summaryrefslogtreecommitdiff
path: root/usr.bin/systat
AgeCommit message (Collapse)Author
2013-10-12adopt to queueing changesHenning Brauer
2013-09-11Correctly NUL-terminate the cpu view array. Fix a segfault on powerpcMartin Pieuchot
and probably others. ok reyk@
2013-09-07Add a new screen "cpu" that simply lists the usage of each CPU core.Reyk Floeter
Also add a new -B command line flag that works like -b but waits some cycles before dumping anything to the console. With much help from jmc@ OK jj@ lambert@ jmc@
2013-07-09back out the cache flipper temporarily to work out of tree.Bob Beck
will come back soon. ok deraadt@
2013-06-11High memory page flipping for the buffer cache.Bob Beck
This change splits the buffer cache free lists into lists of dma reachable buffers and high memory buffers based on the ranges returned by pmemrange. Buffers move from dma to high memory as they age, but are flipped to dma reachable memory if IO is needed to/from and high mem buffer. The total amount of buffers allocated is now bufcachepercent of both the dma and the high memory region. This change allows the use of large buffer caches on amd64 using more than 4 GB of memory ok tedu@ krw@ - testing by many.
2013-06-02<sys/dir.h> isn't needed herePhilip Guenther
2013-05-14Don't display swapin/swapout uvmexp fieldsMiod Vallat
2013-03-20Do not expose a kernel address.Theo de Raadt
2012-12-23%zfod was removed in -r1.24; from NaughtyJason McIntyre
2012-12-05Remove excessive sys/cdefs.h inclusionTheo de Raadt
ok guenther millert kettenis
2012-12-04remove some unnecessary sys/param.h inclusionsTheo de Raadt
2012-09-20add more sensor types to sensor framework.Yojiro Uo
- Pressure (10^-3 Pa) - distance (10^-6 m) - acceleration (10^-6 m/s^2) ok deraadt@ reyk@
2012-08-17clarify that -w is used for raw output only (removes the 'not sure' XXXOkan Demirmen
comment). ok sthen@, jmc@
2012-01-30- allow the default to only show all non-listneing scokets, which matchesOkan Demirmen
the manpage and what netstat(1) does, sans the aflag (-a). - allow one to use 'a' to toggle the above (include listening or not). - implement [r]eset to reset all toggles to default (all/tcp/udp). - document a/n/r/t/u toggles. ok henning@ sthen@ jmc@
2011-11-29minor whitespace fixDavid Gwynne
2011-11-29use a u_int64_t for the state id in pfsync_state. this makes it consistentDavid Gwynne
with every other thing that stores the state id (including other pfsync messages). includes improvements to the systat code to consider the creatorid as well as the state id in its cache to avoid collisions between states created on different hosts. tested by me in production and on amd64 talking to sparc64. ok henning@
2011-10-13Teach some userland tools about NAT64. I think this is mostly from mikeb@Claudio Jeker
OK mcbride@
2011-09-19clean up buffer cache statistics somewhat toBob Beck
remove some now useless statistics, and add some relevant ones regarding kva usage in the cache. make systat io and show bcstats in ddb both show these counters. ok deraadt@ krw@
2011-09-16reorder SENSOR_* in switch() and add missing cases.Yojiro Uo
ok deraadt@
2011-09-16apply following changes to sensor framework:Yojiro Uo
- change accuracy of SENSOR_FREQ from Hz to muHz - add SENSOR_VOLTS_AC entry to userland programs ok deraadt@
2011-07-06add a couple of fields needed for buffer flipping, and change systat toBob Beck
show useful info in systat io instead of goo
2011-04-29Add currently undocumented keyboard options available on ifstat view.lum
ok jmc@
2011-04-10Switch back from KERN_PROC2/kinfo_proc2 to KERN_PROC/kinfo_proc nowPhilip Guenthe
that we've got name we want for the API we want "ZAP!" deraadt@
2011-04-05the tree builds better when you don't use PF_FASTROUTEStuart Henderson
ok henning@ mikeb@
2011-04-05Add support to display numbers with thousands separatorsMarco Pfatschbacher
and to switch the ifstat view to Bits/s. This allows us to see live network throughput in units like MBit/s, which is more practical. OK sthen@, manpage OK jmc@, "put it in" deraadt@
2011-03-31Make the top line of systat stop updating, along with the rest of the datalum
when 'p' is pressed. ok nicm@
2011-03-02- use a common FIELD_ADDR macro, instead of rolling 78 identical copies.Jasper Lievisse Adriaanse
ok canacar@
2011-02-06Remove duplicated prototypes.lum
ok miod@
2011-01-18Remove one of the three occurances of "delay is 5 seconds"lum
ok jmc@
2011-01-17Adjust IPKTS and OPKTS description to fit actual behaviour.lum
ok jmc@
2011-01-13Making the numbers Right aligned (instead of left as it is) as theJasper Lievisse Adriaanse
numbers increase, it may be difficult to keep track of left aligned stuff. ok sthen@
2011-01-13non interactive -> non-interactivelum
ok jmc@
2010-11-19Make KERN_CPTIME return an avarage number of ticks across all CPUsMike Belopuhov
tedu agreed with an idea, tested by Luis Useche and me; ok deraadt
2010-11-05Print relativ number of livelocks that happend between two systatClaudio Jeker
updates instead of showing absolut figures. Makes it easier to estimate the "livelockyness" of a system. OK dlg@
2010-11-02expose the kernels network livelock counterDavid Gwynne
2010-10-28cleanup ;;Theo de Raadt
2010-09-23tweak the mclgeti algorithm to behave better under load.David Gwynne
instead of letting hardware rings grow on every interrupt, restrict it so it can only grow once per softclock tick. we can only punish the rings on softclock ticks, so it make sense to only grow on softclock tick boundaries too. the rings are now punished after >1 lost softclock tick rather than >2. mclgeti is now more aggressive at detecting livelock. the rings get punished by an 8th, rather than by half. we now allow the rings to be punished again even if the system is already considered in livelock. without this diff a livelocked system will have its rx ring sizes scale up and down very rapidly, while holding the rings low for too long. this affected throughput significantly. discussed and tested heavily at j2k10. there are still some games with softnet we can play, but this is a good first step. "put it in" and ok deraadt@ ok claudio@ krw@ henning@ mcbride@ if we find out that it sucks we can pull it out again later. till then we'll run with it and see how it goes.
2010-08-01don't rely on mbuf.h to pull in pool.h here eitherBret Lambert
ok miod@
2010-08-01fix use of uninitialized variable.Charles Longeau
reported by gcc. ok canacar@
2010-07-22Let systat -N states resolve network addressesgiovanni
help and ok sthen@ lum@ ok canacar@
2010-07-21Remove reference to non-existent behaviour.lum
ok canacar@
2010-07-19Add prototype and remove unnecessary includes.lum
ok canacar@
2010-07-19Remove unused function.lum
ok canacar@
2010-07-16Move the description of load averages/top line to a better place.lum
Suggestions and ok canacar@
2010-07-16Make the terminal checking capability of systat better.lum
Checks taken from top(1) screen.c/init_termcap() ok canacar@ sthen@ nicm@
2010-07-05Add prototype and remove unused variable.lum
ok canacar@
2010-07-02Allow systat to print date and time when in rawmode.lum
ok canacar@ millert@
2010-04-21scale angle by 1000000 to permit min.sec accuracyTheo de Raadt
2010-04-21Add the "angle" sensor, measured in degrees; from Luis PintoTheo de Raadt
2010-04-20Get rid of MAXSENSORDEVICES. Gaps in sensordev lists are now handledTheo de Raadt
by returning ENXIO instead of ENOENT, to essentially indicate hotplug sensor that has gone away. Accessing beyond the end of the sensordev list still returns ENOENT, so that you can see there are no further devices. ok kettenis oga