Re: Inode Lock Scalability V4

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Nick Piggin
Date: Saturday, October 16, 2010 - 7:55 pm

On Sun, Oct 17, 2010 at 01:47:59PM +1100, Dave Chinner wrote:

The worst-case microbenchmark is not a "significant performance
regression". It is a worst case demonstration. With the parallel
workloads, are you referring to your postmark xfs workload? It was
actually due to lazy LRU, IIRC. I didn't think RCU overhead was
noticable there actually.

Anyway, I've already gone over this couple of months ago when we
were discussing it. We know it could cause some small regressions,
if they are small it is considered acceptable and outweighed
greatly by fastpath speedup. And I have a design to do slab RCU
which can be used if regressions are large. Linus signed off on
this, in fact. Why weren't you debating it then?




--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
Inode Lock Scalability V4, Dave Chinner, (Sat Oct 16, 1:13 am)
[PATCH 01/19] fs: switch bdev inode bdi's correctly, Dave Chinner, (Sat Oct 16, 1:13 am)
[PATCH 02/19] kernel: add bl_list, Dave Chinner, (Sat Oct 16, 1:13 am)
[PATCH 05/19] fs: inode split IO and LRU lists, Dave Chinner, (Sat Oct 16, 1:13 am)
[PATCH 06/19] fs: Clean up inode reference counting, Dave Chinner, (Sat Oct 16, 1:14 am)
[PATCH 08/19] fs: rework icount to be a locked variable, Dave Chinner, (Sat Oct 16, 1:14 am)
[PATCH 10/19] fs: Introduce per-bucket inode hash locks, Dave Chinner, (Sat Oct 16, 1:14 am)
[PATCH 16/19] fs: icache remove inode_lock, Dave Chinner, (Sat Oct 16, 1:14 am)
Re: [PATCH 02/19] kernel: add bl_list, Nick Piggin, (Sat Oct 16, 2:51 am)
Re: [PATCH 01/19] fs: switch bdev inode bdi's correctly, Christoph Hellwig, (Sat Oct 16, 9:31 am)
Re: [PATCH 02/19] kernel: add bl_list, Christoph Hellwig, (Sat Oct 16, 9:32 am)
Re: [PATCH 04/19] fs: Implement lazy LRU updates for inodes., Christoph Hellwig, (Sat Oct 16, 9:59 am)
Re: [PATCH 04/19] fs: Implement lazy LRU updates for inodes., Christoph Hellwig, (Sat Oct 16, 5:47 pm)
Re: [PATCH 04/19] fs: Implement lazy LRU updates for inodes., Christoph Hellwig, (Sat Oct 16, 5:47 pm)
Re: [PATCH 03/19] fs: Convert nr_inodes and nr_unused to p ..., Christoph Hellwig, (Sat Oct 16, 6:12 pm)
Re: [PATCH 17/19] fs: Reduce inode I_FREEING and factor in ..., Christoph Hellwig, (Sat Oct 16, 6:30 pm)
Re: Inode Lock Scalability V4, Dave Chinner, (Sat Oct 16, 7:47 pm)
Re: Inode Lock Scalability V4, Nick Piggin, (Sat Oct 16, 7:55 pm)
Re: Inode Lock Scalability V4, Nick Piggin, (Sat Oct 16, 7:57 pm)
Re: Inode Lock Scalability V4, Dave Chinner, (Sat Oct 16, 11:10 pm)
Re: Inode Lock Scalability V4, Nick Piggin, (Sat Oct 16, 11:34 pm)
Re: [PATCH 19/19] fs: do not assign default i_ino in new_inode, Christoph Hellwig, (Mon Oct 18, 7:48 am)