search for: mpstat

...rec main () = message (f_"Inspecting the overlay"); let inspect = inspect_source g root_choice in - (* The guest free disk space check and the target free space - * estimation both require statvfs information from mountpoints, so - * get that information first. - *) - let mpstats = List.map ( - fun (dev, path) -> - let statvfs = g#statvfs path in - let vfs = g#vfs_type dev in - { mp_dev = dev; mp_path = path; mp_statvfs = statvfs; mp_vfs = vfs } - ) (g#mountpoints ()) in - - if verbose () then ( - (* This is useful for debugging speed / fstrim iss...

I''m looking for a suggestion on a good way to hunt down the source of high context switching and mutex contentions... Is dtrace the way to go now, or should I stick with something like lockstat? Russ This is a 5 second interval for mpstat: CPU minf mjf xcal intr ithr csw icsw migr smtx srw syscl usr sys wt idl 16 0 0 1115 1241 206 9095 912 2420 7393 0 12105 68 25 0 7 17 1 0 1054 1049 86 9290 921 2420 7355 0 12123 67 25 0 8 18 0 0 1004 984 6 9115 902 2551 7336 0 11843 66...

HI, T5220, S10U4 + patches mdb -k > ::memstat While above is working (takes some time, ideally ::memstat -n 4 to use 4 threads could be useful) mpstat 1 shows: CPU minf mjf xcal intr ithr csw icsw migr smtx srw syscl usr sys wt idl 48 0 0 1922112 9 0 0 8 0 0 0 15254 6 94 0 0 So about 2mln xcalls per second. Let''s check with dtrace: dtrace -n sysinfo:::xcalls''{@=count();}'' -n...

...is where /boot is in that case --- v2v/v2v.ml | 55 ++++++++++++++++++++++++++++--------------------------- 1 file changed, 28 insertions(+), 27 deletions(-) diff --git a/v2v/v2v.ml b/v2v/v2v.ml index b4c41e188..24b38458f 100644 --- a/v2v/v2v.ml +++ b/v2v/v2v.ml @@ -415,34 +415,35 @@ and print_mpstat chan { mp_dev = dev; mp_path = path; *) and check_guest_free_space mpstats = message (f_"Checking for sufficient free disk space in the guest"); + + (* Check whether /boot has its own mount point. *) + let has_boot = List.exists (fun { mp_path } -> mp_path = "/boot")...

In crossbow, each mac_srs has a kernel thread called "mac_rx_srs_poll_ring" to poll the hardware and crossbow will wakeup this thread to poll packets from the hardware automatically. Does crossbow provide any method to disable the polling mechanism, for example disabling the this kernel thread? Thanks Zhihui -------------- next part -------------- An HTML attachment was scrubbed... URL:

...s required to +have at least 100 available inodes. + =head3 Minimum free space check in the host You must have sufficient free space in the host directory used to diff --git a/v2v/v2v.ml b/v2v/v2v.ml index f9d81460..dc1dedd7 100644 --- a/v2v/v2v.ml +++ b/v2v/v2v.ml @@ -375,6 +375,8 @@ and print_mpstat chan { mp_dev = dev; mp_path = path; (* Conversion can fail if there is no space on the guest filesystems * (RHBZ#1139543). To avoid this situation, check there is some * headroom. Mainly we care about the root filesystem. + * + * Also make sure filesystems have available inodes. (RHBZ#17645...

...uire at least 100 available inodes on filesystems that can provide inode counts. --- v2v/v2v.ml | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/v2v/v2v.ml b/v2v/v2v.ml index 03590c9e..b5b2da08 100644 --- a/v2v/v2v.ml +++ b/v2v/v2v.ml @@ -375,6 +375,8 @@ and print_mpstat chan { mp_dev = dev; mp_path = path; (* Conversion can fail if there is no space on the guest filesystems * (RHBZ#1139543). To avoid this situation, check there is some * headroom. Mainly we care about the root filesystem. + * + * Also make sure filesystems have available inodes. (RHBZ#17645...

....com> --- v2v/v2v.ml | 59 ++++++++++++++++++++++++++++++----------------------------- 1 file changed, 30 insertions(+), 29 deletions(-) diff --git a/v2v/v2v.ml b/v2v/v2v.ml index a2b6f52..633c29f 100644 --- a/v2v/v2v.ml +++ b/v2v/v2v.ml @@ -84,35 +84,8 @@ let rec main () = check_free_space mpstats; check_target_free_space mpstats source targets output; - (* Conversion. *) - let guestcaps = - (match inspect.i_product_name with - | "unknown" -> - message (f_"Converting the guest to run on KVM") - | prod -> - message (f_"Converting %s to...

...e Joyent arcstat enhancements with some of my own and am now to the point where it is time to broaden the requirements gathering. The result is to be merged into the illumos tree. arcstat is a perl script to show the value of ARC kstats as they change over time. This is similar to the ideas behind mpstat, iostat, vmstat, and friends. The current usage is: Usage: arcstat [-hvx] [-f fields] [-o file] [interval [count]] Field definitions are as follows: mtxmis : mutex_miss per second arcsz : ARC size mrug : MRU ghost list hits per second l2hit% : L...

This series is a second attempt to add a mode of virt-v2v operation where it leaves the config and disk image conversion, rollback on errors, registering with the destination hypervisor, etc. to a third-party toolset, and performs only tuning of the guest OS to run in the KVM-based hypervisor. The first 14 patches are just refactoring and rearrangement of the code, factoring the implementation

RHV was connecting to the VMware source in order to find out the virtual disk size of the source disk(s), duplicating logic that virt-v2v already provides. This makes that information available using a new ‘virt-v2v --print-target option’. Note in order to get all the information, this has to actually perform the conversion step, so it takes 30 seconds or so before we reach the point where the

...g overlays + else populate_disks g source.s_disks; g#launch (); (* Inspection - this also mounts up the filesystems. *) - message (f_"Inspecting the overlay"); + message (f_"Inspecting the %s") guestfs_kind; let inspect = inspect_source g root_choice in let mpstats = get_mpstats g in check_free_space mpstats; - check_target_free_space mpstats source targets output; + if not in_place then + check_target_free_space mpstats source targets output; - let keep_serial_console = output#keep_serial_console in + let keep_serial_console = + if not in_pla...

...irtuozzo.com> --- v2v/v2v.ml | 59 ++++++++++++++++++++++++++++++----------------------------- 1 file changed, 30 insertions(+), 29 deletions(-) diff --git a/v2v/v2v.ml b/v2v/v2v.ml index 53456ea..c6a567a 100644 --- a/v2v/v2v.ml +++ b/v2v/v2v.ml @@ -371,6 +371,34 @@ let check_target_free_space mpstats source targets output = output#check_target_free_space source targets +let do_convert g inspect source keep_serial_console = + (* Conversion. *) + (match inspect.i_product_name with + | "unknown" -> + message (f_"Converting the guest to run on KVM") + | prod -&...

...t; v2v/v2v.ml | 55 ++++++++++++++++++++++++++++--------------------------- > 1 file changed, 28 insertions(+), 27 deletions(-) > > diff --git a/v2v/v2v.ml b/v2v/v2v.ml > index b4c41e188..24b38458f 100644 > --- a/v2v/v2v.ml > +++ b/v2v/v2v.ml > @@ -415,34 +415,35 @@ and print_mpstat chan { mp_dev = dev; mp_path = path; > *) > and check_guest_free_space mpstats = > message (f_"Checking for sufficient free disk space in the guest"); > + > + (* Check whether /boot has its own mount point. *) > + let has_boot = List.exists (fun { mp_path } ->...

This adds --print-target. In addition, v2 provides a machine-readable version (in JSON format). All of the record -> JSON boilerplate in this patch could be eliminated if we moved the baseline to OCaml 4.02. Rich.

...ys, do_copy, network_map, no_trim, + debug_overlays, do_copy, in_place, network_map, no_trim, output_alloc, output_format, output_name, print_source, root_choice diff --git a/v2v/v2v.ml b/v2v/v2v.ml index 23bd708..26a9b64 100644 --- a/v2v/v2v.ml +++ b/v2v/v2v.ml @@ -41,12 +41,16 @@ let print_mpstat chan { mp_dev = dev; mp_path = path; fprintf chan " bsize=%Ld blocks=%Ld bfree=%Ld bavail=%Ld\n" s.G.bsize s.G.blocks s.G.bfree s.G.bavail +type conversion_mode = + | Copying of overlay list * target list + | In_place + let () = Random.self_init () let rec main () =...

...open_guestfs () in if not in_place then populate_overlays g overlays else populate_disks g source.s_disks; g#launch (); (* Inspection - this also mounts up the filesystems. *) message (f_"Inspecting the %s") guestfs_kind; let inspect = inspect_source g root_choice in let mpstats = get_mpstats g in check_free_space mpstats; if not in_place then check_target_free_space mpstats source targets output; let keep_serial_console = if not in_place then output#keep_serial_console else true in let guestcaps = do_convert g inspect source keep_serial_console in...

We started seeing odd behaviour with clients somehow hammering our ZFS-based NFS server. Nothing is obvious from mpstat/iostat/etc. I''ve seen mention before of NFSv3 client dtrace scripts, and I was wondering if there ever was one for the server end, displaying top talkers, writes/reads, or locations of such to nail down abusive clients short of using snoop/tcpdump to nail down via decoding NFS who is doing...

...e ("my_application.R") command, and measured the times the application ran. The times I measured for each applications in #2 was slower than the times I measured for the application in #1. The application was run in a 4-core machine running Linux. When the application ran, i used "mpstat" to look at the CPU usage. For #1, the CPU usage was 25%, and for #2, the CPU usage was 50%. No other process was running in the machine. My question is, why would #2 be slower than #1? Thanks, Peter [[alternative HTML version deleted]]

...e ("my_application.R") command, and measured the times the application ran. The times I measured for each applications in #2 was slower than the times I measured for the application in #1. The application was run in a 4-core machine running Linux. When the application ran, i used "mpstat" to look at the CPU usage. For #1, the CPU usage was 25%, and for #2, the CPU usage was 50%. No other process was running in the machine. My question is, why would #2 be slower than #1? Thanks, Peter [[alternative HTML version deleted]]