lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
Open Source and information security mailing list archives
| ||
|
Message-ID: <48A9999C.6070609@redhat.com> Date: Mon, 18 Aug 2008 10:47:40 -0500 From: Eric Sandeen <sandeen@...hat.com> To: ext4 development <linux-ext4@...r.kernel.org> CC: "Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com> Subject: Re: [PATCH] use percpu data for lg_prealloc_list Eric Sandeen wrote: > lg_prealloc_list seems to cry out for a per-cpu data structure; on a large > smp system I think this should be better. I've lightly tested this change > on a 4-cpu system. Comments welcome... Any thoughts on this? Does this seem to be the right way to go? Thanks, -Eric > Signed-off-by: Eric Sandeen <sandeen@...hat.com> > --- > > ndex: linux-2.6/fs/ext4/mballoc.c > =================================================================== > --- linux-2.6.orig/fs/ext4/mballoc.c 2008-08-04 15:30:30.000000000 -0500 > +++ linux-2.6/fs/ext4/mballoc.c 2008-08-13 13:48:33.224165751 -0500 > @@ -2540,17 +2540,16 @@ int ext4_mb_init(struct super_block *sb, > sbi->s_mb_history_filter = EXT4_MB_HISTORY_DEFAULT; > sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC; > > - i = sizeof(struct ext4_locality_group) * nr_cpu_ids; > - sbi->s_locality_groups = kmalloc(i, GFP_KERNEL); > + sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); > if (sbi->s_locality_groups == NULL) { > clear_opt(sbi->s_mount_opt, MBALLOC); > kfree(sbi->s_mb_offsets); > kfree(sbi->s_mb_maxs); > return -ENOMEM; > } > - for (i = 0; i < nr_cpu_ids; i++) { > + for_each_possible_cpu(i) { > struct ext4_locality_group *lg; > - lg = &sbi->s_locality_groups[i]; > + lg = per_cpu_ptr(sbi->s_locality_groups, i); > mutex_init(&lg->lg_mutex); > for (j = 0; j < PREALLOC_TB_SIZE; j++) > INIT_LIST_HEAD(&lg->lg_prealloc_list[j]); > @@ -2647,8 +2646,7 @@ int ext4_mb_release(struct super_block * > atomic_read(&sbi->s_mb_discarded)); > } > > - kfree(sbi->s_locality_groups); > - > + free_percpu(sbi->s_locality_groups); > ext4_mb_history_release(sb); > ext4_mb_destroy_per_dev_proc(sb); > > @@ -4055,8 +4053,7 @@ static void ext4_mb_group_or_file(struct > * per cpu locality group is to reduce the contention between block > * request from multiple CPUs. > */ > - ac->ac_lg = &sbi->s_locality_groups[get_cpu()]; > - put_cpu(); > + ac->ac_lg = per_cpu_ptr(sbi->s_locality_groups, smp_processor_id()); > > /* we're going to use group allocation */ > ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC; > > -- > To unsubscribe from this list: send the line "unsubscribe linux-ext4" in > the body of a message to majordomo@...r.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe linux-ext4" in the body of a message to majordomo@...r.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists