[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [rdiff-backup-users] Performance
From: |
Scott Lamb |
Subject: |
Re: [rdiff-backup-users] Performance |
Date: |
Tue, 13 Feb 2007 08:24:35 -0800 |
On Feb 13, 2007, at 7:14 AM, Charles Duffy wrote:
All that said, it would be interesting to do some benchmarking to
see where time is actually being spent -- waiting for network
latency, waiting for the filesystem or doing things in userspace.
oprofile should easily distinguish between the latter two cases;
more primitive tools (comparing wall-clock/user/system execution,
for instance) should provide more general data on the former.
I would also like to see those numbers. The former seems likely, and
possibly easily fixable - if there's a small fixed buffer size
somewhere in rdiff-backup, it could mean a serious hit on high
bandwidth*delay connections.
And if it is doing things in userspace, "python -m profile -s cum
rdiff-backup ..." would be interesting to see.
- [rdiff-backup-users] Performance, Corey Puffalt, 2007/02/11
- Re: [rdiff-backup-users] Performance, Jim C. Nasby, 2007/02/12
- Re: [rdiff-backup-users] Performance, Dave Howorth, 2007/02/13
- Re: [rdiff-backup-users] Performance, Greg Freemyer, 2007/02/13
- Re: [rdiff-backup-users] Performance, Charles Duffy, 2007/02/13
- Re: [rdiff-backup-users] Performance,
Scott Lamb <=
- Re: [rdiff-backup-users] Performance, Corey Puffalt, 2007/02/13
- Re: [rdiff-backup-users] Performance, rdiff, 2007/02/13
- Re: [rdiff-backup-users] Performance, Scott Lamb, 2007/02/13
- Re: [rdiff-backup-users] Performance, Dave Howorth, 2007/02/14