Skip to contentSkip to conversation

Number of File descriptors

DISCUSSION Chuck Winters 3 participants 4 messages Jul 13, 2001 – Jul 18, 2001

lore
Share & tools
lore

Chuck Winters

author
#0 lore raw

Hello All,
My interest has been peaked by a recent email. At one point, I heard two people speaking
about how some database guy wanted to have 2000 open files(or something crazy like that). They said that he must be crazy because the kernel does a sequential search through the open file descriptors. Anyway, I read a posting an a mail list that someone wanted select to select on 3000 files. Alright, the question(Finally!):
To have select() select on 3000 file descriptors, they must be open. That's 3000 open files. Will select be ultra slow trying to select on 3000 file descriptors? Also, what is the clarification on the kernel doing a sequential search through the open file descriptors?

Thanks In Advance,
Chuck Winters

#1 lore raw
Quoted 10 lines

Hello All,
My interest has been peaked by a recent email. At one
point, I heard two people speaking
about how some database guy wanted to have 2000 open files(or something crazy like that).
They said that he must be crazy because the kernel does a sequential search through the open
file descriptors. Anyway, I read a posting an a mail list that someone wanted select to

Quoted 8 lines

select on 3000 files. Alright, the question(Finally!):
To have select() select on 3000 file descriptors,
they must be open. That's 3000 open
files. Will select be ultra slow trying to select
on 3000 file descriptors? Also,
what is the clarification on the kernel doing a
sequential search through the open
file descriptors?

Using 'select' on 3,000 file descriptors is not a problem. I have used
'poll' on 12,000 file descriptors with no problems at all. Performance is not exactly stellar (you can use threads to improve it) but it's quite good.

DS

author
#2 lore raw
In reply to Chuck Winters

Thank You all for the information

Chuck

Quoted 18 lines · Chuck Winters

Hello All,
My interest has been peaked by a recent email. At one point, I heard two people speaking
about how some database guy wanted to have 2000 open files(or something crazy like that). They said that he must be crazy because the kernel does a sequential search through the open file descriptors. Anyway, I read a posting an a mail list that someone wanted select to select on 3000 files. Alright, the question(Finally!):
To have select() select on 3000 file descriptors, they must be open. That's 3000 open files. Will select be ultra slow trying to select on 3000 file descriptors? Also, what is the clarification on the kernel doing a sequential search through the open file descriptors?

Thanks In Advance,
Chuck Winters
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/