summaryrefslogtreecommitdiffstats
path: root/usr.bin/vmstat
Commit message (Collapse)AuthorAgeFilesLines
* Uncomment the description of the -f option. Add rfork() to the list oftjr2003-04-141-9/+10
| | | | | | system calls it displays stats about. PR: 50924
* Reimplement the vmstat -f option (display fork statistics).tjr2003-04-141-15/+17
| | | | | PR: 50924 Submitted by: Ken Stailey (with a few changes)
* Slightly rework formatting in vmstat -i so that it doesn'tmux2003-04-101-3/+3
| | | | break with "fooX irqY" lines that are a bit bigger.
* Run a revision of the devstat interface:phk2003-03-151-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Kernel: Change statistics to use the *uptime() timescale (ie: relative to boottime) rather than the UTC aligned timescale. This makes the device statistics code oblivious to clock steps. Change timestamps to bintime format, they are cheaper. Remove the "busy_count", and replace it with two counter fields: "start_count" and "end_count", which are updated in the down and up paths respectively. This removes the locking constraint on devstat. Add a timestamp argument to devstat_start_transaction(), this will normally be a timestamp set by the *_bio() function in bp->bio_t0. Use this field to calculate duration of I/O operations. Add two timestamp arguments to devstat_end_transaction(), one is the current time, a NULL pointer means "take timestamp yourself", the other is the timestamp of when this transaction started (see above). Change calculation of busy_time to operate on "the salami principle": Only when we are idle, which we can determine by the start+end counts being identical, do we update the "busy_from" field in the down path. In the up path we accumulate the timeslice in busy_time and update busy_from. Change the byte_* and num_* fields into two arrays: bytes[] and operations[]. Userland: Change the misleading "busy_time" name to be called "snap_time" and make the time long double since that is what most users need anyway, fill it using clock_gettime(CLOCK_MONOTONIC) to put it on the same timescale as the kernel fields. Change devstat_compute_etime() to operate on struct bintime. Remove the version 2 legacy interface: the change to bintime makes compatibility far too expensive. Fix a bug in systat's "vm" page where boot relative busy times would be bogus. Bump __FreeBSD_version to 500107 Review & Collaboration by: ken
* Update to use current rev of devstat API.phk2003-03-151-9/+9
|
* Add #include <sys/resource.h>phk2003-02-161-0/+1
| | | | | My apologies for missing these #includes, I must have confused the dependencies with a wrong timestamp or something.
* Remove #include <sys/dkstat.h>phk2003-02-161-1/+0
|
* Make 'sysctl vm.vmtotal' work properly using updated patch from Hiten.dillon2003-01-111-1/+1
| | | | | | | (the patch in the PR was stale). PR: kern/5689 Submitted by: Hiten Pandya <hiten@unixdaemons.com>
* The boottime variable in sys/kern/kern_tc.c is a struct timeval, not atmm2002-08-091-3/+4
| | | | | time_t, so do not use the latter as type when retrieving the variable via libkvm. This should fix vmstat on sparc64.
* The .Nm utilitycharnier2002-07-141-2/+5
|
* Replace /kernel with /boot/kernel/kernel.joe2002-05-091-3/+3
| | | | | PR: docs/37757 Submitted by: Hiten Pandya <hiten@uk.FreeBSD.org>
* Remove malloc_type's ks_limit.jeff2002-04-151-71/+17
| | | | | | | | | | | | Updated the kmemzones logic such that the ks_size bitmap can be used as an index into it to report the size of the zone used. Create the kern.malloc sysctl which replaces the kvm mechanism to report similar data. This will provide an easy place for statistics aggregation if malloc_type statistics become per cpu data. Add some code ifdef'd under MALLOC_PROFILING to facilitate a tool for sizing the malloc buckets.
* Fix a missed conversion of lld to llu for the uint64_t ks_calls and castasmodai2002-04-131-6/+7
| | | | | | | | | | | to unsigned long long. Don't be too overzealous with the printing of ks_calls in the total statistics, cut back from 20 to 13 positions to print (which should last a couple of years easily (20 digits is enough for 3168 years of calls at a measly billion (10^9) calls per second.)). Submitted by: bde
* Cast totreq to unsigned long long, as needed on 64-bit machines.asmodai2002-04-081-1/+2
| | | | Pointed out by: jeff
* Change totreq to uint64_t from a long (the PR has an int64_t, which didn'tasmodai2002-04-081-3/+4
| | | | | | | | | | make sense to me) and change the printf argument from %8ld to %20llu to accompany the printing of the totals. Realigned the header printed above it as well. PR: 32342 Submitted by: ryan beasley <ryanb@goddamnbastard.org> Reviewed by: jeff, Tim J Robbins
* remove __Pimp2002-03-221-16/+16
|
* Remove the kmembuckets stats in preparation for the UMA commit.jeff2002-03-191-68/+9
|
* Remove NO_WERRORs and WARNS=n's. To be revisited after GCC3.markm2002-02-081-1/+0
|
* WARNS=2 fixes, but set NO_WERROR, as there are some HardToFix(tm)markm2001-12-112-55/+63
| | | | warnings originating in system headers.
* SECURITY: Drop `setgid kmem' bit as early as possible.ru2001-08-311-0/+1
|
* Change the compute_stats() call to the new devstat_compute_statistics()ken2001-08-111-21/+21
| | | | | | | | interface. Cast the return of the rest of the printfs in here to void. Submitted by: "Sergey A. Osokin" <osa@freebsd.org.ru>
* Correct the old length argument passed to sysctl to be a pointer to atmm2001-07-291-1/+2
| | | | | | size_t (not to an int). MFC after: 2 days
* Remove whitespace at EOL.dd2001-07-151-9/+9
|
* mdoc(7) police: removed HISTORY info from the .Os call.ru2001-07-101-1/+1
|
* Increase column widths when using -i (they are now wide enough toschweikh2001-06-261-3/+3
| | | | | | | | | hold a 64bit or 32bit ~0 value, i.e. 20 and 10; this anticipates soon-to-be machines with Exahertz rtc interrupt frequencies. :-) PR: bin/16206 Submitted by: John Capo <jc@irbs.com> MFC after: 1 week
* Reduce field width for some columns so that the default output fits in <= 79schweikh2001-06-231-3/+3
| | | | | | | columns. 80 columns + newline is a problem for some terminals including syscons. Requested by: bde MFC after: 1 week
* Made all fields in default output be space separated. Run-togetherschweikh2001-06-191-11/+6
| | | | | | | | | | columns confuse the heck out of other apps trying to parse vmstat output (eg sscope). I made sure we're still <= 80 cols per line. Fixed warnings about unused vars and printf %format mismatches. Requested by: Eugene Aleynikov <eugenea@infospace.com> Reviewed by: joerg (implicitly) MFC after: 2 weeks
* Avoid the avm field joining the w field when avm is > 9.999.999 pagesschweikh2001-06-131-1/+1
| | | | | | | | which is slightly less than 4GB. To use a quote from someone who shall remain nameless "No one will ever need more than 4 GB" :-) But FreeBSD is prepared if we one day will. Requested by: Eugene Aleynikov <eugenea@infospace.com>
* Increase field width by one for 'fre' to accomodate today's memory sizes.schweikh2001-06-121-3/+3
| | | | | | | PR: 25267 Submitted by: Eugene Aleynikov <eugene@infospace.com> Reviewed by: joerg MFC after: 2 weeks
* Removed -I${.CURDIR}/.../sys from CFLAGS.ru2001-05-181-1/+0
|
* MAN[1-9] -> MAN.ru2001-03-271-2/+2
|
* fix usage statement (add missing [-n devs] option)alfred2001-02-221-4/+5
| | | | | | | Submitted by: Maxim Konovalov <maxim@macomnet.ru> Silence a warning by renaming the 'pgtok' #define to 'vmstat_pgtok' so as not to conflict with the 'pgtok' #define in sys/param.h
* mdoc(7) police: split punctuation characters + misc fixes.ru2001-02-011-1/+6
|
* Add mibs to hold the number of forks since boot. New mibs are:ume2001-01-231-0/+8
| | | | | | | | | | | | | | vm.stats.vm.v_forks vm.stats.vm.v_vforks vm.stats.vm.v_rforks vm.stats.vm.v_kthreads vm.stats.vm.v_forkpages vm.stats.vm.v_vforkpages vm.stats.vm.v_rforkpages vm.stats.vm.v_kthreadpages Submitted by: Paul Herman <pherman@frenchfries.net> Reviewed by: alfred
* Document that the -z option is equivalent to 'sysctl vm.zone'.des2001-01-231-1/+5
|
* Use the vm.zone sysctl rather that grope through the zone allocator'sdes2001-01-231-52/+15
| | | | internal data structures.
* Update vm zone list traversal for changes made to kernel. Note that thismjacob2001-01-231-2/+6
| | | | | | is ultimately silly because no locks are held in user space while traversing the list via kvm_reads... really, this should use the sysctl interface which *is* protected by a lock in the kernel.
* Prepare for mdoc(7)NG.ru2000-12-191-5/+5
|
* mdoc(7) police: use the new features of the Nm macro.ru2000-11-201-1/+1
|
* Remove unneeded #include <sys/buf.h>phk2000-05-051-1/+0
|
* unifdef -Uvax -Uhp300 -Uluna68k -Umips -Utahoephk1999-09-011-48/+0
|
* $Id$ -> $FreeBSD$peter1999-08-282-2/+2
|
* Convert interrupt count from signed to unsigned and the totaln_hibma1999-07-261-4/+6
| | | | | | | | from signed long to unsigned lon long. PR: 12808 Submitted by: Kevin Day toasty@dragondata.com Reviewed by: bde
* Correct description of -c and -w optionskris1999-06-061-8/+10
| | | | | Inspired by: PR docs/11774 Submitted by: Chad R. Larson <chad@freeway.dcfinc.com>
* Backed out the previous commit, except for the parts that reducedbde1999-05-121-11/+5
| | | | | | | the magicness of 200. Cleaned up the remaining parts. Circularisation of the list of malloc types was a kernel bug (now fixed). Interfering with applications' definitions of pgtok is a system header bug (not fixed).
* Sometime since this file was written, the list of kernel malloc typesimp1999-05-101-4/+15
| | | | | | | | | changed from a simple list to a circular one. We compensate by only looping until we see the first address again. Before, things would terminate because it was limited to 200 iterations. This lead to bogus statistics and repeating stats for memory types. This should be merged into 3.2, as the same bug is there.
* Move an option outside of a nested list and up a bit to live free amongkris1999-04-261-3/+3
| | | | its brothers and sisters.
* Fixed bitrot in usage message and disordering of options in previous commit.bde1999-02-151-7/+7
| | | | | | | I'm not sure why we have `mvstat -z'. `sysctl vm.zone' gives more information. OTOH, `sysctl vm.zone' shouldn't return ASCII data, and reporting of memory use should be integrated, at least as an option.
* Fixed disordering of options in previous commit.bde1999-02-151-4/+4
|
* Add -z option to vmstat to dump data from the zone allocatordillon1999-02-132-12/+77
|
OpenPOWER on IntegriCloud