Date: Tue, 29 Jan 2013 17:20:15 -0600 From: Kevin Day <toasty@dragondata.com> To: FreeBSD Filesystems <freebsd-fs@freebsd.org> Subject: Improving ZFS performance for large directories Message-ID: <19DB8F4A-6788-44F6-9A2C-E01DEA01BED9@dragondata.com>
next in thread | raw e-mail | index | archive | help
I'm trying to improve performance when using ZFS in large (>60000 files) =
directories. A common activity is to use "getdirentries" to enumerate =
all the files in the directory, then "lstat" on each one to get =
information about it. Doing an "ls -l" in a large directory like this =
can take 10-30 seconds to complete. Trying to figure out why, I did:
ktrace ls -l /path/to/large/directory
kdump -R |sort -rn |more
to see what sys calls were taking the most time, I ended up with:
69247 ls 0.190729 STRU struct stat {dev=3D846475008, =
ino=3D46220085, mode=3D-rw-r--r-- , nlink=3D1, uid=3D0, gid=3D0, =
rdev=3D4294967295, atime=3D1333196714, stime=3D1201004393, =
ctime=3D1333196714.547566024, birthtime=3D1333196714.547566024, =
size=3D30784, blksize=3D31232, blocks=3D62, flags=3D0x0 }
69247 ls 0.180121 STRU struct stat {dev=3D846475008, =
ino=3D46233417, mode=3D-rw-r--r-- , nlink=3D1, uid=3D0, gid=3D0, =
rdev=3D4294967295, atime=3D1333197088, stime=3D1209814737, =
ctime=3D1333197088.913571042, birthtime=3D1333197088.913571042, =
size=3D3162220, blksize=3D131072, blocks=3D6409, flags=3D0x0 }
69247 ls 0.152370 RET getdirentries 4088/0xff8
69247 ls 0.139939 CALL stat(0x800d8f598,0x7fffffffcca0)
69247 ls 0.130411 RET __acl_get_link 0
69247 ls 0.121602 RET __acl_get_link 0
69247 ls 0.105799 RET getdirentries 4064/0xfe0
69247 ls 0.105069 RET getdirentries 4068/0xfe4
69247 ls 0.096862 RET getdirentries 4028/0xfbc
69247 ls 0.085012 RET getdirentries 4088/0xff8
69247 ls 0.082722 STRU struct stat {dev=3D846475008, =
ino=3D72941319, mode=3D-rw-r--r-- , nlink=3D1, uid=3D0, gid=3D0, =
rdev=3D4294967295, atime=3D1348686155, stime=3D1348347621, =
ctime=3D1348686155.768875422, birthtime=3D1348686155.768875422, =
size=3D6686225, blksize=3D131072, blocks=3D13325, flags=3D0x0 }
69247 ls 0.070318 STRU struct stat {dev=3D846475008, =
ino=3D46211679, mode=3D-rw-r--r-- , nlink=3D1, uid=3D0, gid=3D0, =
rdev=3D4294967295, atime=3D1333196475, stime=3D1240230314, =
ctime=3D1333196475.038567672, birthtime=3D1333196475.038567672, =
size=3D829895, blksize=3D131072, blocks=3D1797, flags=3D0x0 }
69247 ls 0.068060 RET getdirentries 4048/0xfd0
69247 ls 0.065118 RET getdirentries 4088/0xff8
69247 ls 0.062536 RET getdirentries 4096/0x1000
69247 ls 0.061118 RET getdirentries 4020/0xfb4
69247 ls 0.055038 STRU struct stat {dev=3D846475008, =
ino=3D46220358, mode=3D-rw-r--r-- , nlink=3D1, uid=3D0, gid=3D0, =
rdev=3D4294967295, atime=3D1333196720, stime=3D1274282669, =
ctime=3D1333196720.972567345, birthtime=3D1333196720.972567345, =
size=3D382344, blksize=3D131072, blocks=3D773, flags=3D0x0 }
69247 ls 0.054948 STRU struct stat {dev=3D846475008, =
ino=3D75025952, mode=3D-rw-r--r-- , nlink=3D1, uid=3D0, gid=3D0, =
rdev=3D4294967295, atime=3D1351071350, stime=3D1349726805, =
ctime=3D1351071350.800873870, birthtime=3D1351071350.800873870, =
size=3D2575559, blksize=3D131072, blocks=3D5127, flags=3D0x0 }
69247 ls 0.054828 STRU struct stat {dev=3D846475008, =
ino=3D65021883, mode=3D-rw-r--r-- , nlink=3D1, uid=3D0, gid=3D0, =
rdev=3D4294967295, atime=3D1335730367, stime=3D1332843230, =
ctime=3D1335730367.541567371, birthtime=3D1335730367.541567371, =
size=3D226347, blksize=3D131072, blocks=3D517, flags=3D0x0 }
69247 ls 0.053743 STRU struct stat {dev=3D846475008, =
ino=3D46222016, mode=3D-rw-r--r-- , nlink=3D1, uid=3D0, gid=3D0, =
rdev=3D4294967295, atime=3D1333196765, stime=3D1257110706, =
ctime=3D1333196765.206574132, birthtime=3D1333196765.206574132, =
size=3D62112, blksize=3D62464, blocks=3D123, flags=3D0x0 }
69247 ls 0.052015 RET getdirentries 4060/0xfdc
69247 ls 0.051388 RET getdirentries 4068/0xfe4
69247 ls 0.049875 RET getdirentries 4088/0xff8
69247 ls 0.049156 RET getdirentries 4032/0xfc0
69247 ls 0.048609 RET getdirentries 4040/0xfc8
69247 ls 0.048279 RET getdirentries 4032/0xfc0
69247 ls 0.048062 RET getdirentries 4064/0xfe0
69247 ls 0.047577 RET getdirentries 4076/0xfec
(snip)
the STRU are returns from calling lstat().
It looks like both getdirentries and lstat are taking quite a while to =
return. The shortest return for any lstat() call is 0.000004 seconds, =
the maximum is 0.190729 and the average is around 0.0004. Just from =
lstat() alone, that makes "ls" take over 20 seconds.
I'm prepared to try an L2arc cache device (with =
secondarycache=3Dmetadata), but I'm having trouble determining how big =
of a device I'd need. We've got >30M inodes now on this filesystem, =
including some files with extremely long names. Is there some way to =
determine the amount of metadata on a ZFS filesystem?
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19DB8F4A-6788-44F6-9A2C-E01DEA01BED9>