40ba7f6172
This patch enables efficent PUT/GET for global distributed cluster[1].
Problem:
Erasure coding has the capability to decrease the amout of actual stored
data less then replicated model. For example, ec_k=6, ec_m=3 parameter
can be 1.5x of the original data which is smaller than 3x replicated.
However, unlike replication, erasure coding requires availability of at
least some ec_k fragments of the total ec_k + ec_m fragments to service
read (e.g. 6 of 9 in the case above). As such, if we stored the
EC object into a swift cluster on 2 geographically distributed data
centers which have the same volume of disks, it is likely the fragments
will be stored evenly (about 4 and 5) so we still need to access a
faraway data center to decode the original object. In addition, if one
of the data centers was lost in a disaster, the stored objects will be
lost forever, and we have to cry a lot. To ensure highly durable
storage, you would think of making *more* parity fragments (e.g.
ec_k=6, ec_m=10), unfortunately this causes *significant* performance
degradation due to the cost of mathmetical caluculation for erasure
coding encode/decode.
How this resolves the problem:
EC Fragment Duplication extends on the initial solution to add *more*
fragments from which to rebuild an object similar to the solution
described above. The difference is making *copies* of encoded fragments.
With experimental results[1][2], employing small ec_k and ec_m shows
enough performance to store/retrieve objects.
On PUT:
- Encode incomming object with small ec_k and ec_m <- faster!
- Make duplicated copies of the encoded fragments. The # of copies
are determined by 'ec_duplication_factor' in swift.conf
- Store all fragments in Swift Global EC Cluster
The duplicated fragments increase pressure on existing requirements
when decoding objects in service to a read request. All fragments are
stored with their X-Object-Sysmeta-Ec-Frag-Index. In this change, the
X-Object-Sysmeta-Ec-Frag-Index represents the actual fragment index
encoded by PyECLib, there *will* be duplicates. Anytime we must decode
the original object data, we must only consider the ec_k fragments as
unique according to their X-Object-Sysmeta-Ec-Frag-Index. On decode no
duplicate X-Object-Sysmeta-Ec-Frag-Index may be used when decoding an
object, duplicate X-Object-Sysmeta-Ec-Frag-Index should be expected and
avoided if possible.
On GET:
This patch inclues following changes:
- Change GET Path to sort primary nodes grouping as subsets, so that
each subset will includes unique fragments
- Change Reconstructor to be more aware of possibly duplicate fragments
For example, with this change, a policy could be configured such that
swift.conf:
ec_num_data_fragments = 2
ec_num_parity_fragments = 1
ec_duplication_factor = 2
(object ring must have 6 replicas)
At Object-Server:
node index (from object ring): 0 1 2 3 4 5 <- keep node index for
reconstruct decision
X-Object-Sysmeta-Ec-Frag-Index: 0 1 2 0 1 2 <- each object keeps actual
fragment index for
backend (PyEClib)
Additional improvements to Global EC Cluster Support will require
features such as Composite Rings, and more efficient fragment
rebalance/reconstruction.
1: http://goo.gl/IYiNPk (Swift Design Spec Repository)
2: http://goo.gl/frgj6w (Slide Share for OpenStack Summit Tokyo)
Doc-Impact
Co-Authored-By: Clay Gerrard <clay.gerrard@gmail.com>
Change-Id: Idd155401982a2c48110c30b480966a863f6bd305
Team and repository tags
Swift
A distributed object storage system designed to scale from a single machine to thousands of servers. Swift is optimized for multi-tenancy and high concurrency. Swift is ideal for backups, web and mobile content, and any other unstructured data that can grow without bound.
Swift provides a simple, REST-based API fully documented at http://docs.openstack.org/.
Swift was originally developed as the basis for Rackspace's Cloud Files and was open-sourced in 2010 as part of the OpenStack project. It has since grown to include contributions from many companies and has spawned a thriving ecosystem of 3rd party tools. Swift's contributors are listed in the AUTHORS file.
Docs
To build documentation install sphinx
(pip install sphinx), run
python setup.py build_sphinx, and then browse to
/doc/build/html/index.html. These docs are auto-generated after every
commit and available online at http://docs.openstack.org/developer/swift/.
For Developers
Getting Started
Swift is part of OpenStack and follows the code contribution, review, and testing processes common to all OpenStack projects.
If you would like to start contributing, check out these notes to help you get started.
The best place to get started is the "SAIO - Swift All In One". This document will walk you through setting up a development cluster of Swift in a VM. The SAIO environment is ideal for running small-scale tests against swift and trying out new features and bug fixes.
Tests
There are three types of tests included in Swift's source tree.
- Unit tests
- Functional tests
- Probe tests
Unit tests check that small sections of the code behave properly. For example, a unit test may test a single function to ensure that various input gives the expected output. This validates that the code is correct and regressions are not introduced.
Functional tests check that the client API is working as expected. These can be run against any endpoint claiming to support the Swift API (although some tests require multiple accounts with different privilege levels). These are "black box" tests that ensure that client apps written against Swift will continue to work.
Probe tests are "white box" tests that validate the internal workings of a Swift cluster. They are written to work against the "SAIO - Swift All In One" dev environment. For example, a probe test may create an object, delete one replica, and ensure that the background consistency processes find and correct the error.
You can run unit tests with .unittests, functional tests
with .functests, and probe tests with
.probetests. There is an additional .alltests
script that wraps the other three.
Code Organization
- bin/: Executable scripts that are the processes run by the deployer
- doc/: Documentation
- etc/: Sample config files
- examples/: Config snippets used in the docs
- swift/: Core code
- account/: account server
- cli/: code that backs some of the CLI tools in bin/
- common/: code shared by different modules
- middleware/: "standard", officially-supported middleware
- ring/: code implementing Swift's ring
- container/: container server
- locale/: internationalization (translation) data
- obj/: object server
- proxy/: proxy server
- test/: Unit, functional, and probe tests
Data Flow
Swift is a WSGI application and uses eventlet's WSGI server. After
the processes are running, the entry point for new requests is the
Application class in swift/proxy/server.py.
From there, a controller is chosen, and the request is processed. The
proxy may choose to forward the request to a back- end server. For
example, the entry point for requests to the object server is the
ObjectController class in
swift/obj/server.py.
For Deployers
Deployer docs are also available at http://docs.openstack.org/developer/swift/. A good starting point is at http://docs.openstack.org/developer/swift/deployment_guide.html
There is an ops runbook that gives information about how to diagnose and troubleshoot common issues when running a Swift cluster.
You can run functional tests against a swift cluster with
.functests. These functional tests require
/etc/swift/test.conf to run. A sample config file can be
found in this source tree in test/sample.conf.
For Client Apps
For client applications, official Python language bindings are provided at http://github.com/openstack/python-swiftclient.
Complete API documentation at http://docs.openstack.org/api/openstack-object-storage/1.0/content/
There is a large ecosystem of applications and libraries that support and work with OpenStack Swift. Several are listed on the associated projects page.
For more information come hang out in #openstack-swift on freenode.
Thanks,
The Swift Development Team