News for hackers. Stuff that matters.

A comment on Immutability, MVCC, and garbage collection (2013). Parent comment

Re:Immutability, MVCC, and garbage collection (2013) by databass on Sunday February 01, 2015 @10:57AM (#8980308)
Do you also have stats on the high percentile latencies, besides the average? Sounds like your avoidance of compaction pauses ought to lead to lower latency at the high percentiles.
[ Parent | on HN ]
Re:Immutability, MVCC, and garbage collection (2013) by hyc_symas on Sunday February 01, 2015 @11:16AM (#8980412)
See the table of data here http://symas.com/mdb/hyperdex/#100M

  100M records, 1M ops
 		MinLatency(us)	AvgLatency(us)	95th%ile(ms)	99th%ile(ms)	MaxLatency(ms)	Runtime(sec)	Throughput(ops/sec)	CPUtime (mm:ss)
  LMDB update	256		33565		130		209		637		8385		119			4:21.41
  LMDB read	215		33493		130		207		817
  LevelDB update 241		63660		231		385		20370		15863		63			17:27
  LevelDB read	188		63250		230		383		7904
(It's formatted properly if you follow the link)

Also look at the latency distribution compared to MySQL's InnoDB http://symas.com/mdb/memcache/

[ Parent | on HN ]