John Wren Kennedy c0e58995e3 Large sync writes perform worse with slog
For synchronous write workloads with large IO sizes, a pool configured
with a slog performs worse than one with an embedded zil:

sequential_writes 1m sync ios, 16 threads
  Write IOPS:              1292          438   -66.10%
  Write Bandwidth:      1323570       448910   -66.08%
  Write Latency:       12128400     36330970      3.0x

sequential_writes 1m sync ios, 32 threads
  Write IOPS:              1293          430   -66.74%
  Write Bandwidth:      1324184       441188   -66.68%
  Write Latency:       24486278     74028536      3.0x

The reason is the `zil_slog_bulk` variable. In `zil_lwb_write_open`,
if a zil block is greater than 768K, the priority of the write is
downgraded from sync to async. Increasing the value allows greater
throughput. To select a value for this PR, I ran an fio workload with
the following values for `zil_slog_bulk`:

    zil_slog_bulk    KiB/s
    1048576         422132
    2097152         478935
    4194304         533645
    8388608         623031
    12582912        827158
    16777216       1038359
    25165824       1142210
    33554432       1211472
    50331648       1292847
    67108864       1308506
    100663296      1306821
    134217728      1304998

At 64M, the results with a slog are now improved to parity with an
embedded zil:

sequential_writes 1m sync ios, 16 threads
  Write IOPS:               438         1288      2.9x
  Write Bandwidth:       448910      1319062      2.9x
  Write Latency:       36330970     12163408   -66.52%

sequential_writes 1m sync ios, 32 threads
  Write IOPS:               430         1290      3.0x
  Write Bandwidth:       441188      1321693      3.0x
  Write Latency:       74028536     24519698   -66.88%

None of the other tests in the performance suite (run with a zil or
slog) had a significant change, including the random_write_zil tests,
which use multiple datasets.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Tony Nguyen <tony.nguyen@delphix.com>
Signed-off-by: John Wren Kennedy <john.kennedy@delphix.com>
Closes #14378
2023-10-13 11:15:09 -07:00
2023-10-13 10:41:11 -07:00
2023-10-02 16:58:54 -07:00
2023-10-10 08:55:42 -07:00
2022-12-22 11:34:28 -08:00
2020-06-09 21:24:09 -07:00
2018-05-29 16:00:33 -07:00
2023-09-12 12:51:11 -07:00
2020-08-26 21:44:41 -07:00
2018-05-29 16:00:33 -07:00
2022-01-06 16:25:01 -08:00
2021-04-02 16:33:40 -07:00
2020-03-16 10:46:03 -07:00

img

OpenZFS is an advanced file system and volume manager which was originally developed for Solaris and is now maintained by the OpenZFS community. This repository contains the code for running OpenZFS on Linux and FreeBSD.

codecov coverity

Official Resources

Installation

Full documentation for installing OpenZFS on your favorite operating system can be found at the Getting Started Page.

Contribute & Develop

We have a separate document with contribution guidelines.

We have a Code of Conduct.

Release

OpenZFS is released under a CDDL license. For more details see the NOTICE, LICENSE and COPYRIGHT files; UCRL-CODE-235197

Supported Kernels

  • The META file contains the officially recognized supported Linux kernel versions.
  • Supported FreeBSD versions are any supported branches and releases starting from 12.2-RELEASE.
S
Description
No description provided
Readme 122 MiB
Languages
C 70.2%
Shell 19.9%
Assembly 5.1%
M4 1.9%
Python 1.6%
Other 1.3%