Re: Tombstones in memtable
Reads increase on all most all nodes same is the case with CPU. it's goes high on all nodes On Sat, Feb 23, 2019, 11:04 PM Kenneth Brotman wrote: > When the CPU utilization spikes from 5-10% to 50%, how many nodes does it > happen to at the same time? > > > > *From:* Rahul Reddy [mailto:rahulreddy1...@gmail.com] > *Sent:* Saturday, February 23, 2019 7:26 PM > *To:* user@cassandra.apache.org > *Subject:* Re: Tombstones in memtable > > > > ```jvm setting > > > > -XX:+UseThreadPriorities > > -XX:ThreadPriorityPolicy=42 > > -XX:+HeapDumpOnOutOfMemoryError > > -Xss256k > > -XX:StringTableSize=103 > > -XX:+AlwaysPreTouch > > -XX:-UseBiasedLocking > > -XX:+UseTLAB > > -XX:+ResizeTLAB > > -XX:+UseNUMA > > -XX:+PerfDisableSharedMem > > -Djava.net.preferIPv4Stack=true > > -XX:+UseG1GC > > -XX:G1RSetUpdatingPauseTimePercent=5 > > -XX:MaxGCPauseMillis=500 > > -XX:+PrintGCDetails > > -XX:+PrintGCDateStamps > > -XX:+PrintHeapAtGC > > -XX:+PrintTenuringDistribution > > -XX:+PrintGCApplicationStoppedTime > > -XX:+PrintPromotionFailure > > -XX:+UseGCLogFileRotation > > -XX:NumberOfGCLogFiles=10 > > -XX:GCLogFileSize=10M > > > > Total memory > > free > > total used free sharedbuffers cached > > Mem: 16434004 16125340 308664 60 1728725565184 > > -/+ buffers/cache: 103872846046720 > > Swap:0 0 0 > > > > Heap settings in cassandra-env.sh > > MAX_HEAP_SIZE="8192M" > > HEAP_NEWSIZE="800M" > > ``` > > > > On Sat, Feb 23, 2019, 10:15 PM Rahul Reddy > wrote: > > Thanks Jeff, > > > > Since low writes and high reads most of the time data in memtables only. > When I noticed intially issue no stables on disk everything in memtable > only. > > > > On Sat, Feb 23, 2019, 10:01 PM Jeff Jirsa wrote: > > Also given your short ttl and low write rate, you may want to think about > how you can keep more in memory - this may mean larger memtable and high > flush thresholds (reading from the memtable), or perhaps the partition > cache (if you are likely to read the same key multiple times). You’ll also > probably win some with basic perf and GC tuning, but can’t really do that > via email. Cassandra-8150 has some pointers. > > -- > > Jeff Jirsa > > > > > On Feb 23, 2019, at 6:52 PM, Jeff Jirsa wrote: > > You’ll only ever have one tombstone per read, so your load is based on > normal read rate not tombstones. The metric isn’t wrong, but it’s not > indicative of a problem here given your data model > > > > You’re using STCS do you may be reading from more than one sstable if you > update column2 for a given column1, otherwise you’re probably just seeing > normal read load. Consider dropping your compression chunk size a bit > (given the sizes in your cfstats I’d probably go to 4K instead of 64k), and > maybe consider LCS or TWCS instead of STCS (Which is appropriate depends on > a lot of factors, but STCS is probably causing a fair bit of unnecessary > compactions and probably is very slow to expire data). > > -- > > Jeff Jirsa > > > > > On Feb 23, 2019, at 6:31 PM, Rahul Reddy wrote: > > Do you see anything wrong with this metric. > > > > metric to scan tombstones > > > increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) > > > > And sametime CPU Spike to 50% whenever I see high tombstone alert. > > > > On Sat, Feb 23, 2019, 9:25 PM Jeff Jirsa wrote: > > Your schema is such that you’ll never read more than one tombstone per > select (unless you’re also doing range reads / table scans that you didn’t > mention) - I’m not quite sure what you’re alerting on, but you’re not going > to have tombstone problems with that table / that select. > > -- > > Jeff Jirsa > > > > > On Feb 23, 2019, at 5:55 PM, Rahul Reddy wrote: > > Changing gcgs didn't help > > > > CREATE KEYSPACE ksname WITH replication = {'class': > 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes = > true; > > > > > > ```CREATE TABLE keyspace."table" ( > > "column1" text PRIMARY KEY, > > "column2" text > > ) WITH bloom_filter_fp_chance = 0.01 > > AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} > > AND comment = '' > > AND compaction = {'class': > 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', > 'max_threshold': '32', 'min_threshold': '4'} > > AND compression = {'chunk_length_in_kb': '64', 'class': > 'org.apache.cassandra.io.compress.LZ4Compressor'} > > AND crc_check_chance = 1.0 > > AND dclocal_read_repair_chance = 0.1 > > AND default_time_to_live = 18000 > > AND gc_grace_seconds = 60 > > AND max_index_interval = 2048 > > AND memtable_flush_period_in_ms = 0 > > AND min_index_interval = 128 > > AND read_repair_chance = 0.0 > > AND speculative_retry = '99PERCENTILE'; > > > > flushed table and took tsstabledump > > grep -i '"expired" : true' SSTables.txt|wc -l > > 16439 > > grep -i '"expired" : false' SSTables.t
RE: Tombstones in memtable
When the CPU utilization spikes from 5-10% to 50%, how many nodes does it happen to at the same time? From: Rahul Reddy [mailto:rahulreddy1...@gmail.com] Sent: Saturday, February 23, 2019 7:26 PM To: user@cassandra.apache.org Subject: Re: Tombstones in memtable ```jvm setting -XX:+UseThreadPriorities -XX:ThreadPriorityPolicy=42 -XX:+HeapDumpOnOutOfMemoryError -Xss256k -XX:StringTableSize=103 -XX:+AlwaysPreTouch -XX:-UseBiasedLocking -XX:+UseTLAB -XX:+ResizeTLAB -XX:+UseNUMA -XX:+PerfDisableSharedMem -Djava.net.preferIPv4Stack=true -XX:+UseG1GC -XX:G1RSetUpdatingPauseTimePercent=5 -XX:MaxGCPauseMillis=500 -XX:+PrintGCDetails -XX:+PrintGCDateStamps -XX:+PrintHeapAtGC -XX:+PrintTenuringDistribution -XX:+PrintGCApplicationStoppedTime -XX:+PrintPromotionFailure -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=10 -XX:GCLogFileSize=10M Total memory free total used free sharedbuffers cached Mem: 16434004 16125340 308664 60 1728725565184 -/+ buffers/cache: 103872846046720 Swap:0 0 0 Heap settings in cassandra-env.sh MAX_HEAP_SIZE="8192M" HEAP_NEWSIZE="800M" ``` On Sat, Feb 23, 2019, 10:15 PM Rahul Reddy wrote: Thanks Jeff, Since low writes and high reads most of the time data in memtables only. When I noticed intially issue no stables on disk everything in memtable only. On Sat, Feb 23, 2019, 10:01 PM Jeff Jirsa wrote: Also given your short ttl and low write rate, you may want to think about how you can keep more in memory - this may mean larger memtable and high flush thresholds (reading from the memtable), or perhaps the partition cache (if you are likely to read the same key multiple times). You’ll also probably win some with basic perf and GC tuning, but can’t really do that via email. Cassandra-8150 has some pointers. -- Jeff Jirsa On Feb 23, 2019, at 6:52 PM, Jeff Jirsa wrote: You’ll only ever have one tombstone per read, so your load is based on normal read rate not tombstones. The metric isn’t wrong, but it’s not indicative of a problem here given your data model You’re using STCS do you may be reading from more than one sstable if you update column2 for a given column1, otherwise you’re probably just seeing normal read load. Consider dropping your compression chunk size a bit (given the sizes in your cfstats I’d probably go to 4K instead of 64k), and maybe consider LCS or TWCS instead of STCS (Which is appropriate depends on a lot of factors, but STCS is probably causing a fair bit of unnecessary compactions and probably is very slow to expire data). -- Jeff Jirsa On Feb 23, 2019, at 6:31 PM, Rahul Reddy wrote: Do you see anything wrong with this metric. metric to scan tombstones increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) And sametime CPU Spike to 50% whenever I see high tombstone alert. On Sat, Feb 23, 2019, 9:25 PM Jeff Jirsa wrote: Your schema is such that you’ll never read more than one tombstone per select (unless you’re also doing range reads / table scans that you didn’t mention) - I’m not quite sure what you’re alerting on, but you’re not going to have tombstone problems with that table / that select. -- Jeff Jirsa On Feb 23, 2019, at 5:55 PM, Rahul Reddy wrote: Changing gcgs didn't help CREATE KEYSPACE ksname WITH replication = {'class': 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes = true; ```CREATE TABLE keyspace."table" ( "column1" text PRIMARY KEY, "column2" text ) WITH bloom_filter_fp_chance = 0.01 AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} AND comment = '' AND compaction = {'class': 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', 'max_threshold': '32', 'min_threshold': '4'} AND compression = {'chunk_length_in_kb': '64', 'class': 'org.apache.cassandra.io.compress.LZ4Compressor'} AND crc_check_chance = 1.0 AND dclocal_read_repair_chance = 0.1 AND default_time_to_live = 18000 AND gc_grace_seconds = 60 AND max_index_interval = 2048 AND memtable_flush_period_in_ms = 0 AND min_index_interval = 128 AND read_repair_chance = 0.0 AND speculative_retry = '99PERCENTILE'; flushed table and took tsstabledump grep -i '"expired" : true' SSTables.txt|wc -l 16439 grep -i '"expired" : false' SSTables.txt |wc -l 2657 ttl is 4 hours. INSERT INTO keyspace."TABLE_NAME" ("column1", "column2") VALUES (?, ?) USING TTL(4hours) ?'; SELECT * FROM keyspace."TABLE_NAME" WHERE "column1" = ?'; metric to scan tombstones increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) during peak hours. we only have couple of hundred inserts and 5-8k reads/s per node. ``` ```table
Re: Tombstones in memtable
G1GC with an 8g heap may be slower than CMS. Also you don’t typically set new gen size on G1. Again though - what problem are you solving here? If you’re serving reads and sitting under 50% cpu, it’s not clear to me what you’re trying to fix. Tombstones scanned won’t matter for your table, so if that’s your only concern, I’d ignore it. -- Jeff Jirsa > On Feb 23, 2019, at 7:26 PM, Rahul Reddy wrote: > > ```jvm setting > > -XX:+UseThreadPriorities > -XX:ThreadPriorityPolicy=42 > -XX:+HeapDumpOnOutOfMemoryError > -Xss256k > -XX:StringTableSize=103 > -XX:+AlwaysPreTouch > -XX:-UseBiasedLocking > -XX:+UseTLAB > -XX:+ResizeTLAB > -XX:+UseNUMA > -XX:+PerfDisableSharedMem > -Djava.net.preferIPv4Stack=true > -XX:+UseG1GC > -XX:G1RSetUpdatingPauseTimePercent=5 > -XX:MaxGCPauseMillis=500 > -XX:+PrintGCDetails > -XX:+PrintGCDateStamps > -XX:+PrintHeapAtGC > -XX:+PrintTenuringDistribution > -XX:+PrintGCApplicationStoppedTime > -XX:+PrintPromotionFailure > -XX:+UseGCLogFileRotation > -XX:NumberOfGCLogFiles=10 > -XX:GCLogFileSize=10M > > Total memory > free > total used free sharedbuffers cached > Mem: 16434004 16125340 308664 60 1728725565184 > -/+ buffers/cache: 103872846046720 > Swap:0 0 0 > > Heap settings in cassandra-env.sh > MAX_HEAP_SIZE="8192M" > HEAP_NEWSIZE="800M" > ``` > >> On Sat, Feb 23, 2019, 10:15 PM Rahul Reddy wrote: >> Thanks Jeff, >> >> Since low writes and high reads most of the time data in memtables only. >> When I noticed intially issue no stables on disk everything in memtable >> only. >> >>> On Sat, Feb 23, 2019, 10:01 PM Jeff Jirsa wrote: >>> Also given your short ttl and low write rate, you may want to think about >>> how you can keep more in memory - this may mean larger memtable and high >>> flush thresholds (reading from the memtable), or perhaps the partition >>> cache (if you are likely to read the same key multiple times). You’ll also >>> probably win some with basic perf and GC tuning, but can’t really do that >>> via email. Cassandra-8150 has some pointers. >>> >>> -- >>> Jeff Jirsa >>> >>> On Feb 23, 2019, at 6:52 PM, Jeff Jirsa wrote: You’ll only ever have one tombstone per read, so your load is based on normal read rate not tombstones. The metric isn’t wrong, but it’s not indicative of a problem here given your data model. You’re using STCS do you may be reading from more than one sstable if you update column2 for a given column1, otherwise you’re probably just seeing normal read load. Consider dropping your compression chunk size a bit (given the sizes in your cfstats I’d probably go to 4K instead of 64k), and maybe consider LCS or TWCS instead of STCS (Which is appropriate depends on a lot of factors, but STCS is probably causing a fair bit of unnecessary compactions and probably is very slow to expire data). -- Jeff Jirsa > On Feb 23, 2019, at 6:31 PM, Rahul Reddy wrote: > > Do you see anything wrong with this metric. > > metric to scan tombstones > increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) > > And sametime CPU Spike to 50% whenever I see high tombstone alert. > >> On Sat, Feb 23, 2019, 9:25 PM Jeff Jirsa wrote: >> Your schema is such that you’ll never read more than one tombstone per >> select (unless you’re also doing range reads / table scans that you >> didn’t mention) - I’m not quite sure what you’re alerting on, but you’re >> not going to have tombstone problems with that table / that select. >> >> -- >> Jeff Jirsa >> >> >>> On Feb 23, 2019, at 5:55 PM, Rahul Reddy >>> wrote: >>> >>> Changing gcgs didn't help >>> >>> CREATE KEYSPACE ksname WITH replication = {'class': >>> 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes >>> = true; >>> >>> >>> ```CREATE TABLE keyspace."table" ( >>> "column1" text PRIMARY KEY, >>> "column2" text >>> ) WITH bloom_filter_fp_chance = 0.01 >>> AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} >>> AND comment = '' >>> AND compaction = {'class': >>> 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', >>> 'max_threshold': '32', 'min_threshold': '4'} >>> AND compression = {'chunk_length_in_kb': '64', 'class': >>> 'org.apache.cassandra.io.compress.LZ4Compressor'} >>> AND crc_check_chance = 1.0 >>> AND dclocal_read_repair_chance = 0.1 >>> AND default_time_to_live = 18000 >>> AND gc_grace_seconds = 60 >>> AND max_index_interval = 2048 >>> AND memtable_flush_period_in_ms = 0 >>> AND min_index_interval = 128 >>> AND read_repair_
Re: Tombstones in memtable
```jvm setting -XX:+UseThreadPriorities -XX:ThreadPriorityPolicy=42 -XX:+HeapDumpOnOutOfMemoryError -Xss256k -XX:StringTableSize=103 -XX:+AlwaysPreTouch -XX:-UseBiasedLocking -XX:+UseTLAB -XX:+ResizeTLAB -XX:+UseNUMA -XX:+PerfDisableSharedMem -Djava.net.preferIPv4Stack=true -XX:+UseG1GC -XX:G1RSetUpdatingPauseTimePercent=5 -XX:MaxGCPauseMillis=500 -XX:+PrintGCDetails -XX:+PrintGCDateStamps -XX:+PrintHeapAtGC -XX:+PrintTenuringDistribution -XX:+PrintGCApplicationStoppedTime -XX:+PrintPromotionFailure -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=10 -XX:GCLogFileSize=10M Total memory free total used free sharedbuffers cached Mem: 16434004 16125340 308664 60 1728725565184 -/+ buffers/cache: 103872846046720 Swap:0 0 0 Heap settings in cassandra-env.sh MAX_HEAP_SIZE="8192M" HEAP_NEWSIZE="800M" ``` On Sat, Feb 23, 2019, 10:15 PM Rahul Reddy wrote: > Thanks Jeff, > > Since low writes and high reads most of the time data in memtables only. > When I noticed intially issue no stables on disk everything in memtable > only. > > On Sat, Feb 23, 2019, 10:01 PM Jeff Jirsa wrote: > >> Also given your short ttl and low write rate, you may want to think about >> how you can keep more in memory - this may mean larger memtable and high >> flush thresholds (reading from the memtable), or perhaps the partition >> cache (if you are likely to read the same key multiple times). You’ll also >> probably win some with basic perf and GC tuning, but can’t really do that >> via email. Cassandra-8150 has some pointers. >> >> -- >> Jeff Jirsa >> >> >> On Feb 23, 2019, at 6:52 PM, Jeff Jirsa wrote: >> >> You’ll only ever have one tombstone per read, so your load is based on >> normal read rate not tombstones. The metric isn’t wrong, but it’s not >> indicative of a problem here given your data model. >> >> You’re using STCS do you may be reading from more than one sstable if you >> update column2 for a given column1, otherwise you’re probably just seeing >> normal read load. Consider dropping your compression chunk size a bit >> (given the sizes in your cfstats I’d probably go to 4K instead of 64k), and >> maybe consider LCS or TWCS instead of STCS (Which is appropriate depends on >> a lot of factors, but STCS is probably causing a fair bit of unnecessary >> compactions and probably is very slow to expire data). >> >> -- >> Jeff Jirsa >> >> >> On Feb 23, 2019, at 6:31 PM, Rahul Reddy >> wrote: >> >> Do you see anything wrong with this metric. >> >> metric to scan tombstones >> >> increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) >> >> And sametime CPU Spike to 50% whenever I see high tombstone alert. >> >> On Sat, Feb 23, 2019, 9:25 PM Jeff Jirsa wrote: >> >>> Your schema is such that you’ll never read more than one tombstone per >>> select (unless you’re also doing range reads / table scans that you didn’t >>> mention) - I’m not quite sure what you’re alerting on, but you’re not going >>> to have tombstone problems with that table / that select. >>> >>> -- >>> Jeff Jirsa >>> >>> >>> On Feb 23, 2019, at 5:55 PM, Rahul Reddy >>> wrote: >>> >>> Changing gcgs didn't help >>> >>> CREATE KEYSPACE ksname WITH replication = {'class': >>> 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes = >>> true; >>> >>> >>> ```CREATE TABLE keyspace."table" ( >>> "column1" text PRIMARY KEY, >>> "column2" text >>> ) WITH bloom_filter_fp_chance = 0.01 >>> AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} >>> AND comment = '' >>> AND compaction = {'class': >>> 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', >>> 'max_threshold': '32', 'min_threshold': '4'} >>> AND compression = {'chunk_length_in_kb': '64', 'class': >>> 'org.apache.cassandra.io.compress.LZ4Compressor'} >>> AND crc_check_chance = 1.0 >>> AND dclocal_read_repair_chance = 0.1 >>> AND default_time_to_live = 18000 >>> AND gc_grace_seconds = 60 >>> AND max_index_interval = 2048 >>> AND memtable_flush_period_in_ms = 0 >>> AND min_index_interval = 128 >>> AND read_repair_chance = 0.0 >>> AND speculative_retry = '99PERCENTILE'; >>> >>> flushed table and took tsstabledump >>> grep -i '"expired" : true' SSTables.txt|wc -l >>> 16439 >>> grep -i '"expired" : false' SSTables.txt |wc -l >>> 2657 >>> >>> ttl is 4 hours. >>> >>> INSERT INTO keyspace."TABLE_NAME" ("column1", "column2") VALUES (?, ?) >>> USING TTL(4hours) ?'; >>> SELECT * FROM keyspace."TABLE_NAME" WHERE "column1" = ?'; >>> >>> metric to scan tombstones >>> >>> increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) >>> >>> during peak hours. we only have couple of hundred inserts and 5-8k >>> reads/s per node. >>> ``` >>> >>> ```tablestats >>> Read Count: 605231874 >>> Read Latency: 0.021268529760215503 ms.
Re: Tombstones in memtable
Thanks Jeff, Since low writes and high reads most of the time data in memtables only. When I noticed intially issue no stables on disk everything in memtable only. On Sat, Feb 23, 2019, 10:01 PM Jeff Jirsa wrote: > Also given your short ttl and low write rate, you may want to think about > how you can keep more in memory - this may mean larger memtable and high > flush thresholds (reading from the memtable), or perhaps the partition > cache (if you are likely to read the same key multiple times). You’ll also > probably win some with basic perf and GC tuning, but can’t really do that > via email. Cassandra-8150 has some pointers. > > -- > Jeff Jirsa > > > On Feb 23, 2019, at 6:52 PM, Jeff Jirsa wrote: > > You’ll only ever have one tombstone per read, so your load is based on > normal read rate not tombstones. The metric isn’t wrong, but it’s not > indicative of a problem here given your data model. > > You’re using STCS do you may be reading from more than one sstable if you > update column2 for a given column1, otherwise you’re probably just seeing > normal read load. Consider dropping your compression chunk size a bit > (given the sizes in your cfstats I’d probably go to 4K instead of 64k), and > maybe consider LCS or TWCS instead of STCS (Which is appropriate depends on > a lot of factors, but STCS is probably causing a fair bit of unnecessary > compactions and probably is very slow to expire data). > > -- > Jeff Jirsa > > > On Feb 23, 2019, at 6:31 PM, Rahul Reddy wrote: > > Do you see anything wrong with this metric. > > metric to scan tombstones > > increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) > > And sametime CPU Spike to 50% whenever I see high tombstone alert. > > On Sat, Feb 23, 2019, 9:25 PM Jeff Jirsa wrote: > >> Your schema is such that you’ll never read more than one tombstone per >> select (unless you’re also doing range reads / table scans that you didn’t >> mention) - I’m not quite sure what you’re alerting on, but you’re not going >> to have tombstone problems with that table / that select. >> >> -- >> Jeff Jirsa >> >> >> On Feb 23, 2019, at 5:55 PM, Rahul Reddy >> wrote: >> >> Changing gcgs didn't help >> >> CREATE KEYSPACE ksname WITH replication = {'class': >> 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes = >> true; >> >> >> ```CREATE TABLE keyspace."table" ( >> "column1" text PRIMARY KEY, >> "column2" text >> ) WITH bloom_filter_fp_chance = 0.01 >> AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} >> AND comment = '' >> AND compaction = {'class': >> 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', >> 'max_threshold': '32', 'min_threshold': '4'} >> AND compression = {'chunk_length_in_kb': '64', 'class': >> 'org.apache.cassandra.io.compress.LZ4Compressor'} >> AND crc_check_chance = 1.0 >> AND dclocal_read_repair_chance = 0.1 >> AND default_time_to_live = 18000 >> AND gc_grace_seconds = 60 >> AND max_index_interval = 2048 >> AND memtable_flush_period_in_ms = 0 >> AND min_index_interval = 128 >> AND read_repair_chance = 0.0 >> AND speculative_retry = '99PERCENTILE'; >> >> flushed table and took tsstabledump >> grep -i '"expired" : true' SSTables.txt|wc -l >> 16439 >> grep -i '"expired" : false' SSTables.txt |wc -l >> 2657 >> >> ttl is 4 hours. >> >> INSERT INTO keyspace."TABLE_NAME" ("column1", "column2") VALUES (?, ?) >> USING TTL(4hours) ?'; >> SELECT * FROM keyspace."TABLE_NAME" WHERE "column1" = ?'; >> >> metric to scan tombstones >> >> increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) >> >> during peak hours. we only have couple of hundred inserts and 5-8k >> reads/s per node. >> ``` >> >> ```tablestats >> Read Count: 605231874 >> Read Latency: 0.021268529760215503 ms. >> Write Count: 2763352 >> Write Latency: 0.027924007871599422 ms. >> Pending Flushes: 0 >> Table: name >> SSTable count: 1 >> Space used (live): 1413203 >> Space used (total): 1413203 >> Space used by snapshots (total): 0 >> Off heap memory used (total): 28813 >> SSTable Compression Ratio: 0.5015090954531143 >> Number of partitions (estimate): 19568 >> Memtable cell count: 573 >> Memtable data size: 22971 >> Memtable off heap memory used: 0 >> Memtable switch count: 6 >> Local read count: 529868919 >> Local read latency: 0.020 ms >> Local write count: 2707371 >> Local write latency: 0.024 ms >> Pending flushes: 0 >> Percent repaired: 0.0 >> Bloom filter false positives: 1 >> Bloom filter false ratio: 0.0 >> Bloom filter space used: 23888 >> Bloom filter off heap memory used: 23880 >> Index summary off heap memory used: 4717 >> Compression metadata off heap memory used: 216 >> Compacted partition minimum bytes: 73 >> Compacted partition maximum bytes: 124 >> Compacted partition mean bytes: 99 >> Average live cells per slice (last five minutes): 1.0 >> Maximum live c
Re: Tombstones in memtable
Also given your short ttl and low write rate, you may want to think about how you can keep more in memory - this may mean larger memtable and high flush thresholds (reading from the memtable), or perhaps the partition cache (if you are likely to read the same key multiple times). You’ll also probably win some with basic perf and GC tuning, but can’t really do that via email. Cassandra-8150 has some pointers. -- Jeff Jirsa > On Feb 23, 2019, at 6:52 PM, Jeff Jirsa wrote: > > You’ll only ever have one tombstone per read, so your load is based on normal > read rate not tombstones. The metric isn’t wrong, but it’s not indicative of > a problem here given your data model. > > You’re using STCS do you may be reading from more than one sstable if you > update column2 for a given column1, otherwise you’re probably just seeing > normal read load. Consider dropping your compression chunk size a bit (given > the sizes in your cfstats I’d probably go to 4K instead of 64k), and maybe > consider LCS or TWCS instead of STCS (Which is appropriate depends on a lot > of factors, but STCS is probably causing a fair bit of unnecessary > compactions and probably is very slow to expire data). > > -- > Jeff Jirsa > > >> On Feb 23, 2019, at 6:31 PM, Rahul Reddy wrote: >> >> Do you see anything wrong with this metric. >> >> metric to scan tombstones >> increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) >> >> And sametime CPU Spike to 50% whenever I see high tombstone alert. >> >>> On Sat, Feb 23, 2019, 9:25 PM Jeff Jirsa wrote: >>> Your schema is such that you’ll never read more than one tombstone per >>> select (unless you’re also doing range reads / table scans that you didn’t >>> mention) - I’m not quite sure what you’re alerting on, but you’re not going >>> to have tombstone problems with that table / that select. >>> >>> -- >>> Jeff Jirsa >>> >>> On Feb 23, 2019, at 5:55 PM, Rahul Reddy wrote: Changing gcgs didn't help CREATE KEYSPACE ksname WITH replication = {'class': 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes = true; ```CREATE TABLE keyspace."table" ( "column1" text PRIMARY KEY, "column2" text ) WITH bloom_filter_fp_chance = 0.01 AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} AND comment = '' AND compaction = {'class': 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', 'max_threshold': '32', 'min_threshold': '4'} AND compression = {'chunk_length_in_kb': '64', 'class': 'org.apache.cassandra.io.compress.LZ4Compressor'} AND crc_check_chance = 1.0 AND dclocal_read_repair_chance = 0.1 AND default_time_to_live = 18000 AND gc_grace_seconds = 60 AND max_index_interval = 2048 AND memtable_flush_period_in_ms = 0 AND min_index_interval = 128 AND read_repair_chance = 0.0 AND speculative_retry = '99PERCENTILE'; flushed table and took tsstabledump grep -i '"expired" : true' SSTables.txt|wc -l 16439 grep -i '"expired" : false' SSTables.txt |wc -l 2657 ttl is 4 hours. INSERT INTO keyspace."TABLE_NAME" ("column1", "column2") VALUES (?, ?) USING TTL(4hours) ?'; SELECT * FROM keyspace."TABLE_NAME" WHERE "column1" = ?'; metric to scan tombstones increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) during peak hours. we only have couple of hundred inserts and 5-8k reads/s per node. ``` ```tablestats Read Count: 605231874 Read Latency: 0.021268529760215503 ms. Write Count: 2763352 Write Latency: 0.027924007871599422 ms. Pending Flushes: 0 Table: name SSTable count: 1 Space used (live): 1413203 Space used (total): 1413203 Space used by snapshots (total): 0 Off heap memory used (total): 28813 SSTable Compression Ratio: 0.5015090954531143 Number of partitions (estimate): 19568 Memtable cell count: 573 Memtable data size: 22971 Memtable off heap memory used: 0 Memtable switch count: 6 Local read count: 529868919 Local read latency: 0.020 ms Local write count: 2707371 Local write latency: 0.024 ms Pending flushes: 0 Percent repaired: 0.0 Bloom filter false positives: 1 Bloom filter false ratio: 0.0 Bloom filter space used: 23888 Bloom filter off heap memory used: 23880 Index summary off heap memory u
Re: Tombstones in memtable
You’ll only ever have one tombstone per read, so your load is based on normal read rate not tombstones. The metric isn’t wrong, but it’s not indicative of a problem here given your data model. You’re using STCS do you may be reading from more than one sstable if you update column2 for a given column1, otherwise you’re probably just seeing normal read load. Consider dropping your compression chunk size a bit (given the sizes in your cfstats I’d probably go to 4K instead of 64k), and maybe consider LCS or TWCS instead of STCS (Which is appropriate depends on a lot of factors, but STCS is probably causing a fair bit of unnecessary compactions and probably is very slow to expire data). -- Jeff Jirsa > On Feb 23, 2019, at 6:31 PM, Rahul Reddy wrote: > > Do you see anything wrong with this metric. > > metric to scan tombstones > increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) > > And sametime CPU Spike to 50% whenever I see high tombstone alert. > >> On Sat, Feb 23, 2019, 9:25 PM Jeff Jirsa wrote: >> Your schema is such that you’ll never read more than one tombstone per >> select (unless you’re also doing range reads / table scans that you didn’t >> mention) - I’m not quite sure what you’re alerting on, but you’re not going >> to have tombstone problems with that table / that select. >> >> -- >> Jeff Jirsa >> >> >>> On Feb 23, 2019, at 5:55 PM, Rahul Reddy wrote: >>> >>> Changing gcgs didn't help >>> >>> CREATE KEYSPACE ksname WITH replication = {'class': >>> 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes = >>> true; >>> >>> >>> ```CREATE TABLE keyspace."table" ( >>> "column1" text PRIMARY KEY, >>> "column2" text >>> ) WITH bloom_filter_fp_chance = 0.01 >>> AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} >>> AND comment = '' >>> AND compaction = {'class': >>> 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', >>> 'max_threshold': '32', 'min_threshold': '4'} >>> AND compression = {'chunk_length_in_kb': '64', 'class': >>> 'org.apache.cassandra.io.compress.LZ4Compressor'} >>> AND crc_check_chance = 1.0 >>> AND dclocal_read_repair_chance = 0.1 >>> AND default_time_to_live = 18000 >>> AND gc_grace_seconds = 60 >>> AND max_index_interval = 2048 >>> AND memtable_flush_period_in_ms = 0 >>> AND min_index_interval = 128 >>> AND read_repair_chance = 0.0 >>> AND speculative_retry = '99PERCENTILE'; >>> >>> flushed table and took tsstabledump >>> grep -i '"expired" : true' SSTables.txt|wc -l >>> 16439 >>> grep -i '"expired" : false' SSTables.txt |wc -l >>> 2657 >>> >>> ttl is 4 hours. >>> >>> INSERT INTO keyspace."TABLE_NAME" ("column1", "column2") VALUES (?, ?) >>> USING TTL(4hours) ?'; >>> SELECT * FROM keyspace."TABLE_NAME" WHERE "column1" = ?'; >>> >>> metric to scan tombstones >>> increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) >>> >>> during peak hours. we only have couple of hundred inserts and 5-8k reads/s >>> per node. >>> ``` >>> >>> ```tablestats >>> Read Count: 605231874 >>> Read Latency: 0.021268529760215503 ms. >>> Write Count: 2763352 >>> Write Latency: 0.027924007871599422 ms. >>> Pending Flushes: 0 >>> Table: name >>> SSTable count: 1 >>> Space used (live): 1413203 >>> Space used (total): 1413203 >>> Space used by snapshots (total): 0 >>> Off heap memory used (total): 28813 >>> SSTable Compression Ratio: 0.5015090954531143 >>> Number of partitions (estimate): 19568 >>> Memtable cell count: 573 >>> Memtable data size: 22971 >>> Memtable off heap memory used: 0 >>> Memtable switch count: 6 >>> Local read count: 529868919 >>> Local read latency: 0.020 ms >>> Local write count: 2707371 >>> Local write latency: 0.024 ms >>> Pending flushes: 0 >>> Percent repaired: 0.0 >>> Bloom filter false positives: 1 >>> Bloom filter false ratio: 0.0 >>> Bloom filter space used: 23888 >>> Bloom filter off heap memory used: 23880 >>> Index summary off heap memory used: 4717 >>> Compression metadata off heap memory used: 216 >>> Compacted partition minimum bytes: 73 >>> Compacted partition maximum bytes: 124 >>> Compacted partition mean bytes: 99 >>> Average live cells per slice (last five minutes): 1.0 >>> Maximum live cells per slice (last five minutes): 1 >>> Average tombstones per slice (last five minutes): 1.0 >>> Maximum tombstones per slice (last five minutes): 1 >>> Dropped Mutations: 0 >>> >>> histograms
RE: Tombstones in memtable
Rahul, You wrote that during peak hours you only have a couple hundred inserts per node so now I’m not sure why the default settings wouldn’t have worked just fine. I sense there is more to the story. What else could explain those tombstones? From: Rahul Reddy [mailto:rahulreddy1...@gmail.com] Sent: Saturday, February 23, 2019 5:56 PM To: user@cassandra.apache.org Subject: Re: Tombstones in memtable Changing gcgs didn't help CREATE KEYSPACE ksname WITH replication = {'class': 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes = true; ```CREATE TABLE keyspace."table" ( "column1" text PRIMARY KEY, "column2" text ) WITH bloom_filter_fp_chance = 0.01 AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} AND comment = '' AND compaction = {'class': 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', 'max_threshold': '32', 'min_threshold': '4'} AND compression = {'chunk_length_in_kb': '64', 'class': 'org.apache.cassandra.io.compress.LZ4Compressor'} AND crc_check_chance = 1.0 AND dclocal_read_repair_chance = 0.1 AND default_time_to_live = 18000 AND gc_grace_seconds = 60 AND max_index_interval = 2048 AND memtable_flush_period_in_ms = 0 AND min_index_interval = 128 AND read_repair_chance = 0.0 AND speculative_retry = '99PERCENTILE'; flushed table and took tsstabledump grep -i '"expired" : true' SSTables.txt|wc -l 16439 grep -i '"expired" : false' SSTables.txt |wc -l 2657 ttl is 4 hours. INSERT INTO keyspace."TABLE_NAME" ("column1", "column2") VALUES (?, ?) USING TTL(4hours) ?'; SELECT * FROM keyspace."TABLE_NAME" WHERE "column1" = ?'; metric to scan tombstones increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) during peak hours. we only have couple of hundred inserts and 5-8k reads/s per node. ``` ```tablestats Read Count: 605231874 Read Latency: 0.021268529760215503 ms. Write Count: 2763352 Write Latency: 0.027924007871599422 ms. Pending Flushes: 0 Table: name SSTable count: 1 Space used (live): 1413203 Space used (total): 1413203 Space used by snapshots (total): 0 Off heap memory used (total): 28813 SSTable Compression Ratio: 0.5015090954531143 Number of partitions (estimate): 19568 Memtable cell count: 573 Memtable data size: 22971 Memtable off heap memory used: 0 Memtable switch count: 6 Local read count: 529868919 Local read latency: 0.020 ms Local write count: 2707371 Local write latency: 0.024 ms Pending flushes: 0 Percent repaired: 0.0 Bloom filter false positives: 1 Bloom filter false ratio: 0.0 Bloom filter space used: 23888 Bloom filter off heap memory used: 23880 Index summary off heap memory used: 4717 Compression metadata off heap memory used: 216 Compacted partition minimum bytes: 73 Compacted partition maximum bytes: 124 Compacted partition mean bytes: 99 Average live cells per slice (last five minutes): 1.0 Maximum live cells per slice (last five minutes): 1 Average tombstones per slice (last five minutes): 1.0 Maximum tombstones per slice (last five minutes): 1 Dropped Mutations: 0 histograms Percentile SSTables Write Latency Read LatencyPartition Size Cell Count (micros) (micros) (bytes) 50% 000 20.50 17.0886 1 75% 0.00 24.60 20.50 124 1 95% 0.00 35.43 29.52 124 1 98% 0.00 35.43 42.51 124 1 99% 0.00 42.51 51.01 124 1 Min 0.00 8.24 5.7273 0 Max 1.00 42.51152.32 124 1 ``` 3 node in
Re: Tombstones in memtable
Do you see anything wrong with this metric. metric to scan tombstones increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) And sametime CPU Spike to 50% whenever I see high tombstone alert. On Sat, Feb 23, 2019, 9:25 PM Jeff Jirsa wrote: > Your schema is such that you’ll never read more than one tombstone per > select (unless you’re also doing range reads / table scans that you didn’t > mention) - I’m not quite sure what you’re alerting on, but you’re not going > to have tombstone problems with that table / that select. > > -- > Jeff Jirsa > > > On Feb 23, 2019, at 5:55 PM, Rahul Reddy wrote: > > Changing gcgs didn't help > > CREATE KEYSPACE ksname WITH replication = {'class': > 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes = > true; > > > ```CREATE TABLE keyspace."table" ( > "column1" text PRIMARY KEY, > "column2" text > ) WITH bloom_filter_fp_chance = 0.01 > AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} > AND comment = '' > AND compaction = {'class': > 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', > 'max_threshold': '32', 'min_threshold': '4'} > AND compression = {'chunk_length_in_kb': '64', 'class': > 'org.apache.cassandra.io.compress.LZ4Compressor'} > AND crc_check_chance = 1.0 > AND dclocal_read_repair_chance = 0.1 > AND default_time_to_live = 18000 > AND gc_grace_seconds = 60 > AND max_index_interval = 2048 > AND memtable_flush_period_in_ms = 0 > AND min_index_interval = 128 > AND read_repair_chance = 0.0 > AND speculative_retry = '99PERCENTILE'; > > flushed table and took tsstabledump > grep -i '"expired" : true' SSTables.txt|wc -l > 16439 > grep -i '"expired" : false' SSTables.txt |wc -l > 2657 > > ttl is 4 hours. > > INSERT INTO keyspace."TABLE_NAME" ("column1", "column2") VALUES (?, ?) > USING TTL(4hours) ?'; > SELECT * FROM keyspace."TABLE_NAME" WHERE "column1" = ?'; > > metric to scan tombstones > > increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) > > during peak hours. we only have couple of hundred inserts and 5-8k reads/s > per node. > ``` > > ```tablestats > Read Count: 605231874 > Read Latency: 0.021268529760215503 ms. > Write Count: 2763352 > Write Latency: 0.027924007871599422 ms. > Pending Flushes: 0 > Table: name > SSTable count: 1 > Space used (live): 1413203 > Space used (total): 1413203 > Space used by snapshots (total): 0 > Off heap memory used (total): 28813 > SSTable Compression Ratio: 0.5015090954531143 > Number of partitions (estimate): 19568 > Memtable cell count: 573 > Memtable data size: 22971 > Memtable off heap memory used: 0 > Memtable switch count: 6 > Local read count: 529868919 > Local read latency: 0.020 ms > Local write count: 2707371 > Local write latency: 0.024 ms > Pending flushes: 0 > Percent repaired: 0.0 > Bloom filter false positives: 1 > Bloom filter false ratio: 0.0 > Bloom filter space used: 23888 > Bloom filter off heap memory used: 23880 > Index summary off heap memory used: 4717 > Compression metadata off heap memory used: 216 > Compacted partition minimum bytes: 73 > Compacted partition maximum bytes: 124 > Compacted partition mean bytes: 99 > Average live cells per slice (last five minutes): 1.0 > Maximum live cells per slice (last five minutes): 1 > Average tombstones per slice (last five minutes): 1.0 > Maximum tombstones per slice (last five minutes): 1 > Dropped Mutations: 0 > histograms > Percentile SSTables Write Latency Read LatencyPartition > SizeCell Count > (micros) (micros) > (bytes) > 50% 0.00 20.50 17.08 > 86 1 > 75% 0.00 24.60 20.50 > 124 1 > 95% 0.00 35.43 29.52 > 124 1 > 98% 0.00 35.43 42.51 > 124 1 > 99% 0.00 42.51 51.01 > 124 1 > Min 0.00 8.24 5.72 > 73 0 > Max 1.00 42.51152.32 > 124 1 > ``` > > 3 node in dc1 and 3 node in dc2 cluster. With instanc type aws ec2 > m4.xlarge > > On Sat, Feb 23, 2019, 7:47 PM Jeff Jirsa wrote: > >> Would also be good to see your schema (anonymized if needed) and the >> select queries you’re running >> >> >> -- >> Jeff Jirsa >> >> >> On Feb 23, 2019, at 4:37 PM, Rahul Reddy >> wrote: >> >> Thanks Jeff, >> >> I'm having gcgs set to 10 mins and changed the table ttl also to 5 hours >> compared to insert ttl to 4 hours . Tracing on doesn't show any tombstone >> scans for the reads. And also log doesn't show tombstone scan alerts. Has >> the reads are happening 5-8k reads per node during the peak hours it shows >> 1M tombstone
Re: Tombstones in memtable
Your schema is such that you’ll never read more than one tombstone per select (unless you’re also doing range reads / table scans that you didn’t mention) - I’m not quite sure what you’re alerting on, but you’re not going to have tombstone problems with that table / that select. -- Jeff Jirsa > On Feb 23, 2019, at 5:55 PM, Rahul Reddy wrote: > > Changing gcgs didn't help > > CREATE KEYSPACE ksname WITH replication = {'class': > 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes = true; > > > ```CREATE TABLE keyspace."table" ( > "column1" text PRIMARY KEY, > "column2" text > ) WITH bloom_filter_fp_chance = 0.01 > AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} > AND comment = '' > AND compaction = {'class': > 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', > 'max_threshold': '32', 'min_threshold': '4'} > AND compression = {'chunk_length_in_kb': '64', 'class': > 'org.apache.cassandra.io.compress.LZ4Compressor'} > AND crc_check_chance = 1.0 > AND dclocal_read_repair_chance = 0.1 > AND default_time_to_live = 18000 > AND gc_grace_seconds = 60 > AND max_index_interval = 2048 > AND memtable_flush_period_in_ms = 0 > AND min_index_interval = 128 > AND read_repair_chance = 0.0 > AND speculative_retry = '99PERCENTILE'; > > flushed table and took tsstabledump > grep -i '"expired" : true' SSTables.txt|wc -l > 16439 > grep -i '"expired" : false' SSTables.txt |wc -l > 2657 > > ttl is 4 hours. > > INSERT INTO keyspace."TABLE_NAME" ("column1", "column2") VALUES (?, ?) USING > TTL(4hours) ?'; > SELECT * FROM keyspace."TABLE_NAME" WHERE "column1" = ?'; > > metric to scan tombstones > increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) > > during peak hours. we only have couple of hundred inserts and 5-8k reads/s > per node. > ``` > > ```tablestats > Read Count: 605231874 > Read Latency: 0.021268529760215503 ms. > Write Count: 2763352 > Write Latency: 0.027924007871599422 ms. > Pending Flushes: 0 > Table: name > SSTable count: 1 > Space used (live): 1413203 > Space used (total): 1413203 > Space used by snapshots (total): 0 > Off heap memory used (total): 28813 > SSTable Compression Ratio: 0.5015090954531143 > Number of partitions (estimate): 19568 > Memtable cell count: 573 > Memtable data size: 22971 > Memtable off heap memory used: 0 > Memtable switch count: 6 > Local read count: 529868919 > Local read latency: 0.020 ms > Local write count: 2707371 > Local write latency: 0.024 ms > Pending flushes: 0 > Percent repaired: 0.0 > Bloom filter false positives: 1 > Bloom filter false ratio: 0.0 > Bloom filter space used: 23888 > Bloom filter off heap memory used: 23880 > Index summary off heap memory used: 4717 > Compression metadata off heap memory used: 216 > Compacted partition minimum bytes: 73 > Compacted partition maximum bytes: 124 > Compacted partition mean bytes: 99 > Average live cells per slice (last five minutes): 1.0 > Maximum live cells per slice (last five minutes): 1 > Average tombstones per slice (last five minutes): 1.0 > Maximum tombstones per slice (last five minutes): 1 > Dropped Mutations: 0 > > histograms > Percentile SSTables Write Latency Read LatencyPartition Size > Cell Count > (micros) (micros) (bytes) > > 50% 0.00 20.50 17.0886 > 1 > 75% 0.00 24.60 20.50 124 > 1 > 95% 0.00 35.43 29.52 124 > 1 > 98% 0.00 35.43 42.51 124 > 1 > 99% 0.00 42.51 51.01 124 > 1 > Min 0.00 8.24 5.7273 > 0 > Max 1.00 42.51152.32 124 > 1 > ``` > > 3 node in dc1 and 3 node in dc2 cluster. With instanc type aws ec2 m4.xlarge > >> On Sat, Feb 23, 2019, 7:47 PM Jeff Jirsa wrote: >> Would also be good to see your schema (anonymized if needed) and the select >> queries you’re running >> >> >> -- >> Jeff Jirsa >> >> >>> On Feb 23, 2019, at 4:37 PM, Rahul Reddy wrote: >
RE: Tombstones in memtable
Rahul, Please see this DataStax article which suggests you might be using Cassandra as a queue-like dataset – and that’s an anti-pattern for Cassandra. It could be you need to use a different database. It could be your data model is wrong: https://www.datastax.com/dev/blog/cassandra-anti-patterns-queues-and-queue-like-datasets Kenneth Brotman From: Jeff Jirsa [mailto:jji...@gmail.com] Sent: Saturday, February 23, 2019 4:47 PM To: user@cassandra.apache.org Subject: Re: Tombstones in memtable Would also be good to see your schema (anonymized if needed) and the select queries you’re running -- Jeff Jirsa On Feb 23, 2019, at 4:37 PM, Rahul Reddy wrote: Thanks Jeff, I'm having gcgs set to 10 mins and changed the table ttl also to 5 hours compared to insert ttl to 4 hours . Tracing on doesn't show any tombstone scans for the reads. And also log doesn't show tombstone scan alerts. Has the reads are happening 5-8k reads per node during the peak hours it shows 1M tombstone scans count per read. On Fri, Feb 22, 2019, 11:46 AM Jeff Jirsa wrote: If all of your data is TTL’d and you never explicitly delete a cell without using s TTL, you can probably drop your GCGS to 1 hour (or less). Which compaction strategy are you using? You need a way to clear out those tombstones. There exist tombstone compaction sub properties that can help encourage compaction to grab sstables just because they’re full of tombstones which will probably help you. -- Jeff Jirsa On Feb 22, 2019, at 8:37 AM, Kenneth Brotman wrote: Can we see the histogram? Why wouldn’t you at times have that many tombstones? Makes sense. Kenneth Brotman From: Rahul Reddy [mailto:rahulreddy1...@gmail.com] Sent: Thursday, February 21, 2019 7:06 AM To: user@cassandra.apache.org Subject: Tombstones in memtable We have small table records are about 5k . All the inserts comes as 4hr ttl and we have table level ttl 1 day and gc grace seconds has 3 hours. We do 5k reads a second during peak load During the peak load seeing Alerts for tomstone scanned histogram reaching million. Cassandra version 3.11.1. Please let me know how can this tombstone scan can be avoided in memtable
Re: Tombstones in memtable
Changing gcgs didn't help CREATE KEYSPACE ksname WITH replication = {'class': 'NetworkTopologyStrategy', 'dc1': '3', 'dc2': '3'} AND durable_writes = true; ```CREATE TABLE keyspace."table" ( "column1" text PRIMARY KEY, "column2" text ) WITH bloom_filter_fp_chance = 0.01 AND caching = {'keys': 'ALL', 'rows_per_partition': 'NONE'} AND comment = '' AND compaction = {'class': 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy', 'max_threshold': '32', 'min_threshold': '4'} AND compression = {'chunk_length_in_kb': '64', 'class': 'org.apache.cassandra.io.compress.LZ4Compressor'} AND crc_check_chance = 1.0 AND dclocal_read_repair_chance = 0.1 AND default_time_to_live = 18000 AND gc_grace_seconds = 60 AND max_index_interval = 2048 AND memtable_flush_period_in_ms = 0 AND min_index_interval = 128 AND read_repair_chance = 0.0 AND speculative_retry = '99PERCENTILE'; flushed table and took tsstabledump grep -i '"expired" : true' SSTables.txt|wc -l 16439 grep -i '"expired" : false' SSTables.txt |wc -l 2657 ttl is 4 hours. INSERT INTO keyspace."TABLE_NAME" ("column1", "column2") VALUES (?, ?) USING TTL(4hours) ?'; SELECT * FROM keyspace."TABLE_NAME" WHERE "column1" = ?'; metric to scan tombstones increase(cassandra_Table_TombstoneScannedHistogram{keyspace="mykeyspace",Table="tablename",function="Count"}[5m]) during peak hours. we only have couple of hundred inserts and 5-8k reads/s per node. ``` ```tablestats Read Count: 605231874 Read Latency: 0.021268529760215503 ms. Write Count: 2763352 Write Latency: 0.027924007871599422 ms. Pending Flushes: 0 Table: name SSTable count: 1 Space used (live): 1413203 Space used (total): 1413203 Space used by snapshots (total): 0 Off heap memory used (total): 28813 SSTable Compression Ratio: 0.5015090954531143 Number of partitions (estimate): 19568 Memtable cell count: 573 Memtable data size: 22971 Memtable off heap memory used: 0 Memtable switch count: 6 Local read count: 529868919 Local read latency: 0.020 ms Local write count: 2707371 Local write latency: 0.024 ms Pending flushes: 0 Percent repaired: 0.0 Bloom filter false positives: 1 Bloom filter false ratio: 0.0 Bloom filter space used: 23888 Bloom filter off heap memory used: 23880 Index summary off heap memory used: 4717 Compression metadata off heap memory used: 216 Compacted partition minimum bytes: 73 Compacted partition maximum bytes: 124 Compacted partition mean bytes: 99 Average live cells per slice (last five minutes): 1.0 Maximum live cells per slice (last five minutes): 1 Average tombstones per slice (last five minutes): 1.0 Maximum tombstones per slice (last five minutes): 1 Dropped Mutations: 0 histograms Percentile SSTables Write Latency Read LatencyPartition Size Cell Count (micros) (micros) (bytes) 50% 0.00 20.50 17.0886 1 75% 0.00 24.60 20.50 124 1 95% 0.00 35.43 29.52 124 1 98% 0.00 35.43 42.51 124 1 99% 0.00 42.51 51.01 124 1 Min 0.00 8.24 5.7273 0 Max 1.00 42.51152.32 124 1 ``` 3 node in dc1 and 3 node in dc2 cluster. With instanc type aws ec2 m4.xlarge On Sat, Feb 23, 2019, 7:47 PM Jeff Jirsa wrote: > Would also be good to see your schema (anonymized if needed) and the > select queries you’re running > > > -- > Jeff Jirsa > > > On Feb 23, 2019, at 4:37 PM, Rahul Reddy wrote: > > Thanks Jeff, > > I'm having gcgs set to 10 mins and changed the table ttl also to 5 hours > compared to insert ttl to 4 hours . Tracing on doesn't show any tombstone > scans for the reads. And also log doesn't show tombstone scan alerts. Has > the reads are happening 5-8k reads per node during the peak hours it shows > 1M tombstone scans count per read. > > On Fri, Feb 22, 2019, 11:46 AM Jeff Jirsa wrote: > >> If all of your data is TTL’d and you never explicitly delete a cell >> without using s TTL, you can probably drop your GCGS to 1 hour (or less). >> >> Which compaction strategy are you using? You need a way to clear out >> those tombstones. There exist tombstone compaction sub properties that can >> help encourage compaction to grab sstables just because they’re full of >> tombstones which will probably help you. >> >> >> -- >> Jeff Jirsa >> >> >> On Feb 22, 2019, at 8:37 AM, Kenneth Brotman < >> kenbrot...@yahoo.com.invalid> wrote: >> >> Can we see the histogram? Why wouldn’t you at times have that many >> tombstones? Makes sense. >> >> >> >> Kenneth Brotman >> >> >> >> *From:* Rahul Reddy [mailto:rahulreddy1.
Re: Tombstones in memtable
Would also be good to see your schema (anonymized if needed) and the select queries you’re running -- Jeff Jirsa > On Feb 23, 2019, at 4:37 PM, Rahul Reddy wrote: > > Thanks Jeff, > > I'm having gcgs set to 10 mins and changed the table ttl also to 5 hours > compared to insert ttl to 4 hours . Tracing on doesn't show any tombstone > scans for the reads. And also log doesn't show tombstone scan alerts. Has > the reads are happening 5-8k reads per node during the peak hours it shows 1M > tombstone scans count per read. > >> On Fri, Feb 22, 2019, 11:46 AM Jeff Jirsa wrote: >> If all of your data is TTL’d and you never explicitly delete a cell without >> using s TTL, you can probably drop your GCGS to 1 hour (or less). >> >> Which compaction strategy are you using? You need a way to clear out those >> tombstones. There exist tombstone compaction sub properties that can help >> encourage compaction to grab sstables just because they’re full of >> tombstones which will probably help you. >> >> >> -- >> Jeff Jirsa >> >> >>> On Feb 22, 2019, at 8:37 AM, Kenneth Brotman >>> wrote: >>> >>> Can we see the histogram? Why wouldn’t you at times have that many >>> tombstones? Makes sense. >>> >>> >>> >>> Kenneth Brotman >>> >>> >>> >>> From: Rahul Reddy [mailto:rahulreddy1...@gmail.com] >>> Sent: Thursday, February 21, 2019 7:06 AM >>> To: user@cassandra.apache.org >>> Subject: Tombstones in memtable >>> >>> >>> >>> We have small table records are about 5k . >>> >>> All the inserts comes as 4hr ttl and we have table level ttl 1 day and gc >>> grace seconds has 3 hours. We do 5k reads a second during peak load During >>> the peak load seeing Alerts for tomstone scanned histogram reaching million. >>> >>> Cassandra version 3.11.1. Please let me know how can this tombstone scan >>> can be avoided in memtable
Re: Tombstones in memtable
I’m not parsing this - did the lower gcgs help or not ? Seeing the table histograms is the next step if this is still a problem The table level TTL doesn’t matter if you set a TTL on each insert -- Jeff Jirsa > On Feb 23, 2019, at 4:37 PM, Rahul Reddy wrote: > > Thanks Jeff, > > I'm having gcgs set to 10 mins and changed the table ttl also to 5 hours > compared to insert ttl to 4 hours . Tracing on doesn't show any tombstone > scans for the reads. And also log doesn't show tombstone scan alerts. Has > the reads are happening 5-8k reads per node during the peak hours it shows 1M > tombstone scans count per read. > >> On Fri, Feb 22, 2019, 11:46 AM Jeff Jirsa wrote: >> If all of your data is TTL’d and you never explicitly delete a cell without >> using s TTL, you can probably drop your GCGS to 1 hour (or less). >> >> Which compaction strategy are you using? You need a way to clear out those >> tombstones. There exist tombstone compaction sub properties that can help >> encourage compaction to grab sstables just because they’re full of >> tombstones which will probably help you. >> >> >> -- >> Jeff Jirsa >> >> >>> On Feb 22, 2019, at 8:37 AM, Kenneth Brotman >>> wrote: >>> >>> Can we see the histogram? Why wouldn’t you at times have that many >>> tombstones? Makes sense. >>> >>> >>> >>> Kenneth Brotman >>> >>> >>> >>> From: Rahul Reddy [mailto:rahulreddy1...@gmail.com] >>> Sent: Thursday, February 21, 2019 7:06 AM >>> To: user@cassandra.apache.org >>> Subject: Tombstones in memtable >>> >>> >>> >>> We have small table records are about 5k . >>> >>> All the inserts comes as 4hr ttl and we have table level ttl 1 day and gc >>> grace seconds has 3 hours. We do 5k reads a second during peak load During >>> the peak load seeing Alerts for tomstone scanned histogram reaching million. >>> >>> Cassandra version 3.11.1. Please let me know how can this tombstone scan >>> can be avoided in memtable
Re: Tombstones in memtable
Thanks Jeff, I'm having gcgs set to 10 mins and changed the table ttl also to 5 hours compared to insert ttl to 4 hours . Tracing on doesn't show any tombstone scans for the reads. And also log doesn't show tombstone scan alerts. Has the reads are happening 5-8k reads per node during the peak hours it shows 1M tombstone scans count per read. On Fri, Feb 22, 2019, 11:46 AM Jeff Jirsa wrote: > If all of your data is TTL’d and you never explicitly delete a cell > without using s TTL, you can probably drop your GCGS to 1 hour (or less). > > Which compaction strategy are you using? You need a way to clear out those > tombstones. There exist tombstone compaction sub properties that can help > encourage compaction to grab sstables just because they’re full of > tombstones which will probably help you. > > > -- > Jeff Jirsa > > > On Feb 22, 2019, at 8:37 AM, Kenneth Brotman > wrote: > > Can we see the histogram? Why wouldn’t you at times have that many > tombstones? Makes sense. > > > > Kenneth Brotman > > > > *From:* Rahul Reddy [mailto:rahulreddy1...@gmail.com > ] > *Sent:* Thursday, February 21, 2019 7:06 AM > *To:* user@cassandra.apache.org > *Subject:* Tombstones in memtable > > > > We have small table records are about 5k . > > All the inserts comes as 4hr ttl and we have table level ttl 1 day and gc > grace seconds has 3 hours. We do 5k reads a second during peak load During > the peak load seeing Alerts for tomstone scanned histogram reaching million. > > Cassandra version 3.11.1. Please let me know how can this tombstone scan > can be avoided in memtable > >
Re: tombstones threshold warning
Thanks Ken, further investigating what I found is the tombstones which I am seeing are from null values in the collection objects. Tombstones are also inserted into when initial collection values are inserted but seems like they are not counted towards threshold warning and do not show up in tracing. These tests I did on 3.11.3 version of cassandra. Record inserted with values in collection objects - I see tombstones but they do not show up in tracing. "partition" : { "key" : [ "e7cd5752-bc0d-4157-a80f-7523add8dbcd" ], "position" : 121 }, "rows" : [ { "type" : "row", "position" : 528, "clustering" : [ "ELVIS" ], "liveness_info" : { "tstamp" : "2019-02-21T21:34:06.574848Z" }, "cells" : [ { "name" : "frozen_race", "value" : {"race_title": "Ronde van Gelderland", "race_date": "2015-04-19 00:00:00.000Z", "race_time": "03:22:23"} }, { "name" : "basics_udt", "deletion_info" : { "marked_deleted" : "2019-02-21T21:34:06.574847Z", "local_delete_time" : "2019-02-21T21:34:06Z" } }, { "name" : "basics_udt", "path" : [ "birthday" ], "value" : "1993-06-18 00:00:00.000Z" }, { "name" : "basics_udt", "path" : [ "nationality" ], "value" : "New Zealand" }, { "name" : "events_list", "deletion_info" : { "marked_deleted" : "2019-02-21T21:34:06.574847Z", "local_delete_time" : "2019-02-21T21:34:06Z" } }, { "name" : "events_list", "path" : [ "6ab41176-3620-11e9-81ac-87caa6eca935" ], "value" : "list-element1" }, { "name" : "events_list", "path" : [ "6ab41177-3620-11e9-81ac-87caa6eca935" ], "value" : "list-element2" }, { "name" : "frozen_race_list", "deletion_info" : { "marked_deleted" : "2019-02-21T21:34:06.574847Z", "local_delete_time" : "2019-02-21T21:34:06Z" } }, { "name" : "frozen_race_list", "path" : [ "6ab41178-3620-11e9-81ac-87caa6eca935" ], "value" : {"race_title": "Rabobank 7-Dorpenomloop Aalburg", "race_date": "2015-05-09 00:00:00.000Z", "race_time": "02:58:33"} }, { "name" : "frozen_race_list", "path" : [ "6ab41179-3620-11e9-81ac-87caa6eca935" ], "value" : {"race_title": "Ronde van Gelderland", "race_date": "2015-04-19 00:00:00.000Z", "race_time": "03:22:23"} }, { "name" : "teams_map", "deletion_info" : { "marked_deleted" : "2019-02-21T21:34:06.574847Z", "local_delete_time" : "2019-02-21T21:34:06Z" } }, { "name" : "teams_map", "path" : [ "1" ], "value" : "map-value1" }, { "name" : "teams_map", "path" : [ "2" ], "value" : "map-value2" }, { "name" : "teams_set", "deletion_info" : { "marked_deleted" : "2019-02-21T21:34:06.574847Z", "local_delete_time" : "2019-02-21T21:34:06Z" } }, { "name" : "teams_set", "path" : [ "set-element1" ], "value" : "" }, { "name" : "teams_set", "path" : [ "set-element2" ], "value" : "" } cassandra@cqlsh:dev_ticket> select * from collsndudt where id = e7cd5752-bc0d-4157-a80f-7523add8dbcd and lastname = 'ELVIS'; id | lastname | basics_udt | events_list| frozen_race | frozen_race_list | teams_map | teams_set --+--+---++---+---++-- e7cd5752-bc0d-4157-a80f-7523add8dbcd |ELVIS | {birthday: '1993-06-18 00:00:00.00+', nationality: 'New Zealand', height: null, weight: null} | ['list-element1', 'list-element2'] | {race_title: 'Ronde van Gelderland', race_date: '2015-04-19 00:00:00.00+', race_time: '03:22:23'} | [{race_title: 'Rabobank 7-Dorpenomloop Aalburg', race_date: '2015-05-09 00:00:00.00+', race_time: '02:58:33'}, {race_title: 'Ronde van Gelderland', race_date: '2015-04-19 00:00:00.00+', race_time: '03:22:23'}] | {1: 'map-value1', 2: 'map-value2'} | {'set-element1', 'set-element2'} (1 rows) Tracing session: aa82f2c0-3621-11e9-81ac-87caa6eca935 activity | timestamp | source| source_elapsed | client -++---++--- Execute CQL3 query | 2019-02-21 21:43:03.404000 | 10.216.87.180 | 0 | 127.0.0.1 Parsing select * from collsndudt where id = e7cd5752-bc0d-4157-a80f-7523add8dbcd and lastname = 'ELVIS'; [CoreTh