The Performance Of EXT4 Then & Now

Published on January 19, 2010
Written by Michael Larabel
Page 1 of 6
Discuss This Article

Over the past week there has been a lot of talk about the EXT4 file-system following the announcement that Google is migrating their EXT2 file-systems to EXT4. Their reasons for this transition to EXT4 are attributed to the easy migration process and Google engineers are pleased with this file-system's performance. However, as we mentioned in that news post last week and in many other articles over the past weeks and months, EXT4 is not as great of a contender as it was in the past, well, for some tests at least. The performance of the EXT4 file-system commonly goes down with new kernel releases and not up, as kernel developers continue to introduce new safeguards to address potential data loss problems that initially plagued some EXT4 users. For our latest EXT4 benchmarks we have numbers that show this file-system's performance using a vanilla 2.6.28 kernel (when EXT4 was marked as stable) and then every major kernel release up through the latest Linux 2.6.33 release candidate.

We had installed Ubuntu 9.04 for this testing and left everything in its stock configuration except for swapping out the kernels. The kernels we used for testing were all obtained from the Ubuntu kernel mainline PPA. These kernels were the 64-bit versions of the 2.6.28, 2.6.29, 2.6.30, 2.6.31, 2.6.32, and 2.6.33-rc4 releases. We tested out a Linux 2.6.33 kernel release candidate as Phoromatic Tracker running in our kernel test farm had found a few performance drops on a solid-state drive with the EXT4 file-system in the current kernel development cycle, with new results being uploaded daily via Phoromatic at kernel-tracker.phoromatic.com. The EXT4 file-system mount options were left at their defaults (though at the end of this article we also have some results using the nobarrier mount option).

This latest round of file-system testing used the IOzone, Threaded I/O Tester, PostgreSQL, PostMark, Dbench, AIO-Stress, and FS-Mark tests, which were run under the Phoronix Test Suite. The system for this testing was an ASRock ION 330HT-BD NetTop with an Intel Atom 330 processor clocked at 1.80GHz (overclocked), ASRock AMCP7AION-HT motherboard, 2GB of system memory, NVIDIA GeForce 9400M ION graphics, and a 320GB Seagate ST9320325AS SATA HDD.

<< Previous Page
1
Latest Hardware Reviews
  1. Intel Haswell HD Graphics 4600 vs. AMD Radeon Graphics On Linux
  2. Intel Haswell HD Graphics 4600 Performance On Ubuntu Linux
  3. Intel Core i7 4770K "Haswell" Benchmarks On Ubuntu Linux
  4. The First Experience Of Intel Haswell On Linux
Latest Software Articles
  1. Optimized Binaries Provide Great Benefits For Intel Haswell
  2. 11-Way Linux, BSD Platform Comparison
  3. SNA Acceleration Works Great For Intel Core i7 Haswell
  4. The Linux Evolution For Intel Haswell's Performance
Latest Linux News
  1. Ubuntu Announces Carrier Advisory Group
  2. Qt 5.1 Release Candidate 1 Has Arrived
  3. In-Fighting Continues Over Mir On Non-Unity Ubuntu
  4. Subversion 1.8 Presents New Features
  5. LLVM 3.3 Officially Released
  6. LLVM/Clang Now Uses Loop Vectorizer At New Levels
  7. Intel GPU Driver Tries To Rip Out FBDEV Support
  8. Coreboot Doing AMD USB 3.0, Q35 QEMU Emulation
  9. VP9 Codec Now Enabled By Default In Chrome
  10. openSUSE 13.1 M2 Plays On PulseAudio 4.0
  11. Debian 7.1 Rounds In Some Bug-Fixes
Latest Forum Talk
  1. In-Fighting Continues Over Mir On Non-Unity Ubuntu
  2. Vote for GOG to add Linux versions of games they...
  3. Intel Haswell HD Graphics 4600 vs. AMD Radeon...
  4. Intel GPU Driver Tries To Rip Out FBDEV Support
  5. Mir Still Causing Concerns By Ubuntu Derivatives
  6. Ubuntu Announces Carrier Advisory Group
  1. Computers
  2. Display Drivers
  3. Graphics Cards
  4. Motherboards
  5. Peripherals
  6. Processors
  7. Software
  8. Operating Systems
  9. All Articles
  1. Linux Benchmarking
  2. OpenBenchmarking.org
  3. Phoronix Test Suite