Shlomi Livne

Getting Scylla Working - missing the code to build scylla

2

https://github.com/thibaultcha/lua-cassandra/blob/232e9688e4810d23c9a6420e7be7d7e9c7feadb8/.ci/setup_env.sh#L26 in the setup you are building scylla-jmx and scylla-tools-java, you are missing the code to build scylla. you can follow https://github.com/scylladb/scylla#quick-start (one niptick ... by default you will build...

Memcached is not working with DPDK on Intel servers

8

DPDK 1.8.0 seastar : 89763c95c92b44d3482e7500ddd5c14b8c47b76en also seastar: 29366cb07683e7b12a849e3058681b8b911942c1 (same results) - boot seastar on dpdk1 with ''' sudo build/release/apps/memcached/memcached --network-stack native --dhcp 0 --host-ipv4-addr 192.168.20.101 --netmask-ipv4-addr 255.255.255.0 --gw-ipv4-addr 192.168.20.185 --smp...

seastar tcpserver - goclient rxrx test with DPDK at times underperforms by x1000

3

http://jenkins.cloudius-systems.com:8080/job/seastar-private-tcpserver-perf/8/PerfPublisher/ this happens at least 1 out of 5 runs On Thor-Loki: | Goserver | tcp-server stack-native-dpdk171 | tcpserver stack-native-dpdk18 | tcpserver stack-posix | | --- | --- | ---...

4.6.1 not able to replace node

34

replace falls with ``` storage_service - replace[7b2becdd-7917-4c17-8eb6-a0db06c2c8ee]: Failed to send heartbeat: std::runtime_error (node_ops_cmd_check: Node 192.168.41.225 rejected node_ops_cmd=8 from node=192.168.41.225 with ops_uuid=7b2becdd-7917-4c17-8eb6-a0db06c2c8ee, pending_node_ops={}, the node ops is unknown) ``` scylla.yaml ```...

Export per table metrics on per node basis - not per shard

1

Enabling per table metrics per shard causes a huge load in deployments that have many shards and many tables (easily passing all the other metrics scylla exports). To reduce the...

No support for nested json

1

Extracted from users slack channel ``` { "group_id": 1010, "competition_count": { "val": 20, "type": "ts" }, "session_count": { "val": 20, "type": "ts" } } ScyllaDb Create Statement : CREATE TYPE...

We have a workaroud in urchin_node to support api_address - the workaround reads add api-address to the command line as we currently do not support api-address from config. Once api-address...

PoolingOptions - should they be adhered when the server support Scylla Shard Extenstions

3

When a client connect to a server supporting the Scylla Protocol Extension for [Intranode Sharding](https://github.com/scylladb/scylla/blob/master/docs/protocol-extensions.md#intranode-sharding) the driver will open connections to each shard A client can also setup [PoolingOptions](https://github.com/scylladb/java-driver/blob/3.x/driver-core/src/main/java/com/datastax/driver/core/PoolingOptions.java) It...

Connections setup from clients that use the additional native_trasport_shard_aware_port - are not all to that port

1

Please answer these questions before submitting your issue. Thanks! ### What version of Scylla or Cassandra are you using? * 2021.1.5 (scylla-cloud) ### What version of Gocql are you using?...

Verify cpu's governance is set to performance

1

Linux provides multiple governance profiles (https://www.kernel.org/doc/Documentation/cpu-freq/governors.txt) for the cpu - some are aimed at energy saving other for performance Since Scylla is used for high performance / low latency has...