- Mar 22, 2018
-
-
Mike Hibler authored
At least I think the problem is that we are doing inadvertent TRIM operations on large (480GB) SSDs. For one, when creating an ext4 filesystem on such a blockstore, we specify "nodiscard". I toyed with the idea of turning off "issue_discards" for the lvremove operations when a blockstore is destroyed, but that led to old metadata being seen when the blockstore was re-created. That led to the last change, which was to force metadata zeroing when we do an lvcreate of a blockstore.
-
Mike Hibler authored
-
- Mar 19, 2018
-
-
Leigh B Stoller authored
-
- Mar 18, 2018
-
-
Leigh B Stoller authored
-
- Mar 14, 2018
-
-
Leigh B Stoller authored
something different in the Portal. Ditto when we fail on an empty testbed, although it appears we never get that anymore.
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
- Mar 13, 2018
-
-
Leigh B Stoller authored
-
- Mar 09, 2018
-
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
nodes (no switch in the middle). Handy for testing, not really something we expect people to do.
-
Leigh B Stoller authored
-
- Mar 08, 2018
-
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
expect that there will be timeout issues, the netscouts seem to hang up on a regular basis for 30 seconds or more.
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
never be executed,
-
- Mar 07, 2018
-
-
David Johnson authored
This is now our strategy for everything except a speed of 0 (which means autonegotiate); and a speed of 1 Gbps (which requires autoneg anyway). Not all cards allow ethtool to "fix" speeds; but some (still) require it. For instance, this commit when applied to an Intel X710 card that should be at 10Gbps has no affect; apparently ethtool cannot fix speeds for that card and/or driver. On the other hand, Mellanox 10/25Gbps cards sometimes require the speed to be manually set (i.e., if they are directly connected to each other via a layer1 switch). Even on those cards, it's not really setting it; it's just hinting to the autoneg process which speed you really want (and I'd guess that is true for all modern high-speed Ethernet chips). Anyway, we don't know when to force the speed set/suggest or not unless we track more data at the server side, so the current strategy is to always attempt to set/suggest the speed we want, and fallback to setting autoneg if we fail. Note that sometimes ethtool returns successfully even if settings fail (I'm looking at you, Intel X710), so this strategy is already sort of doomed to failure (but it hasn't made anything not work!). If it causes problems for any cards/drivers/speed combinations, we'll revisit this, obviously.
-
Robert Ricci authored
-
- Mar 06, 2018
-
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Jonathon Duerig authored
-
Jonathon Duerig authored
-
- Mar 02, 2018
-
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
to do a lockdown.
-
Leigh B Stoller authored
-
- Mar 01, 2018
-
-
Leigh B Stoller authored
finalize step. There are two graphs, one for Radios and one for Servers. This code is very Powder specific, please don't say we want it on any other portals!
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
-
Leigh B Stoller authored
profiles to list them in a big table.
-
Gary Wong authored
-
Leigh B Stoller authored
fancy later as needed.
-
- Feb 28, 2018
-
-
Mike Hibler authored
This is the flip-side of something the Mellanox module already handled: putting a port in trunk mode and having it inherit all existing VLANs. The only sure fire way to do this was to make sure, after creating a new VLAN, that every existing trunk port does not include the VLAN. If it does, we remove it.
-