We can catch most errors when we try to load an sstable. But if the TOC file is
the one missing, we won't try to load the sstable at all. This case is still an
invalid case, but it is way easier for us to treat it by waiting for all files
to be loaded, and then checking if we saw a file during scan_dir, without its
corresponding TOC.
Fixes#114
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
Currently, each column family creates a fiber to handle compaction requests
in parallel to the system. If there are N column families, N compactions
could be running in parallel, which is definitely horrible.
To solve that problem, a per-database compaction manager is introduced here.
Compaction manager is a feature used to service compaction requests from N
column families. Parallelism is made available by creating more than one
fiber to service the requests. That being said, N compaction requests will
be served by M fibers.
A compaction request being submitted will go to a job queue shared between
all fibers, and the fiber with the lowest amount of pending jobs will be
signalled.
Signed-off-by: Raphael S. Carvalho <raphaelsc@cloudius-systems.com>
Without this, Cassandra won't even try to read our sstables. The containing
directories will be ignored.
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
Let's change the default generated tables to ka, which is the one that is present
in Origin
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
A ka file has a slightly different name on disk. Change the
parser so we can deal with both
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
When a schema is available, we use it. However, we have, by now, way too many
tests. Some of them use tables for which we don't even know the schema. It would
have been a massive amount of work to require a schema for all of them - so I am
keeping both constructors around.
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
It is currently only used to log a message, and for that we have an sstable
method that will do just fine. Using the name itself just makes it being passed
along throughout the captures. Remove it.
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
ASan does not like commit 05c23c7f73
("database: Add create_keyspace_on_all() helper"):
==8112==WARNING: AddressSanitizer failed to allocate 0x7f88b84fc690 bytes
==8112==AddressSanitizer's allocator is terminating the process instead of returning 0
==8112==If you don't like this behavior set allocator_may_return_null=1
==8112==Sanitizer CHECK failed: ../../../../libsanitizer/sanitizer_common/sanitizer_allocator.cc:147 ((0)) != (0) (0, 0)
I was not able to determine the source of the bug. Make ASan happy by
reverting the code movement and using the "cpu zero" trick we use for
table creation.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
When probing for the type, I have made the classical mistake of using
as a parameter part of a structure that is moved into the capture. That
is what broke our tests.
But also, when stat'ing, de.name will give us only the component relative to
the current path. We need to add the directory so the stat will succeed.
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
Our directory scanner currently requires a type to be passed, and we have a
FIXME saying that we should stat when there is none. In some filesystems,
in particular, XFS, getdents won't return a type, meaning we should manually
probe it.
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
When forcing a compaction on a column family with no sstables, an
assert will fail because there is no sstables to be compacted.
This problem is fixed by ignoring a compaction request when no
sstable is provided.
Fixes#61.
Signed-off-by: Raphael S. Carvalho <raphaelsc@cloudius-systems.com>
Reviewed-by: Nadav Har'El <nyh@cloudius-systems.com>
There's nothing legacy about it so rename legacy_schema_tables to
schema_tables. The naming comes from a Cassandra 3.x development branch
which is not relevant for us in the near future.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
"This series implements initial support for CQL events. We introduce
migration_listener hook in migration manager as well as event notifier
in the CQL server that's built on top of it to send out the events via
CQL binary protocol. We also wire up create keyspace events to the
system so subscribed clients are notified when a new keyspace is
created.
There's still more work to be done to support all the events. That
requires some work to restructure existing code so it's better to merge
this initial series now and avoid future code conflicts."
Add a create_keyspace_on_all() helper which is needed for sending just
one event notification per created keyspace, not one per shard.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
In case of SELECT DISTINCT statments we are not intersted in clustering
keys at all. The only important information is whether partition key
exists and what's in static row (if it exists).
Signed-off-by: Paweł Dziepak <pdziepak@cloudius-systems.com>
In preparation for adding listener state to migration manager, use
sharded<> for migration manager.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
This message is printed when we are about to run the strategy code
which may not decide to compact anything. Compaction is already
properly logged in sstables::compact_sstables().
Signed-off-by: Raphael S. Carvalho <raphaelsc@cloudius-systems.com>
Add CF UUID validation to update table paths to make us behave like
Origin for parallel table creation.
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>
Abillity to enable/disable specific sub-modules - this settings do not
affect system tables which are allways persisted,cached and written to
commitlog
enable-in-memory-data-store marks if tables will be written/read to/from
disk
enable-commitllog marks if tables will be written to commitlog
enable-cache marks if tables will be written/read to/from cache
Please note in-memory-data-store does not change the read path so "old"
sstables are still read and cache may be used to cache their data
Signed-off-by: Shlomi Livne <shlomi@cloudius-systems.com>
We should only call column_family::start after the checks because
if a check failed, column_family would be destroyed without
column_family::stop being called first, and that would lead to
a problem, such as _compaction_done future not being resolved.
Signed-off-by: Raphael S. Carvalho <raphaelsc@cloudius-systems.com>
So far, automatic compaction was disabled, but now that we support
size-tiered strategy, the default compaction strategy algorithm,
we could definitely enable automatic compaction by default.
Signed-off-by: Raphael S. Carvalho <raphaelsc@cloudius-systems.com>
Currently, compaction will no longer happen for a column family which
a compaction failed for some unexpected reason.
We want to implement a retry policy that will sleep for a while until
the next compaction attempt. This patch implements retry policy for
compaction using exponential_backoff_retry.
With exponential_backoff_retry, the sleep time grows exponentially
with the number of retries until the maximum sleep time is reached.
For compaction specifically, the base sleep time will be 5 seconds and
the maximum sleeping time will be 300 seconds, i.e. 5 minutes.
If compaction succeeded after a retry, the sleep time will be reset to
the base sleep time.
Signed-off-by: Raphael S. Carvalho <raphaelsc@cloudius-systems.com>
We must wait for the system tables to be loaded on all shards before
populating the other keyspaces, or we might miss some keyspaces or column
families. This is hinted at by the fact that we use storage_proxy, which
isn't usable until the system keyspace is ready.
Credit to Tomek for identifying the problem and the fix.
Actually we should rethrow exceptions because they are needed for
keep_doing() to finish. Otherwise, the future _compaction_done
will never be resolved.
This reverts commit 89698b0d1c.
Support to compaction strategy options was recently added.
Previously, we were using default values in compaction strategy for
options, but now we can use the options defined in the schema.
Currently, we only support size-tiered strategy, so let's start
with it.
Signed-off-by: Raphael S. Carvalho <raphaelsc@cloudius-systems.com>
broken_semaphore and seastar::gate_closed_exception exceptions are
used for regular termination of compaction fiber, which otherwise
would live forever. We shouldn't re-throw these exceptions, but
instead only print a log message.
Signed-off-by: Raphael S. Carvalho <raphaelsc@cloudius-systems.com>
