| |||||||||||||
|
| |||||||||||||
Flushing out pdflushFlushing out pdflushPosted Apr 7, 2009 20:08 UTC (Tue) by jzbiciak (✭ supporter ✭, #5246)In reply to: Flushing out pdflush by mjcoder Parent article: Flushing out pdflush Hmmm... At a given point of time, there are between two and eight pdflush threads running in the system.vs. With a ten-disk btrfs filesystem, per-BDI flushing performed 25% fasterCould a noticeable part of the 25% boost be attributed to a 25% boost in number of flushing threads? A 10-disk btrfs filesystem ought to be generating traffic on all 10 spindles, right?
(Log in to post comments)
Flushing out pdflush Posted Apr 17, 2009 12:39 UTC (Fri) by axboe (✭ supporter ✭, #904) [Link]
Actually, no. With btrfs, currently it assigns a per-fs backing device to each inode. So for that particular case, you have just a single bdi flusher thread running even for the 10 disks.
Flushing out pdflush Posted Feb 10, 2011 8:25 UTC (Thu) by bergwolf (guest, #55931) [Link]
Then why does per-bdi flusher improves that much performance for btrfs? If the key idea is *per-bdi*, there is little difference for btrfs. But where does the performance come from?
|
|
||||||||||||