frinnst | Romster: i have two of those | 01:03 |
---|---|---|
frinnst | they are ok | 01:03 |
Romster | rmull, add || true to the end of command | 01:24 |
Romster | jaeger, the only thing i have is keeping away from OCZ after hearing the warranty issues with them. | 01:31 |
Romster | http://www.scorptec.com.au/computer/45423-ssdsc2ct120a3k5 intel 330 | 01:33 |
Romster | http://www.pccasegear.com/index.php?main_page=product_info&cPath=210_902_909&products_id=19790 sandisk http://hexus.net/tech/reviews/storage/36529-sandisk-extreme-ssd-120gb/ | 01:34 |
Romster | and that samsung 830 Series http://www.scorptec.com.au/computer/45507-mz-7pc128b/ww which seems to have a xonsiderbly lower write speed. 320mb/s | 01:35 |
Romster | i prefer to pay a little more if need be for a solid drive that wont degrade over time | 01:36 |
Romster | hmm I also forgot Seagate owns Samsung now too. | 01:50 |
frinnst | Romster: then wait for the new dc-series | 01:53 |
frinnst | more expensive but probably worth it | 01:53 |
Romster | i can wait awhile longer. | 01:54 |
frinnst | http://www.anandtech.com/show/6433/intel-ssd-dc-s3700-200gb-review | 01:54 |
frinnst | i *REALLY* want one of those :D | 01:54 |
frinnst | more expensive, but if you stay around 100gb it should be a nice buy | 01:55 |
Romster | SATA Express... lovely so how long before sata is obsolete -_- | 01:57 |
Romster | 'd imagine it'll be backwards compatible | 01:58 |
Romster | i'd* | 01:58 |
Romster | including the shift from a B-tree indirection table to a direct mapped flat indirection table which helped enable this increase in performance consistency | 01:59 |
Romster | i thought b-trees were fast. | 01:59 |
Romster | 100GB $235 by there guide | 02:01 |
Romster | 100GB is more than enough for root | 02:01 |
Romster | damn if i'm reading that comparison chart correctly the write iops of that S3700 crap over the other models | 02:05 |
frinnst | then youo're not | 02:56 |
frinnst | :) | 02:56 |
frinnst | some models might have higher peaks in some places | 02:56 |
frinnst | but i doubt you'll find more even and predictable performance | 02:57 |
frinnst | my 330 is great here at work running on ext4 | 02:57 |
frinnst | at home with btrfs i get horrible lag sometimes | 02:57 |
frinnst | running lilo can take a couple of mins if there are other semi-intensive i/o tasks running | 02:58 |
Romster | O_O with lilo that seems ridiculous | 02:58 |
frinnst | dunno if its btrfs or something with the drive.. or if i've done something else wrong | 02:59 |
Romster | wonder how long i have to wait for the newer SSD than getting the 330. weeks months next quarter | 03:03 |
frinnst | seems a 335 model is available too | 03:28 |
frinnst | oh, only smaller nand | 03:29 |
prologic | alright we're in business | 03:32 |
prologic | nginx, haproxy or lighttpd for reverse proxying? :) | 03:32 |
Romster | visitors ugh | 04:40 |
Romster | when do i get time to myself | 04:40 |
Romster | reverse proxy for what purpose? | 04:41 |
prologic | web applications | 04:44 |
*** diverse has joined #crux-devel | 04:55 | |
*** horrorSt1uck has joined #crux-devel | 06:19 | |
*** horrorStruck has quit IRC | 06:21 | |
*** horrorSt1uck is now known as horrorStruck | 06:50 | |
*** horrorStruck has quit IRC | 07:01 | |
*** horrorStruck has joined #crux-devel | 07:30 | |
jaeger | Romster: sustained write speed isn't a useful metric, anyway. Look for the small random read/write speeds | 08:19 |
jaeger | The VAST majority of your daily workload is going to be tiny random reads/writes | 08:19 |
jaeger | frinnst: I'd guess that's btrfs, I've never seen that on any of my SSDs, even the shit OCZ ones | 08:20 |
frinnst | yeah must be something. though btrfs on spinning drives seem a lot faster | 08:33 |
frinnst | oh well :) | 08:33 |
jaeger | I just guessed that because I haven't used btrfs but I do have a few SSDs :) | 08:35 |
horrorStruck | no one mentioned crucial, i'm very happy with my m4 but it may be considered old by today's standards | 08:44 |
jaeger | I don't have personal experience with the M4 but they seem to be good from reviews and anecdotal evidence, though you have to be careful about your firmware version sometimes | 08:47 |
jaeger | It was the M4 that had the 5000 hour crash bug if I recall correctly | 08:47 |
diverse | jaeger: what do you use currently? | 08:47 |
jaeger | I've got 2 Samsung 830 256GB, 1 Intel X25-m 128GB, 1 Intel 520 240GB, 1 OCZ Vertex 2 120GB, and 1 OCZ Vertex 60GB | 08:48 |
diverse | did you raid0 them? | 08:50 |
jaeger | no, bad idea :) | 08:50 |
jaeger | It's only very recently that any RAID configuration of SSDs has supported TRIM and that only on a specific chipset | 08:50 |
diverse | ah | 08:51 |
jaeger | So if you put them in RAID on some other configuration TRIM isn't happening and your performance degrades badly over time | 08:51 |
jaeger | You can combat it to a small extent with SSDs using controllers that have aggressive garbage collection but it's still far from ideal | 08:52 |
Romster | also note that kernel now calls TRIM discard | 08:53 |
jaeger | That isn't new, actually | 08:53 |
diverse | TRIM seems to be a mandatory feature | 08:54 |
jaeger | If you want good performance, it is | 08:55 |
jaeger | The drive works without it, certainly, just not nearly as well | 08:55 |
diverse | so do you use the SSDs to store your OS core and configurations while putting your personal data on HDD or is everything you store on SSD? | 08:57 |
jaeger | Depends on the machine. On my main desktop I use it for the OS and a couple games while large data is stored on platters. My laptop only has one drive so everything is on the SSD | 08:59 |
jaeger | One of them is used as a vsphere cache | 09:01 |
diverse | oh, what is vsphere? | 09:01 |
jaeger | vmware's virtualization stuff | 09:02 |
diverse | so you improve the emulation drastically? | 09:02 |
jaeger | The difference isn't particularly noticeable for my small installation, it would likely be far better in a big deployment | 09:03 |
*** sepen has joined #crux-devel | 09:05 | |
sepen | jue: ping | 09:05 |
diverse | jaeger: thanks for the insight. I might end up partitioning / for SSD and /home for HDD on my next installation. | 09:07 |
jaeger | np | 09:07 |
sepen | who created 2.8 branch on contrib.git? | 09:07 |
jaeger | for some reason he really doesn't want to give specific information | 09:11 |
sepen | last 3 commits on contrib.git/2.7 are not in 2.8 and I cannot merge these commits http://46397d29d58e2a11.paste.se/ it said that branch is uptodate | 09:11 |
sepen | yeah jaeger | 09:11 |
jaeger | sepen: if they can't be merged, cherry-pick them? | 09:12 |
sepen | jue told me about subversion-perl, but I remember that I updated it to 2.7 | 09:12 |
sepen | yep, but just I wanted to be sure that the branch 2.8 was created fine | 09:12 |
sepen | I'll do that, thanks | 09:12 |
jaeger | ok :) | 09:13 |
jaeger | jue, frinnst: this conversation in #crux has me thinking we should make a wiki page or web page similar to FreeBSD's UPDATING doc | 09:20 |
jaeger | when things change like udev requiring new kernel config options, in addition to whatever ML posts we normally make, a handy reference of those things on the website would be nice | 09:21 |
*** sepen has quit IRC | 10:38 | |
*** mike_k has joined #crux-devel | 12:50 | |
*** mike_k has quit IRC | 13:30 | |
*** joe9 has joined #crux-devel | 16:53 | |
horrorStruck | jue: wouldn't it be better to have ldns a separate port instead of building it in unbound? | 19:05 |
horrorStruck | jue: https://github.com/destructure/for-jue | 20:02 |
*** __mavrick61 has quit IRC | 21:37 | |
*** joe9 has quit IRC | 21:37 | |
*** _mavrick61 has joined #crux-devel | 21:38 |
Generated by irclog2html.py 2.11.0 by Marius Gedminas - find it at mg.pov.lt!