Reputation
5,739
Top tag
Next privilege 10,000 Rep.
Access moderator tools
Badges
12 29
Newest
 Curious
Impact
~399k people reached

Feb
3
comment NTP using GPS and PPS as clock, PPS is marked as falseticker
I can understand why some devices are rejected, but what I thought the PPS driver did was further optimize the time, once sync'd. That is, the rough time is set by a preferred source, but once set, the PPS will mark the actual second change, and from that point onward PPS will be used. This seems not to be the case.
Jan
31
comment Sender Policy Framework Qualifiers
Can you state the question you are asking more clearly?
Jan
31
revised NTP using GPS and PPS as clock, PPS is marked as falseticker
Add ppstest output
Jan
31
comment NTP using GPS and PPS as clock, PPS is marked as falseticker
Stratum 0 is a directly connected time source. In this case, a PPS clock can act as a time source, given that the approximate second is transmitted using other means. In this case, I'm using GPS and/or other network servers. Once those are sync'd, PPS would provide a stratum 0 source, and is correct.
Jan
31
asked NTP using GPS and PPS as clock, PPS is marked as falseticker
Jan
31
accepted Poor performance with Linux software raid-10
Jan
28
accepted linux software raid10, identical machines, wildly different results
Jan
28
revised linux software raid10, identical machines, wildly different results
added 127 characters in body
Jan
28
comment Poor performance with Linux software raid-10
It was power related. If you make your comments into the form of an answer, I'll accept it. Once we disabled power savings at the BIOS level, we suddenly get our stellar performance back even with the buffer cache in the path.
Jan
28
awarded  Curious
Jan
27
comment Poor performance with Linux software raid-10
I was not aware of PowerTOP. Running it, it shows: 0% C0 polling, 13.1% C1-HSW, 6.1% C3-HSW, and 76.8% C6-HSW. Please do note though that the really rotten performance only occurs when using the buffer cache. When using direct i/o, it is really quite reasonable.
Jan
27
revised Poor performance with Linux software raid-10
added 374 characters in body
Jan
27
comment Poor performance with Linux software raid-10
I'm adding additional data points to the OP.
Jan
27
awarded  Talkative
Jan
27
comment Why does a raid 10 device need to be initialized?
One thing to consider is that usually during initialization, the raid system will ALWAYS read disk A and copy it to disk B. Why? Since you can use the disk while it is initializing, you may have written data at block 100,000. Once the raid init gets to that block, both A and B are already identical, so nothing happens. If It were instead zeroing blocks, it would wipe good data. Thus, once again, I see two reasons to ensure the blocks are identical: "it's always been done" and "so you can run a check later" -- I also question that check's usefulness. Reading is good, comparing? not sure.
Jan
27
comment Why does a raid 10 device need to be initialized?
In my case, as the original poster, I don't care what file system. I know of no file systems that will read sectors that have never been written to, thus any indeterminate state of those unwritten sectors does not matter.
Jan
27
reviewed Approve AWS MongoDB 3.0.6 replicaset - Primary server becomes unresponsive to connections and read timeouts
Jan
27
reviewed Approve Nginx rewrite module (Catch-all)
Jan
27
reviewed Approve Does Intel VT-x (or AMD Pacifica/AMD V) Support Real Virtualisation?
Jan
27
asked Why does a raid 10 device need to be initialized?