public inbox for glibc-bugs@sourceware.org help / color / mirror / Atom feed
From: "mlichvar at redhat dot com" <sourceware-bugzilla@sourceware.org> To: glibc-bugs@sourceware.org Subject: [Bug libc/29437] arc4random is too slow Date: Wed, 03 Aug 2022 06:28:30 +0000 [thread overview] Message-ID: <bug-29437-131-8u6A9VEP9t@http.sourceware.org/bugzilla/> (raw) In-Reply-To: <bug-29437-131@http.sourceware.org/bugzilla/> https://sourceware.org/bugzilla/show_bug.cgi?id=29437 --- Comment #3 from Miroslav Lichvar <mlichvar at redhat dot com> --- I was testing it on 5.18.15-200.fc36.x86_64. The issue is the overhead of making the syscall. For each timestamp only about 6-22 random bits are needed, but as there is no buffering, the number of syscalls is increased significantly. The NTP server is basically a loop of - poll() - recvmmsg() - for each valid request: - arc4random() for RX timestamp from cmsg - arc4random() for TX timestamp taken below - clock_gettime() - TX timestamp - sendmsg() With a vDSO clock_gettime() and arc4random calling getrandom() there are now three syscalls in the inner loop instead of one. -- You are receiving this mail because: You are on the CC list for the bug.
next prev parent reply other threads:[~2022-08-03 6:28 UTC|newest] Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top 2022-08-02 10:46 [Bug libc/29437] New: " mlichvar at redhat dot com 2022-08-02 11:03 ` [Bug libc/29437] " fweimer at redhat dot com 2022-08-02 22:57 ` jason at zx2c4 dot com 2022-08-02 22:58 ` jason at zx2c4 dot com 2022-08-03 6:28 ` mlichvar at redhat dot com [this message] 2022-08-06 13:36 ` crrodriguez at opensuse dot org 2022-08-06 13:54 ` crrodriguez at opensuse dot org 2022-08-08 11:05 ` mlichvar at redhat dot com 2022-08-08 12:29 ` adhemerval.zanella at linaro dot org 2022-08-08 12:35 ` fweimer at redhat dot com 2022-08-08 12:37 ` fweimer at redhat dot com 2022-08-08 12:38 ` adhemerval.zanella at linaro dot org 2022-08-08 12:39 ` jason at zx2c4 dot com 2022-08-08 12:42 ` adhemerval.zanella at linaro dot org 2022-08-08 12:43 ` fweimer at redhat dot com 2022-08-08 12:44 ` fweimer at redhat dot com 2022-08-08 12:45 ` jason at zx2c4 dot com 2022-08-08 12:51 ` adhemerval.zanella at linaro dot org 2022-08-08 12:56 ` jason at zx2c4 dot com 2023-01-09 11:44 ` yann at droneaud dot fr
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=bug-29437-131-8u6A9VEP9t@http.sourceware.org/bugzilla/ \ --to=sourceware-bugzilla@sourceware.org \ --cc=glibc-bugs@sourceware.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 read-only IMAP folder(s) and NNTP newsgroup(s).