lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Fri, 10 Nov 2017 20:33:07 +0300
From:   Dmitry Monakhov <dmonakhov@...nvz.org>
To:     Theodore Ts'o <tytso@....edu>, Andreas Dilger <adilger@...ger.ca>
Cc:     linux-ext4@...r.kernel.org
Subject: Re: [PATCH] ext4: improve smp scalability for inode generation

Theodore Ts'o <tytso@....edu> writes:

> Dmitry, can you try benchmarking this patch?
Hi,
I do not forget about your patch but it looks like some very strange
things happens since last measurements. create_unlink scenario degradates
significantly from 8-16 threads. It looks like something contented on
VFS because I see same result on xfs.
Even more I do not see this contention with 'perf lock record'. Probably
this is because some crappy locking primitives like hlist_bl which has
no lockdep/lockstat support. I'll notify you once found something.
>
> Thanks!!
>
> 						- Ted
>
> commit f0e922e7235e1b5ba6fd964e2cf8dafed3248a15
> Author: Theodore Ts'o <tytso@....edu>
> Date:   Wed Nov 8 22:21:58 2017 -0500
>
>     ext4: improve smp scalability for inode generation
>     
>     ->s_next_generation is protected by s_next_gen_lock but its usage
>     pattern is very primitive.  We don't actually need sequentailly
>     increasing new generation numbers, so let's use prandom_u32() instead.
>     
>     Reported-by: Dmitry Monakhov <dmonakhov@...nvz.org>
>     Signed-off-by: Theodore Ts'o <tytso@....edu>
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index 53ce95b52fd8..5e6d7b6f50c7 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -1355,8 +1355,6 @@ struct ext4_sb_info {
>  	int s_first_ino;
>  	unsigned int s_inode_readahead_blks;
>  	unsigned int s_inode_goal;
> -	spinlock_t s_next_gen_lock;
> -	u32 s_next_generation;
>  	u32 s_hash_seed[4];
>  	int s_def_hash_version;
>  	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
> diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
> index ee823022aa34..da79eb5dba40 100644
> --- a/fs/ext4/ialloc.c
> +++ b/fs/ext4/ialloc.c
> @@ -1138,9 +1138,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
>  			   inode->i_ino);
>  		goto out;
>  	}
> -	spin_lock(&sbi->s_next_gen_lock);
> -	inode->i_generation = sbi->s_next_generation++;
> -	spin_unlock(&sbi->s_next_gen_lock);
> +	inode->i_generation = prandom_u32();
>  
>  	/* Precompute checksum seed for inode metadata */
>  	if (ext4_has_metadata_csum(sb)) {
> diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
> index 144bbda2b808..98ad8172dfd3 100644
> --- a/fs/ext4/ioctl.c
> +++ b/fs/ext4/ioctl.c
> @@ -17,6 +17,7 @@
>  #include <linux/uuid.h>
>  #include <linux/uaccess.h>
>  #include <linux/delay.h>
> +#include <linux/random.h>
>  #include "ext4_jbd2.h"
>  #include "ext4.h"
>  #include <linux/fsmap.h>
> @@ -157,10 +158,8 @@ static long swap_inode_boot_loader(struct super_block *sb,
>  
>  	inode->i_ctime = inode_bl->i_ctime = current_time(inode);
>  
> -	spin_lock(&sbi->s_next_gen_lock);
> -	inode->i_generation = sbi->s_next_generation++;
> -	inode_bl->i_generation = sbi->s_next_generation++;
> -	spin_unlock(&sbi->s_next_gen_lock);
> +	inode->i_generation = prandom_u32();
> +	inode_bl->i_generation = prandom_u32();
>  
>  	ext4_discard_preallocations(inode);
>  
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index 3a278faf5868..9f2e3eb5131f 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -3982,8 +3982,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
>  	}
>  
>  	sbi->s_gdb_count = db_count;
> -	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
> -	spin_lock_init(&sbi->s_next_gen_lock);
>  
>  	timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
>  

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux - Powered by OpenVZ