… to random IO caused by the COW (Copy on Write). SSD‘s solved the issue for us, plus we still benefit from the improved speed of having SSD‘s. SSD are more costly than spinning media, but the speed… write buffering, so make sure these are turned off in InnoDB.
Comment: ZFS on Linux and MySQL
June 7, 2013 By 17 Comments
… not hitting a bottleneck caused by compression. If I use SSD for L2ARC, I’ll need to do the same for… for a MySQL dba to steal 20GB memory from the Innodb buffer pool to give it to the filesystem. I took…
Comment: ZFS on Linux and MySQL
May 24, 2013 By 17 Comments
@JDempster: I could give the SSD to xfs also with Flashcache and the like. Don’t forget all these jbods have a raid controller write cache in front of them. I also did the Innodb tuning. @Nils: no fuse, direct kernel support. Look here: http://zfsonlinux.org/
Comment: Benchmarking Percona Server TokuDB vs InnoDB
May 22, 2013 By 32 Comments
Hi Vadim, I can confirm the steady downfall of InnoDB throughput down to ~1500 insert/sec (and counting) while TokuDB … RAM and a very fast LSI MegaRaid backed storage with SSD Cache. Aurimas worked on that machine a month ago.
Post: Benchmarking Percona Server TokuDB vs InnoDB
May 7, 2013 By 32 Comments
… fill TokuDB tables with 1bln of rows on this SSD, and projected InnoDB performance on this size will be the same or… SSD innodb_flush_neighbor_pages = none innodb_adaptive_flushing_method = keep_average innodb_file_per_table = true innodb_data_file_path = ibdata1:100M:autoextend innodb_flush…
Post: Virident vCache vs. FlashCache: Part 2
May 17, 2013 By 3 Comments
… plus: innodb_read_io_threads = 16 innodb_write_io_threads = 16 We call this configuration B. The next one contained four SSD-specific optimizations based partially on some earlier work that I’d done with this Virident card (configuration C): innodb_io…: #####fixed innodb options innodb_file_format = barracuda innodb_buffer_pool_size = 4G innodb_file_per_table = true innodb_data_file_path = ibdata1:100M innodb_flush_method…
Comment: Benchmarking Percona Server TokuDB vs InnoDB
May 7, 2013 By 32 Comments
The point at 685 sec when InnoDB performance drops, is that when data doesn’t fit all in RAM anymore? I would in general expect to see benefits from TokuDB when workload is diskbound. You could artificially reduce InnoDB buffer pool (and corresponding Tokutek setting) to have more SSD vs RAM.
Post: SSD, XFS, LVM, fsync, write cache, barrier and lost transactions
March 2, 2009 By 32 Comments
… InnoDB on SSD outperforms RAID 10, but recently I faced issue which can make previous results inconsistent. In short words using Intel SSD X25-E card with enabled write-cache (which is default and most performance mode) does not warranty storing all InnoDB… on SSD and running very primitive test with INSERT INTO fs VALUES(0) into auto-increment field into InnoDB table. InnoDB parameters are innodb…
Post: Intel SSD 910 vs HDD RAID in tpcc-mysql benchmark
September 11, 2012 By 6 Comments
…, disks: Seagate ST9750420AS 750GB, 2.5″, 7200RPM, 16MB, SATA. Intel SSD 910 (software RAID over 2x200GB devices) Filesystem: ext4 Software OS… to remove warm-up phase Parameters to vary: we vary innodb_buffer_pool_size:25, 50, 75GB to have different memory… internals + flushing logic. Now, all these results are received with innodb_flush_log_at_trx_commit=2, which in comments to…
Post: Fast storage: 8 SSD Intel X-25M 80GB benchmarks
January 18, 2010 By 15 Comments
…: – For sequential reads you can get pretty decent results from SSD (230MB/sec on 4+ threads) – Cards connected in hardware raid… InnoDB transactional logs on rotation based drives instead of SSD in my InnoDB on FusionIO benchmarks). So in summary I can say With SSD… single FusionIO card, however there is important point that with SSD you may “hot”remove and insert cards, while for FusionIO…
