| From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
|---|---|
| To: | Thomas Hallgren <thomas(at)tada(dot)se> |
| Cc: | Martijn van Oosterhout <kleptog(at)svana(dot)org>, PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org>, PL/Java Development <Pljava-dev(at)gborg(dot)postgresql(dot)org> |
| Subject: | Re: Shared memory |
| Date: | 2006-03-27 15:31:47 |
| Message-ID: | 14559.1143473507@sss.pgh.pa.us |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers pljava-dev |
Thomas Hallgren <thomas(at)tada(dot)se> writes:
> The real downside is that a call from SQL to PL/Java using the current
> in-process approach is really fast. It takes about 5 micro secs on my
> 2.8GHz i386 box. The overhead of an IPC-call on that box is about 18
> micro secs on Linux and 64 micro secs on Windows. That's an overhead
> of between 440% and 1300% due to context switching alone. Yet, for
> some applications, perhaps that overhead is acceptable?
It's only that much difference? Given all the other advantages of
separating the JVM from the backends, I'd say you should gladly pay
that price.
regards, tom lane
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Thomas Hallgren | 2006-03-27 16:27:09 | Re: Shared memory |
| Previous Message | Tom Lane | 2006-03-27 15:26:47 | Re: Recovery from multi trouble |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Thomas Hallgren | 2006-03-27 16:27:09 | Re: Shared memory |
| Previous Message | Thomas Hallgren | 2006-03-27 14:15:38 | [Pljava-dev] [HACKERS] Shared memory |