June 19, 2013

Comment: Slow DROP TABLE

… rationale for not using tmpfs, and using a disk store like ext3: 1) Our database is typically 100% cached (both data and…-4 GB +) sorts that we’d like to spill to disk. It’s okay if these are somewhat slow. I/O… large sorts (which afaics, we definitely do need on disk, since our ram is mostly dedicated to caching the db / indexes). I…

Post: Paul McCullagh answers your questions about PBXT

… because each transaction effectively gets its own snapshot of the database. And write locks are not acquired when updating. Instead, the… and deletes them from the database. The Checkpointer flushes the data written by the Writer to disk. It is also responsible for… returned by the SELECT. These locks are all stored in RAM. The format is quite compact (especially when row IDs are…

Post: Impact of logging on MySQL’s performance

… 5150 @ 2.66GHz, 32GB RAM. There are 8 disks in RAID10(a mirror of 4+4 striped disks). Software It was used MySQL… is 10GiB in terms of database size. The test was run with 1, 20 and 100 database connections Results To reduce random… the highest rate observed. IO-bound case – 100 warehouses Database size 10GiB # of connections No logging, NOTPM Logging queries > 1…

Post: Effect of adaptive_flushing

… was Solaris 10 with 8 disk RAID10 and 2 32GB SSDs used for ZIL and L2ARC, 72G RAM and 40G buffer pool…: ~2GB of uncheckpointed data. mysql> SHOW INNODB STATUS\G …. Database pages 2318457 Old database pages 855816 Modified db pages 457902 Log flushed up… question of system performance impact… More aggressive flushing means more disk IO and possibly  other impact on the system, which could…

Comment: MySQL Partitioning - can save you or kill you

…. Though there are nightly backups of the disk, still better to use InnoDb (though disk requirements increase 2.5 times but that… shall also run the application server along with the Database and So, RAM would be doubled and processor cores increased (new server… worth mentioning.. This is my first ever encounter with a database, so, request you please ignore any stupidity and guide…

Post: Percona Server scalability on multi-cores server

… lab that represents the next generation of commodity servers for databases. It’s a Cisco UCS C250 server, powered by two… memory. It has 384GB of RAM, which is actually more space than the disks contain.  The disks are 270GB in total, with… read-write benchmarks using from 1 to 32 threads. The database size was 100 million rows ( about 23GB of data). (Starting…

Post: RAID and Scale Out Discussions

…extra performance from your IO subsystem. Spreading the database among say 10 commodity boxes is often expensive…people. RAID can be indeed slower than direct disks. For example for BoardReader now indexing almost …people using 2*2 Opterons with 32GB of RAM and 10-14 hard drives. Both solutions …

Comment: Full Text Search Webinar Questions Followup

…: > Since RT indexes are in volatile memory, not stored on disk, you are responsible for integrating new data with the on… their magic in RAM indeed, but they save incoming writes into a binary write-ahead log, just like a database would. You…. Second, you never have to somehow forcibly store RT to disk manually and “integrate” new data. RT should handle that automatically…

Post: Falcon Storage Engine Design Review

… single size, this is complicated. If I have 8GB of RAM I can assume I want 4GB allocated to row cache… for database only, so if you have started transaction accessed table in database A and a while after accessed table in database B… it. [+/-] Only committed changes go to the disk Innodb modifies data in the database when you change it, Falcon only when it…

Post: Guidance for MySQL Optimizer Developers

… of disk IOs/Seeks in same way for all data sets. In practice some people have their database 100% in RAM (even for Disk tables such MyISAM or Innodb) others keep database on SSD which has…