Testbed and methods
Benchmarking filesystems is not an easy task for many reasons: there are endless usage scenarios, each with their specific requirements and usage patterns; each filesystem has its custom options that can modify its behavior considerably; different kernel releases can produce different benchmark results.
So, in order to give you consistent, reproducible results, I had to do some very important choices about the benchmarks, the options and the kernel to use. The benchmark suite is composed of some theoretical and real world tests:
- sysbench (version 0.4.12) is a semi-synthetic test useful to benchmark database performance;
- fs_mark (version 3.3) is a synthetic test aimed at measuring file creation speed;
- postgresql (version 9.2.4) and mysql (version 5.5.31) are the two benchmarked database systems;
- tar/untar and cat are representative of common, real world usage patterns;
- finally, filefrag is a very helpful filesystem utility used to evaluate file fragmentation.
All filesystems where created with default options (which imply that write barriers were enabled for all FS), using the mkfs Linux utility. In detail, mount options as shown by the mount command were:
ext3: /dev/sda3 on /opt type ext3 (rw,relatime,seclabel,data=ordered)
ext4: /dev/sda3 on /opt type ext4 (rw,relatime,seclabel,data=ordered)
xfs: /dev/sda3 on /opt type xfs (rw,relatime,seclabel,attr2,inode64,noquota)
btrfs: /dev/sda3 on /opt type btrfs (rw,relatime,seclabel,space_cache)
Files fragmentation level was checked after sysbench and fs_mark large-file test.
All test were runs on a Dell D620 laptop. The complete system specifications are:
- Core2 T7200 CPU @ 2.0 GHz
- 4 GB of DDR2-667 RAM
- Quadro NVS110 videocard (used in text-only mode)
- a Seagate ST980825AS 7200 RPM 80 GB SATA hard disk drive (in IDE compatibility mode, as the D620's BIOS does not support AHCI operation)
- O.S. Fedora 18 amd64 with kernel version kernel-3.6.10-4.fc18.x86_64
The internal hard disk was partitioned into three slices: a first ~9 GB ext4 partition for the root directory, a second ~4 GB partition for the swap file and a third ~60 GB partition (mounted on /opt) for testing purposes. CPU frequency/voltage scaling was disabled and the system was used in text-only mode (no X running here). All benchmarked services (basically postgresql and mysql) were reconfigured to store their data into the 60 GB testing partition mounted on /opt.