Date: Thu, 19 Jun 2025 11:26:30 +0000 From: bugzilla-noreply@freebsd.org To: net@FreeBSD.org Subject: [Bug 287229] IP reassembly issue in FreeBSD 14.1 Message-ID: <bug-287229-7501-ihd1B3lyEn@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-287229-7501@https.bugs.freebsd.org/bugzilla/> References: <bug-287229-7501@https.bugs.freebsd.org/bugzilla/>
next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D287229 --- Comment #15 from Lucas Aubard <lucas.aubard@irisa.fr> --- Sorry for the late reply; I was running more tests based on the information= you provided. @Timo=20 Thanks for the FreeBSD operating description when processing fragments.=20 I confirm that by commenting vm.kmem_size and vm.kmem_size_max in box bento/freebsd-14.1, the net.inet.ip.maxfragbucketsize value is now set to 7 after a reboot.=20 I also confirm observing the same reassembly across the runs for all our te= st cases. Thanks a lot for pointing out these kernel parameters. @Michael=20 Actually, I did not modify nor check the default VM settings since I observ= ed this behavior with different FreeBSD boxes. For example, the official (?) FreeBSD box freebsd/FreeBSD-14.1-STABLE has o= nly one parameter specified in /boot/loader.conf: autoboot_delay=3D"-1". I am a= lso able to observe a net.inet.ip.maxfragbucketsize value of 1 with this box (t= hat has thus not the vm.kmem_size and vm.kmem_size_max specified) in the case I= run multiple VMs in parallel. From @Rodney's comment, I guess the memory dynamically allocated to the FreeBSD VM is low because multiple VMs are running, leading to a net.inet.ip.maxfragbucketsize value of 1.=20 With the freebsd/FreeBSD-14.1-STABLE box, by manually allocating memory to = the Vagrantfile: - 512Mb gives net.inet.ip.maxfragbucketsize =3D 1. For 40 test cases tested= in parallel, I observed many reassembly inconsistencies. - 1024Mb gives net.inet.ip.maxfragbucketsize =3D 3. For 40 test cases teste= d in parallel, I observed 1 test case reassembly inconsistency (out of the 10,362 test cases). - 2048Mb gives net.inet.ip.maxfragbucketsize =3D 7. For 40 test cases teste= d in parallel, I did not observe any reassembly inconsistency. So, I should force the allocated memory to the FreeBSD box to 2048Mb when running my tests in parallel to avoid observing reassembly inconsistencies. --=20 You are receiving this mail because: You are on the CC list for the bug.=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-287229-7501-ihd1B3lyEn>