我在我们的集群上运行一些R脚本遇到了问题。问题突然出现（所有脚本都正常工作，但有一天它们开始出现“caught segfault”错误）。我无法提供可重现的代码，因为即使是在我的电脑上也无法重现该错误-它只会在集群上发生。我还使用相同的代码处理两组数据-一组数据相当小且可以正常运行，另一组数据使用更大的数据框架（约1000万行），在某些点处崩溃。我仅使用CRAN存储库中的软件包； R和所有软件包应该是最新的。错误出现在完全不相关的操作中，请参见以下示例：
会话信息：
将变量写入NetCDF文件
我尝试按照这个问题的建议，卸载并重新安装包，但没有帮助。
会话信息：
R version 3.4.3 (2017-11-30)
Platform: x86_64-redhat-linux-gnu (64-bit)
Running under: CentOS Linux 7 (Core)
将变量写入NetCDF文件
# code snippet
library(ncdf4)
library(reshape2)
input <- read.csv("input_file.csv")
species <- "no2"
dimX <- ncdim_def(name="x", units = "m", vals = unique(input$x), unlim = FALSE)
dimY <- ncdim_def(name="y", units = "m", vals = unique(input$y), unlim = FALSE)
dimTime <- ncdim_def(name = "time", units = "hours", unlim = TRUE)
varOutput <- ncvar_def(name = species, units = "ug/m3",
dim = list(dimX, dimY, dimTime), missval = -9999, longname = species)
nc_file <- nc_create(filename = "outFile.nc", vars = list(varOutput), force_v4 = T)
ncvar_put(nc = nc_file, varid = species, vals = acast(input, x~y), start = c(1,1,1),
count = c(length(unique(input$x)), length(unique(input$y)), 1))
目前，我遇到了以下错误：
*** caught segfault ***
address 0x2b607cac2000, cause 'memory not mapped'
Traceback:
1: id(rev(ids), drop = FALSE)
2: cast(data, formula, fun.aggregate, ..., subset = subset, fill = fill, drop = drop, value.var = value.var)
3: acast(result, x ~ y)
4: ncvar_put(nc = nc_file, varid = species, vals = acast(result, x ~ y), start = c(1, 1), count = c(length(unique(result$x)), length(unique(result$y))))
An irrecoverable exception occurred. R is aborting now ...
/opt/sge/default/spool/node10/job_scripts/122270: line 3: 13959 Segmentation fault (core dumped)
并行计算的复杂代码
*** caught segfault ***
address 0x330d39b40, cause 'memory not mapped'
Traceback:
1: .Call(gstat_fit_variogram, as.integer(fit.method), as.integer(fit.sills), as.integer(fit.ranges))
2: fit.variogram(experimental_variogram, model = vgm(psill = psill, model = model, range = range, nugget = nugget, kappa = kappa), fit.ranges = c(fit_range), fit.sills = c(fit_nugget, fit_sill), debug.level = 0)
3: doTryCatch(return(expr), name, parentenv, handler)
4: tryCatchOne(expr, names, parentenv, handlers[[1L]])
5: tryCatchList(expr, classes, parentenv, handlers)
6: tryCatch(expr, error = function(e) { call <- conditionCall(e) if (!is.null(call)) { if (identical(call[[1L]], quote(doTryCatch))) call <- sys.call(-4L) dcall <- deparse(call)[1L] prefix <- paste("Error in", dcall, ": ") LONG <- 75L msg <- conditionMessage(e) sm <- strsplit(msg, "\n")[[1L]] w <- 14L + nchar(dcall, type = "w") + nchar(sm[1L], type = "w") if (is.na(w)) w <- 14L + nchar(dcall, type = "b") + nchar(sm[1L], type = "b") if (w > LONG) prefix <- paste0(prefix, "\n ") } else prefix <- "Error : " msg <- paste0(prefix, conditionMessage(e), "\n") .Internal(seterrmessage(msg[1L])) if (!silent && identical(getOption("show.error.messages"), TRUE)) { cat(msg, file = outFile) .Internal(printDeferredWarnings()) } invisible(structure(msg, class = "try-error", condition = e))})
7: try(fit.variogram(experimental_variogram, model = vgm(psill = psill, model = model, range = range, nugget = nugget, kappa = kappa), fit.ranges = c(fit_range), fit.sills = c(fit_nugget, fit_sill), debug.level = 0), TRUE)
8: getModel(initial_sill - initial_nugget, m, initial_range, k, initial_nugget, fit_range, fit_sill, fit_nugget, verbose = verbose)
9: autofitVariogram(lmResids ~ 1, obsDf, model = "Mat", kappa = c(0.05, seq(0.2, 2, 0.1), 3, 5, 10, 15), fix.values = c(NA, NA, NA), start_vals = c(NA, NA, NA), verbose = F)
10: main_us(obsDf[obsDf$class == "rural" | obsDf$class == "rural-nearcity" | obsDf$class == "rural-regional" | obsDf$class == "rural-remote", ], grd_alt, grd_pop, lm_us, fitvar_us, logTransform, plots, "RuralSt", period, preds)
11: doTryCatch(return(expr), name, parentenv, handler)
12: tryCatchOne(expr, names, parentenv, handlers[[1L]])
13: tryCatchList(expr, classes, parentenv, handlers)
14: tryCatch(main_us(obsDf[obsDf$class == "rural" | obsDf$class == "rural-nearcity" | obsDf$class == "rural-regional" | obsDf$class == "rural-remote", ], grd_alt, grd_pop, lm_us, fitvar_us, logTransform, plots, "RuralSt", period, preds), error = function(e) e)
15: eval(.doSnowGlobals$expr, envir = .doSnowGlobals$exportenv)
16: eval(.doSnowGlobals$expr, envir = .doSnowGlobals$exportenv)
17: doTryCatch(return(expr), name, parentenv, handler)
18: tryCatchOne(expr, names, parentenv, handlers[[1L]])
19: tryCatchList(expr, classes, parentenv, handlers)
20: tryCatch(eval(.doSnowGlobals$expr, envir = .doSnowGlobals$exportenv), error = function(e) e)
21: (function (args) { lapply(names(args), function(n) assign(n, args[[n]], pos = .doSnowGlobals$exportenv)) tryCatch(eval(.doSnowGlobals$expr, envir = .doSnowGlobals$exportenv), error = function(e) e)})(quote(list(timeIndex = 255L)))
22: do.call(msg$data$fun, msg$data$args, quote = TRUE)
23: doTryCatch(return(expr), name, parentenv, handler)
24: tryCatchOne(expr, names, parentenv, handlers[[1L]])
25: tryCatchList(expr, classes, parentenv, handlers)
26: tryCatch(do.call(msg$data$fun, msg$data$args, quote = TRUE), error = handler)
27: doTryCatch(return(expr), name, parentenv, handler)
28: tryCatchOne(expr, names, parentenv, handlers[[1L]])
29: tryCatchList(expr, classes, parentenv, handlers)
30: tryCatch({ msg <- recvData(master) if (msg$type == "DONE") { closeNode(master) break } else if (msg$type == "EXEC") { success <- TRUE handler <- function(e) { success <<- FALSE structure(conditionMessage(e), class = c("snow-try-error", "try-error")) } t1 <- proc.time() value <- tryCatch(do.call(msg$data$fun, msg$data$args, quote = TRUE), error = handler) t2 <- proc.time() value <- list(type = "VALUE", value = value, success = success, time = t2 - t1, tag = msg$data$tag) msg <- NULL sendData(master, value) value <- NULL }}, interrupt = function(e) NULL)
31: slaveLoop(makeSOCKmaster(master, port, timeout, useXDR))
32: parallel:::.slaveRSOCK()
An irrecoverable exception occurred. R is aborting now ...
这个问题可能是集群出了问题，而不是代码（或R语言）的问题吗？我不知道它是否相关，但自从一段时间以来，我们一直收到如下错误消息：
Message from syslogd@master1 at Mar 8 13:51:37 ...
kernel:[Hardware Error]: MC4 Error (node 1): DRAM ECC error detected on the NB.
Message from syslogd@master1 at Mar 8 13:51:37 ...
kernel:[Hardware Error]: Error Status: Corrected error, no action required.
Message from syslogd@master1 at Mar 8 13:51:37 ...
kernel:[Hardware Error]: CPU:4 (15:2:0) MC4_STATUS[-|CE|MiscV|-|AddrV|-|-|CECC]: 0x9c08400067080a13
Message from syslogd@master1 at Mar 8 13:51:37 ...
kernel:[Hardware Error]: MC4_ADDR: 0x000000048f32b490
Message from syslogd@master1 at Mar 8 13:51:37 ...
kernel:[Hardware Error]: cache level: L3/GEN, mem/io: MEM, mem-tx: RD, part-proc: RES (no timeout)
我尝试按照这个问题的建议，卸载并重新安装包，但没有帮助。