About these IPC parameters - Mailing list pgsql-hackers

From Peter Eisentraut
Subject About these IPC parameters
Date
Msg-id Pine.LNX.4.21.0007192316280.24612-100000@localhost.localdomain
Whole thread Raw
Responses Re: About these IPC parameters  (Tom Lane <tgl@sss.pgh.pa.us>)
Re: About these IPC parameters  (Bruce Momjian <pgman@candle.pha.pa.us>)
List pgsql-hackers
I'm trying to sort out the documentation regarding the SysV IPC settings,
but I better understand them myself first. :)

We use three shared-memory segments: One is for the spin locks and is of
negligible size (144 bytes currently). The other two I don't know, but one
of them seems to be sized about 550kB + -B * BLCKSZ

My kernel has the following interesting-looking shared memory settings:

SHMMAX    -- max size per segment. Apparently must be >= 550kB + -B * BLCKSZ
SHMMNI    -- max number of segments system wide, better be >= 3
SHMSEG    -- max number of segments per process, also better be >= 3
SHMALL    -- max number of pages for shmem system wide. This seems to be          fixed at some theoretical amount.

The most promising thing to promote here is evidently to raise SHMMAX.


For semaphores, we're using ceil(-N % 16) sets of 16 semaphores. In my
kernel I see:

SEMMNI    -- max number of semaphore "identifiers" (=sets?)
SEMMSL    -- max semaphores per set, this is explained in storage/proc.h
SEMMNS    -- max semaphores in system

So, SEMMNI and SEMMNS seem to be the most promising settings to change.

Is there any noteworthy relevance of some of the other parameters? I see
FAQ_BSDI talks about SEMUME and SEMMNU.


-- 
Peter Eisentraut                  Sernanders väg 10:115
peter_e@gmx.net                   75262 Uppsala
http://yi.org/peter-e/            Sweden



pgsql-hackers by date:

Previous
From: Mikhail Terekhov
Date:
Subject: Re: Untrusted PL/Tcl?
Next
From: Peter Eisentraut
Date:
Subject: Re: Shared library search paths