diff options
author | наб <[email protected]> | 2021-11-30 17:29:50 +0100 |
---|---|---|
committer | GitHub <[email protected]> | 2021-11-30 09:29:50 -0700 |
commit | 4325de09cd2993837bc32a83d61872b57e58298e (patch) | |
tree | c5ae13f192074277bed2acd157c54c54118afac1 /contrib/bash_completion.d | |
parent | 2a673e76a928cca4df7794cdcaa02e0be149c4da (diff) |
etc/systemd/zfs-mount-generator: serialise, handle keylocation=http[s]://
* etc/systemd/zfs-mount-generator: serialise
The wins for a relatively normal workload are rather slim:
real 0.02119s/0.00985s=2.15029x
user 0.02130s/0.00346s=6.15560x
sys 0.03858s/0.00643s=6.00062x
wall-total 0.014518s/0.005925s=2.45009x
wall-init 0.014518s/0.002457s=5.90684x
wall-real 0.014518s/0.003467s=4.18668x
But this is a big win on machines with a lot of datasets and expensive
forks.
For example, the gain on a VM on my work laptop with 900+ legacy-mount
Docker datasets, the original gains from the C rewrite were
only five-fold:
real 0.516s/0.102s=5.05882x
user 0.237s/0.143s=1.65734x
sys 0.287s/0.100s=2.87x
And this serial variant gains this back there as well:
real 0.102s/0.008s=12.75x
user 0.143s/0.007s=20.42857
sys 0.100s/0.001s=100x
wall-total 0.09717s/0.00319s=30.40255x
wall-init 0.00203s/0.00200s=1.015941x
wall-real 0.09513s/0.00118s=80.02043x
For a total of
real 0.516s/0.008s=64.5x
user 0.237s/0.007s=33.85714x
sys 0.287s/0.001s=287x
Suggested-by: Richard Laager <[email protected]>
* etc/systemd/zfs-mount-generator: pull in network for keylocation=https
Also simplify RequiresMountsFor= handling
Ref: #11956
Reviewed-by: Richard Laager <[email protected]>
Reviewed-by: Tony Nguyen <[email protected]>
Signed-off-by: Ahelenia Ziemiańska <[email protected]>
Closes #12138
Diffstat (limited to 'contrib/bash_completion.d')
0 files changed, 0 insertions, 0 deletions