[[email protected]: suspiciously good fsck times?]

Transferring this thread to the linux-ext4 list instead of linux-ext4-owner. :-)

- Ted

Just to be mean, I have been trying to test the fsck speed of ext4 with lots of small files. The test I ran uses fs_mark to fill a 1TB Seagate drive with 45.6 million 20k files (distributed between 256 subdirectories).

Running on ext3, "fsck -f" takes about one hour.

Running on ext4, with uninit_bg, the same fsck is finished in a bit over 5 minutes - more than 10x faster. (Without uninit_bg, the fsck takes about 10 minutes).

Is this too good to be true? Below is the fsck run itself, the tree is Ted's latest git tree and his 1.41 WIP tools,

ric

[root@localhost Perf]# time /sbin/fsck.ext4 -t -t -f /dev/sdb1
e4fsck 1.41-WIP (07-Jul-2008)
Pass 1: Checking inodes, blocks, and sizes
Pass 1: Memory used: 40632k/69424k (36424k/4209k), time: 204.95/78.22/25.58 Pass 1: I/O read: 11140MB, write: 0MB, rate: 54.35MB/s
Pass 2: Checking directory structure
Pass 2: Memory used: 70184k/61968k (51803k/18382k), time: 76.47/50.27/ 8.77 Pass 2: I/O read: 3023MB, write: 0MB, rate: 39.53MB/s
Pass 3: Checking directory connectivity
Peak memory: Memory used: 70184k/61968k (59256k/10929k), time: 281.72/128.59/34.35 Pass 3A: Memory used: 70184k/61968k (59256k/10929k), time: 0.00/ 0.00/ 0.00 Pass 3A: I/O read: 0MB, write: 0MB, rate: 0.00MB/s
Pass 3: Memory used: 70184k/61968k (51803k/18382k), time: 0.03/ 0.00/ 0.00 Pass 3: I/O read: 1MB, write: 0MB, rate: 37.86MB/s
Pass 4: Checking reference counts
Pass 4: Memory used: 70184k/44968k (27354k/42831k), time: 2.37/ 2.36/ 0.00 Pass 4: I/O read: 0MB, write: 0MB, rate: 0.00MB/s
Pass 5: Checking group summary information
Pass 5: Memory used: 70184k/240k (64619k/5566k), time: 19.40/ 5.52/ 0.29 Pass 5: I/O read: 34MB, write: 0MB, rate: 1.75MB/s
/dev/sdb1: 45600268/61054976 files (0.0% non-contiguous), 232657574/244190000 blocks Memory used: 70184k/240k (64889k/5296k), time: 303.54/136.48/34.65
I/O read: 14198MB, write: 1MB, rate: 46.77MB/s

real    5m3.993s
user    2m16.477s
sys     0m35.041s

Wow. My guess is that flex_bg is making the difference. What we would want to compare is the I/O read statistics line:

That's pretty good, and indicates we've avoided a *lot* of seeking. The e2fsck -t -t output for ext3 should show roughly the same mount of I/O read (with 20k files, there would be no advantage towards using extents), but the I/O rate is probably *much* lower, indicating a lot more seeking is going on.

Can you send the full e2fsck -t -t output of the ext3 run? And what is the hdparm -t -t results of the disk?

If I'm right, if you create the filesystem with mke2fs -t ext4dev -O ^flex_bg,^uninit_bg, you should see performance back to the old ext3 levels.

- Ted

P.S. We probably do want to examine the block allocation layout with flex_bg to make sure that the filesystem ages well in the long term.

We did run fsck through seekwatcher & saw a significant reduction in seeks/sec for ext4. Eric has the pretty pictures that he can share.

I didn't run the ext3 test with -t -t (but can refill and rerun, takes about 12 hours).

This disk is a relatively new Seagate 1TB drive, specs at:

http://www.seagate.com/ww/v/index.jsp?vgnextoid=0732f141e7f43110VgnVCM100000f5ee0a0aRCRD

hdparm test:

[root@localhost rwheeler]# /sbin/hdparm -t -t /dev/sdb

/dev/sdb:
Timing buffered disk reads: 186 MB in 3.03 seconds = 61.33 MB/sec

With uninit_bg off, it ran about 10 minutes, but it would be interesting to run without either.

Testing aged file systems is always the holy grail - this workload is a fairly artificial one and was laid down with 4 threads currently writing to a shared subdirectory.

ric

Pictures are always fun! It would be great to see the comparison between ext3 and ext4 for fsck in this case.

I meant hdparm -t -T, but that's ok, the 61.33 MB/sec is what I was curious about. So for this very artificial benchmark, fsck was using 2/3rd of the disk's full benchmark. Not bad. :-)

If you haven't nuked the ext4 filesystem yet, can you grab a dumpe2fs of it first, so we can compare it to the inode allocation patterns under ext3. Thanks!!

- Ted

I thought we actually had flex_bg off at least on the first run and it still looked good. (Ric just made the fs with mkfs.ext3 -j -I 256 -E test_fs initially I think)

Val & I talked about this a little, and came to the conclusion that directory fragmentation might be a pretty big part of it.

I did a similar workload on a much smaller fs, and the largest dir (~11MB) looked like this on ext3:

BLOCKS:
(0-4):3950592-3950596, (5):3950604, (6-7):3950606-3950607, (8):3950630, (9):3950871, (10-11):3950875-3950876, (IND):3950899, (12):3950900, (13):3950934, (14):3950937, (15-16):3950943-3950944, (17):3951390, (18):3951396, (19):3951402, (20):3951406, (21):3951408, (22):3951410, (23):3951581, (24):3951684, (25):3951985, (26):3952031, (27):3952156, (28):3952322, (29):3952418, (30):3952599, (31):3952626, (32):3954038, (33):3954693, (34):3954698, (35):3954874, (36):3955108, (37):3955708, (38):3955711, (39):3956034, (40):3956598, (41):3957173, (42):3957179, (43):3957622, (44):3957763, (45):3957824, (46):3957910, (47):3958190, (48):3958302, (49):3958488, (50):3958834, (51):3959173, (52):3959468, (53):3959842, (54):3959903, (55):3960029, (56):3960245, (57):3960446 ..... ad naseum ...
(4032):4893557, (4033):4894194, (4034):4894719, (4035):4937580, (4036):4937887, (4037):4939087, (4038):4939233, (4039):4939502, (4040):4939508, (4041):4940473, (4042-4043):4940939-4940940, (4044):4941191, (4045):4941402, (4046-4048):4941409-4941411, (4049):4943061, (4050):4943307, (4051-4052):4943314-4943315
TOTAL: 4058

compared to ext4:

BLOCKS:
(0):1900544, (1-5070):1900546-1905615
TOTAL: 5071

sure do (AFAIK these were with neither flex_bg nor uninit_bg):

http://people.redhat.com/esandeen/ext4/e4fsck-1T.png
http://people.redhat.com/esandeen/ext4/e3fsck-1T.png
http://people.redhat.com/esandeen/ext4/ext3-ext4-fsck-1T.png

I'm still working out what's what. But that hockey-stick-shaped red line for ext4 is intriguing, I think it's very densely packed $SOMETHING that ext3 had to seek all over for, guessing it's the directories. Although that strikes me as an odd place for the root-level directories to land.

I need to check, does ext3 use reservation windows for directories? Looks like maybe it should... :)

-Eric

Hmm, could be. Let's see. Ric said 46.5 million files, I don't know how big the filenames were, but let's assume a directory entry size of 32, so that means if we assume perfect packing, 128 directory entries per 4k block. Let's use 100 directory entries/blok just to make the math easyer, so that's 465,000 blocks. If we assume a 10ms seek time, and that the blocks are totally scattered, that's 4650 seconds, or 1.29 hours. So that's roughly within the ballpark that Ric measured.

- Ted

btw guys this thread is not on linux-ext4, it's going to linux-ext4-owner

maybe someone who has them all can bounce to the list ;)

-Eric

Based on the graphs which Eric posted, One interesting thing I think you'll find if you repeat the ext3 experiment with e2fsck -t -t is that pass2 will be about seven times longer than pass1. (Which is backwards from most e2fsck runs, where pass2 is about half pass 1's run time --- although obviously that depends on how many directory blocks you have.)

Yes, some kind of reservation windows would help on ext3 --- but the question is whether such a change would be too-specific for this benchmark or not. Most of the time directories don't grow to such a huge size. So if you use a smallish (around 8 blocks, say) for many directories this might lead to more filesystem fragmentation that in the long run would cause the filesystem not to age well; it also wouldn't help much when you have over 11 million files in the directory, and a directory with over 100,000 blocks.

I don't think delayed allocation is what's helping here either, because the journal will force the directory blocks to be placed as soon as we commit a transaction. I think what's saving us here is that flex_bg and mballoc is separating the directory blocks from the data blocks, allowng the directory blocks to be closely packed together.

- Ted

Pass2 was where both spent most of their time, but I can rerun later to validate that.

I think that the key is to lay out the directories (or files for that matter) in reasonably contiguous chunks. If we could always bump up the allocation by enough to capture a full disk track (128k? 512k?) you would probably be near optimal, but any significant portion of a track would also help.

It would be interesting to rerun with the 46 million files in one directory as well (basically, for working sets that have no natural mapping into directories like some object based workloads).

I can try to validate that, thanks!

ric

I think you'll hit a limit around 15M files in a single directory.

Cheers, Andreas
--
Andreas Dilger
Sr. Staff Engineer, Lustre Group
Sun Microsystems of Canada, Inc.

Probably still worth a quick test, just to see how well it holds up at the edge, thanks!

ric

I made a new ext4 file system without flex_bg or uninit:[

root@localhost Perf]# /sbin/debuge4fs /dev/sdb1
debuge4fs 1.41-WIP (07-Jul-2008)
debuge4fs: feature
Filesystem features: has_journal ext_attr resize_inode dir_index filetype extent sparse_super large_file

The fsck time was a bit slower, but still looks like 8 minutes on ext4 vs 1 hour on ext3:

[root@localhost Perf]# umount /mnt
[root@localhost Perf]# time /sbin/fsck.ext4 -t -t -f /dev/sdb1
e4fsck 1.41-WIP (07-Jul-2008)
Pass 1: Checking inodes, blocks, and sizes
Pass 1: Memory used: 43944k/69424k (36476k/7469k), time: 352.48/93.27/29.45 Pass 1: I/O read: 14914MB, write: 0MB, rate: 42.31MB/s
Pass 2: Checking directory structure
Pass 2: Memory used: 71396k/61968k (51854k/19543k), time: 73.00/50.46/ 7.65 Pass 2: I/O read: 3023MB, write: 0MB, rate: 41.41MB/s
Pass 3: Checking directory connectivity
Peak memory: Memory used: 71396k/61968k (59307k/12090k), time: 425.82/143.83/37.10 Pass 3A: Memory used: 71396k/61968k (59307k/12090k), time: 0.00/ 0.00/ 0.00 Pass 3A: I/O read: 0MB, write: 0MB, rate: 0.00MB/s
Pass 3: Memory used: 71396k/61968k (51854k/19543k), time: 0.01/ 0.00/ 0.00 Pass 3: I/O read: 1MB, write: 0MB, rate: 76.91MB/s
Pass 4: Checking reference counts
Pass 4: Memory used: 71396k/44968k (27406k/43991k), time: 2.37/ 2.36/ 0.00 Pass 4: I/O read: 0MB, write: 0MB, rate: 0.00MB/s
Pass 5: Checking group summary information
Pass 5: Memory used: 71396k/240k (64671k/6726k), time: 63.60/ 4.98/ 0.33 Pass 5: I/O read: 37MB, write: 0MB, rate: 0.58MB/s
/dev/sdb1: 45600268/61054976 files (0.0% non-contiguous), 232657587/244190000 blocks Memory used: 71396k/240k (64671k/6726k), time: 491.82/151.17/37.43
I/O read: 17974MB, write: 1MB, rate: 36.55MB/s

real    8m12.260s
user    2m31.167s
sys     0m37.766s