[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable
From: |
Peter Xu |
Subject: |
Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate |
Date: |
Sun, 5 Mar 2023 17:05:50 -0500 |
Hi, Chuang,
On Fri, Mar 03, 2023 at 06:56:50PM +0800, Chuang Xu wrote:
> Sorry to forget to update the test results in the last patch of v6.
>
> In this version:
>
> - add peter's patch.
> - split mr_do_commit() from mr_commit().
> - adjust the sanity check in address_space_to_flatview().
> - rebase to latest upstream.
> - replace 8260 with 8362 as testing host.
> - update the latest test results.
>
> Here I list some cases which will trigger do_commit() in
> address_space_to_flatview():
>
> 1.virtio_load->virtio_init_region_cache
> 2.virtio_load->virtio_set_features_nocheck
What is this one specifically? I failed to see quickly why this needs to
reference the flatview.
> 3.vapic_post_load
Same confusion to this one..
> 4.tcg_commit
This is not enabled if kvm is on, right?
> 5.ahci_state_post_load
>
> During my test, virtio_init_region_cache() will frequently trigger
> do_commit() in address_space_to_flatview(), which will reduce the
> optimization effect of v6 compared with v1.
IIU above 1 & 4 could leverage one address_space_to_flatview_rcu() which
can keep the old semantics of address_space_to_flatview() by just assert
rcu read lock and do qatomic_rcu_read() (e.g., tcg_commit() will run again
at last stage of vm load). Not sure how much it'll help.
You may also want to have a look at the other patch to optimize ioeventfd
commit here; I think that'll also speed up vm load but not sure how much
your series can further do upon:
https://lore.kernel.org/all/20230228142514.2582-1-longpeng2@huawei.com/
Thanks,
--
Peter Xu
- [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate, Chuang Xu, 2023/03/03
- [PATCH RESEND v6 2/5] rcu: Introduce rcu_read_is_locked(), Chuang Xu, 2023/03/03
- [PATCH RESEND v6 4/5] memory: Add sanity check in address_space_to_flatview, Chuang Xu, 2023/03/03
- [PATCH RESEND v6 1/5] memory: Reference as->current_map directly in memory commit, Chuang Xu, 2023/03/03
- [PATCH RESEND v6 3/5] memory: Introduce memory_region_transaction_do_commit(), Chuang Xu, 2023/03/03
- [PATCH RESEND v6 5/5] migration: Reduce time of loading non-iterable vmstate, Chuang Xu, 2023/03/03
- Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate,
Peter Xu <=
- Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate, Chuang Xu, 2023/03/06
- Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate, Peter Xu, 2023/03/06
- Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate, Chuang Xu, 2023/03/07
- Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate, Peter Xu, 2023/03/07
- Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate, Chuang Xu, 2023/03/08
- Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate, Peter Xu, 2023/03/08
- Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate, Chuang Xu, 2023/03/08
- Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate, Peter Xu, 2023/03/08
- Re: [PATCH RESEND v6 0/5] migration: reduce time of loading non-iterable vmstate, Chuang Xu, 2023/03/09