From: | David Mosberger <davidm(at)napali(dot)hpl(dot)hp(dot)com> |
---|---|
To: | markw(at)osdl(dot)org |
Cc: | pgsql-hackers(at)postgresql(dot)org, linux-kernel(at)vger(dot)kernel(dot)org, linux-lvm(at)redhat(dot)com, osdldbt-general(at)lists(dot)sourceforge(dot)net |
Subject: | dbt-2 tests & profiling on ia64 |
Date: | 2004-02-23 18:18:33 |
Message-ID: | 16442.17401.767305.656013@napali.hpl.hp.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
Mark,
>>>>> On Mon, 23 Feb 2004 09:42:34 -0800 (PST), markw(at)osdl(dot)org said:
Mark> http://developer.osdl.org/markw/ia64/dbt2/
Mark> I have a summary of intial results from our DBT-2 workload with
Mark> PostgreSQL 7.4.1 on a 4-way Itanium2 system with 16GB of memory and 56
Mark> drives using LVM2 and linux-2.6.3. There's readprofile
Mark> and oprofile data, but oprofile is seg faulting when it's trying to
Mark> generate the annotated assembly source.
You could try q-tools, see the announcement here:
http://marc.theaimsgroup.com/?l=linux-ia64&m=107075994721581
Besides the flat profile, it will also give you call-counts. (It
would be nice if this feature could be added to oprofile some day.)
--david
From | Date | Subject | |
---|---|---|---|
Next Message | David Fetter | 2004-02-23 19:42:02 | aliases, &c in HAVING clause? |
Previous Message | Andrew Dunstan | 2004-02-23 18:09:06 | log_line_info |