lkml.org 
[lkml]   [2017]   [Oct]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
Subject[PATCH 0/5] x86/platform/UV: Update TSC support

[Patches merged against 4.14.0-rc4]

The UV BIOS goes to considerable effort to get the TSC synchronization
accurate across the entire system. Included in that are multiple chassis
that can have 32+ sockets. The architecture does support an external
high resolution clock to aid in maintaining this synchronization.

The resulting TSC accuracy set by the UV system BIOS is much better
than the generic kernel TSC ADJUST functions. This is important for
applications that read the TSC values directly for accessing data bases.

* Patch 1 disables an assumption made by the kernel tsc sync functions
that Socket 0 in the system should all have a TSC ADJUST value of
zero. This is not correct when the chassis are reset asynchronously
to each other so which TSC's should be zero is not predictable.

* Patch 2 prevents the kernel from attempting to fix the TSC if the
system BIOS has determined that the TSC is not stable. This prevents
a slew of useless warning messages.

* Patch 3 eliminates another avalanche of warning messages from older
BIOS that did not have the TSC ADJUST MSR (ex. >3000 msgs in a 32
socket Skylake system). It now notes this with a single warning
message and then moves on with fixing them.

* Patch 4 puts in a facility to disable ART if the art to tsc conversion
factor is not constant for all sockets.

* Patch 5 puts a new check in the UV system init to check this new BIOS
flag that displays the result of the TSC synchronization phase. Three
possible states are available, "sync is valid", "sync is unstable", or
TSC sync state is unavailable in this BIOS. In the later case, the
UV kernel init reverts to prior assumptions about TSC sync state.

--

\
 
 \ /
  Last update: 2017-10-12 18:34    [W:0.207 / U:4.360 seconds]
©2003-2017 Jasper Spaans. hosted at Digital OceanAdvertise on this site