[jira] [Commented] (CASSANDRA-7103) Very poor performance with simple setup
[ https://issues.apache.org/jira/browse/CASSANDRA-7103?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13984223#comment-13984223 ] Martin Bligh commented on CASSANDRA-7103: - OK, that explains some stuff ... will take it to user list as you suggest. I was under the impression that the row key was the whole of the primary key, not just the partition key, as described here, for instance: http://wiki.apache.org/cassandra/DataModel The first component of a table's primary key is the partition key; within a partition, rows are clustered by the remaining columns of the PK. In which case, that description seems very misleading Very poor performance with simple setup --- Key: CASSANDRA-7103 URL: https://issues.apache.org/jira/browse/CASSANDRA-7103 Project: Cassandra Issue Type: Bug Components: Core Environment: Fedora 19 (also happens on Ubuntu), Cassandra 2.0.7. dsc standard install Reporter: Martin Bligh Single node (this is just development, 32GB 20 core server), single disk array. Create the following table: {code} CREATE TABLE reut ( time_order bigint, time_start bigint, ack_us mapint, int, gc_strategy maptext, int, gc_strategy_symbol maptext, int, gc_symbol maptext, int, ge_strategy maptext, int, ge_strategy_symbol maptext, int, ge_symbol maptext, int, go_strategy maptext, int, go_strategy_symbol maptext, int, go_symbol maptext, int, message_type maptext, int, PRIMARY KEY (time_order, time_start) ) WITH bloom_filter_fp_chance=0.01 AND caching='KEYS_ONLY' AND comment='' AND dclocal_read_repair_chance=0.00 AND gc_grace_seconds=864000 AND index_interval=128 AND read_repair_chance=0.10 AND replicate_on_write='true' AND populate_io_cache_on_flush='false' AND default_time_to_live=0 AND speculative_retry='99.0PERCENTILE' AND memtable_flush_period_in_ms=0 AND compaction={'class': 'SizeTieredCompactionStrategy'} AND compression={}; {code} Now I just insert data into it (using python driver, async insert, prepared insert statement). Each row only fills out one of the gc_*, go_*, or ge_* columns, and there's something like 20-100 entries per map column, occasionally 1000, but it's nothing huge. First run 685 inserts in 1.004860 seconds (681.687053 Operations/s). OK, not great, but that's fine. Now throw 50,000 rows at it. Now run the first run again, and it takes 53s to do the same insert of 685 rows - I'm getting about 10 rows per second. It's not IO bound - iostat 1 shows quiescent for 9 seconds, then ~640KB write, then sleeps again - seems like the fflush sync. Run nodetool flush and performance goes back to as before Not sure why this gets so slow - I think it just builds huge commit logs and memtables, but never writes out to the data/ directory with sstables because I only have one table? That doesn't seem like a good situation. Worse ... if you let the python driver just throw stuff at it async (I think this allows up to 128 request if I understand the underlying protocol, then it gets so slow that a single write takes over 10s and times out). Seems to be some sort of synchronization problem in Java ... if I limit the concurrent async requests to the left column below, I get the number of seconds elapsed on the right: 1: 103 seconds 2: 63 seconds 8: 53 seconds 16: 53 seconds 32: 66 seconds 64: so slow it explodes in timeouts on write (over 10s each). I guess there's some thundering herd type locking issue in whatever Java primitive you are using to lock concurrent access to a single table. I know some of the Java concurrent.* stuff has this issue. So for the other tests above, I was limiting async writes to 16 pending. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Commented] (CASSANDRA-7103) Very poor performance with simple setup
[ https://issues.apache.org/jira/browse/CASSANDRA-7103?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13984390#comment-13984390 ] Benedict commented on CASSANDRA-7103: - Yes, the terminology is definitely a bit confusing. I even mixed it up myself in my first response to you. This is a result of a major transition in functionality/terminology, and the old terminology lingers (especially here on JIRA) storage row = data stored against a given partition key cql row = data stored against a given a primary key Very poor performance with simple setup --- Key: CASSANDRA-7103 URL: https://issues.apache.org/jira/browse/CASSANDRA-7103 Project: Cassandra Issue Type: Bug Components: Core Environment: Fedora 19 (also happens on Ubuntu), Cassandra 2.0.7. dsc standard install Reporter: Martin Bligh Single node (this is just development, 32GB 20 core server), single disk array. Create the following table: {code} CREATE TABLE reut ( time_order bigint, time_start bigint, ack_us mapint, int, gc_strategy maptext, int, gc_strategy_symbol maptext, int, gc_symbol maptext, int, ge_strategy maptext, int, ge_strategy_symbol maptext, int, ge_symbol maptext, int, go_strategy maptext, int, go_strategy_symbol maptext, int, go_symbol maptext, int, message_type maptext, int, PRIMARY KEY (time_order, time_start) ) WITH bloom_filter_fp_chance=0.01 AND caching='KEYS_ONLY' AND comment='' AND dclocal_read_repair_chance=0.00 AND gc_grace_seconds=864000 AND index_interval=128 AND read_repair_chance=0.10 AND replicate_on_write='true' AND populate_io_cache_on_flush='false' AND default_time_to_live=0 AND speculative_retry='99.0PERCENTILE' AND memtable_flush_period_in_ms=0 AND compaction={'class': 'SizeTieredCompactionStrategy'} AND compression={}; {code} Now I just insert data into it (using python driver, async insert, prepared insert statement). Each row only fills out one of the gc_*, go_*, or ge_* columns, and there's something like 20-100 entries per map column, occasionally 1000, but it's nothing huge. First run 685 inserts in 1.004860 seconds (681.687053 Operations/s). OK, not great, but that's fine. Now throw 50,000 rows at it. Now run the first run again, and it takes 53s to do the same insert of 685 rows - I'm getting about 10 rows per second. It's not IO bound - iostat 1 shows quiescent for 9 seconds, then ~640KB write, then sleeps again - seems like the fflush sync. Run nodetool flush and performance goes back to as before Not sure why this gets so slow - I think it just builds huge commit logs and memtables, but never writes out to the data/ directory with sstables because I only have one table? That doesn't seem like a good situation. Worse ... if you let the python driver just throw stuff at it async (I think this allows up to 128 request if I understand the underlying protocol, then it gets so slow that a single write takes over 10s and times out). Seems to be some sort of synchronization problem in Java ... if I limit the concurrent async requests to the left column below, I get the number of seconds elapsed on the right: 1: 103 seconds 2: 63 seconds 8: 53 seconds 16: 53 seconds 32: 66 seconds 64: so slow it explodes in timeouts on write (over 10s each). I guess there's some thundering herd type locking issue in whatever Java primitive you are using to lock concurrent access to a single table. I know some of the Java concurrent.* stuff has this issue. So for the other tests above, I was limiting async writes to 16 pending. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Commented] (CASSANDRA-7103) Very poor performance with simple setup
[ https://issues.apache.org/jira/browse/CASSANDRA-7103?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13984424#comment-13984424 ] Martin Bligh commented on CASSANDRA-7103: - FWIW, in case anyone trips across this later: changing PRIMARY KEY (time_order, time_start) to PRIMARY KEY ((time_order, time_start)) fixed the insert side of it - ie using both for the storage row index. And this: http://www.datastax.com/dev/blog/whats-new-in-cql-3-0 explained it in more detail, and now I can at least see what they were trying to say in the wiki ;-) Stops me from being able to use and operators, but that's a different problem ... Thanks for the explanation. Very poor performance with simple setup --- Key: CASSANDRA-7103 URL: https://issues.apache.org/jira/browse/CASSANDRA-7103 Project: Cassandra Issue Type: Bug Components: Core Environment: Fedora 19 (also happens on Ubuntu), Cassandra 2.0.7. dsc standard install Reporter: Martin Bligh Single node (this is just development, 32GB 20 core server), single disk array. Create the following table: {code} CREATE TABLE reut ( time_order bigint, time_start bigint, ack_us mapint, int, gc_strategy maptext, int, gc_strategy_symbol maptext, int, gc_symbol maptext, int, ge_strategy maptext, int, ge_strategy_symbol maptext, int, ge_symbol maptext, int, go_strategy maptext, int, go_strategy_symbol maptext, int, go_symbol maptext, int, message_type maptext, int, PRIMARY KEY (time_order, time_start) ) WITH bloom_filter_fp_chance=0.01 AND caching='KEYS_ONLY' AND comment='' AND dclocal_read_repair_chance=0.00 AND gc_grace_seconds=864000 AND index_interval=128 AND read_repair_chance=0.10 AND replicate_on_write='true' AND populate_io_cache_on_flush='false' AND default_time_to_live=0 AND speculative_retry='99.0PERCENTILE' AND memtable_flush_period_in_ms=0 AND compaction={'class': 'SizeTieredCompactionStrategy'} AND compression={}; {code} Now I just insert data into it (using python driver, async insert, prepared insert statement). Each row only fills out one of the gc_*, go_*, or ge_* columns, and there's something like 20-100 entries per map column, occasionally 1000, but it's nothing huge. First run 685 inserts in 1.004860 seconds (681.687053 Operations/s). OK, not great, but that's fine. Now throw 50,000 rows at it. Now run the first run again, and it takes 53s to do the same insert of 685 rows - I'm getting about 10 rows per second. It's not IO bound - iostat 1 shows quiescent for 9 seconds, then ~640KB write, then sleeps again - seems like the fflush sync. Run nodetool flush and performance goes back to as before Not sure why this gets so slow - I think it just builds huge commit logs and memtables, but never writes out to the data/ directory with sstables because I only have one table? That doesn't seem like a good situation. Worse ... if you let the python driver just throw stuff at it async (I think this allows up to 128 request if I understand the underlying protocol, then it gets so slow that a single write takes over 10s and times out). Seems to be some sort of synchronization problem in Java ... if I limit the concurrent async requests to the left column below, I get the number of seconds elapsed on the right: 1: 103 seconds 2: 63 seconds 8: 53 seconds 16: 53 seconds 32: 66 seconds 64: so slow it explodes in timeouts on write (over 10s each). I guess there's some thundering herd type locking issue in whatever Java primitive you are using to lock concurrent access to a single table. I know some of the Java concurrent.* stuff has this issue. So for the other tests above, I was limiting async writes to 16 pending. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Commented] (CASSANDRA-7103) Very poor performance with simple setup
[ https://issues.apache.org/jira/browse/CASSANDRA-7103?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13983567#comment-13983567 ] Martin Bligh commented on CASSANDRA-7103: - BTW, I'm aware that this is (a) a single node (b) half my time_order entries are zero (which I don't think matters as it's a single node anyway), so my partition key doesn't have much variance (c) disk is not performant (but we're not even trying to write to it from iostat, so I don't think this matters). (d) I'm writing to one table (e) I'm using a single writer. So I'm creating a hotspot of some form. But really, 1. I think it should be able to handle more than 700 writes a second to one table. 2. It shouldn't degrade to about 10 writes per second. Sure, I could throw masses of hardware at it, and make it scale a bit better, but ... unless it can perform better than this on a single table, single node, I don't see how it'd perform in any reasonable fashion on a larger cluster. Very poor performance with simple setup --- Key: CASSANDRA-7103 URL: https://issues.apache.org/jira/browse/CASSANDRA-7103 Project: Cassandra Issue Type: Bug Components: Core Environment: Fedora 19 (also happens on Ubuntu), Cassandra 2.0.7. dsc standard install Reporter: Martin Bligh Single node (this is just development, 32GB 20 core server), single disk array. Create the following table: CREATE TABLE reut ( time_order bigint, time_start bigint, ack_us mapint, int, gc_strategy maptext, int, gc_strategy_symbol maptext, int, gc_symbol maptext, int, ge_strategy maptext, int, ge_strategy_symbol maptext, int, ge_symbol maptext, int, go_strategy maptext, int, go_strategy_symbol maptext, int, go_symbol maptext, int, message_type maptext, int, PRIMARY KEY (time_order, time_start) ) WITH bloom_filter_fp_chance=0.01 AND caching='KEYS_ONLY' AND comment='' AND dclocal_read_repair_chance=0.00 AND gc_grace_seconds=864000 AND index_interval=128 AND read_repair_chance=0.10 AND replicate_on_write='true' AND populate_io_cache_on_flush='false' AND default_time_to_live=0 AND speculative_retry='99.0PERCENTILE' AND memtable_flush_period_in_ms=0 AND compaction={'class': 'SizeTieredCompactionStrategy'} AND compression={}; Now I just insert data into it (using python driver, async insert, prepared insert statement). Each row only fills out one of the gc_*, go_*, or ge_* columns, and there's something like 20-100 entries per map column, occasionally 1000, but it's nothing huge. First run 685 inserts in 1.004860 seconds (681.687053 Operations/s). OK, not great, but that's fine. Now throw 50,000 rows at it. Now run the first run again, and it takes 53s to do the same insert of 685 rows - I'm getting about 10 rows per second. It's not IO bound - iostat 1 shows quiescent for 9 seconds, then ~640KB write, then sleeps again - seems like the fflush sync. Run nodetool flush and performance goes back to as before Not sure why this gets so slow - I think it just builds huge commit logs and memtables, but never writes out to the data/ directory with sstables because I only have one table? That doesn't seem like a good situation. Worse ... if you let the python driver just throw stuff at it async (I think this allows up to 128 request if I understand the underlying protocol, then it gets so slow that a single write takes over 10s and times out). Seems to be some sort of synchronization problem in Java ... if I limit the concurrent async requests to the left column below, I get the number of seconds elapsed on the right: 1: 103 seconds 2: 63 seconds 8: 53 seconds 16: 53 seconds 32: 66 seconds 64: so slow it explodes in timeouts on write (over 10s each). I guess there's some thundering herd type locking issue in whatever Java primitive you are using to lock concurrent access to a single table. I know some of the Java concurrent.* stuff has this issue. So for the other tests above, I was limiting async writes to 16 pending. -- This message was sent by Atlassian JIRA (v6.2#6252)