Josh Berkus wrote:
On 12/6/10 6:13 PM, Tom Lane wrote:
Josh Berkus j...@agliodbs.com writes:
OK, patch coming then. Right now test_fsync aborts when O_DIRECT fails.
What should I have it do instead?
Report that it fails, and keep testing the other methods.
Patch attached.
Which means if we just export the macros, we would still not have caught
this. I would like to share all the defines --- I am just saying it
isn't trivial.
I just called all the define variables manually rather than relying on
the macros. Seemed to work fine.
--
Greg, All:
Results for Solaris 10u8, on ZFS on a 7-drive attached storage array:
bash-3.00# ./test_fsync -f /dbdata/pgdata/test.out
Loops = 1
Simple write:
8k write 59988.002/second
Compare file sync methods using one write:
open_datasync 8k write
Josh Berkus wrote:
On 12/6/10 6:13 PM, Tom Lane wrote:
Josh Berkus j...@agliodbs.com writes:
OK, patch coming then. Right now test_fsync aborts when O_DIRECT fails.
What should I have it do instead?
Report that it fails, and keep testing the other methods.
Patch attached.
Tom Lane wrote:
Josh Berkus j...@agliodbs.com writes:
Making it support O_DIRECT would be possible but more complex; I don't
see the point unless we think we're going to have open_sync_with_odirect
as a seperate option.
Whether it's complex or not isn't really the issue. The issue is
On 12/6/10 6:13 PM, Tom Lane wrote:
Josh Berkus j...@agliodbs.com writes:
OK, patch coming then. Right now test_fsync aborts when O_DIRECT fails.
What should I have it do instead?
Report that it fails, and keep testing the other methods.
Patch attached. Includes a fair amount of comment
On 12/5/10 2:12 PM, Greg Smith wrote:
Josh Berkus wrote:
I modified test_fsync in two ways to run this; first, to make it support
O_DIRECT, and second to make it run in the *current* directory.
Patch please? I agree with the latter change; what test_fsync does is
surprising.
Attached.
Josh Berkus j...@agliodbs.com writes:
Making it support O_DIRECT would be possible but more complex; I don't
see the point unless we think we're going to have open_sync_with_odirect
as a seperate option.
Whether it's complex or not isn't really the issue. The issue is that
what test_fsync is
On 12/06/2010 08:38 PM, Tom Lane wrote:
Josh Berkusj...@agliodbs.com writes:
Making it support O_DIRECT would be possible but more complex; I don't
see the point unless we think we're going to have open_sync_with_odirect
as a seperate option.
Whether it's complex or not isn't really the
Whether it's complex or not isn't really the issue. The issue is that
what test_fsync is testing had better match what the backend does, or
people will be making choices based on not-comparable test results.
I think we should have test_fsync just automatically fold in O_DIRECT
the same way
Josh Berkus j...@agliodbs.com writes:
OK, patch coming then. Right now test_fsync aborts when O_DIRECT fails.
What should I have it do instead?
Report that it fails, and keep testing the other methods.
regards, tom lane
--
Sent via pgsql-hackers mailing list
Josh Berkus wrote:
I modified test_fsync in two ways to run this; first, to make it support
O_DIRECT, and second to make it run in the *current* directory.
Patch please? I agree with the latter change; what test_fsync does is
surprising.
I suggested a while ago that we refactor test_fsync
All,
While I have this machine available I've been trying to run some
performance tests using pgbench and various wal_sync_methods. However,
I seem to be maxing out at the speed of pgbench itself; no matter which
wal_sync_method I use (including fsync), it tops out at around 2750 TPS.
Of
All,
So, this week I've had my hands on a medium-high-end test system where I
could test various wal_sync_methods. This is a 24-core Intel Xeon
machine with 72GB of ram, and 8 internal 10K SAS disks attached to a
raid controller with 512MB BBU write cache. 2 of the disks are in a
RAID1, which
Marti Raudsepp wrote:
PostgreSQL's default settings change when built with Linux kernel
headers 2.6.33 or newer. As discussed on the pgsql-performance list,
this causes a significant performance regression:
http://archives.postgresql.org/pgsql-performance/2010-10/msg00602.php
NB! I am not
Tom Lane wrote:
I'm hoping that Greg Smith will take the lead on testing
this, since he seems to have spent the most time in the area so far.
It's not coincidence that the chapter of my book I convinced the
publisher to release as a sample is the one that covers this area; this
mess has
Hi list,
PostgreSQL's default settings change when built with Linux kernel
headers 2.6.33 or newer. As discussed on the pgsql-performance list,
this causes a significant performance regression:
http://archives.postgresql.org/pgsql-performance/2010-10/msg00602.php
NB! I am not proposing to change
Marti Raudsepp ma...@juffo.org writes:
PostgreSQL's default settings change when built with Linux kernel
headers 2.6.33 or newer. As discussed on the pgsql-performance list,
this causes a significant performance regression:
http://archives.postgresql.org/pgsql-performance/2010-10/msg00602.php
On Fri, Nov 5, 2010 at 20:13, Tom Lane t...@sss.pgh.pa.us wrote:
I'm less than convinced this is the right approach ...
If open_dsync is so bad for performance on Linux, maybe it's bad
everywhere? Should we be rethinking the default preference order?
Sure, maybe for PostgreSQL 9.1
But the
Marti Raudsepp ma...@juffo.org writes:
On Fri, Nov 5, 2010 at 20:13, Tom Lane t...@sss.pgh.pa.us wrote:
If open_dsync is so bad for performance on Linux, maybe it's bad
everywhere? Â Should we be rethinking the default preference order?
So I think we should aim to fix old versions first. Do
On Fri, Nov 5, 2010 at 21:20, Tom Lane t...@sss.pgh.pa.us wrote:
Marti Raudsepp ma...@juffo.org writes:
On Fri, Nov 5, 2010 at 20:13, Tom Lane t...@sss.pgh.pa.us wrote:
If open_dsync is so bad for performance on Linux, maybe it's bad
everywhere? Should we be rethinking the default preference
Marti Raudsepp ma...@juffo.org writes:
On Fri, Nov 5, 2010 at 21:20, Tom Lane t...@sss.pgh.pa.us wrote:
What's that got to do with it?
I'm not sure what you're asking.
Surely changing the default wal_sync_method for all OSes in
maintenance releases is out of the question, no?
Well, if we
On Friday 05 November 2010 19:13:47 Tom Lane wrote:
Marti Raudsepp ma...@juffo.org writes:
PostgreSQL's default settings change when built with Linux kernel
headers 2.6.33 or newer. As discussed on the pgsql-performance list,
this causes a significant performance regression:
On Fri, Nov 5, 2010 at 22:16, Tom Lane t...@sss.pgh.pa.us wrote:
I don't really think that change the default on Linux is that
much nicer than change the default everywhere when it comes to
what we ought to consider back-patching. In any case, you're getting
ahead of the game: we need to
Tom Lane wrote:
If open_dsync is so bad for performance on Linux, maybe it's bad
everywhere? Should we be rethinking the default preference order?
And I've seen the expected sync write performance gain over fdatasync on
a system with a battery-backed cache running VxFS on Linux, because
Andres Freund and...@anarazel.de writes:
On Friday 05 November 2010 19:13:47 Tom Lane wrote:
If open_dsync is so bad for performance on Linux, maybe it's bad
everywhere? Should we be rethinking the default preference order?
I fail to see how it could be beneficial on *any* non-buggy
On Friday 05 November 2010 22:53:37 Greg Smith wrote:
If open_dsync is so bad for performance on Linux, maybe it's bad
everywhere? Should we be rethinking the default preference order?
And I've seen the expected sync write performance gain over fdatasync on
a system with a
I think the original idea was that if you had a dedicated WAL drive then
sync-on-write would be reasonable. But that was a very long time ago
and I'm not sure that the system's behavior is anything like what it was
then; for that matter I'm not sure we had proof that it was an optimal
Josh Berkus j...@agliodbs.com writes:
What plaforms do we need to test to get a reasonable idea? Solaris,
FreeBSD, Windows?
At least. I'm hoping that Greg Smith will take the lead on testing
this, since he seems to have spent the most time in the area so far.
regards,
On 11/5/10 3:31 PM, Tom Lane wrote:
Josh Berkus j...@agliodbs.com writes:
What plaforms do we need to test to get a reasonable idea? Solaris,
FreeBSD, Windows?
At least. I'm hoping that Greg Smith will take the lead on testing
this, since he seems to have spent the most time in the area so
30 matches
Mail list logo