Hi Rik
Sounds like a job for memory limits (ulimit?), not for OOM
notification, right?
I suspect one problem could be that an HPC job scheduling program
does not know exactly how much memory each job can take, so it can
sometimes end up making a mistake and overcommitting the memory on
Did those jobs share nodes -- sometimes two or more jobs using the same
nodes? I am sure SGI has such users too, though such job mixes make
the runtimes of specific jobs less obvious, so customers are more
tolerant of variations and some inefficiencies, as they get hidden in
the mix.
Hm
our
Hi Paul,
Thank you for wonderful interestings comment.
your comment is really nice.
I was HPC guy with large NUMA box at past.
I promise i don't ignroe hpc user.
but unfortunately I didn't have experience of use CPUSET
because at that point, it was under development yet.
I hope discuss you
Hi Andrew
and, It is judged out of trouble at the fllowing situations.
o memory pressure decrease and stop moves an anonymous page to the
inactive list.
o free pages increase than (pages_high+lowmem_reserve)*2.
This seems rather arbitrary. Why choose this stage in the page
-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
include/linux/mem_notify.h |3 +++
mm/page_alloc.c|6 +-
2 files changed, 8 insertions(+), 1 deletion(-)
Index: b/include/linux/mem_notify.h
===
--- a/include/linux
SIGUSR1
*/
/usage example
ChangeLog
v5 - v6:
o rewrite usage example
o cleanups number of wakeup tasks calculation.
v5: new
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
mm/mem_notify.c | 109
introduce new API wake_up_locked_nr() and wake_up_locked_all().
it it similar as wake_up_nr() and wake_up_all(), but it doesn't lock.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
include/linux/wait.h | 12
kernel/sched.c
=119427416315676w=2
mem notification v4
http://marc.info/?l=linux-mmm=120035840523718w=2
mem notification v5
http://marc.info/?l=linux-mmm=120114835421602w=2
Changelog
-
v5 - v6 (by KOSAKI Motohiro)
o rebase to 2.6.24-mm1
o fixed thundering
(file, kosaki_wait_queue, wait);
if (data_exist)
return POLLIN | POLLRDNORM;
return 0;
}
/usage example
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
fs/eventpoll.c |7 +--
fs/select.c
;
pollfds.revents = 0;
err = poll(pollfds, 1, -1); // wake up at low memory
...
/usage example
ChangeLog
v5 - v6:
o improve number of wakeup tasks fomula when task is a few.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED
pressure decrease and stop moves an anonymous page to the
inactive list.
o free pages increase than (pages_high+lowmem_reserve)*2.
ChangeLog:
v5: add out of trouble notify to exit of balance_pgdat().
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL
this is usage example of /dev/mem_notify.
Daniel Spang create original version.
kosaki add fasync related code.
Signed-off-by: Daniel Spang [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
Documentation/mem_notify.c | 120 +
1
Hi Jon
I looked at this a year or two back, then ran out of time. But the thing
I wanted to do was have libc's memory allocation routines extended to
handle these through reservations - the kernel should send a userspace
notification and then there should be some kind of concept of returning
Hi Pavel
As user pages are always in highmem, this should be easy to decide:
only send SIGDANGER when highmem is full. (Yes, there are
inodes/dentries/file descriptors in lowmem, but I doubt apps will
respond to SIGDANGER by closing files).
Good point; for a system with at least
The commentary on the mem_notify threads claimed that the signal is
easily provided by setting up the file handle for SIGIO.
BTW:
Of cource, you can receive any signal instead SIGIO by use fcntl(F_SETSIG) :-)
-
To unsubscribe from this list: send the line unsubscribe linux-fsdevel in
the body
And from a performance point of view letting applications voluntarily
free some memory is better even than starting to swap.
Absolutely.
the mem_notify patch can realize just before starting swapping notification :)
to be honest, I don't know fs guys requirement.
if lacking feature of fs
Hi Al
the mem_notify patch can realize just before starting swapping
notification :)
to be honest, I don't know fs guys requirement.
if lacking feature of fs guys needed, I implement it with presure if
you tell me it.
These notifications are really useful, but it may be much wiser
17 matches
Mail list logo