` from multiple disks.
The fastjson parser pool usage ends up returning incorrect
xl.json entries for checksums, with references pointing
to older entries. This led to the subtle bug where checksum
info is duplicated from a previous xl.json read of a different
file from different disk.
With this PR, liveness check responds with 200 OK with "server-not-
initialized" header while objectLayer gets initialized. The header
is removed as objectLayer is initialized. This is to allow
MinIO distributed cluster to get started when running on an
orchestration platforms like Docker Swarm.
This PR also updates sample Swarm yaml files to use correct values
for healthcheck fields.
Fixes#8140
This commit adds an admin API route and handler for
requesting status information about a KMS key.
Therefore, the client specifies the KMS key ID (when
empty / not set the server takes the currently configured
default key-ID) and the server tries to perform a dummy encryption,
re-wrap and decryption operation. If all three succeed we know that
the server can access the KMS and has permissions to generate, re-wrap
and decrypt data keys (policy is set correctly).
This is a defensive change to avoid any future issues,
from this part of the code. New change also ensures
to populate UUID if present for the right disk.
This commit fixes the web ZIP download handler for
encrypted objects. The decryption logic has moved into
`getObjectNInfo`. So trying to decrypt the (already decrypted)
content again in the ZIP handler obviously causes an error.
This commit fixes this by removing the decryption logic from the
the handler.
Fixes#7965
The underlying errors are important, for IAM
requirements and should wait appropriately at
the caller level, this allows for distributed
setups to run properly and not fail prematurely
during startup.
Also additionally fix the onlineDisk counting
The change now is to ensure that we take custom URL as
well for updating the deployment, this is required for
hotfix deliveries for certain deployments - other than
the community release.
This commit changes the previous work d65a2c6725
with newer set of requirements.
Also deprecates PeerUptime()
net.Error is very unreliable in providing better error
handling, we need to ensure that we always have a fallback
option in case of network failures.
This fixes an important issue in our distributed server
setups when one of the servers is down, all deployments
out there are recommended to upgrade after this fix is
merged to ensure that availability is not lost.
Fixes#8127Fixes#8016Fixes#7964
This API implementation simply behaves like listObjects()
but returns back single version for each object, this
implementation should be considered dummy it is only
meant for some applications which rely on this.
This is to avoid using unsafe.Pointer type
code dependency for MinIO, this causes
crashes on ARM64 platforms
Refer #8005 collection of runtime crashes due
to unsafe.Pointer usage incorrectly. We have
seen issues like this before when using
jsoniter library in the past.
This PR hopes to fix this using fastjson
Add better dynamic timeouts for locks, also
add jitters before launching daily sweep to ensure
that not all the servers in distributed setup
are not trying to hold locks to begin the sweep
round.
Also, add enough delay for incoming requests based
on totalSetCount*totalDriveCount.
A possible fix for #8071
It is observed that when `mc admin trace` is being
used due to ResponseWriter wrapper, we loose information
about statusCode,statusText for audit logging.
This PR fixes this behavior
This avoids a network call, also fixes an issue
when empty paths are passed the underlying call
fails with "405 Method Not Allowed".
This is reproducible when you are deleting a
non-existent object.
Fixes#8083
Add API to set policy mapping for a user or group
Contains a breaking Admin APIs change.
- Also enforce all applicable policies
- Removes the previous /set-user-policy API
Bump up peerRESTVersion
Add get user info API to show groups of a user
* Cleanup ui-errors and print proper error messages
Change HELP to HINT instead, handle more error
cases when starting up MinIO. One such is related
to #8048
* Apply suggestions from code review
When a peer client which higher version sends a request to a peer
server with lower version, the returned status code is 200 OK instead
of 405 code. The reason is that the peer client request reaches the
browser handler, which registers itself by '/minio' route but without
any other constraints. Adding filtering by user agent header to the
browser route so internal requests to old endpoints versions return
405 error code.
This is a behavior change from AWS S3, but it is done with
better judgment on our end to allow the listing of buckets only
which user has access to.
The advantage is this declutters the UI for users and only
lists bucket which they have access to.
Precursor for this feature to be applicable is a policy
must have the following actions
```
s3:ListAllMyBuckets
```
and
```
s3:ListBucket
```
enabled in the policy.
Fixes#7458Fixes#7573Fixes#7938Fixes#6934Fixes#6265Fixes#6630
This will allow the cache to consistently work for
server and gateways. Range GET requests will
be cached in the background after the request
is served from the backend.
- All cached content is automatically bitrot protected.
- Avoid ETag verification if a cache-control header
is set and the cached content is still valid.
- This PR changes the cache backend format, and all existing
content will be migrated to the new format. Until the data is
migrated completely, all content will be served from the backend.
Refactor the Dirent parsing code such that when we
calculate offsets are correct based on the platform
This PR fixes a silent potential crash on ARM
architecture.
This commit fixes a DoS issue that is caused by an incorrect
SHA-256 content verification during STS requests.
Before that fix clients could write arbitrary many bytes
to the server memory. This commit fixes this by limiting the
request body size.
This change adds admin APIs and IAM subsystem APIs to:
- add or remove members to a group (group addition and deletion is
implicit on add and remove)
- enable/disable a group
- list and fetch group info
When checking if federation is necessary, the code compares
the SRV record stored in etcd against the list of endpoints
that the MinIO server is exposing. If there is an intersection
in this list the request is forwarded.
The SRV record includes both the host and the port, but the
intersection check previously only looked at the IP address. This
would prevent federation from working in situations where the endpoint
IP is the same for multiple MinIO servers. Some examples of where this
can occur are:
- running mulitiple copies of MinIO on the same host
- using multiple MinIO servers behind a NAT with port-forwarding
This commit adds a new method `UpdateKey` to the KMS
interface.
The purpose of `UpdateKey` is to re-wrap an encrypted
data key (the key generated & encrypted with a master key by e.g.
Vault).
For example, consider Vault with a master key ID: `master-key-1`
and an encrypted data key `E(dk)` for a particular object. The
data key `dk` has been generated randomly when the object was created.
Now, the KMS operator may "rotate" the master key `master-key-1`.
However, the KMS cannot forget the "old" value of that master key
since there is still an object that requires `dk`, and therefore,
the `D(E(dk))`.
With the `UpdateKey` method call MinIO can ask the KMS to decrypt
`E(dk)` with the old key (internally) and re-encrypted `dk` with
the new master key value: `E'(dk)`.
However, this operation only works for the same master key ID.
When rotating the data key (replacing it with a new one) then
we perform a `UnsealKey` operation with the 1st master key ID
and then a `GenerateKey` operation with the 2nd master key ID.
This commit also updates the KMS documentation and removes
the `encrypt` policy entry (we don't use `encrypt`) and
add a policy entry for `rewarp`.
After some extensive refactors, it turned out empty directories
are not healed and heal status is also not reported correctly.
This commit fixes it and adds the appropriate unit tests
This PR fixes relying on r.Context().Done()
by setting
```
Connection: "close"
```
HTTP Header, this has detrimental issues for
client side connection pooling. Since this
header explicitly tells clients to turn-off
connection pooling. This causing pro-active
connections to be closed leaving many conn's
in TIME_WAIT state. This can be observed with
`mc admin trace -a` when running distributed
setup.
This PR also fixes tracing filtering issue
when bucket names have `minio` as prefixes,
trace was erroneously ignoring them.
Golang proactively prints this error
`http: proxy error: context canceled`
when a request arrived to the current deployment and
redirected to another deployment in a federated setup.
Since this error can confuse users, this commit will
just hide it.
Allow renaming/editing a notification config. By replying with
a successful GetBucketNotification response, without checking
for any missing config ARN in targetList.
Fixes#7650
Related to #7982, this PR refactors the code
such that we validate the OPA or JWKS in a
common place.
This is also a refactor which is already done
in the new config migration change. Attempt
to avoid any network I/O during Unmarshal of
JSON from disk, instead do it later when
updating the in-memory data structure.
In situations such as when client uploading data,
prematurely disconnects from server such as pressing
ctrl-c before uploading all the data. Under this
situation in distributed setup we prematurely
disconnect disks causing a reconnect loop. This has
an adverse affect we end up leaving a lot of files
in temporary location which ideally should have been
cleaned up when Put() prematurely fails.
This is also a regression which got introduced in #7610
- Policy mapping is now at `config/iam/policydb/users/myuser1.json`
and includes version.
- User identity file is now versioned.
- Migrate old data to the new format.
Calling ListMultipartUploads fails if an upload is aborted while a
part is being uploaded because the directory for the upload exists
(since fsRenameFile ends up calling os.MkdirAll) but the meta JSON file
doesn't. To fix this we make sure an upload hasn't been aborted during
PutObjectPart by checking the existence of the directory for the upload
while moving the temporary part file into it.
This PR is based off @sinhaashish's PR for object lifecycle
management, which includes support only for,
- Expiration of object
- Filter using object prefix (_not_ object tags)
N B the code for actual expiration of objects will be included in a
subsequent PR.
Current code already allows users to GetPolicy/SetPolicy
there was a missing code in ListAllBucketPolicies to allow
access, this fixes this behavior.
Fixes#7913
The fix in #7646 introduced a regression which
was left unnoticed, the fix didn't work for
sub-commands unfortunately. This fixes it
by moving v1.21.0 version of the minio/cli
package.
Fixes#7924
posix.VerifyFile() doesn't know how to check if a file
is corrupted if that file is empty. We do have the part
size in xl.json so we pass it to VerifyFile to return
an error so healing empty parts can work properly.
When MinIO is behind a proxy, proxies end up killing
clients when no data is seen on the connection, adding
the right content-type ensures that proxies do not come
in the way.
Update prompt shows some weird characters under Windows, the reason
is that go-prompt is used to show a yes/no prompt, since go-prompt
does not seem to have a way to support color/fatih, this PR will
implements its own yes/no prompt with the correct text coloration.
This allows for canonicalization of the strings
throughout our code and provides a common space
for all these constants to reside.
This list is rather non-exhaustive but captures
all the headers used in AWS S3 API operations
r.URL.Path is empty when HEAD bucket with virtual
DNS requests come in since bucket is now part of
r.Host, we should use our domain names and fetch
the right bucket/object names.
This fixes an really old issue in our federation
setups.
This API returns the information related to the self healing routine.
For the moment, it returns:
- The total number of objects that are scanned
- The last time when an item was scanned
- return all objects in web-handlers listObjects response
- added local pagination to object list ui
- also fixed infinite loader and removed unused fields
While checking for port availability, ip address should be included.
When a machine has multiple ip addresses, multiple minio instances
or some other applications can be run on same port but different
ip address.
Fixes#7685
This PR adds support for adding session policies
for further restrictions on STS credentials, useful
in situations when applications want to generate
creds for multiple interested parties with different
set of policy restrictions.
This session policy is not mandatory, but optional.
Fixes#7732
This commit relaxes the restriction that the MinIO gateway
does not accept SSE-KMS headers. Now, the S3 gateway allows
SSE-KMS headers for PUT and MULTIPART PUT requests and forwards them
to the S3 gateway backend (AWS). This is considered SSE pass-through
mode.
Fixes#7753
Previously the read/write lock applied both for gateway use cases as
well the object store use case. Nothing from sys is touched or looked
at in the gateway usecase though, so we don't need to lock. Don't lock
to make the gateway policy getting a little more efficient, particularly
as where this is called from (checkRequestAuthType) is quite common.
etcd when used in federated setups, currently
mandates that all clusters should have same
config.json, which is too restrictive and makes
federation a restrictive environment.
This change makes it apparent that each cluster
needs to be independently managed if necessary
from `mc admin info` command line.
Each cluster with in federation can have their
own root credentials and as well as separate
regions. This way buckets get further restrictions
and allows for root creds to be not common
across clusters/data centers.
Existing data in etcd gets migrated to backend
on each clusters, upon start. Once done
users can change their config entries
independently.
- Background Heal routine receives heal requests from a channel, either to
heal format, buckets or objects
- Daily sweeper lists all objects in all buckets, these objects
don't necessarly have read quorum so they can be removed if
these objects are unhealable
- Heal daily ops receives objects from the daily sweeper
and send them to the heal routine.
Inconsistencies can arise after applying bucket policies in
gateway mode, since all gateway instances do not share a
common shared state. This is by design to keep gateway as
shared nothing architecture.
This PR fixes such inconsistencies by reloading policy
if any from the backend.
Fixes#7723
Consider errors returned by httpClient.Do() as network errors. This is because
the http clients returns different types of errors and it is hard to catch
all the error types.
With these changes we are now able to peak performances
for all Write() operations across disks HDD and NVMe.
Also adds readahead for disk reads, which also increases
performance for reads by 3x.
IsTruncated should not be set to true if there is no further
possible entries beyond maxKeys.
This commit will also move wide testing on object API from xl
to xl sets.
The problem in current code was we were removing
an entry from a lock lockerMap without considering
the fact that different entry for same resource is
a possibility due the nature of locks that can be
acquired in parallel before we decide if the lock
is considered stale
A sequence of events is as follows
- Lock("resource")
- lockMaintenance(finds a long lived lock in this "resource")
- Owner node rebooted which now retruns Expired() as true for
this "resource"
- Unlock("resource") which succeeded in quorum
- Now by this time application retried and acquired a new
Lock() on the same "resource"
- Now that we have Expired() true from the previous call,
we proceed to purge the entry from the local lockMap()
local lockMap reports a different entry for the expired
UID which results in a spurious log entry.
This PR removes this logging as this situation is an
expected scenario.
This will allow cache to consistently work for
server and gateways. Range GET requests will
be cached in the background after the request
is served from the backend.
Fixes: #7458, #7573, #6265, #6630
This is necessary to avoid connection build up between servers
unexpectedly for example in a situation where 16 servers are
talking to each other and one server now allows a maximum of
15*4096 = 61440 idle connections
Will be kept in pool. Such a large pool is perhaps inefficient for
many reasons and also affects overall system resources.
This PR also reduces idleConnection timeout from 120 secs to 60 secs.
errs was passed to many goroutines but they are all allowed
to update errs if any error happens during deletion, which
can cause a data race.
This commit will avoid issuing bulk delete operations in parallel
to avoid the warning race.
We broke into parts previously as we had checksum for the entire file
to tax less on memory and to have better TTFB. We dont need to now,
after the streaming-bitrot change.
Bulk delete at storage level in Multiple Delete Objects API
In order to accelerate bulk delete in Multiple Delete objects API,
a new bulk delete is introduced in storage layer, which will accept
a list of objects to delete rather than only one. Consequently,
a new API is also need to be added to Object API.
PR #7595 fixed part of the regression, but did not handle the
scenario, where in docker, the internal port is different from
the port on the host.
This PR modifies the regular expression such that all the
scenarios are handled.
Fixes#7619
After recent listing refactor, recursive list doesn't return empty
directories, this commit will fix the behavior and add unit tests
so it won't happen again.
When size is unknown and auto encryption is enabled,
and compression is set to true, putobject API is failing.
Moving adding the SSE-S3 header as part of the request to before
checking if compression can be done, otherwise the size is set to -1
and that seems to cause problems.
Currently we used to reload users every five minutes,
regardless of etcd is configured or not. But with etcd
configured we can do this more asynchronously to trigger
a refresh by using the watch API
Fixes#7515
One user has seen this following error log:
API: CompleteMultipartUpload(bucket=vertica, object=perf-dss-v03/cc2/02596813aecd4e476d810148586c2a3300d00000013557ef_0.gt)
Time: 15:44:07 UTC 04/11/2019
RequestID: 159475EFF4DEDFFB
RemoteHost: 172.26.87.184
UserAgent: vertica-v9.1.1-5
Error: open /data/.minio.sys/tmp/100bb3ec-6c0d-4a37-8b36-65241050eb02/xl.json: file exists
1: cmd/xl-v1-metadata.go:448:cmd.writeXLMetadata()
2: cmd/xl-v1-metadata.go:501:cmd.writeUniqueXLMetadata.func1()
This can happen when CompleteMultipartUpload fails with write quorum,
the S3 client will retry (since write quorum is 500 http response),
however the second call of CompleteMultipartUpload will fail because
this latter doesn't truly use a random uuid under .minio.sys/tmp/
directory but pick the upload id.
This commit fixes the behavior to choose a random uuid for generating
xl.json
Since AssumeRole API was introduced we have a wrong route
match which results in certain clients failing to upload objects
using multipart because, multipart POST conflicts with STS POST
AssumeRole API.
Write a proper matcher function which verifies the route more
appropriately such that both can co-exist.
Other listing optimizations include
- remove double sorting while filtering object entries
- improve error message when upload-id is not in quorum
- use jsoniter for full unmarshal json, instead of gjson
- remove unused code
Allow server to start if one of the local nodes in docker/kubernetes setup is successfully resolved
- The rule is that we need atleast one local node to work. We dont need to resolve the
rest at that point.
- In a non-orchestrational setup, we fail if we do not have atleast one local node up
and running.
- In an orchestrational setup (docker-swarm and kubernetes), We retry with a sleep of 5
seconds until any one local node shows up.
Fixes#6995
In distributed mode, use REST API to acquire and manage locks instead
of RPC.
RPC has been completely removed from MinIO source.
Since we are moving from RPC to REST, we cannot use rolling upgrades as the
nodes that have not yet been upgraded cannot talk to the ones that have
been upgraded.
We expect all minio processes on all nodes to be stopped and then the
upgrade process to be completed.
Also force http1.1 for inter-node communication
common prefixes in bucket name if already created
are disallowed when etcd is configured due to the
prefix matching issue. Make sure that when we look
for bucket we are only interested in exact bucket
name not the prefix.
- [x] Support bucket and regular object operations
- [x] Supports Select API on HDFS
- [x] Implement multipart API support
- [x] Completion of ListObjects support
There is no written specification about how to encode key names
when url encoding type is passed.
However, this change will encode URLs as url.QueryEscape() does
while considering AWS S3 exceptions.
This commit adds a unit test for the vault
config verification (which covers also `IsEmpty()`).
Vault-related code is hard to test with unit tests
since a Vault service would be necessary. Therefore
this commit only adds tests for a fraction of the code.
Fixes#7409
Most hadoop distributions hortonworks, cloudera all
depend on aws-sdk-java 1.7.x to 1.10.x - the releases
which have bugs related case sensitive check for
ETag header. Go changes the case of the headers set
to be canonical but only preserves them when set
through a direct map.
This fixes most compatibility issues we have had
in the past supporting older hadoop distributions.
This commit fixes a privilege escalation issue against
the S3 and web handlers. An authenticated IAM user
can:
- Read from or write to the internal '.minio.sys'
bucket by simply sending a properly signed
S3 GET or PUT request. Further, the user can
- Read from or write to the internal '.minio.sys'
bucket using the 'Upload'/'Download'/'DownloadZIP'
API by sending a "browser" request authenticated
with its JWT token.
This commit fixes another privilege escalation issue
abusing the inter-node communication of distributed
servers to obtain/modify the server configuration.
The inter-node communication is authenticated using
JWT-Tokens. Further, IAM users accessing the cluster
via the web UI also get a JWT token and the browser
will add this "user" JWT token to each the request.
Now, a user can extract that JWT token an can craft
HTTP POST requests for the inter-node communication
API endpoint. Since the server accepts ANY valid
JWT token it also accepts inter-node commands from
an authenticated user such that the user can execute
arbitrary commands bypassing the IAM policy engine
and impersonate other users, change its own IAM policy
or extract the admin access/secret key.
This is fixed by only accepting "admin" JWT tokens
(tokens containing the admin access key - and therefore
were generated with the admin secret key). Consequently,
only the admin user can execute such inter-node commands.
Simplify the cmd/http package overall by removing
custom plain text v/s tls connection detection, by
migrating to go1.12 and choose minimum version
to be go1.12
Also remove all the vendored deps, since they
are not useful anymore.
A race is detected between a bytes.Buffer generated with cmd/rpc.Pool
and http2 module. An issue is raised in golang (https://github.com/golang/go/issues/31192).
Meanwhile, this commit disables Pool in RPC code and it generates a
new 1kb of bytes.Buffer for each RPC call.
Before this commit, nodes wait indefinitely without showing any
indicate error message when a node is started with different access
and secret keys.
This PR will show '401 Unauthorized' in this case.
Currently message is set to error type value.
Message field is not used in error logs. it is used only in the case of info logs.
This PR sets error message field to store error type correctly.
Copying an encrypted SSEC object when this latter is uploaded using
multipart mechanism was failing because ETag in case of encrypted
multipart upload is not encrypted.
This PR fixes the behavior.
This fixes varying pids for server-respawns. And avoids duplicate process
creating multiple pids when the server restart signal is triggered with
service restart enabled.
Fixes#7350
It is required to set the environment variable in the case of distributed
minio. LoadCredentials is used to notify peers of the change and will not work if
environment variable is set. so, this function will never be called.
In scenario 1
```
- bucket/object-prefix
- bucket/object-prefix/object
```
Server responds with `XMinioParentIsObject`
In scenario 2
```
- bucket/object-prefix/object
- bucket/object-prefix
```
Server responds with `XMinioObjectExistsAsDirectory`
Fixes#6566
Healing scan used to read all objects parts to check for bitrot
checksum. This commit will add a quicker way of healing scan
by only checking if parts are actually present in disks or not.
We should internally handle when http2 input stream has smaller
content than its content-length header
Upstream issue reported https://github.com/golang/go/issues/30648
This a change which we need to handle internally until Go fixes it
correctly, till now our code doesn't expect a custom error to be returned.
CopyObject precondition checks into GetObjectReader
in order to perform SSE-C pre-condition checks using the
last 32 bytes of encrypted ETag rather than the decrypted
ETag
This also necessitates moving precondition checks for
gateways to gateway layer rather than object handler check
if a bucket with `Captialized letters` is created, `InvalidBucketName` error
will be returned.
In the case of pre-existing buckets, it will be listed.
Fixes#6938
Prevents deferred close functions from being called while still
attempting to copy reader to snappyWriter.
Reduces code duplication when compressing objects.
This change allows indefinitely running go-routines to cleanup
gracefully.
This channel is now closed at the beginning of each test so that
long-running go-routines quit and a new one is assigned.
The side affect of this change memory
increase, but this is a trade-off between
performance and actual memory usage.
For all practical scenarios this should be
an adequate change.
- The events will be persisted in queueStore if `queueDir` is set.
- Else, if queueDir is not set events persist in memory.
The events are replayed back when the mqtt broker is back online.
Clients like AWS SDK Java and AWS cli XML parsers are
unable to handle on `\r\n` characters to avoid these
errors send XML header first and write white space characters
instead.
Also handle cases to avoid double WriteHeader calls
- Current implementation was spawning renewer goroutines
without waiting for the lease duration to end. Remove vault renewer
and call vault.RenewToken directly and manage reauthentication if
lease expired.
We should change the logic for both isObject()
and isObjectDir() leaf detection to be done
with quorum, due to how our directory navigation
works - this allows for properly deleting all
the dangling directories or objects if any.
This commit fixes a nil pointer dereference issue
that can occur when the Vault KMS returns e.g. a 404
with an empty HTTP response. The Vault client SDK
does not treat that as error and returns nil for
the error and the secret.
Further it simplifies the token renewal and
re-authentication mechanism by using a single
background go-routine.
The control-flow of Vault authentications looks
like this:
1. `authenticate()`: Initial login and start of background job
2. Background job starts a `vault.Renewer` to renew the token
3. a) If this succeeds the token gets updated
b) If this fails the background job tries to login again
4. If the login in 3b. succeeded goto 2. If it fails
goto 3b.
Currently, we were sending errors in Select binary format,
which is incompatible with AWS S3 behavior, errors in binary
are sent after HTTP status code is already 200 OK - i.e it
happens during the evaluation of the record reader.
This commit increases storage REST requests to 5 minutes, this includes
the opening TCP connection, and sending/receiving data. This will reduce
clients receiving errors when the server is under high load.
Different gateway implementations due to different backend
API errors, might return different unsupported errors at
our handler layer. Current code posed a problem for us because
this information was lost and we would convert it to InternalError
in this situation all S3 clients end up retrying the request.
To avoid this unexpected situation implement a way to support
this cleanly such that the underlying information is not lost
which is returned by gateway.
Bucket metadata healing in the current code was executed multiple
times each time for a given set. Bucket metadata just like
objects are hashed in accordance with its name on any given set,
to allow hashing to play a role we should let the top level
code decide where to navigate.
Current code also had 3 bucket metadata files hardcoded, whereas
we should make it generic by listing and navigating the .minio.sys
to heal such objects.
We also had another bug where due to isObjectDangling changes
without pre-existing bucket metadata files, we were erroneously
reporting it as grey/corrupted objects.
This PR fixes all of the above items.
This PR also adds some comments and simplifies
the code. Primary handling is done to ensure
that we make sure to honor cached buffer.
Added unit tests as well
Fixes#7141
foo.CORRUPTED should never be created because when
multiple sets are involved we would hash the file
to wrong a location, this PR removes the code.
But allows DeleteBucket() to work properly to delete
dangling buckets/objects. Also adds another option
to Healing where a user needs to specify `--remove`
such that all dangling objects will be deleted with
user confirmation.
ListObjectParts is using xl.readXLMetaParts which picks the first
xl meta found in any disk, which is an inconsistent information.
E.g.: In a middle of a multipart upload, one node can go offline
and get back later with an outdated multipart information.
This commit fixes the computation of Before/After healing state
for empty directories.
Issues before the commit:
- Before state doesn't reflect the real status (no StatVol() called)
- For any MakeVol() error, healObjectDir is exited directly, which is
wrong.
Currently during a heal of a bucket, if one disk is offline an empty endpoint entry is added.
Then another entry with the missing endpoint is also added.
This results in more entries than disks being added.
Code that adds empty endpoint has been removed.
Collect historic cpu and mem stats. Also, use actual values
instead of formatted strings while returning to the client. The string
formatting prevents values from being processed by the server or
by the client without parsing it.
This change will allow the values to be processed (eg.
compute rolling-average over the lifetime of the minio server)
and offloads the formatting to the client.
We made a change previously in #7111 which moved support
for AWS envs only for AWS S3 endpoint. Some users requested
that this be added back to Non-AWS endpoints as well as
they require separate credentials for backend authentication
from security point of view.
More than one client can't use the same clientID for MQTT connection.
This causes problem in distributed deployments where config is shared
across nodes, as each Minio instance tries to connect to MQTT using the
same clientID.
This commit removes the clientID field in config, and allows
MQTT client to create random clientID for each node.
- New parser written from scratch, allows easier and complete parsing
of the full S3 Select SQL syntax. Parser definition is directly
provided by the AST defined for the SQL grammar.
- Bring support to parse and interpret SQL involving JSON path
expressions; evaluation of JSON path expressions will be
subsequently added.
- Bring automatic type inference and conversion for untyped
values (e.g. CSV data).
This situation happens only in gateway nas which supports
etcd based `config.json` to support all FS mode features.
The issue was we would try to migrate something which doesn't
exist when etcd is configured which leads to inconsistent
server configs in memory.
This PR fixes this situation by properly loading config after
initialization, avoiding backend disk config migration to be
done only if etcd is not configured.
Harshavardhana
Shireesh Anjal
Kaloyan Raev
Krishna Srinivas
Poorna Krishnamoorthy
Anis Elleuch
Ritesh H Shukla
ebozduman
Klaus Post
飞雪无情
Andreas Auernhammer
Lenin Alevski
Praveen raj Mani
Nitish Tiwari
Gaige B Paulsen
Jorge Israel Peña
Daniel Valdivia
kannappanr
KevinSmile
Adam Brown
Benjamin Sodenkamp
ethan ho
P R
Nathan Brown
Anton Huck
Erkki Eilonen
Sidhartha Mani
remche
Bala FA
Egor Rudinsky
Dmitry Gadeev
BigUstad
Boaz
Egon Elbre
Taras Parkhomenko
Aditya Manthramurthy
Pontus Leitzler
César Nieto
Ingmar Runge
Stephen N
Kody A Kantor
astorath
Krishnan Parthasarathi
Ashish Kumar Sinha
Forest Lovewood
George Xie
Amol Umbarkar
Aleksandr Petruhin
Clemens Wolff
Sergey Morgunov
svistoi
Ville Skyttä
Kanagaraj M
cc
Kaan Kabalak
Yao Zongyou
Alex Pardoe
maihde
Jakob Ackermann
Daryl Finlay
Christian Muehlhaeuser
mzukowski-reef
mizuno-keyence
iliul
Cody Maloney
Dee Koder
Andrei Mikhalenia
Roman Kalashnikov
Chris Hoffman
Ashish Kumar Sinha
zy
Kirill Motkov
Kale Blankenship
John Liu