public inbox for cluster-cvs@sourceware.org
help / color / mirror / Atom feed
* cluster/gfs-kernel/src/gfs dir.c
@ 2006-09-26 5:32 wcheng
0 siblings, 0 replies; 6+ messages in thread
From: wcheng @ 2006-09-26 5:32 UTC (permalink / raw)
To: cluster-cvs
CVSROOT: /cvs/cluster
Module name: cluster
Branch: RHEL4
Changes by: wcheng@sourceware.org 2006-09-26 05:32:17
Modified files:
gfs-kernel/src/gfs: dir.c
Log message:
Bugzilla 205592:
One problem we've found is that under heavy system load, memory could
be in shortage that results in kmalloc() failure. In previous versions,
upon kmalloc() failure, in certain code paths, sometime it was impossible
to back out - so GFS either panic or hung. In newer versions of GFS, a fix
was added to allow memory allocation falling back to vmalloc() if kmalloc()
failed. Unfortuntely, the linux/vmalloc.h header was not added. Since the
compiler has not been not able to get the correct vmalloc() prototype, it
assumes the default that casts vmalloc() return code to "int" which is 4
byes. This could cause panic with 64 machines (e.g. x86_64) that uses 8
bytes addressing.
Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/gfs-kernel/src/gfs/dir.c.diff?cvsroot=cluster&only_with_tag=RHEL4&r1=1.8.2.4&r2=1.8.2.5
^ permalink raw reply [flat|nested] 6+ messages in thread
* cluster/gfs-kernel/src/gfs dir.c
@ 2006-09-26 14:30 wcheng
0 siblings, 0 replies; 6+ messages in thread
From: wcheng @ 2006-09-26 14:30 UTC (permalink / raw)
To: cluster-cvs
CVSROOT: /cvs/cluster
Module name: cluster
Branch: RHEL4U4
Changes by: wcheng@sourceware.org 2006-09-26 14:30:56
Modified files:
gfs-kernel/src/gfs: dir.c
Log message:
Bugzilla 205592:
One problem we've found is that under heavy system load, memory could
be in shortage that results in kmalloc() failure. In previous versions,
upon kmalloc() failure, in certain code paths, sometime it was impossible
to back out - so GFS either panic or hung. In newer versions of GFS, a fix
was added to allow memory allocation falling back to vmalloc() if kmalloc()
failed. Unfortuntely, the linux/vmalloc.h header was not added. Since the
compiler has not been not able to get the correct vmalloc() prototype, it
assumes the default that casts vmalloc() return code to "int" which is 4
byes. This could cause panic with 64 machines (e.g. x86_64) that uses 8
bytes addressing.
Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/gfs-kernel/src/gfs/dir.c.diff?cvsroot=cluster&only_with_tag=RHEL4U4&r1=1.8.2.4&r2=1.8.2.4.2.1
^ permalink raw reply [flat|nested] 6+ messages in thread
* cluster/gfs-kernel/src/gfs dir.c
@ 2006-02-20 4:31 wcheng
0 siblings, 0 replies; 6+ messages in thread
From: wcheng @ 2006-02-20 4:31 UTC (permalink / raw)
To: cluster-cvs
CVSROOT: /cvs/cluster
Module name: cluster
Changes by: wcheng@sourceware.org 2006-02-20 04:31:33
Modified files:
gfs-kernel/src/gfs: dir.c
Log message:
Bugzilla 182057 - patch 3-2:
GFS was trying to split a full-grown directory (0xffff entries) hash leaf
into two and subseqently hang. The buffer requirement 0xffff*sizeof(uint64_t)/2
= 262144 (256K) was too big for kmalloc to handle. Change into vmalloc if
kmalloc fails.
Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/gfs-kernel/src/gfs/dir.c.diff?cvsroot=cluster&r1=1.11&r2=1.12
^ permalink raw reply [flat|nested] 6+ messages in thread
* cluster/gfs-kernel/src/gfs dir.c
@ 2006-02-20 3:58 wcheng
0 siblings, 0 replies; 6+ messages in thread
From: wcheng @ 2006-02-20 3:58 UTC (permalink / raw)
To: cluster-cvs
CVSROOT: /cvs/cluster
Module name: cluster
Branch: STABLE
Changes by: wcheng@sourceware.org 2006-02-20 03:58:05
Modified files:
gfs-kernel/src/gfs: dir.c
Log message:
Bugzilla 182057 - patch 3-2:
GFS was trying to split a full-grown directory (0xffff entries) hash leaf
into two and subseqently hang. The buffer requirement 0xffff*sizeof(uint64_t)/2
= 262144 (256K) was too big for kmalloc to handle. Change into vmalloc if
kmalloc fails.
Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/gfs-kernel/src/gfs/dir.c.diff?cvsroot=cluster&only_with_tag=STABLE&r1=1.8.6.1.2.1&r2=1.8.6.1.2.2
^ permalink raw reply [flat|nested] 6+ messages in thread
* cluster/gfs-kernel/src/gfs dir.c
@ 2006-02-19 23:37 wcheng
0 siblings, 0 replies; 6+ messages in thread
From: wcheng @ 2006-02-19 23:37 UTC (permalink / raw)
To: cluster-cvs
CVSROOT: /cvs/cluster
Module name: cluster
Branch: RHEL4
Changes by: wcheng@sourceware.org 2006-02-19 23:37:23
Modified files:
gfs-kernel/src/gfs: dir.c
Log message:
bugzilla 182057 - patch 3-2:
GFS was trying to split a full-grown directory (0xffff entries) hash leaf
into two and subseqently hang. The buffer requirement 0xffff*sizeof(uint64_t)/2
= 262144 (256K) was too big for kmalloc to handle. Change into vmalloc.
Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/gfs-kernel/src/gfs/dir.c.diff?cvsroot=cluster&only_with_tag=RHEL4&r1=1.8.2.3&r2=1.8.2.4
^ permalink raw reply [flat|nested] 6+ messages in thread
* cluster/gfs-kernel/src/gfs dir.c
@ 2006-02-15 16:27 wcheng
0 siblings, 0 replies; 6+ messages in thread
From: wcheng @ 2006-02-15 16:27 UTC (permalink / raw)
To: cluster-cvs
CVSROOT: /cvs/cluster
Module name: cluster
Branch: RHEL4
Changes by: wcheng@sourceware.org 2006-02-15 16:27:58
Modified files:
gfs-kernel/src/gfs: dir.c
Log message:
Reset src/gfs/dir.c - accidentally checked in half done code for
another bugzilla.
Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/gfs-kernel/src/gfs/dir.c.diff?cvsroot=cluster&only_with_tag=RHEL4&r1=1.8.2.1&r2=1.8.2.2
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2006-09-26 14:30 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2006-09-26 5:32 cluster/gfs-kernel/src/gfs dir.c wcheng
-- strict thread matches above, loose matches on Subject: below --
2006-09-26 14:30 wcheng
2006-02-20 4:31 wcheng
2006-02-20 3:58 wcheng
2006-02-19 23:37 wcheng
2006-02-15 16:27 wcheng
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).