Linux-Fsdevel Archive on lore.kernel.org help / color / mirror / Atom feed
From: Alessio Balsini <email@example.com> To: Miklos Szeredi <firstname.lastname@example.org> Cc: Alessio Balsini <email@example.com>, Akilesh Kailash <firstname.lastname@example.org>, Amir Goldstein <email@example.com>, Antonio SJ Musumeci <firstname.lastname@example.org>, David Anderson <email@example.com>, Giuseppe Scrivano <firstname.lastname@example.org>, Jann Horn <email@example.com>, Jens Axboe <firstname.lastname@example.org>, Martijn Coenen <email@example.com>, Palmer Dabbelt <firstname.lastname@example.org>, Paul Lawrence <email@example.com>, Stefano Duo <firstname.lastname@example.org>, Zimuzo Ezeozue <email@example.com>, fuse-devel <firstname.lastname@example.org>, kernel-team <email@example.com>, firstname.lastname@example.org, email@example.com Subject: Re: [PATCH V9 0/4] fuse: Add support for passthrough read/write Date: Fri, 2 Oct 2020 14:38:02 +0100 [thread overview] Message-ID: <20201002133802.GA3595556@google.com> (raw) In-Reply-To: <CAJfpeguFZwkZh0wkPjOLpXODdp_9jELKUrwBgEhDVF4+T8FgTw@mail.gmail.com> On Wed, Sep 30, 2020 at 05:33:30PM +0200, Miklos Szeredi wrote: > On Thu, Sep 24, 2020 at 3:13 PM Alessio Balsini <firstname.lastname@example.org> wrote: > > > The first benchmarks were done by running FIO (fio-3.21) with: > > - bs=4Ki; > > - file size: 50Gi; > > - ioengine: sync; > > - fsync_on_close: true. > > The target file has been chosen large enough to avoid it to be entirely > > loaded into the page cache. > > Results are presented in the following table: > > > > +-----------+--------+-------------+--------+ > > | Bandwidth | FUSE | FUSE | Bind | > > | (KiB/s) | | passthrough | mount | > > +-----------+--------+-------------+--------+ > > | read | 468897 | 502085 | 516830 | > > +-----------+--------+-------------+--------+ > > | randread | 15773 | 26632 | 21386 | > > > Have you looked into why passthrough is faster than native? > > Thanks, > Miklos Hi Miklos, Thank you for bringing this to my attention, I probably missed it because focusing on the comparison between FUSE and FUSE passthrough. I jumped back to benchmarkings right after you sent this email. At a first glance I though I made a stupid copy-paste mistake, but looking at a bunch of partial results I'm collecting, I realized that the Vi550 S3 SSD I'm using has sometimes unstable performance, especially when dealing with random offsets. I also realized that SSD performance might change depending on previous operations. To solve these issues, each test is now being run 10 times, and at post-processing time I'm thinking of getting the median to remove possible outliers. I also noticed that the performance noise increases after a few minutes the SSD is busy. This made me think of some kind of SSD thermal throttling I totally overlooked. This might be reason why passthrough is performing better than native in the numbers you highlighted. Unfortunately the SMART registers of my SSD always reports 33 Celsius degrees regardless the workload, so to solve this I'm now applying a 5 minutes cooldown between each run. This time I'm also removing fsync_on_close and reducing the file size to 25 GiB to improve caching and limit the interaction with the SSD during writes. Still for caching reasons I am also separating the creation of the fio target file from the actual execution of the benchmark by first running fio with create_only=1. Before triggering fio, in the above benchmark I was just sync-ing and dropping the pagecache, I now also drop slab objects, including inodes and dentries: echo 3 > /proc/sys/vm/drop_caches that I suspect wouldn't make any difference, but wouldn't harm as well. Please let me know if you have any suggestion on how to improve my benchmarks, or if you recommend tools other than fio (that I actually really like) to make comparisons. Thanks, Alessio
next prev parent reply other threads:[~2020-10-02 13:38 UTC|newest] Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-09-24 13:13 [PATCH V9 0/4] fuse: Add support for passthrough read/write Alessio Balsini 2020-09-24 13:13 ` [PATCH V9 1/4] fuse: Definitions and ioctl() for passthrough Alessio Balsini 2020-09-29 14:37 ` Alessio Balsini 2020-09-30 15:44 ` Miklos Szeredi 2020-10-22 16:12 ` Alessio Balsini 2020-09-24 13:13 ` [PATCH V9 2/4] fuse: Trace daemon creds Alessio Balsini 2020-09-30 18:45 ` Miklos Szeredi 2020-09-30 19:16 ` Antonio SJ Musumeci 2020-10-22 16:14 ` Alessio Balsini 2020-09-24 13:13 ` [PATCH V9 3/4] fuse: Introduce synchronous read and write for passthrough Alessio Balsini 2020-09-30 18:50 ` Miklos Szeredi 2020-10-22 16:17 ` Alessio Balsini 2020-09-24 13:13 ` [PATCH V9 4/4] fuse: Handle asynchronous read and write in passthrough Alessio Balsini 2020-09-30 18:54 ` Miklos Szeredi 2020-10-22 16:38 ` Alessio Balsini 2020-09-30 15:33 ` [PATCH V9 0/4] fuse: Add support for passthrough read/write Miklos Szeredi 2020-10-02 13:38 ` Alessio Balsini [this message] 2020-10-21 15:39 ` Alessio Balsini
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20201002133802.GA3595556@google.com \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).