Date: Fri, 27 Sep 2019 19:14:03 +0000 (UTC) From: Mateusz Guzik <mjg@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org Subject: svn commit: r352813 - head/sys/kern Message-ID: <201909271914.x8RJE3u7046957@repo.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: mjg Date: Fri Sep 27 19:14:03 2019 New Revision: 352813 URL: https://svnweb.freebsd.org/changeset/base/352813 Log: cache: decrease ncnegfactor to 5 The current mechanism is bogus in several ways: - the limit is a percentage of total entries added, which means negative entries get evicted all the time even if there are plenty of resources - evicting code is almost not concurrent, which makes it unable to remove entries fast enough when doing something as simple as -j 104 buildworld - there is no support for performing mass removal if necessary Vast majority of negative entries never get any hits. Only evicting them when the filesystem demands it results in a significant growth of the namecache with almost no improvement in the hit ratio. Sample result about afer 90 minutes of poudriere -j 104: current no evict % of the original numneg 219737 2013157 916 numneghits 266711906 263544562 98 [1] [1] this may look funny but there is a certain dose of variation to the build The number was chosen as something which mostly eliminates spurious evictions during lighter workloads but still keeps the total at bay. Sponsored by: The FreeBSD Foundation Modified: head/sys/kern/vfs_cache.c Modified: head/sys/kern/vfs_cache.c ============================================================================== --- head/sys/kern/vfs_cache.c Fri Sep 27 19:13:22 2019 (r352812) +++ head/sys/kern/vfs_cache.c Fri Sep 27 19:14:03 2019 (r352813) @@ -200,7 +200,7 @@ static __read_mostly LIST_HEAD(nchashhead, namecache) static u_long __read_mostly nchash; /* size of hash table */ SYSCTL_ULONG(_debug, OID_AUTO, nchash, CTLFLAG_RD, &nchash, 0, "Size of namecache hash table"); -static u_long __read_mostly ncnegfactor = 12; /* ratio of negative entries */ +static u_long __read_mostly ncnegfactor = 5; /* ratio of negative entries */ SYSCTL_ULONG(_vfs, OID_AUTO, ncnegfactor, CTLFLAG_RW, &ncnegfactor, 0, "Ratio of negative namecache entries"); static u_long __exclusive_cache_line numneg; /* number of negative entries allocated */
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201909271914.x8RJE3u7046957>