[Firebird-devel] Trunk don't build on Ubuntu 12.04

2013-10-17 Thread Philippe Makowski
Alex, your last changes give this results : http://ci.ibphoenix.fr/job/Firebird30_Ubuntu_Linux/47/console AUTORECONF=autoreconf **Error**: You must have autoconf 2.63 or later installed. Download the appropriate package for your distribution/OS, Ubuntu 12.04 LTS (Precise Pangolin) is not an o

[Firebird-devel] [FB-Tracker] Created: (CORE-4246) fb_inet_server.exe stack up and memory stucked on 100%

2013-10-17 Thread Pirk Lajos (JIRA)
fb_inet_server.exe stack up and memory stucked on 100% -- Key: CORE-4246 URL: http://tracker.firebirdsql.org/browse/CORE-4246 Project: Firebird Core Issue Type: Bug Affects Versions: 2.

Re: [Firebird-devel] TcpRemoteBufferSize

2013-10-17 Thread Dimitry Sibiryakov
17.10.2013 12:15, Alex Peshkoff wrote: > No. > Very small. Buffer size has effect on fast query + latent (but wide) channel + fast client because it decreases number of round-trips. Otherwise network waits will be beyond recognition. -- WBR, SD.

Re: [Firebird-devel] TcpRemoteBufferSize

2013-10-17 Thread Alex Peshkoff
On 10/17/13 14:04, Dimitry Sibiryakov wrote: > 17.10.2013 11:13, Alex Peshkoff wrote: >> I've tried to test fb3. I see no perf difference between 2K and 32K buffers. > Was channel latency high enough? > No. Very small. --

Re: [Firebird-devel] TcpRemoteBufferSize

2013-10-17 Thread Dimitry Sibiryakov
17.10.2013 11:13, Alex Peshkoff wrote: > I've tried to test fb3. I see no perf difference between 2K and 32K buffers. Was channel latency high enough? -- WBR, SD. -- October Webinars: Code for Performance Free Int

Re: [Firebird-devel] TcpRemoteBufferSize

2013-10-17 Thread Alex Peshkoff
On 10/17/13 12:36, marius adrian popa wrote: > Isn't the recent kernels do autotuning for tcp buffer sizes ? > http://fasterdata.es.net/host-tuning/background/#t1 It's not related to our internal buffer size. -- October

Re: [Firebird-devel] TcpRemoteBufferSize

2013-10-17 Thread Alex Peshkoff
On 10/16/13 18:41, Carlos H. Cantu wrote: > Server x Client > 8K 8K > 8K 16K > 8K 32K > 32K 8K > 32K 32K > > The fetch times were almost identical in all the above configurations > :( > > The number of records returned was about 3.500, and average time was > about 11 se

Re: [Firebird-devel] TcpRemoteBufferSize

2013-10-17 Thread Alex Peshkoff
On 10/16/13 18:41, Carlos H. Cantu wrote: > Is there any chance that FB 2.5.1 is ignoring this parameter? "Any" chance is always present, but looking at the code I can hardly imagine that parameter is ignored. > How to > explain such different behavior compared to the last year test (FB 2.1) >

Re: [Firebird-devel] TcpRemoteBufferSize

2013-10-17 Thread marius adrian popa
Isn't the recent kernels do autotuning for tcp buffer sizes ? http://fasterdata.es.net/host-tuning/background/#t1 The max size still can be usefull but we need to see it with real tests On Thu, Oct 17, 2013 at 10:40 AM, Alex Peshkoff wrote: > On 10/16/13 19:04, Dimitry Sibiryakov wrote: >> 16.

Re: [Firebird-devel] TcpRemoteBufferSize

2013-10-17 Thread Alex Peshkoff
On 10/16/13 19:04, Dimitry Sibiryakov wrote: > 16.10.2013 17:01, Leyne, Sean wrote: >> Is this buffer size setting configurable thru a connection/API setting? > AFAIK, no. > It's possible to make it configurable in FB3 at the client side. At the server side we must first allocate some buffer