Great, thanks. I'll look into when I get a few minutes.
Ryan
On 28/07/2014 11:57 PM, Reza Taheri wrote:
Hi Ryan,
We presented a paper at the TPCTC of last year's VLDB (attached). It described
the architecture of the kit, and some of the tuning. Another tuning change was
setting /proc/sys/vm/d
Hi Ryan,
I just noticed that the mail alias manager has stalled the post below because
of the attachment size. But you should have gotten it directly.
If anyone else is interested in a copy, let me know, and I will forward it
Thanks,
Reza
> -Original Message-
> From: Reza Taheri
> Sent:
That does sound pretty similar, modulo the raw performance difference. I
have no idea how many MEE threads there were; it was just a quick run
with exactly zero tuning, so I use whatever dbt5 does out of the box.
Actually, though, if you have any general tuning tips for TPC-E I'd be
interested
Hi Ryan,
Thanks a lot for sharing this. When I run with 12 CE threads and 3-5 MEE
threads (how many MEE threads do you have?) @ 80-90 tps, I get something in
the 20-30% of trade-result transactions rolled back depending on how I count.
E.g., in a 5.5-minute run with 3 MEE threads, I saw 87.5 tp
Dredging through some old run logs, 12 dbt-5 clients gave the following
when everything was run under SSI (fully serializable, even the
transactions that allow repeatable read isolation). Not sure how that
translates to your results. Abort rates were admittedly rather high,
though perhaps lower
Hi Ryan,
That's a very good point. We are looking at dbt5. One question: what throughput
rate, and how many threads of execution did you use for dbt5? The failure
rates I reported were at ~120 tps with 15 trade-result threads.
Thanks,
Reza
> -Original Message-
> From: pgsql-performance
We are hoping the spec will get wrapped up in the next 6 months, but industry
standard councils move very slowly! However, if there is interest in getting
involved and helping, the TPC might be receptive to earlier access.
BTW, just to let folks know how large of an undertaking this has been, t
