Discussion:
inode64 directory placement determinism
Stan Hoeppner
2014-08-18 03:29:21 UTC
Permalink
Say I have a single 4TB disk in an md linear device. The md device has a
filesystem on it formatted with defaults. It has 4 AGs, 0-3. I have
created 4 directories. Each should reside in a different AG, the first in
AG0. Now I expand the linear device with an identical 4TB disk and execute
xfs_growfs. I now have 4 more AGs, 4-7. I create 4 more directories.

Will these 4 new dirs be created sequentially in AGs 4-7, or in the first
4 AGs? Is this deterministic, or is there any chance involved? On the
real system these 4TB drives are actually 48TB LUNs. I'm after
deterministic parallel bandwidth to subsequently added RAIDs after each
grow operation by simply writing to the proper directory.

Currently we have kernel 3.4.26 to work with if that's relevant. I may be
able to get the kernel team to go for 3.4.103 for the bugfixes, but I don't
know about anything newer. This is an embedded type development process.

Thanks,
Stan
Dave Chinner
2014-08-18 07:01:53 UTC
Permalink
Post by Stan Hoeppner
Say I have a single 4TB disk in an md linear device. The md device has a
filesystem on it formatted with defaults. It has 4 AGs, 0-3. I have
created 4 directories. Each should reside in a different AG, the first in
AG0. Now I expand the linear device with an identical 4TB disk and execute
xfs_growfs. I now have 4 more AGs, 4-7. I create 4 more directories.
Will these 4 new dirs be created sequentially in AGs 4-7, or in the first
4 AGs? Is this deterministic, or is there any chance involved? On the
Deterministic, assuming single threaded *file-system-wide* directory
creation. Completely unpredictable under concurrent directory
creations. See xfs_ialloc_ag_select/xfs_ialloc_next_ag.

Note that the rotor used to select the next AG is set to
zero at mount.

i.e. single threaded behaviour at agcount = 4:

dir number rotor value destination AG
1 0 0
2 1 1
3 2 2
4 3 3
5 0 0
6 1 1
....

So, if you do what you suggest, and grow *after* the first 4 dirs
are created, the above is what you'll get because the rotor goes
back to zero on the fourth directory create. Now, with changing from
4 to 8 AGs after the first 4:

dir number rotor value new inode location (AG)
1 0 0
2 1 1
3 2 2
4 3 3
<grow to 8 AGs>
5 0 0
6 1 1
7 2 2
8 3 3
9 4 4
10 5 5
11 6 6
13 7 7
14 0 0
Post by Stan Hoeppner
real system these 4TB drives are actually 48TB LUNs. I'm after
deterministic parallel bandwidth to subsequently added RAIDs after each
grow operation by simply writing to the proper directory.
Just create new directories and use the inode number to
determine their location. If the directory is not in the correct AG,
remove it and create a new one, until you have directories located
in the AGs you want.

Cheers,

Dave.
--
Dave Chinner
***@fromorbit.com
Stan Hoeppner
2014-08-18 16:16:12 UTC
Permalink
Post by Dave Chinner
Post by Stan Hoeppner
Say I have a single 4TB disk in an md linear device. The md device has a
filesystem on it formatted with defaults. It has 4 AGs, 0-3. I have
created 4 directories. Each should reside in a different AG, the first in
AG0. Now I expand the linear device with an identical 4TB disk and execute
xfs_growfs. I now have 4 more AGs, 4-7. I create 4 more directories.
Will these 4 new dirs be created sequentially in AGs 4-7, or in the first
4 AGs? Is this deterministic, or is there any chance involved? On the
Deterministic, assuming single threaded *file-system-wide* directory
creation. Completely unpredictable under concurrent directory
creations. See xfs_ialloc_ag_select/xfs_ialloc_next_ag.
Note that the rotor used to select the next AG is set to
zero at mount.
dir number rotor value destination AG
1 0 0
2 1 1
3 2 2
4 3 3
5 0 0
6 1 1
....
So, if you do what you suggest, and grow *after* the first 4 dirs
are created, the above is what you'll get because the rotor goes
back to zero on the fourth directory create. Now, with changing from
dir number rotor value new inode location (AG)
1 0 0
2 1 1
3 2 2
4 3 3
<grow to 8 AGs>
5 0 0
6 1 1
7 2 2
8 3 3
9 4 4
10 5 5
11 6 6
13 7 7
14 0 0
Post by Stan Hoeppner
real system these 4TB drives are actually 48TB LUNs. I'm after
deterministic parallel bandwidth to subsequently added RAIDs after each
grow operation by simply writing to the proper directory.
Just create new directories and use the inode number to
determine their location. If the directory is not in the correct AG,
remove it and create a new one, until you have directories located
in the AGs you want.
Cheers,
Dave.
Thanks for the info Dave. Was hoping it would be more straightforward.
Modifying the app for this is out of the question. They've spent 3+ years
developing with EXT4 and decided to try XFS at the last minute. Product is
to ship in October, so optimizations I can suggest are limited.
--
Stan
Dave Chinner
2014-08-18 22:48:53 UTC
Permalink
Post by Stan Hoeppner
Post by Dave Chinner
Post by Stan Hoeppner
Say I have a single 4TB disk in an md linear device. The md device has
a
Post by Dave Chinner
Post by Stan Hoeppner
filesystem on it formatted with defaults. It has 4 AGs, 0-3. I have
created 4 directories. Each should reside in a different AG, the first in
AG0. Now I expand the linear device with an identical 4TB disk and execute
xfs_growfs. I now have 4 more AGs, 4-7. I create 4 more directories.
Will these 4 new dirs be created sequentially in AGs 4-7, or in the
first
Post by Dave Chinner
Post by Stan Hoeppner
4 AGs? Is this deterministic, or is there any chance involved? On the
Deterministic, assuming single threaded *file-system-wide* directory
creation. Completely unpredictable under concurrent directory
creations. See xfs_ialloc_ag_select/xfs_ialloc_next_ag.
Note that the rotor used to select the next AG is set to
zero at mount.
dir number rotor value destination AG
1 0 0
2 1 1
3 2 2
4 3 3
5 0 0
6 1 1
....
So, if you do what you suggest, and grow *after* the first 4 dirs
are created, the above is what you'll get because the rotor goes
back to zero on the fourth directory create. Now, with changing from
dir number rotor value new inode location (AG)
1 0 0
2 1 1
3 2 2
4 3 3
<grow to 8 AGs>
5 0 0
6 1 1
7 2 2
8 3 3
9 4 4
10 5 5
11 6 6
13 7 7
14 0 0
Post by Stan Hoeppner
real system these 4TB drives are actually 48TB LUNs. I'm after
deterministic parallel bandwidth to subsequently added RAIDs after each
grow operation by simply writing to the proper directory.
Just create new directories and use the inode number to
determine their location. If the directory is not in the correct AG,
remove it and create a new one, until you have directories located
in the AGs you want.
Cheers,
Dave.
Thanks for the info Dave. Was hoping it would be more straightforward.
Modifying the app for this is out of the question. They've spent 3+ years
developing with EXT4 and decided to try XFS at the last minute. Product is
to ship in October, so optimizations I can suggest are limited.
Perhaps you could actually tell us what the requirement for
layout/separation is, and how they are acheiving it with ext4. We
really need a more "directed" allocation ability, but it's not clear
exactly what requirements need to drive that.

Cheers,

Dave.
--
Dave Chinner
***@fromorbit.com
Stan Hoeppner
2014-08-19 00:02:04 UTC
Permalink
Post by Dave Chinner
Post by Stan Hoeppner
Post by Dave Chinner
Post by Stan Hoeppner
Say I have a single 4TB disk in an md linear device. The md device has
a
Post by Dave Chinner
Post by Stan Hoeppner
filesystem on it formatted with defaults. It has 4 AGs, 0-3. I have
created 4 directories. Each should reside in a different AG, the
first
in
AG0. Now I expand the linear device with an identical 4TB disk and execute
xfs_growfs. I now have 4 more AGs, 4-7. I create 4 more
directories.
Post by Dave Chinner
Post by Stan Hoeppner
Post by Dave Chinner
Post by Stan Hoeppner
Will these 4 new dirs be created sequentially in AGs 4-7, or in the
first
Post by Dave Chinner
Post by Stan Hoeppner
4 AGs? Is this deterministic, or is there any chance involved? On the
Deterministic, assuming single threaded *file-system-wide* directory
creation. Completely unpredictable under concurrent directory
creations. See xfs_ialloc_ag_select/xfs_ialloc_next_ag.
Note that the rotor used to select the next AG is set to
zero at mount.
dir number rotor value destination AG
1 0 0
2 1 1
3 2 2
4 3 3
5 0 0
6 1 1
....
So, if you do what you suggest, and grow *after* the first 4 dirs
are created, the above is what you'll get because the rotor goes
back to zero on the fourth directory create. Now, with changing from
dir number rotor value new inode location (AG)
1 0 0
2 1 1
3 2 2
4 3 3
<grow to 8 AGs>
5 0 0
6 1 1
7 2 2
8 3 3
9 4 4
10 5 5
11 6 6
13 7 7
14 0 0
Post by Stan Hoeppner
real system these 4TB drives are actually 48TB LUNs. I'm after
deterministic parallel bandwidth to subsequently added RAIDs after each
grow operation by simply writing to the proper directory.
Just create new directories and use the inode number to
determine their location. If the directory is not in the correct AG,
remove it and create a new one, until you have directories located
in the AGs you want.
Cheers,
Dave.
Thanks for the info Dave. Was hoping it would be more straightforward.
Modifying the app for this is out of the question. They've spent 3+ years
developing with EXT4 and decided to try XFS at the last minute.
Product
Post by Dave Chinner
Post by Stan Hoeppner
is
to ship in October, so optimizations I can suggest are limited.
Perhaps you could actually tell us what the requirement for
layout/separation is, and how they are acheiving it with ext4. We
really need a more "directed" allocation ability, but it's not clear
exactly what requirements need to drive that.
Cheers,
Dave.
The test harness app writes to thousands of preallocated files in hundreds
of directories. The target is ~250MB/s at the application per array, more
if achievable, writing a combination of fast and slow streams from up to
~1000 threads, to different files, circularly. The mix of stream rates and
the files they write will depend on the end customers' needs. Currently
they have 1 FS per array with 3 top level dirs each w/3 subdirs, 2 of these
with ~100 subdirs each, and hundreds files in each of those. Simply doing
a concat, growing and just running with it might work fine. The concern is
ending up with too many fast stream writers hitting AGs on a single array
which won't be able to keep up. Currently they simply duplicate the layout
on each new filesystem they mount. The application duplicates the same
layout on each filesystem and does its own load balancing among the group
of them.

Ideally they'd obviously like to simply add files to existing directories
after growing, but that won't achieve scalable bandwidth.
--
Stan
stan hoeppner
2014-08-24 20:14:44 UTC
Permalink
Post by Stan Hoeppner
Post by Dave Chinner
Post by Stan Hoeppner
Post by Dave Chinner
Post by Stan Hoeppner
Say I have a single 4TB disk in an md linear device. The md device has
a
Post by Dave Chinner
Post by Stan Hoeppner
filesystem on it formatted with defaults. It has 4 AGs, 0-3. I
have
Post by Dave Chinner
Post by Stan Hoeppner
Post by Dave Chinner
Post by Stan Hoeppner
created 4 directories. Each should reside in a different AG, the
first
in
AG0. Now I expand the linear device with an identical 4TB disk and execute
xfs_growfs. I now have 4 more AGs, 4-7. I create 4 more
directories.
Post by Dave Chinner
Post by Stan Hoeppner
Post by Dave Chinner
Post by Stan Hoeppner
Will these 4 new dirs be created sequentially in AGs 4-7, or in the
first
Post by Dave Chinner
Post by Stan Hoeppner
4 AGs? Is this deterministic, or is there any chance involved? On the
Deterministic, assuming single threaded *file-system-wide* directory
creation. Completely unpredictable under concurrent directory
creations. See xfs_ialloc_ag_select/xfs_ialloc_next_ag.
Note that the rotor used to select the next AG is set to
zero at mount.
dir number rotor value destination AG
1 0 0
2 1 1
3 2 2
4 3 3
5 0 0
6 1 1
....
So, if you do what you suggest, and grow *after* the first 4 dirs
are created, the above is what you'll get because the rotor goes
back to zero on the fourth directory create. Now, with changing from
dir number rotor value new inode location (AG)
1 0 0
2 1 1
3 2 2
4 3 3
<grow to 8 AGs>
5 0 0
6 1 1
7 2 2
8 3 3
9 4 4
10 5 5
11 6 6
13 7 7
14 0 0
Post by Stan Hoeppner
real system these 4TB drives are actually 48TB LUNs. I'm after
deterministic parallel bandwidth to subsequently added RAIDs after each
grow operation by simply writing to the proper directory.
Just create new directories and use the inode number to
determine their location. If the directory is not in the correct AG,
remove it and create a new one, until you have directories located
in the AGs you want.
Cheers,
Dave.
Thanks for the info Dave. Was hoping it would be more straightforward.
Modifying the app for this is out of the question. They've spent 3+ years
developing with EXT4 and decided to try XFS at the last minute.
Product
Post by Dave Chinner
Post by Stan Hoeppner
is
to ship in October, so optimizations I can suggest are limited.
Perhaps you could actually tell us what the requirement for
layout/separation is, and how they are acheiving it with ext4. We
really need a more "directed" allocation ability, but it's not clear
exactly what requirements need to drive that.
Cheers,
Dave.
The test harness app writes to thousands of preallocated files in hundreds
of directories. The target is ~250MB/s at the application per array, more
if achievable, writing a combination of fast and slow streams from up to
~1000 threads, to different files, circularly. The mix of stream rates and
the files they write will depend on the end customers' needs. Currently
they have 1 FS per array with 3 top level dirs each w/3 subdirs, 2 of these
with ~100 subdirs each, and hundreds files in each of those. Simply doing
a concat, growing and just running with it might work fine. The concern is
ending up with too many fast stream writers hitting AGs on a single array
which won't be able to keep up. Currently they simply duplicate the layout
on each new filesystem they mount. The application duplicates the same
layout on each filesystem and does its own load balancing among the group
of them.
Ideally they'd obviously like to simply add files to existing directories
after growing, but that won't achieve scalable bandwidth.
My apologies Dave. The above isn't really a description of a
requirement, but simply how they do things currently. So let me take
another stab at this. I think the generic requirement is best described
as:

Create a directory in the first AG in a range of specified
AGs. Create all child directories and files in AGs within the
range of AGs, starting with the first AG. In other words, we
take the default behavior of the inode64 allocator and we apply
it to a subset of AGs within the filesystem. Something like...

agr = allocation group range

1. mkdir $directory agr=0,47

2. create $directory in AG0 and set flag in metadata to have inode64
allocator rotor new child directories of this parent across only
the AGs in the range specified

3. file allocation policy need not be altered, files go in parent
directory, parent AG. If we spill due to AG free space do what
we already do and allow writing outside of the AGs in agr


So when we expand the concat and grow XFS we simply do

~$ mkdir $directory agr=48,95

All child directories and files created in $directory will be allocated
in AGs 48-95, only on the new LUN. Rinse and repeat.

Such a feature would provide everything needed I think for this
particular workload. I can imagine there are similar workloads out
there that would benefit from something like this given the prevalence
of large concatenated RAID6s today. Another scenario that might benefit
from something like this is short stroking of mechanical storage, but
controlling it at the filesystem level instead of the block or
controller layer.

Setting AGR with an mkdir switch might not fly due to it being a generic
command for all filesystems. But it would sure be the most
straightforward approach and easiest to use.

Due to the timetable and other restrictions I wouldn't be able to use
patches that might come from fleshing out our ideas here, but I think it
would be very useful functionality for others.

Cheers,

Stan
Stan Hoeppner
2014-08-25 02:15:39 UTC
Permalink
Post by stan hoeppner
Due to the timetable and other restrictions I wouldn't be able to use
patches that might come from fleshing out our ideas here, but I think it
would be very useful functionality for others.
Let me restate the above as I don't "think" we'd be able to use patches
in the short term for version 1 of the product. That may change if said
hypothetical patches might become available within the next 3 weeks,
which is probably highly unlikely. They brought me in very late in the
game, unfortunately, so I'm racing against the clock. And of course I
wasn't able to assist in architectural planning, and make such a feature
request here long ago, allowing for sufficient lead time.


Stan
Dave Chinner
2014-08-25 02:19:11 UTC
Permalink
Post by stan hoeppner
Post by Stan Hoeppner
The test harness app writes to thousands of preallocated files in hundreds
of directories. The target is ~250MB/s at the application per array, more
if achievable, writing a combination of fast and slow streams from up to
~1000 threads, to different files, circularly. The mix of stream rates and
the files they write will depend on the end customers' needs. Currently
they have 1 FS per array with 3 top level dirs each w/3 subdirs, 2 of these
with ~100 subdirs each, and hundreds files in each of those. Simply doing
a concat, growing and just running with it might work fine. The concern is
ending up with too many fast stream writers hitting AGs on a single array
which won't be able to keep up. Currently they simply duplicate the layout
on each new filesystem they mount. The application duplicates the same
layout on each filesystem and does its own load balancing among the group
of them.
Ideally they'd obviously like to simply add files to existing directories
after growing, but that won't achieve scalable bandwidth.
My apologies Dave. The above isn't really a description of a
requirement, but simply how they do things currently. So let me
take another stab at this. I think the generic requirement is best
Create a directory in the first AG in a range of specified
AGs. Create all child directories and files in AGs within the
range of AGs, starting with the first AG. In other words, we
take the default behavior of the inode64 allocator and we apply
it to a subset of AGs within the filesystem. Something like...
agr = allocation group range
1. mkdir $directory agr=0,47
2. create $directory in AG0 and set flag in metadata to have inode64
allocator rotor new child directories of this parent across only
the AGs in the range specified
3. file allocation policy need not be altered, files go in parent
directory, parent AG. If we spill due to AG free space do what
we already do and allow writing outside of the AGs in agr
So when we expand the concat and grow XFS we simply do
~$ mkdir $directory agr=48,95
All child directories and files created in $directory will be
allocated in AGs 48-95, only on the new LUN. Rinse and repeat.
So you want a persistent, configurable AG rotor for a specific
directory and all it's children? That's not all that simple to do,
because there's no direct connection between the top level directory
and indirect children.

What you are really asking for is a specific instance of the more
generic concept of specifying per-file allocation policy. That's
been on the radar for a long time, but it's not as simple as it
first sounds. This is something i started prototyping years ago
when I was back at SGI:

http://oss.sgi.com/archives/xfs/2009-02/msg00250.html

but that patch series is *extremely* experimental. There are parts
we should pull from it to start putting generic allocation policy
frameworks in place, but the really difficult part of per-file
allocation policy is the bit that I never got to:

1. persistence and what to do with kernels that don't
understand specific policies
2. how to do the policies generically so that we don't make
a huge mess of the code.
3. user interface for managing policies is has not been
really thought through.

SO, if someone wants a project that will keep them busy for many,
many months...
Post by stan hoeppner
Due to the timetable and other restrictions I wouldn't be able to
use patches that might come from fleshing out our ideas here, but I
think it would be very useful functionality for others.
Yes, such things have long been considered useful. The problem is
finding enough people to implement all the stuff we consider
useful...

Cheers,

Dave.
--
Dave Chinner
***@fromorbit.com
Loading...